/*
* returns 0 if the page was successfully decompressed
* return -1 on entry not found or error
*/
static int zswap_frontswap_load(unsigned type, pgoff_t offset,
struct page *page)
{
struct zswap_tree *tree = zswap_trees[type];
struct zswap_entry *entry;
u8 *src, *dst;
unsigned int dlen;
int ret;
/* find */
spin_lock(&tree->lock);
entry = zswap_entry_find_get(&tree->rbroot, offset);
if (!entry) {
/* entry was written back */
spin_unlock(&tree->lock);
return -1;
}
spin_unlock(&tree->lock);
if (entry->zero_flag == 1) {
dst = kmap_atomic(page);
memset(dst, 0, PAGE_SIZE);
kunmap_atomic(dst);
goto zeropage_out;
}
/* decompress */
dlen = PAGE_SIZE;
src = (u8 *)zpool_map_handle(zswap_pool, entry->handle,
ZPOOL_MM_RO) + sizeof(struct zswap_header);
dst = kmap_atomic(page);
ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src, entry->length,
dst, &dlen);
if (ret) {
hexdump("src buffer", src, entry->length);
if (dlen)
hexdump("dest buffer", dst, dlen);
printk("zswap_comp_op returned %d\n", ret);
}
kunmap_atomic(dst);
zpool_unmap_handle(zswap_pool, entry->handle);
BUG_ON(ret);
zeropage_out:
spin_lock(&tree->lock);
zswap_entry_put(tree, entry);
spin_unlock(&tree->lock);
return 0;
}
/*
* returns 0 if the page was successfully decompressed
* return -1 on entry not found or error
*/
static int zswap_frontswap_load(unsigned type, pgoff_t offset,
struct page *page)
{
struct zswap_tree *tree = zswap_trees[type];
struct zswap_entry *entry;
u8 *src, *dst;
unsigned int dlen;
int ret;
/* find */
spin_lock(&tree->lock);
entry = zswap_entry_find_get(&tree->rbroot, offset);
if (!entry) {
/* entry was written back */
spin_unlock(&tree->lock);
return -1;
}
spin_unlock(&tree->lock);
/* decompress */
dlen = PAGE_SIZE;
src = (u8 *)zpool_map_handle(zswap_pool, entry->handle,
ZPOOL_MM_RO) + sizeof(struct zswap_header);
dst = kmap_atomic(page);
ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src, entry->length,
dst, &dlen);
kunmap_atomic(dst);
zpool_unmap_handle(zswap_pool, entry->handle);
BUG_ON(ret);
spin_lock(&tree->lock);
zswap_entry_put(tree, entry);
spin_unlock(&tree->lock);
return 0;
}
/* attempts to compress and store an single page */
static int zswap_frontswap_store(unsigned type, pgoff_t offset,
struct page *page)
{
struct zswap_tree *tree = zswap_trees[type];
struct zswap_entry *entry, *dupentry;
int ret;
unsigned int dlen = PAGE_SIZE, len;
unsigned long handle;
char *buf;
u8 *src, *dst;
struct zswap_header *zhdr;
if (!tree) {
ret = -ENODEV;
goto reject;
}
/* if this page got EIO on pageout before, give up immediately */
if (PageError(page)) {
ret = -ENOMEM;
goto reject;
}
/* reclaim space if needed */
if (zswap_is_full()) {
zswap_pool_limit_hit++;
if (zpool_shrink(zswap_pool, 1, NULL)) {
zswap_reject_reclaim_fail++;
ret = -ENOMEM;
goto reject;
}
}
/* allocate entry */
entry = zswap_entry_cache_alloc(GFP_KERNEL);
if (!entry) {
zswap_reject_kmemcache_fail++;
ret = -ENOMEM;
goto reject;
}
/* compress */
src = kmap_atomic(page);
if (page_zero_filled(src)) {
atomic_inc(&zswap_zero_pages);
entry->zero_flag = 1;
kunmap_atomic(src);
handle = 0;
dlen = PAGE_SIZE;
goto zeropage_out;
}
dst = get_cpu_var(zswap_dstmem);
ret = zswap_comp_op(ZSWAP_COMPOP_COMPRESS, src, PAGE_SIZE, dst, &dlen);
kunmap_atomic(src);
if (ret) {
ret = -EINVAL;
goto freepage;
}
/* store */
len = dlen + sizeof(struct zswap_header);
ret = zpool_malloc(zswap_pool, len, __GFP_NORETRY | __GFP_NOWARN,
&handle);
if (ret == -ENOSPC) {
zswap_reject_compress_poor++;
goto freepage;
}
if (ret) {
zswap_reject_alloc_fail++;
goto freepage;
}
zhdr = zpool_map_handle(zswap_pool, handle, ZPOOL_MM_RW);
zhdr->swpentry = swp_entry(type, offset);
buf = (u8 *)(zhdr + 1);
memcpy(buf, dst, dlen);
zpool_unmap_handle(zswap_pool, handle);
put_cpu_var(zswap_dstmem);
zeropage_out:
/* populate entry */
entry->offset = offset;
entry->handle = handle;
entry->length = dlen;
/* map */
spin_lock(&tree->lock);
do {
ret = zswap_rb_insert(&tree->rbroot, entry, &dupentry);
if (ret == -EEXIST) {
zswap_duplicate_entry++;
/* remove from rbtree */
zswap_rb_erase(&tree->rbroot, dupentry);
zswap_entry_put(tree, dupentry);
}
} while (ret == -EEXIST);
spin_unlock(&tree->lock);
/* update stats */
atomic_inc(&zswap_stored_pages);
zswap_pool_total_size = zpool_get_total_size(zswap_pool);
zswap_pool_pages = zswap_pool_total_size >> PAGE_SHIFT;
return 0;
freepage:
put_cpu_var(zswap_dstmem);
zswap_entry_cache_free(entry);
reject:
return ret;
}
/*
* Attempts to free an entry by adding a page to the swap cache,
* decompressing the entry data into the page, and issuing a
* bio write to write the page back to the swap device.
*
* This can be thought of as a "resumed writeback" of the page
* to the swap device. We are basically resuming the same swap
* writeback path that was intercepted with the frontswap_store()
* in the first place. After the page has been decompressed into
* the swap cache, the compressed version stored by zswap can be
* freed.
*/
static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
{
struct zswap_header *zhdr;
swp_entry_t swpentry;
struct zswap_tree *tree;
pgoff_t offset;
struct zswap_entry *entry;
struct page *page;
u8 *src, *dst;
unsigned int dlen;
int ret;
struct writeback_control wbc = {
.sync_mode = WB_SYNC_NONE,
};
/* extract swpentry from data */
zhdr = zpool_map_handle(pool, handle, ZPOOL_MM_RO);
swpentry = zhdr->swpentry; /* here */
zpool_unmap_handle(pool, handle);
tree = zswap_trees[swp_type(swpentry)];
offset = swp_offset(swpentry);
/* find and ref zswap entry */
spin_lock(&tree->lock);
entry = zswap_entry_find_get(&tree->rbroot, offset);
if (!entry) {
/* entry was invalidated */
spin_unlock(&tree->lock);
return 0;
}
spin_unlock(&tree->lock);
BUG_ON(offset != entry->offset);
/* try to allocate swap cache page */
switch (zswap_get_swap_cache_page(swpentry, &page)) {
case ZSWAP_SWAPCACHE_FAIL: /* no memory or invalidate happened */
ret = -ENOMEM;
goto fail;
case ZSWAP_SWAPCACHE_EXIST:
/* page is already in the swap cache, ignore for now */
page_cache_release(page);
ret = -EEXIST;
goto fail;
case ZSWAP_SWAPCACHE_NEW: /* page is locked */
/* decompress */
dlen = PAGE_SIZE;
src = (u8 *)zpool_map_handle(zswap_pool, entry->handle,
ZPOOL_MM_RO) + sizeof(struct zswap_header);
dst = kmap_atomic(page);
ret = zswap_comp_op(ZSWAP_COMPOP_DECOMPRESS, src,
entry->length, dst, &dlen);
kunmap_atomic(dst);
zpool_unmap_handle(zswap_pool, entry->handle);
BUG_ON(ret);
BUG_ON(dlen != PAGE_SIZE);
/* page is up to date */
SetPageUptodate(page);
}
/* move it to the tail of the inactive list after end_writeback */
SetPageReclaim(page);
/* start writeback */
__swap_writepage(page, &wbc, end_swap_bio_write);
page_cache_release(page);
zswap_written_back_pages++;
spin_lock(&tree->lock);
/* drop local reference */
zswap_entry_put(tree, entry);
/*
* There are two possible situations for entry here:
* (1) refcount is 1(normal case), entry is valid and on the tree
* (2) refcount is 0, entry is freed and not on the tree
* because invalidate happened during writeback
* search the tree and free the entry if find entry
*/
if (entry == zswap_rb_search(&tree->rbroot, offset))
zswap_entry_put(tree, entry);
spin_unlock(&tree->lock);
goto end;
/*
* if we get here due to ZSWAP_SWAPCACHE_EXIST
* a load may happening concurrently
* it is safe and okay to not free the entry
* if we free the entry in the following put
* it it either okay to return !0
*/
fail:
spin_lock(&tree->lock);
zswap_entry_put(tree, entry);
spin_unlock(&tree->lock);
end:
return ret;
}
/* attempts to compress and store an single page */
static int zswap_frontswap_store(unsigned type, pgoff_t offset,
struct page *page)
{
struct zswap_tree *tree = zswap_trees[type];
struct zswap_entry *entry, *dupentry;
int ret;
unsigned int dlen = PAGE_SIZE, len;
unsigned long handle;
char *buf;
u8 *src, *dst;
struct zswap_header *zhdr;
if (!tree) {
ret = -ENODEV;
goto reject;
}
/* reclaim space if needed */
if (zswap_is_full()) {
zswap_pool_limit_hit++;
if (zbud_reclaim_page(tree->pool, 8)) {
zswap_reject_reclaim_fail++;
ret = -ENOMEM;
goto reject;
}
}
/* allocate entry */
entry = zswap_entry_cache_alloc(GFP_KERNEL);
if (!entry) {
zswap_reject_kmemcache_fail++;
ret = -ENOMEM;
goto reject;
}
/* compress */
dst = get_cpu_var(zswap_dstmem);
src = kmap_atomic(page);
ret = zswap_comp_op(ZSWAP_COMPOP_COMPRESS, src, PAGE_SIZE, dst, &dlen);
kunmap_atomic(src);
if (ret) {
ret = -EINVAL;
goto freepage;
}
/* store */
len = dlen + sizeof(struct zswap_header);
ret = zbud_alloc(tree->pool, len, __GFP_NORETRY | __GFP_NOWARN,
&handle);
if (ret == -ENOSPC) {
zswap_reject_compress_poor++;
goto freepage;
}
if (ret) {
zswap_reject_alloc_fail++;
goto freepage;
}
zhdr = zbud_map(tree->pool, handle);
zhdr->swpentry = swp_entry(type, offset);
buf = (u8 *)(zhdr + 1);
memcpy(buf, dst, dlen);
zbud_unmap(tree->pool, handle);
put_cpu_var(zswap_dstmem);
/* populate entry */
entry->offset = offset;
entry->handle = handle;
entry->length = dlen;
/* map */
spin_lock(&tree->lock);
do {
ret = zswap_rb_insert(&tree->rbroot, entry, &dupentry);
if (ret == -EEXIST) {
zswap_duplicate_entry++;
/* remove from rbtree */
zswap_rb_erase(&tree->rbroot, dupentry);
zswap_entry_put(tree, dupentry);
}
} while (ret == -EEXIST);
spin_unlock(&tree->lock);
/* update stats */
atomic_inc(&zswap_stored_pages);
zswap_pool_pages = zbud_get_pool_size(tree->pool);
return 0;
freepage:
put_cpu_var(zswap_dstmem);
zswap_entry_cache_free(entry);
reject:
return ret;
}