mm: abstract the vma_merge()/split_vma() pattern for mprotect() et al.

mprotect() and other functions which change VMA parameters over a range
each employ a pattern of:-

1. Attempt to merge the range with adjacent VMAs.
2. If this fails, and the range spans a subset of the VMA, split it
   accordingly.

This is open-coded and duplicated in each case. Also in each case most of
the parameters passed to vma_merge() remain the same.

Create a new function, vma_modify(), which abstracts this operation,
accepting only those parameters which can be changed.

To avoid the mess of invoking each function call with unnecessary
parameters, create inline wrapper functions for each of the modify
operations, parameterised only by what is required to perform the action.

We can also significantly simplify the logic - by returning the VMA if we
split (or merged VMA if we do not) we no longer need specific handling for
merge/split cases in any of the call sites.

Note that the userfaultfd_release() case works even though it does not
split VMAs - since start is set to vma->vm_start and end is set to
vma->vm_end, the split logic does not trigger.

In addition, since we calculate pgoff to be equal to vma->vm_pgoff + (start
- vma->vm_start) >> PAGE_SHIFT, and start - vma->vm_start will be 0 in this
instance, this invocation will remain unchanged.

We eliminate a VM_WARN_ON() in mprotect_fixup() as this simply asserts that
vma_merge() correctly ensures that flags remain the same, something that is
already checked in is_mergeable_vma() and elsewhere, and in any case is not
specific to mprotect().

Link: https://lkml.kernel.org/r/0dfa9368f37199a423674bf0ee312e8ea0619044.1697043508.git.lstoakes@gmail.com
Signed-off-by: Lorenzo Stoakes <lstoakes@gmail.com>
Reviewed-by: Vlastimil Babka <vbabka@suse.cz>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Christian Brauner <brauner@kernel.org>
Cc: Liam R. Howlett <Liam.Howlett@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

5 files changed, 63 insertions, 91 deletions

diff --git a/mm/madvise.c b/mm/madvise.c
index 59e8860c86af..a6b48d4796ba 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -141,7 +141,6 @@ static int madvise_update_vma(struct vm_area_struct *vma,
 {
 	struct mm_struct *mm = vma->vm_mm;
 	int error;
-	pgoff_t pgoff;
 	VMA_ITERATOR(vmi, mm, start);
 
 	if (new_flags == vma->vm_flags && anon_vma_name_eq(anon_vma_name(vma), anon_name)) {
@@ -149,30 +148,13 @@ static int madvise_update_vma(struct vm_area_struct *vma,
 		return 0;
 	}
 
-	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
-	*prev = vma_merge(&vmi, mm, *prev, start, end, new_flags,
-			  vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
-			  vma->vm_userfaultfd_ctx, anon_name);
-	if (*prev) {
-		vma = *prev;
-		goto success;
-	}
+	vma = vma_modify_flags_name(&vmi, *prev, vma, start, end, new_flags,
+				    anon_name);
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
 
 	*prev = vma;
 
-	if (start != vma->vm_start) {
-		error = split_vma(&vmi, vma, start, 1);
-		if (error)
-			return error;
-	}
-
-	if (end != vma->vm_end) {
-		error = split_vma(&vmi, vma, end, 0);
-		if (error)
-			return error;
-	}
-
-success:
 	/* vm_flags is protected by the mmap_lock held in write mode. */
 	vma_start_write(vma);
 	vm_flags_reset(vma, new_flags);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 38a47fa33ef4..8bb5b4b4b395 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -811,10 +811,7 @@ static int mbind_range(struct vma_iterator *vmi, struct vm_area_struct *vma,
 		struct vm_area_struct **prev, unsigned long start,
 		unsigned long end, struct mempolicy *new_pol)
 {
-	struct vm_area_struct *merged;
 	unsigned long vmstart, vmend;
-	pgoff_t pgoff;
-	int err;
 
 	vmend = min(end, vma->vm_end);
 	if (start > vma->vm_start) {
@@ -829,26 +826,9 @@ static int mbind_range(struct vma_iterator *vmi, struct vm_area_struct *vma,
 		return 0;
 	}
 
-	pgoff = vma->vm_pgoff + ((vmstart - vma->vm_start) >> PAGE_SHIFT);
-	merged = vma_merge(vmi, vma->vm_mm, *prev, vmstart, vmend, vma->vm_flags,
-			 vma->anon_vma, vma->vm_file, pgoff, new_pol,
-			 vma->vm_userfaultfd_ctx, anon_vma_name(vma));
-	if (merged) {
-		*prev = merged;
-		return vma_replace_policy(merged, new_pol);
-	}
-
-	if (vma->vm_start != vmstart) {
-		err = split_vma(vmi, vma, vmstart, 1);
-		if (err)
-			return err;
-	}
-
-	if (vma->vm_end != vmend) {
-		err = split_vma(vmi, vma, vmend, 0);
-		if (err)
-			return err;
-	}
+	vma =  vma_modify_policy(vmi, *prev, vma, vmstart, vmend, new_pol);
+	if (IS_ERR(vma))
+		return PTR_ERR(vma);
 
 	*prev = vma;
 	return vma_replace_policy(vma, new_pol);
diff --git a/mm/mlock.c b/mm/mlock.c
index 42b6865f8f82..aa44456200e3 100644
--- a/mm/mlock.c
+++ b/mm/mlock.c
@@ -476,7 +476,6 @@ static int mlock_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma,
 	       unsigned long end, vm_flags_t newflags)
 {
 	struct mm_struct *mm = vma->vm_mm;
-	pgoff_t pgoff;
 	int nr_pages;
 	int ret = 0;
 	vm_flags_t oldflags = vma->vm_flags;
@@ -487,28 +486,12 @@ static int mlock_fixup(struct vma_iterator *vmi, struct vm_area_struct *vma,
 		/* don't set VM_LOCKED or VM_LOCKONFAULT and don't count */
 		goto out;
 
-	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
-	*prev = vma_merge(vmi, mm, *prev, start, end, newflags,
-			vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
-			vma->vm_userfaultfd_ctx, anon_vma_name(vma));
-	if (*prev) {
-		vma = *prev;
-		goto success;
-	}
-
-	if (start != vma->vm_start) {
-		ret = split_vma(vmi, vma, start, 1);
-		if (ret)
-			goto out;
-	}
-
-	if (end != vma->vm_end) {
-		ret = split_vma(vmi, vma, end, 0);
-		if (ret)
-			goto out;
+	vma = vma_modify_flags(vmi, *prev, vma, start, end, newflags);
+	if (IS_ERR(vma)) {
+		ret = PTR_ERR(vma);
+		goto out;
 	}
 
-success:
 	/*
 	 * Keep track of amount of locked VM.
 	 */
diff --git a/mm/mmap.c b/mm/mmap.c
index 673429ee8a9e..bca685820763 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2438,6 +2438,54 @@ int split_vma(struct vma_iterator *vmi, struct vm_area_struct *vma,
 }
 
 /*
+ * We are about to modify one or multiple of a VMA's flags, policy, userfaultfd
+ * context and anonymous VMA name within the range [start, end).
+ *
+ * As a result, we might be able to merge the newly modified VMA range with an
+ * adjacent VMA with identical properties.
+ *
+ * If no merge is possible and the range does not span the entirety of the VMA,
+ * we then need to split the VMA to accommodate the change.
+ *
+ * The function returns either the merged VMA, the original VMA if a split was
+ * required instead, or an error if the split failed.
+ */
+struct vm_area_struct *vma_modify(struct vma_iterator *vmi,
+				  struct vm_area_struct *prev,
+				  struct vm_area_struct *vma,
+				  unsigned long start, unsigned long end,
+				  unsigned long vm_flags,
+				  struct mempolicy *policy,
+				  struct vm_userfaultfd_ctx uffd_ctx,
+				  struct anon_vma_name *anon_name)
+{
+	pgoff_t pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
+	struct vm_area_struct *merged;
+
+	merged = vma_merge(vmi, vma->vm_mm, prev, start, end, vm_flags,
+			   vma->anon_vma, vma->vm_file, pgoff, policy,
+			   uffd_ctx, anon_name);
+	if (merged)
+		return merged;
+
+	if (vma->vm_start < start) {
+		int err = split_vma(vmi, vma, start, 1);
+
+		if (err)
+			return ERR_PTR(err);
+	}
+
+	if (vma->vm_end > end) {
+		int err = split_vma(vmi, vma, end, 0);
+
+		if (err)
+			return ERR_PTR(err);
+	}
+
+	return vma;
+}
+
+/*
  * do_vmi_align_munmap() - munmap the aligned region from @start to @end.
  * @vmi: The vma iterator
  * @vma: The starting vm_area_struct
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 03e2cec3e669..f1dc8f8c84ef 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -581,7 +581,6 @@ mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb,
 	long nrpages = (end - start) >> PAGE_SHIFT;
 	unsigned int mm_cp_flags = 0;
 	unsigned long charged = 0;
-	pgoff_t pgoff;
 	int error;
 
 	if (newflags == oldflags) {
@@ -631,34 +630,14 @@ mprotect_fixup(struct vma_iterator *vmi, struct mmu_gather *tlb,
 		newflags &= ~VM_ACCOUNT;
 	}
 
-	/*
-	 * First try to merge with previous and/or next vma.
-	 */
-	pgoff = vma->vm_pgoff + ((start - vma->vm_start) >> PAGE_SHIFT);
-	*pprev = vma_merge(vmi, mm, *pprev, start, end, newflags,
-			   vma->anon_vma, vma->vm_file, pgoff, vma_policy(vma),
-			   vma->vm_userfaultfd_ctx, anon_vma_name(vma));
-	if (*pprev) {
-		vma = *pprev;
-		VM_WARN_ON((vma->vm_flags ^ newflags) & ~VM_SOFTDIRTY);
-		goto success;
+	vma = vma_modify_flags(vmi, *pprev, vma, start, end, newflags);
+	if (IS_ERR(vma)) {
+		error = PTR_ERR(vma);
+		goto fail;
 	}
 
 	*pprev = vma;
 
-	if (start != vma->vm_start) {
-		error = split_vma(vmi, vma, start, 1);
-		if (error)
-			goto fail;
-	}
-
-	if (end != vma->vm_end) {
-		error = split_vma(vmi, vma, end, 0);
-		if (error)
-			goto fail;
-	}
-
-success:
 	/*
 	 * vm_flags and vm_page_prot are protected by the mmap_lock
 	 * held in write mode.