diff mbox series

[RFC,2/2] mm: make mmap_region() internal

Message ID 80b7c4ba4f0a2b3084117975bd1af62a403ac881.1734017293.git.lorenzo.stoakes@oracle.com (mailing list archive)
State New
Headers show
Series mm: update mips to use do_mmap(), make mmap_region() internal | expand

Commit Message

Lorenzo Stoakes Dec. 12, 2024, 3:36 p.m. UTC
Now that we have removed the one user of mmap_region() outside of mm, make
it internal and add it to vma.c so it can be userland tested.

This ensures that all external memory mappings are performed using the
appropriate interfaces and allows us to modify memory mapping logic as we
see fit.

Additionally expand test stubs to allow for the mmap_region() code to
compile and be userland testable.

Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@oracle.com>
---
 include/linux/mm.h               |  3 --
 mm/mmap.c                        | 34 -----------------
 mm/vma.c                         | 36 +++++++++++++++++-
 mm/vma.h                         |  6 +--
 tools/testing/vma/vma_internal.h | 65 ++++++++++++++++++++++++++++++++
 5 files changed, 103 insertions(+), 41 deletions(-)

Comments

Matthew Wilcox (Oracle) Dec. 12, 2024, 3:45 p.m. UTC | #1
On Thu, Dec 12, 2024 at 03:36:47PM +0000, Lorenzo Stoakes wrote:
> +++ b/mm/vma.h
> @@ -242,9 +242,9 @@ 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 __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 mmap_region(struct file *file, unsigned long addr,
> +			  unsigned long len, vm_flags_t vm_flags, unsigned long pgoff,
> +			  struct list_head *uf);

Please don't line up the arguments with the paren.  Just leave it as two
tabs.
Lorenzo Stoakes Dec. 12, 2024, 4:48 p.m. UTC | #2
On Thu, Dec 12, 2024 at 03:45:16PM +0000, Matthew Wilcox wrote:
> On Thu, Dec 12, 2024 at 03:36:47PM +0000, Lorenzo Stoakes wrote:
> > +++ b/mm/vma.h
> > @@ -242,9 +242,9 @@ 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 __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 mmap_region(struct file *file, unsigned long addr,
> > +			  unsigned long len, vm_flags_t vm_flags, unsigned long pgoff,
> > +			  struct list_head *uf);
>
> Please don't line up the arguments with the paren.  Just leave it as two
> tabs.
>

Ack, emacs likes to do this, will tweak on respin assuming mips guys
confirm that idea works!
diff mbox series

Patch

diff --git a/include/linux/mm.h b/include/linux/mm.h
index a672339f2b8f..d145ddf1b2f0 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3436,9 +3436,6 @@  get_unmapped_area(struct file *file, unsigned long addr, unsigned long len,
 	return __get_unmapped_area(file, addr, len, pgoff, flags, 0);
 }
 
-extern 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);
 extern unsigned long do_mmap(struct file *file, unsigned long addr,
 	unsigned long len, unsigned long prot, unsigned long flags,
 	vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate,
diff --git a/mm/mmap.c b/mm/mmap.c
index df9154b15ef9..b771ae617629 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -1016,40 +1016,6 @@  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,
-			  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 && is_shared_maywrite(vm_flags)) {
-		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;
-}
-
 int vm_munmap(unsigned long start, size_t len)
 {
 	return __vm_munmap(start, len, false);
diff --git a/mm/vma.c b/mm/vma.c
index 2fabfd6c8957..218d8f154e99 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -2432,7 +2432,7 @@  static void __mmap_complete(struct mmap_state *map, struct vm_area_struct *vma)
 	vma_set_page_prot(vma);
 }
 
-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)
 {
@@ -2484,6 +2484,40 @@  unsigned long __mmap_region(struct file *file, unsigned long addr,
 	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 && is_shared_maywrite(vm_flags)) {
+		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;
+}
+
 /*
  * do_brk_flags() - Increase the brk vma if the flags match.
  * @vmi: The vma iterator
diff --git a/mm/vma.h b/mm/vma.h
index 24636a2b0acf..dd943a593312 100644
--- a/mm/vma.h
+++ b/mm/vma.h
@@ -242,9 +242,9 @@  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 __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 mmap_region(struct file *file, unsigned long addr,
+			  unsigned long len, vm_flags_t vm_flags, unsigned long pgoff,
+			  struct list_head *uf);
 
 int do_brk_flags(struct vma_iterator *vmi, struct vm_area_struct *brkvma,
 		 unsigned long addr, unsigned long request, unsigned long flags);
diff --git a/tools/testing/vma/vma_internal.h b/tools/testing/vma/vma_internal.h
index 3eeb1317cc69..9f6cf80c9682 100644
--- a/tools/testing/vma/vma_internal.h
+++ b/tools/testing/vma/vma_internal.h
@@ -41,6 +41,8 @@  extern unsigned long dac_mmap_min_addr;
 #define VM_BUG_ON(_expr) (BUG_ON(_expr))
 #define VM_BUG_ON_VMA(_expr, _vma) (BUG_ON(_expr))
 
+#define MMF_HAS_MDWE		28
+
 #define VM_NONE		0x00000000
 #define VM_READ		0x00000001
 #define VM_WRITE	0x00000002
@@ -226,6 +228,8 @@  struct mm_struct {
 	unsigned long stack_vm;	   /* VM_STACK */
 
 	unsigned long def_flags;
+
+	unsigned long flags; /* Must use atomic bitops to access */
 };
 
 struct vma_lock {
@@ -1174,4 +1178,65 @@  static inline void userfaultfd_unmap_complete(struct mm_struct *mm,
 {
 }
 
+/*
+ * Denies creating a writable executable mapping or gaining executable permissions.
+ *
+ * This denies the following:
+ *
+ * 	a)	mmap(PROT_WRITE | PROT_EXEC)
+ *
+ *	b)	mmap(PROT_WRITE)
+ *		mprotect(PROT_EXEC)
+ *
+ *	c)	mmap(PROT_WRITE)
+ *		mprotect(PROT_READ)
+ *		mprotect(PROT_EXEC)
+ *
+ * But allows the following:
+ *
+ *	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(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 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;
+
+	/* ...nor previously non-executable VMAs becoming executable. */
+	if (!(old & VM_EXEC))
+		return true;
+
+	return false;
+}
+
+static inline int mapping_map_writable(struct address_space *mapping)
+{
+	int c = atomic_read(&mapping->i_mmap_writable);
+
+	/* Derived from the raw_atomic_inc_unless_negative() implementation. */
+	do {
+		if (c < 0)
+			return -EPERM;
+	} while (!__sync_bool_compare_and_swap(&mapping->i_mmap_writable, c, c+1));
+
+	return 0;
+}
+
 #endif	/* __MM_VMA_INTERNAL_H */