* Copyright (c) 2004, Luke Kenneth Casson Leighton <lkcl@lkcl.net>
* Copyright (c) 2004 Red Hat, Inc., James Morris <jmorris@redhat.com>
*
+ * tiny-shmem:
+ * Copyright (c) 2004, 2008 Matt Mackall <mpm@selenic.com>
+ *
* This file is released under the GPL.
*/
+#include <linux/fs.h>
+#include <linux/init.h>
+#include <linux/vfs.h>
+#include <linux/mount.h>
+#include <linux/pagemap.h>
+#include <linux/file.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/swap.h>
+
+static struct vfsmount *shm_mnt;
+
+#ifdef CONFIG_SHMEM
/*
* This virtual memory filesystem is heavily based on the ramfs. It
* extends ramfs by the ability to use swap and honor resource limits
* which makes it a completely usable filesystem.
*/
-#include <linux/module.h>
-#include <linux/init.h>
-#include <linux/fs.h>
#include <linux/xattr.h>
+#include <linux/exportfs.h>
+#include <linux/posix_acl.h>
#include <linux/generic_acl.h>
-#include <linux/mm.h>
#include <linux/mman.h>
-#include <linux/file.h>
-#include <linux/swap.h>
-#include <linux/pagemap.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <linux/backing-dev.h>
#include <linux/shmem_fs.h>
-#include <linux/mount.h>
#include <linux/writeback.h>
-#include <linux/vfs.h>
#include <linux/blkdev.h>
+#include <linux/pagevec.h>
+#include <linux/percpu_counter.h>
+#include <linux/splice.h>
#include <linux/security.h>
#include <linux/swapops.h>
#include <linux/mempolicy.h>
#include <linux/ctype.h>
#include <linux/migrate.h>
#include <linux/highmem.h>
+#include <linux/seq_file.h>
+#include <linux/magic.h>
#include <asm/uaccess.h>
-#include <asm/div64.h>
#include <asm/pgtable.h>
-/* This magic number is used in glibc for posix shared memory */
-#define TMPFS_MAGIC 0x01021994
-
-#define ENTRIES_PER_PAGE (PAGE_CACHE_SIZE/sizeof(unsigned long))
-#define ENTRIES_PER_PAGEPAGE (ENTRIES_PER_PAGE*ENTRIES_PER_PAGE)
#define BLOCKS_PER_PAGE (PAGE_CACHE_SIZE/512)
-
-#define SHMEM_MAX_INDEX (SHMEM_NR_DIRECT + (ENTRIES_PER_PAGEPAGE/2) * (ENTRIES_PER_PAGE+1))
-#define SHMEM_MAX_BYTES ((unsigned long long)SHMEM_MAX_INDEX << PAGE_CACHE_SHIFT)
-
#define VM_ACCT(size) (PAGE_CACHE_ALIGN(size) >> PAGE_SHIFT)
-/* info->flags needs VM_flags to handle pagein/truncate races efficiently */
-#define SHMEM_PAGEIN VM_READ
-#define SHMEM_TRUNCATE VM_WRITE
-
-/* Definition to limit shmem_truncate's steps between cond_rescheds */
-#define LATENCY_LIMIT 64
-
/* Pretend that each entry is of this size in directory's i_size */
#define BOGO_DIRENT_SIZE 20
-/* Flag allocation requirements to shmem_getpage and shmem_swp_alloc */
+struct shmem_xattr {
+ struct list_head list; /* anchored by shmem_inode_info->xattr_list */
+ char *name; /* xattr name */
+ size_t size;
+ char value[0];
+};
+
+/* Flag allocation requirements to shmem_getpage */
enum sgp_type {
- SGP_QUICK, /* don't try more than file page cache lookup */
SGP_READ, /* don't exceed i_size, don't allocate page */
SGP_CACHE, /* don't exceed i_size, may allocate page */
+ SGP_DIRTY, /* like SGP_CACHE, but set new page dirty */
SGP_WRITE, /* may exceed i_size, may allocate page */
};
-static int shmem_getpage(struct inode *inode, unsigned long idx,
- struct page **pagep, enum sgp_type sgp, int *type);
-
-static inline struct page *shmem_dir_alloc(gfp_t gfp_mask)
-{
- /*
- * The above definition of ENTRIES_PER_PAGE, and the use of
- * BLOCKS_PER_PAGE on indirect pages, assume PAGE_CACHE_SIZE:
- * might be reconsidered if it ever diverges from PAGE_SIZE.
- */
- return alloc_pages(gfp_mask, PAGE_CACHE_SHIFT-PAGE_SHIFT);
-}
-
-static inline void shmem_dir_free(struct page *page)
-{
- __free_pages(page, PAGE_CACHE_SHIFT-PAGE_SHIFT);
-}
-
-static struct page **shmem_dir_map(struct page *page)
-{
- return (struct page **)kmap_atomic(page, KM_USER0);
-}
-
-static inline void shmem_dir_unmap(struct page **dir)
+#ifdef CONFIG_TMPFS
+static unsigned long shmem_default_max_blocks(void)
{
- kunmap_atomic(dir, KM_USER0);
+ return totalram_pages / 2;
}
-static swp_entry_t *shmem_swp_map(struct page *page)
+static unsigned long shmem_default_max_inodes(void)
{
- return (swp_entry_t *)kmap_atomic(page, KM_USER1);
+ return min(totalram_pages - totalhigh_pages, totalram_pages / 2);
}
+#endif
-static inline void shmem_swp_balance_unmap(void)
-{
- /*
- * When passing a pointer to an i_direct entry, to code which
- * also handles indirect entries and so will shmem_swp_unmap,
- * we must arrange for the preempt count to remain in balance.
- * What kmap_atomic of a lowmem page does depends on config
- * and architecture, so pretend to kmap_atomic some lowmem page.
- */
- (void) kmap_atomic(ZERO_PAGE(0), KM_USER1);
-}
+static int shmem_getpage_gfp(struct inode *inode, pgoff_t index,
+ struct page **pagep, enum sgp_type sgp, gfp_t gfp, int *fault_type);
-static inline void shmem_swp_unmap(swp_entry_t *entry)
+static inline int shmem_getpage(struct inode *inode, pgoff_t index,
+ struct page **pagep, enum sgp_type sgp, int *fault_type)
{
- kunmap_atomic(entry, KM_USER1);
+ return shmem_getpage_gfp(inode, index, pagep, sgp,
+ mapping_gfp_mask(inode->i_mapping), fault_type);
}
static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb)
*/
static inline int shmem_acct_size(unsigned long flags, loff_t size)
{
- return (flags & VM_ACCOUNT)?
- security_vm_enough_memory(VM_ACCT(size)): 0;
+ return (flags & VM_NORESERVE) ?
+ 0 : security_vm_enough_memory_kern(VM_ACCT(size));
}
static inline void shmem_unacct_size(unsigned long flags, loff_t size)
{
- if (flags & VM_ACCOUNT)
+ if (!(flags & VM_NORESERVE))
vm_unacct_memory(VM_ACCT(size));
}
*/
static inline int shmem_acct_block(unsigned long flags)
{
- return (flags & VM_ACCOUNT)?
- 0: security_vm_enough_memory(VM_ACCT(PAGE_CACHE_SIZE));
+ return (flags & VM_NORESERVE) ?
+ security_vm_enough_memory_kern(VM_ACCT(PAGE_CACHE_SIZE)) : 0;
}
static inline void shmem_unacct_blocks(unsigned long flags, long pages)
{
- if (!(flags & VM_ACCOUNT))
+ if (flags & VM_NORESERVE)
vm_unacct_memory(pages * VM_ACCT(PAGE_CACHE_SIZE));
}
-static struct super_operations shmem_ops;
+static const struct super_operations shmem_ops;
static const struct address_space_operations shmem_aops;
-static struct file_operations shmem_file_operations;
-static struct inode_operations shmem_inode_operations;
-static struct inode_operations shmem_dir_inode_operations;
-static struct inode_operations shmem_special_inode_operations;
-static struct vm_operations_struct shmem_vm_ops;
+static const struct file_operations shmem_file_operations;
+static const struct inode_operations shmem_inode_operations;
+static const struct inode_operations shmem_dir_inode_operations;
+static const struct inode_operations shmem_special_inode_operations;
+static const struct vm_operations_struct shmem_vm_ops;
static struct backing_dev_info shmem_backing_dev_info __read_mostly = {
.ra_pages = 0, /* No readahead */
- .capabilities = BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
- .unplug_io_fn = default_unplug_io_fn,
+ .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED,
};
static LIST_HEAD(shmem_swaplist);
-static DEFINE_SPINLOCK(shmem_swaplist_lock);
+static DEFINE_MUTEX(shmem_swaplist_mutex);
static void shmem_free_blocks(struct inode *inode, long pages)
{
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
if (sbinfo->max_blocks) {
- spin_lock(&sbinfo->stat_lock);
- sbinfo->free_blocks += pages;
+ percpu_counter_add(&sbinfo->used_blocks, -pages);
inode->i_blocks -= pages*BLOCKS_PER_PAGE;
+ }
+}
+
+static int shmem_reserve_inode(struct super_block *sb)
+{
+ struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
+ if (sbinfo->max_inodes) {
+ spin_lock(&sbinfo->stat_lock);
+ if (!sbinfo->free_inodes) {
+ spin_unlock(&sbinfo->stat_lock);
+ return -ENOSPC;
+ }
+ sbinfo->free_inodes--;
spin_unlock(&sbinfo->stat_lock);
}
+ return 0;
}
-/*
- * shmem_recalc_inode - recalculate the size of an inode
- *
+static void shmem_free_inode(struct super_block *sb)
+{
+ struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
+ if (sbinfo->max_inodes) {
+ spin_lock(&sbinfo->stat_lock);
+ sbinfo->free_inodes++;
+ spin_unlock(&sbinfo->stat_lock);
+ }
+}
+
+/**
+ * shmem_recalc_inode - recalculate the block usage of an inode
* @inode: inode to recalc
*
* We have to calculate the free blocks since the mm can drop
}
}
-/*
- * shmem_swp_entry - find the swap vector position in the info structure
- *
- * @info: info structure for the inode
- * @index: index of the page to find
- * @page: optional page to add to the structure. Has to be preset to
- * all zeros
- *
- * If there is no space allocated yet it will return NULL when
- * page is NULL, else it will use the page for the needed block,
- * setting it to NULL on return to indicate that it has been used.
- *
- * The swap vector is organized the following way:
- *
- * There are SHMEM_NR_DIRECT entries directly stored in the
- * shmem_inode_info structure. So small files do not need an addional
- * allocation.
- *
- * For pages with index > SHMEM_NR_DIRECT there is the pointer
- * i_indirect which points to a page which holds in the first half
- * doubly indirect blocks, in the second half triple indirect blocks:
- *
- * For an artificial ENTRIES_PER_PAGE = 4 this would lead to the
- * following layout (for SHMEM_NR_DIRECT == 16):
- *
- * i_indirect -> dir --> 16-19
- * | +-> 20-23
- * |
- * +-->dir2 --> 24-27
- * | +-> 28-31
- * | +-> 32-35
- * | +-> 36-39
- * |
- * +-->dir3 --> 40-43
- * +-> 44-47
- * +-> 48-51
- * +-> 52-55
- */
-static swp_entry_t *shmem_swp_entry(struct shmem_inode_info *info, unsigned long index, struct page **page)
+static void shmem_put_swap(struct shmem_inode_info *info, pgoff_t index,
+ swp_entry_t swap)
{
- unsigned long offset;
- struct page **dir;
- struct page *subdir;
-
- if (index < SHMEM_NR_DIRECT) {
- shmem_swp_balance_unmap();
- return info->i_direct+index;
- }
- if (!info->i_indirect) {
- if (page) {
- info->i_indirect = *page;
- *page = NULL;
- }
- return NULL; /* need another page */
- }
-
- index -= SHMEM_NR_DIRECT;
- offset = index % ENTRIES_PER_PAGE;
- index /= ENTRIES_PER_PAGE;
- dir = shmem_dir_map(info->i_indirect);
-
- if (index >= ENTRIES_PER_PAGE/2) {
- index -= ENTRIES_PER_PAGE/2;
- dir += ENTRIES_PER_PAGE/2 + index/ENTRIES_PER_PAGE;
- index %= ENTRIES_PER_PAGE;
- subdir = *dir;
- if (!subdir) {
- if (page) {
- *dir = *page;
- *page = NULL;
- }
- shmem_dir_unmap(dir);
- return NULL; /* need another page */
- }
- shmem_dir_unmap(dir);
- dir = shmem_dir_map(subdir);
- }
-
- dir += index;
- subdir = *dir;
- if (!subdir) {
- if (!page || !(subdir = *page)) {
- shmem_dir_unmap(dir);
- return NULL; /* need a page */
- }
- *dir = subdir;
- *page = NULL;
- }
- shmem_dir_unmap(dir);
- return shmem_swp_map(subdir) + offset;
+ if (index < SHMEM_NR_DIRECT)
+ info->i_direct[index] = swap;
}
-static void shmem_swp_set(struct shmem_inode_info *info, swp_entry_t *entry, unsigned long value)
+static swp_entry_t shmem_get_swap(struct shmem_inode_info *info, pgoff_t index)
{
- long incdec = value? 1: -1;
-
- entry->val = value;
- info->swapped += incdec;
- if ((unsigned long)(entry - info->i_direct) >= SHMEM_NR_DIRECT) {
- struct page *page = kmap_atomic_to_page(entry);
- set_page_private(page, page_private(page) + incdec);
- }
+ return (index < SHMEM_NR_DIRECT) ?
+ info->i_direct[index] : (swp_entry_t){0};
}
/*
- * shmem_swp_alloc - get the position of the swap entry for the page.
- * If it does not exist allocate the entry.
- *
- * @info: info structure for the inode
- * @index: index of the page to find
- * @sgp: check and recheck i_size? skip allocation?
+ * Replace item expected in radix tree by a new item, while holding tree lock.
*/
-static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long index, enum sgp_type sgp)
-{
- struct inode *inode = &info->vfs_inode;
- struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
- struct page *page = NULL;
- swp_entry_t *entry;
-
- if (sgp != SGP_WRITE &&
- ((loff_t) index << PAGE_CACHE_SHIFT) >= i_size_read(inode))
- return ERR_PTR(-EINVAL);
+static int shmem_radix_tree_replace(struct address_space *mapping,
+ pgoff_t index, void *expected, void *replacement)
+{
+ void **pslot;
+ void *item = NULL;
+
+ VM_BUG_ON(!expected);
+ pslot = radix_tree_lookup_slot(&mapping->page_tree, index);
+ if (pslot)
+ item = radix_tree_deref_slot_protected(pslot,
+ &mapping->tree_lock);
+ if (item != expected)
+ return -ENOENT;
+ if (replacement)
+ radix_tree_replace_slot(pslot, replacement);
+ else
+ radix_tree_delete(&mapping->page_tree, index);
+ return 0;
+}
- while (!(entry = shmem_swp_entry(info, index, &page))) {
- if (sgp == SGP_READ)
- return shmem_swp_map(ZERO_PAGE(0));
- /*
- * Test free_blocks against 1 not 0, since we have 1 data
- * page (and perhaps indirect index pages) yet to allocate:
- * a waste to allocate index if we cannot allocate data.
- */
- if (sbinfo->max_blocks) {
- spin_lock(&sbinfo->stat_lock);
- if (sbinfo->free_blocks <= 1) {
- spin_unlock(&sbinfo->stat_lock);
- return ERR_PTR(-ENOSPC);
- }
- sbinfo->free_blocks--;
- inode->i_blocks += BLOCKS_PER_PAGE;
- spin_unlock(&sbinfo->stat_lock);
+/*
+ * Like find_get_pages, but collecting swap entries as well as pages.
+ */
+static unsigned shmem_find_get_pages_and_swap(struct address_space *mapping,
+ pgoff_t start, unsigned int nr_pages,
+ struct page **pages, pgoff_t *indices)
+{
+ unsigned int i;
+ unsigned int ret;
+ unsigned int nr_found;
+
+ rcu_read_lock();
+restart:
+ nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree,
+ (void ***)pages, indices, start, nr_pages);
+ ret = 0;
+ for (i = 0; i < nr_found; i++) {
+ struct page *page;
+repeat:
+ page = radix_tree_deref_slot((void **)pages[i]);
+ if (unlikely(!page))
+ continue;
+ if (radix_tree_exception(page)) {
+ if (radix_tree_exceptional_entry(page))
+ goto export;
+ /* radix_tree_deref_retry(page) */
+ goto restart;
}
+ if (!page_cache_get_speculative(page))
+ goto repeat;
- spin_unlock(&info->lock);
- page = shmem_dir_alloc(mapping_gfp_mask(inode->i_mapping) | __GFP_ZERO);
- if (page)
- set_page_private(page, 0);
- spin_lock(&info->lock);
-
- if (!page) {
- shmem_free_blocks(inode, 1);
- return ERR_PTR(-ENOMEM);
- }
- if (sgp != SGP_WRITE &&
- ((loff_t) index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) {
- entry = ERR_PTR(-EINVAL);
- break;
+ /* Has the page moved? */
+ if (unlikely(page != *((void **)pages[i]))) {
+ page_cache_release(page);
+ goto repeat;
}
- if (info->next_index <= index)
- info->next_index = index + 1;
+export:
+ indices[ret] = indices[i];
+ pages[ret] = page;
+ ret++;
}
- if (page) {
- /* another task gave its page, or truncated the file */
- shmem_free_blocks(inode, 1);
- shmem_dir_free(page);
- }
- if (info->next_index <= index && !IS_ERR(entry))
- info->next_index = index + 1;
- return entry;
+ if (unlikely(!ret && nr_found))
+ goto restart;
+ rcu_read_unlock();
+ return ret;
}
/*
- * shmem_free_swp - free some swap entries in a directory
- *
- * @dir: pointer to the directory
- * @edir: pointer after last entry of the directory
+ * Remove swap entry from radix tree, free the swap and its page cache.
*/
-static int shmem_free_swp(swp_entry_t *dir, swp_entry_t *edir)
+static int shmem_free_swap(struct address_space *mapping,
+ pgoff_t index, void *radswap)
{
- swp_entry_t *ptr;
- int freed = 0;
+ int error;
- for (ptr = dir; ptr < edir; ptr++) {
- if (ptr->val) {
- free_swap_and_cache(*ptr);
- *ptr = (swp_entry_t){0};
- freed++;
- }
- }
- return freed;
-}
-
-static int shmem_map_and_free_swp(struct page *subdir,
- int offset, int limit, struct page ***dir)
-{
- swp_entry_t *ptr;
- int freed = 0;
-
- ptr = shmem_swp_map(subdir);
- for (; offset < limit; offset += LATENCY_LIMIT) {
- int size = limit - offset;
- if (size > LATENCY_LIMIT)
- size = LATENCY_LIMIT;
- freed += shmem_free_swp(ptr+offset, ptr+offset+size);
- if (need_resched()) {
- shmem_swp_unmap(ptr);
- if (*dir) {
- shmem_dir_unmap(*dir);
- *dir = NULL;
- }
- cond_resched();
- ptr = shmem_swp_map(subdir);
- }
- }
- shmem_swp_unmap(ptr);
- return freed;
+ spin_lock_irq(&mapping->tree_lock);
+ error = shmem_radix_tree_replace(mapping, index, radswap, NULL);
+ spin_unlock_irq(&mapping->tree_lock);
+ if (!error)
+ free_swap_and_cache(radix_to_swp_entry(radswap));
+ return error;
}
-static void shmem_free_pages(struct list_head *next)
+/*
+ * Pagevec may contain swap entries, so shuffle up pages before releasing.
+ */
+static void shmem_pagevec_release(struct pagevec *pvec)
{
- struct page *page;
- int freed = 0;
-
- do {
- page = container_of(next, struct page, lru);
- next = next->next;
- shmem_dir_free(page);
- freed++;
- if (freed >= LATENCY_LIMIT) {
- cond_resched();
- freed = 0;
- }
- } while (next);
+ int i, j;
+
+ for (i = 0, j = 0; i < pagevec_count(pvec); i++) {
+ struct page *page = pvec->pages[i];
+ if (!radix_tree_exceptional_entry(page))
+ pvec->pages[j++] = page;
+ }
+ pvec->nr = j;
+ pagevec_release(pvec);
}
-static void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end)
+/*
+ * Remove range of pages and swap entries from radix tree, and free them.
+ */
+void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
{
+ struct address_space *mapping = inode->i_mapping;
struct shmem_inode_info *info = SHMEM_I(inode);
- unsigned long idx;
- unsigned long size;
- unsigned long limit;
- unsigned long stage;
- unsigned long diroff;
- struct page **dir;
- struct page *topdir;
- struct page *middir;
- struct page *subdir;
- swp_entry_t *ptr;
- LIST_HEAD(pages_to_free);
- long nr_pages_to_free = 0;
+ pgoff_t start = (lstart + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+ unsigned partial = lstart & (PAGE_CACHE_SIZE - 1);
+ pgoff_t end = (lend >> PAGE_CACHE_SHIFT);
+ struct pagevec pvec;
+ pgoff_t indices[PAGEVEC_SIZE];
long nr_swaps_freed = 0;
- int offset;
- int freed;
- int punch_hole = 0;
+ pgoff_t index;
+ int i;
+
+ BUG_ON((lend & (PAGE_CACHE_SIZE - 1)) != (PAGE_CACHE_SIZE - 1));
+
+ pagevec_init(&pvec, 0);
+ index = start;
+ while (index <= end) {
+ pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
+ min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
+ pvec.pages, indices);
+ if (!pvec.nr)
+ break;
+ mem_cgroup_uncharge_start();
+ for (i = 0; i < pagevec_count(&pvec); i++) {
+ struct page *page = pvec.pages[i];
- inode->i_ctime = inode->i_mtime = CURRENT_TIME;
- idx = (start + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- if (idx >= info->next_index)
- return;
+ index = indices[i];
+ if (index > end)
+ break;
- spin_lock(&info->lock);
- info->flags |= SHMEM_TRUNCATE;
- if (likely(end == (loff_t) -1)) {
- limit = info->next_index;
- info->next_index = idx;
- } else {
- limit = (end + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- if (limit > info->next_index)
- limit = info->next_index;
- punch_hole = 1;
- }
+ if (radix_tree_exceptional_entry(page)) {
+ nr_swaps_freed += !shmem_free_swap(mapping,
+ index, page);
+ continue;
+ }
- topdir = info->i_indirect;
- if (topdir && idx <= SHMEM_NR_DIRECT && !punch_hole) {
- info->i_indirect = NULL;
- nr_pages_to_free++;
- list_add(&topdir->lru, &pages_to_free);
+ if (!trylock_page(page))
+ continue;
+ if (page->mapping == mapping) {
+ VM_BUG_ON(PageWriteback(page));
+ truncate_inode_page(mapping, page);
+ }
+ unlock_page(page);
+ }
+ shmem_pagevec_release(&pvec);
+ mem_cgroup_uncharge_end();
+ cond_resched();
+ index++;
}
- spin_unlock(&info->lock);
- if (info->swapped && idx < SHMEM_NR_DIRECT) {
- ptr = info->i_direct;
- size = limit;
- if (size > SHMEM_NR_DIRECT)
- size = SHMEM_NR_DIRECT;
- nr_swaps_freed = shmem_free_swp(ptr+idx, ptr+size);
- }
- if (!topdir)
- goto done2;
-
- BUG_ON(limit <= SHMEM_NR_DIRECT);
- limit -= SHMEM_NR_DIRECT;
- idx = (idx > SHMEM_NR_DIRECT)? (idx - SHMEM_NR_DIRECT): 0;
- offset = idx % ENTRIES_PER_PAGE;
- idx -= offset;
-
- dir = shmem_dir_map(topdir);
- stage = ENTRIES_PER_PAGEPAGE/2;
- if (idx < ENTRIES_PER_PAGEPAGE/2) {
- middir = topdir;
- diroff = idx/ENTRIES_PER_PAGE;
- } else {
- dir += ENTRIES_PER_PAGE/2;
- dir += (idx - ENTRIES_PER_PAGEPAGE/2)/ENTRIES_PER_PAGEPAGE;
- while (stage <= idx)
- stage += ENTRIES_PER_PAGEPAGE;
- middir = *dir;
- if (*dir) {
- diroff = ((idx - ENTRIES_PER_PAGEPAGE/2) %
- ENTRIES_PER_PAGEPAGE) / ENTRIES_PER_PAGE;
- if (!diroff && !offset) {
- *dir = NULL;
- nr_pages_to_free++;
- list_add(&middir->lru, &pages_to_free);
- }
- shmem_dir_unmap(dir);
- dir = shmem_dir_map(middir);
- } else {
- diroff = 0;
- offset = 0;
- idx = stage;
+ if (partial) {
+ struct page *page = NULL;
+ shmem_getpage(inode, start - 1, &page, SGP_READ, NULL);
+ if (page) {
+ zero_user_segment(page, partial, PAGE_CACHE_SIZE);
+ set_page_dirty(page);
+ unlock_page(page);
+ page_cache_release(page);
}
}
- for (; idx < limit; idx += ENTRIES_PER_PAGE, diroff++) {
- if (unlikely(idx == stage)) {
- shmem_dir_unmap(dir);
- dir = shmem_dir_map(topdir) +
- ENTRIES_PER_PAGE/2 + idx/ENTRIES_PER_PAGEPAGE;
- while (!*dir) {
- dir++;
- idx += ENTRIES_PER_PAGEPAGE;
- if (idx >= limit)
- goto done1;
- }
- stage = idx + ENTRIES_PER_PAGEPAGE;
- middir = *dir;
- *dir = NULL;
- nr_pages_to_free++;
- list_add(&middir->lru, &pages_to_free);
- shmem_dir_unmap(dir);
- cond_resched();
- dir = shmem_dir_map(middir);
- diroff = 0;
+ index = start;
+ for ( ; ; ) {
+ cond_resched();
+ pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
+ min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1,
+ pvec.pages, indices);
+ if (!pvec.nr) {
+ if (index == start)
+ break;
+ index = start;
+ continue;
}
- subdir = dir[diroff];
- if (subdir && page_private(subdir)) {
- size = limit - idx;
- if (size > ENTRIES_PER_PAGE)
- size = ENTRIES_PER_PAGE;
- freed = shmem_map_and_free_swp(subdir,
- offset, size, &dir);
- if (!dir)
- dir = shmem_dir_map(middir);
- nr_swaps_freed += freed;
- if (offset)
- spin_lock(&info->lock);
- set_page_private(subdir, page_private(subdir) - freed);
- if (offset)
- spin_unlock(&info->lock);
- if (!punch_hole)
- BUG_ON(page_private(subdir) > offset);
+ if (index == start && indices[0] > end) {
+ shmem_pagevec_release(&pvec);
+ break;
}
- if (offset)
- offset = 0;
- else if (subdir && !page_private(subdir)) {
- dir[diroff] = NULL;
- nr_pages_to_free++;
- list_add(&subdir->lru, &pages_to_free);
+ mem_cgroup_uncharge_start();
+ 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)) {
+ nr_swaps_freed += !shmem_free_swap(mapping,
+ index, page);
+ continue;
+ }
+
+ lock_page(page);
+ if (page->mapping == mapping) {
+ VM_BUG_ON(PageWriteback(page));
+ truncate_inode_page(mapping, page);
+ }
+ unlock_page(page);
}
- }
-done1:
- shmem_dir_unmap(dir);
-done2:
- if (inode->i_mapping->nrpages && (info->flags & SHMEM_PAGEIN)) {
- /*
- * Call truncate_inode_pages again: racing shmem_unuse_inode
- * may have swizzled a page in from swap since vmtruncate or
- * generic_delete_inode did it, before we lowered next_index.
- * Also, though shmem_getpage checks i_size before adding to
- * cache, no recheck after: so fix the narrow window there too.
- */
- truncate_inode_pages_range(inode->i_mapping, start, end);
+ shmem_pagevec_release(&pvec);
+ mem_cgroup_uncharge_end();
+ index++;
}
spin_lock(&info->lock);
- info->flags &= ~SHMEM_TRUNCATE;
info->swapped -= nr_swaps_freed;
- if (nr_pages_to_free)
- shmem_free_blocks(inode, nr_pages_to_free);
shmem_recalc_inode(inode);
spin_unlock(&info->lock);
- /*
- * Empty swap vector directory pages to be freed?
- */
- if (!list_empty(&pages_to_free)) {
- pages_to_free.prev->next = NULL;
- shmem_free_pages(pages_to_free.next);
- }
-}
-
-static void shmem_truncate(struct inode *inode)
-{
- shmem_truncate_range(inode, inode->i_size, (loff_t)-1);
+ inode->i_ctime = inode->i_mtime = CURRENT_TIME;
}
+EXPORT_SYMBOL_GPL(shmem_truncate_range);
-static int shmem_notify_change(struct dentry *dentry, struct iattr *attr)
+static int shmem_setattr(struct dentry *dentry, struct iattr *attr)
{
struct inode *inode = dentry->d_inode;
- struct page *page = NULL;
int error;
+ error = inode_change_ok(inode, attr);
+ if (error)
+ return error;
+
if (S_ISREG(inode->i_mode) && (attr->ia_valid & ATTR_SIZE)) {
- if (attr->ia_size < inode->i_size) {
- /*
- * If truncating down to a partial page, then
- * if that page is already allocated, hold it
- * in memory until the truncation is over, so
- * truncate_partial_page cannnot miss it were
- * it assigned to swap.
- */
- if (attr->ia_size & (PAGE_CACHE_SIZE-1)) {
- (void) shmem_getpage(inode,
- attr->ia_size>>PAGE_CACHE_SHIFT,
- &page, SGP_READ, NULL);
- }
- /*
- * Reset SHMEM_PAGEIN flag so that shmem_truncate can
- * detect if any pages might have been added to cache
- * after truncate_inode_pages. But we needn't bother
- * if it's being fully truncated to zero-length: the
- * nrpages check is efficient enough in that case.
- */
- if (attr->ia_size) {
- struct shmem_inode_info *info = SHMEM_I(inode);
- spin_lock(&info->lock);
- info->flags &= ~SHMEM_PAGEIN;
- spin_unlock(&info->lock);
- }
+ loff_t oldsize = inode->i_size;
+ loff_t newsize = attr->ia_size;
+
+ if (newsize != oldsize) {
+ 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);
}
}
- error = inode_change_ok(inode, attr);
- if (!error)
- error = inode_setattr(inode, attr);
+ setattr_copy(inode, attr);
#ifdef CONFIG_TMPFS_POSIX_ACL
- if (!error && (attr->ia_valid & ATTR_MODE))
- error = generic_acl_chmod(inode, &shmem_acl_ops);
+ if (attr->ia_valid & ATTR_MODE)
+ error = generic_acl_chmod(inode);
#endif
- if (page)
- page_cache_release(page);
return error;
}
-static void shmem_delete_inode(struct inode *inode)
+static void shmem_evict_inode(struct inode *inode)
{
- struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
struct shmem_inode_info *info = SHMEM_I(inode);
+ struct shmem_xattr *xattr, *nxattr;
- if (inode->i_op->truncate == shmem_truncate) {
- truncate_inode_pages(inode->i_mapping, 0);
+ if (inode->i_mapping->a_ops == &shmem_aops) {
shmem_unacct_size(info->flags, inode->i_size);
inode->i_size = 0;
- shmem_truncate(inode);
+ shmem_truncate_range(inode, 0, (loff_t)-1);
if (!list_empty(&info->swaplist)) {
- spin_lock(&shmem_swaplist_lock);
+ mutex_lock(&shmem_swaplist_mutex);
list_del_init(&info->swaplist);
- spin_unlock(&shmem_swaplist_lock);
+ mutex_unlock(&shmem_swaplist_mutex);
}
}
- BUG_ON(inode->i_blocks);
- if (sbinfo->max_inodes) {
- spin_lock(&sbinfo->stat_lock);
- sbinfo->free_inodes++;
- spin_unlock(&sbinfo->stat_lock);
- }
- clear_inode(inode);
-}
-static inline int shmem_find_swp(swp_entry_t entry, swp_entry_t *dir, swp_entry_t *edir)
-{
- swp_entry_t *ptr;
-
- for (ptr = dir; ptr < edir; ptr++) {
- if (ptr->val == entry.val)
- return ptr - dir;
+ list_for_each_entry_safe(xattr, nxattr, &info->xattr_list, list) {
+ kfree(xattr->name);
+ kfree(xattr);
}
- return -1;
+ BUG_ON(inode->i_blocks);
+ shmem_free_inode(inode->i_sb);
+ end_writeback(inode);
}
-static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, struct page *page)
+static int shmem_unuse_inode(struct shmem_inode_info *info,
+ swp_entry_t swap, struct page *page)
{
- struct inode *inode;
- unsigned long idx;
- unsigned long size;
- unsigned long limit;
- unsigned long stage;
- struct page **dir;
- struct page *subdir;
- swp_entry_t *ptr;
- int offset;
-
- idx = 0;
- ptr = info->i_direct;
- spin_lock(&info->lock);
- limit = info->next_index;
- size = limit;
- if (size > SHMEM_NR_DIRECT)
- size = SHMEM_NR_DIRECT;
- offset = shmem_find_swp(entry, ptr, ptr+size);
- if (offset >= 0) {
- shmem_swp_balance_unmap();
- goto found;
- }
- if (!info->i_indirect)
- goto lost2;
-
- dir = shmem_dir_map(info->i_indirect);
- stage = SHMEM_NR_DIRECT + ENTRIES_PER_PAGEPAGE/2;
-
- for (idx = SHMEM_NR_DIRECT; idx < limit; idx += ENTRIES_PER_PAGE, dir++) {
- if (unlikely(idx == stage)) {
- shmem_dir_unmap(dir-1);
- dir = shmem_dir_map(info->i_indirect) +
- ENTRIES_PER_PAGE/2 + idx/ENTRIES_PER_PAGEPAGE;
- while (!*dir) {
- dir++;
- idx += ENTRIES_PER_PAGEPAGE;
- if (idx >= limit)
- goto lost1;
- }
- stage = idx + ENTRIES_PER_PAGEPAGE;
- subdir = *dir;
- shmem_dir_unmap(dir);
- dir = shmem_dir_map(subdir);
- }
- subdir = *dir;
- if (subdir && page_private(subdir)) {
- ptr = shmem_swp_map(subdir);
- size = limit - idx;
- if (size > ENTRIES_PER_PAGE)
- size = ENTRIES_PER_PAGE;
- offset = shmem_find_swp(entry, ptr, ptr+size);
- if (offset >= 0) {
- shmem_dir_unmap(dir);
- goto found;
- }
- shmem_swp_unmap(ptr);
- }
- }
-lost1:
- shmem_dir_unmap(dir-1);
-lost2:
- spin_unlock(&info->lock);
+ struct address_space *mapping = info->vfs_inode.i_mapping;
+ pgoff_t index;
+ int error;
+
+ for (index = 0; index < SHMEM_NR_DIRECT; index++)
+ if (shmem_get_swap(info, index).val == swap.val)
+ goto found;
return 0;
found:
- idx += offset;
- inode = &info->vfs_inode;
- if (move_from_swap_cache(page, idx, inode->i_mapping) == 0) {
- info->flags |= SHMEM_PAGEIN;
- shmem_swp_set(info, ptr + offset, 0);
+ spin_lock(&info->lock);
+ if (shmem_get_swap(info, index).val != swap.val) {
+ spin_unlock(&info->lock);
+ return 0;
}
- shmem_swp_unmap(ptr);
- spin_unlock(&info->lock);
+
/*
- * Decrement swap count even when the entry is left behind:
- * try_to_unuse will skip over mms, then reincrement count.
+ * 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.
*/
- swap_free(entry);
- return 1;
+ if (shmem_swaplist.next != &info->swaplist)
+ list_move_tail(&shmem_swaplist, &info->swaplist);
+
+ /*
+ * 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).
+ */
+ error = add_to_page_cache_locked(page, mapping, index, GFP_NOWAIT);
+ /* which does mem_cgroup_uncharge_cache_page on error */
+
+ if (error != -ENOMEM) {
+ delete_from_swap_cache(page);
+ set_page_dirty(page);
+ shmem_put_swap(info, index, (swp_entry_t){0});
+ info->swapped--;
+ swap_free(swap);
+ error = 1; /* not an error, but entry was found */
+ }
+ spin_unlock(&info->lock);
+ return error;
}
/*
* shmem_unuse() search for an eventually swapped out shmem page.
*/
-int shmem_unuse(swp_entry_t entry, struct page *page)
+int shmem_unuse(swp_entry_t swap, struct page *page)
{
- struct list_head *p, *next;
+ struct list_head *this, *next;
struct shmem_inode_info *info;
int found = 0;
+ int error;
- spin_lock(&shmem_swaplist_lock);
- list_for_each_safe(p, next, &shmem_swaplist) {
- info = list_entry(p, struct shmem_inode_info, swaplist);
- if (!info->swapped)
- list_del_init(&info->swaplist);
- else if (shmem_unuse_inode(info, entry, page)) {
- /* move head to start search for next from here */
- list_move_tail(&shmem_swaplist, &info->swaplist);
- found = 1;
- break;
+ /*
+ * 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.
+ * add_to_page_cache() will be called with GFP_NOWAIT.
+ */
+ error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL);
+ if (error)
+ goto out;
+ /*
+ * Try to preload while we can wait, to not make a habit of
+ * draining atomic reserves; but don't latch on to this cpu,
+ * it's okay if sometimes we get rescheduled after this.
+ */
+ error = radix_tree_preload(GFP_KERNEL);
+ if (error)
+ goto uncharge;
+ radix_tree_preload_end();
+
+ 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) {
+ spin_lock(&info->lock);
+ if (!info->swapped)
+ list_del_init(&info->swaplist);
+ spin_unlock(&info->lock);
}
+ if (info->swapped)
+ found = shmem_unuse_inode(info, swap, page);
+ cond_resched();
+ if (found)
+ break;
}
- spin_unlock(&shmem_swaplist_lock);
- return found;
+ mutex_unlock(&shmem_swaplist_mutex);
+
+uncharge:
+ if (!found)
+ mem_cgroup_uncharge_cache_page(page);
+ if (found < 0)
+ error = found;
+out:
+ unlock_page(page);
+ page_cache_release(page);
+ return error;
}
/*
static int shmem_writepage(struct page *page, struct writeback_control *wbc)
{
struct shmem_inode_info *info;
- swp_entry_t *entry, swap;
+ swp_entry_t swap, oswap;
struct address_space *mapping;
- unsigned long index;
+ pgoff_t index;
struct inode *inode;
BUG_ON(!PageLocked(page));
- BUG_ON(page_mapped(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;
+
+ /*
+ * shmem_backing_dev_info's 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;
+ }
+
+ /*
+ * Disable even the toy swapping implementation, while we convert
+ * functions one by one to having swap entries in the radix tree.
+ */
+ if (index < ULONG_MAX)
+ goto redirty;
+
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 because we cannot take
+ * mutex while holding spinlock, and must do so 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 taken the spinlock, because shmem_unuse_inode() will
+ * prune a !swapped inode from the swaplist under both locks.
+ */
+ mutex_lock(&shmem_swaplist_mutex);
+ if (list_empty(&info->swaplist))
+ list_add_tail(&info->swaplist, &shmem_swaplist);
+
spin_lock(&info->lock);
- shmem_recalc_inode(inode);
- if (index >= info->next_index) {
- BUG_ON(!(info->flags & SHMEM_TRUNCATE));
- goto unlock;
+ mutex_unlock(&shmem_swaplist_mutex);
+
+ oswap = shmem_get_swap(info, index);
+ if (oswap.val) {
+ WARN_ON_ONCE(1); /* Still happens? Tell us about it! */
+ free_swap_and_cache(oswap);
+ shmem_put_swap(info, index, (swp_entry_t){0});
+ info->swapped--;
}
- entry = shmem_swp_entry(info, index, NULL);
- BUG_ON(!entry);
- BUG_ON(entry->val);
+ shmem_recalc_inode(inode);
- if (move_to_swap_cache(page, swap) == 0) {
- shmem_swp_set(info, entry, swap.val);
- shmem_swp_unmap(entry);
+ if (add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) {
+ delete_from_page_cache(page);
+ shmem_put_swap(info, index, swap);
+ info->swapped++;
+ swap_shmem_alloc(swap);
spin_unlock(&info->lock);
- if (list_empty(&info->swaplist)) {
- spin_lock(&shmem_swaplist_lock);
- /* move instead of add in case we're racing */
- list_move_tail(&info->swaplist, &shmem_swaplist);
- spin_unlock(&shmem_swaplist_lock);
- }
- unlock_page(page);
+ BUG_ON(page_mapped(page));
+ swap_writepage(page, wbc);
return 0;
}
- shmem_swp_unmap(entry);
-unlock:
spin_unlock(&info->lock);
- swap_free(swap);
+ swapcache_free(swap, NULL);
redirty:
set_page_dirty(page);
- return AOP_WRITEPAGE_ACTIVATE; /* Return with the page locked */
+ if (wbc->for_reclaim)
+ return AOP_WRITEPAGE_ACTIVATE; /* Return with page locked */
+ unlock_page(page);
+ return 0;
}
#ifdef CONFIG_NUMA
-static inline int shmem_parse_mpol(char *value, int *policy, nodemask_t *policy_nodes)
+#ifdef CONFIG_TMPFS
+static void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol)
{
- char *nodelist = strchr(value, ':');
- int err = 1;
+ char buffer[64];
- if (nodelist) {
- /* NUL-terminate policy string */
- *nodelist++ = '\0';
- if (nodelist_parse(nodelist, *policy_nodes))
- goto out;
- }
- if (!strcmp(value, "default")) {
- *policy = MPOL_DEFAULT;
- /* Don't allow a nodelist */
- if (!nodelist)
- err = 0;
- } else if (!strcmp(value, "prefer")) {
- *policy = MPOL_PREFERRED;
- /* Insist on a nodelist of one node only */
- if (nodelist) {
- char *rest = nodelist;
- while (isdigit(*rest))
- rest++;
- if (!*rest)
- err = 0;
- }
- } else if (!strcmp(value, "bind")) {
- *policy = MPOL_BIND;
- /* Insist on a nodelist */
- if (nodelist)
- err = 0;
- } else if (!strcmp(value, "interleave")) {
- *policy = MPOL_INTERLEAVE;
- /* Default to nodes online if no nodelist */
- if (!nodelist)
- *policy_nodes = node_online_map;
- err = 0;
+ if (!mpol || mpol->mode == MPOL_DEFAULT)
+ return; /* show nothing */
+
+ mpol_to_str(buffer, sizeof(buffer), mpol, 1);
+
+ 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);
}
-out:
- /* Restore string for error message */
- if (nodelist)
- *--nodelist = ':';
- return err;
+ return mpol;
}
+#endif /* CONFIG_TMPFS */
-static struct page *shmem_swapin_async(struct shared_policy *p,
- swp_entry_t entry, unsigned long idx)
+static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp,
+ struct shmem_inode_info *info, pgoff_t index)
{
- struct page *page;
+ struct mempolicy mpol, *spol;
struct vm_area_struct pvma;
+ spol = mpol_cond_copy(&mpol,
+ mpol_shared_policy_lookup(&info->policy, index));
+
/* Create a pseudo vma that just contains the policy */
- memset(&pvma, 0, sizeof(struct vm_area_struct));
- pvma.vm_end = PAGE_SIZE;
- pvma.vm_pgoff = idx;
- pvma.vm_policy = mpol_shared_policy_lookup(p, idx);
- page = read_swap_cache_async(entry, &pvma, 0);
- mpol_free(pvma.vm_policy);
- return page;
+ pvma.vm_start = 0;
+ pvma.vm_pgoff = index;
+ pvma.vm_ops = NULL;
+ pvma.vm_policy = spol;
+ return swapin_readahead(swap, gfp, &pvma, 0);
}
-struct page *shmem_swapin(struct shmem_inode_info *info, swp_entry_t entry,
- unsigned long idx)
+static struct page *shmem_alloc_page(gfp_t gfp,
+ struct shmem_inode_info *info, pgoff_t index)
{
- struct shared_policy *p = &info->policy;
- int i, num;
- struct page *page;
- unsigned long offset;
+ struct vm_area_struct pvma;
- num = valid_swaphandles(entry, &offset);
- for (i = 0; i < num; offset++, i++) {
- page = shmem_swapin_async(p,
- swp_entry(swp_type(entry), offset), idx);
- if (!page)
- break;
- page_cache_release(page);
- }
- lru_add_drain(); /* Push any new pages onto the LRU now */
- return shmem_swapin_async(p, entry, idx);
-}
+ /* Create a pseudo vma that just contains the policy */
+ pvma.vm_start = 0;
+ pvma.vm_pgoff = index;
+ pvma.vm_ops = NULL;
+ pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, index);
-static struct page *
-shmem_alloc_page(gfp_t gfp, struct shmem_inode_info *info,
- unsigned long idx)
+ /*
+ * alloc_page_vma() will drop the shared policy reference
+ */
+ return alloc_page_vma(gfp, &pvma, 0);
+}
+#else /* !CONFIG_NUMA */
+#ifdef CONFIG_TMPFS
+static inline void shmem_show_mpol(struct seq_file *seq, struct mempolicy *mpol)
{
- struct vm_area_struct pvma;
- struct page *page;
-
- memset(&pvma, 0, sizeof(struct vm_area_struct));
- pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx);
- pvma.vm_pgoff = idx;
- pvma.vm_end = PAGE_SIZE;
- page = alloc_page_vma(gfp | __GFP_ZERO, &pvma, 0);
- mpol_free(pvma.vm_policy);
- return page;
}
-#else
-static inline int shmem_parse_mpol(char *value, int *policy, nodemask_t *policy_nodes)
+#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 1;
+ return swapin_readahead(swap, gfp, NULL, 0);
}
-static inline struct page *
-shmem_swapin(struct shmem_inode_info *info,swp_entry_t entry,unsigned long idx)
+static inline struct page *shmem_alloc_page(gfp_t gfp,
+ struct shmem_inode_info *info, pgoff_t index)
{
- swapin_readahead(entry, 0, NULL);
- return read_swap_cache_async(entry, NULL, 0);
+ return alloc_page(gfp);
}
+#endif /* CONFIG_NUMA */
-static inline struct page *
-shmem_alloc_page(gfp_t gfp,struct shmem_inode_info *info, unsigned long idx)
+#if !defined(CONFIG_NUMA) || !defined(CONFIG_TMPFS)
+static inline struct mempolicy *shmem_get_sbmpol(struct shmem_sb_info *sbinfo)
{
- return alloc_page(gfp | __GFP_ZERO);
+ return NULL;
}
#endif
/*
- * shmem_getpage - either get the page from swap or allocate a new one
+ * 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(struct inode *inode, unsigned long idx,
- struct page **pagep, enum sgp_type sgp, int *type)
+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 = SHMEM_I(inode);
struct shmem_sb_info *sbinfo;
- struct page *filepage = *pagep;
- struct page *swappage;
- swp_entry_t *entry;
+ struct page *page;
+ struct page *prealloc_page = NULL;
swp_entry_t swap;
int error;
- if (idx >= SHMEM_MAX_INDEX)
+ if (index > (MAX_LFS_FILESIZE >> PAGE_CACHE_SHIFT))
return -EFBIG;
- /*
- * Normally, filepage is NULL on entry, and either found
- * uptodate immediately, or allocated and zeroed, or read
- * in under swappage, which is then assigned to filepage.
- * But shmem_prepare_write passes in a locked filepage,
- * which may be found not uptodate by other callers too,
- * and may need to be copied from the swappage read in.
- */
repeat:
- if (!filepage)
- filepage = find_lock_page(mapping, idx);
- if (filepage && PageUptodate(filepage))
+ page = find_lock_page(mapping, index);
+ if (page) {
+ /*
+ * Once we can get the page lock, it must be uptodate:
+ * if there were an error in reading back from swap,
+ * the page would not be inserted into the filecache.
+ */
+ BUG_ON(!PageUptodate(page));
goto done;
- error = 0;
- if (sgp == SGP_QUICK)
- goto failed;
+ }
- spin_lock(&info->lock);
- shmem_recalc_inode(inode);
- entry = shmem_swp_alloc(info, idx, sgp);
- if (IS_ERR(entry)) {
- spin_unlock(&info->lock);
- error = PTR_ERR(entry);
- goto failed;
+ /*
+ * Try to preload while we can wait, to not make a habit of
+ * draining atomic reserves; but don't latch on to this cpu.
+ */
+ error = radix_tree_preload(gfp & GFP_RECLAIM_MASK);
+ if (error)
+ goto out;
+ radix_tree_preload_end();
+
+ if (sgp != SGP_READ && !prealloc_page) {
+ prealloc_page = shmem_alloc_page(gfp, info, index);
+ if (prealloc_page) {
+ SetPageSwapBacked(prealloc_page);
+ if (mem_cgroup_cache_charge(prealloc_page,
+ current->mm, GFP_KERNEL)) {
+ page_cache_release(prealloc_page);
+ prealloc_page = NULL;
+ }
+ }
}
- swap = *entry;
+ spin_lock(&info->lock);
+ shmem_recalc_inode(inode);
+ swap = shmem_get_swap(info, index);
if (swap.val) {
/* Look it up and read it in.. */
- swappage = lookup_swap_cache(swap);
- if (!swappage) {
- shmem_swp_unmap(entry);
- /* here we actually do the io */
- if (type && *type == VM_FAULT_MINOR) {
- __count_vm_event(PGMAJFAULT);
- *type = VM_FAULT_MAJOR;
- }
+ page = lookup_swap_cache(swap);
+ if (!page) {
spin_unlock(&info->lock);
- swappage = shmem_swapin(info, swap, idx);
- if (!swappage) {
- spin_lock(&info->lock);
- entry = shmem_swp_alloc(info, idx, sgp);
- if (IS_ERR(entry))
- error = PTR_ERR(entry);
- else {
- if (entry->val == swap.val)
- error = -ENOMEM;
- shmem_swp_unmap(entry);
+ /* here we actually do the io */
+ if (fault_type)
+ *fault_type |= VM_FAULT_MAJOR;
+ page = shmem_swapin(swap, gfp, info, index);
+ if (!page) {
+ swp_entry_t nswap = shmem_get_swap(info, index);
+ if (nswap.val == swap.val) {
+ error = -ENOMEM;
+ goto out;
}
- spin_unlock(&info->lock);
- if (error)
- goto failed;
goto repeat;
}
- wait_on_page_locked(swappage);
- page_cache_release(swappage);
+ wait_on_page_locked(page);
+ page_cache_release(page);
goto repeat;
}
/* We have to do this with page locked to prevent races */
- if (TestSetPageLocked(swappage)) {
- shmem_swp_unmap(entry);
+ if (!trylock_page(page)) {
spin_unlock(&info->lock);
- wait_on_page_locked(swappage);
- page_cache_release(swappage);
+ wait_on_page_locked(page);
+ page_cache_release(page);
goto repeat;
}
- if (PageWriteback(swappage)) {
- shmem_swp_unmap(entry);
+ if (PageWriteback(page)) {
spin_unlock(&info->lock);
- wait_on_page_writeback(swappage);
- unlock_page(swappage);
- page_cache_release(swappage);
+ wait_on_page_writeback(page);
+ unlock_page(page);
+ page_cache_release(page);
goto repeat;
}
- if (!PageUptodate(swappage)) {
- shmem_swp_unmap(entry);
+ if (!PageUptodate(page)) {
spin_unlock(&info->lock);
- unlock_page(swappage);
- page_cache_release(swappage);
+ unlock_page(page);
+ page_cache_release(page);
error = -EIO;
- goto failed;
+ goto out;
}
- if (filepage) {
- shmem_swp_set(info, entry, 0);
- shmem_swp_unmap(entry);
- delete_from_swap_cache(swappage);
- spin_unlock(&info->lock);
- copy_highpage(filepage, swappage);
- unlock_page(swappage);
- page_cache_release(swappage);
- flush_dcache_page(filepage);
- SetPageUptodate(filepage);
- set_page_dirty(filepage);
- swap_free(swap);
- } else if (!(error = move_from_swap_cache(
- swappage, idx, mapping))) {
- info->flags |= SHMEM_PAGEIN;
- shmem_swp_set(info, entry, 0);
- shmem_swp_unmap(entry);
- spin_unlock(&info->lock);
- filepage = swappage;
- swap_free(swap);
- } else {
- shmem_swp_unmap(entry);
+ error = add_to_page_cache_locked(page, mapping,
+ index, GFP_NOWAIT);
+ if (error) {
spin_unlock(&info->lock);
- unlock_page(swappage);
- page_cache_release(swappage);
if (error == -ENOMEM) {
- /* let kswapd refresh zone for GFP_ATOMICs */
- blk_congestion_wait(WRITE, HZ/50);
+ /*
+ * reclaim from proper memory cgroup and
+ * call memcg's OOM if needed.
+ */
+ error = mem_cgroup_shmem_charge_fallback(
+ page, current->mm, gfp);
+ if (error) {
+ unlock_page(page);
+ page_cache_release(page);
+ goto out;
+ }
}
+ unlock_page(page);
+ page_cache_release(page);
goto repeat;
}
- } else if (sgp == SGP_READ && !filepage) {
- shmem_swp_unmap(entry);
- filepage = find_get_page(mapping, idx);
- if (filepage &&
- (!PageUptodate(filepage) || TestSetPageLocked(filepage))) {
+
+ delete_from_swap_cache(page);
+ shmem_put_swap(info, index, (swp_entry_t){0});
+ info->swapped--;
+ spin_unlock(&info->lock);
+ set_page_dirty(page);
+ swap_free(swap);
+
+ } else if (sgp == SGP_READ) {
+ page = find_get_page(mapping, index);
+ if (page && !trylock_page(page)) {
spin_unlock(&info->lock);
- wait_on_page_locked(filepage);
- page_cache_release(filepage);
- filepage = NULL;
+ wait_on_page_locked(page);
+ page_cache_release(page);
goto repeat;
}
spin_unlock(&info->lock);
- } else {
- shmem_swp_unmap(entry);
+
+ } else if (prealloc_page) {
sbinfo = SHMEM_SB(inode->i_sb);
if (sbinfo->max_blocks) {
- spin_lock(&sbinfo->stat_lock);
- if (sbinfo->free_blocks == 0 ||
- shmem_acct_block(info->flags)) {
- spin_unlock(&sbinfo->stat_lock);
- spin_unlock(&info->lock);
- error = -ENOSPC;
- goto failed;
- }
- sbinfo->free_blocks--;
+ if (percpu_counter_compare(&sbinfo->used_blocks,
+ sbinfo->max_blocks) >= 0 ||
+ shmem_acct_block(info->flags))
+ goto nospace;
+ percpu_counter_inc(&sbinfo->used_blocks);
inode->i_blocks += BLOCKS_PER_PAGE;
- spin_unlock(&sbinfo->stat_lock);
- } else if (shmem_acct_block(info->flags)) {
- spin_unlock(&info->lock);
- error = -ENOSPC;
- goto failed;
- }
-
- if (!filepage) {
+ } else if (shmem_acct_block(info->flags))
+ goto nospace;
+
+ page = prealloc_page;
+ prealloc_page = NULL;
+
+ swap = shmem_get_swap(info, index);
+ if (swap.val)
+ mem_cgroup_uncharge_cache_page(page);
+ else
+ error = add_to_page_cache_lru(page, mapping,
+ index, GFP_NOWAIT);
+ /*
+ * At add_to_page_cache_lru() failure,
+ * uncharge will be done automatically.
+ */
+ if (swap.val || error) {
+ shmem_unacct_blocks(info->flags, 1);
+ shmem_free_blocks(inode, 1);
spin_unlock(&info->lock);
- filepage = shmem_alloc_page(mapping_gfp_mask(mapping),
- info,
- idx);
- if (!filepage) {
- shmem_unacct_blocks(info->flags, 1);
- shmem_free_blocks(inode, 1);
- error = -ENOMEM;
- goto failed;
- }
-
- spin_lock(&info->lock);
- entry = shmem_swp_alloc(info, idx, sgp);
- if (IS_ERR(entry))
- error = PTR_ERR(entry);
- else {
- swap = *entry;
- shmem_swp_unmap(entry);
- }
- if (error || swap.val || 0 != add_to_page_cache_lru(
- filepage, mapping, idx, GFP_ATOMIC)) {
- spin_unlock(&info->lock);
- page_cache_release(filepage);
- shmem_unacct_blocks(info->flags, 1);
- shmem_free_blocks(inode, 1);
- filepage = NULL;
- if (error)
- goto failed;
- goto repeat;
- }
- info->flags |= SHMEM_PAGEIN;
+ page_cache_release(page);
+ goto repeat;
}
info->alloced++;
spin_unlock(&info->lock);
- flush_dcache_page(filepage);
- SetPageUptodate(filepage);
+ clear_highpage(page);
+ flush_dcache_page(page);
+ SetPageUptodate(page);
+ if (sgp == SGP_DIRTY)
+ set_page_dirty(page);
+
+ } else {
+ spin_unlock(&info->lock);
+ error = -ENOMEM;
+ goto out;
}
done:
- if (*pagep != filepage) {
- unlock_page(filepage);
- *pagep = filepage;
+ *pagep = page;
+ error = 0;
+out:
+ if (prealloc_page) {
+ mem_cgroup_uncharge_cache_page(prealloc_page);
+ page_cache_release(prealloc_page);
}
- return 0;
+ return error;
-failed:
- if (*pagep != filepage) {
- unlock_page(filepage);
- page_cache_release(filepage);
+nospace:
+ /*
+ * Perhaps the page was brought in from swap between find_lock_page
+ * and taking info->lock? We allow for that at add_to_page_cache_lru,
+ * but must also avoid reporting a spurious ENOSPC while working on a
+ * full tmpfs.
+ */
+ page = find_get_page(mapping, index);
+ spin_unlock(&info->lock);
+ if (page) {
+ page_cache_release(page);
+ goto repeat;
}
- return error;
+ error = -ENOSPC;
+ goto out;
}
-struct page *shmem_nopage(struct vm_area_struct *vma, unsigned long address, int *type)
+static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
- struct inode *inode = vma->vm_file->f_dentry->d_inode;
- struct page *page = NULL;
- unsigned long idx;
+ struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
int error;
+ int ret = VM_FAULT_LOCKED;
- idx = (address - vma->vm_start) >> PAGE_SHIFT;
- idx += vma->vm_pgoff;
- idx >>= PAGE_CACHE_SHIFT - PAGE_SHIFT;
- if (((loff_t) idx << PAGE_CACHE_SHIFT) >= i_size_read(inode))
- return NOPAGE_SIGBUS;
+ if (((loff_t)vmf->pgoff << PAGE_CACHE_SHIFT) >= i_size_read(inode))
+ return VM_FAULT_SIGBUS;
- error = shmem_getpage(inode, idx, &page, SGP_CACHE, type);
+ error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret);
if (error)
- return (error == -ENOMEM)? NOPAGE_OOM: NOPAGE_SIGBUS;
-
- mark_page_accessed(page);
- return page;
-}
+ return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);
-static int shmem_populate(struct vm_area_struct *vma,
- unsigned long addr, unsigned long len,
- pgprot_t prot, unsigned long pgoff, int nonblock)
-{
- struct inode *inode = vma->vm_file->f_dentry->d_inode;
- struct mm_struct *mm = vma->vm_mm;
- enum sgp_type sgp = nonblock? SGP_QUICK: SGP_CACHE;
- unsigned long size;
-
- size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
- if (pgoff >= size || pgoff + (len >> PAGE_SHIFT) > size)
- return -EINVAL;
-
- while ((long) len > 0) {
- struct page *page = NULL;
- int err;
- /*
- * Will need changing if PAGE_CACHE_SIZE != PAGE_SIZE
- */
- err = shmem_getpage(inode, pgoff, &page, sgp, NULL);
- if (err)
- return err;
- /* Page may still be null, but only if nonblock was set. */
- if (page) {
- mark_page_accessed(page);
- err = install_page(mm, vma, addr, page, prot);
- if (err) {
- page_cache_release(page);
- return err;
- }
- } else if (vma->vm_flags & VM_NONLINEAR) {
- /* No page was found just because we can't read it in
- * now (being here implies nonblock != 0), but the page
- * may exist, so set the PTE to fault it in later. */
- err = install_file_pte(mm, vma, addr, pgoff, prot);
- if (err)
- return err;
- }
-
- len -= PAGE_SIZE;
- addr += PAGE_SIZE;
- pgoff++;
+ if (ret & VM_FAULT_MAJOR) {
+ count_vm_event(PGMAJFAULT);
+ mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
}
- return 0;
+ return ret;
}
#ifdef CONFIG_NUMA
-int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *new)
+static int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol)
{
- struct inode *i = vma->vm_file->f_dentry->d_inode;
- return mpol_set_shared_policy(&SHMEM_I(i)->policy, vma, new);
+ struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
+ return mpol_set_shared_policy(&SHMEM_I(inode)->policy, vma, mpol);
}
-struct mempolicy *
-shmem_get_policy(struct vm_area_struct *vma, unsigned long addr)
+static struct mempolicy *shmem_get_policy(struct vm_area_struct *vma,
+ unsigned long addr)
{
- struct inode *i = vma->vm_file->f_dentry->d_inode;
- unsigned long idx;
+ struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
+ pgoff_t index;
- idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
- return mpol_shared_policy_lookup(&SHMEM_I(i)->policy, idx);
+ 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->f_dentry->d_inode;
+ struct inode *inode = file->f_path.dentry->d_inode;
struct shmem_inode_info *info = SHMEM_I(inode);
int retval = -ENOMEM;
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);
+ scan_mapping_unevictable_pages(file->f_mapping);
}
retval = 0;
+
out_nomem:
spin_unlock(&info->lock);
return retval;
}
-int shmem_mmap(struct file *file, struct vm_area_struct *vma)
+static int shmem_mmap(struct file *file, struct vm_area_struct *vma)
{
file_accessed(file);
vma->vm_ops = &shmem_vm_ops;
+ vma->vm_flags |= VM_CAN_NONLINEAR;
return 0;
}
-static struct inode *
-shmem_get_inode(struct super_block *sb, int mode, dev_t dev)
-{
- struct inode *inode;
- struct shmem_inode_info *info;
- struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
-
- if (sbinfo->max_inodes) {
- spin_lock(&sbinfo->stat_lock);
- if (!sbinfo->free_inodes) {
- spin_unlock(&sbinfo->stat_lock);
- return NULL;
- }
- sbinfo->free_inodes--;
- spin_unlock(&sbinfo->stat_lock);
- }
-
+static struct inode *shmem_get_inode(struct super_block *sb, const struct inode *dir,
+ int 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_mode = mode;
- inode->i_uid = current->fsuid;
- inode->i_gid = current->fsgid;
+ inode->i_ino = get_next_ino();
+ inode_init_owner(inode, dir, mode);
inode->i_blocks = 0;
- inode->i_mapping->a_ops = &shmem_aops;
inode->i_mapping->backing_dev_info = &shmem_backing_dev_info;
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->flags = flags & VM_NORESERVE;
INIT_LIST_HEAD(&info->swaplist);
+ INIT_LIST_HEAD(&info->xattr_list);
+ cache_no_acl(inode);
switch (mode & S_IFMT) {
default:
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, sbinfo->policy,
- &sbinfo->policy_nodes);
+ mpol_shared_policy_init(&info->policy,
+ shmem_get_sbmpol(sbinfo));
break;
case S_IFDIR:
- inode->i_nlink++;
+ 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;
* Must not load anything in the rbtree,
* mpol_free_shared_policy will not be called.
*/
- mpol_shared_policy_init(&info->policy, MPOL_DEFAULT,
- NULL);
+ mpol_shared_policy_init(&info->policy, NULL);
break;
}
- } else if (sbinfo->max_inodes) {
- spin_lock(&sbinfo->stat_lock);
- sbinfo->free_inodes++;
- spin_unlock(&sbinfo->stat_lock);
- }
+ } else
+ shmem_free_inode(sb);
return inode;
}
#ifdef CONFIG_TMPFS
-static struct inode_operations shmem_symlink_inode_operations;
-static struct inode_operations shmem_symlink_inline_operations;
+static const struct inode_operations shmem_symlink_inode_operations;
+static const struct inode_operations shmem_symlink_inline_operations;
-/*
- * Normally tmpfs makes no use of shmem_prepare_write, but it
- * lets a tmpfs file be used read-write below the loop driver.
- */
static int
-shmem_prepare_write(struct file *file, struct page *page, unsigned offset, unsigned to)
+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 = page->mapping->host;
- return shmem_getpage(inode, page->index, &page, SGP_WRITE, NULL);
+ struct inode *inode = mapping->host;
+ pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+ return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL);
}
-static ssize_t
-shmem_file_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
+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 = file->f_dentry->d_inode;
- loff_t pos;
- unsigned long written;
- ssize_t err;
-
- if ((ssize_t) count < 0)
- return -EINVAL;
-
- if (!access_ok(VERIFY_READ, buf, count))
- return -EFAULT;
-
- mutex_lock(&inode->i_mutex);
-
- pos = *ppos;
- written = 0;
-
- err = generic_write_checks(file, &pos, &count, 0);
- if (err || !count)
- goto out;
-
- err = remove_suid(file->f_dentry);
- if (err)
- goto out;
-
- inode->i_ctime = inode->i_mtime = CURRENT_TIME;
-
- do {
- struct page *page = NULL;
- unsigned long bytes, index, offset;
- char *kaddr;
- int left;
-
- offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */
- index = pos >> PAGE_CACHE_SHIFT;
- bytes = PAGE_CACHE_SIZE - offset;
- if (bytes > count)
- bytes = count;
-
- /*
- * We don't hold page lock across copy from user -
- * what would it guard against? - so no deadlock here.
- * But it still may be a good idea to prefault below.
- */
+ struct inode *inode = mapping->host;
- err = shmem_getpage(inode, index, &page, SGP_WRITE, NULL);
- if (err)
- break;
-
- left = bytes;
- if (PageHighMem(page)) {
- volatile unsigned char dummy;
- __get_user(dummy, buf);
- __get_user(dummy, buf + bytes - 1);
-
- kaddr = kmap_atomic(page, KM_USER0);
- left = __copy_from_user_inatomic(kaddr + offset,
- buf, bytes);
- kunmap_atomic(kaddr, KM_USER0);
- }
- if (left) {
- kaddr = kmap(page);
- left = __copy_from_user(kaddr + offset, buf, bytes);
- kunmap(page);
- }
-
- written += bytes;
- count -= bytes;
- pos += bytes;
- buf += bytes;
- if (pos > inode->i_size)
- i_size_write(inode, pos);
-
- flush_dcache_page(page);
- set_page_dirty(page);
- mark_page_accessed(page);
- page_cache_release(page);
-
- if (left) {
- pos -= left;
- written -= left;
- err = -EFAULT;
- break;
- }
-
- /*
- * Our dirty pages are not counted in nr_dirty,
- * and we do not attempt to balance dirty pages.
- */
+ if (pos + copied > inode->i_size)
+ i_size_write(inode, pos + copied);
- cond_resched();
- } while (count);
+ set_page_dirty(page);
+ unlock_page(page);
+ page_cache_release(page);
- *ppos = pos;
- if (written)
- err = written;
-out:
- mutex_unlock(&inode->i_mutex);
- return err;
+ return copied;
}
static void do_shmem_file_read(struct file *filp, loff_t *ppos, read_descriptor_t *desc, read_actor_t actor)
{
- struct inode *inode = filp->f_dentry->d_inode;
+ struct inode *inode = filp->f_path.dentry->d_inode;
struct address_space *mapping = inode->i_mapping;
- unsigned long index, offset;
+ pgoff_t index;
+ unsigned long offset;
+ enum sgp_type sgp = SGP_READ;
+
+ /*
+ * 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 (segment_eq(get_fs(), KERNEL_DS))
+ sgp = SGP_DIRTY;
index = *ppos >> PAGE_CACHE_SHIFT;
offset = *ppos & ~PAGE_CACHE_MASK;
for (;;) {
struct page *page = NULL;
- unsigned long end_index, nr, ret;
+ pgoff_t end_index;
+ unsigned long nr, ret;
loff_t i_size = i_size_read(inode);
end_index = i_size >> PAGE_CACHE_SHIFT;
break;
}
- desc->error = shmem_getpage(inode, index, &page, SGP_READ, NULL);
+ desc->error = shmem_getpage(inode, index, &page, sgp, NULL);
if (desc->error) {
if (desc->error == -EINVAL)
desc->error = 0;
break;
}
+ if (page)
+ unlock_page(page);
/*
* We must evaluate after, since reads (unlike writes)
file_accessed(filp);
}
-static ssize_t shmem_file_read(struct file *filp, char __user *buf, size_t count, loff_t *ppos)
+static ssize_t shmem_file_aio_read(struct kiocb *iocb,
+ const struct iovec *iov, unsigned long nr_segs, loff_t pos)
{
- read_descriptor_t desc;
+ struct file *filp = iocb->ki_filp;
+ ssize_t retval;
+ unsigned long seg;
+ size_t count;
+ loff_t *ppos = &iocb->ki_pos;
- if ((ssize_t) count < 0)
- return -EINVAL;
- if (!access_ok(VERIFY_WRITE, buf, count))
- return -EFAULT;
- if (!count)
- return 0;
+ retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
+ if (retval)
+ return retval;
- desc.written = 0;
- desc.count = count;
- desc.arg.buf = buf;
- desc.error = 0;
+ for (seg = 0; seg < nr_segs; seg++) {
+ read_descriptor_t desc;
- do_shmem_file_read(filp, ppos, &desc, file_read_actor);
- if (desc.written)
- return desc.written;
- return desc.error;
+ desc.written = 0;
+ desc.arg.buf = iov[seg].iov_base;
+ desc.count = iov[seg].iov_len;
+ if (desc.count == 0)
+ continue;
+ desc.error = 0;
+ do_shmem_file_read(filp, ppos, &desc, file_read_actor);
+ retval += desc.written;
+ if (desc.error) {
+ retval = retval ?: desc.error;
+ break;
+ }
+ if (desc.count > 0)
+ break;
+ }
+ return retval;
}
-static ssize_t shmem_file_sendfile(struct file *in_file, loff_t *ppos,
- size_t count, read_actor_t actor, void *target)
+static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
+ struct pipe_inode_info *pipe, size_t len,
+ unsigned int flags)
{
- read_descriptor_t desc;
-
- if (!count)
+ 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,
+ .flags = flags,
+ .ops = &page_cache_pipe_buf_ops,
+ .spd_release = spd_release_page,
+ };
+
+ isize = i_size_read(inode);
+ if (unlikely(*ppos >= isize))
return 0;
- desc.written = 0;
- desc.count = count;
- desc.arg.data = target;
- desc.error = 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, pipe->buffers);
+
+ 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++]);
- do_shmem_file_read(in_file, ppos, &desc, actor);
- if (desc.written)
- return desc.written;
- return desc.error;
+ if (spd.nr_pages)
+ error = splice_to_pipe(pipe, &spd);
+
+ splice_shrink_spd(pipe, &spd);
+
+ if (error > 0) {
+ *ppos += error;
+ file_accessed(in);
+ }
+ return error;
}
static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf)
buf->f_type = TMPFS_MAGIC;
buf->f_bsize = PAGE_CACHE_SIZE;
buf->f_namelen = NAME_MAX;
- spin_lock(&sbinfo->stat_lock);
if (sbinfo->max_blocks) {
buf->f_blocks = sbinfo->max_blocks;
- buf->f_bavail = buf->f_bfree = sbinfo->free_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 */
- spin_unlock(&sbinfo->stat_lock);
return 0;
}
static int
shmem_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev)
{
- struct inode *inode = shmem_get_inode(dir->i_sb, mode, dev);
+ struct inode *inode;
int error = -ENOSPC;
+ inode = shmem_get_inode(dir->i_sb, dir, mode, dev, VM_NORESERVE);
if (inode) {
- error = security_inode_init_security(inode, dir, NULL, NULL,
- NULL);
+ error = security_inode_init_security(inode, dir,
+ &dentry->d_name, NULL,
+ NULL, NULL);
if (error) {
if (error != -EOPNOTSUPP) {
iput(inode);
return error;
}
}
- error = shmem_acl_init(inode, dir);
+#ifdef CONFIG_TMPFS_POSIX_ACL
+ error = generic_acl_init(inode, dir);
if (error) {
iput(inode);
return error;
}
- if (dir->i_mode & S_ISGID) {
- inode->i_gid = dir->i_gid;
- if (S_ISDIR(mode))
- inode->i_mode |= S_ISGID;
- }
+#else
+ error = 0;
+#endif
dir->i_size += BOGO_DIRENT_SIZE;
dir->i_ctime = dir->i_mtime = CURRENT_TIME;
d_instantiate(dentry, inode);
if ((error = shmem_mknod(dir, dentry, mode | S_IFDIR, 0)))
return error;
- dir->i_nlink++;
+ inc_nlink(dir);
return 0;
}
static int shmem_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
{
struct inode *inode = old_dentry->d_inode;
- struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
+ 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.
*/
- if (sbinfo->max_inodes) {
- spin_lock(&sbinfo->stat_lock);
- if (!sbinfo->free_inodes) {
- spin_unlock(&sbinfo->stat_lock);
- return -ENOSPC;
- }
- sbinfo->free_inodes--;
- spin_unlock(&sbinfo->stat_lock);
- }
+ 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;
- inode->i_nlink++;
- atomic_inc(&inode->i_count); /* New dentry reference */
+ inc_nlink(inode);
+ ihold(inode); /* New dentry reference */
dget(dentry); /* Extra pinning count for the created dentry */
d_instantiate(dentry, inode);
- return 0;
+out:
+ return ret;
}
static int shmem_unlink(struct inode *dir, struct dentry *dentry)
{
struct inode *inode = dentry->d_inode;
- if (inode->i_nlink > 1 && !S_ISDIR(inode->i_mode)) {
- struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
- if (sbinfo->max_inodes) {
- spin_lock(&sbinfo->stat_lock);
- sbinfo->free_inodes++;
- spin_unlock(&sbinfo->stat_lock);
- }
- }
+ 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(old_dir);
} else if (they_are_dirs) {
drop_nlink(old_dir);
- new_dir->i_nlink++;
+ 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, NULL,
+ NULL, NULL);
+ if (error) {
+ if (error != -EOPNOTSUPP) {
+ iput(inode);
+ return error;
+ }
+ error = 0;
+ }
+
+ info = SHMEM_I(inode);
+ inode->i_size = len-1;
+ if (len <= SHMEM_SYMLINK_INLINE_LEN) {
+ /* do it inline */
+ memcpy(info->inline_symlink, symname, len);
+ inode->i_op = &shmem_symlink_inline_operations;
+ } 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, KM_USER0);
+ memcpy(kaddr, symname, len);
+ kunmap_atomic(kaddr, KM_USER0);
+ 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 void *shmem_follow_link_inline(struct dentry *dentry, struct nameidata *nd)
+{
+ nd_set_link(nd, SHMEM_I(dentry->d_inode)->inline_symlink);
+ return NULL;
+}
+
+static void *shmem_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+ struct page *page = NULL;
+ int error = shmem_getpage(dentry->d_inode, 0, &page, SGP_READ, NULL);
+ nd_set_link(nd, error ? ERR_PTR(error) : kmap(page));
+ if (page)
+ unlock_page(page);
+ return page;
+}
+
+static void shmem_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie)
+{
+ if (!IS_ERR(nd_get_link(nd))) {
+ 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.
+ */
+
+static int shmem_xattr_get(struct dentry *dentry, const char *name,
+ void *buffer, size_t size)
+{
+ struct shmem_inode_info *info;
+ struct shmem_xattr *xattr;
+ int ret = -ENODATA;
+
+ info = SHMEM_I(dentry->d_inode);
+
+ spin_lock(&info->lock);
+ list_for_each_entry(xattr, &info->xattr_list, list) {
+ if (strcmp(name, xattr->name))
+ continue;
+
+ ret = xattr->size;
+ if (buffer) {
+ if (size < xattr->size)
+ ret = -ERANGE;
+ else
+ memcpy(buffer, xattr->value, xattr->size);
+ }
+ break;
+ }
+ spin_unlock(&info->lock);
+ return ret;
+}
+
+static int shmem_xattr_set(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags)
+{
+ struct inode *inode = dentry->d_inode;
+ struct shmem_inode_info *info = SHMEM_I(inode);
+ struct shmem_xattr *xattr;
+ struct shmem_xattr *new_xattr = NULL;
+ size_t len;
+ int err = 0;
+
+ /* value == NULL means remove */
+ if (value) {
+ /* wrap around? */
+ len = sizeof(*new_xattr) + size;
+ if (len <= sizeof(*new_xattr))
+ return -ENOMEM;
+
+ new_xattr = kmalloc(len, GFP_KERNEL);
+ if (!new_xattr)
+ return -ENOMEM;
+
+ new_xattr->name = kstrdup(name, GFP_KERNEL);
+ if (!new_xattr->name) {
+ kfree(new_xattr);
+ return -ENOMEM;
+ }
+
+ new_xattr->size = size;
+ memcpy(new_xattr->value, value, size);
+ }
+
+ spin_lock(&info->lock);
+ list_for_each_entry(xattr, &info->xattr_list, list) {
+ if (!strcmp(name, xattr->name)) {
+ if (flags & XATTR_CREATE) {
+ xattr = new_xattr;
+ err = -EEXIST;
+ } else if (new_xattr) {
+ list_replace(&xattr->list, &new_xattr->list);
+ } else {
+ list_del(&xattr->list);
+ }
+ goto out;
+ }
+ }
+ if (flags & XATTR_REPLACE) {
+ xattr = new_xattr;
+ err = -ENODATA;
+ } else {
+ list_add(&new_xattr->list, &info->xattr_list);
+ xattr = NULL;
+ }
+out:
+ spin_unlock(&info->lock);
+ if (xattr)
+ kfree(xattr->name);
+ kfree(xattr);
+ return err;
+}
+
+static const struct xattr_handler *shmem_xattr_handlers[] = {
+#ifdef CONFIG_TMPFS_POSIX_ACL
+ &generic_acl_access_handler,
+ &generic_acl_default_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)
+{
+ 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);
- 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;
+ err = shmem_xattr_validate(name);
+ if (err)
+ return err;
+
+ return shmem_xattr_get(dentry, name, buffer, size);
}
-static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
+static int shmem_setxattr(struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags)
{
- int error;
- int len;
- struct inode *inode;
- struct page *page = NULL;
- char *kaddr;
- struct shmem_inode_info *info;
+ int err;
- len = strlen(symname) + 1;
- if (len > PAGE_CACHE_SIZE)
- return -ENAMETOOLONG;
+ /*
+ * 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);
- inode = shmem_get_inode(dir->i_sb, S_IFLNK|S_IRWXUGO, 0);
- if (!inode)
- return -ENOSPC;
+ err = shmem_xattr_validate(name);
+ if (err)
+ return err;
- error = security_inode_init_security(inode, dir, NULL, NULL,
- NULL);
- if (error) {
- if (error != -EOPNOTSUPP) {
- iput(inode);
- return error;
- }
- error = 0;
- }
+ if (size == 0)
+ value = ""; /* empty EA, do not remove */
+
+ return shmem_xattr_set(dentry, name, value, size, flags);
- info = SHMEM_I(inode);
- inode->i_size = len-1;
- if (len <= (char *)inode - (char *)info) {
- /* do it inline */
- memcpy(info, symname, len);
- inode->i_op = &shmem_symlink_inline_operations;
- } else {
- error = shmem_getpage(inode, 0, &page, SGP_WRITE, NULL);
- if (error) {
- iput(inode);
- return error;
- }
- inode->i_op = &shmem_symlink_inode_operations;
- kaddr = kmap_atomic(page, KM_USER0);
- memcpy(kaddr, symname, len);
- kunmap_atomic(kaddr, KM_USER0);
- set_page_dirty(page);
- page_cache_release(page);
- }
- if (dir->i_mode & S_ISGID)
- inode->i_gid = dir->i_gid;
- dir->i_size += BOGO_DIRENT_SIZE;
- dir->i_ctime = dir->i_mtime = CURRENT_TIME;
- d_instantiate(dentry, inode);
- dget(dentry);
- return 0;
}
-static void *shmem_follow_link_inline(struct dentry *dentry, struct nameidata *nd)
+static int shmem_removexattr(struct dentry *dentry, const char *name)
{
- nd_set_link(nd, (char *)SHMEM_I(dentry->d_inode));
- return NULL;
+ 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 shmem_xattr_set(dentry, name, NULL, 0, XATTR_REPLACE);
}
-static void *shmem_follow_link(struct dentry *dentry, struct nameidata *nd)
+static bool xattr_is_trusted(const char *name)
{
- struct page *page = NULL;
- int res = shmem_getpage(dentry->d_inode, 0, &page, SGP_READ, NULL);
- nd_set_link(nd, res ? ERR_PTR(res) : kmap(page));
- return page;
+ return !strncmp(name, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN);
}
-static void shmem_put_link(struct dentry *dentry, struct nameidata *nd, void *cookie)
+static ssize_t shmem_listxattr(struct dentry *dentry, char *buffer, size_t size)
{
- if (!IS_ERR(nd_get_link(nd))) {
- struct page *page = cookie;
- kunmap(page);
- mark_page_accessed(page);
- page_cache_release(page);
+ bool trusted = capable(CAP_SYS_ADMIN);
+ struct shmem_xattr *xattr;
+ struct shmem_inode_info *info;
+ size_t used = 0;
+
+ info = SHMEM_I(dentry->d_inode);
+
+ spin_lock(&info->lock);
+ list_for_each_entry(xattr, &info->xattr_list, list) {
+ size_t len;
+
+ /* skip "trusted." attributes for unprivileged callers */
+ if (!trusted && xattr_is_trusted(xattr->name))
+ continue;
+
+ len = strlen(xattr->name) + 1;
+ used += len;
+ if (buffer) {
+ if (size < used) {
+ used = -ERANGE;
+ break;
+ }
+ memcpy(buffer, xattr->name, len);
+ buffer += len;
+ }
}
+ spin_unlock(&info->lock);
+
+ return used;
}
+#endif /* CONFIG_TMPFS_XATTR */
-static struct inode_operations shmem_symlink_inline_operations = {
+static const struct inode_operations shmem_symlink_inline_operations = {
.readlink = generic_readlink,
.follow_link = shmem_follow_link_inline,
+#ifdef CONFIG_TMPFS_XATTR
+ .setxattr = shmem_setxattr,
+ .getxattr = shmem_getxattr,
+ .listxattr = shmem_listxattr,
+ .removexattr = shmem_removexattr,
+#endif
};
-static struct inode_operations shmem_symlink_inode_operations = {
- .truncate = shmem_truncate,
+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
};
-#ifdef CONFIG_TMPFS_POSIX_ACL
-/**
- * Superblocks without xattr inode operations will get security.* xattr
- * support from the VFS "for free". As soon as we have any other xattrs
- * like ACLs, we also need to implement the security.* handlers at
- * filesystem level, though.
- */
-
-static size_t shmem_xattr_security_list(struct inode *inode, char *list,
- size_t list_len, const char *name,
- size_t name_len)
+static struct dentry *shmem_get_parent(struct dentry *child)
{
- return security_inode_listsecurity(inode, list, list_len);
+ return ERR_PTR(-ESTALE);
}
-static int shmem_xattr_security_get(struct inode *inode, const char *name,
- void *buffer, size_t size)
+static int shmem_match(struct inode *ino, void *vfh)
{
- if (strcmp(name, "") == 0)
- return -EINVAL;
- return security_inode_getsecurity(inode, name, buffer, size,
- -EOPNOTSUPP);
+ __u32 *fh = vfh;
+ __u64 inum = fh[2];
+ inum = (inum << 32) | fh[1];
+ return ino->i_ino == inum && fh[0] == ino->i_generation;
}
-static int shmem_xattr_security_set(struct inode *inode, const char *name,
- const void *value, size_t size, int flags)
+static struct dentry *shmem_fh_to_dentry(struct super_block *sb,
+ struct fid *fid, int fh_len, int fh_type)
{
- if (strcmp(name, "") == 0)
- return -EINVAL;
- return security_inode_setsecurity(inode, name, value, size, flags);
+ struct inode *inode;
+ struct dentry *dentry = NULL;
+ u64 inum = fid->raw[2];
+ inum = (inum << 32) | fid->raw[1];
+
+ if (fh_len < 3)
+ return NULL;
+
+ inode = ilookup5(sb, (unsigned long)(inum + fid->raw[0]),
+ shmem_match, fid->raw);
+ if (inode) {
+ dentry = d_find_alias(inode);
+ iput(inode);
+ }
+
+ return dentry;
}
-struct xattr_handler shmem_xattr_security_handler = {
- .prefix = XATTR_SECURITY_PREFIX,
- .list = shmem_xattr_security_list,
- .get = shmem_xattr_security_get,
- .set = shmem_xattr_security_set,
-};
+static int shmem_encode_fh(struct dentry *dentry, __u32 *fh, int *len,
+ int connectable)
+{
+ struct inode *inode = dentry->d_inode;
-static struct xattr_handler *shmem_xattr_handlers[] = {
- &shmem_xattr_acl_access_handler,
- &shmem_xattr_acl_default_handler,
- &shmem_xattr_security_handler,
- NULL
+ if (*len < 3) {
+ *len = 3;
+ return 255;
+ }
+
+ 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,
};
-#endif
-static int shmem_parse_options(char *options, int *mode, uid_t *uid,
- gid_t *gid, unsigned long *blocks, unsigned long *inodes,
- int *policy, nodemask_t *policy_nodes)
+static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo,
+ bool remount)
{
char *this_char, *value, *rest;
}
if (*rest)
goto bad_val;
- *blocks = size >> PAGE_CACHE_SHIFT;
+ sbinfo->max_blocks =
+ DIV_ROUND_UP(size, PAGE_CACHE_SIZE);
} else if (!strcmp(this_char,"nr_blocks")) {
- *blocks = memparse(value,&rest);
+ sbinfo->max_blocks = memparse(value, &rest);
if (*rest)
goto bad_val;
} else if (!strcmp(this_char,"nr_inodes")) {
- *inodes = memparse(value,&rest);
+ sbinfo->max_inodes = memparse(value, &rest);
if (*rest)
goto bad_val;
} else if (!strcmp(this_char,"mode")) {
- if (!mode)
+ if (remount)
continue;
- *mode = simple_strtoul(value,&rest,8);
+ sbinfo->mode = simple_strtoul(value, &rest, 8) & 07777;
if (*rest)
goto bad_val;
} else if (!strcmp(this_char,"uid")) {
- if (!uid)
+ if (remount)
continue;
- *uid = simple_strtoul(value,&rest,0);
+ sbinfo->uid = simple_strtoul(value, &rest, 0);
if (*rest)
goto bad_val;
} else if (!strcmp(this_char,"gid")) {
- if (!gid)
+ if (remount)
continue;
- *gid = simple_strtoul(value,&rest,0);
+ sbinfo->gid = simple_strtoul(value, &rest, 0);
if (*rest)
goto bad_val;
} else if (!strcmp(this_char,"mpol")) {
- if (shmem_parse_mpol(value,policy,policy_nodes))
+ if (mpol_parse_str(value, &sbinfo->mpol, 1))
goto bad_val;
} else {
printk(KERN_ERR "tmpfs: Bad mount option %s\n",
static int shmem_remount_fs(struct super_block *sb, int *flags, char *data)
{
struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
- unsigned long max_blocks = sbinfo->max_blocks;
- unsigned long max_inodes = sbinfo->max_inodes;
- int policy = sbinfo->policy;
- nodemask_t policy_nodes = sbinfo->policy_nodes;
- unsigned long blocks;
+ struct shmem_sb_info config = *sbinfo;
unsigned long inodes;
int error = -EINVAL;
- if (shmem_parse_options(data, NULL, NULL, NULL, &max_blocks,
- &max_inodes, &policy, &policy_nodes))
+ if (shmem_parse_options(data, &config, true))
return error;
spin_lock(&sbinfo->stat_lock);
- blocks = sbinfo->max_blocks - sbinfo->free_blocks;
inodes = sbinfo->max_inodes - sbinfo->free_inodes;
- if (max_blocks < blocks)
+ if (percpu_counter_compare(&sbinfo->used_blocks, config.max_blocks) > 0)
goto out;
- if (max_inodes < inodes)
+ if (config.max_inodes < inodes)
goto out;
/*
* Those tests also disallow limited->unlimited while any are in
* but we must separately disallow unlimited->limited, because
* in that case we have no record of how much is already in use.
*/
- if (max_blocks && !sbinfo->max_blocks)
+ if (config.max_blocks && !sbinfo->max_blocks)
goto out;
- if (max_inodes && !sbinfo->max_inodes)
+ if (config.max_inodes && !sbinfo->max_inodes)
goto out;
error = 0;
- sbinfo->max_blocks = max_blocks;
- sbinfo->free_blocks = max_blocks - blocks;
- sbinfo->max_inodes = max_inodes;
- sbinfo->free_inodes = max_inodes - inodes;
- sbinfo->policy = policy;
- sbinfo->policy_nodes = policy_nodes;
+ sbinfo->max_blocks = config.max_blocks;
+ sbinfo->max_inodes = config.max_inodes;
+ sbinfo->free_inodes = config.max_inodes - inodes;
+
+ mpol_put(sbinfo->mpol);
+ sbinfo->mpol = config.mpol; /* transfers initial ref */
out:
spin_unlock(&sbinfo->stat_lock);
return error;
}
-#endif
+
+static int shmem_show_options(struct seq_file *seq, struct vfsmount *vfs)
+{
+ struct shmem_sb_info *sbinfo = SHMEM_SB(vfs->mnt_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=%03o", sbinfo->mode);
+ if (sbinfo->uid != 0)
+ seq_printf(seq, ",uid=%u", sbinfo->uid);
+ if (sbinfo->gid != 0)
+ seq_printf(seq, ",gid=%u", sbinfo->gid);
+ shmem_show_mpol(seq, sbinfo->mpol);
+ return 0;
+}
+#endif /* CONFIG_TMPFS */
static void shmem_put_super(struct super_block *sb)
{
- kfree(sb->s_fs_info);
+ struct shmem_sb_info *sbinfo = SHMEM_SB(sb);
+
+ percpu_counter_destroy(&sbinfo->used_blocks);
+ kfree(sbinfo);
sb->s_fs_info = NULL;
}
-static int shmem_fill_super(struct super_block *sb,
- void *data, int silent)
+int shmem_fill_super(struct super_block *sb, void *data, int silent)
{
struct inode *inode;
struct dentry *root;
- int mode = S_IRWXUGO | S_ISVTX;
- uid_t uid = current->fsuid;
- gid_t gid = current->fsgid;
- int err = -ENOMEM;
struct shmem_sb_info *sbinfo;
- unsigned long blocks = 0;
- unsigned long inodes = 0;
- int policy = MPOL_DEFAULT;
- nodemask_t policy_nodes = node_online_map;
+ 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
/*
* but the internal instance is left unlimited.
*/
if (!(sb->s_flags & MS_NOUSER)) {
- blocks = totalram_pages / 2;
- inodes = totalram_pages - totalhigh_pages;
- if (inodes > blocks)
- inodes = blocks;
- if (shmem_parse_options(data, &mode, &uid, &gid, &blocks,
- &inodes, &policy, &policy_nodes))
- return -EINVAL;
+ 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;
+ }
}
+ sb->s_export_op = &shmem_export_ops;
#else
sb->s_flags |= MS_NOUSER;
#endif
- /* Round up to L1_CACHE_BYTES to resist false sharing */
- sbinfo = kmalloc(max((int)sizeof(struct shmem_sb_info),
- L1_CACHE_BYTES), GFP_KERNEL);
- if (!sbinfo)
- return -ENOMEM;
-
spin_lock_init(&sbinfo->stat_lock);
- sbinfo->max_blocks = blocks;
- sbinfo->free_blocks = blocks;
- sbinfo->max_inodes = inodes;
- sbinfo->free_inodes = inodes;
- sbinfo->policy = policy;
- sbinfo->policy_nodes = policy_nodes;
+ if (percpu_counter_init(&sbinfo->used_blocks, 0))
+ goto failed;
+ sbinfo->free_inodes = sbinfo->max_inodes;
- sb->s_fs_info = sbinfo;
- sb->s_maxbytes = SHMEM_MAX_BYTES;
+ 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_POSIX_ACL
+#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, S_IFDIR | mode, 0);
+ inode = shmem_get_inode(sb, NULL, S_IFDIR | sbinfo->mode, 0, VM_NORESERVE);
if (!inode)
goto failed;
- inode->i_uid = uid;
- inode->i_gid = gid;
+ inode->i_uid = sbinfo->uid;
+ inode->i_gid = sbinfo->gid;
root = d_alloc_root(inode);
if (!root)
goto failed_iput;
static struct inode *shmem_alloc_inode(struct super_block *sb)
{
- struct shmem_inode_info *p;
- p = (struct shmem_inode_info *)kmem_cache_alloc(shmem_inode_cachep, SLAB_KERNEL);
- if (!p)
+ struct shmem_inode_info *info;
+ info = kmem_cache_alloc(shmem_inode_cachep, GFP_KERNEL);
+ if (!info)
return NULL;
- return &p->vfs_inode;
+ return &info->vfs_inode;
+}
+
+static void shmem_destroy_callback(struct rcu_head *head)
+{
+ struct inode *inode = container_of(head, struct inode, i_rcu);
+ INIT_LIST_HEAD(&inode->i_dentry);
+ kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode));
}
static void shmem_destroy_inode(struct inode *inode)
/* only struct inode is valid if it's an inline symlink */
mpol_free_shared_policy(&SHMEM_I(inode)->policy);
}
- shmem_acl_destroy_inode(inode);
- kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode));
+ call_rcu(&inode->i_rcu, shmem_destroy_callback);
}
-static void init_once(void *foo, struct kmem_cache *cachep,
- unsigned long flags)
+static void shmem_init_inode(void *foo)
{
- struct shmem_inode_info *p = (struct shmem_inode_info *) foo;
-
- if ((flags & (SLAB_CTOR_VERIFY|SLAB_CTOR_CONSTRUCTOR)) ==
- SLAB_CTOR_CONSTRUCTOR) {
- inode_init_once(&p->vfs_inode);
-#ifdef CONFIG_TMPFS_POSIX_ACL
- p->i_acl = NULL;
- p->i_default_acl = NULL;
-#endif
- }
+ struct shmem_inode_info *info = foo;
+ inode_init_once(&info->vfs_inode);
}
-static int init_inodecache(void)
+static int shmem_init_inodecache(void)
{
shmem_inode_cachep = kmem_cache_create("shmem_inode_cache",
sizeof(struct shmem_inode_info),
- 0, 0, init_once, NULL);
- if (shmem_inode_cachep == NULL)
- return -ENOMEM;
+ 0, SLAB_PANIC, shmem_init_inode);
return 0;
}
-static void destroy_inodecache(void)
+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_nobuffers,
+ .set_page_dirty = __set_page_dirty_no_writeback,
#ifdef CONFIG_TMPFS
- .prepare_write = shmem_prepare_write,
- .commit_write = simple_commit_write,
+ .write_begin = shmem_write_begin,
+ .write_end = shmem_write_end,
#endif
.migratepage = migrate_page,
+ .error_remove_page = generic_error_remove_page,
};
-static struct file_operations shmem_file_operations = {
+static const struct file_operations shmem_file_operations = {
.mmap = shmem_mmap,
#ifdef CONFIG_TMPFS
.llseek = generic_file_llseek,
- .read = shmem_file_read,
- .write = shmem_file_write,
- .fsync = simple_sync_file,
- .sendfile = shmem_file_sendfile,
+ .read = do_sync_read,
+ .write = do_sync_write,
+ .aio_read = shmem_file_aio_read,
+ .aio_write = generic_file_aio_write,
+ .fsync = noop_fsync,
+ .splice_read = shmem_file_splice_read,
+ .splice_write = generic_file_splice_write,
#endif
};
-static struct inode_operations shmem_inode_operations = {
- .truncate = shmem_truncate,
- .setattr = shmem_notify_change,
+static const struct inode_operations shmem_inode_operations = {
+ .setattr = shmem_setattr,
.truncate_range = shmem_truncate_range,
-#ifdef CONFIG_TMPFS_POSIX_ACL
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
- .listxattr = generic_listxattr,
- .removexattr = generic_removexattr,
- .permission = shmem_permission,
+#ifdef CONFIG_TMPFS_XATTR
+ .setxattr = shmem_setxattr,
+ .getxattr = shmem_getxattr,
+ .listxattr = shmem_listxattr,
+ .removexattr = shmem_removexattr,
#endif
-
};
-static struct inode_operations shmem_dir_inode_operations = {
+static const struct inode_operations shmem_dir_inode_operations = {
#ifdef CONFIG_TMPFS
.create = shmem_create,
.lookup = simple_lookup,
.mknod = shmem_mknod,
.rename = shmem_rename,
#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_notify_change,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
- .listxattr = generic_listxattr,
- .removexattr = generic_removexattr,
- .permission = shmem_permission,
+ .setattr = shmem_setattr,
#endif
};
-static struct inode_operations shmem_special_inode_operations = {
+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_notify_change,
- .setxattr = generic_setxattr,
- .getxattr = generic_getxattr,
- .listxattr = generic_listxattr,
- .removexattr = generic_removexattr,
- .permission = shmem_permission,
+ .setattr = shmem_setattr,
#endif
};
-static struct super_operations shmem_ops = {
+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
- .delete_inode = shmem_delete_inode,
+ .evict_inode = shmem_evict_inode,
.drop_inode = generic_delete_inode,
.put_super = shmem_put_super,
};
-static struct vm_operations_struct shmem_vm_ops = {
- .nopage = shmem_nopage,
- .populate = shmem_populate,
+static const struct vm_operations_struct shmem_vm_ops = {
+ .fault = shmem_fault,
#ifdef CONFIG_NUMA
.set_policy = shmem_set_policy,
.get_policy = shmem_get_policy,
#endif
};
-
-static int shmem_get_sb(struct file_system_type *fs_type,
- int flags, const char *dev_name, void *data, struct vfsmount *mnt)
+static struct dentry *shmem_mount(struct file_system_type *fs_type,
+ int flags, const char *dev_name, void *data)
{
- return get_sb_nodev(fs_type, flags, data, shmem_fill_super, mnt);
+ return mount_nodev(fs_type, flags, data, shmem_fill_super);
}
-static struct file_system_type tmpfs_fs_type = {
+static struct file_system_type shmem_fs_type = {
.owner = THIS_MODULE,
.name = "tmpfs",
- .get_sb = shmem_get_sb,
+ .mount = shmem_mount,
.kill_sb = kill_litter_super,
};
-static struct vfsmount *shm_mnt;
-static int __init init_tmpfs(void)
+int __init shmem_init(void)
{
int error;
- error = init_inodecache();
+ error = bdi_init(&shmem_backing_dev_info);
+ if (error)
+ goto out4;
+
+ error = shmem_init_inodecache();
if (error)
goto out3;
- error = register_filesystem(&tmpfs_fs_type);
+ error = register_filesystem(&shmem_fs_type);
if (error) {
printk(KERN_ERR "Could not register tmpfs\n");
goto out2;
}
- shm_mnt = vfs_kern_mount(&tmpfs_fs_type, MS_NOUSER,
- tmpfs_fs_type.name, NULL);
+ shm_mnt = vfs_kern_mount(&shmem_fs_type, MS_NOUSER,
+ shmem_fs_type.name, NULL);
if (IS_ERR(shm_mnt)) {
error = PTR_ERR(shm_mnt);
printk(KERN_ERR "Could not kern_mount tmpfs\n");
return 0;
out1:
- unregister_filesystem(&tmpfs_fs_type);
+ unregister_filesystem(&shmem_fs_type);
out2:
- destroy_inodecache();
+ shmem_destroy_inodecache();
out3:
+ bdi_destroy(&shmem_backing_dev_info);
+out4:
shm_mnt = ERR_PTR(error);
return error;
}
-module_init(init_tmpfs)
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+/**
+ * mem_cgroup_get_shmem_target - find page or swap assigned to the shmem file
+ * @inode: the inode to be searched
+ * @index: the page offset to be searched
+ * @pagep: the pointer for the found page to be stored
+ * @swapp: the pointer for the found swap entry to be stored
+ *
+ * If a page is found, refcount of it is incremented. Callers should handle
+ * these refcount.
+ */
+void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t index,
+ struct page **pagep, swp_entry_t *swapp)
+{
+ struct shmem_inode_info *info = SHMEM_I(inode);
+ struct page *page = NULL;
+ swp_entry_t swap = {0};
+
+ if ((index << PAGE_CACHE_SHIFT) >= i_size_read(inode))
+ goto out;
+
+ spin_lock(&info->lock);
+#ifdef CONFIG_SWAP
+ swap = shmem_get_swap(info, index);
+ if (swap.val)
+ page = find_get_page(&swapper_space, swap.val);
+ else
+#endif
+ page = find_get_page(inode->i_mapping, index);
+ spin_unlock(&info->lock);
+out:
+ *pagep = page;
+ *swapp = swap;
+}
+#endif
+
+#else /* !CONFIG_SHMEM */
/*
- * shmem_file_setup - get an unlinked file living in tmpfs
+ * 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.
+ */
+
+#include <linux/ramfs.h>
+
+static struct file_system_type shmem_fs_type = {
+ .name = "tmpfs",
+ .mount = ramfs_mount,
+ .kill_sb = kill_litter_super,
+};
+
+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_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);
+
+#ifdef CONFIG_CGROUP_MEM_RES_CTLR
+/**
+ * mem_cgroup_get_shmem_target - find page or swap assigned to the shmem file
+ * @inode: the inode to be searched
+ * @index: the page offset to be searched
+ * @pagep: the pointer for the found page to be stored
+ * @swapp: the pointer for the found swap entry to be stored
*
+ * If a page is found, refcount of it is incremented. Callers should handle
+ * these refcount.
+ */
+void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t index,
+ struct page **pagep, swp_entry_t *swapp)
+{
+ struct page *page = NULL;
+
+ if ((index << PAGE_CACHE_SHIFT) >= i_size_read(inode))
+ goto out;
+ page = find_get_page(inode->i_mapping, index);
+out:
+ *pagep = page;
+ *swapp = (swp_entry_t){0};
+}
+#endif
+
+#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 */
+
+/**
+ * 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(char *name, loff_t size, unsigned long flags)
+struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags)
{
int error;
struct file *file;
struct inode *inode;
- struct dentry *dentry, *root;
+ struct path path;
+ struct dentry *root;
struct qstr this;
if (IS_ERR(shm_mnt))
return (void *)shm_mnt;
- if (size < 0 || size > SHMEM_MAX_BYTES)
+ if (size < 0 || size > MAX_LFS_FILESIZE)
return ERR_PTR(-EINVAL);
if (shmem_acct_size(flags, size))
this.len = strlen(name);
this.hash = 0; /* will go */
root = shm_mnt->mnt_root;
- dentry = d_alloc(root, &this);
- if (!dentry)
+ path.dentry = d_alloc(root, &this);
+ if (!path.dentry)
goto put_memory;
-
- error = -ENFILE;
- file = get_empty_filp();
- if (!file)
- goto put_dentry;
+ path.mnt = mntget(shm_mnt);
error = -ENOSPC;
- inode = shmem_get_inode(root->d_sb, S_IFREG | S_IRWXUGO, 0);
+ inode = shmem_get_inode(root->d_sb, NULL, S_IFREG | S_IRWXUGO, 0, flags);
if (!inode)
- goto close_file;
+ goto put_dentry;
- SHMEM_I(inode)->flags = flags & VM_ACCOUNT;
- d_instantiate(dentry, inode);
+ d_instantiate(path.dentry, inode);
inode->i_size = size;
inode->i_nlink = 0; /* It is unlinked */
- file->f_vfsmnt = mntget(shm_mnt);
- file->f_dentry = dentry;
- file->f_mapping = inode->i_mapping;
- file->f_op = &shmem_file_operations;
- file->f_mode = FMODE_WRITE | FMODE_READ;
+#ifndef CONFIG_MMU
+ error = ramfs_nommu_expand_for_mapping(inode, size);
+ if (error)
+ goto put_dentry;
+#endif
+
+ error = -ENFILE;
+ file = alloc_file(&path, FMODE_WRITE | FMODE_READ,
+ &shmem_file_operations);
+ if (!file)
+ goto put_dentry;
+
return file;
-close_file:
- put_filp(file);
put_dentry:
- dput(dentry);
+ path_put(&path);
put_memory:
shmem_unacct_size(flags, size);
return ERR_PTR(error);
}
+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)
fput(vma->vm_file);
vma->vm_file = file;
vma->vm_ops = &shmem_vm_ops;
+ vma->vm_flags |= VM_CAN_NONLINEAR;
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);
Code Review / linux-2.6.git / blobdiff