From: Jann Horn <jannh@google.com> stable inclusion from stable-v6.6.95 commit af6cfcd0efb7f051af221c418ec8b37a10211947 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/ICIQAH CVE: CVE-2025-38084 Reference: https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id=... -------------------------------- commit 081056dc00a27bccb55ccc3c6f230a3d5fd3f7e0 upstream. Currently, __split_vma() triggers hugetlb page table unsharing through vm_ops->may_split(). This happens before the VMA lock and rmap locks are taken - which is too early, it allows racing VMA-locked page faults in our process and racing rmap walks from other processes to cause page tables to be shared again before we actually perform the split. Fix it by explicitly calling into the hugetlb unshare logic from __split_vma() in the same place where THP splitting also happens. At that point, both the VMA and the rmap(s) are write-locked. An annoying detail is that we can now call into the helper hugetlb_unshare_pmds() from two different locking contexts: 1. from hugetlb_split(), holding: - mmap lock (exclusively) - VMA lock - file rmap lock (exclusively) 2. hugetlb_unshare_all_pmds(), which I think is designed to be able to call us with only the mmap lock held (in shared mode), but currently only runs while holding mmap lock (exclusively) and VMA lock Backporting note: This commit fixes a racy protection that was introduced in commit b30c14cd6102 ("hugetlb: unshare some PMDs when splitting VMAs"); that commit claimed to fix an issue introduced in 5.13, but it should actually also go all the way back. [jannh@google.com: v2] Link: https://lkml.kernel.org/r/20250528-hugetlb-fixes-splitrace-v2-1-1329349bad1a... Link: https://lkml.kernel.org/r/20250528-hugetlb-fixes-splitrace-v2-0-1329349bad1a... Link: https://lkml.kernel.org/r/20250527-hugetlb-fixes-splitrace-v1-1-f4136f5ec58a... Fixes: 39dde65c9940 ("[PATCH] shared page table for hugetlb page") Signed-off-by: Jann Horn <jannh@google.com> Cc: Liam Howlett <liam.howlett@oracle.com> Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Reviewed-by: Oscar Salvador <osalvador@suse.de> Cc: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: <stable@vger.kernel.org> [b30c14cd6102: hugetlb: unshare some PMDs when splitting VMAs] Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> [stable backport: code got moved from mmap.c to vma.c] Signed-off-by: Jann Horn <jannh@google.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Wupeng Ma <mawupeng1@huawei.com> Conflicts: include/linux/hugetlb.h mm/hugetlb.c [Wupeng Ma: context conflict] Signed-off-by: Wupeng Ma <mawupeng1@huawei.com> --- include/linux/hugetlb.h | 3 +++ mm/hugetlb.c | 60 ++++++++++++++++++++++++++++++----------- mm/mmap.c | 6 +++++ 3 files changed, 53 insertions(+), 16 deletions(-) diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h index baa8d4aa009ad..230fd4b2fedf0 100644 --- a/include/linux/hugetlb.h +++ b/include/linux/hugetlb.h @@ -287,6 +287,7 @@ long hugetlb_change_protection(struct vm_area_struct *vma, bool is_hugetlb_entry_migration(pte_t pte); void hugetlb_unshare_all_pmds(struct vm_area_struct *vma); +void hugetlb_split(struct vm_area_struct *vma, unsigned long addr); void enqueue_hugetlb_folio(struct hstate *h, struct folio *folio); struct folio *dequeue_hugetlb_folio_node_exact(struct hstate *h, int nid); @@ -543,6 +544,8 @@ static inline struct folio *alloc_hugetlb_folio_size(int nid, unsigned long size return NULL; } +static inline void hugetlb_split(struct vm_area_struct *vma, unsigned long addr) {} + #endif /* !CONFIG_HUGETLB_PAGE */ /* * hugepages at page global directory. If arch support diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 6120457bd7e3b..b00dda9db0c9f 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -104,7 +104,7 @@ static void hugetlb_vma_lock_free(struct vm_area_struct *vma); static void hugetlb_vma_lock_alloc(struct vm_area_struct *vma); static void __hugetlb_vma_unlock_write_free(struct vm_area_struct *vma); static void hugetlb_unshare_pmds(struct vm_area_struct *vma, - unsigned long start, unsigned long end); + unsigned long start, unsigned long end, bool take_locks); static struct resv_map *vma_resv_map(struct vm_area_struct *vma); static inline bool subpool_is_free(struct hugepage_subpool *spool) @@ -5326,26 +5326,40 @@ static int hugetlb_vm_op_split(struct vm_area_struct *vma, unsigned long addr) { if (addr & ~(huge_page_mask(hstate_vma(vma)))) return -EINVAL; + return 0; +} +void hugetlb_split(struct vm_area_struct *vma, unsigned long addr) +{ /* * PMD sharing is only possible for PUD_SIZE-aligned address ranges * in HugeTLB VMAs. If we will lose PUD_SIZE alignment due to this * split, unshare PMDs in the PUD_SIZE interval surrounding addr now. + * This function is called in the middle of a VMA split operation, with + * MM, VMA and rmap all write-locked to prevent concurrent page table + * walks (except hardware and gup_fast()). */ + vma_assert_write_locked(vma); + i_mmap_assert_write_locked(vma->vm_file->f_mapping); + if (addr & ~PUD_MASK) { - /* - * hugetlb_vm_op_split is called right before we attempt to - * split the VMA. We will need to unshare PMDs in the old and - * new VMAs, so let's unshare before we split. - */ unsigned long floor = addr & PUD_MASK; unsigned long ceil = floor + PUD_SIZE; - if (floor >= vma->vm_start && ceil <= vma->vm_end) - hugetlb_unshare_pmds(vma, floor, ceil); + if (floor >= vma->vm_start && ceil <= vma->vm_end) { + /* + * Locking: + * Use take_locks=false here. + * The file rmap lock is already held. + * The hugetlb VMA lock can't be taken when we already + * hold the file rmap lock, and we don't need it because + * its purpose is to synchronize against concurrent page + * table walks, which are not possible thanks to the + * locks held by our caller. + */ + hugetlb_unshare_pmds(vma, floor, ceil, /* take_locks = */ false); + } } - - return 0; } static unsigned long hugetlb_vm_op_pagesize(struct vm_area_struct *vma) @@ -7780,9 +7794,16 @@ void move_hugetlb_state(struct folio *old_folio, struct folio *new_folio, int re } } +/* + * If @take_locks is false, the caller must ensure that no concurrent page table + * access can happen (except for gup_fast() and hardware page walks). + * If @take_locks is true, we take the hugetlb VMA lock (to lock out things like + * concurrent page fault handling) and the file rmap lock. + */ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, unsigned long start, - unsigned long end) + unsigned long end, + bool take_locks) { struct hstate *h = hstate_vma(vma); unsigned long sz = huge_page_size(h); @@ -7806,8 +7827,12 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, mm, start, end); mmu_notifier_invalidate_range_start(&range); - hugetlb_vma_lock_write(vma); - i_mmap_lock_write(vma->vm_file->f_mapping); + if (take_locks) { + hugetlb_vma_lock_write(vma); + i_mmap_lock_write(vma->vm_file->f_mapping); + } else { + i_mmap_assert_write_locked(vma->vm_file->f_mapping); + } for (address = start; address < end; address += PUD_SIZE) { ptep = hugetlb_walk(vma, address, sz); if (!ptep) @@ -7817,8 +7842,10 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, spin_unlock(ptl); } flush_hugetlb_tlb_range(vma, start, end); - i_mmap_unlock_write(vma->vm_file->f_mapping); - hugetlb_vma_unlock_write(vma); + if (take_locks) { + i_mmap_unlock_write(vma->vm_file->f_mapping); + hugetlb_vma_unlock_write(vma); + } /* * No need to call mmu_notifier_arch_invalidate_secondary_tlbs(), see * Documentation/mm/mmu_notifier.rst. @@ -7833,7 +7860,8 @@ static void hugetlb_unshare_pmds(struct vm_area_struct *vma, void hugetlb_unshare_all_pmds(struct vm_area_struct *vma) { hugetlb_unshare_pmds(vma, ALIGN(vma->vm_start, PUD_SIZE), - ALIGN_DOWN(vma->vm_end, PUD_SIZE)); + ALIGN_DOWN(vma->vm_end, PUD_SIZE), + /* take_locks = */ true); } #ifdef CONFIG_CMA diff --git a/mm/mmap.c b/mm/mmap.c index bd99a80d4a932..6d9e6ab2bb277 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2531,7 +2531,13 @@ int __split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma, init_vma_prep(&vp, vma); vp.insert = new; vma_prepare(&vp); + /* + * Get rid of huge pages and shared page tables straddling the split + * boundary. + */ vma_adjust_trans_huge(vma, vma->vm_start, addr, 0); + if (is_vm_hugetlb_page(vma)) + hugetlb_split(vma, addr); if (vma_is_peer_shared(vma)) vm_object_split(vma, new); -- 2.43.0

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 | 59 +++++++++++++++++++++++++++++++++++++++++------------- 1 file changed, 45 insertions(+), 14 deletions(-) diff --git a/mm/zswap.c b/mm/zswap.c index b1e1100da6f95..a50540bfe0444 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -456,11 +456,12 @@ 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)) { @@ -489,12 +490,15 @@ 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; } @@ -503,17 +507,45 @@ 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 **********************************/ @@ -689,7 +721,7 @@ 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 @@ -727,6 +759,9 @@ 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) @@ -1264,10 +1299,7 @@ bool zswap_store(struct folio *folio) goto freepage; /* 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); sg_set_page(&input, &folio->page, PAGE_SIZE, 0); @@ -1314,7 +1346,7 @@ 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); @@ -1357,7 +1389,7 @@ bool zswap_store(struct folio *folio) return true; put_dstmem: - mutex_unlock(&acomp_ctx->mutex); + acomp_ctx_put_unlock(acomp_ctx); zswap_pool_put(entry->pool); freepage: zswap_entry_cache_free(entry); @@ -1440,20 +1472,19 @@ bool zswap_load(struct folio *folio) zpool_unmap_handle(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); if (crypto_wait_req(crypto_acomp_decompress(acomp_ctx->req), &acomp_ctx->wait)) WARN_ON(1); - mutex_unlock(&acomp_ctx->mutex); if (zpool_can_sleep_mapped(zpool)) zpool_unmap_handle(zpool, entry->handle); else kfree(tmp); + acomp_ctx_put_unlock(acomp_ctx); ret = true; stats: -- 2.43.0