aboutsummaryrefslogtreecommitdiffstats
path: root/mm
diff options
context:
space:
mode:
Diffstat (limited to 'mm')
-rw-r--r--mm/bootmem.c2
-rw-r--r--mm/fadvise.c34
-rw-r--r--mm/fremap.c3
-rw-r--r--mm/frontswap.c34
-rw-r--r--mm/huge_memory.c1
-rw-r--r--mm/kmemleak.c6
-rw-r--r--mm/memcontrol.c7
-rw-r--r--mm/memory_hotplug.c16
-rw-r--r--mm/mmap.c3
-rw-r--r--mm/nommu.c6
-rw-r--r--mm/page_alloc.c2
-rw-r--r--mm/percpu.c2
-rw-r--r--mm/readahead.c14
-rw-r--r--mm/shmem.c171
-rw-r--r--mm/slab.c356
-rw-r--r--mm/slab.h19
-rw-r--r--mm/slab_common.c159
-rw-r--r--mm/slob.c91
-rw-r--r--mm/slub.c223
-rw-r--r--mm/util.c35
-rw-r--r--mm/vmscan.c1
-rw-r--r--mm/vmstat.c2
22 files changed, 554 insertions, 633 deletions
diff --git a/mm/bootmem.c b/mm/bootmem.c
index bcb63ac48cc5..f468185b3b28 100644
--- a/mm/bootmem.c
+++ b/mm/bootmem.c
@@ -419,7 +419,7 @@ int __init reserve_bootmem_node(pg_data_t *pgdat, unsigned long physaddr,
}
/**
- * reserve_bootmem - mark a page range as usable
+ * reserve_bootmem - mark a page range as reserved
* @addr: starting address of the range
* @size: size of the range in bytes
* @flags: reservation flags (see linux/bootmem.h)
diff --git a/mm/fadvise.c b/mm/fadvise.c
index 9b75a045dbf4..a47f0f50c89f 100644
--- a/mm/fadvise.c
+++ b/mm/fadvise.c
@@ -26,7 +26,7 @@
*/
SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
{
- struct file *file = fget(fd);
+ struct fd f = fdget(fd);
struct address_space *mapping;
struct backing_dev_info *bdi;
loff_t endbyte; /* inclusive */
@@ -35,15 +35,15 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
unsigned long nrpages;
int ret = 0;
- if (!file)
+ if (!f.file)
return -EBADF;
- if (S_ISFIFO(file->f_path.dentry->d_inode->i_mode)) {
+ if (S_ISFIFO(f.file->f_path.dentry->d_inode->i_mode)) {
ret = -ESPIPE;
goto out;
}
- mapping = file->f_mapping;
+ mapping = f.file->f_mapping;
if (!mapping || len < 0) {
ret = -EINVAL;
goto out;
@@ -76,21 +76,21 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
switch (advice) {
case POSIX_FADV_NORMAL:
- file->f_ra.ra_pages = bdi->ra_pages;
- spin_lock(&file->f_lock);
- file->f_mode &= ~FMODE_RANDOM;
- spin_unlock(&file->f_lock);
+ f.file->f_ra.ra_pages = bdi->ra_pages;
+ spin_lock(&f.file->f_lock);
+ f.file->f_mode &= ~FMODE_RANDOM;
+ spin_unlock(&f.file->f_lock);
break;
case POSIX_FADV_RANDOM:
- spin_lock(&file->f_lock);
- file->f_mode |= FMODE_RANDOM;
- spin_unlock(&file->f_lock);
+ spin_lock(&f.file->f_lock);
+ f.file->f_mode |= FMODE_RANDOM;
+ spin_unlock(&f.file->f_lock);
break;
case POSIX_FADV_SEQUENTIAL:
- file->f_ra.ra_pages = bdi->ra_pages * 2;
- spin_lock(&file->f_lock);
- file->f_mode &= ~FMODE_RANDOM;
- spin_unlock(&file->f_lock);
+ f.file->f_ra.ra_pages = bdi->ra_pages * 2;
+ spin_lock(&f.file->f_lock);
+ f.file->f_mode &= ~FMODE_RANDOM;
+ spin_unlock(&f.file->f_lock);
break;
case POSIX_FADV_WILLNEED:
/* First and last PARTIAL page! */
@@ -106,7 +106,7 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
* Ignore return value because fadvise() shall return
* success even if filesystem can't retrieve a hint,
*/
- force_page_cache_readahead(mapping, file, start_index,
+ force_page_cache_readahead(mapping, f.file, start_index,
nrpages);
break;
case POSIX_FADV_NOREUSE:
@@ -128,7 +128,7 @@ SYSCALL_DEFINE(fadvise64_64)(int fd, loff_t offset, loff_t len, int advice)
ret = -EINVAL;
}
out:
- fput(file);
+ fdput(f);
return ret;
}
#ifdef CONFIG_HAVE_SYSCALL_WRAPPERS
diff --git a/mm/fremap.c b/mm/fremap.c
index 9ed4fd432467..048659c0c03d 100644
--- a/mm/fremap.c
+++ b/mm/fremap.c
@@ -195,10 +195,9 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
*/
if (mapping_cap_account_dirty(mapping)) {
unsigned long addr;
- struct file *file = vma->vm_file;
+ struct file *file = get_file(vma->vm_file);
flags &= MAP_NONBLOCK;
- get_file(file);
addr = mmap_region(file, start, size,
flags, vma->vm_flags, pgoff);
fput(file);
diff --git a/mm/frontswap.c b/mm/frontswap.c
index 6b3e71a2cd48..2890e67d6026 100644
--- a/mm/frontswap.c
+++ b/mm/frontswap.c
@@ -44,6 +44,13 @@ EXPORT_SYMBOL(frontswap_enabled);
*/
static bool frontswap_writethrough_enabled __read_mostly;
+/*
+ * If enabled, the underlying tmem implementation is capable of doing
+ * exclusive gets, so frontswap_load, on a successful tmem_get must
+ * mark the page as no longer in frontswap AND mark it dirty.
+ */
+static bool frontswap_tmem_exclusive_gets_enabled __read_mostly;
+
#ifdef CONFIG_DEBUG_FS
/*
* Counters available via /sys/kernel/debug/frontswap (if debugfs is
@@ -97,6 +104,15 @@ void frontswap_writethrough(bool enable)
EXPORT_SYMBOL(frontswap_writethrough);
/*
+ * Enable/disable frontswap exclusive gets (see above).
+ */
+void frontswap_tmem_exclusive_gets(bool enable)
+{
+ frontswap_tmem_exclusive_gets_enabled = enable;
+}
+EXPORT_SYMBOL(frontswap_tmem_exclusive_gets);
+
+/*
* Called when a swap device is swapon'd.
*/
void __frontswap_init(unsigned type)
@@ -174,8 +190,13 @@ int __frontswap_load(struct page *page)
BUG_ON(sis == NULL);
if (frontswap_test(sis, offset))
ret = frontswap_ops.load(type, offset, page);
- if (ret == 0)
+ if (ret == 0) {
inc_frontswap_loads();
+ if (frontswap_tmem_exclusive_gets_enabled) {
+ SetPageDirty(page);
+ frontswap_clear(sis, offset);
+ }
+ }
return ret;
}
EXPORT_SYMBOL(__frontswap_load);
@@ -263,6 +284,11 @@ static int __frontswap_unuse_pages(unsigned long total, unsigned long *unused,
return ret;
}
+/*
+ * Used to check if it's necessory and feasible to unuse pages.
+ * Return 1 when nothing to do, 0 when need to shink pages,
+ * error code when there is an error.
+ */
static int __frontswap_shrink(unsigned long target_pages,
unsigned long *pages_to_unuse,
int *type)
@@ -275,7 +301,7 @@ static int __frontswap_shrink(unsigned long target_pages,
if (total_pages <= target_pages) {
/* Nothing to do */
*pages_to_unuse = 0;
- return 0;
+ return 1;
}
total_pages_to_unuse = total_pages - target_pages;
return __frontswap_unuse_pages(total_pages_to_unuse, pages_to_unuse, type);
@@ -292,7 +318,7 @@ static int __frontswap_shrink(unsigned long target_pages,
void frontswap_shrink(unsigned long target_pages)
{
unsigned long pages_to_unuse = 0;
- int type, ret;
+ int uninitialized_var(type), ret;
/*
* we don't want to hold swap_lock while doing a very
@@ -302,7 +328,7 @@ void frontswap_shrink(unsigned long target_pages)
spin_lock(&swap_lock);
ret = __frontswap_shrink(target_pages, &pages_to_unuse, &type);
spin_unlock(&swap_lock);
- if (ret == 0 && pages_to_unuse)
+ if (ret == 0)
try_to_unuse(type, true, pages_to_unuse);
return;
}
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 57c4b9309015..141dbb695097 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -1811,7 +1811,6 @@ static void __collapse_huge_page_copy(pte_t *pte, struct page *page,
src_page = pte_page(pteval);
copy_user_highpage(page, src_page, address, vma);
VM_BUG_ON(page_mapcount(src_page) != 1);
- VM_BUG_ON(page_count(src_page) != 2);
release_pte_page(src_page);
/*
* ptl mostly unnecessary, but preempt has to
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 45eb6217bf38..0de83b4541e9 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -1483,13 +1483,11 @@ static void *kmemleak_seq_next(struct seq_file *seq, void *v, loff_t *pos)
{
struct kmemleak_object *prev_obj = v;
struct kmemleak_object *next_obj = NULL;
- struct list_head *n = &prev_obj->object_list;
+ struct kmemleak_object *obj = prev_obj;
++(*pos);
- list_for_each_continue_rcu(n, &object_list) {
- struct kmemleak_object *obj =
- list_entry(n, struct kmemleak_object, object_list);
+ list_for_each_entry_continue_rcu(obj, &object_list, object_list) {
if (get_object(obj)) {
next_obj = obj;
break;
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 795e525afaba..a72f2ffdc3d0 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -4973,6 +4973,13 @@ mem_cgroup_create(struct cgroup *cont)
} else {
res_counter_init(&memcg->res, NULL);
res_counter_init(&memcg->memsw, NULL);
+ /*
+ * Deeper hierachy with use_hierarchy == false doesn't make
+ * much sense so let cgroup subsystem know about this
+ * unfortunate state in our controller.
+ */
+ if (parent && parent != root_mem_cgroup)
+ mem_cgroup_subsys.broken_hierarchy = true;
}
memcg->last_scanned_node = MAX_NUMNODES;
INIT_LIST_HEAD(&memcg->oom_notify);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 3ad25f9d1fc1..6a5b90d0cfd7 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -126,9 +126,6 @@ static void register_page_bootmem_info_section(unsigned long start_pfn)
struct mem_section *ms;
struct page *page, *memmap;
- if (!pfn_valid(start_pfn))
- return;
-
section_nr = pfn_to_section_nr(start_pfn);
ms = __nr_to_section(section_nr);
@@ -187,9 +184,16 @@ void register_page_bootmem_info_node(struct pglist_data *pgdat)
end_pfn = pfn + pgdat->node_spanned_pages;
/* register_section info */
- for (; pfn < end_pfn; pfn += PAGES_PER_SECTION)
- register_page_bootmem_info_section(pfn);
-
+ for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+ /*
+ * Some platforms can assign the same pfn to multiple nodes - on
+ * node0 as well as nodeN. To avoid registering a pfn against
+ * multiple nodes we check that this pfn does not already
+ * reside in some other node.
+ */
+ if (pfn_valid(pfn) && (pfn_to_nid(pfn) == node))
+ register_page_bootmem_info_section(pfn);
+ }
}
#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
diff --git a/mm/mmap.c b/mm/mmap.c
index ae18a48e7e4e..872441e81914 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1301,8 +1301,7 @@ munmap_back:
goto free_vma;
correct_wcount = 1;
}
- vma->vm_file = file;
- get_file(file);
+ vma->vm_file = get_file(file);
error = file->f_op->mmap(file, vma);
if (error)
goto unmap_and_free_vma;
diff --git a/mm/nommu.c b/mm/nommu.c
index d4b0c10872de..dee2ff89fd58 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -1282,10 +1282,8 @@ unsigned long do_mmap_pgoff(struct file *file,
vma->vm_pgoff = pgoff;
if (file) {
- region->vm_file = file;
- get_file(file);
- vma->vm_file = file;
- get_file(file);
+ region->vm_file = get_file(file);
+ vma->vm_file = get_file(file);
if (vm_flags & VM_EXECUTABLE) {
added_exe_file_vma(current->mm);
vma->vm_mm = current->mm;
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index c66fb875104a..c13ea7538891 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -584,7 +584,7 @@ static inline void __free_one_page(struct page *page,
combined_idx = buddy_idx & page_idx;
higher_page = page + (combined_idx - page_idx);
buddy_idx = __find_buddy_index(combined_idx, order + 1);
- higher_buddy = page + (buddy_idx - combined_idx);
+ higher_buddy = higher_page + (buddy_idx - combined_idx);
if (page_is_buddy(higher_page, higher_buddy, order + 1)) {
list_add_tail(&page->lru,
&zone->free_area[order].free_list[migratetype]);
diff --git a/mm/percpu.c b/mm/percpu.c
index bb4be7435ce3..ddc5efb9c5bb 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1370,7 +1370,7 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
#ifdef CONFIG_SMP
-const char *pcpu_fc_names[PCPU_FC_NR] __initdata = {
+const char * const pcpu_fc_names[PCPU_FC_NR] __initconst = {
[PCPU_FC_AUTO] = "auto",
[PCPU_FC_EMBED] = "embed",
[PCPU_FC_PAGE] = "page",
diff --git a/mm/readahead.c b/mm/readahead.c
index ea8f8fa21649..7963f2391236 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -579,19 +579,19 @@ do_readahead(struct address_space *mapping, struct file *filp,
SYSCALL_DEFINE(readahead)(int fd, loff_t offset, size_t count)
{
ssize_t ret;
- struct file *file;
+ struct fd f;
ret = -EBADF;
- file = fget(fd);
- if (file) {
- if (file->f_mode & FMODE_READ) {
- struct address_space *mapping = file->f_mapping;
+ f = fdget(fd);
+ if (f.file) {
+ if (f.file->f_mode & FMODE_READ) {
+ struct address_space *mapping = f.file->f_mapping;
pgoff_t start = offset >> PAGE_CACHE_SHIFT;
pgoff_t end = (offset + count - 1) >> PAGE_CACHE_SHIFT;
unsigned long len = end - start + 1;
- ret = do_readahead(mapping, file, start, len);
+ ret = do_readahead(mapping, f.file, start, len);
}
- fput(file);
+ fdput(f);
}
return ret;
}
diff --git a/mm/shmem.c b/mm/shmem.c
index d4e184e2a38e..d3752110c8c7 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -77,13 +77,6 @@ static struct vfsmount *shm_mnt;
/* Symlink up to this size is kmalloc'ed instead of using a swappable page */
#define SHORT_SYMLINK_LEN 128
-struct shmem_xattr {
- struct list_head list; /* anchored by shmem_inode_info->xattr_list */
- char *name; /* xattr name */
- size_t size;
- char value[0];
-};
-
/*
* shmem_fallocate and shmem_writepage communicate via inode->i_private
* (with i_mutex making sure that it has only one user at a time):
@@ -636,7 +629,6 @@ static int shmem_setattr(struct dentry *dentry, struct iattr *attr)
static void shmem_evict_inode(struct inode *inode)
{
struct shmem_inode_info *info = SHMEM_I(inode);
- struct shmem_xattr *xattr, *nxattr;
if (inode->i_mapping->a_ops == &shmem_aops) {
shmem_unacct_size(info->flags, inode->i_size);
@@ -650,10 +642,7 @@ static void shmem_evict_inode(struct inode *inode)
} else
kfree(info->symlink);
- list_for_each_entry_safe(xattr, nxattr, &info->xattr_list, list) {
- kfree(xattr->name);
- kfree(xattr);
- }
+ simple_xattrs_free(&info->xattrs);
BUG_ON(inode->i_blocks);
shmem_free_inode(inode->i_sb);
clear_inode(inode);
@@ -1377,7 +1366,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode
spin_lock_init(&info->lock);
info->flags = flags & VM_NORESERVE;
INIT_LIST_HEAD(&info->swaplist);
- INIT_LIST_HEAD(&info->xattr_list);
+ simple_xattrs_init(&info->xattrs);
cache_no_acl(inode);
switch (mode & S_IFMT) {
@@ -2060,28 +2049,6 @@ static void shmem_put_link(struct dentry *dentry, struct nameidata *nd, void *co
*/
/*
- * Allocate new xattr and copy in the value; but leave the name to callers.
- */
-static struct shmem_xattr *shmem_xattr_alloc(const void *value, size_t size)
-{
- struct shmem_xattr *new_xattr;
- size_t len;
-
- /* wrap around? */
- len = sizeof(*new_xattr) + size;
- if (len <= sizeof(*new_xattr))
- return NULL;
-
- new_xattr = kmalloc(len, GFP_KERNEL);
- if (!new_xattr)
- return NULL;
-
- new_xattr->size = size;
- memcpy(new_xattr->value, value, size);
- return new_xattr;
-}
-
-/*
* Callback for security_inode_init_security() for acquiring xattrs.
*/
static int shmem_initxattrs(struct inode *inode,
@@ -2090,11 +2057,11 @@ static int shmem_initxattrs(struct inode *inode,
{
struct shmem_inode_info *info = SHMEM_I(inode);
const struct xattr *xattr;
- struct shmem_xattr *new_xattr;
+ struct simple_xattr *new_xattr;
size_t len;
for (xattr = xattr_array; xattr->name != NULL; xattr++) {
- new_xattr = shmem_xattr_alloc(xattr->value, xattr->value_len);
+ new_xattr = simple_xattr_alloc(xattr->value, xattr->value_len);
if (!new_xattr)
return -ENOMEM;
@@ -2111,91 +2078,12 @@ static int shmem_initxattrs(struct inode *inode,
memcpy(new_xattr->name + XATTR_SECURITY_PREFIX_LEN,
xattr->name, len);
- spin_lock(&info->lock);
- list_add(&new_xattr->list, &info->xattr_list);
- spin_unlock(&info->lock);
+ simple_xattr_list_add(&info->xattrs, new_xattr);
}
return 0;
}
-static int shmem_xattr_get(struct dentry *dentry, const char *name,
- void *buffer, size_t size)
-{
- struct shmem_inode_info *info;
- struct shmem_xattr *xattr;
- int ret = -ENODATA;
-
- info = SHMEM_I(dentry->d_inode);
-
- spin_lock(&info->lock);
- list_for_each_entry(xattr, &info->xattr_list, list) {
- if (strcmp(name, xattr->name))
- continue;
-
- ret = xattr->size;
- if (buffer) {
- if (size < xattr->size)
- ret = -ERANGE;
- else
- memcpy(buffer, xattr->value, xattr->size);
- }
- break;
- }
- spin_unlock(&info->lock);
- return ret;
-}
-
-static int shmem_xattr_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
-{
- struct shmem_inode_info *info = SHMEM_I(inode);
- struct shmem_xattr *xattr;
- struct shmem_xattr *new_xattr = NULL;
- int err = 0;
-
- /* value == NULL means remove */
- if (value) {
- new_xattr = shmem_xattr_alloc(value, size);
- if (!new_xattr)
- return -ENOMEM;
-
- new_xattr->name = kstrdup(name, GFP_KERNEL);
- if (!new_xattr->name) {
- kfree(new_xattr);
- return -ENOMEM;
- }
- }
-
- spin_lock(&info->lock);
- list_for_each_entry(xattr, &info->xattr_list, list) {
- if (!strcmp(name, xattr->name)) {
- if (flags & XATTR_CREATE) {
- xattr = new_xattr;
- err = -EEXIST;
- } else if (new_xattr) {
- list_replace(&xattr->list, &new_xattr->list);
- } else {
- list_del(&xattr->list);
- }
- goto out;
- }
- }
- if (flags & XATTR_REPLACE) {
- xattr = new_xattr;
- err = -ENODATA;
- } else {
- list_add(&new_xattr->list, &info->xattr_list);
- xattr = NULL;
- }
-out:
- spin_unlock(&info->lock);
- if (xattr)
- kfree(xattr->name);
- kfree(xattr);
- return err;
-}
-
static const struct xattr_handler *shmem_xattr_handlers[] = {
#ifdef CONFIG_TMPFS_POSIX_ACL
&generic_acl_access_handler,
@@ -2226,6 +2114,7 @@ static int shmem_xattr_validate(const char *name)
static ssize_t shmem_getxattr(struct dentry *dentry, const char *name,
void *buffer, size_t size)
{
+ struct shmem_inode_info *info = SHMEM_I(dentry->d_inode);
int err;
/*
@@ -2240,12 +2129,13 @@ static ssize_t shmem_getxattr(struct dentry *dentry, const char *name,
if (err)
return err;
- return shmem_xattr_get(dentry, name, buffer, size);
+ return simple_xattr_get(&info->xattrs, name, buffer, size);
}
static int shmem_setxattr(struct dentry *dentry, const char *name,
const void *value, size_t size, int flags)
{
+ struct shmem_inode_info *info = SHMEM_I(dentry->d_inode);
int err;
/*
@@ -2260,15 +2150,12 @@ static int shmem_setxattr(struct dentry *dentry, const char *name,
if (err)
return err;
- if (size == 0)
- value = ""; /* empty EA, do not remove */
-
- return shmem_xattr_set(dentry->d_inode, name, value, size, flags);
-
+ return simple_xattr_set(&info->xattrs, name, value, size, flags);
}
static int shmem_removexattr(struct dentry *dentry, const char *name)
{
+ struct shmem_inode_info *info = SHMEM_I(dentry->d_inode);
int err;
/*
@@ -2283,45 +2170,13 @@ static int shmem_removexattr(struct dentry *dentry, const char *name)
if (err)
return err;
- return shmem_xattr_set(dentry->d_inode, name, NULL, 0, XATTR_REPLACE);
-}
-
-static bool xattr_is_trusted(const char *name)
-{
- return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN);
+ return simple_xattr_remove(&info->xattrs, name);
}
static ssize_t shmem_listxattr(struct dentry *dentry, char *buffer, size_t size)
{
- bool trusted = capable(CAP_SYS_ADMIN);
- struct shmem_xattr *xattr;
- struct shmem_inode_info *info;
- size_t used = 0;
-
- info = SHMEM_I(dentry->d_inode);
-
- spin_lock(&info->lock);
- list_for_each_entry(xattr, &info->xattr_list, list) {
- size_t len;
-
- /* skip "trusted." attributes for unprivileged callers */
- if (!trusted && xattr_is_trusted(xattr->name))
- continue;
-
- len = strlen(xattr->name) + 1;
- used += len;
- if (buffer) {
- if (size < used) {
- used = -ERANGE;
- break;
- }
- memcpy(buffer, xattr->name, len);
- buffer += len;
- }
- }
- spin_unlock(&info->lock);
-
- return used;
+ struct shmem_inode_info *info = SHMEM_I(dentry->d_inode);
+ return simple_xattr_list(&info->xattrs, buffer, size);
}
#endif /* CONFIG_TMPFS_XATTR */
diff --git a/mm/slab.c b/mm/slab.c
index 811af03a14ef..33d3363658df 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -498,14 +498,6 @@ static void **dbg_userword(struct kmem_cache *cachep, void *objp)
#endif
-#ifdef CONFIG_TRACING
-size_t slab_buffer_size(struct kmem_cache *cachep)
-{
- return cachep->size;
-}
-EXPORT_SYMBOL(slab_buffer_size);
-#endif
-
/*
* Do not go above this order unless 0 objects fit into the slab or
* overridden on the command line.
@@ -515,13 +507,6 @@ EXPORT_SYMBOL(slab_buffer_size);
static int slab_max_order = SLAB_MAX_ORDER_LO;
static bool slab_max_order_set __initdata;
-static inline struct kmem_cache *page_get_cache(struct page *page)
-{
- page = compound_head(page);
- BUG_ON(!PageSlab(page));
- return page->slab_cache;
-}
-
static inline struct kmem_cache *virt_to_cache(const void *obj)
{
struct page *page = virt_to_head_page(obj);
@@ -585,9 +570,9 @@ static struct arraycache_init initarray_generic =
{ {0, BOOT_CPUCACHE_ENTRIES, 1, 0} };
/* internal cache of cache description objs */
-static struct kmem_list3 *cache_cache_nodelists[MAX_NUMNODES];
-static struct kmem_cache cache_cache = {
- .nodelists = cache_cache_nodelists,
+static struct kmem_list3 *kmem_cache_nodelists[MAX_NUMNODES];
+static struct kmem_cache kmem_cache_boot = {
+ .nodelists = kmem_cache_nodelists,
.batchcount = 1,
.limit = BOOT_CPUCACHE_ENTRIES,
.shared = 1,
@@ -810,6 +795,7 @@ static void cache_estimate(unsigned long gfporder, size_t buffer_size,
*left_over = slab_size - nr_objs*buffer_size - mgmt_size;
}
+#if DEBUG
#define slab_error(cachep, msg) __slab_error(__func__, cachep, msg)
static void __slab_error(const char *function, struct kmem_cache *cachep,
@@ -818,7 +804,9 @@ static void __slab_error(const char *function, struct kmem_cache *cachep,
printk(KERN_ERR "slab error in %s(): cache `%s': %s\n",
function, cachep->name, msg);
dump_stack();
+ add_taint(TAINT_BAD_PAGE);
}
+#endif
/*
* By default on NUMA we use alien caches to stage the freeing of
@@ -900,7 +888,7 @@ static void __cpuinit start_cpu_timer(int cpu)
*/
if (keventd_up() && reap_work->work.func == NULL) {
init_reap_node(cpu);
- INIT_DELAYED_WORK_DEFERRABLE(reap_work, cache_reap);
+ INIT_DEFERRABLE_WORK(reap_work, cache_reap);
schedule_delayed_work_on(cpu, reap_work,
__round_jiffies_relative(HZ, cpu));
}
@@ -983,7 +971,7 @@ static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac,
}
/* The caller cannot use PFMEMALLOC objects, find another one */
- for (i = 1; i < ac->avail; i++) {
+ for (i = 0; i < ac->avail; i++) {
/* If a !PFMEMALLOC object is found, swap them */
if (!is_obj_pfmemalloc(ac->entry[i])) {
objp = ac->entry[i];
@@ -1000,7 +988,7 @@ static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac,
l3 = cachep->nodelists[numa_mem_id()];
if (!list_empty(&l3->slabs_free) && force_refill) {
struct slab *slabp = virt_to_slab(objp);
- ClearPageSlabPfmemalloc(virt_to_page(slabp->s_mem));
+ ClearPageSlabPfmemalloc(virt_to_head_page(slabp->s_mem));
clear_obj_pfmemalloc(&objp);
recheck_pfmemalloc_active(cachep, ac);
return objp;
@@ -1032,7 +1020,7 @@ static void *__ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac,
{
if (unlikely(pfmemalloc_active)) {
/* Some pfmemalloc slabs exist, check if this is one */
- struct page *page = virt_to_page(objp);
+ struct page *page = virt_to_head_page(objp);
if (PageSlabPfmemalloc(page))
set_obj_pfmemalloc(&objp);
}
@@ -1601,15 +1589,17 @@ void __init kmem_cache_init(void)
int order;
int node;
+ kmem_cache = &kmem_cache_boot;
+
if (num_possible_nodes() == 1)
use_alien_caches = 0;
for (i = 0; i < NUM_INIT_LISTS; i++) {
kmem_list3_init(&initkmem_list3[i]);
if (i < MAX_NUMNODES)
- cache_cache.nodelists[i] = NULL;
+ kmem_cache->nodelists[i] = NULL;
}
- set_up_list3s(&cache_cache, CACHE_CACHE);
+ set_up_list3s(kmem_cache, CACHE_CACHE);
/*
* Fragmentation resistance on low memory - only use bigger
@@ -1621,9 +1611,9 @@ void __init kmem_cache_init(void)
/* Bootstrap is tricky, because several objects are allocated
* from caches that do not exist yet:
- * 1) initialize the cache_cache cache: it contains the struct
- * kmem_cache structures of all caches, except cache_cache itself:
- * cache_cache is statically allocated.
+ * 1) initialize the kmem_cache cache: it contains the struct
+ * kmem_cache structures of all caches, except kmem_cache itself:
+ * kmem_cache is statically allocated.
* Initially an __init data area is used for the head array and the
* kmem_list3 structures, it's replaced with a kmalloc allocated
* array at the end of the bootstrap.
@@ -1632,43 +1622,43 @@ void __init kmem_cache_init(void)
* An __init data area is used for the head array.
* 3) Create the remaining kmalloc caches, with minimally sized
* head arrays.
- * 4) Replace the __init data head arrays for cache_cache and the first
+ * 4) Replace the __init data head arrays for kmem_cache and the first
* kmalloc cache with kmalloc allocated arrays.
- * 5) Replace the __init data for kmem_list3 for cache_cache and
+ * 5) Replace the __init data for kmem_list3 for kmem_cache and
* the other cache's with kmalloc allocated memory.
* 6) Resize the head arrays of the kmalloc caches to their final sizes.
*/
node = numa_mem_id();
- /* 1) create the cache_cache */
+ /* 1) create the kmem_cache */
INIT_LIST_HEAD(&slab_caches);
- list_add(&cache_cache.list, &slab_caches);
- cache_cache.colour_off = cache_line_size();
- cache_cache.array[smp_processor_id()] = &initarray_cache.cache;
- cache_cache.nodelists[node] = &initkmem_list3[CACHE_CACHE + node];
+ list_add(&kmem_cache->list, &slab_caches);
+ kmem_cache->colour_off = cache_line_size();
+ kmem_cache->array[smp_processor_id()] = &initarray_cache.cache;
+ kmem_cache->nodelists[node] = &initkmem_list3[CACHE_CACHE + node];
/*
* struct kmem_cache size depends on nr_node_ids & nr_cpu_ids
*/
- cache_cache.size = offsetof(struct kmem_cache, array[nr_cpu_ids]) +
+ kmem_cache->size = offsetof(struct kmem_cache, array[nr_cpu_ids]) +
nr_node_ids * sizeof(struct kmem_list3 *);
- cache_cache.object_size = cache_cache.size;
- cache_cache.size = ALIGN(cache_cache.size,
+ kmem_cache->object_size = kmem_cache->size;
+ kmem_cache->size = ALIGN(kmem_cache->object_size,
cache_line_size());
- cache_cache.reciprocal_buffer_size =
- reciprocal_value(cache_cache.size);
+ kmem_cache->reciprocal_buffer_size =
+ reciprocal_value(kmem_cache->size);
for (order = 0; order < MAX_ORDER; order++) {
- cache_estimate(order, cache_cache.size,
- cache_line_size(), 0, &left_over, &cache_cache.num);
- if (cache_cache.num)
+ cache_estimate(order, kmem_cache->size,
+ cache_line_size(), 0, &left_over, &kmem_cache->num);
+ if (kmem_cache->num)
break;
}
- BUG_ON(!cache_cache.num);
- cache_cache.gfporder = order;
- cache_cache.colour = left_over / cache_cache.colour_off;
- cache_cache.slab_size = ALIGN(cache_cache.num * sizeof(kmem_bufctl_t) +
+ BUG_ON(!kmem_cache->num);
+ kmem_cache->gfporder = order;
+ kmem_cache->colour = left_over / kmem_cache->colour_off;
+ kmem_cache->slab_size = ALIGN(kmem_cache->num * sizeof(kmem_bufctl_t) +
sizeof(struct slab), cache_line_size());
/* 2+3) create the kmalloc caches */
@@ -1681,19 +1671,22 @@ void __init kmem_cache_init(void)
* bug.
*/
- sizes[INDEX_AC].cs_cachep = __kmem_cache_create(names[INDEX_AC].name,
- sizes[INDEX_AC].cs_size,
- ARCH_KMALLOC_MINALIGN,
- ARCH_KMALLOC_FLAGS|SLAB_PANIC,
- NULL);
+ sizes[INDEX_AC].cs_cachep = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT);
+ sizes[INDEX_AC].cs_cachep->name = names[INDEX_AC].name;
+ sizes[INDEX_AC].cs_cachep->size = sizes[INDEX_AC].cs_size;
+ sizes[INDEX_AC].cs_cachep->object_size = sizes[INDEX_AC].cs_size;
+ sizes[INDEX_AC].cs_cachep->align = ARCH_KMALLOC_MINALIGN;
+ __kmem_cache_create(sizes[INDEX_AC].cs_cachep, ARCH_KMALLOC_FLAGS|SLAB_PANIC);
+ list_add(&sizes[INDEX_AC].cs_cachep->list, &slab_caches);
if (INDEX_AC != INDEX_L3) {
- sizes[INDEX_L3].cs_cachep =
- __kmem_cache_create(names[INDEX_L3].name,
- sizes[INDEX_L3].cs_size,
- ARCH_KMALLOC_MINALIGN,
- ARCH_KMALLOC_FLAGS|SLAB_PANIC,
- NULL);
+ sizes[INDEX_L3].cs_cachep = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT);
+ sizes[INDEX_L3].cs_cachep->name = names[INDEX_L3].name;
+ sizes[INDEX_L3].cs_cachep->size = sizes[INDEX_L3].cs_size;
+ sizes[INDEX_L3].cs_cachep->object_size = sizes[INDEX_L3].cs_size;
+ sizes[INDEX_L3].cs_cachep->align = ARCH_KMALLOC_MINALIGN;
+ __kmem_cache_create(sizes[INDEX_L3].cs_cachep, ARCH_KMALLOC_FLAGS|SLAB_PANIC);
+ list_add(&sizes[INDEX_L3].cs_cachep->list, &slab_caches);
}
slab_early_init = 0;
@@ -1707,20 +1700,23 @@ void __init kmem_cache_init(void)
* allow tighter packing of the smaller caches.
*/
if (!sizes->cs_cachep) {
- sizes->cs_cachep = __kmem_cache_create(names->name,
- sizes->cs_size,
- ARCH_KMALLOC_MINALIGN,
- ARCH_KMALLOC_FLAGS|SLAB_PANIC,
- NULL);
+ sizes->cs_cachep = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT);
+ sizes->cs_cachep->name = names->name;
+ sizes->cs_cachep->size = sizes->cs_size;
+ sizes->cs_cachep->object_size = sizes->cs_size;
+ sizes->cs_cachep->align = ARCH_KMALLOC_MINALIGN;
+ __kmem_cache_create(sizes->cs_cachep, ARCH_KMALLOC_FLAGS|SLAB_PANIC);
+ list_add(&sizes->cs_cachep->list, &slab_caches);
}
#ifdef CONFIG_ZONE_DMA
- sizes->cs_dmacachep = __kmem_cache_create(
- names->name_dma,
- sizes->cs_size,
- ARCH_KMALLOC_MINALIGN,
- ARCH_KMALLOC_FLAGS|SLAB_CACHE_DMA|
- SLAB_PANIC,
- NULL);
+ sizes->cs_dmacachep = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT);
+ sizes->cs_dmacachep->name = names->name_dma;
+ sizes->cs_dmacachep->size = sizes->cs_size;
+ sizes->cs_dmacachep->object_size = sizes->cs_size;
+ sizes->cs_dmacachep->align = ARCH_KMALLOC_MINALIGN;
+ __kmem_cache_create(sizes->cs_dmacachep,
+ ARCH_KMALLOC_FLAGS|SLAB_CACHE_DMA| SLAB_PANIC);
+ list_add(&sizes->cs_dmacachep->list, &slab_caches);
#endif
sizes++;
names++;
@@ -1731,15 +1727,15 @@ void __init kmem_cache_init(void)
ptr = kmalloc(sizeof(struct arraycache_init), GFP_NOWAIT);
- BUG_ON(cpu_cache_get(&cache_cache) != &initarray_cache.cache);
- memcpy(ptr, cpu_cache_get(&cache_cache),
+ BUG_ON(cpu_cache_get(kmem_cache) != &initarray_cache.cache);
+ memcpy(ptr, cpu_cache_get(kmem_cache),
sizeof(struct arraycache_init));
/*
* Do not assume that spinlocks can be initialized via memcpy:
*/
spin_lock_init(&ptr->lock);
- cache_cache.array[smp_processor_id()] = ptr;
+ kmem_cache->array[smp_processor_id()] = ptr;
ptr = kmalloc(sizeof(struct arraycache_init), GFP_NOWAIT);
@@ -1760,7 +1756,7 @@ void __init kmem_cache_init(void)
int nid;
for_each_online_node(nid) {
- init_list(&cache_cache, &initkmem_list3[CACHE_CACHE + nid], nid);
+ init_list(kmem_cache, &initkmem_list3[CACHE_CACHE + nid], nid);
init_list(malloc_sizes[INDEX_AC].cs_cachep,
&initkmem_list3[SIZE_AC + nid], nid);
@@ -1781,9 +1777,6 @@ void __init kmem_cache_init_late(void)
slab_state = UP;
- /* Annotate slab for lockdep -- annotate the malloc caches */
- init_lock_keys();
-
/* 6) resize the head arrays to their final sizes */
mutex_lock(&slab_mutex);
list_for_each_entry(cachep, &slab_caches, list)
@@ -1791,6 +1784,9 @@ void __init kmem_cache_init_late(void)
BUG();
mutex_unlock(&slab_mutex);
+ /* Annotate slab for lockdep -- annotate the malloc caches */
+ init_lock_keys();
+
/* Done! */
slab_state = FULL;
@@ -2209,27 +2205,6 @@ static void slab_destroy(struct kmem_cache *cachep, struct slab *slabp)
}
}
-static void __kmem_cache_destroy(struct kmem_cache *cachep)
-{
- int i;
- struct kmem_list3 *l3;
-
- for_each_online_cpu(i)
- kfree(cachep->array[i]);
-
- /* NUMA: free the list3 structures */
- for_each_online_node(i) {
- l3 = cachep->nodelists[i];
- if (l3) {
- kfree(l3->shared);
- free_alien_cache(l3->alien);
- kfree(l3);
- }
- }
- kmem_cache_free(&cache_cache, cachep);
-}
-
-
/**
* calculate_slab_order - calculate size (page order) of slabs
* @cachep: pointer to the cache that is being created
@@ -2366,9 +2341,6 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
* Cannot be called within a int, but can be interrupted.
* The @ctor is run when new pages are allocated by the cache.
*
- * @name must be valid until the cache is destroyed. This implies that
- * the module calling this has to destroy the cache before getting unloaded.
- *
* The flags are
*
* %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5)
@@ -2381,13 +2353,13 @@ static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
* cacheline. This can be beneficial if you're counting cycles as closely
* as davem.
*/
-struct kmem_cache *
-__kmem_cache_create (const char *name, size_t size, size_t align,
- unsigned long flags, void (*ctor)(void *))
+int
+__kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
{
size_t left_over, slab_size, ralign;
- struct kmem_cache *cachep = NULL;
gfp_t gfp;
+ int err;
+ size_t size = cachep->size;
#if DEBUG
#if FORCED_DEBUG
@@ -2459,8 +2431,8 @@ __kmem_cache_create (const char *name, size_t size, size_t align,
ralign = ARCH_SLAB_MINALIGN;
}
/* 3) caller mandated alignment */
- if (ralign < align) {
- ralign = align;
+ if (ralign < cachep->align) {
+ ralign = cachep->align;
}
/* disable debug if necessary */
if (ralign > __alignof__(unsigned long long))
@@ -2468,21 +2440,14 @@ __kmem_cache_create (const char *name, size_t size, size_t align,
/*
* 4) Store it.
*/
- align = ralign;
+ cachep->align = ralign;
if (slab_is_available())
gfp = GFP_KERNEL;
else
gfp = GFP_NOWAIT;
- /* Get cache's description obj. */
- cachep = kmem_cache_zalloc(&cache_cache, gfp);
- if (!cachep)
- return NULL;
-
cachep->nodelists = (struct kmem_list3 **)&cachep->array[nr_cpu_ids];
- cachep->object_size = size;
- cachep->align = align;
#if DEBUG
/*
@@ -2506,8 +2471,9 @@ __kmem_cache_create (const char *name, size_t size, size_t align,
}
#if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC)
if (size >= malloc_sizes[INDEX_L3 + 1].cs_size
- && cachep->object_size > cache_line_size() && ALIGN(size, align) < PAGE_SIZE) {
- cachep->obj_offset += PAGE_SIZE - ALIGN(size, align);
+ && cachep->object_size > cache_line_size()
+ && ALIGN(size, cachep->align) < PAGE_SIZE) {
+ cachep->obj_offset += PAGE_SIZE - ALIGN(size, cachep->align);
size = PAGE_SIZE;
}
#endif
@@ -2527,18 +2493,15 @@ __kmem_cache_create (const char *name, size_t size, size_t align,
*/
flags |= CFLGS_OFF_SLAB;
- size = ALIGN(size, align);
+ size = ALIGN(size, cachep->align);
- left_over = calculate_slab_order(cachep, size, align, flags);
+ left_over = calculate_slab_order(cachep, size, cachep->align, flags);
+
+ if (!cachep->num)
+ return -E2BIG;
- if (!cachep->num) {
- printk(KERN_ERR
- "kmem_cache_create: couldn't create cache %s.\n", name);
- kmem_cache_free(&cache_cache, cachep);
- return NULL;
- }
slab_size = ALIGN(cachep->num * sizeof(kmem_bufctl_t)
- + sizeof(struct slab), align);
+ + sizeof(struct slab), cachep->align);
/*
* If the slab has been placed off-slab, and we have enough space then
@@ -2566,8 +2529,8 @@ __kmem_cache_create (const char *name, size_t size, size_t align,
cachep->colour_off = cache_line_size();
/* Offset must be a multiple of the alignment. */
- if (cachep->colour_off < align)
- cachep->colour_off = align;
+ if (cachep->colour_off < cachep->align)
+ cachep->colour_off = cachep->align;
cachep->colour = left_over / cachep->colour_off;
cachep->slab_size = slab_size;
cachep->flags = flags;
@@ -2588,12 +2551,11 @@ __kmem_cache_create (const char *name, size_t size, size_t align,
*/
BUG_ON(ZERO_OR_NULL_PTR(cachep->slabp_cache));
}
- cachep->ctor = ctor;
- cachep->name = name;
- if (setup_cpu_cache(cachep, gfp)) {
- __kmem_cache_destroy(cachep);
- return NULL;
+ err = setup_cpu_cache(cachep, gfp);
+ if (err) {
+ __kmem_cache_shutdown(cachep);
+ return err;
}
if (flags & SLAB_DEBUG_OBJECTS) {
@@ -2606,9 +2568,7 @@ __kmem_cache_create (const char *name, size_t size, size_t align,
slab_set_debugobj_lock_classes(cachep);
}
- /* cache setup completed, link it into the list */
- list_add(&cachep->list, &slab_caches);
- return cachep;
+ return 0;
}
#if DEBUG
@@ -2767,49 +2727,29 @@ int kmem_cache_shrink(struct kmem_cache *cachep)
}
EXPORT_SYMBOL(kmem_cache_shrink);
-/**
- * kmem_cache_destroy - delete a cache
- * @cachep: the cache to destroy
- *
- * Remove a &struct kmem_cache object from the slab cache.
- *
- * It is expected this function will be called by a module when it is
- * unloaded. This will remove the cache completely, and avoid a duplicate
- * cache being allocated each time a module is loaded and unloaded, if the
- * module doesn't have persistent in-kernel storage across loads and unloads.
- *
- * The cache must be empty before calling this function.
- *
- * The caller must guarantee that no one will allocate memory from the cache
- * during the kmem_cache_destroy().
- */
-void kmem_cache_destroy(struct kmem_cache *cachep)
+int __kmem_cache_shutdown(struct kmem_cache *cachep)
{
- BUG_ON(!cachep || in_interrupt());
+ int i;
+ struct kmem_list3 *l3;
+ int rc = __cache_shrink(cachep);
- /* Find the cache in the chain of caches. */
- get_online_cpus();
- mutex_lock(&slab_mutex);
- /*
- * the chain is never empty, cache_cache is never destroyed
- */
- list_del(&cachep->list);
- if (__cache_shrink(cachep)) {
- slab_error(cachep, "Can't free all objects");
- list_add(&cachep->list, &slab_caches);
- mutex_unlock(&slab_mutex);
- put_online_cpus();
- return;
- }
+ if (rc)
+ return rc;
- if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU))
- rcu_barrier();
+ for_each_online_cpu(i)
+ kfree(cachep->array[i]);
- __kmem_cache_destroy(cachep);
- mutex_unlock(&slab_mutex);
- put_online_cpus();
+ /* NUMA: free the list3 structures */
+ for_each_online_node(i) {
+ l3 = cachep->nodelists[i];
+ if (l3) {
+ kfree(l3->shared);
+ free_alien_cache(l3->alien);
+ kfree(l3);
+ }
+ }
+ return 0;
}
-EXPORT_SYMBOL(kmem_cache_destroy);
/*
* Get the memory for a slab management obj.
@@ -3098,7 +3038,7 @@ static inline void verify_redzone_free(struct kmem_cache *cache, void *obj)
}
static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
- void *caller)
+ unsigned long caller)
{
struct page *page;
unsigned int objnr;
@@ -3118,7 +3058,7 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
*dbg_redzone2(cachep, objp) = RED_INACTIVE;
}
if (cachep->flags & SLAB_STORE_USER)
- *dbg_userword(cachep, objp) = caller;
+ *dbg_userword(cachep, objp) = (void *)caller;
objnr = obj_to_index(cachep, slabp, objp);
@@ -3131,7 +3071,7 @@ static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
if (cachep->flags & SLAB_POISON) {
#ifdef CONFIG_DEBUG_PAGEALLOC
if ((cachep->size % PAGE_SIZE)==0 && OFF_SLAB(cachep)) {
- store_stackinfo(cachep, objp, (unsigned long)caller);
+ store_stackinfo(cachep, objp, caller);
kernel_map_pages(virt_to_page(objp),
cachep->size / PAGE_SIZE, 0);
} else {
@@ -3285,7 +3225,7 @@ static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep,
#if DEBUG
static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
- gfp_t flags, void *objp, void *caller)
+ gfp_t flags, void *objp, unsigned long caller)
{
if (!objp)
return objp;
@@ -3302,7 +3242,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
poison_obj(cachep, objp, POISON_INUSE);
}
if (cachep->flags & SLAB_STORE_USER)
- *dbg_userword(cachep, objp) = caller;
+ *dbg_userword(cachep, objp) = (void *)caller;
if (cachep->flags & SLAB_RED_ZONE) {
if (*dbg_redzone1(cachep, objp) != RED_INACTIVE ||
@@ -3343,7 +3283,7 @@ static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
static bool slab_should_failslab(struct kmem_cache *cachep, gfp_t flags)
{
- if (cachep == &cache_cache)
+ if (cachep == kmem_cache)
return false;
return should_failslab(cachep->object_size, flags, cachep->flags);
@@ -3576,8 +3516,8 @@ done:
* Fallback to other node is possible if __GFP_THISNODE is not set.
*/
static __always_inline void *
-__cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
- void *caller)
+slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
+ unsigned long caller)
{
unsigned long save_flags;
void *ptr;
@@ -3663,7 +3603,7 @@ __do_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
#endif /* CONFIG_NUMA */
static __always_inline void *
-__cache_alloc(struct kmem_cache *cachep, gfp_t flags, void *caller)
+slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller)
{
unsigned long save_flags;
void *objp;
@@ -3799,7 +3739,7 @@ free_done:
* be in this state _before_ it is released. Called with disabled ints.
*/
static inline void __cache_free(struct kmem_cache *cachep, void *objp,
- void *caller)
+ unsigned long caller)
{
struct array_cache *ac = cpu_cache_get(cachep);
@@ -3839,7 +3779,7 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp,
*/
void *kmem_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
{
- void *ret = __cache_alloc(cachep, flags, __builtin_return_address(0));
+ void *ret = slab_alloc(cachep, flags, _RET_IP_);
trace_kmem_cache_alloc(_RET_IP_, ret,
cachep->object_size, cachep->size, flags);
@@ -3850,14 +3790,14 @@ EXPORT_SYMBOL(kmem_cache_alloc);
#ifdef CONFIG_TRACING
void *
-kmem_cache_alloc_trace(size_t size, struct kmem_cache *cachep, gfp_t flags)
+kmem_cache_alloc_trace(struct kmem_cache *cachep, gfp_t flags, size_t size)
{
void *ret;
- ret = __cache_alloc(cachep, flags, __builtin_return_address(0));
+ ret = slab_alloc(cachep, flags, _RET_IP_);
trace_kmalloc(_RET_IP_, ret,
- size, slab_buffer_size(cachep), flags);
+ size, cachep->size, flags);
return ret;
}
EXPORT_SYMBOL(kmem_cache_alloc_trace);
@@ -3866,8 +3806,7 @@ EXPORT_SYMBOL(kmem_cache_alloc_trace);
#ifdef CONFIG_NUMA
void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
{
- void *ret = __cache_alloc_node(cachep, flags, nodeid,
- __builtin_return_address(0));
+ void *ret = slab_alloc_node(cachep, flags, nodeid, _RET_IP_);
trace_kmem_cache_alloc_node(_RET_IP_, ret,
cachep->object_size, cachep->size,
@@ -3878,17 +3817,17 @@ void *kmem_cache_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid)
EXPORT_SYMBOL(kmem_cache_alloc_node);
#ifdef CONFIG_TRACING
-void *kmem_cache_alloc_node_trace(size_t size,
- struct kmem_cache *cachep,
+void *kmem_cache_alloc_node_trace(struct kmem_cache *cachep,
gfp_t flags,
- int nodeid)
+ int nodeid,
+ size_t size)
{
void *ret;
- ret = __cache_alloc_node(cachep, flags, nodeid,
- __builtin_return_address(0));
+ ret = slab_alloc_node(cachep, flags, nodeid, _RET_IP_);
+
trace_kmalloc_node(_RET_IP_, ret,
- size, slab_buffer_size(cachep),
+ size, cachep->size,
flags, nodeid);
return ret;
}
@@ -3896,34 +3835,33 @@ EXPORT_SYMBOL(kmem_cache_alloc_node_trace);
#endif
static __always_inline void *
-__do_kmalloc_node(size_t size, gfp_t flags, int node, void *caller)
+__do_kmalloc_node(size_t size, gfp_t flags, int node, unsigned long caller)
{
struct kmem_cache *cachep;
cachep = kmem_find_general_cachep(size, flags);
if (unlikely(ZERO_OR_NULL_PTR(cachep)))
return cachep;
- return kmem_cache_alloc_node_trace(size, cachep, flags, node);
+ return kmem_cache_alloc_node_trace(cachep, flags, node, size);
}
#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_TRACING)
void *__kmalloc_node(size_t size, gfp_t flags, int node)
{
- return __do_kmalloc_node(size, flags, node,
- __builtin_return_address(0));
+ return __do_kmalloc_node(size, flags, node, _RET_IP_);
}
EXPORT_SYMBOL(__kmalloc_node);
void *__kmalloc_node_track_caller(size_t size, gfp_t flags,
int node, unsigned long caller)
{
- return __do_kmalloc_node(size, flags, node, (void *)caller);
+ return __do_kmalloc_node(size, flags, node, caller);
}
EXPORT_SYMBOL(__kmalloc_node_track_caller);
#else
void *__kmalloc_node(size_t size, gfp_t flags, int node)
{
- return __do_kmalloc_node(size, flags, node, NULL);
+ return __do_kmalloc_node(size, flags, node, 0);
}
EXPORT_SYMBOL(__kmalloc_node);
#endif /* CONFIG_DEBUG_SLAB || CONFIG_TRACING */
@@ -3936,7 +3874,7 @@ EXPORT_SYMBOL(__kmalloc_node);
* @caller: function caller for debug tracking of the caller
*/
static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
- void *caller)
+ unsigned long caller)
{
struct kmem_cache *cachep;
void *ret;
@@ -3949,9 +3887,9 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
cachep = __find_general_cachep(size, flags);
if (unlikely(ZERO_OR_NULL_PTR(cachep)))
return cachep;
- ret = __cache_alloc(cachep, flags, caller);
+ ret = slab_alloc(cachep, flags, caller);
- trace_kmalloc((unsigned long) caller, ret,
+ trace_kmalloc(caller, ret,
size, cachep->size, flags);
return ret;
@@ -3961,20 +3899,20 @@ static __always_inline void *__do_kmalloc(size_t size, gfp_t flags,
#if defined(CONFIG_DEBUG_SLAB) || defined(CONFIG_TRACING)
void *__kmalloc(size_t size, gfp_t flags)
{
- return __do_kmalloc(size, flags, __builtin_return_address(0));
+ return __do_kmalloc(size, flags, _RET_IP_);
}
EXPORT_SYMBOL(__kmalloc);
void *__kmalloc_track_caller(size_t size, gfp_t flags, unsigned long caller)
{
- return __do_kmalloc(size, flags, (void *)caller);
+ return __do_kmalloc(size, flags, caller);
}
EXPORT_SYMBOL(__kmalloc_track_caller);
#else
void *__kmalloc(size_t size, gfp_t flags)
{
- return __do_kmalloc(size, flags, NULL);
+ return __do_kmalloc(size, flags, 0);
}
EXPORT_SYMBOL(__kmalloc);
#endif
@@ -3995,7 +3933,7 @@ void kmem_cache_free(struct kmem_cache *cachep, void *objp)
debug_check_no_locks_freed(objp, cachep->object_size);
if (!(cachep->flags & SLAB_DEBUG_OBJECTS))
debug_check_no_obj_freed(objp, cachep->object_size);
- __cache_free(cachep, objp, __builtin_return_address(0));
+ __cache_free(cachep, objp, _RET_IP_);
local_irq_restore(flags);
trace_kmem_cache_free(_RET_IP_, objp);
@@ -4026,7 +3964,7 @@ void kfree(const void *objp)
debug_check_no_locks_freed(objp, c->object_size);
debug_check_no_obj_freed(objp, c->object_size);
- __cache_free(c, (void *)objp, __builtin_return_address(0));
+ __cache_free(c, (void *)objp, _RET_IP_);
local_irq_restore(flags);
}
EXPORT_SYMBOL(kfree);
diff --git a/mm/slab.h b/mm/slab.h
index db7848caaa25..7deeb449a301 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -25,9 +25,26 @@ extern enum slab_state slab_state;
/* The slab cache mutex protects the management structures during changes */
extern struct mutex slab_mutex;
+
+/* The list of all slab caches on the system */
extern struct list_head slab_caches;
-struct kmem_cache *__kmem_cache_create(const char *name, size_t size,
+/* The slab cache that manages slab cache information */
+extern struct kmem_cache *kmem_cache;
+
+/* Functions provided by the slab allocators */
+extern int __kmem_cache_create(struct kmem_cache *, unsigned long flags);
+
+#ifdef CONFIG_SLUB
+struct kmem_cache *__kmem_cache_alias(const char *name, size_t size,
size_t align, unsigned long flags, void (*ctor)(void *));
+#else
+static inline struct kmem_cache *__kmem_cache_alias(const char *name, size_t size,
+ size_t align, unsigned long flags, void (*ctor)(void *))
+{ return NULL; }
+#endif
+
+
+int __kmem_cache_shutdown(struct kmem_cache *);
#endif
diff --git a/mm/slab_common.c b/mm/slab_common.c
index aa3ca5bb01b5..9c217255ac49 100644
--- a/mm/slab_common.c
+++ b/mm/slab_common.c
@@ -22,6 +22,53 @@
enum slab_state slab_state;
LIST_HEAD(slab_caches);
DEFINE_MUTEX(slab_mutex);
+struct kmem_cache *kmem_cache;
+
+#ifdef CONFIG_DEBUG_VM
+static int kmem_cache_sanity_check(const char *name, size_t size)
+{
+ struct kmem_cache *s = NULL;
+
+ if (!name || in_interrupt() || size < sizeof(void *) ||
+ size > KMALLOC_MAX_SIZE) {
+ pr_err("kmem_cache_create(%s) integrity check failed\n", name);
+ return -EINVAL;
+ }
+
+ list_for_each_entry(s, &slab_caches, list) {
+ char tmp;
+ int res;
+
+ /*
+ * This happens when the module gets unloaded and doesn't
+ * destroy its slab cache and no-one else reuses the vmalloc
+ * area of the module. Print a warning.
+ */
+ res = probe_kernel_address(s->name, tmp);
+ if (res) {
+ pr_err("Slab cache with size %d has lost its name\n",
+ s->object_size);
+ continue;
+ }
+
+ if (!strcmp(s->name, name)) {
+ pr_err("%s (%s): Cache name already exists.\n",
+ __func__, name);
+ dump_stack();
+ s = NULL;
+ return -EINVAL;
+ }
+ }
+
+ WARN_ON(strchr(name, ' ')); /* It confuses parsers */
+ return 0;
+}
+#else
+static inline int kmem_cache_sanity_check(const char *name, size_t size)
+{
+ return 0;
+}
+#endif
/*
* kmem_cache_create - Create a cache.
@@ -52,68 +99,92 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, size_t align
unsigned long flags, void (*ctor)(void *))
{
struct kmem_cache *s = NULL;
-
-#ifdef CONFIG_DEBUG_VM
- if (!name || in_interrupt() || size < sizeof(void *) ||
- size > KMALLOC_MAX_SIZE) {
- printk(KERN_ERR "kmem_cache_create(%s) integrity check"
- " failed\n", name);
- goto out;
- }
-#endif
+ int err = 0;
get_online_cpus();
mutex_lock(&slab_mutex);
-#ifdef CONFIG_DEBUG_VM
- list_for_each_entry(s, &slab_caches, list) {
- char tmp;
- int res;
+ if (!kmem_cache_sanity_check(name, size) == 0)
+ goto out_locked;
- /*
- * This happens when the module gets unloaded and doesn't
- * destroy its slab cache and no-one else reuses the vmalloc
- * area of the module. Print a warning.
- */
- res = probe_kernel_address(s->name, tmp);
- if (res) {
- printk(KERN_ERR
- "Slab cache with size %d has lost its name\n",
- s->object_size);
- continue;
- }
- if (!strcmp(s->name, name)) {
- printk(KERN_ERR "kmem_cache_create(%s): Cache name"
- " already exists.\n",
- name);
- dump_stack();
- s = NULL;
- goto oops;
+ s = __kmem_cache_alias(name, size, align, flags, ctor);
+ if (s)
+ goto out_locked;
+
+ s = kmem_cache_zalloc(kmem_cache, GFP_KERNEL);
+ if (s) {
+ s->object_size = s->size = size;
+ s->align = align;
+ s->ctor = ctor;
+ s->name = kstrdup(name, GFP_KERNEL);
+ if (!s->name) {
+ kmem_cache_free(kmem_cache, s);
+ err = -ENOMEM;
+ goto out_locked;
}
- }
- WARN_ON(strchr(name, ' ')); /* It confuses parsers */
-#endif
+ err = __kmem_cache_create(s, flags);
+ if (!err) {
- s = __kmem_cache_create(name, size, align, flags, ctor);
+ s->refcount = 1;
+ list_add(&s->list, &slab_caches);
-#ifdef CONFIG_DEBUG_VM
-oops:
-#endif
+ } else {
+ kfree(s->name);
+ kmem_cache_free(kmem_cache, s);
+ }
+ } else
+ err = -ENOMEM;
+
+out_locked:
mutex_unlock(&slab_mutex);
put_online_cpus();
-#ifdef CONFIG_DEBUG_VM
-out:
-#endif
- if (!s && (flags & SLAB_PANIC))
- panic("kmem_cache_create: Failed to create slab '%s'\n", name);
+ if (err) {
+
+ if (flags & SLAB_PANIC)
+ panic("kmem_cache_create: Failed to create slab '%s'. Error %d\n",
+ name, err);
+ else {
+ printk(KERN_WARNING "kmem_cache_create(%s) failed with error %d",
+ name, err);
+ dump_stack();
+ }
+
+ return NULL;
+ }
return s;
}
EXPORT_SYMBOL(kmem_cache_create);
+void kmem_cache_destroy(struct kmem_cache *s)
+{
+ get_online_cpus();
+ mutex_lock(&slab_mutex);
+ s->refcount--;
+ if (!s->refcount) {
+ list_del(&s->list);
+
+ if (!__kmem_cache_shutdown(s)) {
+ if (s->flags & SLAB_DESTROY_BY_RCU)
+ rcu_barrier();
+
+ kfree(s->name);
+ kmem_cache_free(kmem_cache, s);
+ } else {
+ list_add(&s->list, &slab_caches);
+ printk(KERN_ERR "kmem_cache_destroy %s: Slab cache still has objects\n",
+ s->name);
+ dump_stack();
+ }
+ }
+ mutex_unlock(&slab_mutex);
+ put_online_cpus();
+}
+EXPORT_SYMBOL(kmem_cache_destroy);
+
int slab_is_available(void)
{
return slab_state >= UP;
diff --git a/mm/slob.c b/mm/slob.c
index 45d4ca79933a..a08e4681fd0d 100644
--- a/mm/slob.c
+++ b/mm/slob.c
@@ -194,7 +194,7 @@ static void *slob_new_pages(gfp_t gfp, int order, int node)
void *page;
#ifdef CONFIG_NUMA
- if (node != -1)
+ if (node != NUMA_NO_NODE)
page = alloc_pages_exact_node(node, gfp, order);
else
#endif
@@ -290,7 +290,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node)
* If there's a node specification, search for a partial
* page with a matching node id in the freelist.
*/
- if (node != -1 && page_to_nid(sp) != node)
+ if (node != NUMA_NO_NODE && page_to_nid(sp) != node)
continue;
#endif
/* Enough room on this page? */
@@ -425,7 +425,8 @@ out:
* End of slob allocator proper. Begin kmem_cache_alloc and kmalloc frontend.
*/
-void *__kmalloc_node(size_t size, gfp_t gfp, int node)
+static __always_inline void *
+__do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller)
{
unsigned int *m;
int align = max(ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN);
@@ -446,7 +447,7 @@ void *__kmalloc_node(size_t size, gfp_t gfp, int node)
*m = size;
ret = (void *)m + align;
- trace_kmalloc_node(_RET_IP_, ret,
+ trace_kmalloc_node(caller, ret,
size, size + align, gfp, node);
} else {
unsigned int order = get_order(size);
@@ -460,15 +461,35 @@ void *__kmalloc_node(size_t size, gfp_t gfp, int node)
page->private = size;
}
- trace_kmalloc_node(_RET_IP_, ret,
+ trace_kmalloc_node(caller, ret,
size, PAGE_SIZE << order, gfp, node);
}
kmemleak_alloc(ret, size, 1, gfp);
return ret;
}
+
+void *__kmalloc_node(size_t size, gfp_t gfp, int node)
+{
+ return __do_kmalloc_node(size, gfp, node, _RET_IP_);
+}
EXPORT_SYMBOL(__kmalloc_node);
+#ifdef CONFIG_TRACING
+void *__kmalloc_track_caller(size_t size, gfp_t gfp, unsigned long caller)
+{
+ return __do_kmalloc_node(size, gfp, NUMA_NO_NODE, caller);
+}
+
+#ifdef CONFIG_NUMA
+void *__kmalloc_node_track_caller(size_t size, gfp_t gfp,
+ int node, unsigned long caller)
+{
+ return __do_kmalloc_node(size, gfp, node, caller);
+}
+#endif
+#endif
+
void kfree(const void *block)
{
struct page *sp;
@@ -508,44 +529,24 @@ size_t ksize(const void *block)
}
EXPORT_SYMBOL(ksize);
-struct kmem_cache *__kmem_cache_create(const char *name, size_t size,
- size_t align, unsigned long flags, void (*ctor)(void *))
+int __kmem_cache_create(struct kmem_cache *c, unsigned long flags)
{
- struct kmem_cache *c;
-
- c = slob_alloc(sizeof(struct kmem_cache),
- GFP_KERNEL, ARCH_KMALLOC_MINALIGN, -1);
+ size_t align = c->size;
- if (c) {
- c->name = name;
- c->size = size;
- if (flags & SLAB_DESTROY_BY_RCU) {
- /* leave room for rcu footer at the end of object */
- c->size += sizeof(struct slob_rcu);
- }
- c->flags = flags;
- c->ctor = ctor;
- /* ignore alignment unless it's forced */
- c->align = (flags & SLAB_HWCACHE_ALIGN) ? SLOB_ALIGN : 0;
- if (c->align < ARCH_SLAB_MINALIGN)
- c->align = ARCH_SLAB_MINALIGN;
- if (c->align < align)
- c->align = align;
-
- kmemleak_alloc(c, sizeof(struct kmem_cache), 1, GFP_KERNEL);
- c->refcount = 1;
+ if (flags & SLAB_DESTROY_BY_RCU) {
+ /* leave room for rcu footer at the end of object */
+ c->size += sizeof(struct slob_rcu);
}
- return c;
-}
+ c->flags = flags;
+ /* ignore alignment unless it's forced */
+ c->align = (flags & SLAB_HWCACHE_ALIGN) ? SLOB_ALIGN : 0;
+ if (c->align < ARCH_SLAB_MINALIGN)
+ c->align = ARCH_SLAB_MINALIGN;
+ if (c->align < align)
+ c->align = align;
-void kmem_cache_destroy(struct kmem_cache *c)
-{
- kmemleak_free(c);
- if (c->flags & SLAB_DESTROY_BY_RCU)
- rcu_barrier();
- slob_free(c, sizeof(struct kmem_cache));
+ return 0;
}
-EXPORT_SYMBOL(kmem_cache_destroy);
void *kmem_cache_alloc_node(struct kmem_cache *c, gfp_t flags, int node)
{
@@ -613,14 +614,28 @@ unsigned int kmem_cache_size(struct kmem_cache *c)
}
EXPORT_SYMBOL(kmem_cache_size);
+int __kmem_cache_shutdown(struct kmem_cache *c)
+{
+ /* No way to check for remaining objects */
+ return 0;
+}
+
int kmem_cache_shrink(struct kmem_cache *d)
{
return 0;
}
EXPORT_SYMBOL(kmem_cache_shrink);
+struct kmem_cache kmem_cache_boot = {
+ .name = "kmem_cache",
+ .size = sizeof(struct kmem_cache),
+ .flags = SLAB_PANIC,
+ .align = ARCH_KMALLOC_MINALIGN,
+};
+
void __init kmem_cache_init(void)
{
+ kmem_cache = &kmem_cache_boot;
slab_state = UP;
}
diff --git a/mm/slub.c b/mm/slub.c
index 8f78e2577031..a0d698467f70 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -210,11 +210,7 @@ static void sysfs_slab_remove(struct kmem_cache *);
static inline int sysfs_slab_add(struct kmem_cache *s) { return 0; }
static inline int sysfs_slab_alias(struct kmem_cache *s, const char *p)
{ return 0; }
-static inline void sysfs_slab_remove(struct kmem_cache *s)
-{
- kfree(s->name);
- kfree(s);
-}
+static inline void sysfs_slab_remove(struct kmem_cache *s) { }
#endif
@@ -568,6 +564,8 @@ static void slab_bug(struct kmem_cache *s, char *fmt, ...)
printk(KERN_ERR "BUG %s (%s): %s\n", s->name, print_tainted(), buf);
printk(KERN_ERR "----------------------------------------"
"-------------------------------------\n\n");
+
+ add_taint(TAINT_BAD_PAGE);
}
static void slab_fix(struct kmem_cache *s, char *fmt, ...)
@@ -624,7 +622,7 @@ static void object_err(struct kmem_cache *s, struct page *page,
print_trailer(s, page, object);
}
-static void slab_err(struct kmem_cache *s, struct page *page, char *fmt, ...)
+static void slab_err(struct kmem_cache *s, struct page *page, const char *fmt, ...)
{
va_list args;
char buf[100];
@@ -1069,13 +1067,13 @@ bad:
return 0;
}
-static noinline int free_debug_processing(struct kmem_cache *s,
- struct page *page, void *object, unsigned long addr)
+static noinline struct kmem_cache_node *free_debug_processing(
+ struct kmem_cache *s, struct page *page, void *object,
+ unsigned long addr, unsigned long *flags)
{
- unsigned long flags;
- int rc = 0;
+ struct kmem_cache_node *n = get_node(s, page_to_nid(page));
- local_irq_save(flags);
+ spin_lock_irqsave(&n->list_lock, *flags);
slab_lock(page);
if (!check_slab(s, page))
@@ -1113,15 +1111,19 @@ static noinline int free_debug_processing(struct kmem_cache *s,
set_track(s, object, TRACK_FREE, addr);
trace(s, page, object, 0);
init_object(s, object, SLUB_RED_INACTIVE);
- rc = 1;
out:
slab_unlock(page);
- local_irq_restore(flags);
- return rc;
+ /*
+ * Keep node_lock to preserve integrity
+ * until the object is actually freed
+ */
+ return n;
fail:
+ slab_unlock(page);
+ spin_unlock_irqrestore(&n->list_lock, *flags);
slab_fix(s, "Object at 0x%p not freed", object);
- goto out;
+ return NULL;
}
static int __init setup_slub_debug(char *str)
@@ -1214,8 +1216,9 @@ static inline void setup_object_debug(struct kmem_cache *s,
static inline int alloc_debug_processing(struct kmem_cache *s,
struct page *page, void *object, unsigned long addr) { return 0; }
-static inline int free_debug_processing(struct kmem_cache *s,
- struct page *page, void *object, unsigned long addr) { return 0; }
+static inline struct kmem_cache_node *free_debug_processing(
+ struct kmem_cache *s, struct page *page, void *object,
+ unsigned long addr, unsigned long *flags) { return NULL; }
static inline int slab_pad_check(struct kmem_cache *s, struct page *page)
{ return 1; }
@@ -1524,12 +1527,13 @@ static inline void *acquire_slab(struct kmem_cache *s,
}
static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain);
+static inline bool pfmemalloc_match(struct page *page, gfp_t gfpflags);
/*
* Try to allocate a partial slab from a specific node.
*/
-static void *get_partial_node(struct kmem_cache *s,
- struct kmem_cache_node *n, struct kmem_cache_cpu *c)
+static void *get_partial_node(struct kmem_cache *s, struct kmem_cache_node *n,
+ struct kmem_cache_cpu *c, gfp_t flags)
{
struct page *page, *page2;
void *object = NULL;
@@ -1545,9 +1549,13 @@ static void *get_partial_node(struct kmem_cache *s,
spin_lock(&n->list_lock);
list_for_each_entry_safe(page, page2, &n->partial, lru) {
- void *t = acquire_slab(s, n, page, object == NULL);
+ void *t;
int available;
+ if (!pfmemalloc_match(page, flags))
+ continue;
+
+ t = acquire_slab(s, n, page, object == NULL);
if (!t)
break;
@@ -1614,7 +1622,7 @@ static void *get_any_partial(struct kmem_cache *s, gfp_t flags,
if (n && cpuset_zone_allowed_hardwall(zone, flags) &&
n->nr_partial > s->min_partial) {
- object = get_partial_node(s, n, c);
+ object = get_partial_node(s, n, c, flags);
if (object) {
/*
* Return the object even if
@@ -1643,7 +1651,7 @@ static void *get_partial(struct kmem_cache *s, gfp_t flags, int node,
void *object;
int searchnode = (node == NUMA_NO_NODE) ? numa_node_id() : node;
- object = get_partial_node(s, get_node(s, searchnode), c);
+ object = get_partial_node(s, get_node(s, searchnode), c, flags);
if (object || node != NUMA_NO_NODE)
return object;
@@ -1709,7 +1717,7 @@ static inline void note_cmpxchg_failure(const char *n,
stat(s, CMPXCHG_DOUBLE_CPU_FAIL);
}
-void init_kmem_cache_cpus(struct kmem_cache *s)
+static void init_kmem_cache_cpus(struct kmem_cache *s)
{
int cpu;
@@ -1934,7 +1942,7 @@ static void unfreeze_partials(struct kmem_cache *s)
* If we did not find a slot then simply move all the partials to the
* per node partial list.
*/
-int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
+static int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
{
struct page *oldpage;
int pages;
@@ -1957,6 +1965,7 @@ int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain)
local_irq_save(flags);
unfreeze_partials(s);
local_irq_restore(flags);
+ oldpage = NULL;
pobjects = 0;
pages = 0;
stat(s, CPU_PARTIAL_DRAIN);
@@ -2305,7 +2314,7 @@ new_slab:
*
* Otherwise we can simply pick the next object from the lockless free list.
*/
-static __always_inline void *slab_alloc(struct kmem_cache *s,
+static __always_inline void *slab_alloc_node(struct kmem_cache *s,
gfp_t gfpflags, int node, unsigned long addr)
{
void **object;
@@ -2375,9 +2384,15 @@ redo:
return object;
}
+static __always_inline void *slab_alloc(struct kmem_cache *s,
+ gfp_t gfpflags, unsigned long addr)
+{
+ return slab_alloc_node(s, gfpflags, NUMA_NO_NODE, addr);
+}
+
void *kmem_cache_alloc(struct kmem_cache *s, gfp_t gfpflags)
{
- void *ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_);
+ void *ret = slab_alloc(s, gfpflags, _RET_IP_);
trace_kmem_cache_alloc(_RET_IP_, ret, s->object_size, s->size, gfpflags);
@@ -2388,7 +2403,7 @@ EXPORT_SYMBOL(kmem_cache_alloc);
#ifdef CONFIG_TRACING
void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size)
{
- void *ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, _RET_IP_);
+ void *ret = slab_alloc(s, gfpflags, _RET_IP_);
trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags);
return ret;
}
@@ -2406,7 +2421,7 @@ EXPORT_SYMBOL(kmalloc_order_trace);
#ifdef CONFIG_NUMA
void *kmem_cache_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node)
{
- void *ret = slab_alloc(s, gfpflags, node, _RET_IP_);
+ void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_);
trace_kmem_cache_alloc_node(_RET_IP_, ret,
s->object_size, s->size, gfpflags, node);
@@ -2420,7 +2435,7 @@ void *kmem_cache_alloc_node_trace(struct kmem_cache *s,
gfp_t gfpflags,
int node, size_t size)
{
- void *ret = slab_alloc(s, gfpflags, node, _RET_IP_);
+ void *ret = slab_alloc_node(s, gfpflags, node, _RET_IP_);
trace_kmalloc_node(_RET_IP_, ret,
size, s->size, gfpflags, node);
@@ -2452,7 +2467,8 @@ static void __slab_free(struct kmem_cache *s, struct page *page,
stat(s, FREE_SLOWPATH);
- if (kmem_cache_debug(s) && !free_debug_processing(s, page, x, addr))
+ if (kmem_cache_debug(s) &&
+ !(n = free_debug_processing(s, page, x, addr, &flags)))
return;
do {
@@ -2607,6 +2623,13 @@ void kmem_cache_free(struct kmem_cache *s, void *x)
page = virt_to_head_page(x);
+ if (kmem_cache_debug(s) && page->slab != s) {
+ pr_err("kmem_cache_free: Wrong slab cache. %s but object"
+ " is from %s\n", page->slab->name, s->name);
+ WARN_ON_ONCE(1);
+ return;
+ }
+
slab_free(s, page, x, _RET_IP_);
trace_kmem_cache_free(_RET_IP_, x);
@@ -3021,17 +3044,9 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order)
}
-static int kmem_cache_open(struct kmem_cache *s,
- const char *name, size_t size,
- size_t align, unsigned long flags,
- void (*ctor)(void *))
+static int kmem_cache_open(struct kmem_cache *s, unsigned long flags)
{
- memset(s, 0, kmem_size);
- s->name = name;
- s->ctor = ctor;
- s->object_size = size;
- s->align = align;
- s->flags = kmem_cache_flags(size, flags, name, ctor);
+ s->flags = kmem_cache_flags(s->size, flags, s->name, s->ctor);
s->reserved = 0;
if (need_reserve_slab_rcu && (s->flags & SLAB_DESTROY_BY_RCU))
@@ -3093,7 +3108,6 @@ static int kmem_cache_open(struct kmem_cache *s,
else
s->cpu_partial = 30;
- s->refcount = 1;
#ifdef CONFIG_NUMA
s->remote_node_defrag_ratio = 1000;
#endif
@@ -3101,16 +3115,16 @@ static int kmem_cache_open(struct kmem_cache *s,
goto error;
if (alloc_kmem_cache_cpus(s))
- return 1;
+ return 0;
free_kmem_cache_nodes(s);
error:
if (flags & SLAB_PANIC)
panic("Cannot create slab %s size=%lu realsize=%u "
"order=%u offset=%u flags=%lx\n",
- s->name, (unsigned long)size, s->size, oo_order(s->oo),
+ s->name, (unsigned long)s->size, s->size, oo_order(s->oo),
s->offset, flags);
- return 0;
+ return -EINVAL;
}
/*
@@ -3132,7 +3146,7 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page,
sizeof(long), GFP_ATOMIC);
if (!map)
return;
- slab_err(s, page, "%s", text);
+ slab_err(s, page, text, s->name);
slab_lock(page);
get_map(s, page, map);
@@ -3164,7 +3178,7 @@ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n)
discard_slab(s, page);
} else {
list_slab_objects(s, page,
- "Objects remaining on kmem_cache_close()");
+ "Objects remaining in %s on kmem_cache_close()");
}
}
}
@@ -3177,7 +3191,6 @@ static inline int kmem_cache_close(struct kmem_cache *s)
int node;
flush_all(s);
- free_percpu(s->cpu_slab);
/* Attempt to free all objects */
for_each_node_state(node, N_NORMAL_MEMORY) {
struct kmem_cache_node *n = get_node(s, node);
@@ -3186,33 +3199,20 @@ static inline int kmem_cache_close(struct kmem_cache *s)
if (n->nr_partial || slabs_node(s, node))
return 1;
}
+ free_percpu(s->cpu_slab);
free_kmem_cache_nodes(s);
return 0;
}
-/*
- * Close a cache and release the kmem_cache structure
- * (must be used for caches created using kmem_cache_create)
- */
-void kmem_cache_destroy(struct kmem_cache *s)
+int __kmem_cache_shutdown(struct kmem_cache *s)
{
- mutex_lock(&slab_mutex);
- s->refcount--;
- if (!s->refcount) {
- list_del(&s->list);
- mutex_unlock(&slab_mutex);
- if (kmem_cache_close(s)) {
- printk(KERN_ERR "SLUB %s: %s called for cache that "
- "still has objects.\n", s->name, __func__);
- dump_stack();
- }
- if (s->flags & SLAB_DESTROY_BY_RCU)
- rcu_barrier();
+ int rc = kmem_cache_close(s);
+
+ if (!rc)
sysfs_slab_remove(s);
- } else
- mutex_unlock(&slab_mutex);
+
+ return rc;
}
-EXPORT_SYMBOL(kmem_cache_destroy);
/********************************************************************
* Kmalloc subsystem
@@ -3221,8 +3221,6 @@ EXPORT_SYMBOL(kmem_cache_destroy);
struct kmem_cache *kmalloc_caches[SLUB_PAGE_SHIFT];
EXPORT_SYMBOL(kmalloc_caches);
-static struct kmem_cache *kmem_cache;
-
#ifdef CONFIG_ZONE_DMA
static struct kmem_cache *kmalloc_dma_caches[SLUB_PAGE_SHIFT];
#endif
@@ -3268,14 +3266,17 @@ static struct kmem_cache *__init create_kmalloc_cache(const char *name,
{
struct kmem_cache *s;
- s = kmem_cache_alloc(kmem_cache, GFP_NOWAIT);
+ s = kmem_cache_zalloc(kmem_cache, GFP_NOWAIT);
+
+ s->name = name;
+ s->size = s->object_size = size;
+ s->align = ARCH_KMALLOC_MINALIGN;
/*
* This function is called with IRQs disabled during early-boot on
* single CPU so there's no need to take slab_mutex here.
*/
- if (!kmem_cache_open(s, name, size, ARCH_KMALLOC_MINALIGN,
- flags, NULL))
+ if (kmem_cache_open(s, flags))
goto panic;
list_add(&s->list, &slab_caches);
@@ -3357,7 +3358,7 @@ void *__kmalloc(size_t size, gfp_t flags)
if (unlikely(ZERO_OR_NULL_PTR(s)))
return s;
- ret = slab_alloc(s, flags, NUMA_NO_NODE, _RET_IP_);
+ ret = slab_alloc(s, flags, _RET_IP_);
trace_kmalloc(_RET_IP_, ret, size, s->size, flags);
@@ -3400,7 +3401,7 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node)
if (unlikely(ZERO_OR_NULL_PTR(s)))
return s;
- ret = slab_alloc(s, flags, node, _RET_IP_);
+ ret = slab_alloc_node(s, flags, node, _RET_IP_);
trace_kmalloc_node(_RET_IP_, ret, size, s->size, flags, node);
@@ -3477,7 +3478,7 @@ void kfree(const void *x)
if (unlikely(!PageSlab(page))) {
BUG_ON(!PageCompound(page));
kmemleak_free(x);
- put_page(page);
+ __free_pages(page, compound_order(page));
return;
}
slab_free(page->slab, page, object, _RET_IP_);
@@ -3714,12 +3715,12 @@ void __init kmem_cache_init(void)
slub_max_order = 0;
kmem_size = offsetof(struct kmem_cache, node) +
- nr_node_ids * sizeof(struct kmem_cache_node *);
+ nr_node_ids * sizeof(struct kmem_cache_node *);
/* Allocate two kmem_caches from the page allocator */
kmalloc_size = ALIGN(kmem_size, cache_line_size());
order = get_order(2 * kmalloc_size);
- kmem_cache = (void *)__get_free_pages(GFP_NOWAIT, order);
+ kmem_cache = (void *)__get_free_pages(GFP_NOWAIT | __GFP_ZERO, order);
/*
* Must first have the slab cache available for the allocations of the
@@ -3728,9 +3729,10 @@ void __init kmem_cache_init(void)
*/
kmem_cache_node = (void *)kmem_cache + kmalloc_size;
- kmem_cache_open(kmem_cache_node, "kmem_cache_node",
- sizeof(struct kmem_cache_node),
- 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
+ kmem_cache_node->name = "kmem_cache_node";
+ kmem_cache_node->size = kmem_cache_node->object_size =
+ sizeof(struct kmem_cache_node);
+ kmem_cache_open(kmem_cache_node, SLAB_HWCACHE_ALIGN | SLAB_PANIC);
hotplug_memory_notifier(slab_memory_callback, SLAB_CALLBACK_PRI);
@@ -3738,8 +3740,10 @@ void __init kmem_cache_init(void)
slab_state = PARTIAL;
temp_kmem_cache = kmem_cache;
- kmem_cache_open(kmem_cache, "kmem_cache", kmem_size,
- 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL);
+ kmem_cache->name = "kmem_cache";
+ kmem_cache->size = kmem_cache->object_size = kmem_size;
+ kmem_cache_open(kmem_cache, SLAB_HWCACHE_ALIGN | SLAB_PANIC);
+
kmem_cache = kmem_cache_alloc(kmem_cache, GFP_NOWAIT);
memcpy(kmem_cache, temp_kmem_cache, kmem_size);
@@ -3928,11 +3932,10 @@ static struct kmem_cache *find_mergeable(size_t size,
return NULL;
}
-struct kmem_cache *__kmem_cache_create(const char *name, size_t size,
+struct kmem_cache *__kmem_cache_alias(const char *name, size_t size,
size_t align, unsigned long flags, void (*ctor)(void *))
{
struct kmem_cache *s;
- char *n;
s = find_mergeable(size, align, flags, name, ctor);
if (s) {
@@ -3946,36 +3949,29 @@ struct kmem_cache *__kmem_cache_create(const char *name, size_t size,
if (sysfs_slab_alias(s, name)) {
s->refcount--;
- return NULL;
+ s = NULL;
}
- return s;
}
- n = kstrdup(name, GFP_KERNEL);
- if (!n)
- return NULL;
+ return s;
+}
- s = kmalloc(kmem_size, GFP_KERNEL);
- if (s) {
- if (kmem_cache_open(s, n,
- size, align, flags, ctor)) {
- int r;
+int __kmem_cache_create(struct kmem_cache *s, unsigned long flags)
+{
+ int err;
- list_add(&s->list, &slab_caches);
- mutex_unlock(&slab_mutex);
- r = sysfs_slab_add(s);
- mutex_lock(&slab_mutex);
+ err = kmem_cache_open(s, flags);
+ if (err)
+ return err;
- if (!r)
- return s;
+ mutex_unlock(&slab_mutex);
+ err = sysfs_slab_add(s);
+ mutex_lock(&slab_mutex);
- list_del(&s->list);
- kmem_cache_close(s);
- }
- kfree(s);
- }
- kfree(n);
- return NULL;
+ if (err)
+ kmem_cache_close(s);
+
+ return err;
}
#ifdef CONFIG_SMP
@@ -4028,7 +4024,7 @@ void *__kmalloc_track_caller(size_t size, gfp_t gfpflags, unsigned long caller)
if (unlikely(ZERO_OR_NULL_PTR(s)))
return s;
- ret = slab_alloc(s, gfpflags, NUMA_NO_NODE, caller);
+ ret = slab_alloc(s, gfpflags, caller);
/* Honor the call site pointer we received. */
trace_kmalloc(caller, ret, size, s->size, gfpflags);
@@ -4058,7 +4054,7 @@ void *__kmalloc_node_track_caller(size_t size, gfp_t gfpflags,
if (unlikely(ZERO_OR_NULL_PTR(s)))
return s;
- ret = slab_alloc(s, gfpflags, node, caller);
+ ret = slab_alloc_node(s, gfpflags, node, caller);
/* Honor the call site pointer we received. */
trace_kmalloc_node(caller, ret, size, s->size, gfpflags, node);
@@ -5205,14 +5201,6 @@ static ssize_t slab_attr_store(struct kobject *kobj,
return err;
}
-static void kmem_cache_release(struct kobject *kobj)
-{
- struct kmem_cache *s = to_slab(kobj);
-
- kfree(s->name);
- kfree(s);
-}
-
static const struct sysfs_ops slab_sysfs_ops = {
.show = slab_attr_show,
.store = slab_attr_store,
@@ -5220,7 +5208,6 @@ static const struct sysfs_ops slab_sysfs_ops = {
static struct kobj_type slab_ktype = {
.sysfs_ops = &slab_sysfs_ops,
- .release = kmem_cache_release
};
static int uevent_filter(struct kset *kset, struct kobject *kobj)
diff --git a/mm/util.c b/mm/util.c
index 8c7265afa29f..dc3036cdcc6a 100644
--- a/mm/util.c
+++ b/mm/util.c
@@ -105,6 +105,25 @@ void *memdup_user(const void __user *src, size_t len)
}
EXPORT_SYMBOL(memdup_user);
+static __always_inline void *__do_krealloc(const void *p, size_t new_size,
+ gfp_t flags)
+{
+ void *ret;
+ size_t ks = 0;
+
+ if (p)
+ ks = ksize(p);
+
+ if (ks >= new_size)
+ return (void *)p;
+
+ ret = kmalloc_track_caller(new_size, flags);
+ if (ret && p)
+ memcpy(ret, p, ks);
+
+ return ret;
+}
+
/**
* __krealloc - like krealloc() but don't free @p.
* @p: object to reallocate memory for.
@@ -117,23 +136,11 @@ EXPORT_SYMBOL(memdup_user);
*/
void *__krealloc(const void *p, size_t new_size, gfp_t flags)
{
- void *ret;
- size_t ks = 0;
-
if (unlikely(!new_size))
return ZERO_SIZE_PTR;
- if (p)
- ks = ksize(p);
+ return __do_krealloc(p, new_size, flags);
- if (ks >= new_size)
- return (void *)p;
-
- ret = kmalloc_track_caller(new_size, flags);
- if (ret && p)
- memcpy(ret, p, ks);
-
- return ret;
}
EXPORT_SYMBOL(__krealloc);
@@ -157,7 +164,7 @@ void *krealloc(const void *p, size_t new_size, gfp_t flags)
return ZERO_SIZE_PTR;
}
- ret = __krealloc(p, new_size, flags);
+ ret = __do_krealloc(p, new_size, flags);
if (ret && p != ret)
kfree(p);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 8d01243d9560..99b434b674c0 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -3102,6 +3102,7 @@ int kswapd_run(int nid)
/* failure at boot is fatal */
BUG_ON(system_state == SYSTEM_BOOTING);
printk("Failed to start kswapd on node %d\n",nid);
+ pgdat->kswapd = NULL;
ret = -1;
}
return ret;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index df7a6748231d..b3e3b9d525d0 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -1157,7 +1157,7 @@ static void __cpuinit start_cpu_timer(int cpu)
{
struct delayed_work *work = &per_cpu(vmstat_work, cpu);
- INIT_DELAYED_WORK_DEFERRABLE(work, vmstat_update);
+ INIT_DEFERRABLE_WORK(work, vmstat_update);
schedule_delayed_work_on(cpu, work, __round_jiffies_relative(HZ, cpu));
}
Copyright © 1996 – 2023 Jason A. Donenfeld. All Rights Reverse Engineered.