From: Yosry Ahmed <yosryahmed@google.com> mainline inclusion from mainline-v6.13 commit 12dcb0ef540629a281533f9dedc1b6b8e14cfb65 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IBLDIU CVE: CVE-2025-21693 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- 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 some of the resources attached to the acomp_ctx are freed during hotunplug in zswap_cpu_comp_dead() (i.e. acomp_ctx.buffer, acomp_ctx.req, or acomp_ctx.acomp). 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. Use the acomp_ctx.mutex to synchronize CPU hotplug callbacks allocating and freeing resources with compression/decompression paths. Make sure that acomp_ctx.req is NULL when the resources are freed. In the compression/decompression paths, check if acomp_ctx.req is NULL after acquiring the mutex (meaning the CPU was offlined) and retry on the new CPU. The initialization of acomp_ctx.mutex is moved from the CPU hotplug callback to the pool initialization where it belongs (where the mutex is allocated). In addition to adding clarity, this makes sure that CPU hotplug cannot reinitialize a mutex that is already locked by compression/decompression. Previously a fix was attempted by holding cpus_read_lock() [1]. This would have caused a potential deadlock as it is possible for code already holding the lock to fall into reclaim and enter zswap (causing a deadlock). A fix was also attempted using SRCU for synchronization, but Johannes pointed out that synchronize_srcu() cannot be used in CPU hotplug notifiers [2]. Alternative fixes that were considered/attempted and could have worked: - Refcounting the per-CPU acomp_ctx. This involves complexity in handling the race between the refcount dropping to zero in zswap_[de]compress() and the refcount being re-initialized when the CPU is onlined. - Disabling migration before getting the per-CPU acomp_ctx [3], but that's discouraged and is a much bigger hammer than needed, and could result in subtle performance issues. [1]https://lkml.kernel.org/20241219212437.2714151-1-yosryahmed@google.com/ [2]https://lkml.kernel.org/20250107074724.1756696-2-yosryahmed@google.com/ [3]https://lkml.kernel.org/20250107222236.2715883-2-yosryahmed@google.com/ [yosryahmed@google.com: remove comment] Link: https://lkml.kernel.org/r/CAJD7tkaxS1wjn+swugt8QCvQ-rVF5RZnjxwPGX17k8x9zSMan... Link: https://lkml.kernel.org/r/20250108222441.3622031-1-yosryahmed@google.com 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+o2e7Qv4OcuruL4tPg... Cc: Barry Song <baohua@kernel.org> Cc: Chengming Zhou <chengming.zhou@linux.dev> Cc: Kanchana P Sridhar <kanchana.p.sridhar@intel.com> Cc: Nhat Pham <nphamcs@gmail.com> Cc: Vitaly Wool <vitalywool@gmail.com> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Conflicts: mm/zswap.c [Ma Wupeng: heavily conflicts] Signed-off-by: Ma Wupeng <mawupeng1@huawei.com> --- mm/zswap.c | 58 ++++++++++++++++++++++++++++++++++++++++++------------ 1 file changed, 45 insertions(+), 13 deletions(-) diff --git a/mm/zswap.c b/mm/zswap.c index 5e495406555b..bbaa62c4b7c5 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -410,11 +410,12 @@ static int zswap_cpu_comp_prepare(unsigned int cpu, struct hlist_node *node) struct acomp_req *req; int ret; - mutex_init(&acomp_ctx->mutex); - + mutex_lock(&acomp_ctx->mutex); acomp_ctx->buffer = kmalloc_node(PAGE_SIZE * 2, GFP_KERNEL, cpu_to_node(cpu)); - if (!acomp_ctx->buffer) - return -ENOMEM; + if (!acomp_ctx->buffer) { + ret = -ENOMEM; + goto buffer_fail; + } acomp = crypto_alloc_acomp_node(pool->tfm_name, 0, 0, cpu_to_node(cpu)); if (IS_ERR(acomp)) { @@ -443,12 +444,15 @@ 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); + mutex_unlock(&acomp_ctx->mutex); return 0; req_fail: crypto_free_acomp(acomp_ctx->acomp); acomp_fail: kfree(acomp_ctx->buffer); +buffer_fail: + mutex_unlock(&acomp_ctx->mutex); return ret; } @@ -457,17 +461,45 @@ 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); + mutex_lock(&acomp_ctx->mutex); if (!IS_ERR_OR_NULL(acomp_ctx)) { if (!IS_ERR_OR_NULL(acomp_ctx->req)) acomp_request_free(acomp_ctx->req); + acomp_ctx->req = NULL; if (!IS_ERR_OR_NULL(acomp_ctx->acomp)) crypto_free_acomp(acomp_ctx->acomp); kfree(acomp_ctx->buffer); } + mutex_unlock(&acomp_ctx->mutex); 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 **********************************/ @@ -559,7 +591,7 @@ 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 @@ -594,6 +626,9 @@ 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) @@ -1140,9 +1175,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, } /* 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); @@ -1193,7 +1226,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, memcpy(buf, &zhdr, hlen); memcpy(buf + hlen, dst, dlen); zpool_unmap_handle(entry->pool->zpool, handle); - mutex_unlock(&acomp_ctx->mutex); + acomp_ctx_put_unlock(acomp_ctx); /* populate entry */ entry->offset = offset; @@ -1221,7 +1254,7 @@ static int zswap_frontswap_store(unsigned type, pgoff_t offset, return 0; put_dstmem: - mutex_unlock(&acomp_ctx->mutex); + acomp_ctx_put_unlock(acomp_ctx); zswap_pool_put(entry->pool); freepage: zswap_entry_cache_free(entry); @@ -1282,19 +1315,18 @@ static int zswap_frontswap_load(unsigned type, pgoff_t offset, zpool_unmap_handle(entry->pool->zpool, entry->handle); } - acomp_ctx = raw_cpu_ptr(entry->pool->acomp_ctx); - mutex_lock(&acomp_ctx->mutex); + acomp_ctx = acomp_ctx_get_cpu_lock(entry->pool); sg_init_one(&input, src, entry->length); sg_init_table(&output, 1); sg_set_page(&output, page, PAGE_SIZE, 0); acomp_request_set_params(acomp_ctx->req, &input, &output, entry->length, dlen); 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); + acomp_ctx_put_unlock(acomp_ctx); BUG_ON(ret); -- 2.43.0