[PATCH v3 3/3] mm: use vma_start_write_killable() in process_vma_walk_lock()

[Suren Baghdasaryan <surenb@google.com>]

Replace vma_start_write() with vma_start_write_killable() when
process_vma_walk_lock() is used with PGWALK_WRLOCK option.
Adjust its direct and indirect users to check for a possible error
and handle it. Ensure users handle EINTR correctly and do not ignore
it.

Signed-off-by: Suren Baghdasaryan <surenb@google.com>
---
 arch/s390/kvm/kvm-s390.c |  2 +-
 fs/proc/task_mmu.c       |  5 ++++-
 mm/mempolicy.c           | 14 +++++++++++---
 mm/pagewalk.c            | 20 ++++++++++++++------
 mm/vma.c                 | 22 ++++++++++++++--------
 mm/vma.h                 |  6 ++++++
 6 files changed, 50 insertions(+), 19 deletions(-)

diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
index 7a175d86cef0..337e4f7db63a 100644
--- a/arch/s390/kvm/kvm-s390.c
+++ b/arch/s390/kvm/kvm-s390.c
@@ -2948,7 +2948,7 @@ int kvm_arch_vm_ioctl(struct file *filp, unsigned int ioctl, unsigned long arg)
 		}
 		/* must be called without kvm->lock */
 		r = kvm_s390_handle_pv(kvm, &args);
-		if (copy_to_user(argp, &args, sizeof(args))) {
+		if (r != -EINTR && copy_to_user(argp, &args, sizeof(args))) {
 			r = -EFAULT;
 			break;
 		}
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index e091931d7ca1..1238a2988eb6 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -1797,6 +1797,7 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 		struct clear_refs_private cp = {
 			.type = type,
 		};
+		int err;
 
 		if (mmap_write_lock_killable(mm)) {
 			count = -EINTR;
@@ -1824,7 +1825,9 @@ static ssize_t clear_refs_write(struct file *file, const char __user *buf,
 						0, mm, 0, -1UL);
 			mmu_notifier_invalidate_range_start(&range);
 		}
-		walk_page_range(mm, 0, -1, &clear_refs_walk_ops, &cp);
+		err = walk_page_range(mm, 0, -1, &clear_refs_walk_ops, &cp);
+		if (err < 0)
+			count = err;
 		if (type == CLEAR_REFS_SOFT_DIRTY) {
 			mmu_notifier_invalidate_range_end(&range);
 			flush_tlb_mm(mm);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 90939f5bde02..3c8b3dfc9c56 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -988,6 +988,8 @@ queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end,
 			&queue_pages_lock_vma_walk_ops : &queue_pages_walk_ops;
 
 	err = walk_page_range(mm, start, end, ops, &qp);
+	if (err == -EINTR)
+		return err;
 
 	if (!qp.first)
 		/* whole range in hole */
@@ -1309,9 +1311,14 @@ static long migrate_to_node(struct mm_struct *mm, int source, int dest,
 				      flags | MPOL_MF_DISCONTIG_OK, &pagelist);
 	mmap_read_unlock(mm);
 
+	if (nr_failed == -EINTR)
+		err = nr_failed;
+
 	if (!list_empty(&pagelist)) {
-		err = migrate_pages(&pagelist, alloc_migration_target, NULL,
-			(unsigned long)&mtc, MIGRATE_SYNC, MR_SYSCALL, NULL);
+		if (!err)
+			err = migrate_pages(&pagelist, alloc_migration_target,
+					    NULL, (unsigned long)&mtc,
+					    MIGRATE_SYNC, MR_SYSCALL, NULL);
 		if (err)
 			putback_movable_pages(&pagelist);
 	}
@@ -1611,7 +1618,8 @@ static long do_mbind(unsigned long start, unsigned long len,
 				MR_MEMPOLICY_MBIND, NULL);
 	}
 
-	if (nr_failed && (flags & MPOL_MF_STRICT))
+	/* Do not mask EINTR */
+	if ((err != -EINTR) && (nr_failed && (flags & MPOL_MF_STRICT)))
 		err = -EIO;
 	if (!list_empty(&pagelist))
 		putback_movable_pages(&pagelist);
diff --git a/mm/pagewalk.c b/mm/pagewalk.c
index a94c401ab2cf..dc9f7a7709c6 100644
--- a/mm/pagewalk.c
+++ b/mm/pagewalk.c
@@ -425,14 +425,13 @@ static inline void process_mm_walk_lock(struct mm_struct *mm,
 		mmap_assert_write_locked(mm);
 }
 
-static inline void process_vma_walk_lock(struct vm_area_struct *vma,
+static inline int process_vma_walk_lock(struct vm_area_struct *vma,
 					 enum page_walk_lock walk_lock)
 {
 #ifdef CONFIG_PER_VMA_LOCK
 	switch (walk_lock) {
 	case PGWALK_WRLOCK:
-		vma_start_write(vma);
-		break;
+		return vma_start_write_killable(vma);
 	case PGWALK_WRLOCK_VERIFY:
 		vma_assert_write_locked(vma);
 		break;
@@ -444,6 +443,7 @@ static inline void process_vma_walk_lock(struct vm_area_struct *vma,
 		break;
 	}
 #endif
+	return 0;
 }
 
 /*
@@ -487,7 +487,9 @@ int walk_page_range_mm_unsafe(struct mm_struct *mm, unsigned long start,
 			if (ops->pte_hole)
 				err = ops->pte_hole(start, next, -1, &walk);
 		} else { /* inside vma */
-			process_vma_walk_lock(vma, ops->walk_lock);
+			err = process_vma_walk_lock(vma, ops->walk_lock);
+			if (err)
+				break;
 			walk.vma = vma;
 			next = min(end, vma->vm_end);
 			vma = find_vma(mm, vma->vm_end);
@@ -704,6 +706,7 @@ int walk_page_range_vma_unsafe(struct vm_area_struct *vma, unsigned long start,
 		.vma		= vma,
 		.private	= private,
 	};
+	int err;
 
 	if (start >= end || !walk.mm)
 		return -EINVAL;
@@ -711,7 +714,9 @@ int walk_page_range_vma_unsafe(struct vm_area_struct *vma, unsigned long start,
 		return -EINVAL;
 
 	process_mm_walk_lock(walk.mm, ops->walk_lock);
-	process_vma_walk_lock(vma, ops->walk_lock);
+	err = process_vma_walk_lock(vma, ops->walk_lock);
+	if (err)
+		return err;
 	return __walk_page_range(start, end, &walk);
 }
 
@@ -734,6 +739,7 @@ int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
 		.vma		= vma,
 		.private	= private,
 	};
+	int err;
 
 	if (!walk.mm)
 		return -EINVAL;
@@ -741,7 +747,9 @@ int walk_page_vma(struct vm_area_struct *vma, const struct mm_walk_ops *ops,
 		return -EINVAL;
 
 	process_mm_walk_lock(walk.mm, ops->walk_lock);
-	process_vma_walk_lock(vma, ops->walk_lock);
+	err = process_vma_walk_lock(vma, ops->walk_lock);
+	if (err)
+		return err;
 	return __walk_page_range(vma->vm_start, vma->vm_end, &walk);
 }
 
diff --git a/mm/vma.c b/mm/vma.c
index 9f2664f1d078..46bbad6e64a4 100644
--- a/mm/vma.c
+++ b/mm/vma.c
@@ -998,14 +998,18 @@ static __must_check struct vm_area_struct *vma_merge_existing_range(
 	if (anon_dup)
 		unlink_anon_vmas(anon_dup);
 
-	/*
-	 * This means we have failed to clone anon_vma's correctly, but no
-	 * actual changes to VMAs have occurred, so no harm no foul - if the
-	 * user doesn't want this reported and instead just wants to give up on
-	 * the merge, allow it.
-	 */
-	if (!vmg->give_up_on_oom)
-		vmg->state = VMA_MERGE_ERROR_NOMEM;
+	if (err == -EINTR) {
+		vmg->state = VMA_MERGE_ERROR_INTR;
+	} else {
+		/*
+		 * This means we have failed to clone anon_vma's correctly,
+		 * but no actual changes to VMAs have occurred, so no harm no
+		 * foul - if the user doesn't want this reported and instead
+		 * just wants to give up on the merge, allow it.
+		 */
+		if (!vmg->give_up_on_oom)
+			vmg->state = VMA_MERGE_ERROR_NOMEM;
+	}
 	return NULL;
 }
 
@@ -1681,6 +1685,8 @@ static struct vm_area_struct *vma_modify(struct vma_merge_struct *vmg)
 	merged = vma_merge_existing_range(vmg);
 	if (merged)
 		return merged;
+	if (vmg_intr(vmg))
+		return ERR_PTR(-EINTR);
 	if (vmg_nomem(vmg))
 		return ERR_PTR(-ENOMEM);
 
diff --git a/mm/vma.h b/mm/vma.h
index eba388c61ef4..fe4560f81f4f 100644
--- a/mm/vma.h
+++ b/mm/vma.h
@@ -56,6 +56,7 @@ struct vma_munmap_struct {
 enum vma_merge_state {
 	VMA_MERGE_START,
 	VMA_MERGE_ERROR_NOMEM,
+	VMA_MERGE_ERROR_INTR,
 	VMA_MERGE_NOMERGE,
 	VMA_MERGE_SUCCESS,
 };
@@ -226,6 +227,11 @@ static inline bool vmg_nomem(struct vma_merge_struct *vmg)
 	return vmg->state == VMA_MERGE_ERROR_NOMEM;
 }
 
+static inline bool vmg_intr(struct vma_merge_struct *vmg)
+{
+	return vmg->state == VMA_MERGE_ERROR_INTR;
+}
+
 /* Assumes addr >= vma->vm_start. */
 static inline pgoff_t vma_pgoff_offset(struct vm_area_struct *vma,
 				       unsigned long addr)
-- 
2.53.0.414.gf7e9f6c205-goog