[PATCH 10/11] io_uring/memmap: implement kernel allocated regions

[Pavel Begunkov <asml.silence@xxxxxxxxx>]

Allow the kernel to allocate memory for a region. That's the classical
way SQ/CQ are allocated. It's not yet useful to user space as there
is no way to mmap it, which is why it's explicitly disabled in
io_register_mem_region().

Signed-off-by: Pavel Begunkov <asml.silence@xxxxxxxxx>
---
 io_uring/memmap.c   | 44 +++++++++++++++++++++++++++++++++++++++++---
 io_uring/register.c |  2 ++
 2 files changed, 43 insertions(+), 3 deletions(-)

diff --git a/io_uring/memmap.c b/io_uring/memmap.c
index cdd620bdd3ee..8598770bc385 100644
--- a/io_uring/memmap.c
+++ b/io_uring/memmap.c
@@ -263,6 +263,39 @@ static int io_region_pin_pages(struct io_ring_ctx *ctx,
 	return 0;
 }
 
+static int io_region_allocate_pages(struct io_ring_ctx *ctx,
+				    struct io_mapped_region *mr,
+				    struct io_uring_region_desc *reg)
+{
+	gfp_t gfp = GFP_KERNEL_ACCOUNT | __GFP_ZERO | __GFP_NOWARN;
+	unsigned long size = mr->nr_pages << PAGE_SHIFT;
+	unsigned long nr_allocated;
+	struct page **pages;
+	void *p;
+
+	pages = kvmalloc_array(mr->nr_pages, sizeof(*pages), gfp);
+	if (!pages)
+		return -ENOMEM;
+
+	p = io_mem_alloc_compound(pages, mr->nr_pages, size, gfp);
+	if (!IS_ERR(p)) {
+		mr->flags |= IO_REGION_F_SINGLE_REF;
+		mr->pages = pages;
+		return 0;
+	}
+
+	nr_allocated = alloc_pages_bulk_noprof(gfp, numa_node_id(), NULL,
+					       mr->nr_pages, NULL, pages);
+	if (nr_allocated != mr->nr_pages) {
+		if (nr_allocated)
+			release_pages(pages, nr_allocated);
+		kvfree(pages);
+		return -ENOMEM;
+	}
+	mr->pages = pages;
+	return 0;
+}
+
 int io_create_region(struct io_ring_ctx *ctx, struct io_mapped_region *mr,
 		     struct io_uring_region_desc *reg)
 {
@@ -273,9 +306,10 @@ int io_create_region(struct io_ring_ctx *ctx, struct io_mapped_region *mr,
 		return -EFAULT;
 	if (memchr_inv(&reg->__resv, 0, sizeof(reg->__resv)))
 		return -EINVAL;
-	if (reg->flags != IORING_MEM_REGION_TYPE_USER)
+	if (reg->flags & ~IORING_MEM_REGION_TYPE_USER)
 		return -EINVAL;
-	if (!reg->user_addr)
+	/* user_addr should be set IFF it's a user memory backed region */
+	if ((reg->flags & IORING_MEM_REGION_TYPE_USER) != !!reg->user_addr)
 		return -EFAULT;
 	if (!reg->size || reg->mmap_offset || reg->id)
 		return -EINVAL;
@@ -294,9 +328,13 @@ int io_create_region(struct io_ring_ctx *ctx, struct io_mapped_region *mr,
 	}
 	mr->nr_pages = nr_pages;
 
-	ret = io_region_pin_pages(ctx, mr, reg);
+	if (reg->flags & IORING_MEM_REGION_TYPE_USER)
+		ret = io_region_pin_pages(ctx, mr, reg);
+	else
+		ret = io_region_allocate_pages(ctx, mr, reg);
 	if (ret)
 		goto out_free;
+
 	ret = io_region_init_ptr(mr);
 	if (ret)
 		goto out_free;
diff --git a/io_uring/register.c b/io_uring/register.c
index ba61697d7a53..f043d3f6b026 100644
--- a/io_uring/register.c
+++ b/io_uring/register.c
@@ -586,6 +586,8 @@ static int io_register_mem_region(struct io_ring_ctx *ctx, void __user *uarg)
 	if (copy_from_user(&rd, rd_uptr, sizeof(rd)))
 		return -EFAULT;
 
+	if (!(rd.flags & IORING_MEM_REGION_TYPE_USER))
+		return -EINVAL;
 	if (memchr_inv(&reg.__resv, 0, sizeof(reg.__resv)))
 		return -EINVAL;
 	if (reg.flags & ~IORING_MEM_REGION_REG_WAIT_ARG)
-- 
2.46.0