io_uring: add support for IORING_SETUP_SQE_MIXED

Normal rings support 64b SQEs for posting submissions, while certain
features require the ring to be configured with IORING_SETUP_SQE128, as
they need to convey more information per submission. This, in turn,
makes ALL the SQEs be 128b in size. This is somewhat wasteful and
inefficient, particularly when only certain SQEs need to be of the
bigger variant.

This adds support for setting up a ring with mixed SQE sizes, using
IORING_SETUP_SQE_MIXED. When setup in this mode, SQEs posted to the ring
may be either 64b or 128b in size. If a SQE is 128b in size, then opcode
will be set to a variante to indicate that this is the case. Any other
non-128b opcode will assume the SQ's default size.

SQEs on these types of mixed rings may also utilize NOP with skip
success set.  This can happen if the ring is one (small) SQE entry away
from wrapping, and an attempt is made to get a 128b SQE. As SQEs must be
contiguous in the SQ ring, a 128b SQE cannot wrap the ring. For this
case, a single NOP SQE should be inserted with the SKIP_SUCCESS flag
set. The kernel will process this as a normal NOP and without posting a
CQE.

Signed-off-by: Keith Busch <kbusch@kernel.org>
[axboe: {} style fix and assign sqe before opcode read]
Signed-off-by: Jens Axboe <axboe@kernel.dk>

1 files changed, 27 insertions, 7 deletions

diff --git a/io_uring/fdinfo.c b/io_uring/fdinfo.c
index ff3364531c77..1a806ad16840 100644
--- a/io_uring/fdinfo.c
+++ b/io_uring/fdinfo.c
@@ -14,6 +14,7 @@
 #include "fdinfo.h"
 #include "cancel.h"
 #include "rsrc.h"
+#include "opdef.h"
 
 #ifdef CONFIG_NET_RX_BUSY_POLL
 static __cold void common_tracking_show_fdinfo(struct io_ring_ctx *ctx,
@@ -66,7 +67,6 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
 	unsigned int cq_head = READ_ONCE(r->cq.head);
 	unsigned int cq_tail = READ_ONCE(r->cq.tail);
 	unsigned int sq_shift = 0;
-	unsigned int sq_entries;
 	int sq_pid = -1, sq_cpu = -1;
 	u64 sq_total_time = 0, sq_work_time = 0;
 	unsigned int i;
@@ -89,26 +89,45 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
 	seq_printf(m, "CqTail:\t%u\n", cq_tail);
 	seq_printf(m, "CachedCqTail:\t%u\n", data_race(ctx->cached_cq_tail));
 	seq_printf(m, "SQEs:\t%u\n", sq_tail - sq_head);
-	sq_entries = min(sq_tail - sq_head, ctx->sq_entries);
-	for (i = 0; i < sq_entries; i++) {
-		unsigned int entry = i + sq_head;
+	while (sq_head < sq_tail) {
 		struct io_uring_sqe *sqe;
 		unsigned int sq_idx;
+		bool sqe128 = false;
+		u8 opcode;
 
 		if (ctx->flags & IORING_SETUP_NO_SQARRAY)
 			break;
-		sq_idx = READ_ONCE(ctx->sq_array[entry & sq_mask]);
+		sq_idx = READ_ONCE(ctx->sq_array[sq_head & sq_mask]);
 		if (sq_idx > sq_mask)
 			continue;
+
 		sqe = &ctx->sq_sqes[sq_idx << sq_shift];
+		opcode = READ_ONCE(sqe->opcode);
+		if (sq_shift) {
+			sqe128 = true;
+		} else if (io_issue_defs[opcode].is_128) {
+			if (!(ctx->flags & IORING_SETUP_SQE_MIXED)) {
+				seq_printf(m,
+					"%5u: invalid sqe, 128B entry on non-mixed sq\n",
+					sq_idx);
+				break;
+			}
+			if ((++sq_head & sq_mask) == 0) {
+				seq_printf(m,
+					"%5u: corrupted sqe, wrapping 128B entry\n",
+					sq_idx);
+				break;
+			}
+			sqe128 = true;
+		}
 		seq_printf(m, "%5u: opcode:%s, fd:%d, flags:%x, off:%llu, "
 			      "addr:0x%llx, rw_flags:0x%x, buf_index:%d "
 			      "user_data:%llu",
-			   sq_idx, io_uring_get_opcode(sqe->opcode), sqe->fd,
+			   sq_idx, io_uring_get_opcode(opcode), sqe->fd,
 			   sqe->flags, (unsigned long long) sqe->off,
 			   (unsigned long long) sqe->addr, sqe->rw_flags,
 			   sqe->buf_index, sqe->user_data);
-		if (sq_shift) {
+		if (sqe128) {
 			u64 *sqeb = (void *) (sqe + 1);
 			int size = sizeof(struct io_uring_sqe) / sizeof(u64);
 			int j;
@@ -120,6 +139,7 @@ static void __io_uring_show_fdinfo(struct io_ring_ctx *ctx, struct seq_file *m)
 			}
 		}
 		seq_printf(m, "\n");
+		sq_head++;
 	}
 	seq_printf(m, "CQEs:\t%u\n", cq_tail - cq_head);
 	while (cq_head < cq_tail) {