Message-ID: <c1be2cf261bd0d72fe17084c41452f5ebe030d8c.1720006125.git.lorenzo.stoakes@oracle.com>
Date: Wed,  3 Jul 2024 12:57:34 +0100
From: Lorenzo Stoakes <lorenzo.stoakes@...cle.com>
To: Andrew Morton <akpm@...ux-foundation.org>
Cc: linux-fsdevel@...r.kernel.org, linux-kernel@...r.kernel.org,
        linux-mm@...ck.org, "Liam R . Howlett" <Liam.Howlett@...cle.com>,
        Vlastimil Babka <vbabka@...e.cz>, Matthew Wilcox <willy@...radead.org>,
        Alexander Viro <viro@...iv.linux.org.uk>,
        Christian Brauner <brauner@...nel.org>, Jan Kara <jack@...e.cz>,
        Eric Biederman <ebiederm@...ssion.com>, Kees Cook <kees@...nel.org>,
        Suren Baghdasaryan <surenb@...gle.com>
Subject: [PATCH 3/7] mm: move vma_shrink(), vma_expand() to internal header

The vma_shrink() and vma_expand() functions are internal VMA manipulation
functions which we ought to abstract for use outside of memory management
code.

To achieve this, we replace shift_arg_pages() in fs/exec.c with an
invocation of a new relocate_vma_down() function implemented in mm/mmap.c,
which enables us to also move move_page_tables() and vma_iter_prev_range()
to internal.h.

The purpose of doing this is to isolate key VMA manipulation functions in
order that we can both abstract them and later render them easily testable.

Signed-off-by: Lorenzo Stoakes <lorenzo.stoakes@...cle.com>
---
 fs/exec.c          | 81 ++++------------------------------------------
 include/linux/mm.h | 17 +---------
 mm/internal.h      | 18 +++++++++++
 mm/mmap.c          | 81 ++++++++++++++++++++++++++++++++++++++++++++++
 4 files changed, 106 insertions(+), 91 deletions(-)

diff --git a/fs/exec.c b/fs/exec.c
index 40073142288f..8596d325250c 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -680,80 +680,6 @@ static int copy_strings_kernel(int argc, const char *const *argv,

 #ifdef CONFIG_MMU

-/*
- * During bprm_mm_init(), we create a temporary stack at STACK_TOP_MAX.  Once
- * the binfmt code determines where the new stack should reside, we shift it to
- * its final location.  The process proceeds as follows:
- *
- * 1) Use shift to calculate the new vma endpoints.
- * 2) Extend vma to cover both the old and new ranges.  This ensures the
- *    arguments passed to subsequent functions are consistent.
- * 3) Move vma's page tables to the new range.
- * 4) Free up any cleared pgd range.
- * 5) Shrink the vma to cover only the new range.
- */
-static int shift_arg_pages(struct vm_area_struct *vma, unsigned long shift)
-{
-	struct mm_struct *mm = vma->vm_mm;
-	unsigned long old_start = vma->vm_start;
-	unsigned long old_end = vma->vm_end;
-	unsigned long length = old_end - old_start;
-	unsigned long new_start = old_start - shift;
-	unsigned long new_end = old_end - shift;
-	VMA_ITERATOR(vmi, mm, new_start);
-	struct vm_area_struct *next;
-	struct mmu_gather tlb;
-
-	BUG_ON(new_start > new_end);
-
-	/*
-	 * ensure there are no vmas between where we want to go
-	 * and where we are
-	 */
-	if (vma != vma_next(&vmi))
-		return -EFAULT;
-
-	vma_iter_prev_range(&vmi);
-	/*
-	 * cover the whole range: [new_start, old_end)
-	 */
-	if (vma_expand(&vmi, vma, new_start, old_end, vma->vm_pgoff, NULL))
-		return -ENOMEM;
-
-	/*
-	 * move the page tables downwards, on failure we rely on
-	 * process cleanup to remove whatever mess we made.
-	 */
-	if (length != move_page_tables(vma, old_start,
-				       vma, new_start, length, false, true))
-		return -ENOMEM;
-
-	lru_add_drain();
-	tlb_gather_mmu(&tlb, mm);
-	next = vma_next(&vmi);
-	if (new_end > old_start) {
-		/*
-		 * when the old and new regions overlap clear from new_end.
-		 */
-		free_pgd_range(&tlb, new_end, old_end, new_end,
-			next ? next->vm_start : USER_PGTABLES_CEILING);
-	} else {
-		/*
-		 * otherwise, clean from old_start; this is done to not touch
-		 * the address space in [new_end, old_start) some architectures
-		 * have constraints on va-space that make this illegal (IA64) -
-		 * for the others its just a little faster.
-		 */
-		free_pgd_range(&tlb, old_start, old_end, new_end,
-			next ? next->vm_start : USER_PGTABLES_CEILING);
-	}
-	tlb_finish_mmu(&tlb);
-
-	vma_prev(&vmi);
-	/* Shrink the vma to just the new range */
-	return vma_shrink(&vmi, vma, new_start, new_end, vma->vm_pgoff);
-}
-
 /*
  * Finalizes the stack vm_area_struct. The flags and permissions are updated,
  * the stack is optionally relocated, and some extra space is added.
@@ -846,7 +772,12 @@ int setup_arg_pages(struct linux_binprm *bprm,

 	/* Move stack pages down in memory. */
 	if (stack_shift) {
-		ret = shift_arg_pages(vma, stack_shift);
+		/*
+		 * During bprm_mm_init(), we create a temporary stack at STACK_TOP_MAX.  Once
+		 * the binfmt code determines where the new stack should reside, we shift it to
+		 * its final location.
+		 */
+		ret = relocate_vma_down(vma, stack_shift);
 		if (ret)
 			goto out_unlock;
 	}
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 4d2b5538925b..418aca7e37a6 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -998,12 +998,6 @@ static inline struct vm_area_struct *vma_prev(struct vma_iterator *vmi)
 	return mas_prev(&vmi->mas, 0);
 }

-static inline
-struct vm_area_struct *vma_iter_prev_range(struct vma_iterator *vmi)
-{
-	return mas_prev_range(&vmi->mas, 0);
-}
-
 static inline unsigned long vma_iter_addr(struct vma_iterator *vmi)
 {
 	return vmi->mas.index;
@@ -2523,11 +2517,6 @@ int set_page_dirty_lock(struct page *page);

 int get_cmdline(struct task_struct *task, char *buffer, int buflen);

-extern unsigned long move_page_tables(struct vm_area_struct *vma,
-		unsigned long old_addr, struct vm_area_struct *new_vma,
-		unsigned long new_addr, unsigned long len,
-		bool need_rmap_locks, bool for_stack);
-
 /*
  * Flags used by change_protection().  For now we make it a bitmap so
  * that we can pass in multiple flags just like parameters.  However
@@ -3273,11 +3262,6 @@ void anon_vma_interval_tree_verify(struct anon_vma_chain *node);

 /* mmap.c */
 extern int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin);
-extern int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma,
-		      unsigned long start, unsigned long end, pgoff_t pgoff,
-		      struct vm_area_struct *next);
-extern int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma,
-		       unsigned long start, unsigned long end, pgoff_t pgoff);
 extern struct anon_vma *find_mergeable_anon_vma(struct vm_area_struct *);
 extern int insert_vm_struct(struct mm_struct *, struct vm_area_struct *);
 extern void unlink_file_vma(struct vm_area_struct *);
@@ -3285,6 +3269,7 @@ extern struct vm_area_struct *copy_vma(struct vm_area_struct **,
 	unsigned long addr, unsigned long len, pgoff_t pgoff,
 	bool *need_rmap_locks);
 extern void exit_mmap(struct mm_struct *);
+extern int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift);

 static inline int check_data_rlimit(unsigned long rlim,
 				    unsigned long new,
diff --git a/mm/internal.h b/mm/internal.h
index 81564ce0f9e2..a4d0e98ccb97 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -1305,6 +1305,12 @@ static inline struct vm_area_struct
 			  vma_policy(vma), new_ctx, anon_vma_name(vma));
 }

+int vma_expand(struct vma_iterator *vmi, struct vm_area_struct *vma,
+	      unsigned long start, unsigned long end, pgoff_t pgoff,
+	      struct vm_area_struct *next);
+int vma_shrink(struct vma_iterator *vmi, struct vm_area_struct *vma,
+	       unsigned long start, unsigned long end, pgoff_t pgoff);
+
 enum {
 	/* mark page accessed */
 	FOLL_TOUCH = 1 << 16,
@@ -1528,6 +1534,12 @@ static inline int vma_iter_store_gfp(struct vma_iterator *vmi,
 	return 0;
 }

+static inline
+struct vm_area_struct *vma_iter_prev_range(struct vma_iterator *vmi)
+{
+	return mas_prev_range(&vmi->mas, 0);
+}
+
 /*
  * VMA lock generalization
  */
@@ -1639,4 +1651,10 @@ void unlink_file_vma_batch_init(struct unlink_vma_file_batch *);
 void unlink_file_vma_batch_add(struct unlink_vma_file_batch *, struct vm_area_struct *);
 void unlink_file_vma_batch_final(struct unlink_vma_file_batch *);

+/* mremap.c */
+unsigned long move_page_tables(struct vm_area_struct *vma,
+	unsigned long old_addr, struct vm_area_struct *new_vma,
+	unsigned long new_addr, unsigned long len,
+	bool need_rmap_locks, bool for_stack);
+
 #endif	/* __MM_INTERNAL_H */
diff --git a/mm/mmap.c b/mm/mmap.c
index e42d89f98071..c1567b8b2a0a 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -4058,3 +4058,84 @@ static int __meminit init_reserve_notifier(void)
 	return 0;
 }
 subsys_initcall(init_reserve_notifier);
+
+/*
+ * Relocate a VMA downwards by shift bytes. There cannot be any VMAs between
+ * this VMA and its relocated range, which will now reside at [vma->vm_start -
+ * shift, vma->vm_end - shift).
+ *
+ * This function is almost certainly NOT what you want for anything other than
+ * early executable temporary stack relocation.
+ */
+int relocate_vma_down(struct vm_area_struct *vma, unsigned long shift)
+{
+	/*
+	 * The process proceeds as follows:
+	 *
+	 * 1) Use shift to calculate the new vma endpoints.
+	 * 2) Extend vma to cover both the old and new ranges.  This ensures the
+	 *    arguments passed to subsequent functions are consistent.
+	 * 3) Move vma's page tables to the new range.
+	 * 4) Free up any cleared pgd range.
+	 * 5) Shrink the vma to cover only the new range.
+	 */
+
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned long old_start = vma->vm_start;
+	unsigned long old_end = vma->vm_end;
+	unsigned long length = old_end - old_start;
+	unsigned long new_start = old_start - shift;
+	unsigned long new_end = old_end - shift;
+	VMA_ITERATOR(vmi, mm, new_start);
+	struct vm_area_struct *next;
+	struct mmu_gather tlb;
+
+	BUG_ON(new_start > new_end);
+
+	/*
+	 * ensure there are no vmas between where we want to go
+	 * and where we are
+	 */
+	if (vma != vma_next(&vmi))
+		return -EFAULT;
+
+	vma_iter_prev_range(&vmi);
+	/*
+	 * cover the whole range: [new_start, old_end)
+	 */
+	if (vma_expand(&vmi, vma, new_start, old_end, vma->vm_pgoff, NULL))
+		return -ENOMEM;
+
+	/*
+	 * move the page tables downwards, on failure we rely on
+	 * process cleanup to remove whatever mess we made.
+	 */
+	if (length != move_page_tables(vma, old_start,
+				       vma, new_start, length, false, true))
+		return -ENOMEM;
+
+	lru_add_drain();
+	tlb_gather_mmu(&tlb, mm);
+	next = vma_next(&vmi);
+	if (new_end > old_start) {
+		/*
+		 * when the old and new regions overlap clear from new_end.
+		 */
+		free_pgd_range(&tlb, new_end, old_end, new_end,
+			next ? next->vm_start : USER_PGTABLES_CEILING);
+	} else {
+		/*
+		 * otherwise, clean from old_start; this is done to not touch
+		 * the address space in [new_end, old_start) some architectures
+		 * have constraints on va-space that make this illegal (IA64) -
+		 * for the others its just a little faster.
+		 */
+		free_pgd_range(&tlb, old_start, old_end, new_end,
+			next ? next->vm_start : USER_PGTABLES_CEILING);
+	}
+	tlb_finish_mmu(&tlb);
+
+	vma_prev(&vmi);
+	/* Shrink the vma to just the new range */
+	return vma_shrink(&vmi, vma, new_start, new_end, vma->vm_pgoff);
+}
--
2.45.2

Powered by blists - more mailing lists