diff options
author | Liam R. Howlett <Liam.Howlett@oracle.com> | 2023-02-27 09:36:07 -0800 |
---|---|---|
committer | Andrew Morton <akpm@linux-foundation.org> | 2023-04-05 18:06:22 -0700 |
commit | 3dd4432549415f3c65dd52d5c687629efbf4ece1 (patch) | |
tree | b7e002610cfb3f3e2fd0cd30eca7dbe91cf50918 | |
parent | 790e1fa86b340c2bd4a327e01c161f7a1ad885f6 (diff) | |
download | linux-stable-3dd4432549415f3c65dd52d5c687629efbf4ece1.tar.gz linux-stable-3dd4432549415f3c65dd52d5c687629efbf4ece1.tar.bz2 linux-stable-3dd4432549415f3c65dd52d5c687629efbf4ece1.zip |
mm: enable maple tree RCU mode by default
Use the maple tree in RCU mode for VMA tracking.
The maple tree tracks the stack and is able to update the pivot
(lower/upper boundary) in-place to allow the page fault handler to write
to the tree while holding just the mmap read lock. This is safe as the
writes to the stack have a guard VMA which ensures there will always be a
NULL in the direction of the growth and thus will only update a pivot.
It is possible, but not recommended, to have VMAs that grow up/down
without guard VMAs. syzbot has constructed a testcase which sets up a VMA
to grow and consume the empty space. Overwriting the entire NULL entry
causes the tree to be altered in a way that is not safe for concurrent
readers; the readers may see a node being rewritten or one that does not
match the maple state they are using.
Enabling RCU mode allows the concurrent readers to see a stable node and
will return the expected result.
[Liam.Howlett@Oracle.com: we don't need to free the nodes with RCU[
Link: https://lore.kernel.org/linux-mm/000000000000b0a65805f663ace6@google.com/
Link: https://lkml.kernel.org/r/20230227173632.3292573-9-surenb@google.com
Fixes: d4af56c5c7c6 ("mm: start tracking VMAs with maple tree")
Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
Reported-by: syzbot+8d95422d3537159ca390@syzkaller.appspotmail.com
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
-rw-r--r-- | include/linux/mm_types.h | 3 | ||||
-rw-r--r-- | kernel/fork.c | 3 | ||||
-rw-r--r-- | mm/mmap.c | 3 |
3 files changed, 7 insertions, 2 deletions
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h index 0722859c3647..a57e6ae78e65 100644 --- a/include/linux/mm_types.h +++ b/include/linux/mm_types.h @@ -774,7 +774,8 @@ struct mm_struct { unsigned long cpu_bitmap[]; }; -#define MM_MT_FLAGS (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN) +#define MM_MT_FLAGS (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN | \ + MT_FLAGS_USE_RCU) extern struct mm_struct init_mm; /* Pointer magic because the dynamic array size confuses some compilers. */ diff --git a/kernel/fork.c b/kernel/fork.c index c0257cbee093..0c92f224c68c 100644 --- a/kernel/fork.c +++ b/kernel/fork.c @@ -617,6 +617,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, if (retval) goto out; + mt_clear_in_rcu(vmi.mas.tree); for_each_vma(old_vmi, mpnt) { struct file *file; @@ -700,6 +701,8 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm, retval = arch_dup_mmap(oldmm, mm); loop_out: vma_iter_free(&vmi); + if (!retval) + mt_set_in_rcu(vmi.mas.tree); out: mmap_write_unlock(mm); flush_tlb_mm(oldmm); diff --git a/mm/mmap.c b/mm/mmap.c index ad499f7b767f..ff68a67a2a7c 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2277,7 +2277,7 @@ do_vmi_align_munmap(struct vma_iterator *vmi, struct vm_area_struct *vma, int count = 0; int error = -ENOMEM; MA_STATE(mas_detach, &mt_detach, 0, 0); - mt_init_flags(&mt_detach, MT_FLAGS_LOCK_EXTERN); + mt_init_flags(&mt_detach, vmi->mas.tree->ma_flags & MT_FLAGS_LOCK_MASK); mt_set_external_lock(&mt_detach, &mm->mmap_lock); /* @@ -3037,6 +3037,7 @@ void exit_mmap(struct mm_struct *mm) */ set_bit(MMF_OOM_SKIP, &mm->flags); mmap_write_lock(mm); + mt_clear_in_rcu(&mm->mm_mt); free_pgtables(&tlb, &mm->mm_mt, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING); tlb_finish_mmu(&tlb); |