Merge: CVE-2025-21693 mm: zswap: properly synchronize freeing resources during CPU hotunplug

MR: https://gitlab.com/redhat/centos-stream/src/kernel/centos-stream-9/-/merge_requests/6880

JIRA: https://issues.redhat.com/browse/RHEL-78678
CVE: CVE-2025-21693

Backport of upstream commit 12dcb0e ("mm: zswap: properly synchronize freeing resources during CPU hotunplug")
and its follow-up fixes to address the tagged CVE.

Signed-off-by: Rafael Aquini <raquini@redhat.com>

Approved-by: Herton R. Krzesinski <herton@redhat.com>
Approved-by: Aristeu Rozanski <arozansk@redhat.com>
Approved-by: CKI KWF Bot <cki-ci-bot+kwf-gitlab-com@redhat.com>

Merged-by: Augusto Caringi <acaringi@redhat.com>

Author: caringi

mm/zswap.c

@@ -710,35 +710,41 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 {
 	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
 	struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu);
-	struct crypto_acomp *acomp;
-	struct acomp_req *req;
+	struct crypto_acomp *acomp = NULL;
+	struct acomp_req *req = NULL;
+	u8 *buffer = NULL;
 	int ret;
 
-	mutex_init(&acomp_ctx->mutex);
-
-	acomp_ctx->buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
-	if (!acomp_ctx->buffer)
-		return -ENOMEM;
+	buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu));
+	if (!buffer) {
+		ret = -ENOMEM;
+		goto fail;
+	}
 
 	acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu));
 	if (IS_ERR(acomp)) {
 		pr_err("could not alloc crypto acomp %s : %ld\n",
 				pool->tfm_name, PTR_ERR(acomp));
 		ret = PTR_ERR(acomp);
-		goto acomp_fail;
+		goto fail;
 	}
-	acomp_ctx->acomp = acomp;
 
-	req = acomp_request_alloc(acomp_ctx->acomp);
+	req = acomp_request_alloc(acomp);
 	if (!req) {
 		pr_err("could not alloc crypto acomp_request %s\n",
 		       pool->tfm_name);
 		ret = -ENOMEM;
-		goto req_fail;
+		goto fail;
 	}
-	acomp_ctx->req = req;
 
+	/*
+	 * Only hold the mutex after completing allocations, otherwise we may
+	 * recurse into zswap through reclaim and attempt to hold the mutex
+	 * again resulting in a deadlock.
+	 */
+	mutex_lock(&acomp_ctx->mutex);
 	crypto_init_wait(&acomp_ctx->wait);
+
 	/*
 	 * if the backend of acomp is async zip, crypto_req_done() will wakeup
 	 * crypto_wait_req(); if the backend of acomp is scomp, the callback
@@ -747,31 +753,77 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 	acomp_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
 				   crypto_req_done, &acomp_ctx->wait);
 
+	acomp_ctx->buffer = buffer;
+	acomp_ctx->acomp = acomp;
+	acomp_ctx->req = req;
+	mutex_unlock(&acomp_ctx->mutex);
 	return 0;
 
-req_fail:
-	crypto_free_acomp(acomp_ctx->acomp);
-acomp_fail:
-	kfree(acomp_ctx->buffer);
+fail:
+	if (acomp)
+		crypto_free_acomp(acomp);
+	kfree(buffer);
 	return ret;
 }
 
 static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node)
 {
 	struct zswap_pool *pool = hlist_entry(node, struct zswap_pool, node);
 	struct crypto_acomp_ctx *acomp_ctx = per_cpu_ptr(pool->acomp_ctx, cpu);
+	struct acomp_req *req;
+	struct crypto_acomp *acomp;
+	u8 *buffer;
 
-	if (!IS_ERR_OR_NULL(acomp_ctx)) {
-		if (!IS_ERR_OR_NULL(acomp_ctx->req))
-			acomp_request_free(acomp_ctx->req);
-		if (!IS_ERR_OR_NULL(acomp_ctx->acomp))
-			crypto_free_acomp(acomp_ctx->acomp);
-		kfree(acomp_ctx->buffer);
-	}
+	if (IS_ERR_OR_NULL(acomp_ctx))
+		return 0;
+
+	mutex_lock(&acomp_ctx->mutex);
+	req = acomp_ctx->req;
+	acomp = acomp_ctx->acomp;
+	buffer = acomp_ctx->buffer;
+	acomp_ctx->req = NULL;
+	acomp_ctx->acomp = NULL;
+	acomp_ctx->buffer = NULL;
+	mutex_unlock(&acomp_ctx->mutex);
+
+	/*
+	 * Do the actual freeing after releasing the mutex to avoid subtle
+	 * locking dependencies causing deadlocks.
+	 */
+	if (!IS_ERR_OR_NULL(req))
+		acomp_request_free(req);
+	if (!IS_ERR_OR_NULL(acomp))
+		crypto_free_acomp(acomp);
+	kfree(buffer);
 
 	return 0;
 }
 
+static struct crypto_acomp_ctx *acomp_ctx_get_cpu_lock(struct zswap_pool *pool)
+{
+	struct crypto_acomp_ctx *acomp_ctx;
+
+	for (;;) {
+		acomp_ctx = raw_cpu_ptr(pool->acomp_ctx);
+		mutex_lock(&acomp_ctx->mutex);
+		if (likely(acomp_ctx->req))
+			return acomp_ctx;
+		/*
+		 * It is possible that we were migrated to a different CPU after
+		 * getting the per-CPU ctx but before the mutex was acquired. If
+		 * the old CPU got offlined, zswap_cpu_comp_dead() could have
+		 * already freed ctx->req (among other things) and set it to
+		 * NULL. Just try again on the new CPU that we ended up on.
+		 */
+		mutex_unlock(&acomp_ctx->mutex);
+	}
+}
+
+static void acomp_ctx_put_unlock(struct crypto_acomp_ctx *acomp_ctx)
+{
+	mutex_unlock(&acomp_ctx->mutex);
+}
+
 /*********************************
 * pool functions
 **********************************/
@@ -1029,7 +1081,7 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 	struct zswap_pool *pool;
 	char name[38]; /* 'zswap' + 32 char (max) num + \0 */
 	gfp_t gfp = __GFP_NORETRY | __GFP_NOWARN | __GFP_KSWAPD_RECLAIM;
-	int ret;
+	int ret, cpu;
 
 	if (!zswap_has_pool) {
 		/* if either are unset, pool initialization failed, and we
@@ -1067,6 +1119,9 @@ static struct zswap_pool *zswap_pool_create(char *type, char *compressor)
 		goto error;
 	}
 
+	for_each_possible_cpu(cpu)
+		mutex_init(&per_cpu_ptr(pool->acomp_ctx, cpu)->mutex);
+
 	ret = cpuhp_state_add_instance(CPUHP_MM_ZSWP_POOL_PREPARE,
 				       &pool->node);
 	if (ret)
@@ -1376,9 +1431,7 @@ static void __zswap_load(struct zswap_entry *entry, struct page *page)
 	struct crypto_acomp_ctx *acomp_ctx;
 	u8 *src;
 
-	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
-	mutex_lock(&acomp_ctx->mutex);
-
+	acomp_ctx = acomp_ctx_get_cpu_lock(entry->pool);
 	src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
 	if (!zpool_can_sleep_mapped(zpool)) {
 		memcpy(acomp_ctx->buffer, src, entry->length);
@@ -1392,10 +1445,10 @@ static void __zswap_load(struct zswap_entry *entry, struct page *page)
 	acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, PAGE_SIZE);
 	BUG_ON(crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait));
 	BUG_ON(acomp_ctx->req->dlen != PAGE_SIZE);
-	mutex_unlock(&acomp_ctx->mutex);
 
 	if (zpool_can_sleep_mapped(zpool))
 		zpool_unmap_handle(zpool, entry->handle);
+	acomp_ctx_put_unlock(acomp_ctx);
 }
 
 /*********************************
@@ -1612,9 +1665,7 @@ bool zswap_store(struct folio *folio)
 	}
 
 	/* compress */
-	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
-
-	mutex_lock(&acomp_ctx->mutex);
+	acomp_ctx = acomp_ctx_get_cpu_lock(entry->pool);
 
 	dst = acomp_ctx->buffer;
 	sg_init_table(&input, 1);
@@ -1662,7 +1713,7 @@ bool zswap_store(struct folio *folio)
 	buf = zpool_map_handle(zpool, handle, ZPOOL_MM_WO);
 	memcpy(buf, dst, dlen);
 	zpool_unmap_handle(zpool, handle);
-	mutex_unlock(&acomp_ctx->mutex);
+	acomp_ctx_put_unlock(acomp_ctx);
 
 	/* populate entry */
 	entry->swpentry = swp_entry(type, offset);
@@ -1705,7 +1756,7 @@ bool zswap_store(struct folio *folio)
 	return true;
 
 put_dstmem:
-	mutex_unlock(&acomp_ctx->mutex);
+	acomp_ctx_put_unlock(acomp_ctx);
 put_pool:
 	zswap_pool_put(entry->pool);
 freepage: