From: Pavel Begunkov <[email protected]>
To: [email protected]
Cc: [email protected]
Subject: [PATCH v3 10/18] io_uring/memmap: implement kernel allocated regions
Date: Fri, 29 Nov 2024 13:34:31 +0000 [thread overview]
Message-ID: <7b8c40e6542546bbf93f4842a9a42a7373b81e0d.1732886067.git.asml.silence@gmail.com> (raw)
In-Reply-To: <[email protected]>
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 <[email protected]>
---
io_uring/memmap.c | 43 ++++++++++++++++++++++++++++++++++++++++---
io_uring/register.c | 2 ++
2 files changed, 42 insertions(+), 3 deletions(-)
diff --git a/io_uring/memmap.c b/io_uring/memmap.c
index a37ccb167258..0908a71bf57e 100644
--- a/io_uring/memmap.c
+++ b/io_uring/memmap.c
@@ -273,6 +273,39 @@ 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_array_node(gfp, NUMA_NO_NODE,
+ mr->nr_pages, 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)
{
@@ -283,9 +316,10 @@ int io_create_region(struct io_ring_ctx *ctx, struct io_mapped_region *mr,
return -EFAULT;
if (memchr_inv(®->__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;
@@ -304,7 +338,10 @@ 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;
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(®.__resv, 0, sizeof(reg.__resv)))
return -EINVAL;
if (reg.flags & ~IORING_MEM_REGION_REG_WAIT_ARG)
--
2.47.1
next prev parent reply other threads:[~2024-11-29 13:34 UTC|newest]
Thread overview: 21+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-11-29 13:34 [PATCH v3 00/18] kernel allocated regions and convert memmap to regions Pavel Begunkov
2024-11-29 13:34 ` [PATCH v3 01/18] io_uring: rename ->resize_lock Pavel Begunkov
2024-11-29 13:34 ` [PATCH v3 02/18] io_uring/rsrc: export io_check_coalesce_buffer Pavel Begunkov
2024-11-29 13:34 ` [PATCH v3 03/18] io_uring/memmap: flag vmap'ed regions Pavel Begunkov
2024-11-29 13:34 ` [PATCH v3 04/18] io_uring/memmap: flag regions with user pages Pavel Begunkov
2024-11-29 13:34 ` [PATCH v3 05/18] io_uring/memmap: account memory before pinning Pavel Begunkov
2024-11-29 13:34 ` [PATCH v3 06/18] io_uring/memmap: reuse io_free_region for failure path Pavel Begunkov
2024-11-29 13:34 ` [PATCH v3 07/18] io_uring/memmap: optimise single folio regions Pavel Begunkov
2024-11-29 13:34 ` [PATCH v3 08/18] io_uring/memmap: helper for pinning region pages Pavel Begunkov
2024-11-29 13:34 ` [PATCH v3 09/18] io_uring/memmap: add IO_REGION_F_SINGLE_REF Pavel Begunkov
2024-11-29 13:34 ` Pavel Begunkov [this message]
2024-11-29 13:34 ` [PATCH v3 11/18] io_uring/memmap: implement mmap for regions Pavel Begunkov
2024-11-29 13:34 ` [PATCH v3 12/18] io_uring: pass ctx to io_register_free_rings Pavel Begunkov
2024-11-29 13:34 ` [PATCH v3 13/18] io_uring: use region api for SQ Pavel Begunkov
2024-11-29 13:34 ` [PATCH v3 14/18] io_uring: use region api for CQ Pavel Begunkov
2024-11-29 13:34 ` [PATCH v3 15/18] io_uring/kbuf: use mmap_lock to sync with mmap Pavel Begunkov
2024-11-29 13:34 ` [PATCH v3 16/18] io_uring/kbuf: remove pbuf ring refcounting Pavel Begunkov
2024-11-29 13:34 ` [PATCH v3 17/18] io_uring/kbuf: use region api for pbuf rings Pavel Begunkov
2024-11-29 13:34 ` [PATCH v3 18/18] io_uring/memmap: unify io_uring mmap'ing code Pavel Begunkov
2024-11-29 16:04 ` [PATCH v3 00/18] kernel allocated regions and convert memmap to regions Jens Axboe
2024-11-29 16:06 ` Jens Axboe
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=7b8c40e6542546bbf93f4842a9a42a7373b81e0d.1732886067.git.asml.silence@gmail.com \
[email protected] \
[email protected] \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox