/* Symlink up to this size is kmalloc'ed instead of using a swappable page */
#define SHORT_SYMLINK_LEN 128
+/*
+ * vmtruncate_range() communicates with shmem_fault via
+ * inode->i_private (with i_mutex making sure that it has only one user at
+ * a time): we would prefer not to enlarge the shmem inode just for that.
+ */
+struct shmem_falloc {
+ pgoff_t start; /* start of range currently being fallocated */
+ pgoff_t next; /* the next page offset to be fallocated */
+};
+
struct shmem_xattr {
struct list_head list; /* anchored by shmem_inode_info->xattr_list */
char *name; /* xattr name */
/*
* Pagevec may contain swap entries, so shuffle up pages before releasing.
*/
-static void shmem_pagevec_release(struct pagevec *pvec)
+static void shmem_deswap_pagevec(struct pagevec *pvec)
{
int i, j;
pvec->pages[j++] = page;
}
pvec->nr = j;
- pagevec_release(pvec);
+}
+
+/*
+ * SysV IPC SHM_UNLOCK restore Unevictable pages to their evictable lists.
+ */
+void shmem_unlock_mapping(struct address_space *mapping)
+{
+ struct pagevec pvec;
+ pgoff_t indices[PAGEVEC_SIZE];
+ pgoff_t index = 0;
+
+ pagevec_init(&pvec, 0);
+ /*
+ * Minor point, but we might as well stop if someone else SHM_LOCKs it.
+ */
+ while (!mapping_unevictable(mapping)) {
+ /*
+ * Avoid pagevec_lookup(): find_get_pages() returns 0 as if it
+ * has finished, if it hits a row of PAGEVEC_SIZE swap entries.
+ */
+ pvec.nr = shmem_find_get_pages_and_swap(mapping, index,
+ PAGEVEC_SIZE, pvec.pages, indices);
+ if (!pvec.nr)
+ break;
+ index = indices[pvec.nr - 1] + 1;
+ shmem_deswap_pagevec(&pvec);
+ check_move_unevictable_pages(pvec.pages, pvec.nr);
+ pagevec_release(&pvec);
+ cond_resched();
+ }
}
/*
}
unlock_page(page);
}
- shmem_pagevec_release(&pvec);
+ shmem_deswap_pagevec(&pvec);
+ pagevec_release(&pvec);
mem_cgroup_uncharge_end();
cond_resched();
index++;
continue;
}
if (index == start && indices[0] > end) {
- shmem_pagevec_release(&pvec);
+ shmem_deswap_pagevec(&pvec);
+ pagevec_release(&pvec);
break;
}
mem_cgroup_uncharge_start();
}
unlock_page(page);
}
- shmem_pagevec_release(&pvec);
+ shmem_deswap_pagevec(&pvec);
+ pagevec_release(&pvec);
mem_cgroup_uncharge_end();
index++;
}
kfree(xattr->name);
kfree(xattr);
}
- BUG_ON(inode->i_blocks);
+ WARN_ON(inode->i_blocks);
shmem_free_inode(inode->i_sb);
end_writeback(inode);
}
static struct page *shmem_swapin(swp_entry_t swap, gfp_t gfp,
struct shmem_inode_info *info, pgoff_t index)
{
- struct mempolicy mpol, *spol;
struct vm_area_struct pvma;
-
- spol = mpol_cond_copy(&mpol,
- mpol_shared_policy_lookup(&info->policy, index));
+ struct page *page;
/* Create a pseudo vma that just contains the policy */
pvma.vm_start = 0;
pvma.vm_pgoff = index;
pvma.vm_ops = NULL;
- pvma.vm_policy = spol;
- return swapin_readahead(swap, gfp, &pvma, 0);
+ pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, index);
+
+ page = swapin_readahead(swap, gfp, &pvma, 0);
+
+ /* Drop reference taken by mpol_shared_policy_lookup() */
+ mpol_cond_put(pvma.vm_policy);
+
+ return page;
}
static struct page *shmem_alloc_page(gfp_t gfp,
struct shmem_inode_info *info, pgoff_t index)
{
struct vm_area_struct pvma;
+ struct page *page;
/* Create a pseudo vma that just contains the policy */
pvma.vm_start = 0;
pvma.vm_ops = NULL;
pvma.vm_policy = mpol_shared_policy_lookup(&info->policy, index);
- /*
- * alloc_page_vma() will drop the shared policy reference
- */
- return alloc_page_vma(gfp, &pvma, 0);
+ page = alloc_page_vma(gfp, &pvma, 0);
+
+ /* Drop reference taken by mpol_shared_policy_lookup() */
+ mpol_cond_put(pvma.vm_policy);
+
+ return page;
}
#else /* !CONFIG_NUMA */
#ifdef CONFIG_TMPFS
int error;
int ret = VM_FAULT_LOCKED;
+ /*
+ * Trinity finds that probing a hole which tmpfs is punching can
+ * prevent the hole-punch from ever completing: which in turn
+ * locks writers out with its hold on i_mutex. So refrain from
+ * faulting pages into the hole while it's being punched, and
+ * wait on i_mutex to be released if vmf->flags permits.
+ */
+ if (unlikely(inode->i_private)) {
+ struct shmem_falloc *shmem_falloc;
+
+ spin_lock(&inode->i_lock);
+ shmem_falloc = inode->i_private;
+ if (!shmem_falloc ||
+ vmf->pgoff < shmem_falloc->start ||
+ vmf->pgoff >= shmem_falloc->next)
+ shmem_falloc = NULL;
+ spin_unlock(&inode->i_lock);
+ /*
+ * i_lock has protected us from taking shmem_falloc seriously
+ * once return from vmtruncate_range() went back up that stack.
+ * i_lock does not serialize with i_mutex at all, but it does
+ * not matter if sometimes we wait unnecessarily, or sometimes
+ * miss out on waiting: we just need to make those cases rare.
+ */
+ if (shmem_falloc) {
+ if ((vmf->flags & FAULT_FLAG_ALLOW_RETRY) &&
+ !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT)) {
+ up_read(&vma->vm_mm->mmap_sem);
+ mutex_lock(&inode->i_mutex);
+ mutex_unlock(&inode->i_mutex);
+ return VM_FAULT_RETRY;
+ }
+ /* cond_resched? Leave that to GUP or return to user */
+ return VM_FAULT_NOPAGE;
+ }
+ }
+
error = shmem_getpage(inode, vmf->pgoff, &vmf->page, SGP_CACHE, &ret);
if (error)
return ((error == -ENOMEM) ? VM_FAULT_OOM : VM_FAULT_SIGBUS);
return ret;
}
+int vmtruncate_range(struct inode *inode, loff_t lstart, loff_t lend)
+{
+ /*
+ * If the underlying filesystem is not going to provide
+ * a way to truncate a range of blocks (punch a hole) -
+ * we should return failure right now.
+ * Only CONFIG_SHMEM shmem.c ever supported i_op->truncate_range().
+ */
+ if (inode->i_op->truncate_range != shmem_truncate_range)
+ return -ENOSYS;
+
+ mutex_lock(&inode->i_mutex);
+ {
+ struct shmem_falloc shmem_falloc;
+ struct address_space *mapping = inode->i_mapping;
+ loff_t unmap_start = round_up(lstart, PAGE_SIZE);
+ loff_t unmap_end = round_down(1 + lend, PAGE_SIZE) - 1;
+
+ shmem_falloc.start = unmap_start >> PAGE_SHIFT;
+ shmem_falloc.next = (unmap_end + 1) >> PAGE_SHIFT;
+ spin_lock(&inode->i_lock);
+ inode->i_private = &shmem_falloc;
+ spin_unlock(&inode->i_lock);
+
+ if ((u64)unmap_end > (u64)unmap_start)
+ unmap_mapping_range(mapping, unmap_start,
+ 1 + unmap_end - unmap_start, 0);
+ shmem_truncate_range(inode, lstart, lend);
+ /* No need to unmap again: hole-punching leaves COWed pages */
+
+ spin_lock(&inode->i_lock);
+ inode->i_private = NULL;
+ spin_unlock(&inode->i_lock);
+ }
+ mutex_unlock(&inode->i_mutex);
+ return 0;
+}
+
#ifdef CONFIG_NUMA
static int shmem_set_policy(struct vm_area_struct *vma, struct mempolicy *mpol)
{
user_shm_unlock(inode->i_size, user);
info->flags &= ~VM_LOCKED;
mapping_clear_unevictable(file->f_mapping);
- /*
- * Ensure that a racing putback_lru_page() can see
- * the pages of this mapping are evictable when we
- * skip them due to !PageLRU during the scan.
- */
- smp_mb__after_clear_bit();
- scan_mapping_unevictable_pages(file->f_mapping);
}
retval = 0;
struct splice_pipe_desc spd = {
.pages = pages,
.partial = partial,
+ .nr_pages_max = PIPE_DEF_BUFFERS,
.flags = flags,
.ops = &page_cache_pipe_buf_ops,
.spd_release = spd_release_page,
if (spd.nr_pages)
error = splice_to_pipe(pipe, &spd);
- splice_shrink_spd(pipe, &spd);
+ splice_shrink_spd(&spd);
if (error > 0) {
*ppos += error;
{
struct inode *inode;
struct dentry *dentry = NULL;
- u64 inum = fid->raw[2];
- inum = (inum << 32) | fid->raw[1];
+ u64 inum;
if (fh_len < 3)
return NULL;
+ inum = fid->raw[2];
+ inum = (inum << 32) | fid->raw[1];
+
inode = ilookup5(sb, (unsigned long)(inum + fid->raw[0]),
shmem_match, fid->raw);
if (inode) {
unsigned long inodes;
int error = -EINVAL;
+ config.mpol = NULL;
if (shmem_parse_options(data, &config, true))
return error;
sbinfo->max_inodes = config.max_inodes;
sbinfo->free_inodes = config.max_inodes - inodes;
- mpol_put(sbinfo->mpol);
- sbinfo->mpol = config.mpol; /* transfers initial ref */
+ /*
+ * Preserve previous mempolicy unless mpol remount option was specified.
+ */
+ if (config.mpol) {
+ mpol_put(sbinfo->mpol);
+ sbinfo->mpol = config.mpol; /* transfers initial ref */
+ }
out:
spin_unlock(&sbinfo->stat_lock);
return error;
return 0;
}
+void shmem_unlock_mapping(struct address_space *mapping)
+{
+}
+
void shmem_truncate_range(struct inode *inode, loff_t lstart, loff_t lend)
{
truncate_inode_pages_range(inode->i_mapping, lstart, lend);
}
EXPORT_SYMBOL_GPL(shmem_truncate_range);
+int vmtruncate_range(struct inode *inode, loff_t lstart, loff_t lend)
+{
+ /* Only CONFIG_SHMEM shmem.c ever supported i_op->truncate_range(). */
+ return -ENOSYS;
+}
+
#define shmem_vm_ops generic_file_vm_ops
#define shmem_file_operations ramfs_file_operations
#define shmem_get_inode(sb, dir, mode, dev, flags) ramfs_get_inode(sb, dir, mode, dev)