mm: unconditionally close VMAs on error

[ Upstream commit 4080ef1579b2413435413988d14ac8c68e4d42c8 ]

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.

Link: https://lkml.kernel.org/r/28e89dda96f68c505cb6f8e9fc9b57c3e9f74b42.1730224667.git.lorenzo.stoakes@oracle.com
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: Vlastimil Babka <vbabka@suse.cz>
Reviewed-by: Liam R. Howlett <Liam.Howlett@oracle.com>
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>

diff --git a/mm/internal.h b/mm/internal.h
index 85ac9c6a13933065023c106abc6bc34de9aa72cc..16a4a9aece3043565628eeaf79f26b8d2f168b92 100644 (file)
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -64,6 +64,13 @@ void page_writeback_init(void);
  */
 int mmap_file(struct file *file, struct vm_area_struct *vma);
 
+/*
+ * If the VMA has a close hook then close it, and since closing it might leave
+ * it in an inconsistent state which makes the use of any hooks suspect, clear
+ * them down by installing dummy empty hooks.
+ */
+void vma_close(struct vm_area_struct *vma);
+
 static inline void *folio_raw_mapping(struct folio *folio)
 {
        unsigned long mapping = (unsigned long)folio->mapping;

diff --git a/mm/mmap.c b/mm/mmap.c
index bf2f1ca87bef2e8bd64b861ea0a27a78edce352e..4bfec4df51c2d0ba4a8fbfabdfcf5023e4e035a3 100644 (file)
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -136,8 +136,7 @@ void unlink_file_vma(struct vm_area_struct *vma)
 static void remove_vma(struct vm_area_struct *vma)
 {
        might_sleep();
-       if (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));
@@ -2388,8 +2387,7 @@ int __split_vma(struct mm_struct *mm, struct vm_area_struct *vma,
        new->vm_start = new->vm_end;
        new->vm_pgoff = 0;
        /* Clean everything up if vma_adjust failed. */
-       if (new->vm_ops && new->vm_ops->close)
-               new->vm_ops->close(new);
+       vma_close(new);
        if (new->vm_file)
                fput(new->vm_file);
        unlink_anon_vmas(new);
@@ -2885,8 +2883,7 @@ expanded:
        return addr;
 
 close_and_free_vma:
-       if (vma->vm_ops && vma->vm_ops->close)
-               vma->vm_ops->close(vma);
+       vma_close(vma);
 unmap_and_free_vma:
        fput(vma->vm_file);
        vma->vm_file = NULL;
@@ -3376,8 +3373,7 @@ 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/nommu.c b/mm/nommu.c
index f09e798a44166aaa01ba248d8ed670e79b8fd658..e0428fa575269581c237adb2a0f4e3ce036f9a79 100644 (file)
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -650,8 +650,7 @@ 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/util.c b/mm/util.c
index 15f1970da665dfd52330d393d54bd445403ba679..d3a2877c176f98c67f282e60612532592398c900 100644 (file)
--- a/mm/util.c
+++ b/mm/util.c
@@ -1121,6 +1121,21 @@ int mmap_file(struct file *file, struct vm_area_struct *vma)
        return err;
 }
 
+void vma_close(struct vm_area_struct *vma)
+{
+       static const struct vm_operations_struct dummy_vm_ops = {};
+
+       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 = &dummy_vm_ops;
+       }
+}
+
 #ifdef CONFIG_PRINTK
 /**
  * mem_dump_obj - Print available provenance information