[PATCH v2 7/9] mm: vmalloc: Support multiple nodes in vread_iter

["Uladzislau Rezki (Sony)" <urezki@gmail.com>]

Extend the vread_iter() to be able to perform a sequential
reading of VAs which are spread among multiple nodes. So a
data read over the /dev/kmem correctly reflects a vmalloc
memory layout.

Signed-off-by: Uladzislau Rezki (Sony) <urezki@gmail.com>
---
 mm/vmalloc.c | 67 +++++++++++++++++++++++++++++++++++++++++-----------
 1 file changed, 53 insertions(+), 14 deletions(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 4fd4915c532d..968144c16237 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -870,7 +870,7 @@ unsigned long vmalloc_nr_pages(void)
 
 /* Look up the first VA which satisfies addr < va_end, NULL if none. */
 static struct vmap_area *
-find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root)
+__find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root)
 {
 	struct vmap_area *va = NULL;
 	struct rb_node *n = root->rb_node;
@@ -894,6 +894,41 @@ find_vmap_area_exceed_addr(unsigned long addr, struct rb_root *root)
 	return va;
 }
 
+/*
+ * Returns a node where a first VA, that satisfies addr < va_end, resides.
+ * If success, a node is locked. A user is responsible to unlock it when a
+ * VA is no longer needed to be accessed.
+ *
+ * Returns NULL if nothing found.
+ */
+static struct vmap_node *
+find_vmap_area_exceed_addr_lock(unsigned long addr, struct vmap_area **va)
+{
+	struct vmap_node *vn, *va_node = NULL;
+	struct vmap_area *va_lowest;
+	int i;
+
+	for (i = 0; i < nr_nodes; i++) {
+		vn = &nodes[i];
+
+		spin_lock(&vn->busy.lock);
+		va_lowest = __find_vmap_area_exceed_addr(addr, &vn->busy.root);
+		if (va_lowest) {
+			if (!va_node || va_lowest->va_start < (*va)->va_start) {
+				if (va_node)
+					spin_unlock(&va_node->busy.lock);
+
+				*va = va_lowest;
+				va_node = vn;
+				continue;
+			}
+		}
+		spin_unlock(&vn->busy.lock);
+	}
+
+	return va_node;
+}
+
 static struct vmap_area *__find_vmap_area(unsigned long addr, struct rb_root *root)
 {
 	struct rb_node *n = root->rb_node;
@@ -4048,6 +4083,7 @@ long vread_iter(struct iov_iter *iter, const char *addr, size_t count)
 	struct vm_struct *vm;
 	char *vaddr;
 	size_t n, size, flags, remains;
+	unsigned long next;
 
 	addr = kasan_reset_tag(addr);
 
@@ -4057,19 +4093,15 @@ long vread_iter(struct iov_iter *iter, const char *addr, size_t count)
 
 	remains = count;
 
-	/* Hooked to node_0 so far. */
-	vn = addr_to_node(0);
-	spin_lock(&vn->busy.lock);
-
-	va = find_vmap_area_exceed_addr((unsigned long)addr, &vn->busy.root);
-	if (!va)
+	vn = find_vmap_area_exceed_addr_lock((unsigned long) addr, &va);
+	if (!vn)
 		goto finished_zero;
 
 	/* no intersects with alive vmap_area */
 	if ((unsigned long)addr + remains <= va->va_start)
 		goto finished_zero;
 
-	list_for_each_entry_from(va, &vn->busy.head, list) {
+	do {
 		size_t copied;
 
 		if (remains == 0)
@@ -4084,10 +4116,10 @@ long vread_iter(struct iov_iter *iter, const char *addr, size_t count)
 		WARN_ON(flags == VMAP_BLOCK);
 
 		if (!vm && !flags)
-			continue;
+			goto next_va;
 
 		if (vm && (vm->flags & VM_UNINITIALIZED))
-			continue;
+			goto next_va;
 
 		/* Pair with smp_wmb() in clear_vm_uninitialized_flag() */
 		smp_rmb();
@@ -4096,7 +4128,7 @@ long vread_iter(struct iov_iter *iter, const char *addr, size_t count)
 		size = vm ? get_vm_area_size(vm) : va_size(va);
 
 		if (addr >= vaddr + size)
-			continue;
+			goto next_va;
 
 		if (addr < vaddr) {
 			size_t to_zero = min_t(size_t, vaddr - addr, remains);
@@ -4125,15 +4157,22 @@ long vread_iter(struct iov_iter *iter, const char *addr, size_t count)
 
 		if (copied != n)
 			goto finished;
-	}
+
+	next_va:
+		next = va->va_end;
+		spin_unlock(&vn->busy.lock);
+	} while ((vn = find_vmap_area_exceed_addr_lock(next, &va)));
 
 finished_zero:
-	spin_unlock(&vn->busy.lock);
+	if (vn)
+		spin_unlock(&vn->busy.lock);
+
 	/* zero-fill memory holes */
 	return count - remains + zero_iter(iter, remains);
 finished:
 	/* Nothing remains, or We couldn't copy/zero everything. */
-	spin_unlock(&vn->busy.lock);
+	if (vn)
+		spin_unlock(&vn->busy.lock);
 
 	return count - remains;
 }
-- 
2.30.2