Merge tag 'for-6.12/io_uring-20240913' of git://git.kernel.dk/linux

Pull io_uring updates from Jens Axboe:

 - NAPI fixes and cleanups (Pavel, Olivier)

 - Add support for absolute timeouts (Pavel)

 - Fixes for io-wq/sqpoll affinities (Felix)

 - Efficiency improvements for dealing with huge pages (Chenliang)

 - Support for a minwait mode, where the application essentially has two
   timouts - one smaller one that defines the batch timeout, and the
   overall large one similar to what we had before. This enables
   efficient use of batching based on count + timeout, while still
   working well with periods of less intensive workloads

 - Use ITER_UBUF for single segment sends

 - Add support for incremental buffer consumption. Right now each
   operation will always consume a full buffer. With incremental
   consumption, a recv/read operation only consumes the part of the
   buffer that it needs to satisfy the operation

 - Add support for GCOV for io_uring, to help retain a high coverage of
   test to code ratio

 - Fix regression with ocfs2, where an odd -EOPNOTSUPP wasn't correctly
   converted to a blocking retry

 - Add support for cloning registered buffers from one ring to another

 - Misc cleanups (Anuj, me)

* tag 'for-6.12/io_uring-20240913' of git://git.kernel.dk/linux: (35 commits)
  io_uring: add IORING_REGISTER_COPY_BUFFERS method
  io_uring/register: provide helper to get io_ring_ctx from 'fd'
  io_uring/rsrc: add reference count to struct io_mapped_ubuf
  io_uring/rsrc: clear 'slot' entry upfront
  io_uring/io-wq: inherit cpuset of cgroup in io worker
  io_uring/io-wq: do not allow pinning outside of cpuset
  io_uring/rw: drop -EOPNOTSUPP check in __io_complete_rw_common()
  io_uring/rw: treat -EOPNOTSUPP for IOCB_NOWAIT like -EAGAIN
  io_uring/sqpoll: do not allow pinning outside of cpuset
  io_uring/eventfd: move refs to refcount_t
  io_uring: remove unused rsrc_put_fn
  io_uring: add new line after variable declaration
  io_uring: add GCOV_PROFILE_URING Kconfig option
  io_uring/kbuf: add support for incremental buffer consumption
  io_uring/kbuf: pass in 'len' argument for buffer commit
  Revert "io_uring: Require zeroed sqe->len on provided-buffers send"
  io_uring/kbuf: move io_ring_head_to_buf() to kbuf.h
  io_uring/kbuf: add io_kbuf_commit() helper
  io_uring/kbuf: shrink nr_iovs/mode in struct buf_sel_arg
  io_uring: wire up min batch wake timeout
  ...

Author: torvalds

include/linux/io_uring_types.h

@@ -239,6 +239,9 @@ struct io_ring_ctx {
 		struct io_rings		*rings;
 		struct percpu_ref	refs;
 
+		clockid_t		clockid;
+		enum tk_offsets		clock_offset;
+
 		enum task_work_notify_mode	notify_method;
 		unsigned			sq_thread_idle;
 	} ____cacheline_aligned_in_smp;

include/uapi/linux/io_uring.h

@@ -440,11 +440,21 @@ struct io_uring_cqe {
  * IORING_CQE_F_SOCK_NONEMPTY	If set, more data to read after socket recv
  * IORING_CQE_F_NOTIF	Set for notification CQEs. Can be used to distinct
  * 			them from sends.
+ * IORING_CQE_F_BUF_MORE If set, the buffer ID set in the completion will get
+ *			more completions. In other words, the buffer is being
+ *			partially consumed, and will be used by the kernel for
+ *			more completions. This is only set for buffers used via
+ *			the incremental buffer consumption, as provided by
+ *			a ring buffer setup with IOU_PBUF_RING_INC. For any
+ *			other provided buffer type, all completions with a
+ *			buffer passed back is automatically returned to the
+ *			application.
  */
 #define IORING_CQE_F_BUFFER		(1U << 0)
 #define IORING_CQE_F_MORE		(1U << 1)
 #define IORING_CQE_F_SOCK_NONEMPTY	(1U << 2)
 #define IORING_CQE_F_NOTIF		(1U << 3)
+#define IORING_CQE_F_BUF_MORE		(1U << 4)
 
 #define IORING_CQE_BUFFER_SHIFT		16
 
@@ -507,6 +517,7 @@ struct io_cqring_offsets {
 #define IORING_ENTER_SQ_WAIT		(1U << 2)
 #define IORING_ENTER_EXT_ARG		(1U << 3)
 #define IORING_ENTER_REGISTERED_RING	(1U << 4)
+#define IORING_ENTER_ABS_TIMER		(1U << 5)
 
 /*
  * Passed in for io_uring_setup(2). Copied back with updated info on success
@@ -542,6 +553,7 @@ struct io_uring_params {
 #define IORING_FEAT_LINKED_FILE		(1U << 12)
 #define IORING_FEAT_REG_REG_RING	(1U << 13)
 #define IORING_FEAT_RECVSEND_BUNDLE	(1U << 14)
+#define IORING_FEAT_MIN_TIMEOUT		(1U << 15)
 
 /*
  * io_uring_register(2) opcodes and arguments
@@ -595,6 +607,11 @@ enum io_uring_register_op {
 	IORING_REGISTER_NAPI			= 27,
 	IORING_UNREGISTER_NAPI			= 28,
 
+	IORING_REGISTER_CLOCK			= 29,
+
+	/* copy registered buffers from source ring to current ring */
+	IORING_REGISTER_COPY_BUFFERS		= 30,
+
 	/* this goes last */
 	IORING_REGISTER_LAST,
 
@@ -675,6 +692,21 @@ struct io_uring_restriction {
 	__u32 resv2[3];
 };
 
+struct io_uring_clock_register {
+	__u32	clockid;
+	__u32	__resv[3];
+};
+
+enum {
+	IORING_REGISTER_SRC_REGISTERED = 1,
+};
+
+struct io_uring_copy_buffers {
+	__u32	src_fd;
+	__u32	flags;
+	__u32	pad[6];
+};
+
 struct io_uring_buf {
 	__u64	addr;
 	__u32	len;
@@ -707,9 +739,17 @@ struct io_uring_buf_ring {
  *			mmap(2) with the offset set as:
  *			IORING_OFF_PBUF_RING | (bgid << IORING_OFF_PBUF_SHIFT)
  *			to get a virtual mapping for the ring.
+ * IOU_PBUF_RING_INC:	If set, buffers consumed from this buffer ring can be
+ *			consumed incrementally. Normally one (or more) buffers
+ *			are fully consumed. With incremental consumptions, it's
+ *			feasible to register big ranges of buffers, and each
+ *			use of it will consume only as much as it needs. This
+ *			requires that both the kernel and application keep
+ *			track of where the current read/recv index is at.
  */
 enum io_uring_register_pbuf_ring_flags {
 	IOU_PBUF_RING_MMAP	= 1,
+	IOU_PBUF_RING_INC	= 2,
 };
 
 /* argument for IORING_(UN)REGISTER_PBUF_RING */
@@ -758,7 +798,7 @@ enum io_uring_register_restriction_op {
 struct io_uring_getevents_arg {
 	__u64	sigmask;
 	__u32	sigmask_sz;
-	__u32	pad;
+	__u32	min_wait_usec;
 	__u64	ts;
 };
 

init/Kconfig

@@ -1687,6 +1687,19 @@ config IO_URING
 	  applications to submit and complete IO through submission and
 	  completion rings that are shared between the kernel and application.
 
+config GCOV_PROFILE_URING
+	bool "Enable GCOV profiling on the io_uring subsystem"
+	depends on GCOV_KERNEL
+	help
+	  Enable GCOV profiling on the io_uring subsystem, to facilitate
+	  code coverage testing.
+
+	  If unsure, say N.
+
+	  Note that this will have a negative impact on the performance of
+	  the io_uring subsystem, hence this should only be enabled for
+	  specific test purposes.
+
 config ADVISE_SYSCALLS
 	bool "Enable madvise/fadvise syscalls" if EXPERT
 	default y

io_uring/Makefile

@@ -2,6 +2,10 @@
 #
 # Makefile for io_uring
 
+ifdef CONFIG_GCOV_PROFILE_URING
+GCOV_PROFILE := y
+endif
+
 obj-$(CONFIG_IO_URING)		+= io_uring.o opdef.o kbuf.o rsrc.o notif.o \
 					tctx.o filetable.o rw.o net.o poll.o \
 					eventfd.o uring_cmd.o openclose.o \

io_uring/eventfd.c

@@ -15,7 +15,7 @@ struct io_ev_fd {
 	struct eventfd_ctx	*cq_ev_fd;
 	unsigned int		eventfd_async: 1;
 	struct rcu_head		rcu;
-	atomic_t		refs;
+	refcount_t		refs;
 	atomic_t		ops;
 };
 
@@ -37,7 +37,7 @@ static void io_eventfd_do_signal(struct rcu_head *rcu)
 
 	eventfd_signal_mask(ev_fd->cq_ev_fd, EPOLL_URING_WAKE);
 
-	if (atomic_dec_and_test(&ev_fd->refs))
+	if (refcount_dec_and_test(&ev_fd->refs))
 		io_eventfd_free(rcu);
 }
 
@@ -63,7 +63,7 @@ void io_eventfd_signal(struct io_ring_ctx *ctx)
 	 */
 	if (unlikely(!ev_fd))
 		return;
-	if (!atomic_inc_not_zero(&ev_fd->refs))
+	if (!refcount_inc_not_zero(&ev_fd->refs))
 		return;
 	if (ev_fd->eventfd_async && !io_wq_current_is_worker())
 		goto out;
@@ -77,7 +77,7 @@ void io_eventfd_signal(struct io_ring_ctx *ctx)
 		}
 	}
 out:
-	if (atomic_dec_and_test(&ev_fd->refs))
+	if (refcount_dec_and_test(&ev_fd->refs))
 		call_rcu(&ev_fd->rcu, io_eventfd_free);
 }
 
@@ -126,6 +126,7 @@ int io_eventfd_register(struct io_ring_ctx *ctx, void __user *arg,
 	ev_fd->cq_ev_fd = eventfd_ctx_fdget(fd);
 	if (IS_ERR(ev_fd->cq_ev_fd)) {
 		int ret = PTR_ERR(ev_fd->cq_ev_fd);
+
 		kfree(ev_fd);
 		return ret;
 	}
@@ -136,7 +137,7 @@ int io_eventfd_register(struct io_ring_ctx *ctx, void __user *arg,
 
 	ev_fd->eventfd_async = eventfd_async;
 	ctx->has_evfd = true;
-	atomic_set(&ev_fd->refs, 1);
+	refcount_set(&ev_fd->refs, 1);
 	atomic_set(&ev_fd->ops, 0);
 	rcu_assign_pointer(ctx->io_ev_fd, ev_fd);
 	return 0;
@@ -151,7 +152,7 @@ int io_eventfd_unregister(struct io_ring_ctx *ctx)
 	if (ev_fd) {
 		ctx->has_evfd = false;
 		rcu_assign_pointer(ctx->io_ev_fd, NULL);
-		if (atomic_dec_and_test(&ev_fd->refs))
+		if (refcount_dec_and_test(&ev_fd->refs))
 			call_rcu(&ev_fd->rcu, io_eventfd_free);
 		return 0;
 	}

io_uring/fdinfo.c

@@ -221,7 +221,19 @@ __cold void io_uring_show_fdinfo(struct seq_file *m, struct file *file)
 			   cqe->user_data, cqe->res, cqe->flags);
 
 	}
-
 	spin_unlock(&ctx->completion_lock);
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	if (ctx->napi_enabled) {
+		seq_puts(m, "NAPI:\tenabled\n");
+		seq_printf(m, "napi_busy_poll_dt:\t%llu\n", ctx->napi_busy_poll_dt);
+		if (ctx->napi_prefer_busy_poll)
+			seq_puts(m, "napi_prefer_busy_poll:\ttrue\n");
+		else
+			seq_puts(m, "napi_prefer_busy_poll:\tfalse\n");
+	} else {
+		seq_puts(m, "NAPI:\tdisabled\n");
+	}
+#endif
 }
 #endif

io_uring/io-wq.c

@@ -13,6 +13,7 @@
 #include <linux/slab.h>
 #include <linux/rculist_nulls.h>
 #include <linux/cpu.h>
+#include <linux/cpuset.h>
 #include <linux/task_work.h>
 #include <linux/audit.h>
 #include <linux/mmu_context.h>
@@ -1167,7 +1168,7 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
 
 	if (!alloc_cpumask_var(&wq->cpu_mask, GFP_KERNEL))
 		goto err;
-	cpumask_copy(wq->cpu_mask, cpu_possible_mask);
+	cpuset_cpus_allowed(data->task, wq->cpu_mask);
 	wq->acct[IO_WQ_ACCT_BOUND].max_workers = bounded;
 	wq->acct[IO_WQ_ACCT_UNBOUND].max_workers =
 				task_rlimit(current, RLIMIT_NPROC);
@@ -1322,17 +1323,29 @@ static int io_wq_cpu_offline(unsigned int cpu, struct hlist_node *node)
 
 int io_wq_cpu_affinity(struct io_uring_task *tctx, cpumask_var_t mask)
 {
+	cpumask_var_t allowed_mask;
+	int ret = 0;
+
 	if (!tctx || !tctx->io_wq)
 		return -EINVAL;
 
+	if (!alloc_cpumask_var(&allowed_mask, GFP_KERNEL))
+		return -ENOMEM;
+
 	rcu_read_lock();
-	if (mask)
-		cpumask_copy(tctx->io_wq->cpu_mask, mask);
-	else
-		cpumask_copy(tctx->io_wq->cpu_mask, cpu_possible_mask);
+	cpuset_cpus_allowed(tctx->io_wq->task, allowed_mask);
+	if (mask) {
+		if (cpumask_subset(mask, allowed_mask))
+			cpumask_copy(tctx->io_wq->cpu_mask, mask);
+		else
+			ret = -EINVAL;
+	} else {
+		cpumask_copy(tctx->io_wq->cpu_mask, allowed_mask);
+	}
 	rcu_read_unlock();
 
-	return 0;
+	free_cpumask_var(allowed_mask);
+	return ret;
 }
 
 /*