[ 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 --- mm/internal.h | 27 +++++++++++++++++++++++++++ mm/mmap.c | 4 ++-- mm/nommu.c | 4 ++-- 3 files changed, 31 insertions(+), 4 deletions(-)

diff --git a/mm/internal.h b/mm/internal.h index ef8d787a510c..d52d6b57dafb 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -83,6 +83,33 @@ static inline void *folio_raw_mapping(struct folio *folio) return (void *)(mapping & ~PAGE_MAPPING_FLAGS); }

+/* + * 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. + */ +static inline int mmap_file(struct file *file, struct vm_area_struct *vma) +{ + 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 = &vma_dummy_vm_ops; + + return err; +} + void __acct_reclaim_writeback(pg_data_t *pgdat, struct folio *folio, int nr_throttled); static inline void acct_reclaim_writeback(struct folio *folio) diff --git a/mm/mmap.c b/mm/mmap.c index 6530e9cac458..8a055bae6bdb 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2779,7 +2779,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, }

vma->vm_file = get_file(file); - error = call_mmap(file, vma); + error = mmap_file(file, vma); if (error) goto unmap_and_free_vma;

@@ -2793,7 +2793,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,

vma_iter_config(&vmi, addr, end); /* - * If vm_flags changed after call_mmap(), we should try merge + * 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 7f9e9e5a0e12..e976c62264c9 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -896,7 +896,7 @@ 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; @@ -929,7 +929,7 @@ static int do_mmap_private(struct vm_area_struct *vma, * happy. */ if (capabilities & NOMMU_MAP_DIRECT) { - ret = call_mmap(vma->vm_file, vma); + ret = mmap_file(vma->vm_file, vma); /* shouldn't return success if we're not sharing */ if (WARN_ON_ONCE(!is_nommu_shared_mapping(vma->vm_flags))) ret = -ENOSYS;

[ Upstream commit 0fb4a7ad270b3b209e510eb9dc5b07bf02b7edaf ]

Refactor the map_deny_write_exec() to not unnecessarily require a VMA parameter but rather to accept VMA flags parameters, which allows us to use this function early in mmap_region() in a subsequent commit.

While we're here, we refactor the function to be more readable and add some additional documentation.

Link: https://lkml.kernel.org/r/6be8bb59cd7c68006ebb006eb9d8dc27104b1f70.173022466... 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 --- include/linux/mman.h | 21 ++++++++++++++++++--- mm/mmap.c | 2 +- mm/mprotect.c | 2 +- 3 files changed, 20 insertions(+), 5 deletions(-)

diff --git a/include/linux/mman.h b/include/linux/mman.h index db4741007bef..651705c2bf47 100644 --- a/include/linux/mman.h +++ b/include/linux/mman.h @@ -187,16 +187,31 @@ static inline bool arch_memory_deny_write_exec_supported(void) * * d) mmap(PROT_READ | PROT_EXEC) * mmap(PROT_READ | PROT_EXEC | PROT_BTI) + * + * This is only applicable if the user has set the Memory-Deny-Write-Execute + * (MDWE) protection mask for the current process. + * + * @old specifies the VMA flags the VMA originally possessed, and @new the ones + * we propose to set. + * + * Return: false if proposed change is OK, true if not ok and should be denied. */ -static inline bool map_deny_write_exec(struct vm_area_struct *vma, unsigned long vm_flags) +static inline bool map_deny_write_exec(unsigned long old, unsigned long new) { + /* If MDWE is disabled, we have nothing to deny. */ if (!test_bit(MMF_HAS_MDWE, &current->mm->flags)) return false;

- if ((vm_flags & VM_EXEC) && (vm_flags & VM_WRITE)) + /* If the new VMA is not executable, we have nothing to deny. */ + if (!(new & VM_EXEC)) + return false; + + /* Under MDWE we do not accept newly writably executable VMAs... */ + if (new & VM_WRITE) return true;

- if (!(vma->vm_flags & VM_EXEC) && (vm_flags & VM_EXEC)) + /* ...nor previously non-executable VMAs becoming executable. */ + if (!(old & VM_EXEC)) return true;

return false; diff --git a/mm/mmap.c b/mm/mmap.c index 9fefd13640d1..d71ac65563b2 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2826,7 +2826,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, vma_set_anonymous(vma); }

- if (map_deny_write_exec(vma, vma->vm_flags)) { + if (map_deny_write_exec(vma->vm_flags, vma->vm_flags)) { error = -EACCES; goto close_and_free_vma; } diff --git a/mm/mprotect.c b/mm/mprotect.c index b94fbb45d5c7..7e870a8c9402 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -791,7 +791,7 @@ static int do_mprotect_pkey(unsigned long start, size_t len, break; }

- if (map_deny_write_exec(vma, newflags)) { + if (map_deny_write_exec(vma->vm_flags, newflags)) { error = -EACCES; break; }

[ 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 --- mm/mmap.c | 115 +++++++++++++++++++++++++++++++----------------------- 1 file changed, 66 insertions(+), 49 deletions(-)

diff --git a/mm/mmap.c b/mm/mmap.c index fca3429da2fe..e4dfeaef668a 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2666,14 +2666,14 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len, return do_vmi_munmap(&vmi, mm, start, len, uf, false); }

-unsigned long mmap_region(struct file *file, unsigned long addr, +static 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) { struct mm_struct *mm = current->mm; struct vm_area_struct *vma = NULL; struct vm_area_struct *next, *prev, *merge; - pgoff_t pglen = len >> PAGE_SHIFT; + pgoff_t pglen = PHYS_PFN(len); unsigned long charged = 0; unsigned long end = addr + len; unsigned long merge_start = addr, merge_end = end; @@ -2770,25 +2770,26 @@ unsigned long mmap_region(struct file *file, unsigned long addr, vma->vm_page_prot = vm_get_page_prot(vm_flags); vma->vm_pgoff = pgoff;

- if (file) { - if (vm_flags & VM_SHARED) { - error = mapping_map_writable(file->f_mapping); - if (error) - goto free_vma; - } + if (vma_iter_prealloc(&vmi, vma)) { + error = -ENOMEM; + goto free_vma; + }

+ if (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;

+ /* Drivers cannot alter the address of the VMA. */ + WARN_ON_ONCE(addr != vma->vm_start); /* - * Expansion is handled above, merging is handled below. - * Drivers should not alter the address of the VMA. + * Drivers should not permit writability when previously it was + * disallowed. */ - error = -EINVAL; - if (WARN_ON((addr != vma->vm_start))) - goto close_and_free_vma; + VM_WARN_ON_ONCE(vm_flags != vma->vm_flags && + !(vm_flags & VM_MAYWRITE) && + (vma->vm_flags & VM_MAYWRITE));

vma_iter_config(&vmi, addr, end); /* @@ -2800,6 +2801,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, vma->vm_end, vma->vm_flags, NULL, vma->vm_file, vma->vm_pgoff, NULL, NULL_VM_UFFD_CTX, NULL); + if (merge) { /* * ->mmap() can change vma->vm_file and fput @@ -2813,7 +2815,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, vma = merge; /* Update vm_flags to pick up the change. */ vm_flags = vma->vm_flags; - goto unmap_writable; + goto file_expanded; } }

@@ -2821,24 +2823,15 @@ unsigned long mmap_region(struct file *file, unsigned long addr, } else if (vm_flags & VM_SHARED) { error = shmem_zero_setup(vma); if (error) - goto free_vma; + goto free_iter_vma; } else { vma_set_anonymous(vma); }

- if (map_deny_write_exec(vma->vm_flags, vma->vm_flags)) { - error = -EACCES; - goto close_and_free_vma; - } - - /* Allow architectures to sanity-check the vm_flags */ - error = -EINVAL; - if (!arch_validate_flags(vma->vm_flags)) - goto close_and_free_vma; - - error = -ENOMEM; - if (vma_iter_prealloc(&vmi, vma)) - goto close_and_free_vma; +#ifdef CONFIG_SPARC64 + /* TODO: Fix SPARC ADI! */ + WARN_ON_ONCE(!arch_validate_flags(vm_flags)); +#endif

/* Lock the VMA since it is modified after insertion into VMA tree */ vma_start_write(vma); @@ -2861,10 +2854,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr, */ khugepaged_enter_vma(vma, vma->vm_flags);

- /* Once vma denies write, undo our temporary denial count */ -unmap_writable: - if (file && vm_flags & VM_SHARED) - mapping_unmap_writable(file->f_mapping); +file_expanded: file = vma->vm_file; ksm_add_vma(vma); expanded: @@ -2894,33 +2884,60 @@ unsigned long mmap_region(struct file *file, unsigned long addr,

vma_set_page_prot(vma);

- validate_mm(mm); return addr;

-close_and_free_vma: - vma_close(vma); - - if (file || vma->vm_file) { -unmap_and_free_vma: - fput(vma->vm_file); - vma->vm_file = NULL; +unmap_and_free_file_vma: + fput(vma->vm_file); + vma->vm_file = NULL;

- vma_iter_set(&vmi, vma->vm_end); - /* Undo any partial mapping done by a device driver. */ - unmap_region(mm, &vmi.mas, vma, prev, next, vma->vm_start, - vma->vm_end, vma->vm_end, true); - } - if (file && (vm_flags & VM_SHARED)) - mapping_unmap_writable(file->f_mapping); + vma_iter_set(&vmi, vma->vm_end); + /* Undo any partial mapping done by a device driver. */ + unmap_region(mm, &vmi.mas, vma, prev, next, vma->vm_start, + vma->vm_end, vma->vm_end, true); +free_iter_vma: + vma_iter_free(&vmi); free_vma: vm_area_free(vma); unacct_error: if (charged) vm_unacct_memory(charged); - validate_mm(mm); 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) +{ + unsigned long ret; + bool writable_file_mapping = false; + + /* Check to see if MDWE is applicable. */ + if (map_deny_write_exec(vm_flags, vm_flags)) + return -EACCES; + + /* 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(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; +} + static int __vm_munmap(unsigned long start, size_t len, bool unlock) { int ret;