/*
* Replace item expected in radix tree by a new item, while holding tree lock.
*/
static int shmem_radix_tree_replace(struct address_space *mapping,
pgoff_t index, void *expected, void *replacement)
{
void **pslot;
void *item;
VM_BUG_ON(!expected);
VM_BUG_ON(!replacement);
pslot = radix_tree_lookup_slot(&mapping->page_tree, index);
if (!pslot)
return -ENOENT;
item = radix_tree_deref_slot_protected(pslot, &mapping->tree_lock);
if (item != expected)
return -ENOENT;
radix_tree_replace_slot(pslot, replacement);
return 0;
}
/*
* Sometimes, before we decide whether to proceed or to fail, we must check
* that an entry was not already brought back from swap by a racing thread.
*
* Checking page is not enough: by the time a SwapCache page is locked, it
* might be reused, and again be SwapCache, using the same swap as before.
*/
static bool shmem_confirm_swap(struct address_space *mapping,
pgoff_t index, swp_entry_t swap)
{
void *item;
rcu_read_lock();
item = radix_tree_lookup(&mapping->page_tree, index);
rcu_read_unlock();
return item == swp_to_radix_entry(swap);
}
/*
* Like add_to_page_cache_locked, but error if expected item has gone.
*/
static int shmem_add_to_page_cache(struct page *page,
struct address_space *mapping,
pgoff_t index, void *expected)
{
int error;
VM_BUG_ON_PAGE(!PageLocked(page), page);
VM_BUG_ON_PAGE(!PageSwapBacked(page), page);
page_cache_get(page);
page->mapping = mapping;
page->index = index;
spin_lock_irq(&mapping->tree_lock);
if (!expected)
error = radix_tree_insert(&mapping->page_tree, index, page);
else
error = shmem_radix_tree_replace(mapping, index, expected,
page);
if (!error) {
mapping->nrpages++;
__inc_zone_page_state(page, NR_FILE_PAGES);
__inc_zone_page_state(page, NR_SHMEM);
spin_unlock_irq(&mapping->tree_lock);
} else {
page->mapping = NULL;
spin_unlock_irq(&mapping->tree_lock);
page_cache_release(page);
}
return error;
}
/*
* Like delete_from_page_cache, but substitutes swap for page.
*/
static void shmem_delete_from_page_cache(struct page *page, void *radswap)
{
struct address_space *mapping = page->mapping;
int error;
spin_lock_irq(&mapping->tree_lock);
error = shmem_radix_tree_replace(mapping, page->index, page, radswap);
page->mapping = NULL;
mapping->nrpages--;
__dec_zone_page_state(page, NR_FILE_PAGES);
__dec_zone_page_state(page, NR_SHMEM);
spin_unlock_irq(&mapping->tree_lock);
page_cache_release(page);
BUG_ON(error);
}
/*
* Remove swap entry from radix tree, free the swap and its page cache.
*/
static int shmem_free_swap(struct address_space *mapping,
pgoff_t index, void *radswap)
{
void *old;
spin_lock_irq(&mapping->tree_lock);
old = radix_tree_delete_item(&mapping->page_tree, index, radswap);
spin_unlock_irq(&mapping->tree_lock);
if (old != radswap)
return -ENOENT;
free_swap_and_cache(radix_to_swp_entry(radswap));
return 0;
}
/*
* SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists.
*/
void shmem_unlock_mapping(struct address_space *mapping)
{
struct pagevec pvec;
pgoff_t indices[PAGEVEC_SIZE];
pgoff_t index = 0;
pagevec_init(&pvec, 0);
/*
* Minor point, but we might as well stop if someone else SHM_LOCKs it.
*/
while (!mapping_unevictable(mapping)) {
/*
* Avoid pagevec_lookup(): find_get_pages() returns 0 as if it
* has finished, if it hits a row of PAGEVEC_SIZE swap entries.
*/
pvec.nr = find_get_entries(mapping, index,
PAGEVEC_SIZE, pvec.pages, indices);
if (!pvec.nr)
break;
index = indices[pvec.nr - 1] + 1;
pagevec_remove_exceptionals(&pvec);
check_move_unevictable_pages(pvec.pages, pvec.nr);
pagevec_release(&pvec);
cond_resched();
}
}
/*
* Remove range of pages and swap entries from radix tree, and free them.
* If !unfalloc, truncate or punch hole; if unfalloc, undo failed fallocate.
*/
static void shmem_undo_range(struct inode *inode, loff_t lstart, loff_t lend,
bool unfalloc)
{
struct address_space *mapping = inode->i_mapping;
struct shmem_inode_info *info = SHMEM_I(inode);
pgoff_t start = (lstart + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
pgoff_t end = (lend + 1) >> PAGE_CACHE_SHIFT;
unsigned int partial_start = lstart & (PAGE_CACHE_SIZE - 1);
unsigned int partial_end = (lend + 1) & (PAGE_CACHE_SIZE - 1);
struct pagevec pvec;
pgoff_t indices[PAGEVEC_SIZE];
long nr_swaps_freed = 0;
pgoff_t index;
int i;
if (lend == -1)
end = -1; /* unsigned, so actually very big */
pagevec_init(&pvec, 0);
index = start;
while (index < end) {
pvec.nr = find_get_entries(mapping, index,
min(end - index, (pgoff_t)PAGEVEC_SIZE),
pvec.pages, indices);
if (!pvec.nr)
break;
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
index = indices[i];
if (index >= end)
break;
if (radix_tree_exceptional_entry(page)) {
if (unfalloc)
continue;
nr_swaps_freed += !shmem_free_swap(mapping,
index, page);
continue;
}
if (!trylock_page(page))
continue;
if (!unfalloc || !PageUptodate(page)) {
if (page->mapping == mapping) {
VM_BUG_ON_PAGE(PageWriteback(page), page);
truncate_inode_page(mapping, page);
}
}
unlock_page(page);
}
pagevec_remove_exceptionals(&pvec);
pagevec_release(&pvec);
cond_resched();
index++;
}
if (partial_start) {
struct page *page = NULL;
shmem_getpage(inode, start - 1, &page, SGP_READ, NULL);
if (page) {
unsigned int top = PAGE_CACHE_SIZE;
if (start > end) {
top = partial_end;
partial_end = 0;
}
zero_user_segment(page, partial_start, top);
set_page_dirty(page);
unlock_page(page);
page_cache_release(page);
}
}
if (partial_end) {
struct page *page = NULL;
shmem_getpage(inode, end, &page, SGP_READ, NULL);
if (page) {
zero_user_segment(page, 0, partial_end);
set_page_dirty(page);
unlock_page(page);
page_cache_release(page);
}
}
if (start >= end)
return;
index = start;
while (index < end) {
cond_resched();
pvec.nr = find_get_entries(mapping, index,
min(end - index, (pgoff_t)PAGEVEC_SIZE),
pvec.pages, indices);
if (!pvec.nr) {
/* If all gone or hole-punch or unfalloc, we're done */
if (index == start || end != -1)
break;
/* But if truncating, restart to make sure all gone */
index = start;
continue;
}
for (i = 0; i < pagevec_count(&pvec); i++) {
struct page *page = pvec.pages[i];
index = indices[i];
if (index >= end)
break;
if (radix_tree_exceptional_entry(page)) {
if (unfalloc)
continue;
if (shmem_free_swap(mapping, index, page)) {
/* Swap was replaced by page: retry */
index--;
break;
}
nr_swaps_freed++;
continue;
}
lock_page(page);
if (!unfalloc || !PageUptodate(page)) {
if (page->mapping == mapping) {
VM_BUG_ON_PAGE(PageWriteback(page), page);
truncate_inode_page(mapping, page);
} else {
/* Page was replaced by swap: retry */
unlock_page(page);
index--;
break;
}
}
unlock_page(page);
}
pagevec_remove_exceptionals(&pvec);
pagevec_release(&pvec);
index++;
}
spin_lock(&info->lock);
info->swapped -= nr_swaps_freed;
shmem_recalc_inode(inode);
spin_unlock(&info->lock);
}
void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
{
shmem_undo_range(inode, lstart, lend, false);
inode->i_ctime = inode->i_mtime = CURRENT_TIME;
}
EXPORT_SYMBOL_GPL(shmem_truncate_range);
static int shmem_setattr(struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = d_inode(dentry);
struct shmem_inode_info *info = SHMEM_I(inode);
int error;
error = inode_change_ok(inode, attr);
if (error)
return error;
if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
loff_t oldsize = inode->i_size;
loff_t newsize = attr->ia_size;
/* protected by i_mutex */
if ((newsize < oldsize && (info->seals & F_SEAL_SHRINK)) ||
(newsize > oldsize && (info->seals & F_SEAL_GROW)))
return -EPERM;
if (newsize != oldsize) {
error = shmem_reacct_size(SHMEM_I(inode)->flags,
oldsize, newsize);
if (error)
return error;
i_size_write(inode, newsize);
inode->i_ctime = inode->i_mtime = CURRENT_TIME;
}
if (newsize <= oldsize) {
loff_t holebegin = round_up(newsize, PAGE_SIZE);
unmap_mapping_range(inode->i_mapping, holebegin, 0, 1);
shmem_truncate_range(inode, newsize, (loff_t)-1);
/* unmap again to remove racily COWed private pages */
unmap_mapping_range(inode->i_mapping, holebegin, 0, 1);
}
}
setattr_copy(inode, attr);
if (attr->ia_valid & ATTR_MODE)
error = posix_acl_chmod(inode, inode->i_mode);
return error;
}
static void shmem_evict_inode(struct inode *inode)
{
struct shmem_inode_info *info = SHMEM_I(inode);
if (inode->i_mapping->a_ops == &shmem_aops) {
shmem_unacct_size(info->flags, inode->i_size);
inode->i_size = 0;
shmem_truncate_range(inode, 0, (loff_t)-1);
if (!list_empty(&info->swaplist)) {
mutex_lock(&shmem_swaplist_mutex);
list_del_init(&info->swaplist);
mutex_unlock(&shmem_swaplist_mutex);
}
} else
kfree(info->symlink);
simple_xattrs_free(&info->xattrs);
WARN_ON(inode->i_blocks);
shmem_free_inode(inode->i_sb);
clear_inode(inode);
}
/*
* If swap found in inode, free it and move page from swapcache to filecache.
*/
static int shmem_unuse_inode(struct shmem_inode_info *info,
swp_entry_t swap, struct page **pagep)
{
struct address_space *mapping = info->vfs_inode.i_mapping;
void *radswap;
pgoff_t index;
gfp_t gfp;
int error = 0;
radswap = swp_to_radix_entry(swap);
index = radix_tree_locate_item(&mapping->page_tree, radswap);
if (index == -1)
return -EAGAIN; /* tell shmem_unuse we found nothing */
/*
* Move _head_ to start search for next from here.
* But be careful: shmem_evict_inode checks list_empty without taking
* mutex, and there's an instant in list_move_tail when info->swaplist
* would appear empty, if it were the only one on shmem_swaplist.
*/
if (shmem_swaplist.next != &info->swaplist)
list_move_tail(&shmem_swaplist, &info->swaplist);
gfp = mapping_gfp_mask(mapping);
if (shmem_should_replace_page(*pagep, gfp)) {
mutex_unlock(&shmem_swaplist_mutex);
error = shmem_replace_page(pagep, gfp, info, index);
mutex_lock(&shmem_swaplist_mutex);
/*
* We needed to drop mutex to make that restrictive page
* allocation, but the inode might have been freed while we
* dropped it: although a racing shmem_evict_inode() cannot
* complete without emptying the radix_tree, our page lock
* on this swapcache page is not enough to prevent that -
* free_swap_and_cache() of our swap entry will only
* trylock_page(), removing swap from radix_tree whatever.
*
* We must not proceed to shmem_add_to_page_cache() if the
* inode has been freed, but of course we cannot rely on
* inode or mapping or info to check that. However, we can
* safely check if our swap entry is still in use (and here
* it can't have got reused for another page): if it's still
* in use, then the inode cannot have been freed yet, and we
* can safely proceed (if it's no longer in use, that tells
* nothing about the inode, but we don't need to unuse swap).
*/
if (!page_swapcount(*pagep))
error = -ENOENT;
}
/*
* We rely on shmem_swaplist_mutex, not only to protect the swaplist,
* but also to hold up shmem_evict_inode(): so inode cannot be freed
* beneath us (pagelock doesn't help until the page is in pagecache).
*/
if (!error)
error = shmem_add_to_page_cache(*pagep, mapping, index,
radswap);
if (error != -ENOMEM) {
/*
* Truncation and eviction use free_swap_and_cache(), which
* only does trylock page: if we raced, best clean up here.
*/
delete_from_swap_cache(*pagep);
set_page_dirty(*pagep);
if (!error) {
spin_lock(&info->lock);
info->swapped--;
spin_unlock(&info->lock);
swap_free(swap);
}
}
return error;
}
/*
* Search through swapped inodes to find and replace swap by page.
*/
int shmem_unuse(swp_entry_t swap, struct page *page)
{
struct list_head *this, *next;
struct shmem_inode_info *info;
struct mem_cgroup *memcg;
int error = 0;
/*
* There's a faint possibility that swap page was replaced before
* caller locked it: caller will come back later with the right page.
*/
if (unlikely(!PageSwapCache(page) || page_private(page) != swap.val))
goto out;
/*
* Charge page using GFP_KERNEL while we can wait, before taking
* the shmem_swaplist_mutex which might hold up shmem_writepage().
* Charged back to the user (not to caller) when swap account is used.
*/
error = mem_cgroup_try_charge(page, current->mm, GFP_KERNEL, &memcg);
if (error)
goto out;
/* No radix_tree_preload: swap entry keeps a place for page in tree */
error = -EAGAIN;
mutex_lock(&shmem_swaplist_mutex);
list_for_each_safe(this, next, &shmem_swaplist) {
info = list_entry(this, struct shmem_inode_info, swaplist);
if (info->swapped)
error = shmem_unuse_inode(info, swap, &page);
else
list_del_init(&info->swaplist);
cond_resched();
if (error != -EAGAIN)
break;
/* found nothing in this: move on to search the next */
}
mutex_unlock(&shmem_swaplist_mutex);
if (error) {
if (error != -ENOMEM)
error = 0;
mem_cgroup_cancel_charge(page, memcg);
} else
mem_cgroup_commit_charge(page, memcg, true);
out:
unlock_page(page);
page_cache_release(page);
return error;
}
/*
* Move the page from the page cache to the swap cache.
*/
static int shmem_writepage(struct page *page, struct writeback_control *wbc)
{
struct shmem_inode_info *info;
struct address_space *mapping;
struct inode *inode;
swp_entry_t swap;
pgoff_t index;
BUG_ON(!PageLocked(page));
mapping = page->mapping;
index = page->index;
inode = mapping->host;
info = SHMEM_I(inode);
if (info->flags & VM_LOCKED)
goto redirty;
if (!total_swap_pages)
goto redirty;
/*
* Our capabilities prevent regular writeback or sync from ever calling
* shmem_writepage; but a stacking filesystem might use ->writepage of
* its underlying filesystem, in which case tmpfs should write out to
* swap only in response to memory pressure, and not for the writeback
* threads or sync.
*/
if (!wbc->for_reclaim) {
WARN_ON_ONCE(1); /* Still happens? Tell us about it! */
goto redirty;
}
/*
* This is somewhat ridiculous, but without plumbing a SWAP_MAP_FALLOC
* value into swapfile.c, the only way we can correctly account for a
* fallocated page arriving here is now to initialize it and write it.
*
* That's okay for a page already fallocated earlier, but if we have
* not yet completed the fallocation, then (a) we want to keep track
* of this page in case we have to undo it, and (b) it may not be a
* good idea to continue anyway, once we're pushing into swap. So
* reactivate the page, and let shmem_fallocate() quit when too many.
*/
if (!PageUptodate(page)) {
if (inode->i_private) {
struct shmem_falloc *shmem_falloc;
spin_lock(&inode->i_lock);
shmem_falloc = inode->i_private;
if (shmem_falloc &&
!shmem_falloc->waitq &&
index >= shmem_falloc->start &&
index < shmem_falloc->next)
shmem_falloc->nr_unswapped++;
else
shmem_falloc = NULL;
spin_unlock(&inode->i_lock);
if (shmem_falloc)
goto redirty;
}
clear_highpage(page);
flush_dcache_page(page);
SetPageUptodate(page);
}
swap = get_swap_page();
if (!swap.val)
goto redirty;
/*
* Add inode to shmem_unuse()'s list of swapped-out inodes,
* if it's not already there. Do it now before the page is
* moved to swap cache, when its pagelock no longer protects
* the inode from eviction. But don't unlock the mutex until
* we've incremented swapped, because shmem_unuse_inode() will
* prune a !swapped inode from the swaplist under this mutex.
*/
mutex_lock(&shmem_swaplist_mutex);
if (list_empty(&info->swaplist))
list_add_tail(&info->swaplist, &shmem_swaplist);
if (add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) {
swap_shmem_alloc(swap);
shmem_delete_from_page_cache(page, swp_to_radix_entry(swap));
spin_lock(&info->lock);
info->swapped++;
shmem_recalc_inode(inode);
spin_unlock(&info->lock);
mutex_unlock(&shmem_swaplist_mutex);
BUG_ON(page_mapped(page));
swap_writepage(page, wbc);
return 0;
}
mutex_unlock(&shmem_swaplist_mutex);
swapcache_free(swap);
redirty:
set_page_dirty(page);
if (wbc->for_reclaim)
return AOP_WRITEPAGE_ACTIVATE; /* Return with page locked */
unlock_page(page);
return 0;
}
#ifdef CONFIG_NUMA
#ifdef CONFIG_TMPFS
static void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol)
{
char buffer[64];
if (!mpol || mpol->mode == MPOL_DEFAULT)
return; /* show nothing */
mpol_to_str(buffer, sizeof(buffer), mpol);
seq_printf(seq, ",mpol=%s", buffer);
}
static struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo)
{
struct mempolicy *mpol = NULL;
if (sbinfo->mpol) {
spin_lock(&sbinfo->stat_lock); /* prevent replace/use races */
mpol = sbinfo->mpol;
mpol_get(mpol);
spin_unlock(&sbinfo->stat_lock);
}
return mpol;
}
#endif /* CONFIG_TMPFS */
static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp,
struct shmem_inode_info *info, pgoff_t index)
{
struct vm_area_struct pvma;
struct page *page;
/* Create a pseudo vma that just contains the policy */
pvma.vm_start = 0;
/* Bias interleave by inode number to distribute better across nodes */
pvma.vm_pgoff = index + info->vfs_inode.i_ino;
pvma.vm_ops = NULL;
pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, index);
page = swapin_readahead(swap, gfp, &pvma, 0);
/* Drop reference taken by mpol_shared_policy_lookup() */
mpol_cond_put(pvma.vm_policy);
return page;
}
static struct page *shmem_alloc_page(gfp_t gfp,
struct shmem_inode_info *info, pgoff_t index)
{
struct vm_area_struct pvma;
struct page *page;
/* Create a pseudo vma that just contains the policy */
pvma.vm_start = 0;
/* Bias interleave by inode number to distribute better across nodes */
pvma.vm_pgoff = index + info->vfs_inode.i_ino;
pvma.vm_ops = NULL;
pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, index);
page = alloc_page_vma(gfp, &pvma, 0);
/* Drop reference taken by mpol_shared_policy_lookup() */
mpol_cond_put(pvma.vm_policy);
return page;
}
#else /* !CONFIG_NUMA */
#ifdef CONFIG_TMPFS
static inline void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol)
{
}
#endif /* CONFIG_TMPFS */
static inline struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp,
struct shmem_inode_info *info, pgoff_t index)
{
return swapin_readahead(swap, gfp, NULL, 0);
}
static inline struct page *shmem_alloc_page(gfp_t gfp,
struct shmem_inode_info *info, pgoff_t index)
{
return alloc_page(gfp);
}
#endif /* CONFIG_NUMA */
#if !defined(CONFIG_NUMA) || !defined(CONFIG_TMPFS)
static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo)
{
return NULL;
}
#endif
/*
* When a page is moved from swapcache to shmem filecache (either by the
* usual swapin of shmem_getpage_gfp(), or by the less common swapoff of
* shmem_unuse_inode()), it may have been read in earlier from swap, in
* ignorance of the mapping it belongs to. If that mapping has special
* constraints (like the gma500 GEM driver, which requires RAM below 4GB),
* we may need to copy to a suitable page before moving to filecache.
*
* In a future release, this may well be extended to respect cpuset and
* NUMA mempolicy, and applied also to anonymous pages in do_swap_page();
* but for now it is a simple matter of zone.
*/
static bool shmem_should_replace_page(struct page *page, gfp_t gfp)
{
return page_zonenum(page) > gfp_zone(gfp);
}
static int shmem_replace_page(struct page **pagep, gfp_t gfp,
struct shmem_inode_info *info, pgoff_t index)
{
struct page *oldpage, *newpage;
struct address_space *swap_mapping;
pgoff_t swap_index;
int error;
oldpage = *pagep;
swap_index = page_private(oldpage);
swap_mapping = page_mapping(oldpage);
/*
* We have arrived here because our zones are constrained, so don't
* limit chance of success by further cpuset and node constraints.
*/
gfp &= ~GFP_CONSTRAINT_MASK;
newpage = shmem_alloc_page(gfp, info, index);
if (!newpage)
return -ENOMEM;
page_cache_get(newpage);
copy_highpage(newpage, oldpage);
flush_dcache_page(newpage);
__set_page_locked(newpage);
SetPageUptodate(newpage);
SetPageSwapBacked(newpage);
set_page_private(newpage, swap_index);
SetPageSwapCache(newpage);
/*
* Our caller will very soon move newpage out of swapcache, but it's
* a nice clean interface for us to replace oldpage by newpage there.
*/
spin_lock_irq(&swap_mapping->tree_lock);
error = shmem_radix_tree_replace(swap_mapping, swap_index, oldpage,
newpage);
if (!error) {
__inc_zone_page_state(newpage, NR_FILE_PAGES);
__dec_zone_page_state(oldpage, NR_FILE_PAGES);
}
spin_unlock_irq(&swap_mapping->tree_lock);
if (unlikely(error)) {
/*
* Is this possible? I think not, now that our callers check
* both PageSwapCache and page_private after getting page lock;
* but be defensive. Reverse old to newpage for clear and free.
*/
oldpage = newpage;
} else {
mem_cgroup_migrate(oldpage, newpage, true);
lru_cache_add_anon(newpage);
*pagep = newpage;
}
ClearPageSwapCache(oldpage);
set_page_private(oldpage, 0);
unlock_page(oldpage);
page_cache_release(oldpage);
page_cache_release(oldpage);
return error;
}
/*
* shmem_getpage_gfp - find page in cache, or get from swap, or allocate
*
* If we allocate a new one we do not mark it dirty. That's up to the
* vm. If we swap it in we mark it dirty since we also free the swap
* entry since a page cannot live in both the swap and page cache
*/
static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
struct page **pagep, enum sgp_type sgp, gfp_t gfp, int *fault_type)
{
struct address_space *mapping = inode->i_mapping;
struct shmem_inode_info *info;
struct shmem_sb_info *sbinfo;
struct mem_cgroup *memcg;
struct page *page;
swp_entry_t swap;
int error;
int once = 0;
int alloced = 0;
if (index > (MAX_LFS_FILESIZE >> PAGE_CACHE_SHIFT))
return -EFBIG;
repeat:
swap.val = 0;
page = find_lock_entry(mapping, index);
if (radix_tree_exceptional_entry(page)) {
swap = radix_to_swp_entry(page);
page = NULL;
}
if (sgp != SGP_WRITE && sgp != SGP_FALLOC &&
((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) {
error = -EINVAL;
goto failed;
}
if (page && sgp == SGP_WRITE)
mark_page_accessed(page);
/* fallocated page? */
if (page && !PageUptodate(page)) {
if (sgp != SGP_READ)
goto clear;
unlock_page(page);
page_cache_release(page);
page = NULL;
}
if (page || (sgp == SGP_READ && !swap.val)) {
*pagep = page;
return 0;
}
/*
* Fast cache lookup did not find it:
* bring it back from swap or allocate.
*/
info = SHMEM_I(inode);
sbinfo = SHMEM_SB(inode->i_sb);
if (swap.val) {
/* Look it up and read it in.. */
page = lookup_swap_cache(swap);
if (!page) {
/* here we actually do the io */
if (fault_type)
*fault_type |= VM_FAULT_MAJOR;
page = shmem_swapin(swap, gfp, info, index);
if (!page) {
error = -ENOMEM;
goto failed;
}
}
/* We have to do this with page locked to prevent races */
lock_page(page);
if (!PageSwapCache(page) || page_private(page) != swap.val ||
!shmem_confirm_swap(mapping, index, swap)) {
error = -EEXIST; /* try again */
goto unlock;
}
if (!PageUptodate(page)) {
error = -EIO;
goto failed;
}
wait_on_page_writeback(page);
if (shmem_should_replace_page(page, gfp)) {
error = shmem_replace_page(&page, gfp, info, index);
if (error)
goto failed;
}
error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg);
if (!error) {
error = shmem_add_to_page_cache(page, mapping, index,
swp_to_radix_entry(swap));
/*
* We already confirmed swap under page lock, and make
* no memory allocation here, so usually no possibility
* of error; but free_swap_and_cache() only trylocks a
* page, so it is just possible that the entry has been
* truncated or holepunched since swap was confirmed.
* shmem_undo_range() will have done some of the
* unaccounting, now delete_from_swap_cache() will do
* the rest.
* Reset swap.val? No, leave it so "failed" goes back to
* "repeat": reading a hole and writing should succeed.
*/
if (error) {
mem_cgroup_cancel_charge(page, memcg);
delete_from_swap_cache(page);
}
}
if (error)
goto failed;
mem_cgroup_commit_charge(page, memcg, true);
spin_lock(&info->lock);
info->swapped--;
shmem_recalc_inode(inode);
spin_unlock(&info->lock);
if (sgp == SGP_WRITE)
mark_page_accessed(page);
delete_from_swap_cache(page);
set_page_dirty(page);
swap_free(swap);
} else {
if (shmem_acct_block(info->flags)) {
error = -ENOSPC;
goto failed;
}
if (sbinfo->max_blocks) {
if (percpu_counter_compare(&sbinfo->used_blocks,
sbinfo->max_blocks) >= 0) {
error = -ENOSPC;
goto unacct;
}
percpu_counter_inc(&sbinfo->used_blocks);
}
page = shmem_alloc_page(gfp, info, index);
if (!page) {
error = -ENOMEM;
goto decused;
}
__SetPageSwapBacked(page);
__set_page_locked(page);
if (sgp == SGP_WRITE)
__SetPageReferenced(page);
error = mem_cgroup_try_charge(page, current->mm, gfp, &memcg);
if (error)
goto decused;
error = radix_tree_maybe_preload(gfp & GFP_RECLAIM_MASK);
if (!error) {
error = shmem_add_to_page_cache(page, mapping, index,
NULL);
radix_tree_preload_end();
}
if (error) {
mem_cgroup_cancel_charge(page, memcg);
goto decused;
}
mem_cgroup_commit_charge(page, memcg, false);
lru_cache_add_anon(page);
spin_lock(&info->lock);
info->alloced++;
inode->i_blocks += BLOCKS_PER_PAGE;
shmem_recalc_inode(inode);
spin_unlock(&info->lock);
alloced = true;
/*
* Let SGP_FALLOC use the SGP_WRITE optimization on a new page.
*/
if (sgp == SGP_FALLOC)
sgp = SGP_WRITE;
clear:
/*
* Let SGP_WRITE caller clear ends if write does not fill page;
* but SGP_FALLOC on a page fallocated earlier must initialize
* it now, lest undo on failure cancel our earlier guarantee.
*/
if (sgp != SGP_WRITE) {
clear_highpage(page);
flush_dcache_page(page);
SetPageUptodate(page);
}
if (sgp == SGP_DIRTY)
set_page_dirty(page);
}
/* Perhaps the file has been truncated since we checked */
if (sgp != SGP_WRITE && sgp != SGP_FALLOC &&
((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) {
error = -EINVAL;
if (alloced)
goto trunc;
else
goto failed;
}
*pagep = page;
return 0;
/*
* Error recovery.
*/
trunc:
info = SHMEM_I(inode);
ClearPageDirty(page);
delete_from_page_cache(page);
spin_lock(&info->lock);
info->alloced--;
inode->i_blocks -= BLOCKS_PER_PAGE;
spin_unlock(&info->lock);
decused:
sbinfo = SHMEM_SB(inode->i_sb);
if (sbinfo->max_blocks)
percpu_counter_add(&sbinfo->used_blocks, -1);
unacct:
shmem_unacct_blocks(info->flags, 1);
failed:
if (swap.val && error != -EINVAL &&
!shmem_confirm_swap(mapping, index, swap))
error = -EEXIST;
unlock:
if (page) {
unlock_page(page);
page_cache_release(page);
}
if (error == -ENOSPC && !once++) {
info = SHMEM_I(inode);
spin_lock(&info->lock);
shmem_recalc_inode(inode);
spin_unlock(&info->lock);
goto repeat;
}
if (error == -EEXIST) /* from above or from radix_tree_insert */
goto repeat;
return error;
}
static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct inode *inode = file_inode(vma->vm_file);
int error;
int ret = VM_FAULT_LOCKED;
/*
* Trinity finds that probing a hole which tmpfs is punching can
* prevent the hole-punch from ever completing: which in turn
* locks writers out with its hold on i_mutex. So refrain from
* faulting pages into the hole while it's being punched. Although
* shmem_undo_range() does remove the additions, it may be unable to
* keep up, as each new page needs its own unmap_mapping_range() call,
* and the i_mmap tree grows ever slower to scan if new vmas are added.
*
* It does not matter if we sometimes reach this check just before the
* hole-punch begins, so that one fault then races with the punch:
* we just need to make racing faults a rare case.
*
* The implementation below would be much simpler if we just used a
* standard mutex or completion: but we cannot take i_mutex in fault,
* and bloating every shmem inode for this unlikely case would be sad.
*/
if (unlikely(inode->i_private)) {
struct shmem_falloc *shmem_falloc;
spin_lock(&inode->i_lock);
shmem_falloc = inode->i_private;
if (shmem_falloc &&
shmem_falloc->waitq &&
vmf->pgoff >= shmem_falloc->start &&
vmf->pgoff < shmem_falloc->next) {
wait_queue_head_t *shmem_falloc_waitq;
DEFINE_WAIT(shmem_fault_wait);
ret = VM_FAULT_NOPAGE;
if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) &&
!(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
/* It's polite to up mmap_sem if we can */
up_read(&vma->vm_mm->mmap_sem);
ret = VM_FAULT_RETRY;
}
shmem_falloc_waitq = shmem_falloc->waitq;
prepare_to_wait(shmem_falloc_waitq, &shmem_fault_wait,
TASK_UNINTERRUPTIBLE);
spin_unlock(&inode->i_lock);
schedule();
/*
* shmem_falloc_waitq points into the shmem_fallocate()
* stack of the hole-punching task: shmem_falloc_waitq
* is usually invalid by the time we reach here, but
* finish_wait() does not dereference it in that case;
* though i_lock needed lest racing with wake_up_all().
*/
spin_lock(&inode->i_lock);
finish_wait(shmem_falloc_waitq, &shmem_fault_wait);
spin_unlock(&inode->i_lock);
return ret;
}
spin_unlock(&inode->i_lock);
}
error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret);
if (error)
return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);
if (ret & VM_FAULT_MAJOR) {
count_vm_event(PGMAJFAULT);
mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
}
return ret;
}
#ifdef CONFIG_NUMA
static int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol)
{
struct inode *inode = file_inode(vma->vm_file);
return mpol_set_shared_policy(&SHMEM_I(inode)->policy, vma, mpol);
}
static struct mempolicy *shmem_get_policy(struct vm_area_struct *vma,
unsigned long addr)
{
struct inode *inode = file_inode(vma->vm_file);
pgoff_t index;
index = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
return mpol_shared_policy_lookup(&SHMEM_I(inode)->policy, index);
}
#endif
int shmem_lock(struct file *file, int lock, struct user_struct *user)
{
struct inode *inode = file_inode(file);
struct shmem_inode_info *info = SHMEM_I(inode);
int retval = -ENOMEM;
spin_lock(&info->lock);
if (lock && !(info->flags & VM_LOCKED)) {
if (!user_shm_lock(inode->i_size, user))
goto out_nomem;
info->flags |= VM_LOCKED;
mapping_set_unevictable(file->f_mapping);
}
if (!lock && (info->flags & VM_LOCKED) && user) {
user_shm_unlock(inode->i_size, user);
info->flags &= ~VM_LOCKED;
mapping_clear_unevictable(file->f_mapping);
}
retval = 0;
out_nomem:
spin_unlock(&info->lock);
return retval;
}
static int shmem_mmap(struct file *file, struct vm_area_struct *vma)
{
file_accessed(file);
vma->vm_ops = &shmem_vm_ops;
return 0;
}
static struct inode *shmem_get_inode(struct super_block *sb, const struct inode *dir,
umode_t mode, dev_t dev, unsigned long flags)
{
struct inode *inode;
struct shmem_inode_info *info;
struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
if (shmem_reserve_inode(sb))
return NULL;
inode = new_inode(sb);
if (inode) {
inode->i_ino = get_next_ino();
inode_init_owner(inode, dir, mode);
inode->i_blocks = 0;
inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME;
inode->i_generation = get_seconds();
info = SHMEM_I(inode);
memset(info, 0, (char *)inode - (char *)info);
spin_lock_init(&info->lock);
info->seals = F_SEAL_SEAL;
info->flags = flags & VM_NORESERVE;
INIT_LIST_HEAD(&info->swaplist);
simple_xattrs_init(&info->xattrs);
cache_no_acl(inode);
switch (mode & S_IFMT) {
default:
inode->i_op = &shmem_special_inode_operations;
init_special_inode(inode, mode, dev);
break;
case S_IFREG:
inode->i_mapping->a_ops = &shmem_aops;
inode->i_op = &shmem_inode_operations;
inode->i_fop = &shmem_file_operations;
mpol_shared_policy_init(&info->policy,
shmem_get_sbmpol(sbinfo));
break;
case S_IFDIR:
inc_nlink(inode);
/* Some things misbehave if size == 0 on a directory */
inode->i_size = 2 * BOGO_DIRENT_SIZE;
inode->i_op = &shmem_dir_inode_operations;
inode->i_fop = &simple_dir_operations;
break;
case S_IFLNK:
/*
* Must not load anything in the rbtree,
* mpol_free_shared_policy will not be called.
*/
mpol_shared_policy_init(&info->policy, NULL);
break;
}
} else
shmem_free_inode(sb);
return inode;
}
bool shmem_mapping(struct address_space *mapping)
{
if (!mapping->host)
return false;
return mapping->host->i_sb->s_op == &shmem_ops;
}
#ifdef CONFIG_TMPFS
static const struct inode_operations shmem_symlink_inode_operations;
static const struct inode_operations shmem_short_symlink_operations;
#ifdef CONFIG_TMPFS_XATTR
static int shmem_initxattrs(struct inode *, const struct xattr *, void *);
#else
#define shmem_initxattrs NULL
#endif
static int
shmem_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
struct page **pagep, void **fsdata)
{
struct inode *inode = mapping->host;
struct shmem_inode_info *info = SHMEM_I(inode);
pgoff_t index = pos >> PAGE_CACHE_SHIFT;
/* i_mutex is held by caller */
if (unlikely(info->seals)) {
if (info->seals & F_SEAL_WRITE)
return -EPERM;
if ((info->seals & F_SEAL_GROW) && pos + len > inode->i_size)
return -EPERM;
}
return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL);
}
static int
shmem_write_end(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned copied,
struct page *page, void *fsdata)
{
struct inode *inode = mapping->host;
if (pos + copied > inode->i_size)
i_size_write(inode, pos + copied);
if (!PageUptodate(page)) {
if (copied < PAGE_CACHE_SIZE) {
unsigned from = pos & (PAGE_CACHE_SIZE - 1);
zero_user_segments(page, 0, from,
from + copied, PAGE_CACHE_SIZE);
}
SetPageUptodate(page);
}
set_page_dirty(page);
unlock_page(page);
page_cache_release(page);
return copied;
}
static ssize_t shmem_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
{
struct file *file = iocb->ki_filp;
struct inode *inode = file_inode(file);
struct address_space *mapping = inode->i_mapping;
pgoff_t index;
unsigned long offset;
enum sgp_type sgp = SGP_READ;
int error = 0;
ssize_t retval = 0;
loff_t *ppos = &iocb->ki_pos;
/*
* Might this read be for a stacking filesystem? Then when reading
* holes of a sparse file, we actually need to allocate those pages,
* and even mark them dirty, so it cannot exceed the max_blocks limit.
*/
if (!iter_is_iovec(to))
sgp = SGP_DIRTY;
index = *ppos >> PAGE_CACHE_SHIFT;
offset = *ppos & ~PAGE_CACHE_MASK;
for (;;) {
struct page *page = NULL;
pgoff_t end_index;
unsigned long nr, ret;
loff_t i_size = i_size_read(inode);
end_index = i_size >> PAGE_CACHE_SHIFT;
if (index > end_index)
break;
if (index == end_index) {
nr = i_size & ~PAGE_CACHE_MASK;
if (nr <= offset)
break;
}
error = shmem_getpage(inode, index, &page, sgp, NULL);
if (error) {
if (error == -EINVAL)
error = 0;
break;
}
if (page)
unlock_page(page);
/*
* We must evaluate after, since reads (unlike writes)
* are called without i_mutex protection against truncate
*/
nr = PAGE_CACHE_SIZE;
i_size = i_size_read(inode);
end_index = i_size >> PAGE_CACHE_SHIFT;
if (index == end_index) {
nr = i_size & ~PAGE_CACHE_MASK;
if (nr <= offset) {
if (page)
page_cache_release(page);
break;
}
}
nr -= offset;
if (page) {
/*
* If users can be writing to this page using arbitrary
* virtual addresses, take care about potential aliasing
* before reading the page on the kernel side.
*/
if (mapping_writably_mapped(mapping))
flush_dcache_page(page);
/*
* Mark the page accessed if we read the beginning.
*/
if (!offset)
mark_page_accessed(page);
} else {
page = ZERO_PAGE(0);
page_cache_get(page);
}
/*
* Ok, we have the page, and it's up-to-date, so
* now we can copy it to user space...
*/
ret = copy_page_to_iter(page, offset, nr, to);
retval += ret;
offset += ret;
index += offset >> PAGE_CACHE_SHIFT;
offset &= ~PAGE_CACHE_MASK;
page_cache_release(page);
if (!iov_iter_count(to))
break;
if (ret < nr) {
error = -EFAULT;
break;
}
cond_resched();
}
*ppos = ((loff_t) index << PAGE_CACHE_SHIFT) + offset;
file_accessed(file);
return retval ? retval : error;
}
static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
struct pipe_inode_info *pipe, size_t len,
unsigned int flags)
{
struct address_space *mapping = in->f_mapping;
struct inode *inode = mapping->host;
unsigned int loff, nr_pages, req_pages;
struct page *pages[PIPE_DEF_BUFFERS];
struct partial_page partial[PIPE_DEF_BUFFERS];
struct page *page;
pgoff_t index, end_index;
loff_t isize, left;
int error, page_nr;
struct splice_pipe_desc spd = {
.pages = pages,
.partial = partial,
.nr_pages_max = PIPE_DEF_BUFFERS,
.flags = flags,
.ops = &page_cache_pipe_buf_ops,
.spd_release = spd_release_page,
};
isize = i_size_read(inode);
if (unlikely(*ppos >= isize))
return 0;
left = isize - *ppos;
if (unlikely(left < len))
len = left;
if (splice_grow_spd(pipe, &spd))
return -ENOMEM;
index = *ppos >> PAGE_CACHE_SHIFT;
loff = *ppos & ~PAGE_CACHE_MASK;
req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
nr_pages = min(req_pages, spd.nr_pages_max);
spd.nr_pages = find_get_pages_contig(mapping, index,
nr_pages, spd.pages);
index += spd.nr_pages;
error = 0;
while (spd.nr_pages < nr_pages) {
error = shmem_getpage(inode, index, &page, SGP_CACHE, NULL);
if (error)
break;
unlock_page(page);
spd.pages[spd.nr_pages++] = page;
index++;
}
index = *ppos >> PAGE_CACHE_SHIFT;
nr_pages = spd.nr_pages;
spd.nr_pages = 0;
for (page_nr = 0; page_nr < nr_pages; page_nr++) {
unsigned int this_len;
if (!len)
break;
this_len = min_t(unsigned long, len, PAGE_CACHE_SIZE - loff);
page = spd.pages[page_nr];
if (!PageUptodate(page) || page->mapping != mapping) {
error = shmem_getpage(inode, index, &page,
SGP_CACHE, NULL);
if (error)
break;
unlock_page(page);
page_cache_release(spd.pages[page_nr]);
spd.pages[page_nr] = page;
}
isize = i_size_read(inode);
end_index = (isize - 1) >> PAGE_CACHE_SHIFT;
if (unlikely(!isize || index > end_index))
break;
if (end_index == index) {
unsigned int plen;
plen = ((isize - 1) & ~PAGE_CACHE_MASK) + 1;
if (plen <= loff)
break;
this_len = min(this_len, plen - loff);
len = this_len;
}
spd.partial[page_nr].offset = loff;
spd.partial[page_nr].len = this_len;
len -= this_len;
loff = 0;
spd.nr_pages++;
index++;
}
while (page_nr < nr_pages)
page_cache_release(spd.pages[page_nr++]);
if (spd.nr_pages)
error = splice_to_pipe(pipe, &spd);
splice_shrink_spd(&spd);
if (error > 0) {
*ppos += error;
file_accessed(in);
}
return error;
}
/*
* llseek SEEK_DATA or SEEK_HOLE through the radix_tree.
*/
static pgoff_t shmem_seek_hole_data(struct address_space *mapping,
pgoff_t index, pgoff_t end, int whence)
{
struct page *page;
struct pagevec pvec;
pgoff_t indices[PAGEVEC_SIZE];
bool done = false;
int i;
pagevec_init(&pvec, 0);
pvec.nr = 1; /* start small: we may be there already */
while (!done) {
pvec.nr = find_get_entries(mapping, index,
pvec.nr, pvec.pages, indices);
if (!pvec.nr) {
if (whence == SEEK_DATA)
index = end;
break;
}
for (i = 0; i < pvec.nr; i++, index++) {
if (index < indices[i]) {
if (whence == SEEK_HOLE) {
done = true;
break;
}
index = indices[i];
}
page = pvec.pages[i];
if (page && !radix_tree_exceptional_entry(page)) {
if (!PageUptodate(page))
page = NULL;
}
if (index >= end ||
(page && whence == SEEK_DATA) ||
(!page && whence == SEEK_HOLE)) {
done = true;
break;
}
}
pagevec_remove_exceptionals(&pvec);
pagevec_release(&pvec);
pvec.nr = PAGEVEC_SIZE;
cond_resched();
}
return index;
}
static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence)
{
struct address_space *mapping = file->f_mapping;
struct inode *inode = mapping->host;
pgoff_t start, end;
loff_t new_offset;
if (whence != SEEK_DATA && whence != SEEK_HOLE)
return generic_file_llseek_size(file, offset, whence,
MAX_LFS_FILESIZE, i_size_read(inode));
mutex_lock(&inode->i_mutex);
/* We're holding i_mutex so we can access i_size directly */
if (offset < 0)
offset = -EINVAL;
else if (offset >= inode->i_size)
offset = -ENXIO;
else {
start = offset >> PAGE_CACHE_SHIFT;
end = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
new_offset = shmem_seek_hole_data(mapping, start, end, whence);
new_offset <<= PAGE_CACHE_SHIFT;
if (new_offset > offset) {
if (new_offset < inode->i_size)
offset = new_offset;
else if (whence == SEEK_DATA)
offset = -ENXIO;
else
offset = inode->i_size;
}
}
if (offset >= 0)
offset = vfs_setpos(file, offset, MAX_LFS_FILESIZE);
mutex_unlock(&inode->i_mutex);
return offset;
}
/*
* We need a tag: a new tag would expand every radix_tree_node by 8 bytes,
* so reuse a tag which we firmly believe is never set or cleared on shmem.
*/
#define SHMEM_TAG_PINNED PAGECACHE_TAG_TOWRITE
#define LAST_SCAN 4 /* about 150ms max */
static void shmem_tag_pins(struct address_space *mapping)
{
struct radix_tree_iter iter;
void **slot;
pgoff_t start;
struct page *page;
lru_add_drain();
start = 0;
rcu_read_lock();
restart:
radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) {
page = radix_tree_deref_slot(slot);
if (!page || radix_tree_exception(page)) {
if (radix_tree_deref_retry(page))
goto restart;
} else if (page_count(page) - page_mapcount(page) > 1) {
spin_lock_irq(&mapping->tree_lock);
radix_tree_tag_set(&mapping->page_tree, iter.index,
SHMEM_TAG_PINNED);
spin_unlock_irq(&mapping->tree_lock);
}
if (need_resched()) {
cond_resched_rcu();
start = iter.index + 1;
goto restart;
}
}
rcu_read_unlock();
}
/*
* Setting SEAL_WRITE requires us to verify there's no pending writer. However,
* via get_user_pages(), drivers might have some pending I/O without any active
* user-space mappings (eg., direct-IO, AIO). Therefore, we look at all pages
* and see whether it has an elevated ref-count. If so, we tag them and wait for
* them to be dropped.
* The caller must guarantee that no new user will acquire writable references
* to those pages to avoid races.
*/
static int shmem_wait_for_pins(struct address_space *mapping)
{
struct radix_tree_iter iter;
void **slot;
pgoff_t start;
struct page *page;
int error, scan;
shmem_tag_pins(mapping);
error = 0;
for (scan = 0; scan <= LAST_SCAN; scan++) {
if (!radix_tree_tagged(&mapping->page_tree, SHMEM_TAG_PINNED))
break;
if (!scan)
lru_add_drain_all();
else if (schedule_timeout_killable((HZ << scan) / 200))
scan = LAST_SCAN;
start = 0;
rcu_read_lock();
restart:
radix_tree_for_each_tagged(slot, &mapping->page_tree, &iter,
start, SHMEM_TAG_PINNED) {
page = radix_tree_deref_slot(slot);
if (radix_tree_exception(page)) {
if (radix_tree_deref_retry(page))
goto restart;
page = NULL;
}
if (page &&
page_count(page) - page_mapcount(page) != 1) {
if (scan < LAST_SCAN)
goto continue_resched;
/*
* On the last scan, we clean up all those tags
* we inserted; but make a note that we still
* found pages pinned.
*/
error = -EBUSY;
}
spin_lock_irq(&mapping->tree_lock);
radix_tree_tag_clear(&mapping->page_tree,
iter.index, SHMEM_TAG_PINNED);
spin_unlock_irq(&mapping->tree_lock);
continue_resched:
if (need_resched()) {
cond_resched_rcu();
start = iter.index + 1;
goto restart;
}
}
rcu_read_unlock();
}
return error;
}
#define F_ALL_SEALS (F_SEAL_SEAL | \
F_SEAL_SHRINK | \
F_SEAL_GROW | \
F_SEAL_WRITE)
int shmem_add_seals(struct file *file, unsigned int seals)
{
struct inode *inode = file_inode(file);
struct shmem_inode_info *info = SHMEM_I(inode);
int error;
/*
* SEALING
* Sealing allows multiple parties to share a shmem-file but restrict
* access to a specific subset of file operations. Seals can only be
* added, but never removed. This way, mutually untrusted parties can
* share common memory regions with a well-defined policy. A malicious
* peer can thus never perform unwanted operations on a shared object.
*
* Seals are only supported on special shmem-files and always affect
* the whole underlying inode. Once a seal is set, it may prevent some
* kinds of access to the file. Currently, the following seals are
* defined:
* SEAL_SEAL: Prevent further seals from being set on this file
* SEAL_SHRINK: Prevent the file from shrinking
* SEAL_GROW: Prevent the file from growing
* SEAL_WRITE: Prevent write access to the file
*
* As we don't require any trust relationship between two parties, we
* must prevent seals from being removed. Therefore, sealing a file
* only adds a given set of seals to the file, it never touches
* existing seals. Furthermore, the "setting seals"-operation can be
* sealed itself, which basically prevents any further seal from being
* added.
*
* Semantics of sealing are only defined on volatile files. Only
* anonymous shmem files support sealing. More importantly, seals are
* never written to disk. Therefore, there's no plan to support it on
* other file types.
*/
if (file->f_op != &shmem_file_operations)
return -EINVAL;
if (!(file->f_mode & FMODE_WRITE))
return -EPERM;
if (seals & ~(unsigned int)F_ALL_SEALS)
return -EINVAL;
mutex_lock(&inode->i_mutex);
if (info->seals & F_SEAL_SEAL) {
error = -EPERM;
goto unlock;
}
if ((seals & F_SEAL_WRITE) && !(info->seals & F_SEAL_WRITE)) {
error = mapping_deny_writable(file->f_mapping);
if (error)
goto unlock;
error = shmem_wait_for_pins(file->f_mapping);
if (error) {
mapping_allow_writable(file->f_mapping);
goto unlock;
}
}
info->seals |= seals;
error = 0;
unlock:
mutex_unlock(&inode->i_mutex);
return error;
}
EXPORT_SYMBOL_GPL(shmem_add_seals);
int shmem_get_seals(struct file *file)
{
if (file->f_op != &shmem_file_operations)
return -EINVAL;
return SHMEM_I(file_inode(file))->seals;
}
EXPORT_SYMBOL_GPL(shmem_get_seals);
long shmem_fcntl(struct file *file, unsigned int cmd, unsigned long arg)
{
long error;
switch (cmd) {
case F_ADD_SEALS:
/* disallow upper 32bit */
if (arg > UINT_MAX)
return -EINVAL;
error = shmem_add_seals(file, arg);
break;
case F_GET_SEALS:
error = shmem_get_seals(file);
break;
default:
error = -EINVAL;
break;
}
return error;
}
static long shmem_fallocate(struct file *file, int mode, loff_t offset,
loff_t len)
{
struct inode *inode = file_inode(file);
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
struct shmem_inode_info *info = SHMEM_I(inode);
struct shmem_falloc shmem_falloc;
pgoff_t start, index, end;
int error;
if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE))
return -EOPNOTSUPP;
mutex_lock(&inode->i_mutex);
if (mode & FALLOC_FL_PUNCH_HOLE) {
struct address_space *mapping = file->f_mapping;
loff_t unmap_start = round_up(offset, PAGE_SIZE);
loff_t unmap_end = round_down(offset + len, PAGE_SIZE) - 1;
DECLARE_WAIT_QUEUE_HEAD_ONSTACK(shmem_falloc_waitq);
/* protected by i_mutex */
if (info->seals & F_SEAL_WRITE) {
error = -EPERM;
goto out;
}
shmem_falloc.waitq = &shmem_falloc_waitq;
shmem_falloc.start = unmap_start >> PAGE_SHIFT;
shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT;
spin_lock(&inode->i_lock);
inode->i_private = &shmem_falloc;
spin_unlock(&inode->i_lock);
if ((u64)unmap_end > (u64)unmap_start)
unmap_mapping_range(mapping, unmap_start,
1 + unmap_end - unmap_start, 0);
shmem_truncate_range(inode, offset, offset + len - 1);
/* No need to unmap again: hole-punching leaves COWed pages */
spin_lock(&inode->i_lock);
inode->i_private = NULL;
wake_up_all(&shmem_falloc_waitq);
spin_unlock(&inode->i_lock);
error = 0;
goto out;
}
/* We need to check rlimit even when FALLOC_FL_KEEP_SIZE */
error = inode_newsize_ok(inode, offset + len);
if (error)
goto out;
if ((info->seals & F_SEAL_GROW) && offset + len > inode->i_size) {
error = -EPERM;
goto out;
}
start = offset >> PAGE_CACHE_SHIFT;
end = (offset + len + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
/* Try to avoid a swapstorm if len is impossible to satisfy */
if (sbinfo->max_blocks && end - start > sbinfo->max_blocks) {
error = -ENOSPC;
goto out;
}
shmem_falloc.waitq = NULL;
shmem_falloc.start = start;
shmem_falloc.next = start;
shmem_falloc.nr_falloced = 0;
shmem_falloc.nr_unswapped = 0;
spin_lock(&inode->i_lock);
inode->i_private = &shmem_falloc;
spin_unlock(&inode->i_lock);
for (index = start; index < end; index++) {
struct page *page;
/*
* Good, the fallocate(2) manpage permits EINTR: we may have
* been interrupted because we are using up too much memory.
*/
if (signal_pending(current))
error = -EINTR;
else if (shmem_falloc.nr_unswapped > shmem_falloc.nr_falloced)
error = -ENOMEM;
else
error = shmem_getpage(inode, index, &page, SGP_FALLOC,
NULL);
if (error) {
/* Remove the !PageUptodate pages we added */
shmem_undo_range(inode,
(loff_t)start << PAGE_CACHE_SHIFT,
(loff_t)index << PAGE_CACHE_SHIFT, true);
goto undone;
}
/*
* Inform shmem_writepage() how far we have reached.
* No need for lock or barrier: we have the page lock.
*/
shmem_falloc.next++;
if (!PageUptodate(page))
shmem_falloc.nr_falloced++;
/*
* If !PageUptodate, leave it that way so that freeable pages
* can be recognized if we need to rollback on error later.
* But set_page_dirty so that memory pressure will swap rather
* than free the pages we are allocating (and SGP_CACHE pages
* might still be clean: we now need to mark those dirty too).
*/
set_page_dirty(page);
unlock_page(page);
page_cache_release(page);
cond_resched();
}
if (!(mode & FALLOC_FL_KEEP_SIZE) && offset + len > inode->i_size)
i_size_write(inode, offset + len);
inode->i_ctime = CURRENT_TIME;
undone:
spin_lock(&inode->i_lock);
inode->i_private = NULL;
spin_unlock(&inode->i_lock);
out:
mutex_unlock(&inode->i_mutex);
return error;
}
static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct shmem_sb_info *sbinfo = SHMEM_SB(dentry->d_sb);
buf->f_type = TMPFS_MAGIC;
buf->f_bsize = PAGE_CACHE_SIZE;
buf->f_namelen = NAME_MAX;
if (sbinfo->max_blocks) {
buf->f_blocks = sbinfo->max_blocks;
buf->f_bavail =
buf->f_bfree = sbinfo->max_blocks -
percpu_counter_sum(&sbinfo->used_blocks);
}
if (sbinfo->max_inodes) {
buf->f_files = sbinfo->max_inodes;
buf->f_ffree = sbinfo->free_inodes;
}
/* else leave those fields 0 like simple_statfs */
return 0;
}
/*
* File creation. Allocate an inode, and we're done..
*/
static int
shmem_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev)
{
struct inode *inode;
int error = -ENOSPC;
inode = shmem_get_inode(dir->i_sb, dir, mode, dev, VM_NORESERVE);
if (inode) {
error = simple_acl_create(dir, inode);
if (error)
goto out_iput;
error = security_inode_init_security(inode, dir,
&dentry->d_name,
shmem_initxattrs, NULL);
if (error && error != -EOPNOTSUPP)
goto out_iput;
error = 0;
dir->i_size += BOGO_DIRENT_SIZE;
dir->i_ctime = dir->i_mtime = CURRENT_TIME;
d_instantiate(dentry, inode);
dget(dentry); /* Extra count - pin the dentry in core */
}
return error;
out_iput:
iput(inode);
return error;
}
static int
shmem_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
{
struct inode *inode;
int error = -ENOSPC;
inode = shmem_get_inode(dir->i_sb, dir, mode, 0, VM_NORESERVE);
if (inode) {
error = security_inode_init_security(inode, dir,
NULL,
shmem_initxattrs, NULL);
if (error && error != -EOPNOTSUPP)
goto out_iput;
error = simple_acl_create(dir, inode);
if (error)
goto out_iput;
d_tmpfile(dentry, inode);
}
return error;
out_iput:
iput(inode);
return error;
}
static int shmem_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
{
int error;
if ((error = shmem_mknod(dir, dentry, mode | S_IFDIR, 0)))
return error;
inc_nlink(dir);
return 0;
}
static int shmem_create(struct inode *dir, struct dentry *dentry, umode_t mode,
bool excl)
{
return shmem_mknod(dir, dentry, mode | S_IFREG, 0);
}
/*
* Link a file..
*/
static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
{
struct inode *inode = d_inode(old_dentry);
int ret;
/*
* No ordinary (disk based) filesystem counts links as inodes;
* but each new link needs a new dentry, pinning lowmem, and
* tmpfs dentries cannot be pruned until they are unlinked.
*/
ret = shmem_reserve_inode(inode->i_sb);
if (ret)
goto out;
dir->i_size += BOGO_DIRENT_SIZE;
inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
inc_nlink(inode);
ihold(inode); /* New dentry reference */
dget(dentry); /* Extra pinning count for the created dentry */
d_instantiate(dentry, inode);
out:
return ret;
}
static int shmem_unlink(struct inode *dir, struct dentry *dentry)
{
struct inode *inode = d_inode(dentry);
if (inode->i_nlink > 1 && !S_ISDIR(inode->i_mode))
shmem_free_inode(inode->i_sb);
dir->i_size -= BOGO_DIRENT_SIZE;
inode->i_ctime = dir->i_ctime = dir->i_mtime = CURRENT_TIME;
drop_nlink(inode);
dput(dentry); /* Undo the count from "create" - this does all the work */
return 0;
}
static int shmem_rmdir(struct inode *dir, struct dentry *dentry)
{
if (!simple_empty(dentry))
return -ENOTEMPTY;
drop_nlink(d_inode(dentry));
drop_nlink(dir);
return shmem_unlink(dir, dentry);
}
static int shmem_exchange(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry)
{
bool old_is_dir = d_is_dir(old_dentry);
bool new_is_dir = d_is_dir(new_dentry);
if (old_dir != new_dir && old_is_dir != new_is_dir) {
if (old_is_dir) {
drop_nlink(old_dir);
inc_nlink(new_dir);
} else {
drop_nlink(new_dir);
inc_nlink(old_dir);
}
}
old_dir->i_ctime = old_dir->i_mtime =
new_dir->i_ctime = new_dir->i_mtime =
d_inode(old_dentry)->i_ctime =
d_inode(new_dentry)->i_ctime = CURRENT_TIME;
return 0;
}
static int shmem_whiteout(struct inode *old_dir, struct dentry *old_dentry)
{
struct dentry *whiteout;
int error;
whiteout = d_alloc(old_dentry->d_parent, &old_dentry->d_name);
if (!whiteout)
return -ENOMEM;
error = shmem_mknod(old_dir, whiteout,
S_IFCHR | WHITEOUT_MODE, WHITEOUT_DEV);
dput(whiteout);
if (error)
return error;
/*
* Cheat and hash the whiteout while the old dentry is still in
* place, instead of playing games with FS_RENAME_DOES_D_MOVE.
*
* d_lookup() will consistently find one of them at this point,
* not sure which one, but that isn't even important.
*/
d_rehash(whiteout);
return 0;
}
/*
* The VFS layer already does all the dentry stuff for rename,
* we just have to decrement the usage count for the target if
* it exists so that the VFS layer correctly free's it when it
* gets overwritten.
*/
static int shmem_rename2(struct inode *old_dir, struct dentry *old_dentry, struct inode *new_dir, struct dentry *new_dentry, unsigned int flags)
{
struct inode *inode = d_inode(old_dentry);
int they_are_dirs = S_ISDIR(inode->i_mode);
if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
return -EINVAL;
if (flags & RENAME_EXCHANGE)
return shmem_exchange(old_dir, old_dentry, new_dir, new_dentry);
if (!simple_empty(new_dentry))
return -ENOTEMPTY;
if (flags & RENAME_WHITEOUT) {
int error;
error = shmem_whiteout(old_dir, old_dentry);
if (error)
return error;
}
if (d_really_is_positive(new_dentry)) {
(void) shmem_unlink(new_dir, new_dentry);
if (they_are_dirs) {
drop_nlink(d_inode(new_dentry));
drop_nlink(old_dir);
}
} else if (they_are_dirs) {
drop_nlink(old_dir);
inc_nlink(new_dir);
}
old_dir->i_size -= BOGO_DIRENT_SIZE;
new_dir->i_size += BOGO_DIRENT_SIZE;
old_dir->i_ctime = old_dir->i_mtime =
new_dir->i_ctime = new_dir->i_mtime =
inode->i_ctime = CURRENT_TIME;
return 0;
}
static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
{
int error;
int len;
struct inode *inode;
struct page *page;
char *kaddr;
struct shmem_inode_info *info;
len = strlen(symname) + 1;
if (len > PAGE_CACHE_SIZE)
return -ENAMETOOLONG;
inode = shmem_get_inode(dir->i_sb, dir, S_IFLNK|S_IRWXUGO, 0, VM_NORESERVE);
if (!inode)
return -ENOSPC;
error = security_inode_init_security(inode, dir, &dentry->d_name,
shmem_initxattrs, NULL);
if (error) {
if (error != -EOPNOTSUPP) {
iput(inode);
return error;
}
error = 0;
}
info = SHMEM_I(inode);
inode->i_size = len-1;
if (len <= SHORT_SYMLINK_LEN) {
info->symlink = kmemdup(symname, len, GFP_KERNEL);
if (!info->symlink) {
iput(inode);
return -ENOMEM;
}
inode->i_op = &shmem_short_symlink_operations;
inode->i_link = info->symlink;
} else {
error = shmem_getpage(inode, 0, &page, SGP_WRITE, NULL);
if (error) {
iput(inode);
return error;
}
inode->i_mapping->a_ops = &shmem_aops;
inode->i_op = &shmem_symlink_inode_operations;
kaddr = kmap_atomic(page);
memcpy(kaddr, symname, len);
kunmap_atomic(kaddr);
SetPageUptodate(page);
set_page_dirty(page);
unlock_page(page);
page_cache_release(page);
}
dir->i_size += BOGO_DIRENT_SIZE;
dir->i_ctime = dir->i_mtime = CURRENT_TIME;
d_instantiate(dentry, inode);
dget(dentry);
return 0;
}
static const char *shmem_follow_link(struct dentry *dentry, void **cookie)
{
struct page *page = NULL;
int error = shmem_getpage(d_inode(dentry), 0, &page, SGP_READ, NULL);
if (error)
return ERR_PTR(error);
unlock_page(page);
*cookie = page;
return kmap(page);
}
static void shmem_put_link(struct inode *unused, void *cookie)
{
struct page *page = cookie;
kunmap(page);
mark_page_accessed(page);
page_cache_release(page);
}
#ifdef CONFIG_TMPFS_XATTR
/*
* Superblocks without xattr inode operations may get some security.* xattr
* support from the LSM "for free". As soon as we have any other xattrs
* like ACLs, we also need to implement the security.* handlers at
* filesystem level, though.
*/
/*
* Callback for security_inode_init_security() for acquiring xattrs.
*/
static int shmem_initxattrs(struct inode *inode,
const struct xattr *xattr_array,
void *fs_info)
{
struct shmem_inode_info *info = SHMEM_I(inode);
const struct xattr *xattr;
struct simple_xattr *new_xattr;
size_t len;
for (xattr = xattr_array; xattr->name != NULL; xattr++) {
new_xattr = simple_xattr_alloc(xattr->value, xattr->value_len);
if (!new_xattr)
return -ENOMEM;
len = strlen(xattr->name) + 1;
new_xattr->name = kmalloc(XATTR_SECURITY_PREFIX_LEN + len,
GFP_KERNEL);
if (!new_xattr->name) {
kfree(new_xattr);
return -ENOMEM;
}
memcpy(new_xattr->name, XATTR_SECURITY_PREFIX,
XATTR_SECURITY_PREFIX_LEN);
memcpy(new_xattr->name + XATTR_SECURITY_PREFIX_LEN,
xattr->name, len);
simple_xattr_list_add(&info->xattrs, new_xattr);
}
return 0;
}
static const struct xattr_handler *shmem_xattr_handlers[] = {
#ifdef CONFIG_TMPFS_POSIX_ACL
&posix_acl_access_xattr_handler,
&posix_acl_default_xattr_handler,
#endif
NULL
};
static int shmem_xattr_validate(const char *name)
{
struct { const char *prefix; size_t len; } arr[] = {
{ XATTR_SECURITY_PREFIX, XATTR_SECURITY_PREFIX_LEN },
{ XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN }
};
int i;
for (i = 0; i < ARRAY_SIZE(arr); i++) {
size_t preflen = arr[i].len;
if (strncmp(name, arr[i].prefix, preflen) == 0) {
if (!name[preflen])
return -EINVAL;
return 0;
}
}
return -EOPNOTSUPP;
}
static ssize_t shmem_getxattr(struct dentry *dentry, const char *name,
void *buffer, size_t size)
{
struct shmem_inode_info *info = SHMEM_I(d_inode(dentry));
int err;
/*
* If this is a request for a synthetic attribute in the system.*
* namespace use the generic infrastructure to resolve a handler
* for it via sb->s_xattr.
*/
if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
return generic_getxattr(dentry, name, buffer, size);
err = shmem_xattr_validate(name);
if (err)
return err;
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(d_inode(dentry));
int err;
/*
* If this is a request for a synthetic attribute in the system.*
* namespace use the generic infrastructure to resolve a handler
* for it via sb->s_xattr.
*/
if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
return generic_setxattr(dentry, name, value, size, flags);
err = shmem_xattr_validate(name);
if (err)
return err;
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(d_inode(dentry));
int err;
/*
* If this is a request for a synthetic attribute in the system.*
* namespace use the generic infrastructure to resolve a handler
* for it via sb->s_xattr.
*/
if (!strncmp(name, XATTR_SYSTEM_PREFIX, XATTR_SYSTEM_PREFIX_LEN))
return generic_removexattr(dentry, name);
err = shmem_xattr_validate(name);
if (err)
return err;
return simple_xattr_remove(&info->xattrs, name);
}
static ssize_t shmem_listxattr(struct dentry *dentry, char *buffer, size_t size)
{
struct shmem_inode_info *info = SHMEM_I(d_inode(dentry));
return simple_xattr_list(&info->xattrs, buffer, size);
}
#endif /* CONFIG_TMPFS_XATTR */
static const struct inode_operations shmem_short_symlink_operations = {
.readlink = generic_readlink,
.follow_link = simple_follow_link,
#ifdef CONFIG_TMPFS_XATTR
.setxattr = shmem_setxattr,
.getxattr = shmem_getxattr,
.listxattr = shmem_listxattr,
.removexattr = shmem_removexattr,
#endif
};
static const struct inode_operations shmem_symlink_inode_operations = {
.readlink = generic_readlink,
.follow_link = shmem_follow_link,
.put_link = shmem_put_link,
#ifdef CONFIG_TMPFS_XATTR
.setxattr = shmem_setxattr,
.getxattr = shmem_getxattr,
.listxattr = shmem_listxattr,
.removexattr = shmem_removexattr,
#endif
};
static struct dentry *shmem_get_parent(struct dentry *child)
{
return ERR_PTR(-ESTALE);
}
static int shmem_match(struct inode *ino, void *vfh)
{
__u32 *fh = vfh;
__u64 inum = fh[2];
inum = (inum << 32) | fh[1];
return ino->i_ino == inum && fh[0] == ino->i_generation;
}
static struct dentry *shmem_fh_to_dentry(struct super_block *sb,
struct fid *fid, int fh_len, int fh_type)
{
struct inode *inode;
struct dentry *dentry = NULL;
u64 inum;
if (fh_len < 3)
return NULL;
inum = fid->raw[2];
inum = (inum << 32) | fid->raw[1];
inode = ilookup5(sb, (unsigned long)(inum + fid->raw[0]),
shmem_match, fid->raw);
if (inode) {
dentry = d_find_alias(inode);
iput(inode);
}
return dentry;
}
static int shmem_encode_fh(struct inode *inode, __u32 *fh, int *len,
struct inode *parent)
{
if (*len < 3) {
*len = 3;
return FILEID_INVALID;
}
if (inode_unhashed(inode)) {
/* Unfortunately insert_inode_hash is not idempotent,
* so as we hash inodes here rather than at creation
* time, we need a lock to ensure we only try
* to do it once
*/
static DEFINE_SPINLOCK(lock);
spin_lock(&lock);
if (inode_unhashed(inode))
__insert_inode_hash(inode,
inode->i_ino + inode->i_generation);
spin_unlock(&lock);
}
fh[0] = inode->i_generation;
fh[1] = inode->i_ino;
fh[2] = ((__u64)inode->i_ino) >> 32;
*len = 3;
return 1;
}
static const struct export_operations shmem_export_ops = {
.get_parent = shmem_get_parent,
.encode_fh = shmem_encode_fh,
.fh_to_dentry = shmem_fh_to_dentry,
};
static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo,
bool remount)
{
char *this_char, *value, *rest;
struct mempolicy *mpol = NULL;
uid_t uid;
gid_t gid;
while (options != NULL) {
this_char = options;
for (;;) {
/*
* NUL-terminate this option: unfortunately,
* mount options form a comma-separated list,
* but mpol's nodelist may also contain commas.
*/
options = strchr(options, ',');
if (options == NULL)
break;
options++;
if (!isdigit(*options)) {
options[-1] = '\0';
break;
}
}
if (!*this_char)
continue;
if ((value = strchr(this_char,'=')) != NULL) {
*value++ = 0;
} else {
printk(KERN_ERR
"tmpfs: No value for mount option '%s'\n",
this_char);
goto error;
}
if (!strcmp(this_char,"size")) {
unsigned long long size;
size = memparse(value,&rest);
if (*rest == '%') {
size <<= PAGE_SHIFT;
size *= totalram_pages;
do_div(size, 100);
rest++;
}
if (*rest)
goto bad_val;
sbinfo->max_blocks =
DIV_ROUND_UP(size, PAGE_CACHE_SIZE);
} else if (!strcmp(this_char,"nr_blocks")) {
sbinfo->max_blocks = memparse(value, &rest);
if (*rest)
goto bad_val;
} else if (!strcmp(this_char,"nr_inodes")) {
sbinfo->max_inodes = memparse(value, &rest);
if (*rest)
goto bad_val;
} else if (!strcmp(this_char,"mode")) {
if (remount)
continue;
sbinfo->mode = simple_strtoul(value, &rest, 8) & 07777;
if (*rest)
goto bad_val;
} else if (!strcmp(this_char,"uid")) {
if (remount)
continue;
uid = simple_strtoul(value, &rest, 0);
if (*rest)
goto bad_val;
sbinfo->uid = make_kuid(current_user_ns(), uid);
if (!uid_valid(sbinfo->uid))
goto bad_val;
} else if (!strcmp(this_char,"gid")) {
if (remount)
continue;
gid = simple_strtoul(value, &rest, 0);
if (*rest)
goto bad_val;
sbinfo->gid = make_kgid(current_user_ns(), gid);
if (!gid_valid(sbinfo->gid))
goto bad_val;
} else if (!strcmp(this_char,"mpol")) {
mpol_put(mpol);
mpol = NULL;
if (mpol_parse_str(value, &mpol))
goto bad_val;
} else {
printk(KERN_ERR "tmpfs: Bad mount option %s\n",
this_char);
goto error;
}
}
sbinfo->mpol = mpol;
return 0;
bad_val:
printk(KERN_ERR "tmpfs: Bad value '%s' for mount option '%s'\n",
value, this_char);
error:
mpol_put(mpol);
return 1;
}
static int shmem_remount_fs(struct super_block *sb, int *flags, char *data)
{
struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
struct shmem_sb_info config = *sbinfo;
unsigned long inodes;
int error = -EINVAL;
config.mpol = NULL;
if (shmem_parse_options(data, &config, true))
return error;
spin_lock(&sbinfo->stat_lock);
inodes = sbinfo->max_inodes - sbinfo->free_inodes;
if (percpu_counter_compare(&sbinfo->used_blocks, config.max_blocks) > 0)
goto out;
if (config.max_inodes < inodes)
goto out;
/*
* Those tests disallow limited->unlimited while any are in use;
* but we must separately disallow unlimited->limited, because
* in that case we have no record of how much is already in use.
*/
if (config.max_blocks && !sbinfo->max_blocks)
goto out;
if (config.max_inodes && !sbinfo->max_inodes)
goto out;
error = 0;
sbinfo->max_blocks = config.max_blocks;
sbinfo->max_inodes = config.max_inodes;
sbinfo->free_inodes = config.max_inodes - inodes;
/*
* Preserve previous mempolicy unless mpol remount option was specified.
*/
if (config.mpol) {
mpol_put(sbinfo->mpol);
sbinfo->mpol = config.mpol; /* transfers initial ref */
}
out:
spin_unlock(&sbinfo->stat_lock);
return error;
}
static int shmem_show_options(struct seq_file *seq, struct dentry *root)
{
struct shmem_sb_info *sbinfo = SHMEM_SB(root->d_sb);
if (sbinfo->max_blocks != shmem_default_max_blocks())
seq_printf(seq, ",size=%luk",
sbinfo->max_blocks << (PAGE_CACHE_SHIFT - 10));
if (sbinfo->max_inodes != shmem_default_max_inodes())
seq_printf(seq, ",nr_inodes=%lu", sbinfo->max_inodes);
if (sbinfo->mode != (S_IRWXUGO | S_ISVTX))
seq_printf(seq, ",mode=%03ho", sbinfo->mode);
if (!uid_eq(sbinfo->uid, GLOBAL_ROOT_UID))
seq_printf(seq, ",uid=%u",
from_kuid_munged(&init_user_ns, sbinfo->uid));
if (!gid_eq(sbinfo->gid, GLOBAL_ROOT_GID))
seq_printf(seq, ",gid=%u",
from_kgid_munged(&init_user_ns, sbinfo->gid));
shmem_show_mpol(seq, sbinfo->mpol);
return 0;
}
#define MFD_NAME_PREFIX "memfd:"
#define MFD_NAME_PREFIX_LEN (sizeof(MFD_NAME_PREFIX) - 1)
#define MFD_NAME_MAX_LEN (NAME_MAX - MFD_NAME_PREFIX_LEN)
#define MFD_ALL_FLAGS (MFD_CLOEXEC | MFD_ALLOW_SEALING)
SYSCALL_DEFINE2(memfd_create,
const char __user *, uname,
unsigned int, flags)
{
struct shmem_inode_info *info;
struct file *file;
int fd, error;
char *name;
long len;
if (flags & ~(unsigned int)MFD_ALL_FLAGS)
return -EINVAL;
/* length includes terminating zero */
len = strnlen_user(uname, MFD_NAME_MAX_LEN + 1);
if (len <= 0)
return -EFAULT;
if (len > MFD_NAME_MAX_LEN + 1)
return -EINVAL;
name = kmalloc(len + MFD_NAME_PREFIX_LEN, GFP_TEMPORARY);
if (!name)
return -ENOMEM;
strcpy(name, MFD_NAME_PREFIX);
if (copy_from_user(&name[MFD_NAME_PREFIX_LEN], uname, len)) {
error = -EFAULT;
goto err_name;
}
/* terminating-zero may have changed after strnlen_user() returned */
if (name[len + MFD_NAME_PREFIX_LEN - 1]) {
error = -EFAULT;
goto err_name;
}
fd = get_unused_fd_flags((flags & MFD_CLOEXEC) ? O_CLOEXEC : 0);
if (fd < 0) {
error = fd;
goto err_name;
}
file = shmem_file_setup(name, 0, VM_NORESERVE);
if (IS_ERR(file)) {
error = PTR_ERR(file);
goto err_fd;
}
info = SHMEM_I(file_inode(file));
file->f_mode |= FMODE_LSEEK | FMODE_PREAD | FMODE_PWRITE;
file->f_flags |= O_RDWR | O_LARGEFILE;
if (flags & MFD_ALLOW_SEALING)
info->seals &= ~F_SEAL_SEAL;
fd_install(fd, file);
kfree(name);
return fd;
err_fd:
put_unused_fd(fd);
err_name:
kfree(name);
return error;
}
#endif /* CONFIG_TMPFS */
static void shmem_put_super(struct super_block *sb)
{
struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
percpu_counter_destroy(&sbinfo->used_blocks);
mpol_put(sbinfo->mpol);
kfree(sbinfo);
sb->s_fs_info = NULL;
}
int shmem_fill_super(struct super_block *sb, void *data, int silent)
{
struct inode *inode;
struct shmem_sb_info *sbinfo;
int err = -ENOMEM;
/* Round up to L1_CACHE_BYTES to resist false sharing */
sbinfo = kzalloc(max((int)sizeof(struct shmem_sb_info),
L1_CACHE_BYTES), GFP_KERNEL);
if (!sbinfo)
return -ENOMEM;
sbinfo->mode = S_IRWXUGO | S_ISVTX;
sbinfo->uid = current_fsuid();
sbinfo->gid = current_fsgid();
sb->s_fs_info = sbinfo;
#ifdef CONFIG_TMPFS
/*
* Per default we only allow half of the physical ram per
* tmpfs instance, limiting inodes to one per page of lowmem;
* but the internal instance is left unlimited.
*/
if (!(sb->s_flags & MS_KERNMOUNT)) {
sbinfo->max_blocks = shmem_default_max_blocks();
sbinfo->max_inodes = shmem_default_max_inodes();
if (shmem_parse_options(data, sbinfo, false)) {
err = -EINVAL;
goto failed;
}
} else {
sb->s_flags |= MS_NOUSER;
}
sb->s_export_op = &shmem_export_ops;
sb->s_flags |= MS_NOSEC;
#else
sb->s_flags |= MS_NOUSER;
#endif
spin_lock_init(&sbinfo->stat_lock);
if (percpu_counter_init(&sbinfo->used_blocks, 0, GFP_KERNEL))
goto failed;
sbinfo->free_inodes = sbinfo->max_inodes;
sb->s_maxbytes = MAX_LFS_FILESIZE;
sb->s_blocksize = PAGE_CACHE_SIZE;
sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
sb->s_magic = TMPFS_MAGIC;
sb->s_op = &shmem_ops;
sb->s_time_gran = 1;
#ifdef CONFIG_TMPFS_XATTR
sb->s_xattr = shmem_xattr_handlers;
#endif
#ifdef CONFIG_TMPFS_POSIX_ACL
sb->s_flags |= MS_POSIXACL;
#endif
inode = shmem_get_inode(sb, NULL, S_IFDIR | sbinfo->mode, 0, VM_NORESERVE);
if (!inode)
goto failed;
inode->i_uid = sbinfo->uid;
inode->i_gid = sbinfo->gid;
sb->s_root = d_make_root(inode);
if (!sb->s_root)
goto failed;
return 0;
failed:
shmem_put_super(sb);
return err;
}
static struct kmem_cache *shmem_inode_cachep;
static struct inode *shmem_alloc_inode(struct super_block *sb)
{
struct shmem_inode_info *info;
info = kmem_cache_alloc(shmem_inode_cachep, GFP_KERNEL);
if (!info)
return NULL;
return &info->vfs_inode;
}
static void shmem_destroy_callback(struct rcu_head *head)
{
struct inode *inode = container_of(head, struct inode, i_rcu);
kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode));
}
static void shmem_destroy_inode(struct inode *inode)
{
if (S_ISREG(inode->i_mode))
mpol_free_shared_policy(&SHMEM_I(inode)->policy);
call_rcu(&inode->i_rcu, shmem_destroy_callback);
}
static void shmem_init_inode(void *foo)
{
struct shmem_inode_info *info = foo;
inode_init_once(&info->vfs_inode);
}
static int shmem_init_inodecache(void)
{
shmem_inode_cachep = kmem_cache_create("shmem_inode_cache",
sizeof(struct shmem_inode_info),
0, SLAB_PANIC, shmem_init_inode);
return 0;
}
static void shmem_destroy_inodecache(void)
{
kmem_cache_destroy(shmem_inode_cachep);
}
static const struct address_space_operations shmem_aops = {
.writepage = shmem_writepage,
.set_page_dirty = __set_page_dirty_no_writeback,
#ifdef CONFIG_TMPFS
.write_begin = shmem_write_begin,
.write_end = shmem_write_end,
#endif
#ifdef CONFIG_MIGRATION
.migratepage = migrate_page,
#endif
.error_remove_page = generic_error_remove_page,
};
static const struct file_operations shmem_file_operations = {
.mmap = shmem_mmap,
#ifdef CONFIG_TMPFS
.llseek = shmem_file_llseek,
.read_iter = shmem_file_read_iter,
.write_iter = generic_file_write_iter,
.fsync = noop_fsync,
.splice_read = shmem_file_splice_read,
.splice_write = iter_file_splice_write,
.fallocate = shmem_fallocate,
#endif
};
static const struct inode_operations shmem_inode_operations = {
.setattr = shmem_setattr,
#ifdef CONFIG_TMPFS_XATTR
.setxattr = shmem_setxattr,
.getxattr = shmem_getxattr,
.listxattr = shmem_listxattr,
.removexattr = shmem_removexattr,
.set_acl = simple_set_acl,
#endif
};
static const struct inode_operations shmem_dir_inode_operations = {
#ifdef CONFIG_TMPFS
.create = shmem_create,
.lookup = simple_lookup,
.link = shmem_link,
.unlink = shmem_unlink,
.symlink = shmem_symlink,
.mkdir = shmem_mkdir,
.rmdir = shmem_rmdir,
.mknod = shmem_mknod,
.rename2 = shmem_rename2,
.tmpfile = shmem_tmpfile,
#endif
#ifdef CONFIG_TMPFS_XATTR
.setxattr = shmem_setxattr,
.getxattr = shmem_getxattr,
.listxattr = shmem_listxattr,
.removexattr = shmem_removexattr,
#endif
#ifdef CONFIG_TMPFS_POSIX_ACL
.setattr = shmem_setattr,
.set_acl = simple_set_acl,
#endif
};
static const struct inode_operations shmem_special_inode_operations = {
#ifdef CONFIG_TMPFS_XATTR
.setxattr = shmem_setxattr,
.getxattr = shmem_getxattr,
.listxattr = shmem_listxattr,
.removexattr = shmem_removexattr,
#endif
#ifdef CONFIG_TMPFS_POSIX_ACL
.setattr = shmem_setattr,
.set_acl = simple_set_acl,
#endif
};
static const struct super_operations shmem_ops = {
.alloc_inode = shmem_alloc_inode,
.destroy_inode = shmem_destroy_inode,
#ifdef CONFIG_TMPFS
.statfs = shmem_statfs,
.remount_fs = shmem_remount_fs,
.show_options = shmem_show_options,
#endif
.evict_inode = shmem_evict_inode,
.drop_inode = generic_delete_inode,
.put_super = shmem_put_super,
};
static const struct vm_operations_struct shmem_vm_ops = {
.fault = shmem_fault,
.map_pages = filemap_map_pages,
#ifdef CONFIG_NUMA
.set_policy = shmem_set_policy,
.get_policy = shmem_get_policy,
#endif
};
static struct dentry *shmem_mount(struct file_system_type *fs_type,
int flags, const char *dev_name, void *data)
{
return mount_nodev(fs_type, flags, data, shmem_fill_super);
}
static struct file_system_type shmem_fs_type = {
.owner = THIS_MODULE,
.name = "tmpfs",
.mount = shmem_mount,
.kill_sb = kill_litter_super,
.fs_flags = FS_USERNS_MOUNT,
};
int __init shmem_init(void)
{
int error;
/* If rootfs called this, don't re-init */
if (shmem_inode_cachep)
return 0;
error = shmem_init_inodecache();
if (error)
goto out3;
error = register_filesystem(&shmem_fs_type);
if (error) {
printk(KERN_ERR "Could not register tmpfs\n");
goto out2;
}
shm_mnt = kern_mount(&shmem_fs_type);
if (IS_ERR(shm_mnt)) {
error = PTR_ERR(shm_mnt);
printk(KERN_ERR "Could not kern_mount tmpfs\n");
goto out1;
}
return 0;
out1:
unregister_filesystem(&shmem_fs_type);
out2:
shmem_destroy_inodecache();
out3:
shm_mnt = ERR_PTR(error);
return error;
}
#else /* !CONFIG_SHMEM */
/*
* tiny-shmem: simple shmemfs and tmpfs using ramfs code
*
* This is intended for small system where the benefits of the full
* shmem code (swap-backed and resource-limited) are outweighed by
* their complexity. On systems without swap this code should be
* effectively equivalent, but much lighter weight.
*/
static struct file_system_type shmem_fs_type = {
.name = "tmpfs",
.mount = ramfs_mount,
.kill_sb = kill_litter_super,
.fs_flags = FS_USERNS_MOUNT,
};
int __init shmem_init(void)
{
BUG_ON(register_filesystem(&shmem_fs_type) != 0);
shm_mnt = kern_mount(&shmem_fs_type);
BUG_ON(IS_ERR(shm_mnt));
return 0;
}
int shmem_unuse(swp_entry_t swap, struct page *page)
{
return 0;
}
int shmem_lock(struct file *file, int lock, struct user_struct *user)
{
return 0;
}
void shmem_unlock_mapping(struct address_space *mapping)
{
}
void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
{
truncate_inode_pages_range(inode->i_mapping, lstart, lend);
}
EXPORT_SYMBOL_GPL(shmem_truncate_range);
#define shmem_vm_ops generic_file_vm_ops
#define shmem_file_operations ramfs_file_operations
#define shmem_get_inode(sb, dir, mode, dev, flags) ramfs_get_inode(sb, dir, mode, dev)
#define shmem_acct_size(flags, size) 0
#define shmem_unacct_size(flags, size) do {} while (0)
#endif /* CONFIG_SHMEM */
/* common code */
static struct dentry_operations anon_ops = {
.d_dname = simple_dname
};
static struct file *__shmem_file_setup(const char *name, loff_t size,
unsigned long flags, unsigned int i_flags)
{
struct file *res;
struct inode *inode;
struct path path;
struct super_block *sb;
struct qstr this;
if (IS_ERR(shm_mnt))
return ERR_CAST(shm_mnt);
if (size < 0 || size > MAX_LFS_FILESIZE)
return ERR_PTR(-EINVAL);
if (shmem_acct_size(flags, size))
return ERR_PTR(-ENOMEM);
res = ERR_PTR(-ENOMEM);
this.name = name;
this.len = strlen(name);
this.hash = 0; /* will go */
sb = shm_mnt->mnt_sb;
path.mnt = mntget(shm_mnt);
path.dentry = d_alloc_pseudo(sb, &this);
if (!path.dentry)
goto put_memory;
d_set_d_op(path.dentry, &anon_ops);
res = ERR_PTR(-ENOSPC);
inode = shmem_get_inode(sb, NULL, S_IFREG | S_IRWXUGO, 0, flags);
if (!inode)
goto put_memory;
inode->i_flags |= i_flags;
d_instantiate(path.dentry, inode);
inode->i_size = size;
clear_nlink(inode); /* It is unlinked */
res = ERR_PTR(ramfs_nommu_expand_for_mapping(inode, size));
if (IS_ERR(res))
goto put_path;
res = alloc_file(&path, FMODE_WRITE | FMODE_READ,
&shmem_file_operations);
if (IS_ERR(res))
goto put_path;
return res;
put_memory:
shmem_unacct_size(flags, size);
put_path:
path_put(&path);
return res;
}
/**
* shmem_kernel_file_setup - get an unlinked file living in tmpfs which must be
* kernel internal. There will be NO LSM permission checks against the
* underlying inode. So users of this interface must do LSM checks at a
* higher layer. The users are the big_key and shm implementations. LSM
* checks are provided at the key or shm level rather than the inode.
* @name: name for dentry (to be seen in /proc/<pid>/maps
* @size: size to be set for the file
* @flags: VM_NORESERVE suppresses pre-accounting of the entire object size
*/
struct file *shmem_kernel_file_setup(const char *name, loff_t size, unsigned long flags)
{
return __shmem_file_setup(name, size, flags, S_PRIVATE);
}
/**
* shmem_file_setup - get an unlinked file living in tmpfs
* @name: name for dentry (to be seen in /proc/<pid>/maps
* @size: size to be set for the file
* @flags: VM_NORESERVE suppresses pre-accounting of the entire object size
*/
struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags)
{
return __shmem_file_setup(name, size, flags, 0);
}
EXPORT_SYMBOL_GPL(shmem_file_setup);
/**
* shmem_zero_setup - setup a shared anonymous mapping
* @vma: the vma to be mmapped is prepared by do_mmap_pgoff
*/
int shmem_zero_setup(struct vm_area_struct *vma)
{
struct file *file;
loff_t size = vma->vm_end - vma->vm_start;
/*
* Cloning a new file under mmap_sem leads to a lock ordering conflict
* between XFS directory reading and selinux: since this file is only
* accessible to the user through its mapping, use S_PRIVATE flag to
* bypass file security, in the same way as shmem_kernel_file_setup().
*/
file = __shmem_file_setup("dev/zero", size, vma->vm_flags, S_PRIVATE);
if (IS_ERR(file))
return PTR_ERR(file);
if (vma->vm_file)
fput(vma->vm_file);
vma->vm_file = file;
vma->vm_ops = &shmem_vm_ops;
return 0;
}
/**
* shmem_read_mapping_page_gfp - read into page cache, using specified page allocation flags.
* @mapping: the page's address_space
* @index: the page index
* @gfp: the page allocator flags to use if allocating
*
* This behaves as a tmpfs "read_cache_page_gfp(mapping, index, gfp)",
* with any new page allocations done using the specified allocation flags.
* But read_cache_page_gfp() uses the ->readpage() method: which does not
* suit tmpfs, since it may have pages in swapcache, and needs to find those
* for itself; although drivers/gpu/drm i915 and ttm rely upon this support.
*
* i915_gem_object_get_pages_gtt() mixes __GFP_NORETRY | __GFP_NOWARN in
* with the mapping_gfp_mask(), to avoid OOMing the machine unnecessarily.
*/
struct page *shmem_read_mapping_page_gfp(struct address_space *mapping,
pgoff_t index, gfp_t gfp)
{
#ifdef CONFIG_SHMEM
struct inode *inode = mapping->host;
struct page *page;
int error;
BUG_ON(mapping->a_ops != &shmem_aops);
error = shmem_getpage_gfp(inode, index, &page, SGP_CACHE, gfp, NULL);
if (error)
page = ERR_PTR(error);
else
unlock_page(page);
return page;
#else
/*
* The tiny !SHMEM case uses ramfs without swap
*/
return read_cache_page_gfp(mapping, index, gfp);
#endif
}
EXPORT_SYMBOL_GPL(shmem_read_mapping_page_gfp);
C:\Users\Admin\Desktop\linux-4.2.y-new\linux-4.2.y\mm/slab.c
/*
* linux/mm/slab.c
* Written by Mark Hemment, 1996/97.
* (markhe@nextd.demon.co.uk)
*
* kmem_cache_destroy() + some cleanup - 1999 Andrea Arcangeli
*
* Major cleanup, different bufctl logic, per-cpu arrays
* (c) 2000 Manfred Spraul
*
* Cleanup, make the head arrays unconditional, preparation for NUMA
* (c) 2002 Manfred Spraul
*
* An implementation of the Slab Allocator as described in outline in;
* UNIX Internals: The New Frontiers by Uresh Vahalia
* Pub: Prentice Hall ISBN 0-13-101908-2
* or with a little more detail in;
* The Slab Allocator: An Object-Caching Kernel Memory Allocator
* Jeff Bonwick (Sun Microsystems).
* Presented at: USENIX Summer 1994 Technical Conference
*
* The memory is organized in caches, one cache for each object type.
* (e.g. inode_cache, dentry_cache, buffer_head, vm_area_struct)
* Each cache consists out of many slabs (they are small (usually one
* page long) and always contiguous), and each slab contains multiple
* initialized objects.
*
* This means, that your constructor is used only for newly allocated
* slabs and you must pass objects with the same initializations to
* kmem_cache_free.
*
* Each cache can only support one memory type (GFP_DMA, GFP_HIGHMEM,
* normal). If you need a special memory type, then must create a new
* cache for that memory type.
*
* In order to reduce fragmentation, the slabs are sorted in 3 groups:
* full slabs with 0 free objects
* partial slabs
* empty slabs with no allocated objects
*
* If partial slabs exist, then new allocations come from these slabs,
* otherwise from empty slabs or new slabs are allocated.
*
* kmem_cache_destroy() CAN CRASH if you try to allocate from the cache
* during kmem_cache_destroy(). The caller must prevent concurrent allocs.
*
* Each cache has a short per-cpu head array, most allocs
* and frees go into that array, and if that array overflows, then 1/2
* of the entries in the array are given back into the global cache.
* The head array is strictly LIFO and should improve the cache hit rates.
* On SMP, it additionally reduces the spinlock operations.
*
* The c_cpuarray may not be read with enabled local interrupts -
* it's changed with a smp_call_function().
*
* SMP synchronization:
* constructors and destructors are called without any locking.
* Several members in struct kmem_cache and struct slab never change, they
* are accessed without any locking.
* The per-cpu arrays are never accessed from the wrong cpu, no locking,
* and local interrupts are disabled so slab code is preempt-safe.
* The non-constant members are protected with a per-cache irq spinlock.
*
* Many thanks to Mark Hemment, who wrote another per-cpu slab patch
* in 2000 - many ideas in the current implementation are derived from
* his patch.
*
* Further notes from the original documentation:
*
* 11 April '97. Started multi-threading - markhe
* The global cache-chain is protected by the mutex 'slab_mutex'.
* The sem is only needed when accessing/extending the cache-chain, which
* can never happen inside an interrupt (kmem_cache_create(),
* kmem_cache_shrink() and kmem_cache_reap()).
*
* At present, each engine can be growing a cache. This should be blocked.
*
* 15 March 2005. NUMA slab allocator.
* Shai Fultheim <shai@scalex86.org>.
* Shobhit Dayal <shobhit@calsoftinc.com>
* Alok N Kataria <alokk@calsoftinc.com>
* Christoph Lameter <christoph@lameter.com>
*
* Modified the slab allocator to be node aware on NUMA systems.
* Each node has its own list of partial, free and full slabs.
* All object allocations for a node occur from node specific slab lists.
*/
#include <linux/slab.h>
#include <linux/mm.h>
#include <linux/poison.h>
#include <linux/swap.h>
#include <linux/cache.h>
#include <linux/interrupt.h>
#include <linux/init.h>
#include <linux/compiler.h>
#include <linux/cpuset.h>
#include <linux/proc_fs.h>
#include <linux/seq_file.h>
#include <linux/notifier.h>
#include <linux/kallsyms.h>
#include <linux/cpu.h>
#include <linux/sysctl.h>
#include <linux/module.h>
#include <linux/rcupdate.h>
#include <linux/string.h>
#include <linux/uaccess.h>
#include <linux/nodemask.h>
#include <linux/kmemleak.h>
#include <linux/mempolicy.h>
#include <linux/mutex.h>
#include <linux/fault-inject.h>
#include <linux/rtmutex.h>
#include <linux/reciprocal_div.h>
#include <linux/debugobjects.h>
#include <linux/kmemcheck.h>
#include <linux/memory.h>
#include <linux/prefetch.h>
#include <net/sock.h>
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
#include <asm/page.h>
#include <trace/events/kmem.h>
#include "internal.h"
#include "slab.h"
/*
* DEBUG - 1 for kmem_cache_create() to honour; SLAB_RED_ZONE & SLAB_POISON.
* 0 for faster, smaller code (especially in the critical paths).
*
* STATS - 1 to collect stats for /proc/slabinfo.
* 0 for faster, smaller code (especially in the critical paths).
*
* FORCED_DEBUG - 1 enables SLAB_RED_ZONE and SLAB_POISON (if possible)
*/
#ifdef CONFIG_DEBUG_SLAB
#define DEBUG 1
#define STATS 1
#define FORCED_DEBUG 1
#else
#define DEBUG 0
#define STATS 0
#define FORCED_DEBUG 0
#endif
/* Shouldn't this be in a header file somewhere? */
#define BYTES_PER_WORD sizeof(void *)
#define REDZONE_ALIGN max(BYTES_PER_WORD, __alignof__(unsigned long long))
#ifndef ARCH_KMALLOC_FLAGS
#define ARCH_KMALLOC_FLAGS SLAB_HWCACHE_ALIGN
#endif
#define FREELIST_BYTE_INDEX (((PAGE_SIZE >> BITS_PER_BYTE) \
<= SLAB_OBJ_MIN_SIZE) ? 1 : 0)
#if FREELIST_BYTE_INDEX
typedef unsigned char freelist_idx_t;
#else
typedef unsigned short freelist_idx_t;
#endif
#define SLAB_OBJ_MAX_NUM ((1 << sizeof(freelist_idx_t) * BITS_PER_BYTE) - 1)
/*
* true if a page was allocated from pfmemalloc reserves for network-based
* swap
*/
static bool pfmemalloc_active __read_mostly;
/*
* struct array_cache
*
* Purpose:
* - LIFO ordering, to hand out cache-warm objects from _alloc
* - reduce the number of linked list operations
* - reduce spinlock operations
*
* The limit is stored in the per-cpu structure to reduce the data cache
* footprint.
*
*/
struct array_cache {
unsigned int avail;
unsigned int limit;
unsigned int batchcount;
unsigned int touched;
void *entry[]; /*
* Must have this definition in here for the proper
* alignment of array_cache. Also simplifies accessing
* the entries.
*
* Entries should not be directly dereferenced as
* entries belonging to slabs marked pfmemalloc will
* have the lower bits set SLAB_OBJ_PFMEMALLOC
*/
};
struct alien_cache {
spinlock_t lock;
struct array_cache ac;
};
#define SLAB_OBJ_PFMEMALLOC 1
static inline bool is_obj_pfmemalloc(void *objp)
{
return (unsigned long)objp & SLAB_OBJ_PFMEMALLOC;
}
static inline void set_obj_pfmemalloc(void **objp)
{
*objp = (void *)((unsigned long)*objp | SLAB_OBJ_PFMEMALLOC);
return;
}
static inline void clear_obj_pfmemalloc(void **objp)
{
*objp = (void *)((unsigned long)*objp & ~SLAB_OBJ_PFMEMALLOC);
}
/*
* bootstrap: The caches do not work without cpuarrays anymore, but the
* cpuarrays are allocated from the generic caches...
*/
#define BOOT_CPUCACHE_ENTRIES 1
struct arraycache_init {
struct array_cache cache;
void *entries[BOOT_CPUCACHE_ENTRIES];
};
/*
* Need this for bootstrapping a per node allocator.
*/
#define NUM_INIT_LISTS (2 * MAX_NUMNODES)
static struct kmem_cache_node __initdata init_kmem_cache_node[NUM_INIT_LISTS];
#define CACHE_CACHE 0
#define SIZE_NODE (MAX_NUMNODES)
static int drain_freelist(struct kmem_cache *cache,
struct kmem_cache_node *n, int tofree);
static void free_block(struct kmem_cache *cachep, void **objpp, int len,
int node, struct list_head *list);
static void slabs_destroy(struct kmem_cache *cachep, struct list_head *list);
static int enable_cpucache(struct kmem_cache *cachep, gfp_t gfp);
static void cache_reap(struct work_struct *unused);
static int slab_early_init = 1;
#define INDEX_NODE kmalloc_index(sizeof(struct kmem_cache_node))
static void kmem_cache_node_init(struct kmem_cache_node *parent)
{
INIT_LIST_HEAD(&parent->slabs_full);
INIT_LIST_HEAD(&parent->slabs_partial);
INIT_LIST_HEAD(&parent->slabs_free);
parent->shared = NULL;
parent->alien = NULL;
parent->colour_next = 0;
spin_lock_init(&parent->list_lock);
parent->free_objects = 0;
parent->free_touched = 0;
}
#define MAKE_LIST(cachep, listp, slab, nodeid) \
do { \
INIT_LIST_HEAD(listp); \
list_splice(&get_node(cachep, nodeid)->slab, listp); \
} while (0)
#define MAKE_ALL_LISTS(cachep, ptr, nodeid) \
do { \
MAKE_LIST((cachep), (&(ptr)->slabs_full), slabs_full, nodeid); \
MAKE_LIST((cachep), (&(ptr)->slabs_partial), slabs_partial, nodeid); \
MAKE_LIST((cachep), (&(ptr)->slabs_free), slabs_free, nodeid); \
} while (0)
#define CFLGS_OFF_SLAB (0x80000000UL)
#define OFF_SLAB(x) ((x)->flags & CFLGS_OFF_SLAB)
#define BATCHREFILL_LIMIT 16
/*
* Optimization question: fewer reaps means less probability for unnessary
* cpucache drain/refill cycles.
*
* OTOH the cpuarrays can contain lots of objects,
* which could lock up otherwise freeable slabs.
*/
#define REAPTIMEOUT_AC (2*HZ)
#define REAPTIMEOUT_NODE (4*HZ)
#if STATS
#define STATS_INC_ACTIVE(x) ((x)->num_active++)
#define STATS_DEC_ACTIVE(x) ((x)->num_active--)
#define STATS_INC_ALLOCED(x) ((x)->num_allocations++)
#define STATS_INC_GROWN(x) ((x)->grown++)
#define STATS_ADD_REAPED(x,y) ((x)->reaped += (y))
#define STATS_SET_HIGH(x) \
do { \
if ((x)->num_active > (x)->high_mark) \
(x)->high_mark = (x)->num_active; \
} while (0)
#define STATS_INC_ERR(x) ((x)->errors++)
#define STATS_INC_NODEALLOCS(x) ((x)->node_allocs++)
#define STATS_INC_NODEFREES(x) ((x)->node_frees++)
#define STATS_INC_ACOVERFLOW(x) ((x)->node_overflow++)
#define STATS_SET_FREEABLE(x, i) \
do { \
if ((x)->max_freeable < i) \
(x)->max_freeable = i; \
} while (0)
#define STATS_INC_ALLOCHIT(x) atomic_inc(&(x)->allochit)
#define STATS_INC_ALLOCMISS(x) atomic_inc(&(x)->allocmiss)
#define STATS_INC_FREEHIT(x) atomic_inc(&(x)->freehit)
#define STATS_INC_FREEMISS(x) atomic_inc(&(x)->freemiss)
#else
#define STATS_INC_ACTIVE(x) do { } while (0)
#define STATS_DEC_ACTIVE(x) do { } while (0)
#define STATS_INC_ALLOCED(x) do { } while (0)
#define STATS_INC_GROWN(x) do { } while (0)
#define STATS_ADD_REAPED(x,y) do { (void)(y); } while (0)
#define STATS_SET_HIGH(x) do { } while (0)
#define STATS_INC_ERR(x) do { } while (0)
#define STATS_INC_NODEALLOCS(x) do { } while (0)
#define STATS_INC_NODEFREES(x) do { } while (0)
#define STATS_INC_ACOVERFLOW(x) do { } while (0)
#define STATS_SET_FREEABLE(x, i) do { } while (0)
#define STATS_INC_ALLOCHIT(x) do { } while (0)
#define STATS_INC_ALLOCMISS(x) do { } while (0)
#define STATS_INC_FREEHIT(x) do { } while (0)
#define STATS_INC_FREEMISS(x) do { } while (0)
#endif
#if DEBUG
/*
* memory layout of objects:
* 0 : objp
* 0 .. cachep->obj_offset - BYTES_PER_WORD - 1: padding. This ensures that
* the end of an object is aligned with the end of the real
* allocation. Catches writes behind the end of the allocation.
* cachep->obj_offset - BYTES_PER_WORD .. cachep->obj_offset - 1:
* redzone word.
* cachep->obj_offset: The real object.
* cachep->size - 2* BYTES_PER_WORD: redzone word [BYTES_PER_WORD long]
* cachep->size - 1* BYTES_PER_WORD: last caller address
* [BYTES_PER_WORD long]
*/
static int obj_offset(struct kmem_cache *cachep)
{
return cachep->obj_offset;
}
static unsigned long long *dbg_redzone1(struct kmem_cache *cachep, void *objp)
{
BUG_ON(!(cachep->flags & SLAB_RED_ZONE));
return (unsigned long long*) (objp + obj_offset(cachep) -
sizeof(unsigned long long));
}
static unsigned long long *dbg_redzone2(struct kmem_cache *cachep, void *objp)
{
BUG_ON(!(cachep->flags & SLAB_RED_ZONE));
if (cachep->flags & SLAB_STORE_USER)
return (unsigned long long *)(objp + cachep->size -
sizeof(unsigned long long) -
REDZONE_ALIGN);
return (unsigned long long *) (objp + cachep->size -
sizeof(unsigned long long));
}
static void **dbg_userword(struct kmem_cache *cachep, void *objp)
{
BUG_ON(!(cachep->flags & SLAB_STORE_USER));
return (void **)(objp + cachep->size - BYTES_PER_WORD);
}
#else
#define obj_offset(x) 0
#define dbg_redzone1(cachep, objp) ({BUG(); (unsigned long long *)NULL;})
#define dbg_redzone2(cachep, objp) ({BUG(); (unsigned long long *)NULL;})
#define dbg_userword(cachep, objp) ({BUG(); (void **)NULL;})
#endif
#define OBJECT_FREE (0)
#define OBJECT_ACTIVE (1)
#ifdef CONFIG_DEBUG_SLAB_LEAK
static void set_obj_status(struct page *page, int idx, int val)
{
int freelist_size;
char *status;
struct kmem_cache *cachep = page->slab_cache;
freelist_size = cachep->num * sizeof(freelist_idx_t);
status = (char *)page->freelist + freelist_size;
status[idx] = val;
}
static inline unsigned int get_obj_status(struct page *page, int idx)
{
int freelist_size;
char *status;
struct kmem_cache *cachep = page->slab_cache;
freelist_size = cachep->num * sizeof(freelist_idx_t);
status = (char *)page->freelist + freelist_size;
return status[idx];
}
#else
static inline void set_obj_status(struct page *page, int idx, int val) {}
#endif
/*
* Do not go above this order unless 0 objects fit into the slab or
* overridden on the command line.
*/
#define SLAB_MAX_ORDER_HI 1
#define SLAB_MAX_ORDER_LO 0
static int slab_max_order = SLAB_MAX_ORDER_LO;
static bool slab_max_order_set __initdata;
static inline struct kmem_cache *virt_to_cache(const void *obj)
{
struct page *page = virt_to_head_page(obj);
return page->slab_cache;
}
static inline void *index_to_obj(struct kmem_cache *cache, struct page *page,
unsigned int idx)
{
return page->s_mem + cache->size * idx;
}
/*
* We want to avoid an expensive divide : (offset / cache->size)
* Using the fact that size is a constant for a particular cache,
* we can replace (offset / cache->size) by
* reciprocal_divide(offset, cache->reciprocal_buffer_size)
*/
static inline unsigned int obj_to_index(const struct kmem_cache *cache,
const struct page *page, void *obj)
{
u32 offset = (obj - page->s_mem);
return reciprocal_divide(offset, cache->reciprocal_buffer_size);
}
/* internal cache of cache description objs */
static struct kmem_cache kmem_cache_boot = {
.batchcount = 1,
.limit = BOOT_CPUCACHE_ENTRIES,
.shared = 1,
.size = sizeof(struct kmem_cache),
.name = "kmem_cache",
};
#define BAD_ALIEN_MAGIC 0x01020304ul
static DEFINE_PER_CPU(struct delayed_work, slab_reap_work);
static inline struct array_cache *cpu_cache_get(struct kmem_cache *cachep)
{
return this_cpu_ptr(cachep->cpu_cache);
}
static size_t calculate_freelist_size(int nr_objs, size_t align)
{
size_t freelist_size;
freelist_size = nr_objs * sizeof(freelist_idx_t);
if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK))
freelist_size += nr_objs * sizeof(char);
if (align)
freelist_size = ALIGN(freelist_size, align);
return freelist_size;
}
static int calculate_nr_objs(size_t slab_size, size_t buffer_size,
size_t idx_size, size_t align)
{
int nr_objs;
size_t remained_size;
size_t freelist_size;
int extra_space = 0;
if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK))
extra_space = sizeof(char);
/*
* Ignore padding for the initial guess. The padding
* is at most @align-1 bytes, and @buffer_size is at
* least @align. In the worst case, this result will
* be one greater than the number of objects that fit
* into the memory allocation when taking the padding
* into account.
*/
nr_objs = slab_size / (buffer_size + idx_size + extra_space);
/*
* This calculated number will be either the right
* amount, or one greater than what we want.
*/
remained_size = slab_size - nr_objs * buffer_size;
freelist_size = calculate_freelist_size(nr_objs, align);
if (remained_size < freelist_size)
nr_objs--;
return nr_objs;
}
/*
* Calculate the number of objects and left-over bytes for a given buffer size.
*/
static void cache_estimate(unsigned long gfporder, size_t buffer_size,
size_t align, int flags, size_t *left_over,
unsigned int *num)
{
int nr_objs;
size_t mgmt_size;
size_t slab_size = PAGE_SIZE << gfporder;
/*
* The slab management structure can be either off the slab or
* on it. For the latter case, the memory allocated for a
* slab is used for:
*
* - One unsigned int for each object
* - Padding to respect alignment of @align
* - @buffer_size bytes for each object
*
* If the slab management structure is off the slab, then the
* alignment will already be calculated into the size. Because
* the slabs are all pages aligned, the objects will be at the
* correct alignment when allocated.
*/
if (flags & CFLGS_OFF_SLAB) {
mgmt_size = 0;
nr_objs = slab_size / buffer_size;
} else {
nr_objs = calculate_nr_objs(slab_size, buffer_size,
sizeof(freelist_idx_t), align);
mgmt_size = calculate_freelist_size(nr_objs, align);
}
*num = nr_objs;
*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,
char *msg)
{
printk(KERN_ERR "slab error in %s(): cache `%s': %s\n",
function, cachep->name, msg);
dump_stack();
add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE);
}
#endif
/*
* By default on NUMA we use alien caches to stage the freeing of
* objects allocated from other nodes. This causes massive memory
* inefficiencies when using fake NUMA setup to split memory into a
* large number of small nodes, so it can be disabled on the command
* line
*/
static int use_alien_caches __read_mostly = 1;
static int __init noaliencache_setup(char *s)
{
use_alien_caches = 0;
return 1;
}
__setup("noaliencache", noaliencache_setup);
static int __init slab_max_order_setup(char *str)
{
get_option(&str, &slab_max_order);
slab_max_order = slab_max_order < 0 ? 0 :
min(slab_max_order, MAX_ORDER - 1);
slab_max_order_set = true;
return 1;
}
__setup("slab_max_order=", slab_max_order_setup);
#ifdef CONFIG_NUMA
/*
* Special reaping functions for NUMA systems called from cache_reap().
* These take care of doing round robin flushing of alien caches (containing
* 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, slab_reap_node);
static void init_reap_node(int cpu)
{
int node;
node = next_node(cpu_to_mem(cpu), node_online_map);
if (node == MAX_NUMNODES)
node = first_node(node_online_map);
per_cpu(slab_reap_node, cpu) = node;
}
static void next_reap_node(void)
{
int node = __this_cpu_read(slab_reap_node);
node = next_node(node, node_online_map);
if (unlikely(node >= MAX_NUMNODES))
node = first_node(node_online_map);
__this_cpu_write(slab_reap_node, node);
}
#else
#define init_reap_node(cpu) do { } while (0)
#define next_reap_node(void) do { } while (0)
#endif
/*
* Initiate the reap timer running on the target CPU. We run at around 1 to 2Hz
* via the workqueue/eventd.
* Add the CPU number into the expiration time to minimize the possibility of
* the CPUs getting into lockstep and contending for the global cache chain
* lock.
*/
static void start_cpu_timer(int cpu)
{
struct delayed_work *reap_work = &per_cpu(slab_reap_work, cpu);
/*
* When this gets called from do_initcalls via cpucache_init(),
* init_workqueues() has already run, so keventd will be setup
* at that time.
*/
if (keventd_up() && reap_work->work.func == NULL) {
init_reap_node(cpu);
INIT_DEFERRABLE_WORK(reap_work, cache_reap);
schedule_delayed_work_on(cpu, reap_work,
__round_jiffies_relative(HZ, cpu));
}
}
static void init_arraycache(struct array_cache *ac, int limit, int batch)
{
/*
* The array_cache structures contain pointers to free object.
* However, when such objects are allocated or transferred to another
* cache the pointers are not cleared and they could be counted as
* valid references during a kmemleak scan. Therefore, kmemleak must
* not scan such objects.
*/
kmemleak_no_scan(ac);
if (ac) {
ac->avail = 0;
ac->limit = limit;
ac->batchcount = batch;
ac->touched = 0;
}
}
static struct array_cache *alloc_arraycache(int node, int entries,
int batchcount, gfp_t gfp)
{
size_t memsize = sizeof(void *) * entries + sizeof(struct array_cache);
struct array_cache *ac = NULL;
ac = kmalloc_node(memsize, gfp, node);
init_arraycache(ac, entries, batchcount);
return ac;
}
static inline bool is_slab_pfmemalloc(struct page *page)
{
return PageSlabPfmemalloc(page);
}
/* Clears pfmemalloc_active if no slabs have pfmalloc set */
static void recheck_pfmemalloc_active(struct kmem_cache *cachep,
struct array_cache *ac)
{
struct kmem_cache_node *n = get_node(cachep, numa_mem_id());
struct page *page;
unsigned long flags;
if (!pfmemalloc_active)
return;
spin_lock_irqsave(&n->list_lock, flags);
list_for_each_entry(page, &n->slabs_full, lru)
if (is_slab_pfmemalloc(page))
goto out;
list_for_each_entry(page, &n->slabs_partial, lru)
if (is_slab_pfmemalloc(page))
goto out;
list_for_each_entry(page, &n->slabs_free, lru)
if (is_slab_pfmemalloc(page))
goto out;
pfmemalloc_active = false;
out:
spin_unlock_irqrestore(&n->list_lock, flags);
}
static void *__ac_get_obj(struct kmem_cache *cachep, struct array_cache *ac,
gfp_t flags, bool force_refill)
{
int i;
void *objp = ac->entry[--ac->avail];
/* Ensure the caller is allowed to use objects from PFMEMALLOC slab */
if (unlikely(is_obj_pfmemalloc(objp))) {
struct kmem_cache_node *n;
if (gfp_pfmemalloc_allowed(flags)) {
clear_obj_pfmemalloc(&objp);
return objp;
}
/* The caller cannot use PFMEMALLOC objects, find another one */
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];
ac->entry[i] = ac->entry[ac->avail];
ac->entry[ac->avail] = objp;
return objp;
}
}
/*
* If there are empty slabs on the slabs_free list and we are
* being forced to refill the cache, mark this one !pfmemalloc.
*/
n = get_node(cachep, numa_mem_id());
if (!list_empty(&n->slabs_free) && force_refill) {
struct page *page = virt_to_head_page(objp);
ClearPageSlabPfmemalloc(page);
clear_obj_pfmemalloc(&objp);
recheck_pfmemalloc_active(cachep, ac);
return objp;
}
/* No !PFMEMALLOC objects available */
ac->avail++;
objp = NULL;
}
return objp;
}
static inline void *ac_get_obj(struct kmem_cache *cachep,
struct array_cache *ac, gfp_t flags, bool force_refill)
{
void *objp;
if (unlikely(sk_memalloc_socks()))
objp = __ac_get_obj(cachep, ac, flags, force_refill);
else
objp = ac->entry[--ac->avail];
return objp;
}
static noinline void *__ac_put_obj(struct kmem_cache *cachep,
struct array_cache *ac, void *objp)
{
if (unlikely(pfmemalloc_active)) {
/* Some pfmemalloc slabs exist, check if this is one */
struct page *page = virt_to_head_page(objp);
if (PageSlabPfmemalloc(page))
set_obj_pfmemalloc(&objp);
}
return objp;
}
static inline void ac_put_obj(struct kmem_cache *cachep, struct array_cache *ac,
void *objp)
{
if (unlikely(sk_memalloc_socks()))
objp = __ac_put_obj(cachep, ac, objp);
ac->entry[ac->avail++] = objp;
}
/*
* Transfer objects in one arraycache to another.
* Locking must be handled by the caller.
*
* Return the number of entries transferred.
*/
static int transfer_objects(struct array_cache *to,
struct array_cache *from, unsigned int max)
{
/* Figure out how many entries to transfer */
int nr = min3(from->avail, max, to->limit - to->avail);
if (!nr)
return 0;
memcpy(to->entry + to->avail, from->entry + from->avail -nr,
sizeof(void *) *nr);
from->avail -= nr;
to->avail += nr;
return nr;
}
#ifndef CONFIG_NUMA
#define drain_alien_cache(cachep, alien) do { } while (0)
#define reap_alien(cachep, n) do { } while (0)
static inline struct alien_cache **alloc_alien_cache(int node,
int limit, gfp_t gfp)
{
return (struct alien_cache **)BAD_ALIEN_MAGIC;
}
static inline void free_alien_cache(struct alien_cache **ac_ptr)
{
}
static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
{
return 0;
}
static inline void *alternate_node_alloc(struct kmem_cache *cachep,
gfp_t flags)
{
return NULL;
}
static inline void *____cache_alloc_node(struct kmem_cache *cachep,
gfp_t flags, int nodeid)
{
return NULL;
}
static inline gfp_t gfp_exact_node(gfp_t flags)
{
return flags;
}
#else /* CONFIG_NUMA */
static void *____cache_alloc_node(struct kmem_cache *, gfp_t, int);
static void *alternate_node_alloc(struct kmem_cache *, gfp_t);
static struct alien_cache *__alloc_alien_cache(int node, int entries,
int batch, gfp_t gfp)
{
size_t memsize = sizeof(void *) * entries + sizeof(struct alien_cache);
struct alien_cache *alc = NULL;
alc = kmalloc_node(memsize, gfp, node);
init_arraycache(&alc->ac, entries, batch);
spin_lock_init(&alc->lock);
return alc;
}
static struct alien_cache **alloc_alien_cache(int node, int limit, gfp_t gfp)
{
struct alien_cache **alc_ptr;
size_t memsize = sizeof(void *) * nr_node_ids;
int i;
if (limit > 1)
limit = 12;
alc_ptr = kzalloc_node(memsize, gfp, node);
if (!alc_ptr)
return NULL;
for_each_node(i) {
if (i == node || !node_online(i))
continue;
alc_ptr[i] = __alloc_alien_cache(node, limit, 0xbaadf00d, gfp);
if (!alc_ptr[i]) {
for (i--; i >= 0; i--)
kfree(alc_ptr[i]);
kfree(alc_ptr);
return NULL;
}
}
return alc_ptr;
}
static void free_alien_cache(struct alien_cache **alc_ptr)
{
int i;
if (!alc_ptr)
return;
for_each_node(i)
kfree(alc_ptr[i]);
kfree(alc_ptr);
}
static void __drain_alien_cache(struct kmem_cache *cachep,
struct array_cache *ac, int node,
struct list_head *list)
{
struct kmem_cache_node *n = get_node(cachep, node);
if (ac->avail) {
spin_lock(&n->list_lock);
/*
* Stuff objects into the remote nodes shared array first.
* That way we could avoid the overhead of putting the objects
* into the free lists and getting them back later.
*/
if (n->shared)
transfer_objects(n->shared, ac, ac->limit);
free_block(cachep, ac->entry, ac->avail, node, list);
ac->avail = 0;
spin_unlock(&n->list_lock);
}
}
/*
* Called from cache_reap() to regularly drain alien caches round robin.
*/
static void reap_alien(struct kmem_cache *cachep, struct kmem_cache_node *n)
{
int node = __this_cpu_read(slab_reap_node);
if (n->alien) {
struct alien_cache *alc = n->alien[node];
struct array_cache *ac;
if (alc) {
ac = &alc->ac;
if (ac->avail && spin_trylock_irq(&alc->lock)) {
LIST_HEAD(list);
__drain_alien_cache(cachep, ac, node, &list);
spin_unlock_irq(&alc->lock);
slabs_destroy(cachep, &list);
}
}
}
}
static void drain_alien_cache(struct kmem_cache *cachep,
struct alien_cache **alien)
{
int i = 0;
struct alien_cache *alc;
struct array_cache *ac;
unsigned long flags;
for_each_online_node(i) {
alc = alien[i];
if (alc) {
LIST_HEAD(list);
ac = &alc->ac;
spin_lock_irqsave(&alc->lock, flags);
__drain_alien_cache(cachep, ac, i, &list);
spin_unlock_irqrestore(&alc->lock, flags);
slabs_destroy(cachep, &list);
}
}
}
static int __cache_free_alien(struct kmem_cache *cachep, void *objp,
int node, int page_node)
{
struct kmem_cache_node *n;
struct alien_cache *alien = NULL;
struct array_cache *ac;
LIST_HEAD(list);
n = get_node(cachep, node);
STATS_INC_NODEFREES(cachep);
if (n->alien && n->alien[page_node]) {
alien = n->alien[page_node];
ac = &alien->ac;
spin_lock(&alien->lock);
if (unlikely(ac->avail == ac->limit)) {
STATS_INC_ACOVERFLOW(cachep);
__drain_alien_cache(cachep, ac, page_node, &list);
}
ac_put_obj(cachep, ac, objp);
spin_unlock(&alien->lock);
slabs_destroy(cachep, &list);
} else {
n = get_node(cachep, page_node);
spin_lock(&n->list_lock);
free_block(cachep, &objp, 1, page_node, &list);
spin_unlock(&n->list_lock);
slabs_destroy(cachep, &list);
}
return 1;
}
static inline int cache_free_alien(struct kmem_cache *cachep, void *objp)
{
int page_node = page_to_nid(virt_to_page(objp));
int node = numa_mem_id();
/*
* Make sure we are not freeing a object from another node to the array
* cache on this cpu.
*/
if (likely(node == page_node))
return 0;
return __cache_free_alien(cachep, objp, node, page_node);
}
/*
* Construct gfp mask to allocate from a specific node but do not invoke reclaim
* or warn about failures.
*/
static inline gfp_t gfp_exact_node(gfp_t flags)
{
return (flags | __GFP_THISNODE | __GFP_NOWARN) & ~__GFP_WAIT;
}
#endif
/*
* Allocates and initializes node for a node on each slab cache, used for
* either memory or cpu hotplug. If memory is being hot-added, the kmem_cache_node
* will be allocated off-node since memory is not yet online for the new node.
* When hotplugging memory or a cpu, existing node are not replaced if
* already in use.
*
* Must hold slab_mutex.
*/
static int init_cache_node_node(int node)
{
struct kmem_cache *cachep;
struct kmem_cache_node *n;
const size_t memsize = sizeof(struct kmem_cache_node);
list_for_each_entry(cachep, &slab_caches, list) {
/*
* Set up the kmem_cache_node for cpu before we can
* begin anything. Make sure some other cpu on this
* node has not already allocated this
*/
n = get_node(cachep, node);
if (!n) {
n = kmalloc_node(memsize, GFP_KERNEL, node);
if (!n)
return -ENOMEM;
kmem_cache_node_init(n);
n->next_reap = jiffies + REAPTIMEOUT_NODE +
((unsigned long)cachep) % REAPTIMEOUT_NODE;
/*
* The kmem_cache_nodes don't come and go as CPUs
* come and go. slab_mutex is sufficient
* protection here.
*/
cachep->node[node] = n;
}
spin_lock_irq(&n->list_lock);
n->free_limit =
(1 + nr_cpus_node(node)) *
cachep->batchcount + cachep->num;
spin_unlock_irq(&n->list_lock);
}
return 0;
}
static inline int slabs_tofree(struct kmem_cache *cachep,
struct kmem_cache_node *n)
{
return (n->free_objects + cachep->num - 1) / cachep->num;
}
static void cpuup_canceled(long cpu)
{
struct kmem_cache *cachep;
struct kmem_cache_node *n = NULL;
int node = cpu_to_mem(cpu);
const struct cpumask *mask = cpumask_of_node(node);
list_for_each_entry(cachep, &slab_caches, list) {
struct array_cache *nc;
struct array_cache *shared;
struct alien_cache **alien;
LIST_HEAD(list);
n = get_node(cachep, node);
if (!n)
continue;
spin_lock_irq(&n->list_lock);
/* Free limit for this kmem_cache_node */
n->free_limit -= cachep->batchcount;
/* cpu is dead; no one can alloc from it. */
nc = per_cpu_ptr(cachep->cpu_cache, cpu);
if (nc) {
free_block(cachep, nc->entry, nc->avail, node, &list);
nc->avail = 0;
}
if (!cpumask_empty(mask)) {
spin_unlock_irq(&n->list_lock);
goto free_slab;
}
shared = n->shared;
if (shared) {
free_block(cachep, shared->entry,
shared->avail, node, &list);
n->shared = NULL;
}
alien = n->alien;
n->alien = NULL;
spin_unlock_irq(&n->list_lock);
kfree(shared);
if (alien) {
drain_alien_cache(cachep, alien);
free_alien_cache(alien);
}
free_slab:
slabs_destroy(cachep, &list);
}
/*
* In the previous loop, all the objects were freed to
* the respective cache's slabs, now we can go ahead and
* shrink each nodelist to its limit.
*/
list_for_each_entry(cachep, &slab_caches, list) {
n = get_node(cachep, node);
if (!n)
continue;
drain_freelist(cachep, n, slabs_tofree(cachep, n));
}
}
static int cpuup_prepare(long cpu)
{
struct kmem_cache *cachep;
struct kmem_cache_node *n = NULL;
int node = cpu_to_mem(cpu);
int err;
/*
* We need to do this right in the beginning since
* alloc_arraycache's are going to use this list.
* kmalloc_node allows us to add the slab to the right
* kmem_cache_node and not this cpu's kmem_cache_node
*/
err = init_cache_node_node(node);
if (err < 0)
goto bad;
/*
* Now we can go ahead with allocating the shared arrays and
* array caches
*/
list_for_each_entry(cachep, &slab_caches, list) {
struct array_cache *shared = NULL;
struct alien_cache **alien = NULL;
if (cachep->shared) {
shared = alloc_arraycache(node,
cachep->shared * cachep->batchcount,
0xbaadf00d, GFP_KERNEL);
if (!shared)
goto bad;
}
if (use_alien_caches) {
alien = alloc_alien_cache(node, cachep->limit, GFP_KERNEL);
if (!alien) {
kfree(shared);
goto bad;
}
}
n = get_node(cachep, node);
BUG_ON(!n);
spin_lock_irq(&n->list_lock);
if (!n->shared) {
/*
* We are serialised from CPU_DEAD or
* CPU_UP_CANCELLED by the cpucontrol lock
*/
n->shared = shared;
shared = NULL;
}
#ifdef CONFIG_NUMA
if (!n->alien) {
n->alien = alien;
alien = NULL;
}
#endif
spin_unlock_irq(&n->list_lock);
kfree(shared);
free_alien_cache(alien);
}
return 0;
bad:
cpuup_canceled(cpu);
return -ENOMEM;
}
static int cpuup_callback(struct notifier_block *nfb,
unsigned long action, void *hcpu)
{
long cpu = (long)hcpu;
int err = 0;
switch (action) {
case CPU_UP_PREPARE:
case CPU_UP_PREPARE_FROZEN:
mutex_lock(&slab_mutex);
err = cpuup_prepare(cpu);
mutex_unlock(&slab_mutex);
break;
case CPU_ONLINE:
case CPU_ONLINE_FROZEN:
start_cpu_timer(cpu);
break;
#ifdef CONFIG_HOTPLUG_CPU
case CPU_DOWN_PREPARE:
case CPU_DOWN_PREPARE_FROZEN:
/*
* Shutdown cache reaper. Note that the slab_mutex is
* held so that if cache_reap() is invoked it cannot do
* anything expensive but will only modify reap_work
* and reschedule the timer.
*/
cancel_delayed_work_sync(&per_cpu(slab_reap_work, cpu));
/* Now the cache_reaper is guaranteed to be not running. */
per_cpu(slab_reap_work, cpu).work.func = NULL;
break;
case CPU_DOWN_FAILED:
case CPU_DOWN_FAILED_FROZEN:
start_cpu_timer(cpu);
break;
case CPU_DEAD:
case CPU_DEAD_FROZEN:
/*
* Even if all the cpus of a node are down, we don't free the
* kmem_cache_node of any cache. This to avoid a race between
* cpu_down, and a kmalloc allocation from another cpu for
* memory from the node of the cpu going down. The node
* structure is usually allocated from kmem_cache_create() and
* gets destroyed at kmem_cache_destroy().
*/
/* fall through */
#endif
case CPU_UP_CANCELED:
case CPU_UP_CANCELED_FROZEN:
mutex_lock(&slab_mutex);
cpuup_canceled(cpu);
mutex_unlock(&slab_mutex);
break;
}
return notifier_from_errno(err);
}
static struct notifier_block cpucache_notifier = {
&cpuup_callback, NULL, 0
};
#if defined(CONFIG_NUMA) && defined(CONFIG_MEMORY_HOTPLUG)
/*
* Drains freelist for a node on each slab cache, used for memory hot-remove.
* Returns -EBUSY if all objects cannot be drained so that the node is not
* removed.
*
* Must hold slab_mutex.
*/
static int __meminit drain_cache_node_node(int node)
{
struct kmem_cache *cachep;
int ret = 0;
list_for_each_entry(cachep, &slab_caches, list) {
struct kmem_cache_node *n;
n = get_node(cachep, node);
if (!n)
continue;
drain_freelist(cachep, n, slabs_tofree(cachep, n));
if (!list_empty(&n->slabs_full) ||
!list_empty(&n->slabs_partial)) {
ret = -EBUSY;
break;
}
}
return ret;
}
static int __meminit slab_memory_callback(struct notifier_block *self,
unsigned long action, void *arg)
{
struct memory_notify *mnb = arg;
int ret = 0;
int nid;
nid = mnb->status_change_nid;
if (nid < 0)
goto out;
switch (action) {
case MEM_GOING_ONLINE:
mutex_lock(&slab_mutex);
ret = init_cache_node_node(nid);
mutex_unlock(&slab_mutex);
break;
case MEM_GOING_OFFLINE:
mutex_lock(&slab_mutex);
ret = drain_cache_node_node(nid);
mutex_unlock(&slab_mutex);
break;
case MEM_ONLINE:
case MEM_OFFLINE:
case MEM_CANCEL_ONLINE:
case MEM_CANCEL_OFFLINE:
break;
}
out:
return notifier_from_errno(ret);
}
#endif /* CONFIG_NUMA && CONFIG_MEMORY_HOTPLUG */
/*
* swap the static kmem_cache_node with kmalloced memory
*/
static void __init init_list(struct kmem_cache *cachep, struct kmem_cache_node *list,
int nodeid)
{
struct kmem_cache_node *ptr;
ptr = kmalloc_node(sizeof(struct kmem_cache_node), GFP_NOWAIT, nodeid);
BUG_ON(!ptr);
memcpy(ptr, list, sizeof(struct kmem_cache_node));
/*
* Do not assume that spinlocks can be initialized via memcpy:
*/
spin_lock_init(&ptr->list_lock);
MAKE_ALL_LISTS(cachep, ptr, nodeid);
cachep->node[nodeid] = ptr;
}
/*
* For setting up all the kmem_cache_node for cache whose buffer_size is same as
* size of kmem_cache_node.
*/
static void __init set_up_node(struct kmem_cache *cachep, int index)
{
int node;
for_each_online_node(node) {
cachep->node[node] = &init_kmem_cache_node[index + node];
cachep->node[node]->next_reap = jiffies +
REAPTIMEOUT_NODE +
((unsigned long)cachep) % REAPTIMEOUT_NODE;
}
}
/*
* Initialisation. Called after the page allocator have been initialised and
* before smp_init().
*/
void __init kmem_cache_init(void)
{
int i;
BUILD_BUG_ON(sizeof(((struct page *)NULL)->lru) <
sizeof(struct rcu_head));
kmem_cache = &kmem_cache_boot;
if (num_possible_nodes() == 1)
use_alien_caches = 0;
for (i = 0; i < NUM_INIT_LISTS; i++)
kmem_cache_node_init(&init_kmem_cache_node[i]);
/*
* Fragmentation resistance on low memory - only use bigger
* page orders on machines with more than 32MB of memory if
* not overridden on the command line.
*/
if (!slab_max_order_set && totalram_pages > (32 << 20) >> PAGE_SHIFT)
slab_max_order = SLAB_MAX_ORDER_HI;
/* Bootstrap is tricky, because several objects are allocated
* from caches that do not exist yet:
* 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_cache_node structures, it's replaced with a kmalloc allocated
* array at the end of the bootstrap.
* 2) Create the first kmalloc cache.
* The struct kmem_cache for the new cache is allocated normally.
* 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 kmem_cache and the first
* kmalloc cache with kmalloc allocated arrays.
* 5) Replace the __init data for kmem_cache_node 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.
*/
/* 1) create the kmem_cache */
/*
* struct kmem_cache size depends on nr_node_ids & nr_cpu_ids
*/
create_boot_cache(kmem_cache, "kmem_cache",
offsetof(struct kmem_cache, node) +
nr_node_ids * sizeof(struct kmem_cache_node *),
SLAB_HWCACHE_ALIGN);
list_add(&kmem_cache->list, &slab_caches);
slab_state = PARTIAL;
/*
* Initialize the caches that provide memory for the kmem_cache_node
* structures first. Without this, further allocations will bug.
*/
kmalloc_caches[INDEX_NODE] = create_kmalloc_cache("kmalloc-node",
kmalloc_size(INDEX_NODE), ARCH_KMALLOC_FLAGS);
slab_state = PARTIAL_NODE;
setup_kmalloc_cache_index_table();
slab_early_init = 0;
/* 5) Replace the bootstrap kmem_cache_node */
{
int nid;
for_each_online_node(nid) {
init_list(kmem_cache, &init_kmem_cache_node[CACHE_CACHE + nid], nid);
init_list(kmalloc_caches[INDEX_NODE],
&init_kmem_cache_node[SIZE_NODE + nid], nid);
}
}
create_kmalloc_caches(ARCH_KMALLOC_FLAGS);
}
void __init kmem_cache_init_late(void)
{
struct kmem_cache *cachep;
slab_state = UP;
/* 6) resize the head arrays to their final sizes */
mutex_lock(&slab_mutex);
list_for_each_entry(cachep, &slab_caches, list)
if (enable_cpucache(cachep, GFP_NOWAIT))
BUG();
mutex_unlock(&slab_mutex);
/* Done! */
slab_state = FULL;
/*
* Register a cpu startup notifier callback that initializes
* cpu_cache_get for all new cpus
*/
register_cpu_notifier(&cpucache_notifier);
#ifdef CONFIG_NUMA
/*
* Register a memory hotplug callback that initializes and frees
* node.
*/
hotplug_memory_notifier(slab_memory_callback, SLAB_CALLBACK_PRI);
#endif
/*
* The reap timers are started later, with a module init call: That part
* of the kernel is not yet operational.
*/
}
static int __init cpucache_init(void)
{
int cpu;
/*
* Register the timers that return unneeded pages to the page allocator
*/
for_each_online_cpu(cpu)
start_cpu_timer(cpu);
/* Done! */
slab_state = FULL;
return 0;
}
__initcall(cpucache_init);
static noinline void
slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid)
{
#if DEBUG
struct kmem_cache_node *n;
struct page *page;
unsigned long flags;
int node;
static DEFINE_RATELIMIT_STATE(slab_oom_rs, DEFAULT_RATELIMIT_INTERVAL,
DEFAULT_RATELIMIT_BURST);
if ((gfpflags & __GFP_NOWARN) || !__ratelimit(&slab_oom_rs))
return;
printk(KERN_WARNING
"SLAB: Unable to allocate memory on node %d (gfp=0x%x)\n",
nodeid, gfpflags);
printk(KERN_WARNING " cache: %s, object size: %d, order: %d\n",
cachep->name, cachep->size, cachep->gfporder);
for_each_kmem_cache_node(cachep, node, n) {
unsigned long active_objs = 0, num_objs = 0, free_objects = 0;
unsigned long active_slabs = 0, num_slabs = 0;
spin_lock_irqsave(&n->list_lock, flags);
list_for_each_entry(page, &n->slabs_full, lru) {
active_objs += cachep->num;
active_slabs++;
}
list_for_each_entry(page, &n->slabs_partial, lru) {
active_objs += page->active;
active_slabs++;
}
list_for_each_entry(page, &n->slabs_free, lru)
num_slabs++;
free_objects += n->free_objects;
spin_unlock_irqrestore(&n->list_lock, flags);
num_slabs += active_slabs;
num_objs = num_slabs * cachep->num;
printk(KERN_WARNING
" node %d: slabs: %ld/%ld, objs: %ld/%ld, free: %ld\n",
node, active_slabs, num_slabs, active_objs, num_objs,
free_objects);
}
#endif
}
/*
* Interface to system's page allocator. No need to hold the
* kmem_cache_node ->list_lock.
*
* If we requested dmaable memory, we will get it. Even if we
* did not request dmaable memory, we might get it, but that
* would be relatively rare and ignorable.
*/
static struct page *kmem_getpages(struct kmem_cache *cachep, gfp_t flags,
int nodeid)
{
struct page *page;
int nr_pages;
flags |= cachep->allocflags;
if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
flags |= __GFP_RECLAIMABLE;
if (memcg_charge_slab(cachep, flags, cachep->gfporder))
return NULL;
page = alloc_pages_exact_node(nodeid, flags | __GFP_NOTRACK, cachep->gfporder);
if (!page) {
memcg_uncharge_slab(cachep, cachep->gfporder);
slab_out_of_memory(cachep, flags, nodeid);
return NULL;
}
/* Record if ALLOC_NO_WATERMARKS was set when allocating the slab */
if (page_is_pfmemalloc(page))
pfmemalloc_active = true;
nr_pages = (1 << cachep->gfporder);
if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
add_zone_page_state(page_zone(page),
NR_SLAB_RECLAIMABLE, nr_pages);
else
add_zone_page_state(page_zone(page),
NR_SLAB_UNRECLAIMABLE, nr_pages);
__SetPageSlab(page);
if (page_is_pfmemalloc(page))
SetPageSlabPfmemalloc(page);
if (kmemcheck_enabled && !(cachep->flags & SLAB_NOTRACK)) {
kmemcheck_alloc_shadow(page, cachep->gfporder, flags, nodeid);
if (cachep->ctor)
kmemcheck_mark_uninitialized_pages(page, nr_pages);
else
kmemcheck_mark_unallocated_pages(page, nr_pages);
}
return page;
}
/*
* Interface to system's page release.
*/
static void kmem_freepages(struct kmem_cache *cachep, struct page *page)
{
const unsigned long nr_freed = (1 << cachep->gfporder);
kmemcheck_free_shadow(page, cachep->gfporder);
if (cachep->flags & SLAB_RECLAIM_ACCOUNT)
sub_zone_page_state(page_zone(page),
NR_SLAB_RECLAIMABLE, nr_freed);
else
sub_zone_page_state(page_zone(page),
NR_SLAB_UNRECLAIMABLE, nr_freed);
BUG_ON(!PageSlab(page));
__ClearPageSlabPfmemalloc(page);
__ClearPageSlab(page);
page_mapcount_reset(page);
page->mapping = NULL;
if (current->reclaim_state)
current->reclaim_state->reclaimed_slab += nr_freed;
__free_pages(page, cachep->gfporder);
memcg_uncharge_slab(cachep, cachep->gfporder);
}
static void kmem_rcu_free(struct rcu_head *head)
{
struct kmem_cache *cachep;
struct page *page;
page = container_of(head, struct page, rcu_head);
cachep = page->slab_cache;
kmem_freepages(cachep, page);
}
#if DEBUG
#ifdef CONFIG_DEBUG_PAGEALLOC
static void store_stackinfo(struct kmem_cache *cachep, unsigned long *addr,
unsigned long caller)
{
int size = cachep->object_size;
addr = (unsigned long *)&((char *)addr)[obj_offset(cachep)];
if (size < 5 * sizeof(unsigned long))
return;
*addr++ = 0x12345678;
*addr++ = caller;
*addr++ = smp_processor_id();
size -= 3 * sizeof(unsigned long);
{
unsigned long *sptr = &caller;
unsigned long svalue;
while (!kstack_end(sptr)) {
svalue = *sptr++;
if (kernel_text_address(svalue)) {
*addr++ = svalue;
size -= sizeof(unsigned long);
if (size <= sizeof(unsigned long))
break;
}
}
}
*addr++ = 0x87654321;
}
#endif
static void poison_obj(struct kmem_cache *cachep, void *addr, unsigned char val)
{
int size = cachep->object_size;
addr = &((char *)addr)[obj_offset(cachep)];
memset(addr, val, size);
*(unsigned char *)(addr + size - 1) = POISON_END;
}
static void dump_line(char *data, int offset, int limit)
{
int i;
unsigned char error = 0;
int bad_count = 0;
printk(KERN_ERR "%03x: ", offset);
for (i = 0; i < limit; i++) {
if (data[offset + i] != POISON_FREE) {
error = data[offset + i];
bad_count++;
}
}
print_hex_dump(KERN_CONT, "", 0, 16, 1,
&data[offset], limit, 1);
if (bad_count == 1) {
error ^= POISON_FREE;
if (!(error & (error - 1))) {
printk(KERN_ERR "Single bit error detected. Probably "
"bad RAM.\n");
#ifdef CONFIG_X86
printk(KERN_ERR "Run memtest86+ or a similar memory "
"test tool.\n");
#else
printk(KERN_ERR "Run a memory test tool.\n");
#endif
}
}
}
#endif
#if DEBUG
static void print_objinfo(struct kmem_cache *cachep, void *objp, int lines)
{
int i, size;
char *realobj;
if (cachep->flags & SLAB_RED_ZONE) {
printk(KERN_ERR "Redzone: 0x%llx/0x%llx.\n",
*dbg_redzone1(cachep, objp),
*dbg_redzone2(cachep, objp));
}
if (cachep->flags & SLAB_STORE_USER) {
printk(KERN_ERR "Last user: [<%p>](%pSR)\n",
*dbg_userword(cachep, objp),
*dbg_userword(cachep, objp));
}
realobj = (char *)objp + obj_offset(cachep);
size = cachep->object_size;
for (i = 0; i < size && lines; i += 16, lines--) {
int limit;
limit = 16;
if (i + limit > size)
limit = size - i;
dump_line(realobj, i, limit);
}
}
static void check_poison_obj(struct kmem_cache *cachep, void *objp)
{
char *realobj;
int size, i;
int lines = 0;
realobj = (char *)objp + obj_offset(cachep);
size = cachep->object_size;
for (i = 0; i < size; i++) {
char exp = POISON_FREE;
if (i == size - 1)
exp = POISON_END;
if (realobj[i] != exp) {
int limit;
/* Mismatch ! */
/* Print header */
if (lines == 0) {
printk(KERN_ERR
"Slab corruption (%s): %s start=%p, len=%d\n",
print_tainted(), cachep->name, realobj, size);
print_objinfo(cachep, objp, 0);
}
/* Hexdump the affected line */
i = (i / 16) * 16;
limit = 16;
if (i + limit > size)
limit = size - i;
dump_line(realobj, i, limit);
i += 16;
lines++;
/* Limit to 5 lines */
if (lines > 5)
break;
}
}
if (lines != 0) {
/* Print some data about the neighboring objects, if they
* exist:
*/
struct page *page = virt_to_head_page(objp);
unsigned int objnr;
objnr = obj_to_index(cachep, page, objp);
if (objnr) {
objp = index_to_obj(cachep, page, objnr - 1);
realobj = (char *)objp + obj_offset(cachep);
printk(KERN_ERR "Prev obj: start=%p, len=%d\n",
realobj, size);
print_objinfo(cachep, objp, 2);
}
if (objnr + 1 < cachep->num) {
objp = index_to_obj(cachep, page, objnr + 1);
realobj = (char *)objp + obj_offset(cachep);
printk(KERN_ERR "Next obj: start=%p, len=%d\n",
realobj, size);
print_objinfo(cachep, objp, 2);
}
}
}
#endif
#if DEBUG
static void slab_destroy_debugcheck(struct kmem_cache *cachep,
struct page *page)
{
int i;
for (i = 0; i < cachep->num; i++) {
void *objp = index_to_obj(cachep, page, i);
if (cachep->flags & SLAB_POISON) {
#ifdef CONFIG_DEBUG_PAGEALLOC
if (cachep->size % PAGE_SIZE == 0 &&
OFF_SLAB(cachep))
kernel_map_pages(virt_to_page(objp),
cachep->size / PAGE_SIZE, 1);
else
check_poison_obj(cachep, objp);
#else
check_poison_obj(cachep, objp);
#endif
}
if (cachep->flags & SLAB_RED_ZONE) {
if (*dbg_redzone1(cachep, objp) != RED_INACTIVE)
slab_error(cachep, "start of a freed object "
"was overwritten");
if (*dbg_redzone2(cachep, objp) != RED_INACTIVE)
slab_error(cachep, "end of a freed object "
"was overwritten");
}
}
}
#else
static void slab_destroy_debugcheck(struct kmem_cache *cachep,
struct page *page)
{
}
#endif
/**
* slab_destroy - destroy and release all objects in a slab
* @cachep: cache pointer being destroyed
* @page: page pointer being destroyed
*
* Destroy all the objs in a slab page, and release the mem back to the system.
* Before calling the slab page must have been unlinked from the cache. The
* kmem_cache_node ->list_lock is not held/needed.
*/
static void slab_destroy(struct kmem_cache *cachep, struct page *page)
{
void *freelist;
freelist = page->freelist;
slab_destroy_debugcheck(cachep, page);
if (unlikely(cachep->flags & SLAB_DESTROY_BY_RCU)) {
struct rcu_head *head;
/*
* RCU free overloads the RCU head over the LRU.
* slab_page has been overloeaded over the LRU,
* however it is not used from now on so that
* we can use it safely.
*/
head = (void *)&page->rcu_head;
call_rcu(head, kmem_rcu_free);
} else {
kmem_freepages(cachep, page);
}
/*
* From now on, we don't use freelist
* although actual page can be freed in rcu context
*/
if (OFF_SLAB(cachep))
kmem_cache_free(cachep->freelist_cache, freelist);
}
static void slabs_destroy(struct kmem_cache *cachep, struct list_head *list)
{
struct page *page, *n;
list_for_each_entry_safe(page, n, list, lru) {
list_del(&page->lru);
slab_destroy(cachep, page);
}
}
/**
* calculate_slab_order - calculate size (page order) of slabs
* @cachep: pointer to the cache that is being created
* @size: size of objects to be created in this cache.
* @align: required alignment for the objects.
* @flags: slab allocation flags
*
* Also calculates the number of objects per slab.
*
* This could be made much more intelligent. For now, try to avoid using
* high order pages for slabs. When the gfp() functions are more friendly
* towards high-order requests, this should be changed.
*/
static size_t calculate_slab_order(struct kmem_cache *cachep,
size_t size, size_t align, unsigned long flags)
{
unsigned long offslab_limit;
size_t left_over = 0;
int gfporder;
for (gfporder = 0; gfporder <= KMALLOC_MAX_ORDER; gfporder++) {
unsigned int num;
size_t remainder;
cache_estimate(gfporder, size, align, flags, &remainder, &num);
if (!num)
continue;
/* Can't handle number of objects more than SLAB_OBJ_MAX_NUM */
if (num > SLAB_OBJ_MAX_NUM)
break;
if (flags & CFLGS_OFF_SLAB) {
size_t freelist_size_per_obj = sizeof(freelist_idx_t);
/*
* Max number of objs-per-slab for caches which
* use off-slab slabs. Needed to avoid a possible
* looping condition in cache_grow().
*/
if (IS_ENABLED(CONFIG_DEBUG_SLAB_LEAK))
freelist_size_per_obj += sizeof(char);
offslab_limit = size;
offslab_limit /= freelist_size_per_obj;
if (num > offslab_limit)
break;
}
/* Found something acceptable - save it away */
cachep->num = num;
cachep->gfporder = gfporder;
left_over = remainder;
/*
* A VFS-reclaimable slab tends to have most allocations
* as GFP_NOFS and we really don't want to have to be allocating
* higher-order pages when we are unable to shrink dcache.
*/
if (flags & SLAB_RECLAIM_ACCOUNT)
break;
/*
* Large number of objects is good, but very large slabs are
* currently bad for the gfp()s.
*/
if (gfporder >= slab_max_order)
break;
/*
* Acceptable internal fragmentation?
*/
if (left_over * 8 <= (PAGE_SIZE << gfporder))
break;
}
return left_over;
}
static struct array_cache __percpu *alloc_kmem_cache_cpus(
struct kmem_cache *cachep, int entries, int batchcount)
{
int cpu;
size_t size;
struct array_cache __percpu *cpu_cache;
size = sizeof(void *) * entries + sizeof(struct array_cache);
cpu_cache = __alloc_percpu(size, sizeof(void *));
if (!cpu_cache)
return NULL;
for_each_possible_cpu(cpu) {
init_arraycache(per_cpu_ptr(cpu_cache, cpu),
entries, batchcount);
}
return cpu_cache;
}
static int __init_refok setup_cpu_cache(struct kmem_cache *cachep, gfp_t gfp)
{
if (slab_state >= FULL)
return enable_cpucache(cachep, gfp);
cachep->cpu_cache = alloc_kmem_cache_cpus(cachep, 1, 1);
if (!cachep->cpu_cache)
return 1;
if (slab_state == DOWN) {
/* Creation of first cache (kmem_cache). */
set_up_node(kmem_cache, CACHE_CACHE);
} else if (slab_state == PARTIAL) {
/* For kmem_cache_node */
set_up_node(cachep, SIZE_NODE);
} else {
int node;
for_each_online_node(node) {
cachep->node[node] = kmalloc_node(
sizeof(struct kmem_cache_node), gfp, node);
BUG_ON(!cachep->node[node]);
kmem_cache_node_init(cachep->node[node]);
}
}
cachep->node[numa_mem_id()]->next_reap =
jiffies + REAPTIMEOUT_NODE +
((unsigned long)cachep) % REAPTIMEOUT_NODE;
cpu_cache_get(cachep)->avail = 0;
cpu_cache_get(cachep)->limit = BOOT_CPUCACHE_ENTRIES;
cpu_cache_get(cachep)->batchcount = 1;
cpu_cache_get(cachep)->touched = 0;
cachep->batchcount = 1;
cachep->limit = BOOT_CPUCACHE_ENTRIES;
return 0;
}
unsigned long kmem_cache_flags(unsigned long object_size,
unsigned long flags, const char *name,
void (*ctor)(void *))
{
return flags;
}
struct kmem_cache *
__kmem_cache_alias(const char *name, size_t size, size_t align,
unsigned long flags, void (*ctor)(void *))
{
struct kmem_cache *cachep;
cachep = find_mergeable(size, align, flags, name, ctor);
if (cachep) {
cachep->refcount++;
/*
* Adjust the object sizes so that we clear
* the complete object on kzalloc.
*/
cachep->object_size = max_t(int, cachep->object_size, size);
}
return cachep;
}
/**
* __kmem_cache_create - Create a cache.
* @cachep: cache management descriptor
* @flags: SLAB flags
*
* Returns a ptr to the cache on success, NULL on failure.
* Cannot be called within a int, but can be interrupted.
* The @ctor is run when new pages are allocated by the cache.
*
* The flags are
*
* %SLAB_POISON - Poison the slab with a known test pattern (a5a5a5a5)
* to catch references to uninitialised memory.
*
* %SLAB_RED_ZONE - Insert `Red' zones around the allocated memory to check
* for buffer overruns.
*
* %SLAB_HWCACHE_ALIGN - Align the objects in this cache to a hardware
* cacheline. This can be beneficial if you're counting cycles as closely
* as davem.
*/
int
__kmem_cache_create (struct kmem_cache *cachep, unsigned long flags)
{
size_t left_over, freelist_size;
size_t ralign = BYTES_PER_WORD;
gfp_t gfp;
int err;
size_t size = cachep->size;
#if DEBUG
#if FORCED_DEBUG
/*
* Enable redzoning and last user accounting, except for caches with
* large objects, if the increased size would increase the object size
* above the next power of two: caches with object sizes just above a
* power of two have a significant amount of internal fragmentation.
*/
if (size < 4096 || fls(size - 1) == fls(size-1 + REDZONE_ALIGN +
2 * sizeof(unsigned long long)))
flags |= SLAB_RED_ZONE | SLAB_STORE_USER;
if (!(flags & SLAB_DESTROY_BY_RCU))
flags |= SLAB_POISON;
#endif
if (flags & SLAB_DESTROY_BY_RCU)
BUG_ON(flags & SLAB_POISON);
#endif
/*
* Check that size is in terms of words. This is needed to avoid
* unaligned accesses for some archs when redzoning is used, and makes
* sure any on-slab bufctl's are also correctly aligned.
*/
if (size & (BYTES_PER_WORD - 1)) {
size += (BYTES_PER_WORD - 1);
size &= ~(BYTES_PER_WORD - 1);
}
if (flags & SLAB_RED_ZONE) {
ralign = REDZONE_ALIGN;
/* If redzoning, ensure that the second redzone is suitably
* aligned, by adjusting the object size accordingly. */
size += REDZONE_ALIGN - 1;
size &= ~(REDZONE_ALIGN - 1);
}
/* 3) caller mandated alignment */
if (ralign < cachep->align) {
ralign = cachep->align;
}
/* disable debug if necessary */
if (ralign > __alignof__(unsigned long long))
flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
/*
* 4) Store it.
*/
cachep->align = ralign;
if (slab_is_available())
gfp = GFP_KERNEL;
else
gfp = GFP_NOWAIT;
#if DEBUG
/*
* Both debugging options require word-alignment which is calculated
* into align above.
*/
if (flags & SLAB_RED_ZONE) {
/* add space for red zone words */
cachep->obj_offset += sizeof(unsigned long long);
size += 2 * sizeof(unsigned long long);
}
if (flags & SLAB_STORE_USER) {
/* user store requires one word storage behind the end of
* the real object. But if the second red zone needs to be
* aligned to 64 bits, we must allow that much space.
*/
if (flags & SLAB_RED_ZONE)
size += REDZONE_ALIGN;
else
size += BYTES_PER_WORD;
}
#if FORCED_DEBUG && defined(CONFIG_DEBUG_PAGEALLOC)
/*
* To activate debug pagealloc, off-slab management is necessary
* requirement. In early phase of initialization, small sized slab
* doesn't get initialized so it would not be possible. So, we need
* to check size >= 256. It guarantees that all necessary small
* sized slab is initialized in current slab initialization sequence.
*/
if (!slab_early_init && size >= kmalloc_size(INDEX_NODE) &&
size >= 256 && 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
#endif
/*
* Determine if the slab management is 'on' or 'off' slab.
* (bootstrapping cannot cope with offslab caches so don't do
* it too early on. Always use on-slab management when
* SLAB_NOLEAKTRACE to avoid recursive calls into kmemleak)
*/
if ((size >= (PAGE_SIZE >> 5)) && !slab_early_init &&
!(flags & SLAB_NOLEAKTRACE))
/*
* Size is large, assume best to place the slab management obj
* off-slab (should allow better packing of objs).
*/
flags |= CFLGS_OFF_SLAB;
size = ALIGN(size, cachep->align);
/*
* We should restrict the number of objects in a slab to implement
* byte sized index. Refer comment on SLAB_OBJ_MIN_SIZE definition.
*/
if (FREELIST_BYTE_INDEX && size < SLAB_OBJ_MIN_SIZE)
size = ALIGN(SLAB_OBJ_MIN_SIZE, cachep->align);
left_over = calculate_slab_order(cachep, size, cachep->align, flags);
if (!cachep->num)
return -E2BIG;
freelist_size = calculate_freelist_size(cachep->num, cachep->align);
/*
* If the slab has been placed off-slab, and we have enough space then
* move it on-slab. This is at the expense of any extra colouring.
*/
if (flags & CFLGS_OFF_SLAB && left_over >= freelist_size) {
flags &= ~CFLGS_OFF_SLAB;
left_over -= freelist_size;
}
if (flags & CFLGS_OFF_SLAB) {
/* really off slab. No need for manual alignment */
freelist_size = calculate_freelist_size(cachep->num, 0);
#ifdef CONFIG_PAGE_POISONING
/* If we're going to use the generic kernel_map_pages()
* poisoning, then it's going to smash the contents of
* the redzone and userword anyhow, so switch them off.
*/
if (size % PAGE_SIZE == 0 && flags & SLAB_POISON)
flags &= ~(SLAB_RED_ZONE | SLAB_STORE_USER);
#endif
}
cachep->colour_off = cache_line_size();
/* Offset must be a multiple of the alignment. */
if (cachep->colour_off < cachep->align)
cachep->colour_off = cachep->align;
cachep->colour = left_over / cachep->colour_off;
cachep->freelist_size = freelist_size;
cachep->flags = flags;
cachep->allocflags = __GFP_COMP;
if (CONFIG_ZONE_DMA_FLAG && (flags & SLAB_CACHE_DMA))
cachep->allocflags |= GFP_DMA;
cachep->size = size;
cachep->reciprocal_buffer_size = reciprocal_value(size);
if (flags & CFLGS_OFF_SLAB) {
cachep->freelist_cache = kmalloc_slab(freelist_size, 0u);
/*
* This is a possibility for one of the kmalloc_{dma,}_caches.
* But since we go off slab only for object size greater than
* PAGE_SIZE/8, and kmalloc_{dma,}_caches get created
* in ascending order,this should not happen at all.
* But leave a BUG_ON for some lucky dude.
*/
BUG_ON(ZERO_OR_NULL_PTR(cachep->freelist_cache));
}
err = setup_cpu_cache(cachep, gfp);
if (err) {
__kmem_cache_shutdown(cachep);
return err;
}
return 0;
}
#if DEBUG
static void check_irq_off(void)
{
BUG_ON(!irqs_disabled());
}
static void check_irq_on(void)
{
BUG_ON(irqs_disabled());
}
static void check_spinlock_acquired(struct kmem_cache *cachep)
{
#ifdef CONFIG_SMP
check_irq_off();
assert_spin_locked(&get_node(cachep, numa_mem_id())->list_lock);
#endif
}
static void check_spinlock_acquired_node(struct kmem_cache *cachep, int node)
{
#ifdef CONFIG_SMP
check_irq_off();
assert_spin_locked(&get_node(cachep, node)->list_lock);
#endif
}
#else
#define check_irq_off() do { } while(0)
#define check_irq_on() do { } while(0)
#define check_spinlock_acquired(x) do { } while(0)
#define check_spinlock_acquired_node(x, y) do { } while(0)
#endif
static void drain_array(struct kmem_cache *cachep, struct kmem_cache_node *n,
struct array_cache *ac,
int force, int node);
static void do_drain(void *arg)
{
struct kmem_cache *cachep = arg;
struct array_cache *ac;
int node = numa_mem_id();
struct kmem_cache_node *n;
LIST_HEAD(list);
check_irq_off();
ac = cpu_cache_get(cachep);
n = get_node(cachep, node);
spin_lock(&n->list_lock);
free_block(cachep, ac->entry, ac->avail, node, &list);
spin_unlock(&n->list_lock);
slabs_destroy(cachep, &list);
ac->avail = 0;
}
static void drain_cpu_caches(struct kmem_cache *cachep)
{
struct kmem_cache_node *n;
int node;
on_each_cpu(do_drain, cachep, 1);
check_irq_on();
for_each_kmem_cache_node(cachep, node, n)
if (n->alien)
drain_alien_cache(cachep, n->alien);
for_each_kmem_cache_node(cachep, node, n)
drain_array(cachep, n, n->shared, 1, node);
}
/*
* Remove slabs from the list of free slabs.
* Specify the number of slabs to drain in tofree.
*
* Returns the actual number of slabs released.
*/
static int drain_freelist(struct kmem_cache *cache,
struct kmem_cache_node *n, int tofree)
{
struct list_head *p;
int nr_freed;
struct page *page;
nr_freed = 0;
while (nr_freed < tofree && !list_empty(&n->slabs_free)) {
spin_lock_irq(&n->list_lock);
p = n->slabs_free.prev;
if (p == &n->slabs_free) {
spin_unlock_irq(&n->list_lock);
goto out;
}
page = list_entry(p, struct page, lru);
#if DEBUG
BUG_ON(page->active);
#endif
list_del(&page->lru);
/*
* Safe to drop the lock. The slab is no longer linked
* to the cache.
*/
n->free_objects -= cache->num;
spin_unlock_irq(&n->list_lock);
slab_destroy(cache, page);
nr_freed++;
}
out:
return nr_freed;
}
int __kmem_cache_shrink(struct kmem_cache *cachep, bool deactivate)
{
int ret = 0;
int node;
struct kmem_cache_node *n;
drain_cpu_caches(cachep);
check_irq_on();
for_each_kmem_cache_node(cachep, node, n) {
drain_freelist(cachep, n, slabs_tofree(cachep, n));
ret += !list_empty(&n->slabs_full) ||
!list_empty(&n->slabs_partial);
}
return (ret ? 1 : 0);
}
int __kmem_cache_shutdown(struct kmem_cache *cachep)
{
int i;
struct kmem_cache_node *n;
int rc = __kmem_cache_shrink(cachep, false);
if (rc)
return rc;
free_percpu(cachep->cpu_cache);
/* NUMA: free the node structures */
for_each_kmem_cache_node(cachep, i, n) {
kfree(n->shared);
free_alien_cache(n->alien);
kfree(n);
cachep->node[i] = NULL;
}
return 0;
}
/*
* Get the memory for a slab management obj.
*
* For a slab cache when the slab descriptor is off-slab, the
* slab descriptor can't come from the same cache which is being created,
* Because if it is the case, that means we defer the creation of
* the kmalloc_{dma,}_cache of size sizeof(slab descriptor) to this point.
* And we eventually call down to __kmem_cache_create(), which
* in turn looks up in the kmalloc_{dma,}_caches for the disired-size one.
* This is a "chicken-and-egg" problem.
*
* So the off-slab slab descriptor shall come from the kmalloc_{dma,}_caches,
* which are all initialized during kmem_cache_init().
*/
static void *alloc_slabmgmt(struct kmem_cache *cachep,
struct page *page, int colour_off,
gfp_t local_flags, int nodeid)
{
void *freelist;
void *addr = page_address(page);
if (OFF_SLAB(cachep)) {
/* Slab management obj is off-slab. */
freelist = kmem_cache_alloc_node(cachep->freelist_cache,
local_flags, nodeid);
if (!freelist)
return NULL;
} else {
freelist = addr + colour_off;
colour_off += cachep->freelist_size;
}
page->active = 0;
page->s_mem = addr + colour_off;
return freelist;
}
static inline freelist_idx_t get_free_obj(struct page *page, unsigned int idx)
{
return ((freelist_idx_t *)page->freelist)[idx];
}
static inline void set_free_obj(struct page *page,
unsigned int idx, freelist_idx_t val)
{
((freelist_idx_t *)(page->freelist))[idx] = val;
}
static void cache_init_objs(struct kmem_cache *cachep,
struct page *page)
{
int i;
for (i = 0; i < cachep->num; i++) {
void *objp = index_to_obj(cachep, page, i);
#if DEBUG
/* need to poison the objs? */
if (cachep->flags & SLAB_POISON)
poison_obj(cachep, objp, POISON_FREE);
if (cachep->flags & SLAB_STORE_USER)
*dbg_userword(cachep, objp) = NULL;
if (cachep->flags & SLAB_RED_ZONE) {
*dbg_redzone1(cachep, objp) = RED_INACTIVE;
*dbg_redzone2(cachep, objp) = RED_INACTIVE;
}
/*
* Constructors are not allowed to allocate memory from the same
* cache which they are a constructor for. Otherwise, deadlock.
* They must also be threaded.
*/
if (cachep->ctor && !(cachep->flags & SLAB_POISON))
cachep->ctor(objp + obj_offset(cachep));
if (cachep->flags & SLAB_RED_ZONE) {
if (*dbg_redzone2(cachep, objp) != RED_INACTIVE)
slab_error(cachep, "constructor overwrote the"
" end of an object");
if (*dbg_redzone1(cachep, objp) != RED_INACTIVE)
slab_error(cachep, "constructor overwrote the"
" start of an object");
}
if ((cachep->size % PAGE_SIZE) == 0 &&
OFF_SLAB(cachep) && cachep->flags & SLAB_POISON)
kernel_map_pages(virt_to_page(objp),
cachep->size / PAGE_SIZE, 0);
#else
if (cachep->ctor)
cachep->ctor(objp);
#endif
set_obj_status(page, i, OBJECT_FREE);
set_free_obj(page, i, i);
}
}
static void kmem_flagcheck(struct kmem_cache *cachep, gfp_t flags)
{
if (CONFIG_ZONE_DMA_FLAG) {
if (flags & GFP_DMA)
BUG_ON(!(cachep->allocflags & GFP_DMA));
else
BUG_ON(cachep->allocflags & GFP_DMA);
}
}
static void *slab_get_obj(struct kmem_cache *cachep, struct page *page,
int nodeid)
{
void *objp;
objp = index_to_obj(cachep, page, get_free_obj(page, page->active));
page->active++;
#if DEBUG
WARN_ON(page_to_nid(virt_to_page(objp)) != nodeid);
#endif
return objp;
}
static void slab_put_obj(struct kmem_cache *cachep, struct page *page,
void *objp, int nodeid)
{
unsigned int objnr = obj_to_index(cachep, page, objp);
#if DEBUG
unsigned int i;
/* Verify that the slab belongs to the intended node */
WARN_ON(page_to_nid(virt_to_page(objp)) != nodeid);
/* Verify double free bug */
for (i = page->active; i < cachep->num; i++) {
if (get_free_obj(page, i) == objnr) {
printk(KERN_ERR "slab: double free detected in cache "
"'%s', objp %p\n", cachep->name, objp);
BUG();
}
}
#endif
page->active--;
set_free_obj(page, page->active, objnr);
}
/*
* Map pages beginning at addr to the given cache and slab. This is required
* for the slab allocator to be able to lookup the cache and slab of a
* virtual address for kfree, ksize, and slab debugging.
*/
static void slab_map_pages(struct kmem_cache *cache, struct page *page,
void *freelist)
{
page->slab_cache = cache;
page->freelist = freelist;
}
/*
* Grow (by 1) the number of slabs within a cache. This is called by
* kmem_cache_alloc() when there are no active objs left in a cache.
*/
static int cache_grow(struct kmem_cache *cachep,
gfp_t flags, int nodeid, struct page *page)
{
void *freelist;
size_t offset;
gfp_t local_flags;
struct kmem_cache_node *n;
/*
* Be lazy and only check for valid flags here, keeping it out of the
* critical path in kmem_cache_alloc().
*/
if (unlikely(flags & GFP_SLAB_BUG_MASK)) {
pr_emerg("gfp: %u\n", flags & GFP_SLAB_BUG_MASK);
BUG();
}
local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK);
/* Take the node list lock to change the colour_next on this node */
check_irq_off();
n = get_node(cachep, nodeid);
spin_lock(&n->list_lock);
/* Get colour for the slab, and cal the next value. */
offset = n->colour_next;
n->colour_next++;
if (n->colour_next >= cachep->colour)
n->colour_next = 0;
spin_unlock(&n->list_lock);
offset *= cachep->colour_off;
if (local_flags & __GFP_WAIT)
local_irq_enable();
/*
* The test for missing atomic flag is performed here, rather than
* the more obvious place, simply to reduce the critical path length
* in kmem_cache_alloc(). If a caller is seriously mis-behaving they
* will eventually be caught here (where it matters).
*/
kmem_flagcheck(cachep, flags);
/*
* Get mem for the objs. Attempt to allocate a physical page from
* 'nodeid'.
*/
if (!page)
page = kmem_getpages(cachep, local_flags, nodeid);
if (!page)
goto failed;
/* Get slab management. */
freelist = alloc_slabmgmt(cachep, page, offset,
local_flags & ~GFP_CONSTRAINT_MASK, nodeid);
if (!freelist)
goto opps1;
slab_map_pages(cachep, page, freelist);
cache_init_objs(cachep, page);
if (local_flags & __GFP_WAIT)
local_irq_disable();
check_irq_off();
spin_lock(&n->list_lock);
/* Make slab active. */
list_add_tail(&page->lru, &(n->slabs_free));
STATS_INC_GROWN(cachep);
n->free_objects += cachep->num;
spin_unlock(&n->list_lock);
return 1;
opps1:
kmem_freepages(cachep, page);
failed:
if (local_flags & __GFP_WAIT)
local_irq_disable();
return 0;
}
#if DEBUG
/*
* Perform extra freeing checks:
* - detect bad pointers.
* - POISON/RED_ZONE checking
*/
static void kfree_debugcheck(const void *objp)
{
if (!virt_addr_valid(objp)) {
printk(KERN_ERR "kfree_debugcheck: out of range ptr %lxh.\n",
(unsigned long)objp);
BUG();
}
}
static inline void verify_redzone_free(struct kmem_cache *cache, void *obj)
{
unsigned long long redzone1, redzone2;
redzone1 = *dbg_redzone1(cache, obj);
redzone2 = *dbg_redzone2(cache, obj);
/*
* Redzone is ok.
*/
if (redzone1 == RED_ACTIVE && redzone2 == RED_ACTIVE)
return;
if (redzone1 == RED_INACTIVE && redzone2 == RED_INACTIVE)
slab_error(cache, "double free detected");
else
slab_error(cache, "memory outside object was overwritten");
printk(KERN_ERR "%p: redzone 1:0x%llx, redzone 2:0x%llx.\n",
obj, redzone1, redzone2);
}
static void *cache_free_debugcheck(struct kmem_cache *cachep, void *objp,
unsigned long caller)
{
unsigned int objnr;
struct page *page;
BUG_ON(virt_to_cache(objp) != cachep);
objp -= obj_offset(cachep);
kfree_debugcheck(objp);
page = virt_to_head_page(objp);
if (cachep->flags & SLAB_RED_ZONE) {
verify_redzone_free(cachep, objp);
*dbg_redzone1(cachep, objp) = RED_INACTIVE;
*dbg_redzone2(cachep, objp) = RED_INACTIVE;
}
if (cachep->flags & SLAB_STORE_USER)
*dbg_userword(cachep, objp) = (void *)caller;
objnr = obj_to_index(cachep, page, objp);
BUG_ON(objnr >= cachep->num);
BUG_ON(objp != index_to_obj(cachep, page, objnr));
set_obj_status(page, objnr, OBJECT_FREE);
if (cachep->flags & SLAB_POISON) {
#ifdef CONFIG_DEBUG_PAGEALLOC
if ((cachep->size % PAGE_SIZE)==0 && OFF_SLAB(cachep)) {
store_stackinfo(cachep, objp, caller);
kernel_map_pages(virt_to_page(objp),
cachep->size / PAGE_SIZE, 0);
} else {
poison_obj(cachep, objp, POISON_FREE);
}
#else
poison_obj(cachep, objp, POISON_FREE);
#endif
}
return objp;
}
#else
#define kfree_debugcheck(x) do { } while(0)
#define cache_free_debugcheck(x,objp,z) (objp)
#endif
static void *cache_alloc_refill(struct kmem_cache *cachep, gfp_t flags,
bool force_refill)
{
int batchcount;
struct kmem_cache_node *n;
struct array_cache *ac;
int node;
check_irq_off();
node = numa_mem_id();
if (unlikely(force_refill))
goto force_grow;
retry:
ac = cpu_cache_get(cachep);
batchcount = ac->batchcount;
if (!ac->touched && batchcount > BATCHREFILL_LIMIT) {
/*
* If there was little recent activity on this cache, then
* perform only a partial refill. Otherwise we could generate
* refill bouncing.
*/
batchcount = BATCHREFILL_LIMIT;
}
n = get_node(cachep, node);
BUG_ON(ac->avail > 0 || !n);
spin_lock(&n->list_lock);
/* See if we can refill from the shared array */
if (n->shared && transfer_objects(ac, n->shared, batchcount)) {
n->shared->touched = 1;
goto alloc_done;
}
while (batchcount > 0) {
struct list_head *entry;
struct page *page;
/* Get slab alloc is to come from. */
entry = n->slabs_partial.next;
if (entry == &n->slabs_partial) {
n->free_touched = 1;
entry = n->slabs_free.next;
if (entry == &n->slabs_free)
goto must_grow;
}
page = list_entry(entry, struct page, lru);
check_spinlock_acquired(cachep);
/*
* The slab was either on partial or free list so
* there must be at least one object available for
* allocation.
*/
BUG_ON(page->active >= cachep->num);
while (page->active < cachep->num && batchcount--) {
STATS_INC_ALLOCED(cachep);
STATS_INC_ACTIVE(cachep);
STATS_SET_HIGH(cachep);
ac_put_obj(cachep, ac, slab_get_obj(cachep, page,
node));
}
/* move slabp to correct slabp list: */
list_del(&page->lru);
if (page->active == cachep->num)
list_add(&page->lru, &n->slabs_full);
else
list_add(&page->lru, &n->slabs_partial);
}
must_grow:
n->free_objects -= ac->avail;
alloc_done:
spin_unlock(&n->list_lock);
if (unlikely(!ac->avail)) {
int x;
force_grow:
x = cache_grow(cachep, gfp_exact_node(flags), node, NULL);
/* cache_grow can reenable interrupts, then ac could change. */
ac = cpu_cache_get(cachep);
node = numa_mem_id();
/* no objects in sight? abort */
if (!x && (ac->avail == 0 || force_refill))
return NULL;
if (!ac->avail) /* objects refilled by interrupt? */
goto retry;
}
ac->touched = 1;
return ac_get_obj(cachep, ac, flags, force_refill);
}
static inline void cache_alloc_debugcheck_before(struct kmem_cache *cachep,
gfp_t flags)
{
might_sleep_if(flags & __GFP_WAIT);
#if DEBUG
kmem_flagcheck(cachep, flags);
#endif
}
#if DEBUG
static void *cache_alloc_debugcheck_after(struct kmem_cache *cachep,
gfp_t flags, void *objp, unsigned long caller)
{
struct page *page;
if (!objp)
return objp;
if (cachep->flags & SLAB_POISON) {
#ifdef CONFIG_DEBUG_PAGEALLOC
if ((cachep->size % PAGE_SIZE) == 0 && OFF_SLAB(cachep))
kernel_map_pages(virt_to_page(objp),
cachep->size / PAGE_SIZE, 1);
else
check_poison_obj(cachep, objp);
#else
check_poison_obj(cachep, objp);
#endif
poison_obj(cachep, objp, POISON_INUSE);
}
if (cachep->flags & SLAB_STORE_USER)
*dbg_userword(cachep, objp) = (void *)caller;
if (cachep->flags & SLAB_RED_ZONE) {
if (*dbg_redzone1(cachep, objp) != RED_INACTIVE ||
*dbg_redzone2(cachep, objp) != RED_INACTIVE) {
slab_error(cachep, "double free, or memory outside"
" object was overwritten");
printk(KERN_ERR
"%p: redzone 1:0x%llx, redzone 2:0x%llx\n",
objp, *dbg_redzone1(cachep, objp),
*dbg_redzone2(cachep, objp));
}
*dbg_redzone1(cachep, objp) = RED_ACTIVE;
*dbg_redzone2(cachep, objp) = RED_ACTIVE;
}
page = virt_to_head_page(objp);
set_obj_status(page, obj_to_index(cachep, page, objp), OBJECT_ACTIVE);
objp += obj_offset(cachep);
if (cachep->ctor && cachep->flags & SLAB_POISON)
cachep->ctor(objp);
if (ARCH_SLAB_MINALIGN &&
((unsigned long)objp & (ARCH_SLAB_MINALIGN-1))) {
printk(KERN_ERR "0x%p: not aligned to ARCH_SLAB_MINALIGN=%d\n",
objp, (int)ARCH_SLAB_MINALIGN);
}
return objp;
}
#else
#define cache_alloc_debugcheck_after(a,b,objp,d) (objp)
#endif
static bool slab_should_failslab(struct kmem_cache *cachep, gfp_t flags)
{
if (unlikely(cachep == kmem_cache))
return false;
return should_failslab(cachep->object_size, flags, cachep->flags);
}
static inline void *____cache_alloc(struct kmem_cache *cachep, gfp_t flags)
{
void *objp;
struct array_cache *ac;
bool force_refill = false;
check_irq_off();
ac = cpu_cache_get(cachep);
if (likely(ac->avail)) {
ac->touched = 1;
objp = ac_get_obj(cachep, ac, flags, false);
/*
* Allow for the possibility all avail objects are not allowed
* by the current flags
*/
if (objp) {
STATS_INC_ALLOCHIT(cachep);
goto out;
}
force_refill = true;
}
STATS_INC_ALLOCMISS(cachep);
objp = cache_alloc_refill(cachep, flags, force_refill);
/*
* the 'ac' may be updated by cache_alloc_refill(),
* and kmemleak_erase() requires its correct value.
*/
ac = cpu_cache_get(cachep);
out:
/*
* 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.
*/
if (objp)
kmemleak_erase(&ac->entry[ac->avail]);
return objp;
}
#ifdef CONFIG_NUMA
/*
* Try allocating on another node if PFA_SPREAD_SLAB is a mempolicy is set.
*
* If we are in_interrupt, then process context, including cpusets and
* mempolicy, may not apply and should not be used for allocation policy.
*/
static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags)
{
int nid_alloc, nid_here;
if (in_interrupt() || (flags & __GFP_THISNODE))
return NULL;
nid_alloc = nid_here = numa_mem_id();
if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD))
nid_alloc = cpuset_slab_spread_node();
else if (current->mempolicy)
nid_alloc = mempolicy_slab_node();
if (nid_alloc != nid_here)
return ____cache_alloc_node(cachep, flags, nid_alloc);
return NULL;
}
/*
* Fallback function if there was no memory available and no objects on a
* certain node and fall back is permitted. First we scan all the
* available node for available objects. If that fails then we
* perform an allocation without specifying a node. This allows the page
* allocator to do its reclaim / fallback magic. We then insert the
* slab into the proper nodelist and then allocate from it.
*/
static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags)
{
struct zonelist *zonelist;
gfp_t local_flags;
struct zoneref *z;
struct zone *zone;
enum zone_type high_zoneidx = gfp_zone(flags);
void *obj = NULL;
int nid;
unsigned int cpuset_mems_cookie;
if (flags & __GFP_THISNODE)
return NULL;
local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK);
retry_cpuset:
cpuset_mems_cookie = read_mems_allowed_begin();
zonelist = node_zonelist(mempolicy_slab_node(), flags);
retry:
/*
* Look through allowed nodes for objects available
* from existing per node queues.
*/
for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) {
nid = zone_to_nid(zone);
if (cpuset_zone_allowed(zone, flags) &&
get_node(cache, nid) &&
get_node(cache, nid)->free_objects) {
obj = ____cache_alloc_node(cache,
gfp_exact_node(flags), nid);
if (obj)
break;
}
}
if (!obj) {
/*
* This allocation will be performed within the constraints
* of the current cpuset / memory policy requirements.
* We may trigger various forms of reclaim on the allowed
* set and go into memory reserves if necessary.
*/
struct page *page;
if (local_flags & __GFP_WAIT)
local_irq_enable();
kmem_flagcheck(cache, flags);
page = kmem_getpages(cache, local_flags, numa_mem_id());
if (local_flags & __GFP_WAIT)
local_irq_disable();
if (page) {
/*
* Insert into the appropriate per node queues
*/
nid = page_to_nid(page);
if (cache_grow(cache, flags, nid, page)) {
obj = ____cache_alloc_node(cache,
gfp_exact_node(flags), nid);
if (!obj)
/*
* Another processor may allocate the
* objects in the slab since we are
* not holding any locks.
*/
goto retry;
} else {
/* cache_grow already freed obj */
obj = NULL;
}
}
}
if (unlikely(!obj && read_mems_allowed_retry(cpuset_mems_cookie)))
goto retry_cpuset;
return obj;
}
/*
* A interface to enable slab creation on nodeid
*/
static void *____cache_alloc_node(struct kmem_cache *cachep, gfp_t flags,
int nodeid)
{
struct list_head *entry;
struct page *page;
struct kmem_cache_node *n;
void *obj;
int x;
VM_BUG_ON(nodeid < 0 || nodeid >= MAX_NUMNODES);
n = get_node(cachep, nodeid);
BUG_ON(!n);
retry:
check_irq_off();
spin_lock(&n->list_lock);
entry = n->slabs_partial.next;
if (entry == &n->slabs_partial) {
n->free_touched = 1;
entry = n->slabs_free.next;
if (entry == &n->slabs_free)
goto must_grow;
}
page = list_entry(entry, struct page, lru);
check_spinlock_acquired_node(cachep, nodeid);
STATS_INC_NODEALLOCS(cachep);
STATS_INC_ACTIVE(cachep);
STATS_SET_HIGH(cachep);
BUG_ON(page->active == cachep->num);
obj = slab_get_obj(cachep, page, nodeid);
n->free_objects--;
/* move slabp to correct slabp list: */
list_del(&page->lru);
if (page->active == cachep->num)
list_add(&page->lru, &n->slabs_full);
else
list_add(&page->lru, &n->slabs_partial);
spin_unlock(&n->list_lock);
goto done;
must_grow:
spin_unlock(&n->list_lock);
x = cache_grow(cachep, gfp_exact_node(flags), nodeid, NULL);
if (x)
goto retry;
return fallback_alloc(cachep, flags);
done:
return obj;
}
static __always_inline void *
slab_alloc_node(struct kmem_cache *cachep, gfp_t flags, int nodeid,
unsigned long caller)
{
unsigned long save_flags;
void *ptr;
int slab_node = numa_mem_id();
flags &= gfp_allowed_mask;
lockdep_trace_alloc(flags);
if (slab_should_failslab(cachep, flags))
return NULL;
cachep = memcg_kmem_get_cache(cachep, flags);
cache_alloc_debugcheck_before(cachep, flags);
local_irq_save(save_flags);
if (nodeid == NUMA_NO_NODE)
nodeid = slab_node;
if (unlikely(!get_node(cachep, nodeid))) {
/* Node not bootstrapped yet */
ptr = fallback_alloc(cachep, flags);
goto out;
}
if (nodeid == slab_node) {
/*
* Use the locally cached objects if possible.
* However ____cache_alloc does not allow fallback
* to other nodes. It may fail while we still have
* objects on other nodes available.
*/
ptr = ____cache_alloc(cachep, flags);
if (ptr)
goto out;
}
/* ___cache_alloc_node can fall back to other nodes */
ptr = ____cache_alloc_node(cachep, flags, nodeid);
out:
local_irq_restore(save_flags);
ptr = cache_alloc_debugcheck_after(cachep, flags, ptr, caller);
kmemleak_alloc_recursive(ptr, cachep->object_size, 1, cachep->flags,
flags);
if (likely(ptr)) {
kmemcheck_slab_alloc(cachep, flags, ptr, cachep->object_size);
if (unlikely(flags & __GFP_ZERO))
memset(ptr, 0, cachep->object_size);
}
memcg_kmem_put_cache(cachep);
return ptr;
}
static __always_inline void *
__do_cache_alloc(struct kmem_cache *cache, gfp_t flags)
{
void *objp;
if (current->mempolicy || cpuset_do_slab_mem_spread()) {
objp = alternate_node_alloc(cache, flags);
if (objp)
goto out;
}
objp = ____cache_alloc(cache, flags);
/*
* We may just have run out of memory on the local node.
* ____cache_alloc_node() knows how to locate memory on other nodes
*/
if (!objp)
objp = ____cache_alloc_node(cache, flags, numa_mem_id());
out:
return objp;
}
#else
static __always_inline void *
__do_cache_alloc(struct kmem_cache *cachep, gfp_t flags)
{
return ____cache_alloc(cachep, flags);
}
#endif /* CONFIG_NUMA */
static __always_inline void *
slab_alloc(struct kmem_cache *cachep, gfp_t flags, unsigned long caller)
{
unsigned long save_flags;
void *objp;
flags &= gfp_allowed_mask;
lockdep_trace_alloc(flags);
if (slab_should_failslab(cachep, flags))
return NULL;
cachep = memcg_kmem_get_cache(cachep, flags);
cache_alloc_debugcheck_before(cachep, flags);
local_irq_save(save_flags);
objp = __do_cache_alloc(cachep, flags);
local_irq_restore(save_flags);
objp = cache_alloc_debugcheck_after(cachep, flags, objp, caller);
kmemleak_alloc_recursive(objp, cachep->object_size, 1, cachep->flags,
flags);
prefetchw(objp);
if (likely(objp)) {
kmemcheck_slab_alloc(cachep, flags, objp, cachep->object_size);
if (unlikely(flags & __GFP_ZERO))
memset(objp, 0, cachep->object_size);
}
memcg_kmem_put_cache(cachep);
return objp;
}
/*
* Caller needs to acquire correct kmem_cache_node's list_lock
* @list: List of detached free slabs should be freed by caller
*/
static void free_block(struct kmem_cache *cachep, void **objpp,
int nr_objects, int node, struct list_head *list)
{
int i;
struct kmem_cache_node *n = get_node(cachep, node);
for (i = 0; i < nr_objects; i++) {
void *objp;
struct page *page;
clear_obj_pfmemalloc(&objpp[i]);
objp = objpp[i];
page = virt_to_head_page(objp);
list_del(&page->lru);
check_spinlock_acquired_node(cachep, node);
slab_put_obj(cachep, page, objp, node);
STATS_DEC_ACTIVE(cachep);
n->free_objects++;
/* fixup slab chains */
if (page->active == 0) {
if (n->free_objects > n->free_limit) {
n->free_objects -= cachep->num;
list_add_tail(&page->lru, list);
} else {
list_add(&page->lru, &n->slabs_free);
}
} else {
/* Unconditionally move a slab to the end of the
* partial list on free - maximum time for the
* other objects to be freed, too.
*/
list_add_tail(&page->lru, &n->slabs_partial);
}
}
}
static void cache_flusharray(struct kmem_cache *cachep, struct array_cache *ac)
{
int batchcount;
struct kmem_cache_node *n;
int node = numa_mem_id();
LIST_HEAD(list);
batchcount = ac->batchcount;
#if DEBUG
BUG_ON(!batchcount || batchcount > ac->avail);
#endif
check_irq_off();
n = get_node(cachep, node);
spin_lock(&n->list_lock);
if (n->shared) {
struct array_cache *shared_array = n->shared;
int max = shared_array->limit - shared_array->avail;
if (max) {
if (batchcount > max)
batchcount = max;
memcpy(&(shared_array->entry[shared_array->avail]),
ac->entry, sizeof(void *) * batchcount);
shared_array->avail += batchcount;
goto free_done;
}
}
free_block(cachep, ac->entry, batchcount, node, &list);
free_done:
#if STATS
{
int i = 0;
struct list_head *p;
p = n->slabs_free.next;
while (p != &(n->slabs_free)) {
struct page *page;
page = list_entry(p, struct page, lru);
BUG_ON(page->active);
i++;
p = p->next;
}
STATS_SET_FREEABLE(cachep, i);
}
#endif
spin_unlock(&n->list_lock);
slabs_destroy(cachep, &list);
ac->avail -= batchcount;
memmove(ac->entry, &(ac->entry[batchcount]), sizeof(void *)*ac->avail);
}
mm18.txt
最新推荐文章于 2024-07-26 12:28:02 发布