diff options
author | Liam R. Howlett <Liam.Howlett@Oracle.com> | 2024-08-30 06:00:54 +0200 |
---|---|---|
committer | Andrew Morton <akpm@linux-foundation.org> | 2024-09-04 06:15:51 +0200 |
commit | f8d112a4e657c65c888e6b8a8435ef61a66e4ab8 (patch) | |
tree | 29a13a59d9e65ededb27fac972068278dcd80e35 /mm/vma.h | |
parent | mm: clean up unmap_region() argument list (diff) | |
download | linux-f8d112a4e657c65c888e6b8a8435ef61a66e4ab8.tar.xz linux-f8d112a4e657c65c888e6b8a8435ef61a66e4ab8.zip |
mm/mmap: avoid zeroing vma tree in mmap_region()
Instead of zeroing the vma tree and then overwriting the area, let the
area be overwritten and then clean up the gathered vmas using
vms_complete_munmap_vmas().
To ensure locking is downgraded correctly, the mm is set regardless of
MAP_FIXED or not (NULL vma).
If a driver is mapping over an existing vma, then clear the ptes before
the call_mmap() invocation. This is done using the vms_clean_up_area()
helper. If there is a close vm_ops, that must also be called to ensure
any cleanup is done before mapping over the area. This also means that
calling open has been added to the abort of an unmap operation, for now.
Since vm_ops->open() and vm_ops->close() are not always undo each other
(state cleanup may exist in ->close() that is lost forever), the code
cannot be left in this way, but that change has been isolated to another
commit to make this point very obvious for traceability.
Temporarily keep track of the number of pages that will be removed and
reduce the charged amount.
This also drops the validate_mm() call in the vma_expand() function. It
is necessary to drop the validate as it would fail since the mm map_count
would be incorrect during a vma expansion, prior to the cleanup from
vms_complete_munmap_vmas().
Clean up the error handing of the vms_gather_munmap_vmas() by calling the
verification within the function.
Link: https://lkml.kernel.org/r/20240830040101.822209-15-Liam.Howlett@oracle.com
Signed-off-by: Liam R. Howlett <Liam.Howlett@Oracle.com>
Reviewed-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Bert Karwatzki <spasswolf@web.de>
Cc: Jeff Xu <jeffxu@chromium.org>
Cc: Jiri Olsa <olsajiri@gmail.com>
Cc: Kees Cook <kees@kernel.org>
Cc: Lorenzo Stoakes <lstoakes@gmail.com>
Cc: Mark Brown <broonie@kernel.org>
Cc: Matthew Wilcox <willy@infradead.org>
Cc: "Paul E. McKenney" <paulmck@kernel.org>
Cc: Paul Moore <paul@paul-moore.com>
Cc: Sidhartha Kumar <sidhartha.kumar@oracle.com>
Cc: Suren Baghdasaryan <surenb@google.com>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm/vma.h')
-rw-r--r-- | mm/vma.h | 22 |
1 files changed, 16 insertions, 6 deletions
@@ -48,6 +48,8 @@ struct vma_munmap_struct { unsigned long stack_vm; unsigned long data_vm; bool unlock; /* Unlock after the munmap */ + bool clear_ptes; /* If there are outstanding PTE to be cleared */ + bool closed_vm_ops; /* call_mmap() was encountered, so vmas may be closed */ }; #ifdef CONFIG_DEBUG_VM_MAPLE_TREE @@ -96,14 +98,13 @@ static inline void init_vma_munmap(struct vma_munmap_struct *vms, unsigned long start, unsigned long end, struct list_head *uf, bool unlock) { + vms->mm = current->mm; vms->vmi = vmi; vms->vma = vma; if (vma) { - vms->mm = vma->vm_mm; vms->start = start; vms->end = end; } else { - vms->mm = NULL; vms->start = vms->end = 0; } vms->unlock = unlock; @@ -113,6 +114,8 @@ static inline void init_vma_munmap(struct vma_munmap_struct *vms, vms->exec_vm = vms->stack_vm = vms->data_vm = 0; vms->unmap_start = FIRST_USER_ADDRESS; vms->unmap_end = USER_PGTABLES_CEILING; + vms->clear_ptes = false; + vms->closed_vm_ops = false; } #endif @@ -122,18 +125,24 @@ int vms_gather_munmap_vmas(struct vma_munmap_struct *vms, void vms_complete_munmap_vmas(struct vma_munmap_struct *vms, struct ma_state *mas_detach); +void vms_clean_up_area(struct vma_munmap_struct *vms, + struct ma_state *mas_detach, bool mm_wr_locked); + /* * abort_munmap_vmas - Undo any munmap work and free resources * * Reattach any detached vmas and free up the maple tree used to track the vmas. */ -static inline void abort_munmap_vmas(struct ma_state *mas_detach) +static inline void abort_munmap_vmas(struct ma_state *mas_detach, bool closed) { struct vm_area_struct *vma; mas_set(mas_detach, 0); - mas_for_each(mas_detach, vma, ULONG_MAX) + mas_for_each(mas_detach, vma, ULONG_MAX) { vma_mark_detached(vma, false); + if (closed && vma->vm_ops && vma->vm_ops->open) + vma->vm_ops->open(vma); + } __mt_destroy(mas_detach->tree); } @@ -147,7 +156,7 @@ int do_vmi_munmap(struct vma_iterator *vmi, struct mm_struct *mm, unsigned long start, size_t len, struct list_head *uf, bool unlock); -void remove_vma(struct vm_area_struct *vma, bool unreachable); +void remove_vma(struct vm_area_struct *vma, bool unreachable, bool closed); void unmap_region(struct ma_state *mas, struct vm_area_struct *vma, struct vm_area_struct *prev, struct vm_area_struct *next); @@ -261,7 +270,8 @@ bool vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot); int mm_take_all_locks(struct mm_struct *mm); void mm_drop_all_locks(struct mm_struct *mm); unsigned long count_vma_pages_range(struct mm_struct *mm, - unsigned long addr, unsigned long end); + unsigned long addr, unsigned long end, + unsigned long *nr_accounted); static inline bool vma_wants_manual_pte_write_upgrade(struct vm_area_struct *vma) { |