From: "Liam R. Howlett" <Liam.Howlett@oracle.com>
To: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Cc: Andrew Morton <akpm@linux-foundation.org>,
Vlastimil Babka <vbabka@suse.cz>, Jann Horn <jannh@google.com>,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
Linus Torvalds <torvalds@linux-foundation.org>,
Peter Xu <peterx@redhat.com>
Subject: Re: [PATCH hotfix 6.12 2/8] mm: unconditionally close VMAs on error
Date: Wed, 23 Oct 2024 10:41:57 -0400 [thread overview]
Message-ID: <7gssykgsibgeaz3qivq3qrwciff6k7qkafsugwnmlc5vxjgbwe@7uwypnam6lp4> (raw)
In-Reply-To: <9a84bad9fdebbdb0adca2b5b43ed63afceb5bacc.1729628198.git.lorenzo.stoakes@oracle.com>
* Lorenzo Stoakes <lorenzo.stoakes@oracle.com> [241022 16:41]:
> Incorrect invocation of VMA callbacks when the VMA is no longer in a
> consistent state is bug prone and risky to perform.
>
> With regards to the important vm_ops->close() callback We have gone to
> great lengths to try to track whether or not we ought to close VMAs.
>
> Rather than doing so and risking making a mistake somewhere, instead
> unconditionally close and reset vma->vm_ops to an empty dummy operations
> set with a NULL .close operator.
>
> We introduce a new function to do so - vma_close() - and simplify existing
> vms logic which tracked whether we needed to close or not.
>
> This simplifies the logic, avoids incorrect double-calling of the .close()
> callback and allows us to update error paths to simply call vma_close()
> unconditionally - making VMA closure idempotent.
>
> Reported-by: Jann Horn <jannh@google.com>
> Fixes: deb0f6562884 ("mm/mmap: undo ->mmap() when arch_validate_flags() fails")
> Cc: stable <stable@kernel.org>
> Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
> ---
> mm/internal.h | 17 +++++++++++++++++
> mm/mmap.c | 5 ++---
> mm/nommu.c | 3 +--
> mm/vma.c | 14 +++++---------
> mm/vma.h | 4 +---
> 5 files changed, 26 insertions(+), 17 deletions(-)
>
> diff --git a/mm/internal.h b/mm/internal.h
> index af032e76dfd4..3a45cc592fd0 100644
> --- a/mm/internal.h
> +++ b/mm/internal.h
> @@ -135,6 +135,23 @@ static inline int mmap_file(struct file *file, struct vm_area_struct *vma)
> return err;
> }
>
> +/*
> + * Unconditionally close the VMA if it has a close hook and prevent hooks from
> + * being invoked after close. VMA hooks are mutated.
> + */
> +static inline void vma_close(struct vm_area_struct *vma)
> +{
> + if (vma->vm_ops && vma->vm_ops->close) {
> + vma->vm_ops->close(vma);
> +
> + /*
> + * The mapping is in an inconsistent state, and no further hooks
> + * may be invoked upon it.
> + */
> + vma->vm_ops = &vma_dummy_vm_ops;
> + }
> +}
> +
> #ifdef CONFIG_MMU
>
> /* Flags for folio_pte_batch(). */
> diff --git a/mm/mmap.c b/mm/mmap.c
> index 10f4ccaf491b..d55c58e99a54 100644
> --- a/mm/mmap.c
> +++ b/mm/mmap.c
> @@ -1576,8 +1576,7 @@ unsigned long mmap_region(struct file *file, unsigned long addr,
> return addr;
>
> close_and_free_vma:
> - if (file && !vms.closed_vm_ops && vma->vm_ops && vma->vm_ops->close)
> - vma->vm_ops->close(vma);
> + vma_close(vma);
>
> if (file || vma->vm_file) {
> unmap_and_free_vma:
> @@ -1937,7 +1936,7 @@ void exit_mmap(struct mm_struct *mm)
> do {
> if (vma->vm_flags & VM_ACCOUNT)
> nr_accounted += vma_pages(vma);
> - remove_vma(vma, /* unreachable = */ true, /* closed = */ false);
> + remove_vma(vma, /* unreachable = */ true);
> count++;
> cond_resched();
> vma = vma_next(&vmi);
> diff --git a/mm/nommu.c b/mm/nommu.c
> index f9ccc02458ec..635d028d647b 100644
> --- a/mm/nommu.c
> +++ b/mm/nommu.c
> @@ -589,8 +589,7 @@ static int delete_vma_from_mm(struct vm_area_struct *vma)
> */
> static void delete_vma(struct mm_struct *mm, struct vm_area_struct *vma)
> {
> - if (vma->vm_ops && vma->vm_ops->close)
> - vma->vm_ops->close(vma);
> + vma_close(vma);
> if (vma->vm_file)
> fput(vma->vm_file);
> put_nommu_region(vma->vm_region);
> diff --git a/mm/vma.c b/mm/vma.c
> index 3c5a80876725..bb7cfa2dc282 100644
> --- a/mm/vma.c
> +++ b/mm/vma.c
> @@ -323,11 +323,10 @@ static bool can_vma_merge_right(struct vma_merge_struct *vmg,
> /*
> * Close a vm structure and free it.
> */
> -void remove_vma(struct vm_area_struct *vma, bool unreachable, bool closed)
> +void remove_vma(struct vm_area_struct *vma, bool unreachable)
> {
> might_sleep();
> - if (!closed && vma->vm_ops && vma->vm_ops->close)
> - vma->vm_ops->close(vma);
> + vma_close(vma);
> if (vma->vm_file)
> fput(vma->vm_file);
> mpol_put(vma_policy(vma));
> @@ -1115,9 +1114,7 @@ void vms_clean_up_area(struct vma_munmap_struct *vms,
> vms_clear_ptes(vms, mas_detach, true);
> mas_set(mas_detach, 0);
> mas_for_each(mas_detach, vma, ULONG_MAX)
> - if (vma->vm_ops && vma->vm_ops->close)
> - vma->vm_ops->close(vma);
> - vms->closed_vm_ops = true;
> + vma_close(vma);
> }
>
> /*
> @@ -1160,7 +1157,7 @@ void vms_complete_munmap_vmas(struct vma_munmap_struct *vms,
> /* Remove and clean up vmas */
> mas_set(mas_detach, 0);
> mas_for_each(mas_detach, vma, ULONG_MAX)
> - remove_vma(vma, /* = */ false, vms->closed_vm_ops);
> + remove_vma(vma, /* unreachable = */ false);
>
> vm_unacct_memory(vms->nr_accounted);
> validate_mm(mm);
> @@ -1684,8 +1681,7 @@ struct vm_area_struct *copy_vma(struct vm_area_struct **vmap,
> return new_vma;
>
> out_vma_link:
> - if (new_vma->vm_ops && new_vma->vm_ops->close)
> - new_vma->vm_ops->close(new_vma);
> + vma_close(new_vma);
>
> if (new_vma->vm_file)
> fput(new_vma->vm_file);
> diff --git a/mm/vma.h b/mm/vma.h
> index 55457cb68200..75558b5e9c8c 100644
> --- a/mm/vma.h
> +++ b/mm/vma.h
> @@ -42,7 +42,6 @@ struct vma_munmap_struct {
> int vma_count; /* Number of vmas that will be removed */
> 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 */
> /* 1 byte hole */
> unsigned long nr_pages; /* Number of pages being removed */
> unsigned long locked_vm; /* Number of locked pages */
> @@ -198,7 +197,6 @@ static inline void init_vma_munmap(struct vma_munmap_struct *vms,
> vms->unmap_start = FIRST_USER_ADDRESS;
> vms->unmap_end = USER_PGTABLES_CEILING;
> vms->clear_ptes = false;
> - vms->closed_vm_ops = false;
> }
> #endif
>
> @@ -269,7 +267,7 @@ 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, bool closed);
> +void remove_vma(struct vm_area_struct *vma, bool unreachable);
>
> void unmap_region(struct ma_state *mas, struct vm_area_struct *vma,
> struct vm_area_struct *prev, struct vm_area_struct *next);
> --
> 2.47.0
next prev parent reply other threads:[~2024-10-23 14:42 UTC|newest]
Thread overview: 46+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-10-22 20:40 [PATCH hotfix 6.12 0/8] fix error handling in mmap_region() and refactor Lorenzo Stoakes
2024-10-22 20:40 ` [PATCH hotfix 6.12 1/8] mm: avoid unsafe VMA hook invocation when error arises on mmap hook Lorenzo Stoakes
2024-10-22 21:14 ` Jann Horn
2024-10-23 16:56 ` Lorenzo Stoakes
2024-10-23 9:11 ` Vlastimil Babka
2024-10-23 14:22 ` Liam R. Howlett
2024-10-22 20:40 ` [PATCH hotfix 6.12 2/8] mm: unconditionally close VMAs on error Lorenzo Stoakes
2024-10-22 21:15 ` Jann Horn
2024-10-23 17:00 ` Lorenzo Stoakes
2024-10-23 9:24 ` Vlastimil Babka
2024-10-23 16:58 ` Lorenzo Stoakes
2024-10-23 14:26 ` Liam R. Howlett
2024-10-23 14:41 ` Liam R. Howlett [this message]
2024-10-22 20:40 ` [PATCH hotfix 6.12 3/8] mm: refactor map_deny_write_exec() Lorenzo Stoakes
2024-10-22 21:15 ` Jann Horn
2024-10-23 16:35 ` Lorenzo Stoakes
2024-10-23 9:57 ` Vlastimil Babka
2024-10-23 14:30 ` Liam R. Howlett
2024-10-23 16:25 ` Linus Torvalds
2024-10-23 16:37 ` Lorenzo Stoakes
2024-10-22 20:40 ` [PATCH hotfix 6.12 4/8] mm: resolve faulty mmap_region() error path behaviour Lorenzo Stoakes
2024-10-23 12:58 ` Vlastimil Babka
2024-10-23 14:20 ` Liam R. Howlett
2024-10-23 17:11 ` Lorenzo Stoakes
2024-10-23 15:02 ` Liam R. Howlett
2024-10-22 20:40 ` [PATCH hotfix 6.12 5/8] tools: testing: add additional vma_internal.h stubs Lorenzo Stoakes
2024-10-22 20:40 ` [PATCH hotfix 6.12 6/8] mm: insolate mmap internal logic to mm/vma.c Lorenzo Stoakes
2024-10-22 20:40 ` [PATCH hotfix 6.12 7/8] mm: refactor __mmap_region() Lorenzo Stoakes
2024-10-23 14:38 ` Vlastimil Babka
2024-10-23 15:21 ` Liam R. Howlett
2024-10-23 17:39 ` Lorenzo Stoakes
2024-10-23 18:12 ` Liam R. Howlett
2024-10-23 17:30 ` Lorenzo Stoakes
2024-10-23 17:19 ` Liam R. Howlett
2024-10-23 17:52 ` Lorenzo Stoakes
2024-10-22 20:40 ` [PATCH hotfix 6.12 8/8] mm: do not attempt second merge for file-backed VMAs Lorenzo Stoakes
2024-10-23 15:01 ` Vlastimil Babka
2024-10-23 15:16 ` Lorenzo Stoakes
2024-10-23 18:16 ` Liam R. Howlett
2024-10-23 18:20 ` Lorenzo Stoakes
2024-10-22 20:58 ` [PATCH hotfix 6.12 0/8] fix error handling in mmap_region() and refactor Lorenzo Stoakes
2024-10-23 8:37 ` Vlastimil Babka
2024-10-23 8:45 ` Lorenzo Stoakes
2024-10-23 10:22 ` Andrew Morton
2024-10-23 10:25 ` Andrew Morton
2024-10-23 10:26 ` Lorenzo Stoakes
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=7gssykgsibgeaz3qivq3qrwciff6k7qkafsugwnmlc5vxjgbwe@7uwypnam6lp4 \
--to=liam.howlett@oracle.com \
--cc=akpm@linux-foundation.org \
--cc=jannh@google.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=lorenzo.stoakes@oracle.com \
--cc=peterx@redhat.com \
--cc=torvalds@linux-foundation.org \
--cc=vbabka@suse.cz \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox