Merge tag 'for-5.20/io_uring-zerocopy-send-2022-07-29' of git://git.kernel.dk/linux-block

Pull io_uring zerocopy support from Jens Axboe:
 "This adds support for efficient support for zerocopy sends through
  io_uring. Both ipv4 and ipv6 is supported, as well as both TCP and
  UDP.

  The core network changes to support this is in a stable branch from
  Jakub that both io_uring and net-next has pulled in, and the io_uring
  changes are layered on top of that.

  All of the work has been done by Pavel"

* tag 'for-5.20/io_uring-zerocopy-send-2022-07-29' of git://git.kernel.dk/linux-block: (34 commits)
  io_uring: notification completion optimisation
  io_uring: export req alloc from core
  io_uring/net: use unsigned for flags
  io_uring/net: make page accounting more consistent
  io_uring/net: checks errors of zc mem accounting
  io_uring/net: improve io_get_notif_slot types
  selftests/io_uring: test zerocopy send
  io_uring: enable managed frags with register buffers
  io_uring: add zc notification flush requests
  io_uring: rename IORING_OP_FILES_UPDATE
  io_uring: flush notifiers after sendzc
  io_uring: sendzc with fixed buffers
  io_uring: allow to pass addr into sendzc
  io_uring: account locked pages for non-fixed zc
  io_uring: wire send zc request type
  io_uring: add notification slot registration
  io_uring: add rsrc referencing for notifiers
  io_uring: complete notifiers in tw
  io_uring: cache struct io_notif
  io_uring: add zc notification infrastructure
  ...

1 files changed, 159 insertions, 0 deletions

diff --git a/io_uring/notif.c b/io_uring/notif.c
new file mode 100644
index 000000000000..b5f989dff9de
--- /dev/null
+++ b/io_uring/notif.c
@@ -0,0 +1,159 @@
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/file.h>
+#include <linux/slab.h>
+#include <linux/net.h>
+#include <linux/io_uring.h>
+
+#include "io_uring.h"
+#include "notif.h"
+#include "rsrc.h"
+
+static void __io_notif_complete_tw(struct io_kiocb *notif, bool *locked)
+{
+	struct io_notif_data *nd = io_notif_to_data(notif);
+	struct io_ring_ctx *ctx = notif->ctx;
+
+	if (nd->account_pages && ctx->user) {
+		__io_unaccount_mem(ctx->user, nd->account_pages);
+		nd->account_pages = 0;
+	}
+	io_req_task_complete(notif, locked);
+}
+
+static inline void io_notif_complete(struct io_kiocb *notif)
+	__must_hold(&notif->ctx->uring_lock)
+{
+	bool locked = true;
+
+	__io_notif_complete_tw(notif, &locked);
+}
+
+static void io_uring_tx_zerocopy_callback(struct sk_buff *skb,
+					  struct ubuf_info *uarg,
+					  bool success)
+{
+	struct io_notif_data *nd = container_of(uarg, struct io_notif_data, uarg);
+	struct io_kiocb *notif = cmd_to_io_kiocb(nd);
+
+	if (refcount_dec_and_test(&uarg->refcnt)) {
+		notif->io_task_work.func = __io_notif_complete_tw;
+		io_req_task_work_add(notif);
+	}
+}
+
+struct io_kiocb *io_alloc_notif(struct io_ring_ctx *ctx,
+				struct io_notif_slot *slot)
+	__must_hold(&ctx->uring_lock)
+{
+	struct io_kiocb *notif;
+	struct io_notif_data *nd;
+
+	if (unlikely(!io_alloc_req_refill(ctx)))
+		return NULL;
+	notif = io_alloc_req(ctx);
+	notif->opcode = IORING_OP_NOP;
+	notif->flags = 0;
+	notif->file = NULL;
+	notif->task = current;
+	io_get_task_refs(1);
+	notif->rsrc_node = NULL;
+	io_req_set_rsrc_node(notif, ctx, 0);
+	notif->cqe.user_data = slot->tag;
+	notif->cqe.flags = slot->seq++;
+	notif->cqe.res = 0;
+
+	nd = io_notif_to_data(notif);
+	nd->account_pages = 0;
+	nd->uarg.flags = SKBFL_ZEROCOPY_FRAG | SKBFL_DONT_ORPHAN;
+	nd->uarg.callback = io_uring_tx_zerocopy_callback;
+	/* master ref owned by io_notif_slot, will be dropped on flush */
+	refcount_set(&nd->uarg.refcnt, 1);
+	return notif;
+}
+
+void io_notif_slot_flush(struct io_notif_slot *slot)
+	__must_hold(&ctx->uring_lock)
+{
+	struct io_kiocb *notif = slot->notif;
+	struct io_notif_data *nd = io_notif_to_data(notif);
+
+	slot->notif = NULL;
+
+	/* drop slot's master ref */
+	if (refcount_dec_and_test(&nd->uarg.refcnt))
+		io_notif_complete(notif);
+}
+
+__cold int io_notif_unregister(struct io_ring_ctx *ctx)
+	__must_hold(&ctx->uring_lock)
+{
+	int i;
+
+	if (!ctx->notif_slots)
+		return -ENXIO;
+
+	for (i = 0; i < ctx->nr_notif_slots; i++) {
+		struct io_notif_slot *slot = &ctx->notif_slots[i];
+		struct io_kiocb *notif = slot->notif;
+		struct io_notif_data *nd;
+
+		if (!notif)
+			continue;
+		nd = io_kiocb_to_cmd(notif);
+		slot->notif = NULL;
+		if (!refcount_dec_and_test(&nd->uarg.refcnt))
+			continue;
+		notif->io_task_work.func = __io_notif_complete_tw;
+		io_req_task_work_add(notif);
+	}
+
+	kvfree(ctx->notif_slots);
+	ctx->notif_slots = NULL;
+	ctx->nr_notif_slots = 0;
+	return 0;
+}
+
+__cold int io_notif_register(struct io_ring_ctx *ctx,
+			     void __user *arg, unsigned int size)
+	__must_hold(&ctx->uring_lock)
+{
+	struct io_uring_notification_slot __user *slots;
+	struct io_uring_notification_slot slot;
+	struct io_uring_notification_register reg;
+	unsigned i;
+
+	BUILD_BUG_ON(sizeof(struct io_notif_data) > 64);
+
+	if (ctx->nr_notif_slots)
+		return -EBUSY;
+	if (size != sizeof(reg))
+		return -EINVAL;
+	if (copy_from_user(&reg, arg, sizeof(reg)))
+		return -EFAULT;
+	if (!reg.nr_slots || reg.nr_slots > IORING_MAX_NOTIF_SLOTS)
+		return -EINVAL;
+	if (reg.resv || reg.resv2 || reg.resv3)
+		return -EINVAL;
+
+	slots = u64_to_user_ptr(reg.data);
+	ctx->notif_slots = kvcalloc(reg.nr_slots, sizeof(ctx->notif_slots[0]),
+				GFP_KERNEL_ACCOUNT);
+	if (!ctx->notif_slots)
+		return -ENOMEM;
+
+	for (i = 0; i < reg.nr_slots; i++, ctx->nr_notif_slots++) {
+		struct io_notif_slot *notif_slot = &ctx->notif_slots[i];
+
+		if (copy_from_user(&slot, &slots[i], sizeof(slot))) {
+			io_notif_unregister(ctx);
+			return -EFAULT;
+		}
+		if (slot.resv[0] | slot.resv[1] | slot.resv[2]) {
+			io_notif_unregister(ctx);
+			return -EINVAL;
+		}
+		notif_slot->tag = slot.tag;
+	}
+	return 0;
+}