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.

[natechancellor@gmail.com: add return value in zswap_frontswap_load]
  Link: https://lkml.kernel.org/r/20210121214804.926843-1-natechancellor@gmail.com
[tiantao6@hisilicon.com: fix potential memory leak]
  Link: https://lkml.kernel.org/r/1611538365-51811-1-git-send-email-tiantao6@hisilicon.com
[colin.king@canonical.com: fix potential uninitialized pointer read on tmp]
  Link: https://lkml.kernel.org/r/20210128141728.639030-1-colin.king@canonical.com
[tiantao6@hisilicon.com: fix variable 'entry' is uninitialized when used]
  Link: https://lkml.kernel.org/r/1611223030-58346-1-git-send-email-tiantao6@hisilicon.comLink: https://lkml.kernel.org/r/1611035683-12732-1-git-send-email-tiantao6@hisilicon.com

Link: https://lkml.kernel.org/r/1611035683-12732-2-git-send-email-tiantao6@hisilicon.com
Signed-off-by: Tian Tao <tiantao6@hisilicon.com>
Signed-off-by: Nathan Chancellor <natechancellor@gmail.com>
Signed-off-by: Colin Ian King <colin.king@canonical.com>
Reviewed-by: Vitaly Wool <vitaly.wool@konsulko.com>
Acked-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reported-by: Mike Galbraith <efault@gmx.de>
Cc: Barry Song <song.bao.hua@hisilicon.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Seth Jennings <sjenning@redhat.com>
Cc: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

include/linux/zpool.h

@@ -73,6 +73,7 @@ u64 zpool_get_total_size(struct zpool *pool);
  * @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.
@@ -100,6 +101,7 @@ struct zpool_driver {
 	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);
@@ -112,5 +114,6 @@ void zpool_register_driver(struct zpool_driver *driver);
 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

@@ -23,6 +23,7 @@ struct zpool {
 	void *pool;
 	const struct zpool_ops *ops;
 	bool evictable;
+	bool can_sleep_mapped;
 
 	struct list_head list;
 };
@@ -183,6 +184,7 @@ struct zpool *zpool_create_pool(const char *type, const char *name, gfp_t gfp,
 	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);
@@ -393,6 +395,17 @@ 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");
 MODULE_AUTHOR("Dan Streetman <ddstreet@ieee.org>");
 MODULE_DESCRIPTION("Common API for compressed memory storage");

mm/zswap.c

@@ -935,13 +935,19 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
 	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);
 	swpentry = zhdr->swpentry; /* here */
@@ -955,6 +961,7 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
 		/* entry was invalidated */
 		spin_unlock(&tree->lock);
 		zpool_unmap_handle(pool, handle);
+		kfree(tmp);
 		return 0;
 	}
 	spin_unlock(&tree->lock);
@@ -979,6 +986,14 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
 		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);
 		sg_init_table(&output, 1);
@@ -1033,7 +1048,11 @@ static int zswap_writeback_entry(struct zpool *pool, unsigned long handle)
 	spin_unlock(&tree->lock);
 
 end:
+	if (zpool_can_sleep_mapped(pool))
 		zpool_unmap_handle(pool, handle);
+	else
+		kfree(tmp);
+
 	return ret;
 }
 
@@ -1235,7 +1254,7 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset,
 	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;
 
@@ -1253,15 +1272,33 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset,
 		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 */
 	dlen = PAGE_SIZE;
 	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);
 	sg_init_one(&input, src, entry->length);
@@ -1271,7 +1308,11 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset,
 	ret = crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait);
 	mutex_unlock(acomp_ctx->mutex);
 
+	if (zpool_can_sleep_mapped(entry->pool->zpool))
 		zpool_unmap_handle(entry->pool->zpool, entry->handle);
+	else
+		kfree(tmp);
+
 	BUG_ON(ret);
 
 freeentry:
@@ -1279,7 +1320,7 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset,
 	zswap_entry_put(tree, entry);
 	spin_unlock(&tree->lock);
 
-	return 0;
+	return ret;
 }
 
 /* frees an entry in zswap */