From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> stable inclusion from stable-v5.10.231 commit f68a0236337e39b77e0c4976fb80f0b680d8d652 category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IB7051 CVE: CVE-2024-53096 Reference: https://lore.kernel.org/linux-mm/99f72d6dc52835126ca6d2e79732d397f6bfa20b.17... -------------------------------- [ Upstream commit 3dd6ed34ce1f2356a77fb88edafb5ec96784e3cf ] Patch series "fix error handling in mmap_region() and refactor (hotfixes)", v4. mmap_region() is somewhat terrifying, with spaghetti-like control flow and numerous means by which issues can arise and incomplete state, memory leaks and other unpleasantness can occur. A large amount of the complexity arises from trying to handle errors late in the process of mapping a VMA, which forms the basis of recently observed issues with resource leaks and observable inconsistent state. This series goes to great lengths to simplify how mmap_region() works and to avoid unwinding errors late on in the process of setting up the VMA for the new mapping, and equally avoids such operations occurring while the VMA is in an inconsistent state. The patches in this series comprise the minimal changes required to resolve existing issues in mmap_region() error handling, in order that they can be hotfixed and backported. There is additionally a follow up series which goes further, separated out from the v1 series and sent and updated separately. This patch (of 5): After an attempted mmap() fails, we are no longer in a situation where we can safely interact with VMA hooks. This is currently not enforced, meaning that we need complicated handling to ensure we do not incorrectly call these hooks. We can avoid the whole issue by treating the VMA as suspect the moment that the file->f_ops->mmap() function reports an error by replacing whatever VMA operations were installed with a dummy empty set of VMA operations. We do so through a new helper function internal to mm - mmap_file() - which is both more logically named than the existing call_mmap() function and correctly isolates handling of the vm_op reassignment to mm. All the existing invocations of call_mmap() outside of mm are ultimately nested within the call_mmap() from mm, which we now replace. It is therefore safe to leave call_mmap() in place as a convenience function (and to avoid churn). The invokers are: ovl_file_operations -> mmap -> ovl_mmap() -> backing_file_mmap() coda_file_operations -> mmap -> coda_file_mmap() shm_file_operations -> shm_mmap() shm_file_operations_huge -> shm_mmap() dma_buf_fops -> dma_buf_mmap_internal -> i915_dmabuf_ops -> i915_gem_dmabuf_mmap() None of these callers interact with vm_ops or mappings in a problematic way on error, quickly exiting out. Link: https://lkml.kernel.org/r/cover.1730224667.git.lorenzo.stoakes@oracle.com Link: https://lkml.kernel.org/r/d41fd763496fd0048a962f3fd9407dc72dd4fd86.173022466... Fixes: deb0f6562884 ("mm/mmap: undo ->mmap() when arch_validate_flags() fails") Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Reported-by: Jann Horn <jannh@google.com> Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Reviewed-by: Jann Horn <jannh@google.com> Cc: Andreas Larsson <andreas@gaisler.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: David S. Miller <davem@davemloft.net> Cc: Helge Deller <deller@gmx.de> Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Mark Brown <broonie@kernel.org> Cc: Peter Xu <peterx@redhat.com> Cc: Will Deacon <will@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Ma Wupeng <mawupeng1@huawei.com> --- mm/internal.h | 12 ++++++++++++ mm/mmap.c | 4 ++-- mm/nommu.c | 4 ++-- mm/util.c | 18 ++++++++++++++++++ 4 files changed, 34 insertions(+), 4 deletions(-) diff --git a/mm/internal.h b/mm/internal.h index 0c4e6959b83c..6897a119a383 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -49,6 +49,18 @@ void page_writeback_init(void); +/* + * This is a file-backed mapping, and is about to be memory mapped - invoke its + * mmap hook and safely handle error conditions. On error, VMA hooks will be + * mutated. + * + * @file: File which backs the mapping. + * @vma: VMA which we are mapping. + * + * Returns: 0 if success, error otherwise. + */ +int mmap_file(struct file *file, struct vm_area_struct *vma); + vm_fault_t do_swap_page(struct vm_fault *vmf); void free_pgtables(struct mmu_gather *tlb, struct vm_area_struct *start_vma, diff --git a/mm/mmap.c b/mm/mmap.c index d21e50908d59..d4e1099be6e0 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1865,7 +1865,7 @@ static unsigned long __mmap_region(struct mm_struct *mm, struct file *file, * new file must not have been exposed to user-space, yet. */ vma->vm_file = get_file(file); - error = call_mmap(file, vma); + error = mmap_file(file, vma); if (error) goto unmap_and_free_vma; @@ -1880,7 +1880,7 @@ static unsigned long __mmap_region(struct mm_struct *mm, struct file *file, addr = vma->vm_start; - /* If vm_flags changed after call_mmap(), we should try merge vma again + /* If vm_flags changed after mmap_file(), we should try merge vma again * as we may succeed this time. */ if (unlikely(vm_flags != vma->vm_flags && prev)) { diff --git a/mm/nommu.c b/mm/nommu.c index 0faf39b32cdb..fdacc3d119c3 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -955,7 +955,7 @@ static int do_mmap_shared_file(struct vm_area_struct *vma) { int ret; - ret = call_mmap(vma->vm_file, vma); + ret = mmap_file(vma->vm_file, vma); if (ret == 0) { vma->vm_region->vm_top = vma->vm_region->vm_end; return 0; @@ -986,7 +986,7 @@ static int do_mmap_private(struct vm_area_struct *vma, * - VM_MAYSHARE will be set if it may attempt to share */ if (capabilities & NOMMU_MAP_DIRECT) { - ret = call_mmap(vma->vm_file, vma); + ret = mmap_file(vma->vm_file, vma); if (ret == 0) { /* shouldn't return success if we're not sharing */ BUG_ON(!(vma->vm_flags & VM_MAYSHARE)); diff --git a/mm/util.c b/mm/util.c index b2e0ae3c65aa..154335493dee 100644 --- a/mm/util.c +++ b/mm/util.c @@ -1079,3 +1079,21 @@ int __weak memcmp_pages(struct page *page1, struct page *page2) kunmap_atomic(addr1); return ret; } + +int mmap_file(struct file *file, struct vm_area_struct *vma) +{ + static const struct vm_operations_struct dummy_vm_ops = {}; + int err = call_mmap(file, vma); + + if (likely(!err)) + return 0; + + /* + * OK, we tried to call the file hook for mmap(), but an error + * arose. The mapping is in an inconsistent state and we most not invoke + * any further hooks on it. + */ + vma->vm_ops = &dummy_vm_ops; + + return err; +} -- 2.43.0

From: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> stable inclusion from stable-v5.10.231 commit 43323a4e5b3f8ccc08e2f835abfdc7ee9da8f6ed category: bugfix bugzilla: https://gitee.com/src-openeuler/kernel/issues/IB7051 CVE: CVE-2024-53096 Reference: https://lore.kernel.org/linux-mm/99f72d6dc52835126ca6d2e79732d397f6bfa20b.17... -------------------------------- [ Upstream commit 5de195060b2e251a835f622759550e6202167641 ] The mmap_region() function is somewhat terrifying, with spaghetti-like control flow and numerous means by which issues can arise and incomplete state, memory leaks and other unpleasantness can occur. A large amount of the complexity arises from trying to handle errors late in the process of mapping a VMA, which forms the basis of recently observed issues with resource leaks and observable inconsistent state. Taking advantage of previous patches in this series we move a number of checks earlier in the code, simplifying things by moving the core of the logic into a static internal function __mmap_region(). Doing this allows us to perform a number of checks up front before we do any real work, and allows us to unwind the writable unmap check unconditionally as required and to perform a CONFIG_DEBUG_VM_MAPLE_TREE validation unconditionally also. We move a number of things here: 1. We preallocate memory for the iterator before we call the file-backed memory hook, allowing us to exit early and avoid having to perform complicated and error-prone close/free logic. We carefully free iterator state on both success and error paths. 2. The enclosing mmap_region() function handles the mapping_map_writable() logic early. Previously the logic had the mapping_map_writable() at the point of mapping a newly allocated file-backed VMA, and a matching mapping_unmap_writable() on success and error paths. We now do this unconditionally if this is a file-backed, shared writable mapping. If a driver changes the flags to eliminate VM_MAYWRITE, however doing so does not invalidate the seal check we just performed, and we in any case always decrement the counter in the wrapper. We perform a debug assert to ensure a driver does not attempt to do the opposite. 3. We also move arch_validate_flags() up into the mmap_region() function. This is only relevant on arm64 and sparc64, and the check is only meaningful for SPARC with ADI enabled. We explicitly add a warning for this arch if a driver invalidates this check, though the code ought eventually to be fixed to eliminate the need for this. With all of these measures in place, we no longer need to explicitly close the VMA on error paths, as we place all checks which might fail prior to a call to any driver mmap hook. This eliminates an entire class of errors, makes the code easier to reason about and more robust. Link: https://lkml.kernel.org/r/6e0becb36d2f5472053ac5d544c0edfe9b899e25.173022466... Fixes: deb0f6562884 ("mm/mmap: undo ->mmap() when arch_validate_flags() fails") Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Reported-by: Jann Horn <jannh@google.com> Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com> Reviewed-by: Vlastimil Babka <vbabka@suse.cz> Tested-by: Mark Brown <broonie@kernel.org> Cc: Andreas Larsson <andreas@gaisler.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: David S. Miller <davem@davemloft.net> Cc: Helge Deller <deller@gmx.de> Cc: James E.J. Bottomley <James.Bottomley@HansenPartnership.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Xu <peterx@redhat.com> Cc: Will Deacon <will@kernel.org> Cc: <stable@vger.kernel.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Conflicts: mm/mmap.c [Ma Wupeng: conflict with ascend change of __mmap_region] Signed-off-by: Ma Wupeng <mawupeng1@huawei.com> --- mm/mmap.c | 86 ++++++++++++++++++++++++++++++++++--------------------- 1 file changed, 54 insertions(+), 32 deletions(-) diff --git a/mm/mmap.c b/mm/mmap.c index 3a1f685bff50..6bf5d219aece 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1411,7 +1411,7 @@ static inline bool file_mmap_ok(struct file *file, struct inode *inode, return true; } -static unsigned long __mmap_region(struct mm_struct *mm, +static unsigned long __mmap_region_ext(struct mm_struct *mm, struct file *file, unsigned long addr, unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, struct list_head *uf); @@ -1606,7 +1606,7 @@ unsigned long __do_mmap_mm(struct mm_struct *mm, struct file *file, if (flags & MAP_CHECKNODE) set_vm_checknode(&vm_flags, flags); - addr = __mmap_region(mm, file, addr, len, vm_flags, pgoff, uf); + addr = __mmap_region_ext(mm, file, addr, len, vm_flags, pgoff, uf); if (!IS_ERR_VALUE(addr) && ((vm_flags & VM_LOCKED) || (flags & (MAP_POPULATE | MAP_NONBLOCK)) == MAP_POPULATE)) @@ -1852,11 +1852,6 @@ static unsigned long __mmap_region(struct mm_struct *mm, struct file *file, if (error) goto free_vma; } - if (vm_flags & VM_SHARED) { - error = mapping_map_writable(file->f_mapping); - if (error) - goto allow_write_and_free_vma; - } /* ->mmap() can change vma->vm_file, but must guarantee that * vma_link() below can deny write-access if VM_DENYWRITE is set @@ -1866,7 +1861,7 @@ static unsigned long __mmap_region(struct mm_struct *mm, struct file *file, vma->vm_file = get_file(file); error = mmap_file(file, vma); if (error) - goto unmap_and_free_vma; + goto unmap_and_free_file_vma; /* Can addr have changed?? * @@ -1877,6 +1872,14 @@ static unsigned long __mmap_region(struct mm_struct *mm, struct file *file, */ WARN_ON_ONCE(addr != vma->vm_start); + /* + * Drivers should not permit writability when previously it was + * disallowed. + */ + VM_WARN_ON_ONCE(vm_flags != vma->vm_flags && + !(vm_flags & VM_MAYWRITE) && + (vma->vm_flags & VM_MAYWRITE)); + addr = vma->vm_start; /* If vm_flags changed after mmap_file(), we should try merge vma again @@ -1908,21 +1911,14 @@ static unsigned long __mmap_region(struct mm_struct *mm, struct file *file, vma_set_anonymous(vma); } - /* Allow architectures to sanity-check the vm_flags */ - if (!arch_validate_flags(vma->vm_flags)) { - error = -EINVAL; - if (file) - goto close_and_free_vma; - else - goto free_vma; - } +#ifdef CONFIG_SPARC64 + /* TODO: Fix SPARC ADI! */ + WARN_ON_ONCE(!arch_validate_flags(vm_flags)); +#endif vma_link(mm, vma, prev, rb_link, rb_parent); - /* Once vma denies write, undo our temporary denial count */ if (file) { unmap_writable: - if (vm_flags & VM_SHARED) - mapping_unmap_writable(file->f_mapping); if (vm_flags & VM_DENYWRITE) allow_write_access(file); } @@ -1957,17 +1953,12 @@ static unsigned long __mmap_region(struct mm_struct *mm, struct file *file, return addr; -close_and_free_vma: - vma_close(vma); -unmap_and_free_vma: +unmap_and_free_file_vma: vma->vm_file = NULL; fput(file); /* Undo any partial mapping done by a device driver. */ unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end); - if (vm_flags & VM_SHARED) - mapping_unmap_writable(file->f_mapping); -allow_write_and_free_vma: if (vm_flags & VM_DENYWRITE) allow_write_access(file); free_vma: @@ -1978,13 +1969,6 @@ static unsigned long __mmap_region(struct mm_struct *mm, struct file *file, return error; } -unsigned long mmap_region(struct file *file, unsigned long addr, - unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, - struct list_head *uf) -{ - return __mmap_region(current->mm, file, addr, len, vm_flags, pgoff, uf); -} - static unsigned long unmapped_area(struct vm_unmapped_area_info *info) { /* @@ -3028,6 +3012,44 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, return __do_munmap(mm, start, len, uf, false); } +static unsigned long __mmap_region_ext(struct mm_struct *mm, struct file *file, + unsigned long addr, unsigned long len, + vm_flags_t vm_flags, unsigned long pgoff, + struct list_head *uf) +{ + unsigned long ret; + bool writable_file_mapping = false; + + /* Allow architectures to sanity-check the vm_flags. */ + if (!arch_validate_flags(vm_flags)) + return -EINVAL; + + /* Map writable and ensure this isn't a sealed memfd. */ + if (file && (vm_flags & VM_SHARED)) { + int error = mapping_map_writable(file->f_mapping); + + if (error) + return error; + writable_file_mapping = true; + } + + ret = __mmap_region(mm, file, addr, len, vm_flags, pgoff, uf); + + /* Clear our write mapping regardless of error. */ + if (writable_file_mapping) + mapping_unmap_writable(file->f_mapping); + + validate_mm(current->mm); + return ret; +} + +unsigned long mmap_region(struct file *file, unsigned long addr, + unsigned long len, vm_flags_t vm_flags, unsigned long pgoff, + struct list_head *uf) +{ + return __mmap_region_ext(current->mm, file, addr, len, vm_flags, pgoff, uf); +} + static int __vm_munmap(unsigned long start, size_t len, bool downgrade) { int ret; -- 2.43.0