diff mbox series

[v9,06/11] io_uring: introduce attributes for read/write and PI support

Message ID 20241114104517.51726-7-anuj20.g@samsung.com
State New
Headers show
Series Read/Write with meta/integrity | expand

Commit Message

Anuj Gupta Nov. 14, 2024, 10:45 a.m. UTC 
Add the ability to pass additional attributes along with read/write.
Application can populate an array of 'struct io_uring_attr_vec' and pass
its address using the SQE field:
	__u64	attr_vec_addr;

Along with number of attributes using:
	__u8	nr_attr_indirect;

Overall 16 attributes are allowed and currently one attribute
'ATTR_TYPE_PI' is supported.

With PI attribute, userspace can pass following information:
- flags: integrity check flags IO_INTEGRITY_CHK_{GUARD/APPTAG/REFTAG}
- len: length of PI/metadata buffer
- addr: address of metadata buffer
- seed: seed value for reftag remapping
- app_tag: application defined 16b value

Process this information to prepare uio_meta_descriptor and pass it down
using kiocb->private.

PI attribute is supported only for direct IO. Also, vectored read/write
operations are not supported with PI currently.

Signed-off-by: Anuj Gupta <anuj20.g@samsung.com>
Signed-off-by: Kanchan Joshi <joshi.k@samsung.com>
---
 include/uapi/linux/io_uring.h |  29 ++++++++
 io_uring/io_uring.c           |   1 +
 io_uring/rw.c                 | 128 +++++++++++++++++++++++++++++++++-
 io_uring/rw.h                 |  14 +++-
 4 files changed, 169 insertions(+), 3 deletions(-)

Comments

kernel test robot Nov. 16, 2024, 11:09 p.m. UTC | #1 
Hi Anuj,

kernel test robot noticed the following build warnings:

[auto build test WARNING on axboe-block/for-next]
[also build test WARNING on next-20241115]
[cannot apply to brauner-vfs/vfs.all mkp-scsi/for-next hch-configfs/for-next linus/master jejb-scsi/for-next v6.12-rc7]
[If your patch is applied to the wrong git tree, kindly drop us a note.
And when submitting patch, we suggest to use '--base' as documented in
https://git-scm.com/docs/git-format-patch#_base_tree_information]

url:    https://github.com/intel-lab-lkp/linux/commits/Anuj-Gupta/block-define-set-of-integrity-flags-to-be-inherited-by-cloned-bip/20241114-193419
base:   https://git.kernel.org/pub/scm/linux/kernel/git/axboe/linux-block.git for-next
patch link:    https://lore.kernel.org/r/20241114104517.51726-7-anuj20.g%40samsung.com
patch subject: [PATCH v9 06/11] io_uring: introduce attributes for read/write and PI support
config: arc-nsimosci_hs_smp_defconfig (https://download.01.org/0day-ci/archive/20241117/202411170724.GLZyWdlD-lkp@intel.com/config)
compiler: arc-elf-gcc (GCC) 13.2.0
reproduce (this is a W=1 build): (https://download.01.org/0day-ci/archive/20241117/202411170724.GLZyWdlD-lkp@intel.com/reproduce)

If you fix the issue in a separate patch/commit (i.e. not just a new version of
the same patch/commit), kindly add following tags
| Reported-by: kernel test robot <lkp@intel.com>
| Closes: https://lore.kernel.org/oe-kbuild-all/202411170724.GLZyWdlD-lkp@intel.com/

All warnings (new ones prefixed by >>):

   io_uring/rw.c: In function 'io_prep_pi_indirect':
>> io_uring/rw.c:305:38: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast]
     305 |         if (copy_from_user(&pi_attr, (void __user *)pi_attr_addr, sizeof(pi_attr)))
         |                                      ^
   io_uring/rw.c: In function 'io_prep_attr_vec':
   io_uring/rw.c:321:38: warning: cast to pointer from integer of different size [-Wint-to-pointer-cast]
     321 |         if (copy_from_user(attr_vec, (void __user *)attr_addr, attr_vec_size))
         |                                      ^


vim +305 io_uring/rw.c

   298	
   299	
   300	static inline int io_prep_pi_indirect(struct io_kiocb *req, struct io_rw *rw,
   301					      int ddir, u64 pi_attr_addr)
   302	{
   303		struct io_uring_attr_pi pi_attr;
   304	
 > 305		if (copy_from_user(&pi_attr, (void __user *)pi_attr_addr, sizeof(pi_attr)))
   306			return -EFAULT;
   307		return io_prep_rw_pi(req, rw, ddir, &pi_attr);
   308	}
   309
diff mbox series

Patch

diff --git a/include/uapi/linux/io_uring.h b/include/uapi/linux/io_uring.h
index 5d08435b95a8..2e6808f6ba28 100644
--- a/include/uapi/linux/io_uring.h
+++ b/include/uapi/linux/io_uring.h
@@ -92,12 +92,18 @@  struct io_uring_sqe {
 			__u16	addr_len;
 			__u16	__pad3[1];
 		};
+		struct {
+			/* number of elements in the attribute vector */
+			__u8	nr_attr_indirect;
+			__u8	__pad4[3];
+		};
 	};
 	union {
 		struct {
 			__u64	addr3;
 			__u64	__pad2[1];
 		};
+		__u64	attr_vec_addr;
 		__u64	optval;
 		/*
 		 * If the ring is initialized with IORING_SETUP_SQE128, then
@@ -107,6 +113,29 @@  struct io_uring_sqe {
 	};
 };
 
+
+/* Attributes to be passed with read/write */
+enum io_uring_attr_type {
+	ATTR_TYPE_PI,
+	/* max supported attributes */
+	ATTR_TYPE_LAST = 16,
+};
+
+struct io_uring_attr_vec {
+	enum io_uring_attr_type	type;
+	__u64			addr;
+};
+
+/* PI attribute information */
+struct io_uring_attr_pi {
+		__u16	flags;
+		__u16	app_tag;
+		__u32	len;
+		__u64	addr;
+		__u64	seed;
+		__u64	rsvd;
+};
+
 /*
  * If sqe->file_index is set to this for opcodes that instantiate a new
  * direct descriptor (like openat/openat2/accept), then io_uring will allocate
diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
index bd71782057de..e32dd118d7c8 100644
--- a/io_uring/io_uring.c
+++ b/io_uring/io_uring.c
@@ -3867,6 +3867,7 @@  static int __init io_uring_init(void)
 	BUILD_BUG_SQE_ELEM(44, __u32,  file_index);
 	BUILD_BUG_SQE_ELEM(44, __u16,  addr_len);
 	BUILD_BUG_SQE_ELEM(46, __u16,  __pad3[0]);
+	BUILD_BUG_SQE_ELEM(44, __u8,   nr_attr_indirect);
 	BUILD_BUG_SQE_ELEM(48, __u64,  addr3);
 	BUILD_BUG_SQE_ELEM_SIZE(48, 0, cmd);
 	BUILD_BUG_SQE_ELEM(56, __u64,  __pad2);
diff --git a/io_uring/rw.c b/io_uring/rw.c
index cce8bc2ecd3f..93d7451b9370 100644
--- a/io_uring/rw.c
+++ b/io_uring/rw.c
@@ -257,11 +257,98 @@  static int io_prep_rw_setup(struct io_kiocb *req, int ddir, bool do_import)
 	return 0;
 }
 
+static inline void io_meta_save_state(struct io_async_rw *io)
+{
+	io->meta_state.seed = io->meta.seed;
+	iov_iter_save_state(&io->meta.iter, &io->meta_state.iter_meta);
+}
+
+static inline void io_meta_restore(struct io_async_rw *io)
+{
+	io->meta.seed = io->meta_state.seed;
+	iov_iter_restore(&io->meta.iter, &io->meta_state.iter_meta);
+}
+
+static int io_prep_rw_pi(struct io_kiocb *req, struct io_rw *rw, int ddir,
+			 const struct io_uring_attr_pi *pi_attr)
+{
+	const struct io_issue_def *def;
+	struct io_async_rw *io;
+	int ret;
+
+	if (READ_ONCE(pi_attr->rsvd))
+		return -EINVAL;
+
+	def = &io_issue_defs[req->opcode];
+	if (def->vectored)
+		return -EOPNOTSUPP;
+
+	io = req->async_data;
+	io->meta.flags = READ_ONCE(pi_attr->flags);
+	io->meta.app_tag = READ_ONCE(pi_attr->app_tag);
+	io->meta.seed = READ_ONCE(pi_attr->seed);
+	ret = import_ubuf(ddir, u64_to_user_ptr(READ_ONCE(pi_attr->addr)),
+			  READ_ONCE(pi_attr->len), &io->meta.iter);
+	if (unlikely(ret < 0))
+		return ret;
+	rw->kiocb.ki_flags |= IOCB_HAS_METADATA;
+	io_meta_save_state(io);
+	return ret;
+}
+
+
+static inline int io_prep_pi_indirect(struct io_kiocb *req, struct io_rw *rw,
+				      int ddir, u64 pi_attr_addr)
+{
+	struct io_uring_attr_pi pi_attr;
+
+	if (copy_from_user(&pi_attr, (void __user *)pi_attr_addr, sizeof(pi_attr)))
+		return -EFAULT;
+	return io_prep_rw_pi(req, rw, ddir, &pi_attr);
+}
+
+static int io_prep_attr_vec(struct io_kiocb *req, struct io_rw *rw, int ddir,
+			      u64 attr_addr, u8 nr_attr)
+{
+	struct io_uring_attr_vec attr_vec[ATTR_TYPE_LAST];
+	size_t attr_vec_size = sizeof(struct io_uring_attr_vec) * nr_attr;
+	u8 dup[ATTR_TYPE_LAST] = {0};
+	enum io_uring_attr_type t;
+	int i, ret;
+
+	if (nr_attr > ATTR_TYPE_LAST)
+		return -EINVAL;
+	if (copy_from_user(attr_vec, (void __user *)attr_addr, attr_vec_size))
+		return -EFAULT;
+
+	for (i = 0; i < nr_attr; i++) {
+		t = attr_vec[i].type;
+		if (t >= ATTR_TYPE_LAST)
+			return -EINVAL;
+		/* allow each attribute only once */
+		if (dup[ATTR_TYPE_PI])
+			return -EBUSY;
+		dup[ATTR_TYPE_PI] = 1;
+
+		switch (t) {
+		case ATTR_TYPE_PI:
+			ret = io_prep_pi_indirect(req, rw, ddir, attr_vec[i].addr);
+			break;
+		default:
+			ret = -EOPNOTSUPP;
+		}
+		if (unlikely(ret))
+			return ret;
+	}
+	return 0;
+}
+
 static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		      int ddir, bool do_import)
 {
 	struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
 	unsigned ioprio;
+	u8 nr_attr_indirect;
 	int ret;
 
 	rw->kiocb.ki_pos = READ_ONCE(sqe->off);
@@ -279,11 +366,29 @@  static int io_prep_rw(struct io_kiocb *req, const struct io_uring_sqe *sqe,
 		rw->kiocb.ki_ioprio = get_current_ioprio();
 	}
 	rw->kiocb.dio_complete = NULL;
+	rw->kiocb.ki_flags = 0;
 
 	rw->addr = READ_ONCE(sqe->addr);
 	rw->len = READ_ONCE(sqe->len);
 	rw->flags = READ_ONCE(sqe->rw_flags);
-	return io_prep_rw_setup(req, ddir, do_import);
+	ret = io_prep_rw_setup(req, ddir, do_import);
+
+	if (unlikely(ret))
+		return ret;
+
+	nr_attr_indirect = READ_ONCE(sqe->nr_attr_indirect);
+	if (nr_attr_indirect) {
+		u64 attr_vec_usr_addr = READ_ONCE(sqe->attr_vec_addr);
+
+		if (READ_ONCE(sqe->__pad4[0]) || READ_ONCE(sqe->__pad4[1]) ||
+		    READ_ONCE(sqe->__pad4[2]))
+			return -EINVAL;
+
+		ret = io_prep_attr_vec(req, rw, ddir, attr_vec_usr_addr,
+					 nr_attr_indirect);
+	}
+
+	return ret;
 }
 
 int io_prep_read(struct io_kiocb *req, const struct io_uring_sqe *sqe)
@@ -409,7 +514,10 @@  static inline loff_t *io_kiocb_update_pos(struct io_kiocb *req)
 static void io_resubmit_prep(struct io_kiocb *req)
 {
 	struct io_async_rw *io = req->async_data;
+	struct io_rw *rw = io_kiocb_to_cmd(req, struct io_rw);
 
+	if (rw->kiocb.ki_flags & IOCB_HAS_METADATA)
+		io_meta_restore(io);
 	iov_iter_restore(&io->iter, &io->iter_state);
 }
 
@@ -794,7 +902,7 @@  static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type)
 	if (!(req->flags & REQ_F_FIXED_FILE))
 		req->flags |= io_file_get_flags(file);
 
-	kiocb->ki_flags = file->f_iocb_flags;
+	kiocb->ki_flags |= file->f_iocb_flags;
 	ret = kiocb_set_rw_flags(kiocb, rw->flags, rw_type);
 	if (unlikely(ret))
 		return ret;
@@ -828,6 +936,18 @@  static int io_rw_init_file(struct io_kiocb *req, fmode_t mode, int rw_type)
 		kiocb->ki_complete = io_complete_rw;
 	}
 
+	if (kiocb->ki_flags & IOCB_HAS_METADATA) {
+		struct io_async_rw *io = req->async_data;
+
+		/*
+		 * We have a union of meta fields with wpq used for buffered-io
+		 * in io_async_rw, so fail it here.
+		 */
+		if (!(req->file->f_flags & O_DIRECT))
+			return -EOPNOTSUPP;
+		kiocb->private = &io->meta;
+	}
+
 	return 0;
 }
 
@@ -902,6 +1022,8 @@  static int __io_read(struct io_kiocb *req, unsigned int issue_flags)
 	 * manually if we need to.
 	 */
 	iov_iter_restore(&io->iter, &io->iter_state);
+	if (kiocb->ki_flags & IOCB_HAS_METADATA)
+		io_meta_restore(io);
 
 	do {
 		/*
@@ -1125,6 +1247,8 @@  int io_write(struct io_kiocb *req, unsigned int issue_flags)
 	} else {
 ret_eagain:
 		iov_iter_restore(&io->iter, &io->iter_state);
+		if (kiocb->ki_flags & IOCB_HAS_METADATA)
+			io_meta_restore(io);
 		if (kiocb->ki_flags & IOCB_WRITE)
 			io_req_end_write(req);
 		return -EAGAIN;
diff --git a/io_uring/rw.h b/io_uring/rw.h
index 3f432dc75441..2d7656bd268d 100644
--- a/io_uring/rw.h
+++ b/io_uring/rw.h
@@ -2,6 +2,11 @@ 
 
 #include <linux/pagemap.h>
 
+struct io_meta_state {
+	u32			seed;
+	struct iov_iter_state	iter_meta;
+};
+
 struct io_async_rw {
 	size_t				bytes_done;
 	struct iov_iter			iter;
@@ -9,7 +14,14 @@  struct io_async_rw {
 	struct iovec			fast_iov;
 	struct iovec			*free_iovec;
 	int				free_iov_nr;
-	struct wait_page_queue		wpq;
+	/* wpq is for buffered io, while meta fields are used with direct io */
+	union {
+		struct wait_page_queue		wpq;
+		struct {
+			struct uio_meta			meta;
+			struct io_meta_state		meta_state;
+		};
+	};
 };
 
 int io_prep_read_fixed(struct io_kiocb *req, const struct io_uring_sqe *sqe);