Merge branch 'mana-shared' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Leon Romanovsky says:

====================
net: mana: Allow variable size indirection table

Like we talked, I created new shared branch for this patch:
https://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma.git/log/?h=mana-shared

* 'mana-shared' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma:
   net: mana: Allow variable size indirection table
====================

Link: https://lore.kernel.org/all/20240612183051.GE4966@unreal
Signed-off-by: Leon Romanovsky <leon@kernel.org>

7 files changed, 34 insertions, 22 deletions

diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c
index d1c47a9d9215..7d3316fe9bfc 100644
--- a/io_uring/io-wq.c
+++ b/io_uring/io-wq.c
@@ -927,7 +927,11 @@ void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work)
 {
 	struct io_wq_acct *acct = io_work_get_acct(wq, work);
 	unsigned long work_flags = work->flags;
-	struct io_cb_cancel_data match;
+	struct io_cb_cancel_data match = {
+		.fn		= io_wq_work_match_item,
+		.data		= work,
+		.cancel_all	= false,
+	};
 	bool do_create;
 
 	/*
@@ -965,10 +969,6 @@ void io_wq_enqueue(struct io_wq *wq, struct io_wq_work *work)
 		raw_spin_unlock(&wq->lock);
 
 		/* fatal condition, failed to create the first worker */
-		match.fn		= io_wq_work_match_item,
-		match.data		= work,
-		match.cancel_all	= false,
-
 		io_acct_cancel_pending_work(wq, acct, &match);
 	}
 }
diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
index 624ca9076a50..726e6367af4d 100644
--- a/io_uring/io_uring.h
+++ b/io_uring/io_uring.h
@@ -433,7 +433,7 @@ static inline bool io_file_can_poll(struct io_kiocb *req)
 {
 	if (req->flags & REQ_F_CAN_POLL)
 		return true;
-	if (file_can_poll(req->file)) {
+	if (req->file && file_can_poll(req->file)) {
 		req->flags |= REQ_F_CAN_POLL;
 		return true;
 	}
diff --git a/io_uring/memmap.c b/io_uring/memmap.c
index 4785d6af5fee..a0f32a255fd1 100644
--- a/io_uring/memmap.c
+++ b/io_uring/memmap.c
@@ -244,6 +244,7 @@ __cold int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
 	struct io_ring_ctx *ctx = file->private_data;
 	size_t sz = vma->vm_end - vma->vm_start;
 	long offset = vma->vm_pgoff << PAGE_SHIFT;
+	unsigned int npages;
 	void *ptr;
 
 	ptr = io_uring_validate_mmap_request(file, vma->vm_pgoff, sz);
@@ -253,8 +254,8 @@ __cold int io_uring_mmap(struct file *file, struct vm_area_struct *vma)
 	switch (offset & IORING_OFF_MMAP_MASK) {
 	case IORING_OFF_SQ_RING:
 	case IORING_OFF_CQ_RING:
-		return io_uring_mmap_pages(ctx, vma, ctx->ring_pages,
-						ctx->n_ring_pages);
+		npages = min(ctx->n_ring_pages, (sz + PAGE_SIZE - 1) >> PAGE_SHIFT);
+		return io_uring_mmap_pages(ctx, vma, ctx->ring_pages, npages);
 	case IORING_OFF_SQES:
 		return io_uring_mmap_pages(ctx, vma, ctx->sqe_pages,
 						ctx->n_sqe_pages);
diff --git a/io_uring/napi.c b/io_uring/napi.c
index 883a1a665907..8c18ede595c4 100644
--- a/io_uring/napi.c
+++ b/io_uring/napi.c
@@ -261,12 +261,14 @@ int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg)
 }
 
 /*
- * __io_napi_adjust_timeout() - Add napi id to the busy poll list
+ * __io_napi_adjust_timeout() - adjust busy loop timeout
  * @ctx: pointer to io-uring context structure
  * @iowq: pointer to io wait queue
  * @ts: pointer to timespec or NULL
  *
  * Adjust the busy loop timeout according to timespec and busy poll timeout.
+ * If the specified NAPI timeout is bigger than the wait timeout, then adjust
+ * the NAPI timeout accordingly.
  */
 void __io_napi_adjust_timeout(struct io_ring_ctx *ctx, struct io_wait_queue *iowq,
 			      struct timespec64 *ts)
@@ -274,16 +276,16 @@ void __io_napi_adjust_timeout(struct io_ring_ctx *ctx, struct io_wait_queue *iow
 	unsigned int poll_to = READ_ONCE(ctx->napi_busy_poll_to);
 
 	if (ts) {
-		struct timespec64 poll_to_ts = ns_to_timespec64(1000 * (s64)poll_to);
-
-		if (timespec64_compare(ts, &poll_to_ts) > 0) {
-			*ts = timespec64_sub(*ts, poll_to_ts);
-		} else {
-			u64 to = timespec64_to_ns(ts);
-
-			do_div(to, 1000);
-			ts->tv_sec = 0;
-			ts->tv_nsec = 0;
+		struct timespec64 poll_to_ts;
+
+		poll_to_ts = ns_to_timespec64(1000 * (s64)poll_to);
+		if (timespec64_compare(ts, &poll_to_ts) < 0) {
+			s64 poll_to_ns = timespec64_to_ns(ts);
+			if (poll_to_ns > 0) {
+				u64 val = poll_to_ns + 999;
+				do_div(val, (s64) 1000);
+				poll_to = val;
+			}
 		}
 	}
 
diff --git a/io_uring/net.c b/io_uring/net.c
index 0a48596429d9..7c98c4d50946 100644
--- a/io_uring/net.c
+++ b/io_uring/net.c
@@ -1127,6 +1127,9 @@ int io_recv(struct io_kiocb *req, unsigned int issue_flags)
 		flags |= MSG_DONTWAIT;
 
 retry_multishot:
+	kmsg->msg.msg_inq = -1;
+	kmsg->msg.msg_flags = 0;
+
 	if (io_do_buffer_select(req)) {
 		ret = io_recv_buf_select(req, kmsg, &len, issue_flags);
 		if (unlikely(ret))
@@ -1134,9 +1137,6 @@ retry_multishot:
 		sr->buf = NULL;
 	}
 
-	kmsg->msg.msg_inq = -1;
-	kmsg->msg.msg_flags = 0;
-
 	if (flags & MSG_WAITALL)
 		min_ret = iov_iter_count(&kmsg->msg.msg_iter);
 
diff --git a/io_uring/opdef.c b/io_uring/opdef.c
index 2de5cca9504e..2e3b7b16effb 100644
--- a/io_uring/opdef.c
+++ b/io_uring/opdef.c
@@ -516,10 +516,12 @@ const struct io_cold_def io_cold_defs[] = {
 	},
 	[IORING_OP_READ_FIXED] = {
 		.name			= "READ_FIXED",
+		.cleanup		= io_readv_writev_cleanup,
 		.fail			= io_rw_fail,
 	},
 	[IORING_OP_WRITE_FIXED] = {
 		.name			= "WRITE_FIXED",
+		.cleanup		= io_readv_writev_cleanup,
 		.fail			= io_rw_fail,
 	},
 	[IORING_OP_POLL_ADD] = {
@@ -582,10 +584,12 @@ const struct io_cold_def io_cold_defs[] = {
 	},
 	[IORING_OP_READ] = {
 		.name			= "READ",
+		.cleanup		= io_readv_writev_cleanup,
 		.fail			= io_rw_fail,
 	},
 	[IORING_OP_WRITE] = {
 		.name			= "WRITE",
+		.cleanup		= io_readv_writev_cleanup,
 		.fail			= io_rw_fail,
 	},
 	[IORING_OP_FADVISE] = {
@@ -692,6 +696,7 @@ const struct io_cold_def io_cold_defs[] = {
 	},
 	[IORING_OP_READ_MULTISHOT] = {
 		.name			= "READ_MULTISHOT",
+		.cleanup		= io_readv_writev_cleanup,
 	},
 	[IORING_OP_WAITID] = {
 		.name			= "WAITID",
diff --git a/io_uring/register.c b/io_uring/register.c
index ef8c908346a4..c0010a66a6f2 100644
--- a/io_uring/register.c
+++ b/io_uring/register.c
@@ -355,8 +355,10 @@ static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
 	}
 
 	if (sqd) {
+		mutex_unlock(&ctx->uring_lock);
 		mutex_unlock(&sqd->lock);
 		io_put_sq_data(sqd);
+		mutex_lock(&ctx->uring_lock);
 	}
 
 	if (copy_to_user(arg, new_count, sizeof(new_count)))
@@ -380,8 +382,10 @@ static __cold int io_register_iowq_max_workers(struct io_ring_ctx *ctx,
 	return 0;
 err:
 	if (sqd) {
+		mutex_unlock(&ctx->uring_lock);
 		mutex_unlock(&sqd->lock);
 		io_put_sq_data(sqd);
+		mutex_lock(&ctx->uring_lock);
 	}
 	return ret;
 }