mm/zswap: add the flag can_sleep_mapped

Patch series "Fix the compatibility of zsmalloc and zswap".

Patch #1 adds a flag to zpool, then zswap used to determine if zpool
drivers such as zbud/z3fold/zsmalloc will enter an atomic context after
mapping.

The difference between zbud/z3fold and zsmalloc is that zsmalloc requires
an atomic context that since its map function holds a preempt-disabled,
but zbud/z3fold don't require an atomic context. So patch #2 sets flag
sleep_mapped to true indicating that zbud/z3fold can sleep after mapping.
zsmalloc didn't support sleep after mapping, so don't set that flag to
true.

This patch (of 2):

Add a flag to zpool, named is "can_sleep_mapped", and have it set true for
zbud/z3fold, not set this flag for zsmalloc, so its default value is
false. Then zswap could go the current path if the flag is true; and if
it's false, copy data from src to a temporary buffer, then unmap the
handle, take the mutex, process the buffer instead of src to avoid
sleeping function called from atomic context.

[[e-mail]: add return value in zswap_frontswap_load]
Link: https://lkml.kernel.org/r/[e-mail]
[[e-mail]: fix potential memory leak]
Link: https://lkml.kernel.org/r/[e-mail]
[[e-mail]: fix potential uninitialized pointer read on tmp]
Link: https://lkml.kernel.org/r/[e-mail]
[[e-mail]: fix variable 'entry' is uninitialized when used]
Link: https://lkml.kernel.org/r/[e-mail]: https://lkml.kernel.org/r/[e-mail]

Link: https://lkml.kernel.org/r/[e-mail]
Signed-off-by: Tian Tao <[e-mail]>
Signed-off-by: Nathan Chancellor <[e-mail]>
Signed-off-by: Colin Ian King <[e-mail]>
Reviewed-by: Vitaly Wool <[e-mail]>
Acked-by: Sebastian Andrzej Siewior <[e-mail]>
Reported-by: Mike Galbraith <[e-mail]>
Cc: Barry Song <[e-mail]>
Cc: Dan Streetman <[e-mail]>
Cc: Seth Jennings <[e-mail]>
Cc: Dan Carpenter <[e-mail]>
Signed-off-by: Andrew Morton <[e-mail]>
Signed-off-by: Linus Torvalds <[e-mail]>

include/linux/zpool.h

···
  * @malloc:	allocate mem from a pool.
  * @free:	free mem from a pool.
  * @shrink:	shrink the pool.
+ * @sleep_mapped: whether zpool driver can sleep during map.
  * @map:	map a handle.
  * @unmap:	unmap a handle.
  * @total_size:	get total size of a pool.
···
 	int (*shrink)(void *pool, unsigned int pages,
 				unsigned int *reclaimed);
 
+	bool sleep_mapped;
 	void *(*map)(void *pool, unsigned long handle,
 				enum zpool_mapmode mm);
 	void (*unmap)(void *pool, unsigned long handle);
···
 int zpool_unregister_driver(struct zpool_driver *driver);
 
 bool zpool_evictable(struct zpool *pool);
+bool zpool_can_sleep_mapped(struct zpool *pool);
 
 #endif

mm/zpool.c

···
 	void *pool;
 	const struct zpool_ops *ops;
 	bool evictable;
+	bool can_sleep_mapped;
 
 	struct list_head list;
 };
···
 	zpool->pool = driver->create(name, gfp, ops, zpool);
 	zpool->ops = ops;
 	zpool->evictable = driver->shrink && ops && ops->evict;
+	zpool->can_sleep_mapped = driver->sleep_mapped;
 
 	if (!zpool->pool) {
 		pr_err("couldn't create %s pool\n", type);
···
 bool zpool_evictable(struct zpool *zpool)
 {
 	return zpool->evictable;
+}
+
+/**
+ * zpool_can_sleep_mapped - Test if zpool can sleep when do mapped.
+ * @zpool:	The zpool to test
+ *
+ * Returns: true if zpool can sleep; false otherwise.
+ */
+bool zpool_can_sleep_mapped(struct zpool *zpool)
+{
+	return zpool->can_sleep_mapped;
 }
 
 MODULE_LICENSE("GPL");

mm/zswap.c

···
 	struct scatterlist input, output;
 	struct crypto_acomp_ctx *acomp_ctx;
 
-	u8 *src;
+	u8 *src, *tmp = NULL;
 	unsigned int dlen;
 	int ret;
 	struct writeback_control wbc = {
 		.sync_mode = WB_SYNC_NONE,
 	};
+
+	if (!zpool_can_sleep_mapped(pool)) {
+		tmp = kmalloc(PAGE_SIZE, GFP_ATOMIC);
+		if (!tmp)
+			return -ENOMEM;
+	}
 
 	/* extract swpentry from data */
 	zhdr = zpool_map_handle(pool, handle, ZPOOL_MM_RO);
···
 		/* entry was invalidated */
 		spin_unlock(&tree->lock);
 		zpool_unmap_handle(pool, handle);
+		kfree(tmp);
 		return 0;
 	}
 	spin_unlock(&tree->lock);
···
 
 		dlen = PAGE_SIZE;
 		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);
···
 	spin_unlock(&tree->lock);
 
 end:
-	zpool_unmap_handle(pool, handle);
+	if (zpool_can_sleep_mapped(pool))
+		zpool_unmap_handle(pool, handle);
+	else
+		kfree(tmp);
+
 	return ret;
 }
 
···
 	struct zswap_entry *entry;
 	struct scatterlist input, output;
 	struct crypto_acomp_ctx *acomp_ctx;
-	u8 *src, *dst;
+	u8 *src, *dst, *tmp;
 	unsigned int dlen;
 	int ret;
 
···
 		dst = kmap_atomic(page);
 		zswap_fill_page(dst, entry->value);
 		kunmap_atomic(dst);
+		ret = 0;
 		goto freeentry;
+	}
+
+	if (!zpool_can_sleep_mapped(entry->pool->zpool)) {
+
+		tmp = kmalloc(entry->length, GFP_ATOMIC);
+		if (!tmp) {
+			ret = -ENOMEM;
+			goto freeentry;
+		}
 	}
 
 	/* decompress */
···
 	src = zpool_map_handle(entry->pool->zpool, entry->handle, ZPOOL_MM_RO);
 	if (zpool_evictable(entry->pool->zpool))
 		src += sizeof(struct zswap_header);
+
+	if (!zpool_can_sleep_mapped(entry->pool->zpool)) {
+
+		memcpy(tmp, src, entry->length);
+		src = tmp;
+
+		zpool_unmap_handle(entry->pool->zpool, entry->handle);
+	}
 
 	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
 	mutex_lock(acomp_ctx->mutex);
···
 	ret = crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait);
 	mutex_unlock(acomp_ctx->mutex);
 
-	zpool_unmap_handle(entry->pool->zpool, entry->handle);
+	if (zpool_can_sleep_mapped(entry->pool->zpool))
+		zpool_unmap_handle(entry->pool->zpool, entry->handle);
+	else
+		kfree(tmp);
+
 	BUG_ON(ret);
 
 freeentry:
···
 	zswap_entry_put(tree, entry);
 	spin_unlock(&tree->lock);
 
-	return 0;
+	return ret;
 }
 
 /* frees an entry in zswap */