BPF controlled io_uring

Note: I'll be targeting 7.1 as it's rc7 and it can use some time to settle down.

This series introduces a way to override the standard io_uring_enter syscall execution with an extendible event loop, which can be controlled by BPF via new io_uring struct_ops or from within the kernel.

There are multiple use cases I want to cover with this:

- Syscall avoidance. Instead of returning to the userspace for CQE processing, a part of the logic can be moved into BPF to avoid excessive number of syscalls.

- Access to in-kernel io_uring resources. For example, there are registered buffers that can't be directly accessed by the userspace, however we can give BPF the ability to peek at them. It can be used to take a look at in-buffer app level headers to decide what to do with data next and issuing IO using it.

- Smarter request ordering and linking. Request links are pretty limited and inflexible as they can't pass information from one request to another. With BPF we can peek at CQEs and memory and compile a subsequent request.

- Feature semi-deprecation. It can be used to simplify handling of deprecated features by moving it into the callback out core io_uring. For example, it should be trivial to simulate IOSQE_IO_DRAIN. Another target could be request linking logic.

- It can serve as a base for custom algorithms and fine tuning. Often, it'd be impractical to introduce a generic feature because it's either niche or requires a lot of configuration. For example, there is support min-wait, however BPF can help to further fine tune it by doing it in multiple steps with different number of CQEs / timeouts. Another feature people were asking about is allowing to over queue SQEs but make the kernel to maintain a given QD.

- Smarter polling. Napi polling is performed only once per syscall and then it switches to waiting. We can do smarter and intermix polling with waiting using the hook.

It might need more specialised kfuncs in the future, but the core functionality is implemented with just two simple functions. One returns region memory, which gives BPF access to CQ/SQ/etc. And the second is for submitting requests. It's also given a structure as an argument, which is used to pass waiting parameters.

It showed good numbers in a test that sequentially executes N nop requests, where BPF was more than twice as fast than a 2-nop request link implementation.

Pavel Begunkov (6):
io_uring: introduce callback driven main loop io_uring/bpf-ops: add basic bpf struct_ops boilerplate io_uring/bpf-ops: add loop_step struct_ops callback io_uring/bpf-ops: add kfunc helpers io_uring/bpf-ops: add bpf struct ops registration selftests/io_uring: add a bpf io_uring selftest

 include/linux/io_uring_types.h               |  10 +
 io_uring/Kconfig                             |   5 +
 io_uring/Makefile                            |   3 +-
 io_uring/bpf-ops.c                           | 265 +++++++++++++++++++
 io_uring/bpf-ops.h                           |  28 ++
 io_uring/io_uring.c                          |   8 +
 io_uring/loop.c                              |  88 ++++++
 io_uring/loop.h                              |  27 ++
 tools/testing/selftests/Makefile             |   3 +-
 tools/testing/selftests/io_uring/Makefile    | 143 ++++++++++
 tools/testing/selftests/io_uring/basic.bpf.c | 116 ++++++++
 tools/testing/selftests/io_uring/common.h    |   6 +
 tools/testing/selftests/io_uring/runner.c    | 107 ++++++++
 tools/testing/selftests/io_uring/types.bpf.h | 131 +++++++++
 14 files changed, 938 insertions(+), 2 deletions(-)
 create mode 100644 io_uring/bpf-ops.c
 create mode 100644 io_uring/bpf-ops.h
 create mode 100644 io_uring/loop.c
 create mode 100644 io_uring/loop.h
 create mode 100644 tools/testing/selftests/io_uring/Makefile
 create mode 100644 tools/testing/selftests/io_uring/basic.bpf.c
 create mode 100644 tools/testing/selftests/io_uring/common.h
 create mode 100644 tools/testing/selftests/io_uring/runner.c
 create mode 100644 tools/testing/selftests/io_uring/types.bpf.h

2.52.0

The io_uring_enter() has a fixed order of execution: it submits requests, waits for completions, and returns to the user. Allow to optionally replace it with a custom loop driven by a callback called loop_step. The basic requirements to the callback is that it should be able to submit requests, wait for completions, parse them and repeat. Most of the communication including parameter passing can be implemented via shared memory.

The callback should return IOU_LOOP_CONTINUE to continue execution or IOU_LOOP_STOP to return to the user space. Note that the kernel may decide to prematurely terminate it as well, e.g. in case the process was signalled or killed.

The hook takes a structure with parameters. It can be used to ask the kernel to wait for CQEs by setting cq_wait_idx to the CQE index it wants to wait for. Spurious wake ups are possible and even likely, the callback is expected to handle it. There will be more parameters in the future like timeout.

It can be used with kernel callbacks, for example, as a slow path deprecation mechanism overwiting SQEs and emulating the wanted behaviour, however it's more useful together with BPF programs implemented in following patches.

Note that keeping it separately from the normal io_uring wait loop makes things much simpler and cleaner. It keeps it in one place instead of spreading a bunch of checks in different places including disabling the submission path. It holds the lock by default, which is a better fit for BPF synchronisation and the loop execution model. It nicely avoids existing quirks like forced wake ups on timeout request completion. And it should be easier to implement new features.

---
 include/linux/io_uring_types.h |  5 ++
 io_uring/Makefile              |  2 +-
 io_uring/io_uring.c            |  6 +++
 io_uring/loop.c                | 88 ++++++++++++++++++++++++++++++++++
 io_uring/loop.h                | 27 +++++++++++
 5 files changed, 127 insertions(+), 1 deletion(-)
 create mode 100644 io_uring/loop.c
 create mode 100644 io_uring/loop.h

index dc6bd6940a0d..9990df98790d 100644
@@ -41,6 +41,8 @@ enum io_uring_cmd_flags {
 	IO_URING_F_COMPAT		= (1 << 12),
 };
 
+struct iou_loop_params;
+
 struct io_wq_work_node {
 	struct io_wq_work_node *next;
 };

@@ -342,6 +344,9 @@ struct io_ring_ctx {
 		struct io_alloc_cache	rw_cache;
 		struct io_alloc_cache	cmd_cache;
 
+		int (*loop_step)(struct io_ring_ctx *ctx,
+				 struct iou_loop_params *);
+
 		/*
 		 * Any cancelable uring_cmd is added to this list in
 		 * ->uring_cmd() by io_uring_cmd_insert_cancelable()

index bf9eff88427a..d4dbc16a58a5 100644
@@ -14,7 +14,7 @@ obj-$(CONFIG_IO_URING)		+= io_uring.o opdef.o kbuf.o rsrc.o notif.o \
 					advise.o openclose.o statx.o timeout.o \
 					cancel.o waitid.o register.o \
 					truncate.o memmap.o alloc_cache.o \
-					query.o
+					query.o loop.o
 
 obj-$(CONFIG_IO_URING_ZCRX)	+= zcrx.o
 obj-$(CONFIG_IO_WQ)		+= io-wq.o

index 5c503a3f6ecc..aea27e3538bb 100644
@@ -94,6 +94,7 @@
 #include "alloc_cache.h"
 #include "eventfd.h"
 #include "wait.h"
+#include "loop.h"
 
 #define SQE_COMMON_FLAGS (IOSQE_FIXED_FILE | IOSQE_IO_LINK | \
 			  IOSQE_IO_HARDLINK | IOSQE_ASYNC)

@@ -2557,6 +2558,11 @@ SYSCALL_DEFINE6(io_uring_enter, unsigned int, fd, u32, to_submit,
 	if (unlikely(smp_load_acquire(&ctx->flags) & IORING_SETUP_R_DISABLED))
 		goto out;
 
+	if (io_has_loop_ops(ctx)) {
+		ret = io_run_loop(ctx);
+		goto out;
+	}
+
 	/*
 	 * For SQ polling, the thread will do all submissions and completions.
 	 * Just return the requested submit count, and wake the thread if

new file mode 100644
index 000000000000..d7718b9ce61e
@@ -0,0 +1,27 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef IOU_LOOP_H
+#define IOU_LOOP_H
+
+#include <linux/io_uring_types.h>
+
+struct iou_loop_params {
+	/*
+	 * The CQE index to wait for. Only serves as a hint and can still be
+	 * woken up earlier.
+	 */
+	__u32			cq_wait_idx;
+};
+
+enum {
+	IOU_LOOP_CONTINUE = 0,
+	IOU_LOOP_STOP,
+};
+
+static inline bool io_has_loop_ops(struct io_ring_ctx *ctx)
+{
+	return data_race(ctx->loop_step);
+}
+
+int io_run_loop(struct io_ring_ctx *ctx);
+
+#endif

2.52.0

Add boilerplate code with a basic bpf_struct_ops implementation and related files and definitions. It'll be used in following patches to add support for io_uring bpf ops.

---
 io_uring/Kconfig    |  5 +++
 io_uring/Makefile   |  1 +
 io_uring/bpf-ops.c  | 91 +++++++++++++++++++++++++++++++++++++++++++++
 io_uring/bpf-ops.h  | 10 +++++
 io_uring/io_uring.c |  1 +
 5 files changed, 108 insertions(+)
 create mode 100644 io_uring/bpf-ops.c
 create mode 100644 io_uring/bpf-ops.h

index 4b949c42c0bf..b4dad9b74544 100644
@@ -9,3 +9,8 @@ config IO_URING_ZCRX
 	depends on PAGE_POOL
 	depends on INET
 	depends on NET_RX_BUSY_POLL
+
+config IO_URING_BPF
+	def_bool y
+	depends on IO_URING
+	depends on BPF_SYSCALL && BPF_JIT && DEBUG_INFO_BTF

index d4dbc16a58a5..675865ddb906 100644
@@ -24,3 +24,4 @@ obj-$(CONFIG_NET_RX_BUSY_POLL)	+= napi.o
 obj-$(CONFIG_NET) += net.o cmd_net.o
 obj-$(CONFIG_PROC_FS) += fdinfo.o
 obj-$(CONFIG_IO_URING_MOCK_FILE) += mock_file.o
+obj-$(CONFIG_IO_URING_BPF)	+= bpf-ops.o

new file mode 100644
index 000000000000..a6756b391387
@@ -0,0 +1,10 @@
+// SPDX-License-Identifier: GPL-2.0
+#ifndef IOU_BPF_OPS_H
+#define IOU_BPF_OPS_H
+
+#include <linux/io_uring_types.h>
+
+struct io_uring_bpf_ops {
+};
+
+#endif /* IOU_BPF_OPS_H */

index aea27e3538bb..09920e56c9c9 100644
@@ -87,6 +87,7 @@
 #include "msg_ring.h"
 #include "memmap.h"
 #include "zcrx.h"
+#include "bpf-ops.h"
 
 #include "timeout.h"
 #include "poll.h"

2.52.0

Allow BPF to implement the loop_step callback to overwrite the main loop logic. As described in the patch introducing the callback, it receives iou_loop_params as an argument, which BPF can directly use to control the loop.

---
 io_uring/bpf-ops.c | 36 ++++++++++++++++++++++++++++++++++++
 io_uring/bpf-ops.h |  4 ++++
 2 files changed, 40 insertions(+)

index a89d1dea60c7..7db07eda5a48 100644
@@ -1,11 +1,22 @@
 #include <linux/mutex.h>
 #include <linux/bpf.h>
+#include <linux/bpf_verifier.h>
 
 #include "io_uring.h"
 #include "register.h"
 #include "bpf-ops.h"
+#include "loop.h"
+
+static const struct btf_type *loop_params_type;
+
+static int io_bpf_ops__loop_step(struct io_ring_ctx *ctx,
+				 struct iou_loop_params *lp)
+{
+	return IOU_LOOP_STOP;
+}
 
 static struct io_uring_bpf_ops io_bpf_ops_stubs = {
+	.loop_step = io_bpf_ops__loop_step,
 };
 
 static bool bpf_io_is_valid_access(int off, int size,

@@ -27,6 +38,14 @@ static int bpf_io_btf_struct_access(struct bpf_verifier_log *log,
 				    const struct bpf_reg_state *reg, int off,
 				    int size)
 {
+	const struct btf_type *t = btf_type_by_id(reg->btf, reg->btf_id);
+
+	if (t == loop_params_type) {
+		if (off >= offsetof(struct iou_loop_params, cq_wait_idx) &&
+		    off + size <= offsetofend(struct iou_loop_params, cq_wait_idx))
+			return SCALAR_VALUE;
+	}
+
 	return -EACCES;
 }
 

@@ -36,8 +55,25 @@ static const struct bpf_verifier_ops bpf_io_verifier_ops = {
 	.btf_struct_access = bpf_io_btf_struct_access,
 };
 
+static const struct btf_type *
+io_lookup_struct_type(struct btf *btf, const char *name)
+{
+	s32 type_id;
+
+	type_id = btf_find_by_name_kind(btf, name, BTF_KIND_STRUCT);
+	if (type_id < 0)
+		return NULL;
+	return btf_type_by_id(btf, type_id);
+}
+
 static int bpf_io_init(struct btf *btf)
 {
+	loop_params_type = io_lookup_struct_type(btf, "iou_loop_params");
+	if (!loop_params_type) {
+		pr_err("io_uring: Failed to locate iou_loop_params\n");
+		return -EINVAL;
+	}
+
 	return 0;
 }
 

index a6756b391387..e8a08ae2df0a 100644
@@ -5,6 +5,10 @@
 #include <linux/io_uring_types.h>
 
 struct io_uring_bpf_ops {
+	int (*loop_step)(struct io_ring_ctx *ctx, struct iou_loop_params *lp);
+
+	__u32 ring_fd;
+	void *priv;
 };
 
 #endif /* IOU_BPF_OPS_H */

2.52.0

Add two kfuncs that should cover most of the needs:

1. bpf_io_uring_submit_sqes(), which allows to submit io_uring requests. It mirrors the normal user space submission path and follows all related io_uring_enter(2) rules. i.e. SQEs are taken from the SQ according to head/tail values. In case of IORING_SETUP_SQ_REWIND, it'll submit first N entries.

2. bpf_io_uring_get_region() returns a pointer to the specified region, where io_uring regions are kernel-userspace shared chunks of memory. It takes the size as an argument, which should be a load time constant. There are 3 types of regions:
- IOU_REGION_SQ returns the submission queue.
- IOU_REGION_CQ stores the CQ, SQ/CQ headers and the sqarray. In other words, it gives same memory that would normally be mmap'ed with IORING_FEAT_SINGLE_MMAP enabled IORING_OFF_SQ_RING.
- IOU_REGION_MEM represents the memory / parameter region. It can be used to store request indirect parameters and for kernel - user communication.

It intentionally provides a thin but flexible API and expects BPF programs to implement CQ/SQ header parsing, CQ walking, etc. That mirrors how the normal user space works with rings and should help to minimise kernel / kfunc helpers changes while introducing new generic io_uring features.

---
 io_uring/bpf-ops.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++
 io_uring/bpf-ops.h |  6 ++++++
 2 files changed, 59 insertions(+)

index 7db07eda5a48..ad4e3dc889ba 100644
@@ -4,11 +4,56 @@
 
 #include "io_uring.h"
 #include "register.h"
+#include "memmap.h"
 #include "bpf-ops.h"
 #include "loop.h"
 
 static const struct btf_type *loop_params_type;
 
+__bpf_kfunc_start_defs();
+
+__bpf_kfunc int bpf_io_uring_submit_sqes(struct io_ring_ctx *ctx, u32 nr)
+{
+	return io_submit_sqes(ctx, nr);
+}
+
+__bpf_kfunc
+__u8 *bpf_io_uring_get_region(struct io_ring_ctx *ctx, __u32 region_id,
+			      const size_t rdwr_buf_size)
+{
+	struct io_mapped_region *r;
+
+	switch (region_id) {
+	case IOU_REGION_MEM:
+		r = &ctx->param_region;
+		break;
+	case IOU_REGION_CQ:
+		r = &ctx->ring_region;
+		break;
+	case IOU_REGION_SQ:
+		r = &ctx->sq_region;
+		break;
+	default:
+		return NULL;
+	}
+
+	if (unlikely(rdwr_buf_size > io_region_size(r)))
+		return NULL;
+	return io_region_get_ptr(r);
+}
+
+__bpf_kfunc_end_defs();
+
+BTF_KFUNCS_START(io_uring_kfunc_set)
+BTF_ID_FLAGS(func, bpf_io_uring_submit_sqes, KF_SLEEPABLE | KF_TRUSTED_ARGS);
+BTF_ID_FLAGS(func, bpf_io_uring_get_region, KF_RET_NULL | KF_TRUSTED_ARGS);
+BTF_KFUNCS_END(io_uring_kfunc_set)
+
+static const struct btf_kfunc_id_set bpf_io_uring_kfunc_set = {
+	.owner = THIS_MODULE,
+	.set = &io_uring_kfunc_set,
+};
+
 static int io_bpf_ops__loop_step(struct io_ring_ctx *ctx,
 				 struct iou_loop_params *lp)
 {

@@ -68,12 +113,20 @@ io_lookup_struct_type(struct btf *btf, const char *name)
 
 static int bpf_io_init(struct btf *btf)
 {
+	int ret;
+
 	loop_params_type = io_lookup_struct_type(btf, "iou_loop_params");
 	if (!loop_params_type) {
 		pr_err("io_uring: Failed to locate iou_loop_params\n");
 		return -EINVAL;
 	}
 
+	ret = register_btf_kfunc_id_set(BPF_PROG_TYPE_STRUCT_OPS,
+					&bpf_io_uring_kfunc_set);
+	if (ret) {
+		pr_err("io_uring: Failed to register kfuncs (%d)\n", ret);
+		return ret;
+	}
 	return 0;
 }
 

index e8a08ae2df0a..b9e589ad519a 100644
@@ -4,6 +4,12 @@
 
 #include <linux/io_uring_types.h>
 
+enum {
+	IOU_REGION_MEM,
+	IOU_REGION_CQ,
+	IOU_REGION_SQ,
+};
+
 struct io_uring_bpf_ops {
 	int (*loop_step)(struct io_ring_ctx *ctx, struct iou_loop_params *lp);
 

2.52.0

Implement BPF struct ops registration. It's registered from the BPF path, and can be removed by BPF as well as io_uring, which is why it's protected by a global lock io_bpf_ctrl_mutex.

---
 include/linux/io_uring_types.h |  5 ++
 io_uring/bpf-ops.c             | 87 +++++++++++++++++++++++++++++++++-
 io_uring/bpf-ops.h             |  8 ++++
 io_uring/io_uring.c            |  1 +
 4 files changed, 100 insertions(+), 1 deletion(-)

index 9990df98790d..5dfe3608dbb9 100644
@@ -8,6 +8,9 @@
 #include <linux/llist.h>
 #include <uapi/linux/io_uring.h>
 
+struct iou_loop_params;
+struct io_uring_bpf_ops;
+
 enum {
 	/*
 	 * A hint to not wake right away but delay until there are enough of

@@ -462,6 +465,8 @@ struct io_ring_ctx {
 	DECLARE_HASHTABLE(napi_ht, 4);
 #endif
 
+	struct io_uring_bpf_ops		*bpf_ops;
+
 	/*
 	 * Protection for resize vs mmap races - both the mmap and resize
 	 * side will need to grab this lock, to prevent either side from

index b9e589ad519a..bf4d5b9bb8c9 100644
@@ -17,4 +17,12 @@ struct io_uring_bpf_ops {
 	void *priv;
 };
 
+#ifdef CONFIG_IO_URING_BPF
+void io_unregister_bpf_ops(struct io_ring_ctx *ctx);
+#else
+static inline void io_unregister_bpf_ops(struct io_ring_ctx *ctx)
+{
+}
+#endif
+
 #endif /* IOU_BPF_OPS_H */

index 09920e56c9c9..9d6eef7ccf22 100644
@@ -2141,6 +2141,7 @@ static __cold void io_req_caches_free(struct io_ring_ctx *ctx)
 
 static __cold void io_ring_ctx_free(struct io_ring_ctx *ctx)
 {
+	io_unregister_bpf_ops(ctx);
 	io_sq_thread_finish(ctx);
 
 	mutex_lock(&ctx->uring_lock);

2.52.0

Add a simple io_uring BPF selftest, where the BPF program implemented in basic.bpf.c executes a given number of NOP requests with QD=1, writes some stats and returns back. The makefile is borrowed from sched_ext tests.

---
 tools/testing/selftests/Makefile             |   3 +-
 tools/testing/selftests/io_uring/Makefile    | 143 +++++++++++++++++++
 tools/testing/selftests/io_uring/basic.bpf.c | 116 +++++++++++++++
 tools/testing/selftests/io_uring/common.h    |   6 +
 tools/testing/selftests/io_uring/runner.c    | 107 ++++++++++++++
 tools/testing/selftests/io_uring/types.bpf.h | 131 +++++++++++++++++
 6 files changed, 505 insertions(+), 1 deletion(-)
 create mode 100644 tools/testing/selftests/io_uring/Makefile
 create mode 100644 tools/testing/selftests/io_uring/basic.bpf.c
 create mode 100644 tools/testing/selftests/io_uring/common.h
 create mode 100644 tools/testing/selftests/io_uring/runner.c
 create mode 100644 tools/testing/selftests/io_uring/types.bpf.h

index 56e44a98d6a5..5e965ba3697c 100644
@@ -130,6 +130,7 @@ TARGETS += vfio
 TARGETS += x86
 TARGETS += x86/bugs
 TARGETS += zram
+TARGETS += io_uring
 #Please keep the TARGETS list alphabetically sorted
 # Run "make quicktest=1 run_tests" or
 # "make quicktest=1 kselftest" from top level Makefile

@@ -147,7 +148,7 @@ endif
 # User can optionally provide a TARGETS skiplist. By default we skip
 # targets using BPF since it has cutting edge build time dependencies
 # which require more effort to install.
-SKIP_TARGETS ?= bpf sched_ext
+SKIP_TARGETS ?= bpf sched_ext io_uring
 ifneq ($(SKIP_TARGETS),)
 	TMP := $(filter-out $(SKIP_TARGETS), $(TARGETS))
 	override TARGETS := $(TMP)

new file mode 100644
index 000000000000..40e3182b8e5a
@@ -0,0 +1,6 @@
+#define CQ_ENTRIES 8
+#define SQ_ENTRIES 8
+
+#define SLOT_RES	0
+#define SLOT_NR_CQES	1
+#define SLOT_NR_SQES	2

2.52.0

Got it, will change both, thanks

Is there a struct_ops hook that can help with that? check_return_code() has some hard-coded checks, but I can't find anything customizable for struct_ops.

Pavel Begunkov

yep. check_return_code() is the one and you're correct. It's not customizable atm. Much simpler to do a runtime check for now and improve through the verifier support later.

Makes sense, thanks!

Pavel Begunkov