#include <linux/shmem_fs.h>
#include <linux/writeback.h>
#include <linux/blkdev.h>
+#include <linux/splice.h>
#include <linux/security.h>
#include <linux/swapops.h>
#include <linux/mempolicy.h>
#include <asm/div64.h>
#include <asm/pgtable.h>
-/*
- * The maximum size of a shmem/tmpfs file is limited by the maximum size of
- * its triple-indirect swap vector - see illustration at shmem_swp_entry().
- *
- * With 4kB page size, maximum file size is just over 2TB on a 32-bit kernel,
- * but one eighth of that on a 64-bit kernel. With 8kB page size, maximum
- * file size is just over 4TB on a 64-bit kernel, but 16TB on a 32-bit kernel,
- * MAX_LFS_FILESIZE being then more restrictive than swap vector layout.
- *
- * We use / and * instead of shifts in the definitions below, so that the swap
- * vector can be tested with small even values (e.g. 20) for ENTRIES_PER_PAGE.
- */
-#define ENTRIES_PER_PAGE (PAGE_CACHE_SIZE/sizeof(unsigned long))
-#define ENTRIES_PER_PAGEPAGE ((unsigned long long)ENTRIES_PER_PAGE*ENTRIES_PER_PAGE)
-
-#define SHMSWP_MAX_INDEX (SHMEM_NR_DIRECT + (ENTRIES_PER_PAGEPAGE/2) * (ENTRIES_PER_PAGE+1))
-#define SHMSWP_MAX_BYTES (SHMSWP_MAX_INDEX << PAGE_CACHE_SHIFT)
-
-#define SHMEM_MAX_BYTES min_t(unsigned long long, SHMSWP_MAX_BYTES, MAX_LFS_FILESIZE)
-#define SHMEM_MAX_INDEX ((unsigned long)((SHMEM_MAX_BYTES+1) >> PAGE_CACHE_SHIFT))
-
#define BLOCKS_PER_PAGE (PAGE_CACHE_SIZE/512)
#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
char value[0];
};
-/* Flag allocation requirements to shmem_getpage and shmem_swp_alloc */
+/* Flag allocation requirements to shmem_getpage */
enum sgp_type {
SGP_READ, /* don't exceed i_size, don't allocate page */
SGP_CACHE, /* don't exceed i_size, may allocate page */
}
#endif
-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.
- *
- * Mobility flags are masked out as swap vectors cannot move
- */
- return alloc_pages((gfp_mask & ~GFP_MOVABLE_MASK) | __GFP_ZERO,
- 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)
-{
- kunmap_atomic(dir, KM_USER0);
-}
-
-static swp_entry_t *shmem_swp_map(struct page *page)
-{
- return (swp_entry_t *)kmap_atomic(page, KM_USER1);
-}
-
-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)
struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
if (sbinfo->max_blocks) {
percpu_counter_add(&sbinfo->used_blocks, -pages);
- spin_lock(&inode->i_lock);
inode->i_blocks -= pages*BLOCKS_PER_PAGE;
- spin_unlock(&inode->i_lock);
}
}
}
}
-/**
- * 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.
- * @info: info structure for the inode
- * @index: index of the page to find
- * @sgp: check and recheck i_size? skip allocation?
- *
- * If the entry does not exist, allocate it.
- */
-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);
-
- while (!(entry = shmem_swp_entry(info, index, &page))) {
- if (sgp == SGP_READ)
- return shmem_swp_map(ZERO_PAGE(0));
- /*
- * Test used_blocks against 1 less max_blocks, 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) {
- if (percpu_counter_compare(&sbinfo->used_blocks,
- sbinfo->max_blocks - 1) >= 0)
- return ERR_PTR(-ENOSPC);
- percpu_counter_inc(&sbinfo->used_blocks);
- spin_lock(&inode->i_lock);
- inode->i_blocks += BLOCKS_PER_PAGE;
- spin_unlock(&inode->i_lock);
- }
-
- spin_unlock(&info->lock);
- page = shmem_dir_alloc(mapping_gfp_mask(inode->i_mapping));
- 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;
- }
- if (info->next_index <= index)
- info->next_index = index + 1;
- }
- 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;
-}
-
-/**
- * shmem_free_swp - free some swap entries in a directory
- * @dir: pointer to the directory
- * @edir: pointer after last entry of the directory
- * @punch_lock: pointer to spinlock when needed for the holepunch case
- */
-static int shmem_free_swp(swp_entry_t *dir, swp_entry_t *edir,
- spinlock_t *punch_lock)
-{
- spinlock_t *punch_unlock = NULL;
- swp_entry_t *ptr;
- int freed = 0;
-
- for (ptr = dir; ptr < edir; ptr++) {
- if (ptr->val) {
- if (unlikely(punch_lock)) {
- punch_unlock = punch_lock;
- punch_lock = NULL;
- spin_lock(punch_unlock);
- if (!ptr->val)
- continue;
- }
- free_swap_and_cache(*ptr);
- *ptr = (swp_entry_t){0};
- freed++;
- }
- }
- if (punch_unlock)
- spin_unlock(punch_unlock);
- return freed;
-}
-
-static int shmem_map_and_free_swp(struct page *subdir, int offset,
- int limit, struct page ***dir, spinlock_t *punch_lock)
-{
- 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,
- punch_lock);
- 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;
-}
-
-static void shmem_free_pages(struct list_head *next)
-{
- 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);
-}
-
-void shmem_truncate_range(struct inode *inode, loff_t start, loff_t end)
+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;
- long nr_swaps_freed = 0;
- int offset;
- int freed;
- int punch_hole;
- spinlock_t *needs_lock;
- spinlock_t *punch_lock;
- unsigned long upper_limit;
+ pgoff_t start = (lstart + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+ pgoff_t end = (lend >> PAGE_CACHE_SHIFT);
+ pgoff_t index;
+ swp_entry_t swap;
- truncate_inode_pages_range(inode->i_mapping, start, end);
+ truncate_inode_pages_range(mapping, lstart, lend);
- inode->i_ctime = inode->i_mtime = CURRENT_TIME;
- idx = (start + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- if (idx >= info->next_index)
- return;
+ if (end > SHMEM_NR_DIRECT)
+ end = SHMEM_NR_DIRECT;
spin_lock(&info->lock);
- info->flags |= SHMEM_TRUNCATE;
- if (likely(end == (loff_t) -1)) {
- limit = info->next_index;
- upper_limit = SHMEM_MAX_INDEX;
- info->next_index = idx;
- needs_lock = NULL;
- punch_hole = 0;
- } else {
- if (end + 1 >= inode->i_size) { /* we may free a little more */
- limit = (inode->i_size + PAGE_CACHE_SIZE - 1) >>
- PAGE_CACHE_SHIFT;
- upper_limit = SHMEM_MAX_INDEX;
- } else {
- limit = (end + 1) >> PAGE_CACHE_SHIFT;
- upper_limit = limit;
- }
- needs_lock = &info->lock;
- punch_hole = 1;
- }
-
- 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);
- }
- 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, needs_lock);
- }
-
- /*
- * If there are no indirect blocks or we are punching a hole
- * below indirect blocks, nothing to be done.
- */
- if (!topdir || limit <= SHMEM_NR_DIRECT)
- goto done2;
-
- /*
- * The truncation case has already dropped info->lock, and we're safe
- * because i_size and next_index have already been lowered, preventing
- * access beyond. But in the punch_hole case, we still need to take
- * the lock when updating the swap directory, because there might be
- * racing accesses by shmem_getpage(SGP_CACHE), shmem_unuse_inode or
- * shmem_writepage. However, whenever we find we can remove a whole
- * directory page (not at the misaligned start or end of the range),
- * we first NULLify its pointer in the level above, and then have no
- * need to take the lock when updating its contents: needs_lock and
- * punch_lock (either pointing to info->lock or NULL) manage this.
- */
-
- upper_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 && upper_limit >= stage) {
- if (needs_lock) {
- spin_lock(needs_lock);
- *dir = NULL;
- spin_unlock(needs_lock);
- needs_lock = NULL;
- } else
- *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;
+ for (index = start; index < end; index++) {
+ swap = shmem_get_swap(info, index);
+ if (swap.val) {
+ free_swap_and_cache(swap);
+ shmem_put_swap(info, index, (swp_entry_t){0});
+ info->swapped--;
}
}
- 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;
- if (punch_hole)
- needs_lock = &info->lock;
- if (upper_limit >= stage) {
- if (needs_lock) {
- spin_lock(needs_lock);
- *dir = NULL;
- spin_unlock(needs_lock);
- needs_lock = NULL;
- } else
- *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;
- }
- punch_lock = needs_lock;
- subdir = dir[diroff];
- if (subdir && !offset && upper_limit-idx >= ENTRIES_PER_PAGE) {
- if (needs_lock) {
- spin_lock(needs_lock);
- dir[diroff] = NULL;
- spin_unlock(needs_lock);
- punch_lock = NULL;
- } else
- dir[diroff] = NULL;
- nr_pages_to_free++;
- list_add(&subdir->lru, &pages_to_free);
- }
- if (subdir && page_private(subdir) /* has swap entries */) {
- size = limit - idx;
- if (size > ENTRIES_PER_PAGE)
- size = ENTRIES_PER_PAGE;
- freed = shmem_map_and_free_swp(subdir,
- offset, size, &dir, punch_lock);
- if (!dir)
- dir = shmem_dir_map(middir);
- nr_swaps_freed += freed;
- if (offset || punch_lock) {
- spin_lock(&info->lock);
- set_page_private(subdir,
- page_private(subdir) - freed);
- spin_unlock(&info->lock);
- } else
- BUG_ON(page_private(subdir) != freed);
- }
- offset = 0;
- }
-done1:
- shmem_dir_unmap(dir);
-done2:
- if (inode->i_mapping->nrpages && (info->flags & SHMEM_PAGEIN)) {
+ if (mapping->nrpages) {
+ spin_unlock(&info->lock);
/*
- * Call truncate_inode_pages again: racing shmem_unuse_inode
- * may have swizzled a page in from swap since
- * truncate_pagecache 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.
+ * A page may have meanwhile sneaked in from swap.
*/
- truncate_inode_pages_range(inode->i_mapping, start, end);
+ truncate_inode_pages_range(mapping, lstart, lend);
+ spin_lock(&info->lock);
}
- 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);
- }
+ inode->i_ctime = inode->i_mtime = CURRENT_TIME;
}
EXPORT_SYMBOL_GPL(shmem_truncate_range);
if (page)
unlock_page(page);
}
- /*
- * 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 (newsize) {
- struct shmem_inode_info *info = SHMEM_I(inode);
- spin_lock(&info->lock);
- info->flags &= ~SHMEM_PAGEIN;
- spin_unlock(&info->lock);
- }
}
if (newsize != oldsize) {
i_size_write(inode, newsize);
end_writeback(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;
- }
- return -1;
-}
-
static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, struct page *page)
{
- struct address_space *mapping;
+ struct address_space *mapping = info->vfs_inode.i_mapping;
unsigned long idx;
- unsigned long size;
- unsigned long limit;
- unsigned long stage;
- struct page **dir;
- struct page *subdir;
- swp_entry_t *ptr;
- int offset;
int error;
- idx = 0;
- ptr = info->i_direct;
- spin_lock(&info->lock);
- if (!info->swapped) {
- list_del_init(&info->swaplist);
- goto lost2;
- }
- 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);
- if (cond_resched_lock(&info->lock)) {
- /* check it has not been truncated */
- if (limit > info->next_index) {
- limit = info->next_index;
- if (idx >= limit)
- goto lost2;
- }
- }
- 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);
- shmem_swp_unmap(ptr);
- if (offset >= 0) {
- shmem_dir_unmap(dir);
- ptr = shmem_swp_map(subdir);
- goto found;
- }
- }
- }
-lost1:
- shmem_dir_unmap(dir-1);
-lost2:
- spin_unlock(&info->lock);
+ for (idx = 0; idx < SHMEM_NR_DIRECT; idx++)
+ if (shmem_get_swap(info, idx).val == entry.val)
+ goto found;
return 0;
found:
- idx += offset;
- ptr += offset;
+ spin_lock(&info->lock);
+ if (shmem_get_swap(info, idx).val != entry.val) {
+ spin_unlock(&info->lock);
+ return 0;
+ }
/*
* 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. We
- * could avoid doing it if inode NULL; or use this minor optimization.
+ * would appear empty, if it were the only one on shmem_swaplist.
*/
if (shmem_swaplist.next != &info->swaplist)
list_move_tail(&shmem_swaplist, &info->swaplist);
* 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).
*/
- mapping = info->vfs_inode.i_mapping;
error = add_to_page_cache_locked(page, mapping, idx, GFP_NOWAIT);
/* which does mem_cgroup_uncharge_cache_page on error */
- if (error == -EEXIST) {
- struct page *filepage = find_get_page(mapping, idx);
- error = 1;
- if (filepage) {
- /*
- * There might be a more uptodate page coming down
- * from a stacked writepage: forget our swappage if so.
- */
- if (PageUptodate(filepage))
- error = 0;
- page_cache_release(filepage);
- }
- }
- if (!error) {
+ if (error != -ENOMEM) {
delete_from_swap_cache(page);
set_page_dirty(page);
- info->flags |= SHMEM_PAGEIN;
- shmem_swp_set(info, ptr, 0);
+ shmem_put_swap(info, idx, (swp_entry_t){0});
+ info->swapped--;
swap_free(entry);
error = 1; /* not an error, but entry was found */
}
- shmem_swp_unmap(ptr);
spin_unlock(&info->lock);
return error;
}
mutex_lock(&shmem_swaplist_mutex);
list_for_each_safe(p, next, &shmem_swaplist) {
info = list_entry(p, struct shmem_inode_info, swaplist);
- found = shmem_unuse_inode(info, entry, page);
+ 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, entry, page);
cond_resched();
if (found)
break;
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;
struct inode *inode;
/*
* shmem_backing_dev_info's capabilities prevent regular writeback or
* sync from ever calling shmem_writepage; but a stacking filesystem
- * may use the ->writepage of its underlying filesystem, in which case
+ * 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. However, in those cases,
- * we do still want to check if there's a redundant swappage to be
- * discarded.
+ * and not for the writeback threads or sync.
*/
- if (wbc->for_reclaim)
- swap = get_swap_page();
- else
- swap.val = 0;
+ if (!wbc->for_reclaim) {
+ WARN_ON_ONCE(1); /* Still happens? Tell us about it! */
+ goto redirty;
+ }
+
+ /*
+ * Just for this patch, we have a toy implementation,
+ * which can swap out only the first SHMEM_NR_DIRECT pages:
+ * for simple demonstration of where we need to think about swap.
+ */
+ if (index >= SHMEM_NR_DIRECT)
+ goto redirty;
+
+ swap = get_swap_page();
+ if (!swap.val)
+ goto redirty;
/*
* Add inode to shmem_unuse()'s list of swapped-out inodes,
* we've taken the spinlock, because shmem_unuse_inode() will
* prune a !swapped inode from the swaplist under both locks.
*/
- if (swap.val) {
- mutex_lock(&shmem_swaplist_mutex);
- if (list_empty(&info->swaplist))
- list_add_tail(&info->swaplist, &shmem_swaplist);
- }
+ mutex_lock(&shmem_swaplist_mutex);
+ if (list_empty(&info->swaplist))
+ list_add_tail(&info->swaplist, &shmem_swaplist);
spin_lock(&info->lock);
- if (swap.val)
- mutex_unlock(&shmem_swaplist_mutex);
+ mutex_unlock(&shmem_swaplist_mutex);
- if (index >= info->next_index) {
- BUG_ON(!(info->flags & SHMEM_TRUNCATE));
- goto unlock;
- }
- entry = shmem_swp_entry(info, index, NULL);
- if (entry->val) {
- /*
- * The more uptodate page coming down from a stacked
- * writepage should replace our old swappage.
- */
- free_swap_and_cache(*entry);
- shmem_swp_set(info, entry, 0);
+ 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--;
}
shmem_recalc_inode(inode);
- if (swap.val && add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) {
+ if (add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) {
delete_from_page_cache(page);
- shmem_swp_set(info, entry, swap.val);
- shmem_swp_unmap(entry);
+ shmem_put_swap(info, index, swap);
+ info->swapped++;
swap_shmem_alloc(swap);
spin_unlock(&info->lock);
BUG_ON(page_mapped(page));
return 0;
}
- shmem_swp_unmap(entry);
-unlock:
spin_unlock(&info->lock);
- /*
- * add_to_swap_cache() doesn't return -EEXIST, so we can safely
- * clear SWAP_HAS_CACHE flag.
- */
swapcache_free(swap, NULL);
redirty:
set_page_dirty(page);
#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 idx,
+ 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;
+ struct page *page;
struct page *prealloc_page = NULL;
- swp_entry_t *entry;
swp_entry_t swap;
- gfp_t gfp;
int error;
- if (idx >= SHMEM_MAX_INDEX)
+ if (idx > (MAX_LFS_FILESIZE >> PAGE_CACHE_SHIFT))
return -EFBIG;
-
- if (type)
- *type = 0;
-
- /*
- * 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_readpage (required for splice) 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))
- goto done;
- gfp = mapping_gfp_mask(mapping);
- if (!filepage) {
+ page = find_lock_page(mapping, idx);
+ if (page) {
/*
- * Try to preload while we can wait, to not make a habit of
- * draining atomic reserves; but don't latch on to this cpu.
+ * 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.
*/
- error = radix_tree_preload(gfp & ~__GFP_HIGHMEM);
- if (error)
- goto failed;
- radix_tree_preload_end();
- if (sgp != SGP_READ && !prealloc_page) {
- /* We don't care if this fails */
- prealloc_page = shmem_alloc_page(gfp, info, idx);
- if (prealloc_page) {
- if (mem_cgroup_cache_charge(prealloc_page,
- current->mm, GFP_KERNEL)) {
- page_cache_release(prealloc_page);
- prealloc_page = NULL;
- }
+ BUG_ON(!PageUptodate(page));
+ goto done;
+ }
+
+ /*
+ * 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, idx);
+ 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;
}
}
}
- error = 0;
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;
- }
- swap = *entry;
-
+ swap = shmem_get_swap(info, idx);
if (swap.val) {
/* Look it up and read it in.. */
- swappage = lookup_swap_cache(swap);
- if (!swappage) {
- shmem_swp_unmap(entry);
+ page = lookup_swap_cache(swap);
+ if (!page) {
spin_unlock(&info->lock);
/* here we actually do the io */
- if (type)
- *type |= VM_FAULT_MAJOR;
- swappage = shmem_swapin(swap, gfp, info, 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);
+ if (fault_type)
+ *fault_type |= VM_FAULT_MAJOR;
+ page = shmem_swapin(swap, gfp, info, idx);
+ if (!page) {
+ swp_entry_t nswap = shmem_get_swap(info, idx);
+ 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 (!trylock_page(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 = add_to_page_cache_locked(swappage, mapping,
- idx, GFP_NOWAIT))) {
- info->flags |= SHMEM_PAGEIN;
- shmem_swp_set(info, entry, 0);
- shmem_swp_unmap(entry);
- delete_from_swap_cache(swappage);
- spin_unlock(&info->lock);
- filepage = swappage;
- set_page_dirty(filepage);
- swap_free(swap);
- } else {
- shmem_swp_unmap(entry);
+ error = add_to_page_cache_locked(page, mapping,
+ idx, GFP_NOWAIT);
+ if (error) {
spin_unlock(&info->lock);
if (error == -ENOMEM) {
/*
* call memcg's OOM if needed.
*/
error = mem_cgroup_shmem_charge_fallback(
- swappage,
- current->mm,
- gfp);
+ page, current->mm, gfp);
if (error) {
- unlock_page(swappage);
- page_cache_release(swappage);
- goto failed;
+ unlock_page(page);
+ page_cache_release(page);
+ goto out;
}
}
- unlock_page(swappage);
- page_cache_release(swappage);
+ 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) || !trylock_page(filepage))) {
+
+ delete_from_swap_cache(page);
+ shmem_put_swap(info, idx, (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, idx);
+ 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) {
if (percpu_counter_compare(&sbinfo->used_blocks,
shmem_acct_block(info->flags))
goto nospace;
percpu_counter_inc(&sbinfo->used_blocks);
- spin_lock(&inode->i_lock);
inode->i_blocks += BLOCKS_PER_PAGE;
- spin_unlock(&inode->i_lock);
} else if (shmem_acct_block(info->flags))
goto nospace;
- if (!filepage) {
- int ret;
-
- if (!prealloc_page) {
- spin_unlock(&info->lock);
- filepage = shmem_alloc_page(gfp, info, idx);
- if (!filepage) {
- shmem_unacct_blocks(info->flags, 1);
- shmem_free_blocks(inode, 1);
- error = -ENOMEM;
- goto failed;
- }
- SetPageSwapBacked(filepage);
+ page = prealloc_page;
+ prealloc_page = NULL;
- /*
- * Precharge page while we can wait, compensate
- * after
- */
- error = mem_cgroup_cache_charge(filepage,
- current->mm, GFP_KERNEL);
- if (error) {
- page_cache_release(filepage);
- shmem_unacct_blocks(info->flags, 1);
- shmem_free_blocks(inode, 1);
- filepage = NULL;
- goto failed;
- }
-
- spin_lock(&info->lock);
- } else {
- filepage = prealloc_page;
- prealloc_page = NULL;
- SetPageSwapBacked(filepage);
- }
-
- entry = shmem_swp_alloc(info, idx, sgp);
- if (IS_ERR(entry))
- error = PTR_ERR(entry);
- else {
- swap = *entry;
- shmem_swp_unmap(entry);
- }
- ret = error || swap.val;
- if (ret)
- mem_cgroup_uncharge_cache_page(filepage);
- else
- ret = add_to_page_cache_lru(filepage, mapping,
+ swap = shmem_get_swap(info, idx);
+ if (swap.val)
+ mem_cgroup_uncharge_cache_page(page);
+ else
+ error = add_to_page_cache_lru(page, mapping,
idx, GFP_NOWAIT);
- /*
- * At add_to_page_cache_lru() failure, uncharge will
- * be done automatically.
- */
- if (ret) {
- 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;
+ /*
+ * 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);
+ page_cache_release(page);
+ goto repeat;
}
info->alloced++;
spin_unlock(&info->lock);
- clear_highpage(filepage);
- flush_dcache_page(filepage);
- SetPageUptodate(filepage);
+ clear_highpage(page);
+ flush_dcache_page(page);
+ SetPageUptodate(page);
if (sgp == SGP_DIRTY)
- set_page_dirty(filepage);
+ set_page_dirty(page);
+
+ } else {
+ spin_unlock(&info->lock);
+ error = -ENOMEM;
+ goto out;
}
done:
- *pagep = filepage;
+ *pagep = page;
error = 0;
- goto out;
+out:
+ if (prealloc_page) {
+ mem_cgroup_uncharge_cache_page(prealloc_page);
+ page_cache_release(prealloc_page);
+ }
+ return error;
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. (When filepage has been passed in to shmem_getpage, it
- * is already in page cache, which prevents this race from occurring.)
+ * full tmpfs.
*/
- if (!filepage) {
- struct page *page = find_get_page(mapping, idx);
- if (page) {
- spin_unlock(&info->lock);
- page_cache_release(page);
- goto repeat;
- }
- }
+ page = find_get_page(mapping, idx);
spin_unlock(&info->lock);
- error = -ENOSPC;
-failed:
- if (*pagep != filepage) {
- unlock_page(filepage);
- page_cache_release(filepage);
- }
-out:
- if (prealloc_page) {
- mem_cgroup_uncharge_cache_page(prealloc_page);
- page_cache_release(prealloc_page);
+ if (page) {
+ page_cache_release(page);
+ goto repeat;
}
- return error;
+ error = -ENOSPC;
+ goto out;
}
static int shmem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
{
struct inode *inode = vma->vm_file->f_path.dentry->d_inode;
int error;
- int ret;
+ int ret = VM_FAULT_LOCKED;
if (((loff_t)vmf->pgoff << PAGE_CACHE_SHIFT) >= i_size_read(inode))
return VM_FAULT_SIGBUS;
error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret);
if (error)
return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);
+
if (ret & VM_FAULT_MAJOR) {
count_vm_event(PGMAJFAULT);
mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
}
- return ret | VM_FAULT_LOCKED;
+ return ret;
}
#ifdef CONFIG_NUMA
static const struct inode_operations shmem_symlink_inode_operations;
static const struct inode_operations shmem_symlink_inline_operations;
-/*
- * Normally tmpfs avoids the use of shmem_readpage and shmem_write_begin;
- * but providing them allows a tmpfs file to be used for splice, sendfile, and
- * below the loop driver, in the generic fashion that many filesystems support.
- */
-static int shmem_readpage(struct file *file, struct page *page)
-{
- struct inode *inode = page->mapping->host;
- int error = shmem_getpage(inode, page->index, &page, SGP_CACHE, NULL);
- unlock_page(page);
- return error;
-}
-
static int
shmem_write_begin(struct file *file, struct address_space *mapping,
loff_t pos, unsigned len, unsigned flags,
{
struct inode *inode = mapping->host;
pgoff_t index = pos >> PAGE_CACHE_SHIFT;
- *pagep = NULL;
return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL);
}
return retval;
}
+static ssize_t shmem_file_splice_read(struct file *in, loff_t *ppos,
+ struct pipe_inode_info *pipe, size_t len,
+ unsigned int flags)
+{
+ struct address_space *mapping = in->f_mapping;
+ struct inode *inode = mapping->host;
+ unsigned int loff, nr_pages, req_pages;
+ struct page *pages[PIPE_DEF_BUFFERS];
+ struct partial_page partial[PIPE_DEF_BUFFERS];
+ struct page *page;
+ pgoff_t index, end_index;
+ loff_t isize, left;
+ int error, page_nr;
+ struct splice_pipe_desc spd = {
+ .pages = pages,
+ .partial = partial,
+ .flags = flags,
+ .ops = &page_cache_pipe_buf_ops,
+ .spd_release = spd_release_page,
+ };
+
+ isize = i_size_read(inode);
+ if (unlikely(*ppos >= isize))
+ return 0;
+
+ left = isize - *ppos;
+ if (unlikely(left < len))
+ len = left;
+
+ if (splice_grow_spd(pipe, &spd))
+ return -ENOMEM;
+
+ index = *ppos >> PAGE_CACHE_SHIFT;
+ loff = *ppos & ~PAGE_CACHE_MASK;
+ req_pages = (len + loff + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+ nr_pages = min(req_pages, 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++]);
+
+ 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)
{
struct shmem_sb_info *sbinfo = SHMEM_SB(dentry->d_sb);
int error;
int len;
struct inode *inode;
- struct page *page = NULL;
+ struct page *page;
char *kaddr;
struct shmem_inode_info *info;
goto failed;
sbinfo->free_inodes = sbinfo->max_inodes;
- 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;
.writepage = shmem_writepage,
.set_page_dirty = __set_page_dirty_no_writeback,
#ifdef CONFIG_TMPFS
- .readpage = shmem_readpage,
.write_begin = shmem_write_begin,
.write_end = shmem_write_end,
#endif
.aio_read = shmem_file_aio_read,
.aio_write = generic_file_aio_write,
.fsync = noop_fsync,
- .splice_read = generic_file_splice_read,
+ .splice_read = shmem_file_splice_read,
.splice_write = generic_file_splice_write,
#endif
};
.listxattr = shmem_listxattr,
.removexattr = shmem_removexattr,
#endif
-#ifdef CONFIG_TMPFS_POSIX_ACL
- .check_acl = generic_check_acl,
-#endif
-
};
static const struct inode_operations shmem_dir_inode_operations = {
#endif
#ifdef CONFIG_TMPFS_POSIX_ACL
.setattr = shmem_setattr,
- .check_acl = generic_check_acl,
#endif
};
#endif
#ifdef CONFIG_TMPFS_POSIX_ACL
.setattr = shmem_setattr,
- .check_acl = generic_check_acl,
#endif
};
void mem_cgroup_get_shmem_target(struct inode *inode, pgoff_t pgoff,
struct page **pagep, swp_entry_t *ent)
{
- swp_entry_t entry = { .val = 0 }, *ptr;
+ swp_entry_t entry = { .val = 0 };
struct page *page = NULL;
struct shmem_inode_info *info = SHMEM_I(inode);
goto out;
spin_lock(&info->lock);
- ptr = shmem_swp_entry(info, pgoff, NULL);
#ifdef CONFIG_SWAP
- if (ptr && ptr->val) {
- entry.val = ptr->val;
+ entry = shmem_get_swap(info, pgoff);
+ if (entry.val)
page = find_get_page(&swapper_space, entry.val);
- } else
+ else
#endif
page = find_get_page(inode->i_mapping, pgoff);
- if (ptr)
- shmem_swp_unmap(ptr);
spin_unlock(&info->lock);
out:
*pagep = page;
#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)
-#define SHMEM_MAX_BYTES MAX_LFS_FILESIZE
#endif /* CONFIG_SHMEM */
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))
* 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.
*
- * Provide a stub for those callers to start using now, then later
- * flesh it out to call shmem_getpage() with additional gfp mask, when
- * shmem_file_splice_read() is added and shmem_readpage() is removed.
+ * 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);