[PATCH 2/2] mm: zswap: use SRCU to synchronize with CPU hotunplug

[Yosry Ahmed <yosryahmed@google.com>]

In zswap_compress() and zswap_decompress(), the per-CPU acomp_ctx of the
current CPU at the beginning of the operation is retrieved and used
throughout.  However, since neither preemption nor migration are disabled,
it is possible that the operation continues on a different CPU.

If the original CPU is hotunplugged while the acomp_ctx is still in use,
we run into a UAF bug as the resources attached to the acomp_ctx are freed
during hotunplug in zswap_cpu_comp_dead().

The problem was introduced in commit 1ec3b5fe6eec ("mm/zswap: move to use
crypto_acomp API for hardware acceleration") when the switch to the
crypto_acomp API was made.  Prior to that, the per-CPU crypto_comp was
retrieved using get_cpu_ptr() which disables preemption and makes sure the
CPU cannot go away from under us.  Preemption cannot be disabled with the
crypto_acomp API as a sleepable context is needed.

Commit 8ba2f844f050 ("mm/zswap: change per-cpu mutex and buffer to
per-acomp_ctx") increased the UAF surface area by making the per-CPU
buffers dynamic, adding yet another resource that can be freed from under
zswap compression/decompression by CPU hotunplug.

There are a few ways to fix this:
(a) Add a refcount for acomp_ctx.
(b) Disable migration while using the per-CPU acomp_ctx.
(c) Use SRCU to wait for other CPUs using the acomp_ctx of the CPU being
hotunplugged. Normal RCU cannot be used as a sleepable context is
required.

Implement (c) since it's simpler than (a), and (b) involves using
migrate_disable() which is apparently undesired (see huge comment in
include/linux/preempt.h).

Fixes: 1ec3b5fe6eec ("mm/zswap: move to use crypto_acomp API for hardware acceleration")
Signed-off-by: Yosry Ahmed <yosryahmed@google.com>
Reported-by: Johannes Weiner <hannes@cmpxchg.org>
Closes: https://lore.kernel.org/lkml/20241113213007.GB1564047@cmpxchg.org/
Reported-by: Sam Sun <samsun1006219@gmail.com>
Closes: https://lore.kernel.org/lkml/CAEkJfYMtSdM5HceNsXUDf5haghD5+o2e7Qv4OcuruL4tPg6OaQ@mail.gmail.com/
---
 mm/zswap.c | 31 ++++++++++++++++++++++++++++---
 1 file changed, 28 insertions(+), 3 deletions(-)

diff --git a/mm/zswap.c b/mm/zswap.c
index f6316b66fb236..4b0eb370823e8 100644
--- a/mm/zswap.c
+++ b/mm/zswap.c
@@ -864,12 +864,22 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node)
 	return ret;
 }
 
+DEFINE_STATIC_SRCU(acomp_srcu);
+
 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);
 
 	if (!IS_ERR_OR_NULL(acomp_ctx)) {
+		/*
+		 * Even though the acomp_ctx should not be currently in use on
+		 * @cpu, it may still be used by compress/decompress operations
+		 * that started on @cpu and migrated to a different CPU. Wait
+		 * for such usages to complete, any news usages would be a bug.
+		 */
+		synchronize_srcu(&acomp_srcu);
+
 		if (!IS_ERR_OR_NULL(acomp_ctx->req))
 			acomp_request_free(acomp_ctx->req);
 		if (!IS_ERR_OR_NULL(acomp_ctx->acomp))
@@ -880,6 +890,18 @@ static int zswap_cpu_comp_dead(unsigned int cpu, struct hlist_node *node)
 	return 0;
 }
 
+static struct crypto_acomp_ctx *acomp_ctx_get_cpu(struct crypto_acomp_ctx __percpu *acomp_ctx,
+						  int *idx)
+{
+	*idx = srcu_read_lock(&acomp_srcu);
+	return raw_cpu_ptr(acomp_ctx);
+}
+
+static void acomp_ctx_put_cpu(int idx)
+{
+	srcu_read_unlock(&acomp_srcu, idx);
+}
+
 static bool zswap_compress(struct page *page, struct zswap_entry *entry,
 			   struct zswap_pool *pool)
 {
@@ -892,9 +914,9 @@ static bool zswap_compress(struct page *page, struct zswap_entry *entry,
 	char *buf;
 	gfp_t gfp;
 	u8 *dst;
+	int idx;
 
-	acomp_ctx = raw_cpu_ptr(pool->acomp_ctx);
-
+	acomp_ctx = acomp_ctx_get_cpu(pool->acomp_ctx, &idx);
 	mutex_lock(&acomp_ctx->mutex);
 
 	dst = acomp_ctx->buffer;
@@ -950,6 +972,7 @@ static bool zswap_compress(struct page *page, struct zswap_entry *entry,
 		zswap_reject_alloc_fail++;
 
 	mutex_unlock(&acomp_ctx->mutex);
+	acomp_ctx_put_cpu(idx);
 	return comp_ret == 0 && alloc_ret == 0;
 }
 
@@ -959,8 +982,9 @@ static void zswap_decompress(struct zswap_entry *entry, struct folio *folio)
 	struct scatterlist input, output;
 	struct crypto_acomp_ctx *acomp_ctx;
 	u8 *src;
+	int idx;
 
-	acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx);
+	acomp_ctx = acomp_ctx_get_cpu(entry->pool->acomp_ctx, &idx);
 	mutex_lock(&acomp_ctx->mutex);
 
 	src = zpool_map_handle(zpool, entry->handle, ZPOOL_MM_RO);
@@ -990,6 +1014,7 @@ static void zswap_decompress(struct zswap_entry *entry, struct folio *folio)
 
 	if (src != acomp_ctx->buffer)
 		zpool_unmap_handle(zpool, entry->handle);
+	acomp_ctx_put_cpu(idx);
 }
 
 /*********************************
-- 
2.47.1.613.gc27f4b7a9f-goog