zswap: fix writeback lock ordering for zsmalloc

Patch series "Implement writeback for zsmalloc", v7.

Unlike other zswap allocators such as zbud or z3fold, zsmalloc currently
lacks the writeback mechanism.  This means that when the zswap pool is
full, it will simply reject further allocations, and the pages will be
written directly to swap.

This series of patches implements writeback for zsmalloc. When the zswap
pool becomes full, zsmalloc will attempt to evict all the compressed
objects in the least-recently used zspages.


This patch (of 6):

zswap's customary lock order is tree->lock before pool->lock, because the
tree->lock protects the entries' refcount, and the free callbacks in the
backends acquire their respective pool locks to dispatch the backing
object.  zsmalloc's map callback takes the pool lock, so zswap must not
grab the tree->lock while a handle is mapped.  This currently only happens
during writeback, which isn't implemented for zsmalloc.  In preparation
for it, move the tree->lock section out of the mapped entry section

Link: https://lkml.kernel.org/r/20221128191616.1261026-1-nphamcs@gmail.com
Link: https://lkml.kernel.org/r/20221128191616.1261026-2-nphamcs@gmail.com
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Nhat Pham <nphamcs@gmail.com>
Reviewed-by: Sergey Senozhatsky <senozhatsky@chromium.org>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Vitaly Wool <vitaly.wool@konsulko.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

1 files changed, 19 insertions, 16 deletions

diff --git a/mm/zswap.c b/mm/zswap.c
index 3019f0bde194..f6c89049cf70 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -968,6 +968,7 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
 	swpentry = zhdr->swpentry; /* here */
 	tree = zswap_trees[swp_type(swpentry)];
 	offset = swp_offset(swpentry);
+	zpool_unmap_handle(pool, handle);
 
 	/* find and ref zswap entry */
 	spin_lock(&tree->lock);
@@ -975,20 +976,12 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
 	if (!entry) {
 		/* entry was invalidated */
 		spin_unlock(&tree->lock);
-		zpool_unmap_handle(pool, handle);
 		kfree(tmp);
 		return 0;
 	}
 	spin_unlock(&tree->lock);
 	BUG_ON(offset != entry->offset);
 
-	src = (u8 *)zhdr + sizeof(struct zswap_header);
-	if (!zpool_can_sleep_mapped(pool)) {
-		memcpy(tmp, src, entry->length);
-		src = tmp;
-		zpool_unmap_handle(pool, handle);
-	}
-
 	/* try to allocate swap cache page */
 	switch (zswap_get_swap_cache_page(swpentry, &page)) {
 	case ZSWAP_SWAPCACHE_FAIL: /* no memory or invalidate happened */
@@ -1006,6 +999,14 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
 		acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
 		dlen = PAGE_SIZE;
 
+		zhdr = zpool_map_handle(pool, handle, ZPOOL_MM_RO);
+		src = (u8 *)zhdr + sizeof(struct zswap_header);
+		if (!zpool_can_sleep_mapped(pool)) {
+			memcpy(tmp, src, entry->length);
+			src = tmp;
+			zpool_unmap_handle(pool, handle);
+		}
+
 		mutex_lock(acomp_ctx->mutex);
 		sg_init_one(&input, src, entry->length);
 		sg_init_table(&output, 1);
@@ -1015,6 +1016,11 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
 		dlen = acomp_ctx->req->dlen;
 		mutex_unlock(acomp_ctx->mutex);
 
+		if (!zpool_can_sleep_mapped(pool))
+			kfree(tmp);
+		else
+			zpool_unmap_handle(pool, handle);
+
 		BUG_ON(ret);
 		BUG_ON(dlen != PAGE_SIZE);
 
@@ -1045,7 +1051,11 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
 		zswap_entry_put(tree, entry);
 	spin_unlock(&tree->lock);
 
-	goto end;
+	return ret;
+
+fail:
+	if (!zpool_can_sleep_mapped(pool))
+		kfree(tmp);
 
 	/*
 	* if we get here due to ZSWAP_SWAPCACHE_EXIST
@@ -1054,17 +1064,10 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
 	* if we free the entry in the following put
 	* it is also okay to return !0
 	*/
-fail:
 	spin_lock(&tree->lock);
 	zswap_entry_put(tree, entry);
 	spin_unlock(&tree->lock);
 
-end:
-	if (zpool_can_sleep_mapped(pool))
-		zpool_unmap_handle(pool, handle);
-	else
-		kfree(tmp);
-
 	return ret;
 }