IB/mlx5: Don't hold spin lock while checking device state (6c75520f) · Commits · 戴 / test

mdev->state device state is not protected by the QP for which WRs are being processed. Therefore, there is no need to hold spin lock while checking mdev state. Given that device fatal error is unlikely situation, wrap the condition check with unlikely(). Additionally, kernel QP1 is also a kernel ULP for which soft CQEs needs to be generated. Therefore, check for device fatal error before processing QP1 work requests. Fixes: ("IB/mlx5: Reset flow support for IB kernel ULPs") Signed-off-by:

Parav Pandit <parav@mellanox.com> Reviewed-by:

Daniel Jurgens <danielj@mellanox.com> Reviewed-by:

Maor Gottlieb <maorg@mellanox.com> Signed-off-by:

Leon Romanovsky <leonro@mellanox.com> Signed-off-by:

Jason Gunthorpe <jgg@mellanox.com>

drivers/infiniband/hw/mlx5/qp.c

+12 −14

Original line number	Diff line number	Diff line
		@@ -4400,6 +4400,12 @@ static int _mlx5_ib_post_send(struct ib_qp ibqp, const struct ib_send_wr wr,
		u8 next_fence = 0;
		u8 fence;

		if (unlikely(mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR &&
		!drain)) {
		*bad_wr = wr;
		return -EIO;
		}

		if (unlikely(ibqp->qp_type == IB_QPT_GSI))
		return mlx5_ib_gsi_post_send(ibqp, wr, bad_wr);

		@@ -4409,13 +4415,6 @@ static int _mlx5_ib_post_send(struct ib_qp ibqp, const struct ib_send_wr wr,

		spin_lock_irqsave(&qp->sq.lock, flags);

		if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR && !drain) {
		err = -EIO;
		*bad_wr = wr;
		nreq = 0;
		goto out;
		}

		for (nreq = 0; wr; nreq++, wr = wr->next) {
		if (unlikely(wr->opcode >= ARRAY_SIZE(mlx5_ib_opcode))) {
		mlx5_ib_warn(dev, "\n");
		@@ -4729,18 +4728,17 @@ static int _mlx5_ib_post_recv(struct ib_qp ibqp, const struct ib_recv_wr wr,
		int ind;
		int i;

		if (unlikely(mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR &&
		!drain)) {
		*bad_wr = wr;
		return -EIO;
		}

		if (unlikely(ibqp->qp_type == IB_QPT_GSI))
		return mlx5_ib_gsi_post_recv(ibqp, wr, bad_wr);

		spin_lock_irqsave(&qp->rq.lock, flags);

		if (mdev->state == MLX5_DEVICE_STATE_INTERNAL_ERROR && !drain) {
		err = -EIO;
		*bad_wr = wr;
		nreq = 0;
		goto out;
		}

		ind = qp->rq.head & (qp->rq.wqe_cnt - 1);

		for (nreq = 0; wr; nreq++, wr = wr->next) {

Admin message