if (unlikely(zbpg == NULL))
goto out;
/* ok, have a page, now compress the data before taking locks */
- spin_lock(&zbpg->lock);
spin_lock(&zbud_budlists_spinlock);
+ spin_lock(&zbpg->lock);
list_add_tail(&zbpg->bud_list, &zbud_unbuddied[nchunks].list);
zbud_unbuddied[nchunks].count++;
zh = &zbpg->buddy[0];
zh->oid = *oid;
zh->pool_id = pool_id;
zh->client_id = client_id;
- /* can wait to copy the data until the list locks are dropped */
- spin_unlock(&zbud_budlists_spinlock);
-
to = zbud_data(zh, size);
memcpy(to, cdata, size);
spin_unlock(&zbpg->lock);
+ spin_unlock(&zbud_budlists_spinlock);
+
zbud_cumul_chunk_counts[nchunks]++;
atomic_inc(&zcache_zbud_curr_zpages);
zcache_zbud_cumul_zpages++;
*/
static unsigned int zv_max_mean_zsize = (PAGE_SIZE / 8) * 5;
-static unsigned long zv_curr_dist_counts[NCHUNKS];
-static unsigned long zv_cumul_dist_counts[NCHUNKS];
+static atomic_t zv_curr_dist_counts[NCHUNKS];
+static atomic_t zv_cumul_dist_counts[NCHUNKS];
static struct zv_hdr *zv_create(struct xv_pool *xvpool, uint32_t pool_id,
struct tmem_oid *oid, uint32_t index,
&page, &offset, ZCACHE_GFP_MASK);
if (unlikely(ret))
goto out;
- zv_curr_dist_counts[chunks]++;
- zv_cumul_dist_counts[chunks]++;
+ atomic_inc(&zv_curr_dist_counts[chunks]);
+ atomic_inc(&zv_cumul_dist_counts[chunks]);
zv = kmap_atomic(page, KM_USER0) + offset;
zv->index = index;
zv->oid = *oid;
ASSERT_SENTINEL(zv, ZVH);
BUG_ON(chunks >= NCHUNKS);
- zv_curr_dist_counts[chunks]--;
+ atomic_dec(&zv_curr_dist_counts[chunks]);
size -= sizeof(*zv);
BUG_ON(size == 0);
INVERT_SENTINEL(zv, ZVH);
char *p = buf;
for (i = 0; i < NCHUNKS; i++) {
- n = zv_curr_dist_counts[i];
+ n = atomic_read(&zv_curr_dist_counts[i]);
p += sprintf(p, "%lu ", n);
chunks += n;
sum_total_chunks += i * n;
char *p = buf;
for (i = 0; i < NCHUNKS; i++) {
- n = zv_cumul_dist_counts[i];
+ n = atomic_read(&zv_cumul_dist_counts[i]);
p += sprintf(p, "%lu ", n);
chunks += n;
sum_total_chunks += i * n;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- err = strict_strtoul(buf, 10, &val);
+ err = kstrtoul(buf, 10, &val);
if (err || (val == 0) || (val > (PAGE_SIZE / 8) * 7))
return -EINVAL;
zv_max_zsize = val;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- err = strict_strtoul(buf, 10, &val);
+ err = kstrtoul(buf, 10, &val);
if (err || (val == 0) || (val > (PAGE_SIZE / 8) * 7))
return -EINVAL;
zv_max_mean_zsize = val;
if (!capable(CAP_SYS_ADMIN))
return -EPERM;
- err = strict_strtoul(buf, 10, &val);
+ err = kstrtoul(buf, 10, &val);
if (err || (val == 0) || (val > 150))
return -EINVAL;
zv_page_count_policy_percent = val;
static struct cleancache_ops zcache_cleancache_ops = {
.put_page = zcache_cleancache_put_page,
.get_page = zcache_cleancache_get_page,
- .flush_page = zcache_cleancache_flush_page,
- .flush_inode = zcache_cleancache_flush_inode,
- .flush_fs = zcache_cleancache_flush_fs,
+ .invalidate_page = zcache_cleancache_flush_page,
+ .invalidate_inode = zcache_cleancache_flush_inode,
+ .invalidate_fs = zcache_cleancache_flush_fs,
.init_shared_fs = zcache_cleancache_init_shared_fs,
.init_fs = zcache_cleancache_init_fs
};
* Swizzling increases objects per swaptype, increasing tmem concurrency
* for heavy swaploads. Later, larger nr_cpus -> larger SWIZ_BITS
* Setting SWIZ_BITS to 27 basically reconstructs the swap entry from
- * frontswap_get_page()
+ * frontswap_get_page(), but has side-effects. Hence using 8.
*/
-#define SWIZ_BITS 27
+#define SWIZ_BITS 8
#define SWIZ_MASK ((1 << SWIZ_BITS) - 1)
#define _oswiz(_type, _ind) ((_type << SWIZ_BITS) | (_ind & SWIZ_MASK))
#define iswiz(_ind) (_ind >> SWIZ_BITS)
static struct frontswap_ops zcache_frontswap_ops = {
.put_page = zcache_frontswap_put_page,
.get_page = zcache_frontswap_get_page,
- .flush_page = zcache_frontswap_flush_page,
- .flush_area = zcache_frontswap_flush_area,
+ .invalidate_page = zcache_frontswap_flush_page,
+ .invalidate_area = zcache_frontswap_flush_area,
.init = zcache_frontswap_init
};
#include <linux/uio.h>
#include <linux/namei.h>
#include <linux/log2.h>
-#include <linux/kmemleak.h>
#include <linux/cleancache.h>
#include <asm/uaccess.h>
#include "internal.h"
/* 99% of the time, we don't need to flush the cleancache on the bdev.
* But, for the strange corners, lets be cautious
*/
- cleancache_flush_inode(mapping);
+ cleancache_invalidate_inode(mapping);
}
EXPORT_SYMBOL(invalidate_bdev);
void __init bdev_cache_init(void)
{
int err;
- struct vfsmount *bd_mnt;
+ static struct vfsmount *bd_mnt;
bdev_cachep = kmem_cache_create("bdev_cache", sizeof(struct bdev_inode),
0, (SLAB_HWCACHE_ALIGN|SLAB_RECLAIM_ACCOUNT|
bd_mnt = kern_mount(&bd_type);
if (IS_ERR(bd_mnt))
panic("Cannot create bdev pseudo-fs");
- /*
- * This vfsmount structure is only used to obtain the
- * blockdev_superblock, so tell kmemleak not to report it.
- */
- kmemleak_not_leak(bd_mnt);
- blockdev_superblock = bd_mnt->mnt_sb; /* For writeback */
+ blockdev_superblock = bd_mnt->mnt_sb; /* For writeback */
}
/*
mutex_lock_nested(&bdev->bd_mutex, for_part);
if (!bdev->bd_openers) {
bdev->bd_disk = disk;
+ bdev->bd_queue = disk->queue;
bdev->bd_contains = bdev;
if (!partno) {
struct backing_dev_info *bdi;
disk_put_part(bdev->bd_part);
bdev->bd_part = NULL;
bdev->bd_disk = NULL;
+ bdev->bd_queue = NULL;
mutex_unlock(&bdev->bd_mutex);
disk_unblock_events(disk);
put_disk(disk);
* The latter is necessary to prevent ghost
* partitions on a removed medium.
*/
- if (bdev->bd_invalidated && (!ret || ret == -ENOMEDIUM))
- rescan_partitions(disk, bdev);
+ if (bdev->bd_invalidated) {
+ if (!ret)
+ rescan_partitions(disk, bdev);
+ else if (ret == -ENOMEDIUM)
+ invalidate_partitions(disk, bdev);
+ }
if (ret)
goto out_clear;
} else {
if (bdev->bd_disk->fops->open)
ret = bdev->bd_disk->fops->open(bdev, mode);
/* the same as first opener case, read comment there */
- if (bdev->bd_invalidated && (!ret || ret == -ENOMEDIUM))
- rescan_partitions(bdev->bd_disk, bdev);
+ if (bdev->bd_invalidated) {
+ if (!ret)
+ rescan_partitions(bdev->bd_disk, bdev);
+ else if (ret == -ENOMEDIUM)
+ invalidate_partitions(bdev->bd_disk, bdev);
+ }
if (ret)
goto out_unlock_bdev;
}
disk_put_part(bdev->bd_part);
bdev->bd_disk = NULL;
bdev->bd_part = NULL;
+ bdev->bd_queue = NULL;
bdev_inode_switch_bdi(bdev->bd_inode, &default_backing_dev_info);
if (bdev != bdev->bd_contains)
__blkdev_put(bdev->bd_contains, mode, 1);
{
struct file_system_type *fs = s->s_type;
if (atomic_dec_and_test(&s->s_active)) {
- cleancache_flush_fs(s);
+ cleancache_invalidate_fs(s);
fs->kill_sb(s);
/* caches are now gone, we can safely kill the shrinker now */
EXPORT_SYMBOL(get_super);
+/**
+ * get_super_thawed - get thawed superblock of a device
+ * @bdev: device to get the superblock for
+ *
+ * Scans the superblock list and finds the superblock of the file system
+ * mounted on the device. The superblock is returned once it is thawed
+ * (or immediately if it was not frozen). %NULL is returned if no match
+ * is found.
+ */
+struct super_block *get_super_thawed(struct block_device *bdev)
+{
+ while (1) {
+ struct super_block *s = get_super(bdev);
+ if (!s || s->s_frozen == SB_UNFROZEN)
+ return s;
+ up_read(&s->s_umount);
+ vfs_check_frozen(s, SB_FREEZE_WRITE);
+ put_super(s);
+ }
+}
+EXPORT_SYMBOL(get_super_thawed);
+
/**
* get_active_super - get an active reference to the superblock of a device
* @bdev: device to get the superblock for
printk(KERN_ERR
"VFS:Filesystem freeze failed\n");
sb->s_frozen = SB_UNFROZEN;
+ smp_wmb();
+ wake_up(&sb->s_wait_unfrozen);
deactivate_locked_super(sb);
return ret;
}
if (PageUptodate(page) && PageMappedToDisk(page))
cleancache_put_page(page);
else
- cleancache_flush_page(mapping, page);
+ cleancache_invalidate_page(mapping, page);
radix_tree_delete(&mapping->page_tree, page->index);
page->mapping = NULL;
int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask)
{
int error;
- struct mem_cgroup *memcg = NULL;
VM_BUG_ON(!PageLocked(old));
VM_BUG_ON(!PageLocked(new));
VM_BUG_ON(new->mapping);
- /*
- * This is not page migration, but prepare_migration and
- * end_migration does enough work for charge replacement.
- *
- * In the longer term we probably want a specialized function
- * for moving the charge from old to new in a more efficient
- * manner.
- */
- error = mem_cgroup_prepare_migration(old, new, &memcg, gfp_mask);
- if (error)
- return error;
-
error = radix_tree_preload(gfp_mask & ~__GFP_HIGHMEM);
if (!error) {
struct address_space *mapping = old->mapping;
if (PageSwapBacked(new))
__inc_zone_page_state(new, NR_SHMEM);
spin_unlock_irq(&mapping->tree_lock);
+ /* mem_cgroup codes must not be called under tree_lock */
+ mem_cgroup_replace_page_cache(old, new);
radix_tree_preload_end();
if (freepage)
freepage(old);
page_cache_release(old);
- mem_cgroup_end_migration(memcg, old, new, true);
- } else {
- mem_cgroup_end_migration(memcg, old, new, false);
}
return error;
unsigned long seg = 0;
size_t count;
loff_t *ppos = &iocb->ki_pos;
- struct blk_plug plug;
count = 0;
retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE);
if (retval)
return retval;
- blk_start_plug(&plug);
-
/* coalesce the iovecs and go direct-to-BIO for O_DIRECT */
if (filp->f_flags & O_DIRECT) {
loff_t size;
retval = filemap_write_and_wait_range(mapping, pos,
pos + iov_length(iov, nr_segs) - 1);
if (!retval) {
+ struct blk_plug plug;
+
+ blk_start_plug(&plug);
retval = mapping->a_ops->direct_IO(READ, iocb,
iov, pos, nr_segs);
+ blk_finish_plug(&plug);
}
if (retval > 0) {
*ppos = pos + retval;
break;
}
out:
- blk_finish_plug(&plug);
return retval;
}
EXPORT_SYMBOL(generic_file_aio_read);
pgoff_t index, unsigned flags)
{
int status;
+ gfp_t gfp_mask;
struct page *page;
gfp_t gfp_notmask = 0;
+
+ gfp_mask = mapping_gfp_mask(mapping) | __GFP_WRITE;
if (flags & AOP_FLAG_NOFS)
gfp_notmask = __GFP_FS;
repeat:
if (page)
goto found;
- page = __page_cache_alloc(mapping_gfp_mask(mapping) & ~gfp_notmask);
+ page = __page_cache_alloc(gfp_mask & ~gfp_notmask);
if (!page)
return NULL;
status = add_to_page_cache_lru(page, mapping, index,
projects / cascardo / linux.git / commitdiff