#include <linux/init.h>
#include <linux/fs.h>
#include <linux/xattr.h>
+#include <linux/exportfs.h>
#include <linux/generic_acl.h>
#include <linux/mm.h>
#include <linux/mman.h>
#include <linux/ctype.h>
#include <linux/migrate.h>
#include <linux/highmem.h>
+#include <linux/seq_file.h>
#include <asm/uaccess.h>
#include <asm/div64.h>
/* Flag allocation requirements to shmem_getpage and shmem_swp_alloc */
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 */
};
+#ifdef CONFIG_TMPFS
+static unsigned long shmem_default_max_blocks(void)
+{
+ return totalram_pages / 2;
+}
+
+static unsigned long shmem_default_max_inodes(void)
+{
+ return min(totalram_pages - totalhigh_pages, totalram_pages / 2);
+}
+#endif
+
static int shmem_getpage(struct inode *inode, unsigned long idx,
struct page **pagep, enum sgp_type sgp, int *type);
* 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, PAGE_CACHE_SHIFT-PAGE_SHIFT);
+ return alloc_pages((gfp_mask & ~GFP_MOVABLE_MASK) | __GFP_ZERO,
+ PAGE_CACHE_SHIFT-PAGE_SHIFT);
}
static inline void shmem_dir_free(struct page *page)
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 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 struct vm_operations_struct shmem_vm_ops;
static struct backing_dev_info shmem_backing_dev_info __read_mostly = {
};
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)
{
}
}
-/*
+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;
+}
+
+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 size 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
}
}
-/*
+/**
* 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?
+ *
+ * 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)
{
}
spin_unlock(&info->lock);
- page = shmem_dir_alloc(mapping_gfp_mask(inode->i_mapping) | __GFP_ZERO);
+ page = shmem_dir_alloc(mapping_gfp_mask(inode->i_mapping));
if (page)
set_page_private(page, 0);
spin_lock(&info->lock);
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
+ * @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)
+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)
+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;
int size = limit - offset;
if (size > LATENCY_LIMIT)
size = LATENCY_LIMIT;
- freed += shmem_free_swp(ptr+offset, ptr+offset+size);
+ freed += shmem_free_swp(ptr+offset, ptr+offset+size,
+ punch_lock);
if (need_resched()) {
shmem_swp_unmap(ptr);
if (*dir) {
long nr_swaps_freed = 0;
int offset;
int freed;
- int punch_hole = 0;
+ int punch_hole;
+ spinlock_t *needs_lock;
+ spinlock_t *punch_lock;
+ unsigned long upper_limit;
inode->i_ctime = inode->i_mtime = CURRENT_TIME;
idx = (start + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
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 {
- limit = (end + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
- if (limit > info->next_index)
- limit = info->next_index;
+ 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;
}
size = limit;
if (size > SHMEM_NR_DIRECT)
size = SHMEM_NR_DIRECT;
- nr_swaps_freed = shmem_free_swp(ptr+idx, ptr+size);
+ nr_swaps_freed = shmem_free_swp(ptr+idx, ptr+size, needs_lock);
}
- if (!topdir)
+
+ /*
+ * 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;
- BUG_ON(limit <= SHMEM_NR_DIRECT);
+ /*
+ * 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;
if (*dir) {
diroff = ((idx - ENTRIES_PER_PAGEPAGE/2) %
ENTRIES_PER_PAGEPAGE) / ENTRIES_PER_PAGE;
- if (!diroff && !offset) {
- *dir = NULL;
+ 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);
}
}
stage = idx + ENTRIES_PER_PAGEPAGE;
middir = *dir;
- *dir = NULL;
- nr_pages_to_free++;
- list_add(&middir->lru, &pages_to_free);
+ 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 && page_private(subdir)) {
+ 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);
+ offset, size, &dir, punch_lock);
if (!dir)
dir = shmem_dir_map(middir);
nr_swaps_freed += freed;
- if (offset)
+ if (offset || punch_lock) {
spin_lock(&info->lock);
- set_page_private(subdir, page_private(subdir) - freed);
- if (offset)
+ set_page_private(subdir,
+ page_private(subdir) - freed);
spin_unlock(&info->lock);
- if (!punch_hole)
- BUG_ON(page_private(subdir) > offset);
- }
- if (offset)
- offset = 0;
- else if (subdir && !page_private(subdir)) {
- dir[diroff] = NULL;
- nr_pages_to_free++;
- list_add(&subdir->lru, &pages_to_free);
+ } else
+ BUG_ON(page_private(subdir) != freed);
}
+ offset = 0;
}
done1:
shmem_dir_unmap(dir);
* 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.
+ *
+ * Recalling truncate_inode_pages_range and unmap_mapping_range
+ * every time for punch_hole (which never got a chance to clear
+ * SHMEM_PAGEIN at the start of vmtruncate_range) is expensive,
+ * yet hardly ever necessary: try to optimize them out later.
*/
truncate_inode_pages_range(inode->i_mapping, start, end);
+ if (punch_hole)
+ unmap_mapping_range(inode->i_mapping, start,
+ end - start, 1);
}
spin_lock(&info->lock);
(void) shmem_getpage(inode,
attr->ia_size>>PAGE_CACHE_SHIFT,
&page, SGP_READ, NULL);
+ if (page)
+ unlock_page(page);
}
/*
* Reset SHMEM_PAGEIN flag so that shmem_truncate can
static void shmem_delete_inode(struct inode *inode)
{
- struct shmem_sb_info *sbinfo = SHMEM_SB(inode->i_sb);
struct shmem_inode_info *info = SHMEM_I(inode);
if (inode->i_op->truncate == shmem_truncate) {
inode->i_size = 0;
shmem_truncate(inode);
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);
- }
+ shmem_free_inode(inode->i_sb);
clear_inode(inode);
}
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();
+ if (offset >= 0)
goto found;
- }
if (!info->i_indirect)
goto lost2;
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) {
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);
goto found;
}
- shmem_swp_unmap(ptr);
}
}
lost1:
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);
- }
- shmem_swp_unmap(ptr);
+ inode = igrab(&info->vfs_inode);
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_delete_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.
*/
- swap_free(entry);
- return 1;
+ if (shmem_swaplist.next != &info->swaplist)
+ list_move_tail(&shmem_swaplist, &info->swaplist);
+ mutex_unlock(&shmem_swaplist_mutex);
+
+ error = 1;
+ if (!inode)
+ goto out;
+ /* Precharge page while we can wait, compensate afterwards */
+ error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL);
+ if (error)
+ goto out;
+ error = radix_tree_preload(GFP_KERNEL);
+ if (error)
+ goto uncharge;
+ error = 1;
+
+ spin_lock(&info->lock);
+ ptr = shmem_swp_entry(info, idx, NULL);
+ if (ptr && ptr->val == entry.val)
+ error = add_to_page_cache(page, inode->i_mapping,
+ idx, GFP_NOWAIT);
+ if (error == -EEXIST) {
+ struct page *filepage = find_get_page(inode->i_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) {
+ delete_from_swap_cache(page);
+ set_page_dirty(page);
+ info->flags |= SHMEM_PAGEIN;
+ shmem_swp_set(info, ptr, 0);
+ swap_free(entry);
+ error = 1; /* not an error, but entry was found */
+ }
+ if (ptr)
+ shmem_swp_unmap(ptr);
+ spin_unlock(&info->lock);
+ radix_tree_preload_end();
+uncharge:
+ mem_cgroup_uncharge_page(page);
+out:
+ unlock_page(page);
+ page_cache_release(page);
+ iput(inode); /* allows for NULL */
+ return error;
}
/*
struct shmem_inode_info *info;
int found = 0;
- spin_lock(&shmem_swaplist_lock);
+ mutex_lock(&shmem_swaplist_mutex);
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;
- }
+ found = shmem_unuse_inode(info, entry, page);
+ cond_resched();
+ if (found)
+ goto out;
}
- spin_unlock(&shmem_swaplist_lock);
- return found;
+ mutex_unlock(&shmem_swaplist_mutex);
+out: return found; /* 0 or 1 or -ENOMEM */
}
/*
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;
- swap = get_swap_page();
- if (!swap.val)
+ 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
+ * may use the ->writepage of its underlying filesystem, in which case
+ * tmpfs should write out to swap only in response to memory pressure,
+ * and not for pdflush or sync. However, in those cases, we do still
+ * want to check if there's a redundant swappage to be discarded.
+ */
+ if (wbc->for_reclaim)
+ swap = get_swap_page();
+ else
+ swap.val = 0;
+
spin_lock(&info->lock);
- shmem_recalc_inode(inode);
if (index >= info->next_index) {
BUG_ON(!(info->flags & SHMEM_TRUNCATE));
goto unlock;
}
entry = shmem_swp_entry(info, index, NULL);
- BUG_ON(!entry);
- BUG_ON(entry->val);
+ 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);
+ }
+ shmem_recalc_inode(inode);
- if (move_to_swap_cache(page, swap) == 0) {
+ if (swap.val && add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) {
+ remove_from_page_cache(page);
shmem_swp_set(info, entry, swap.val);
shmem_swp_unmap(entry);
+ if (list_empty(&info->swaplist))
+ inode = igrab(inode);
+ else
+ inode = NULL;
spin_unlock(&info->lock);
- if (list_empty(&info->swaplist)) {
- spin_lock(&shmem_swaplist_lock);
+ swap_duplicate(swap);
+ BUG_ON(page_mapped(page));
+ page_cache_release(page); /* pagecache ref */
+ set_page_dirty(page);
+ unlock_page(page);
+ if (inode) {
+ mutex_lock(&shmem_swaplist_mutex);
/* move instead of add in case we're racing */
list_move_tail(&info->swaplist, &shmem_swaplist);
- spin_unlock(&shmem_swaplist_lock);
+ mutex_unlock(&shmem_swaplist_mutex);
+ iput(inode);
}
- unlock_page(page);
return 0;
}
swap_free(swap);
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 int shmem_parse_mpol(char *value, unsigned short *policy,
+ unsigned short *mode_flags, nodemask_t *policy_nodes)
{
char *nodelist = strchr(value, ':');
+ char *flags = strchr(value, '=');
int err = 1;
if (nodelist) {
*nodelist++ = '\0';
if (nodelist_parse(nodelist, *policy_nodes))
goto out;
+ if (!nodes_subset(*policy_nodes, node_states[N_HIGH_MEMORY]))
+ goto out;
}
+ if (flags)
+ *flags++ = '\0';
if (!strcmp(value, "default")) {
*policy = MPOL_DEFAULT;
/* Don't allow a nodelist */
err = 0;
} else if (!strcmp(value, "interleave")) {
*policy = MPOL_INTERLEAVE;
- /* Default to nodes online if no nodelist */
+ /*
+ * Default to online nodes with memory if no nodelist
+ */
if (!nodelist)
- *policy_nodes = node_online_map;
+ *policy_nodes = node_states[N_HIGH_MEMORY];
err = 0;
}
+
+ *mode_flags = 0;
+ if (flags) {
+ /*
+ * Currently, we only support two mutually exclusive
+ * mode flags.
+ */
+ if (!strcmp(flags, "static"))
+ *mode_flags |= MPOL_F_STATIC_NODES;
+ else if (!strcmp(flags, "relative"))
+ *mode_flags |= MPOL_F_RELATIVE_NODES;
+ else
+ err = 1; /* unrecognized flag */
+ }
out:
/* Restore string for error message */
if (nodelist)
*--nodelist = ':';
+ if (flags)
+ *--flags = '=';
return err;
}
-static struct page *shmem_swapin_async(struct shared_policy *p,
- swp_entry_t entry, unsigned long idx)
+static void shmem_show_mpol(struct seq_file *seq, unsigned short policy,
+ unsigned short flags, const nodemask_t policy_nodes)
{
- struct page *page;
- struct vm_area_struct pvma;
+ char *policy_string;
- /* 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;
+ switch (policy) {
+ case MPOL_PREFERRED:
+ policy_string = "prefer";
+ break;
+ case MPOL_BIND:
+ policy_string = "bind";
+ break;
+ case MPOL_INTERLEAVE:
+ policy_string = "interleave";
+ break;
+ default:
+ /* MPOL_DEFAULT */
+ return;
+ }
+
+ seq_printf(seq, ",mpol=%s", policy_string);
+
+ if (policy != MPOL_INTERLEAVE ||
+ !nodes_equal(policy_nodes, node_states[N_HIGH_MEMORY])) {
+ char buffer[64];
+ int len;
+
+ len = nodelist_scnprintf(buffer, sizeof(buffer), policy_nodes);
+ if (len < sizeof(buffer))
+ seq_printf(seq, ":%s", buffer);
+ else
+ seq_printf(seq, ":?");
+ }
}
+#endif /* CONFIG_TMPFS */
-struct page *shmem_swapin(struct shmem_inode_info *info, swp_entry_t entry,
- unsigned long idx)
+static struct page *shmem_swapin(swp_entry_t entry, gfp_t gfp,
+ struct shmem_inode_info *info, unsigned long idx)
{
- struct shared_policy *p = &info->policy;
- int i, num;
+ struct vm_area_struct pvma;
struct page *page;
- unsigned long offset;
- 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 = idx;
+ pvma.vm_ops = NULL;
+ pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx);
+ page = swapin_readahead(entry, gfp, &pvma, 0);
+ mpol_put(pvma.vm_policy);
+ return page;
}
-static struct page *
-shmem_alloc_page(gfp_t gfp, struct shmem_inode_info *info,
- unsigned long idx)
+static struct page *shmem_alloc_page(gfp_t gfp,
+ struct shmem_inode_info *info, unsigned long idx)
{
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);
+ /* Create a pseudo vma that just contains the policy */
+ pvma.vm_start = 0;
pvma.vm_pgoff = idx;
- pvma.vm_end = PAGE_SIZE;
- page = alloc_page_vma(gfp | __GFP_ZERO, &pvma, 0);
- mpol_free(pvma.vm_policy);
+ pvma.vm_ops = NULL;
+ pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, idx);
+ page = alloc_page_vma(gfp, &pvma, 0);
+ mpol_put(pvma.vm_policy);
return page;
}
-#else
-static inline int shmem_parse_mpol(char *value, int *policy, nodemask_t *policy_nodes)
+#else /* !CONFIG_NUMA */
+#ifdef CONFIG_TMPFS
+static inline int shmem_parse_mpol(char *value, unsigned short *policy,
+ unsigned short *mode_flags, nodemask_t *policy_nodes)
{
return 1;
}
-static inline struct page *
-shmem_swapin(struct shmem_inode_info *info,swp_entry_t entry,unsigned long idx)
+static inline void shmem_show_mpol(struct seq_file *seq, unsigned short policy,
+ unsigned short flags, const nodemask_t policy_nodes)
{
- swapin_readahead(entry, 0, NULL);
- return read_swap_cache_async(entry, NULL, 0);
}
+#endif /* CONFIG_TMPFS */
-static inline struct page *
-shmem_alloc_page(gfp_t gfp,struct shmem_inode_info *info, unsigned long idx)
+static inline struct page *shmem_swapin(swp_entry_t entry, gfp_t gfp,
+ struct shmem_inode_info *info, unsigned long idx)
{
- return alloc_page(gfp | __GFP_ZERO);
+ return swapin_readahead(entry, gfp, NULL, 0);
}
-#endif
+
+static inline struct page *shmem_alloc_page(gfp_t gfp,
+ struct shmem_inode_info *info, unsigned long idx)
+{
+ return alloc_page(gfp);
+}
+#endif /* CONFIG_NUMA */
/*
* shmem_getpage - either get the page from swap or allocate a new one
struct page *swappage;
swp_entry_t *entry;
swp_entry_t swap;
+ gfp_t gfp;
int error;
if (idx >= SHMEM_MAX_INDEX)
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_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.
+ * 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)
if (filepage && PageUptodate(filepage))
goto done;
error = 0;
- if (sgp == SGP_QUICK)
- goto failed;
+ gfp = mapping_gfp_mask(mapping);
+ if (!filepage) {
+ /*
+ * 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_HIGHMEM);
+ if (error)
+ goto failed;
+ radix_tree_preload_end();
+ }
spin_lock(&info->lock);
shmem_recalc_inode(inode);
if (!swappage) {
shmem_swp_unmap(entry);
/* here we actually do the io */
- if (type && *type == VM_FAULT_MINOR) {
+ if (type && !(*type & VM_FAULT_MAJOR)) {
__count_vm_event(PGMAJFAULT);
- *type = VM_FAULT_MAJOR;
+ *type |= VM_FAULT_MAJOR;
}
spin_unlock(&info->lock);
- swappage = shmem_swapin(info, swap, idx);
+ swappage = shmem_swapin(swap, gfp, info, idx);
if (!swappage) {
spin_lock(&info->lock);
entry = shmem_swp_alloc(info, idx, sgp);
SetPageUptodate(filepage);
set_page_dirty(filepage);
swap_free(swap);
- } else if (!(error = move_from_swap_cache(
- swappage, idx, mapping))) {
+ } else if (!(error = add_to_page_cache(
+ 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);
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);
+ /* allow reclaim from this memory cgroup */
+ error = mem_cgroup_cache_charge(swappage,
+ current->mm, gfp & ~__GFP_HIGHMEM);
+ if (error) {
+ page_cache_release(swappage);
+ goto failed;
+ }
+ mem_cgroup_uncharge_page(swappage);
}
+ page_cache_release(swappage);
goto repeat;
}
} else if (sgp == SGP_READ && !filepage) {
if (!filepage) {
spin_unlock(&info->lock);
- filepage = shmem_alloc_page(mapping_gfp_mask(mapping),
- info,
- idx);
+ filepage = shmem_alloc_page(gfp, info, idx);
if (!filepage) {
shmem_unacct_blocks(info->flags, 1);
shmem_free_blocks(inode, 1);
goto failed;
}
+ /* Precharge page while we can wait, compensate after */
+ error = mem_cgroup_cache_charge(filepage, current->mm,
+ gfp & ~__GFP_HIGHMEM);
+ 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);
entry = shmem_swp_alloc(info, idx, sgp);
if (IS_ERR(entry))
shmem_swp_unmap(entry);
}
if (error || swap.val || 0 != add_to_page_cache_lru(
- filepage, mapping, idx, GFP_ATOMIC)) {
+ filepage, mapping, idx, GFP_NOWAIT)) {
spin_unlock(&info->lock);
+ mem_cgroup_uncharge_page(filepage);
page_cache_release(filepage);
shmem_unacct_blocks(info->flags, 1);
shmem_free_blocks(inode, 1);
goto failed;
goto repeat;
}
+ mem_cgroup_uncharge_page(filepage);
info->flags |= SHMEM_PAGEIN;
}
info->alloced++;
spin_unlock(&info->lock);
+ clear_highpage(filepage);
flush_dcache_page(filepage);
SetPageUptodate(filepage);
+ if (sgp == SGP_DIRTY)
+ set_page_dirty(filepage);
}
done:
- if (*pagep != filepage) {
- unlock_page(filepage);
- *pagep = filepage;
- }
+ *pagep = filepage;
return 0;
failed:
return error;
}
-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;
- 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;
-}
-
-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;
+ return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);
- 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++;
- }
- return 0;
+ mark_page_accessed(vmf->page);
+ return ret | VM_FAULT_LOCKED;
}
#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 *new)
{
- struct inode *i = vma->vm_file->f_dentry->d_inode;
+ struct inode *i = vma->vm_file->f_path.dentry->d_inode;
return mpol_set_shared_policy(&SHMEM_I(i)->policy, vma, new);
}
-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;
+ struct inode *i = vma->vm_file->f_path.dentry->d_inode;
unsigned long idx;
idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff;
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;
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;
}
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);
- }
+ if (shmem_reserve_inode(sb))
+ return NULL;
inode = new_inode(sb);
if (inode) {
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);
inode->i_op = &shmem_inode_operations;
inode->i_fop = &shmem_file_operations;
mpol_shared_policy_init(&info->policy, sbinfo->policy,
- &sbinfo->policy_nodes);
+ sbinfo->flags, &sbinfo->policy_nodes);
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,
+ mpol_shared_policy_init(&info->policy, MPOL_DEFAULT, 0,
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.
+ * 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_prepare_write(struct file *file, struct page *page, unsigned offset, unsigned to)
+static int shmem_readpage(struct file *file, struct page *page)
{
struct inode *inode = page->mapping->host;
- return shmem_getpage(inode, page->index, &page, SGP_WRITE, NULL);
+ int error = shmem_getpage(inode, page->index, &page, SGP_CACHE, NULL);
+ unlock_page(page);
+ return error;
}
-static ssize_t
-shmem_file_write(struct file *file, const char __user *buf, size_t count, loff_t *ppos)
+static int
+shmem_write_begin(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned flags,
+ struct page **pagep, void **fsdata)
{
- struct inode *inode = 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.
- */
-
- 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);
+ struct inode *inode = mapping->host;
+ pgoff_t index = pos >> PAGE_CACHE_SHIFT;
+ *pagep = NULL;
+ return shmem_getpage(inode, index, pagep, SGP_WRITE, NULL);
+}
- if (left) {
- pos -= left;
- written -= left;
- err = -EFAULT;
- break;
- }
+static int
+shmem_write_end(struct file *file, struct address_space *mapping,
+ loff_t pos, unsigned len, unsigned copied,
+ struct page *page, void *fsdata)
+{
+ struct inode *inode = mapping->host;
- /*
- * 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);
+ unlock_page(page);
+ set_page_dirty(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;
+ 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;
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)
return desc.error;
}
-static ssize_t shmem_file_sendfile(struct file *in_file, loff_t *ppos,
- size_t count, read_actor_t actor, void *target)
-{
- read_descriptor_t desc;
-
- if (!count)
- return 0;
-
- desc.written = 0;
- desc.count = count;
- desc.arg.data = target;
- desc.error = 0;
-
- do_shmem_file_read(in_file, ppos, &desc, actor);
- if (desc.written)
- return desc.written;
- return desc.error;
-}
-
static int shmem_statfs(struct dentry *dentry, struct kstatfs *buf)
{
struct shmem_sb_info *sbinfo = SHMEM_SB(dentry->d_sb);
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++;
+ inc_nlink(inode);
atomic_inc(&inode->i_count); /* 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;
iput(inode);
return error;
}
+ unlock_page(page);
inode->i_op = &shmem_symlink_inode_operations;
kaddr = kmap_atomic(page, KM_USER0);
memcpy(kaddr, symname, len);
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));
+ if (page)
+ unlock_page(page);
return page;
}
}
}
-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,
};
-static struct inode_operations shmem_symlink_inode_operations = {
+static const struct inode_operations shmem_symlink_inode_operations = {
.truncate = shmem_truncate,
.readlink = generic_readlink,
.follow_link = shmem_follow_link,
};
#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
{
if (strcmp(name, "") == 0)
return -EINVAL;
- return security_inode_getsecurity(inode, name, buffer, size,
- -EOPNOTSUPP);
+ return xattr_getsecurity(inode, name, buffer, size);
}
static int shmem_xattr_security_set(struct inode *inode, const char *name,
return security_inode_setsecurity(inode, name, value, size, flags);
}
-struct xattr_handler shmem_xattr_security_handler = {
+static struct xattr_handler shmem_xattr_security_handler = {
.prefix = XATTR_SECURITY_PREFIX,
.list = shmem_xattr_security_list,
.get = shmem_xattr_security_get,
};
#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 struct dentry *shmem_get_parent(struct dentry *child)
+{
+ return ERR_PTR(-ESTALE);
+}
+
+static int shmem_match(struct inode *ino, void *vfh)
+{
+ __u32 *fh = vfh;
+ __u64 inum = fh[2];
+ inum = (inum << 32) | fh[1];
+ return ino->i_ino == inum && fh[0] == ino->i_generation;
+}
+
+static struct dentry *shmem_fh_to_dentry(struct super_block *sb,
+ struct fid *fid, int fh_len, int fh_type)
+{
+ struct inode *inode;
+ struct dentry *dentry = NULL;
+ u64 inum = 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;
+}
+
+static int shmem_encode_fh(struct dentry *dentry, __u32 *fh, int *len,
+ int connectable)
+{
+ struct inode *inode = dentry->d_inode;
+
+ if (*len < 3)
+ return 255;
+
+ if (hlist_unhashed(&inode->i_hash)) {
+ /* 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 (hlist_unhashed(&inode->i_hash))
+ __insert_inode_hash(inode,
+ inode->i_ino + inode->i_generation);
+ spin_unlock(&lock);
+ }
+
+ fh[0] = inode->i_generation;
+ fh[1] = inode->i_ino;
+ fh[2] = ((__u64)inode->i_ino) >> 32;
+
+ *len = 3;
+ return 1;
+}
+
+static const struct export_operations shmem_export_ops = {
+ .get_parent = shmem_get_parent,
+ .encode_fh = shmem_encode_fh,
+ .fh_to_dentry = shmem_fh_to_dentry,
+};
+
+static int shmem_parse_options(char *options, struct shmem_sb_info *sbinfo,
+ bool remount)
{
char *this_char, *value, *rest;
}
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 (shmem_parse_mpol(value, &sbinfo->policy,
+ &sbinfo->flags, &sbinfo->policy_nodes))
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;
+ struct shmem_sb_info config = *sbinfo;
unsigned long blocks;
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 (config.max_blocks < blocks)
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->free_blocks = config.max_blocks - blocks;
+ sbinfo->max_inodes = config.max_inodes;
+ sbinfo->free_inodes = config.max_inodes - inodes;
+ sbinfo->policy = config.policy;
+ sbinfo->flags = config.flags;
+ sbinfo->policy_nodes = config.policy_nodes;
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->policy, sbinfo->flags,
+ sbinfo->policy_nodes);
+ return 0;
+}
+#endif /* CONFIG_TMPFS */
static void shmem_put_super(struct super_block *sb)
{
{
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 = kmalloc(max((int)sizeof(struct shmem_sb_info),
+ L1_CACHE_BYTES), GFP_KERNEL);
+ if (!sbinfo)
+ return -ENOMEM;
+
+ sbinfo->max_blocks = 0;
+ sbinfo->max_inodes = 0;
+ sbinfo->mode = S_IRWXUGO | S_ISVTX;
+ sbinfo->uid = current->fsuid;
+ sbinfo->gid = current->fsgid;
+ sbinfo->policy = MPOL_DEFAULT;
+ sbinfo->flags = 0;
+ sbinfo->policy_nodes = node_states[N_HIGH_MEMORY];
+ 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;
+ sbinfo->free_blocks = sbinfo->max_blocks;
+ sbinfo->free_inodes = sbinfo->max_inodes;
- sb->s_fs_info = sbinfo;
sb->s_maxbytes = SHMEM_MAX_BYTES;
sb->s_blocksize = PAGE_CACHE_SIZE;
sb->s_blocksize_bits = PAGE_CACHE_SHIFT;
sb->s_flags |= MS_POSIXACL;
#endif
- inode = shmem_get_inode(sb, S_IFDIR | mode, 0);
+ inode = shmem_get_inode(sb, S_IFDIR | sbinfo->mode, 0);
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);
+ p = (struct shmem_inode_info *)kmem_cache_alloc(shmem_inode_cachep, GFP_KERNEL);
if (!p)
return NULL;
return &p->vfs_inode;
kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode));
}
-static void init_once(void *foo, struct kmem_cache *cachep,
- unsigned long flags)
+static void init_once(struct kmem_cache *cachep, 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);
+ inode_init_once(&p->vfs_inode);
#ifdef CONFIG_TMPFS_POSIX_ACL
- p->i_acl = NULL;
- p->i_default_acl = NULL;
+ p->i_acl = NULL;
+ p->i_default_acl = NULL;
#endif
- }
}
static int 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, init_once);
return 0;
}
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,
+ .readpage = shmem_readpage,
+ .write_begin = shmem_write_begin,
+ .write_end = shmem_write_end,
#endif
.migratepage = migrate_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,
+ .write = do_sync_write,
+ .aio_write = generic_file_aio_write,
.fsync = simple_sync_file,
- .sendfile = shmem_file_sendfile,
+ .splice_read = generic_file_splice_read,
+ .splice_write = generic_file_splice_write,
#endif
};
-static struct inode_operations shmem_inode_operations = {
+static const struct inode_operations shmem_inode_operations = {
.truncate = shmem_truncate,
.setattr = shmem_notify_change,
.truncate_range = shmem_truncate_range,
};
-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,
#endif
};
-static struct inode_operations shmem_special_inode_operations = {
+static const struct inode_operations shmem_special_inode_operations = {
#ifdef CONFIG_TMPFS_POSIX_ACL
.setattr = shmem_notify_change,
.setxattr = generic_setxattr,
#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,
.drop_inode = generic_delete_inode,
};
static struct vm_operations_struct shmem_vm_ops = {
- .nopage = shmem_nopage,
- .populate = shmem_populate,
+ .fault = shmem_fault,
#ifdef CONFIG_NUMA
.set_policy = shmem_set_policy,
.get_policy = shmem_get_policy,
{
int error;
+ error = bdi_init(&shmem_backing_dev_info);
+ if (error)
+ goto out4;
+
error = init_inodecache();
if (error)
goto out3;
out2:
destroy_inodecache();
out3:
+ bdi_destroy(&shmem_backing_dev_info);
+out4:
shm_mnt = ERR_PTR(error);
return error;
}
module_init(init_tmpfs)
-/*
+/**
* 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_flags
*/
struct file *shmem_file_setup(char *name, loff_t size, unsigned long flags)
{
d_instantiate(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;
+ init_file(file, shm_mnt, dentry, FMODE_WRITE | FMODE_READ,
+ &shmem_file_operations);
return file;
close_file:
return ERR_PTR(error);
}
-/*
+/**
* 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)
Code Review / linux-2.6.git / blobdiff