mainline inclusion from mainline-v6.16-rc1 commit 2b12d06c37fd3a394376f42f026a7478d826ed63 category: bugfix bugzilla: https://gitee.com/openeuler/kernel/issues/ICIYRH Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i... -------------------------------- Patch series "Fix uprobe pte be overwritten when expanding vma". This patch (of 4): We encountered a BUG alert triggered by Syzkaller as follows: BUG: Bad rss-counter state mm:00000000b4a60fca type:MM_ANONPAGES val:1 And we can reproduce it with the following steps: 1. register uprobe on file at zero offset 2. mmap the file at zero offset: addr1 = mmap(NULL, 2 * 4096, PROT_NONE, MAP_PRIVATE, fd, 0); 3. mremap part of vma1 to new vma2: addr2 = mremap(addr1, 4096, 2 * 4096, MREMAP_MAYMOVE); 4. mremap back to orig addr1: mremap(addr2, 4096, 4096, MREMAP_MAYMOVE | MREMAP_FIXED, addr1); In step 3, the vma1 range [addr1, addr1 + 4096] will be remap to new vma2 with range [addr2, addr2 + 8192], and remap uprobe anon page from the vma1 to vma2, then unmap the vma1 range [addr1, addr1 + 4096]. In step 4, the vma2 range [addr2, addr2 + 4096] will be remap back to the addr range [addr1, addr1 + 4096]. Since the addr range [addr1 + 4096, addr1 + 8192] still maps the file, it will take vma_merge_new_range to expand the range, and then do uprobe_mmap in vma_complete. Since the merged vma pgoff is also zero offset, it will install uprobe anon page to the merged vma. However, the upcomming move_page_tables step, which use set_pte_at to remap the vma2 uprobe pte to the merged vma, will overwrite the newly uprobe pte in the merged vma, and lead that pte to be orphan. Since the uprobe pte will be remapped to the merged vma, we can remove the unnecessary uprobe_mmap upon merged vma. This problem was first found in linux-6.6.y and also exists in the community syzkaller: https://lore.kernel.org/all/000000000000ada39605a5e71711@google.com/T/ Link: https://lkml.kernel.org/r/20250529155650.4017699-1-pulehui@huaweicloud.com Link: https://lkml.kernel.org/r/20250529155650.4017699-2-pulehui@huaweicloud.com Fixes: 2b1444983508 ("uprobes, mm, x86: Add the ability to install and remove uprobes breakpoints") Signed-off-by: Pu Lehui <pulehui@huawei.com> Suggested-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Jann Horn <jannh@google.com> Cc: Liam Howlett <liam.howlett@oracle.com> Cc: "Masami Hiramatsu (Google)" <mhiramat@kernel.org> Cc: Oleg Nesterov <oleg@redhat.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Conflicts: fs/userfaultfd.c include/linux/mm.h mm/madvise.c mm/mempolicy.c mm/mlock.c mm/mmap.c mm/mprotect.c mm/vma.h mm/vma.c [The conflicts were due to refactor commit 440703e082b9c and 2f1c6611b0a8] Signed-off-by: Pu Lehui <pulehui@huawei.com> --- fs/userfaultfd.c | 6 +++--- include/linux/mm.h | 6 +++--- mm/madvise.c | 2 +- mm/mempolicy.c | 2 +- mm/mlock.c | 2 +- mm/mmap.c | 46 ++++++++++++++++++++++++++++++++++------------ mm/mprotect.c | 2 +- 7 files changed, 44 insertions(+), 22 deletions(-) diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c index 803c61f66d54..3e11e9763527 100644 --- a/fs/userfaultfd.c +++ b/fs/userfaultfd.c @@ -925,7 +925,7 @@ static int userfaultfd_release(struct inode *inode, struct file *file) new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), - NULL_VM_UFFD_CTX); + NULL_VM_UFFD_CTX, false); if (prev) vma = prev; else @@ -1492,7 +1492,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx, prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), - ((struct vm_userfaultfd_ctx){ ctx })); + ((struct vm_userfaultfd_ctx){ ctx }), false); if (prev) { vma = prev; goto next; @@ -1654,7 +1654,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx, prev = vma_merge(mm, prev, start, vma_end, new_flags, vma->anon_vma, vma->vm_file, vma->vm_pgoff, vma_policy(vma), - NULL_VM_UFFD_CTX); + NULL_VM_UFFD_CTX, false); if (prev) { vma = prev; goto next; diff --git a/include/linux/mm.h b/include/linux/mm.h index 67e299374ac8..8cae7fb6542a 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2367,16 +2367,16 @@ void anon_vma_interval_tree_verify(struct anon_vma_chain *node); extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin); extern int __vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert, - struct vm_area_struct *expand); + struct vm_area_struct *expand, bool skip_vma_uprobe); static inline int vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert) { - return __vma_adjust(vma, start, end, pgoff, insert, NULL); + return __vma_adjust(vma, start, end, pgoff, insert, NULL, false); } extern struct vm_area_struct *vma_merge(struct mm_struct *, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *, struct file *, pgoff_t, - struct mempolicy *, struct vm_userfaultfd_ctx); + struct mempolicy *, struct vm_userfaultfd_ctx, bool skip_vma_uprobe); extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *); extern int __split_vma(struct mm_struct *, struct vm_area_struct *, unsigned long addr, int new_below); diff --git a/mm/madvise.c b/mm/madvise.c index 263c2c68b0de..0670786a23a5 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -145,7 +145,7 @@ static long madvise_behavior(struct vm_area_struct *vma, pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *prev = vma_merge(mm, *prev, start, end, new_flags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx); + vma->vm_userfaultfd_ctx, false); if (*prev) { vma = *prev; goto success; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index e8c82f3235e2..882310ef3d93 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -818,7 +818,7 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, ((vmstart - vma->vm_start) >> PAGE_SHIFT); prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, - new_pol, vma->vm_userfaultfd_ctx); + new_pol, vma->vm_userfaultfd_ctx, false); if (prev) { vma = prev; goto replace; diff --git a/mm/mlock.c b/mm/mlock.c index d9040aea2be0..cb4e1207169a 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -540,7 +540,7 @@ static int mlock_fixup(struct vm_area_struct *vma, struct vm_area_struct **prev, pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *prev = vma_merge(mm, *prev, start, end, newflags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx); + vma->vm_userfaultfd_ctx, false); if (*prev) { vma = *prev; goto success; diff --git a/mm/mmap.c b/mm/mmap.c index ad643f9dd3a4..19ec00c197d7 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -684,10 +684,13 @@ static inline void __vma_unlink_prev(struct mm_struct *mm, * The following helper function should be used when such adjustments * are necessary. The "insert" vma (if any) is to be inserted * before we drop the necessary locks. + * + * @skip_vma_uprobe: only valid for copy_vma process, others please + * mark it as false. */ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, unsigned long end, pgoff_t pgoff, struct vm_area_struct *insert, - struct vm_area_struct *expand) + struct vm_area_struct *expand, bool skip_vma_uprobe) { struct mm_struct *mm = vma->vm_mm; struct vm_area_struct *next = vma->vm_next, *orig_vma = vma; @@ -894,10 +897,12 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start, i_mmap_unlock_write(mapping); if (root) { - uprobe_mmap(vma); + if (!skip_vma_uprobe) { + uprobe_mmap(vma); - if (adjust_next) - uprobe_mmap(next); + if (adjust_next) + uprobe_mmap(next); + } } if (remove_next) { @@ -1102,13 +1107,17 @@ can_vma_merge_after(struct vm_area_struct *vma, unsigned long vm_flags, * or other rmap walkers (if working on addresses beyond the "end" * parameter) may establish ptes with the wrong permissions of NNNN * instead of the right permissions of XXXX. + * + * @skip_vma_uprobe: only valid for copy_vma process, others please + * mark it as false. */ struct vm_area_struct *vma_merge(struct mm_struct *mm, struct vm_area_struct *prev, unsigned long addr, unsigned long end, unsigned long vm_flags, struct anon_vma *anon_vma, struct file *file, pgoff_t pgoff, struct mempolicy *policy, - struct vm_userfaultfd_ctx vm_userfaultfd_ctx) + struct vm_userfaultfd_ctx vm_userfaultfd_ctx, + bool skip_vma_uprobe) { pgoff_t pglen = (end - addr) >> PAGE_SHIFT; struct vm_area_struct *area, *next; @@ -1160,10 +1169,11 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, /* cases 1, 6 */ err = __vma_adjust(prev, prev->vm_start, next->vm_end, prev->vm_pgoff, NULL, - prev); + prev, skip_vma_uprobe); } else /* cases 2, 5, 7 */ err = __vma_adjust(prev, prev->vm_start, - end, prev->vm_pgoff, NULL, prev); + end, prev->vm_pgoff, NULL, + prev, skip_vma_uprobe); if (err) return NULL; khugepaged_enter_vma_merge(prev, vm_flags); @@ -1180,10 +1190,12 @@ struct vm_area_struct *vma_merge(struct mm_struct *mm, vm_userfaultfd_ctx)) { if (prev && addr < prev->vm_end) /* case 4 */ err = __vma_adjust(prev, prev->vm_start, - addr, prev->vm_pgoff, NULL, next); + addr, prev->vm_pgoff, NULL, + next, skip_vma_uprobe); else { /* cases 3, 8 */ err = __vma_adjust(area, addr, next->vm_end, - next->vm_pgoff - pglen, NULL, next); + next->vm_pgoff - pglen, NULL, + next, skip_vma_uprobe); /* * In case 3 area is already equal to next and * this is a noop, but in case 8 "area" has @@ -1974,7 +1986,7 @@ static unsigned long __mmap_region(struct mm_struct *mm, struct file *file, * Can we just expand an old mapping? */ vma = vma_merge(mm, prev, addr, addr + len, vm_flags, - NULL, file, pgoff, NULL, NULL_VM_UFFD_CTX); + NULL, file, pgoff, NULL, NULL_VM_UFFD_CTX, false); if (vma) goto out; @@ -3381,7 +3393,7 @@ static int do_brk_flags(unsigned long addr, unsigned long len, unsigned long fla /* Can we just expand an old private anonymous mapping? */ vma = vma_merge(mm, prev, addr, addr + len, flags, - NULL, NULL, pgoff, NULL, NULL_VM_UFFD_CTX); + NULL, NULL, pgoff, NULL, NULL_VM_UFFD_CTX, false); if (vma) goto out; @@ -3566,6 +3578,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, struct vm_area_struct *new_vma, *prev; struct rb_node **rb_link, *rb_parent; bool faulted_in_anon_vma = true; + bool skip_vma_uprobe = false; /* * If anonymous vma has not yet been faulted, update new pgoff @@ -3578,9 +3591,18 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap, if (find_vma_links(mm, addr, addr + len, &prev, &rb_link, &rb_parent)) return NULL; /* should never get here */ + + /* + * If the VMA we are copying might contain a uprobe PTE, ensure + * that we do not establish one upon merge. Otherwise, when mremap() + * moves page tables, it will orphan the newly created PTE. + */ + if (vma->vm_file) + skip_vma_uprobe = true; + new_vma = vma_merge(mm, prev, addr, addr + len, vma->vm_flags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx); + vma->vm_userfaultfd_ctx, skip_vma_uprobe); if (new_vma) { /* * Source vma may have been merged into new_vma diff --git a/mm/mprotect.c b/mm/mprotect.c index 86837f25055b..4c7370fd3e90 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -432,7 +432,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT); *pprev = vma_merge(mm, *pprev, start, end, newflags, vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma), - vma->vm_userfaultfd_ctx); + vma->vm_userfaultfd_ctx, false); if (*pprev) { vma = *pprev; VM_WARN_ON((vma->vm_flags ^ newflags) & ~VM_SOFTDIRTY); -- 2.34.1