From nobody Thu Apr 2 22:08:39 2026 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 726841F03EF; Fri, 13 Feb 2026 11:01:57 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1770980517; cv=none; b=OabCeXlSs6HeadUhFaAoQfZ944OOGhFSoCt0Xzn5tkt3M63Y4NwOKFQjXxB8FfOX6oBwWN4rVUuXpRSunR2bC1Wscg7QNp9/rVhZf66XUhMVYkeTpPJytkOrz873t05UPd/TU7AzB6xpvu+bxxZKbfyB9bPBahl3a/WpdjmBp0U= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1770980517; c=relaxed/simple; bh=fNGUs5AQ9nFbUrFwGoGxWr1OmLlcSEue3DXaKTPPRPk=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=txlYzhtRPnIrezTOucUUE4BP1qeesmf+qUZ/6ul0TpwLhBOXkZ7dFm351aGTdws8Z/OJAElpjz4RgczqRXCPlyaXOHx8HW8pVlbLd7CcSyK1IsN2nOoGuqCOG50YLXWcgHe//a9v1AhT1OxMJTGZwQa0wCzklBBFQu70LsrZBQ8= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=rsk1ivq2; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b="rsk1ivq2" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 128FAC116C6; Fri, 13 Feb 2026 11:01:56 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1770980517; bh=fNGUs5AQ9nFbUrFwGoGxWr1OmLlcSEue3DXaKTPPRPk=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=rsk1ivq24d8TYk4UHjpwCHlqD31mwB7ASM9n0clduY4Zji/wYQ9eFiS7t9WmezbPG FJ54S2ojCM/lw4qqX5Ep1QIKruMUTz9V9GRa+1rnqh2OqwVAKETBVvYsqEdWTtQzNf ahdkZany5kNDlNXkf+WT9aOE4AD/+QCsGHYn08icjUVfM/txKOUpFyO5cOLOKM9O6t FPp2oncY193CPGUA+4k1Gl8ZLFniOzPtKZPFSAVBWbKs8lQxBMxQSJygwOnchutPoy oUB78fzdDPWMPzqYtNYii+RNVqX054Hr0mXPskQxFuzxcf+AvsmU6PfquC2oUSXXow eQGHUGguxz9oA== From: Leon Romanovsky To: Jason Gunthorpe , Leon Romanovsky , Selvin Xavier , Kalesh AP , Potnuri Bharat Teja , Michael Margolin , Gal Pressman , Yossi Leybovich , Cheng Xu , Kai Shen , Chengchang Tang , Junxian Huang , Abhijit Gangurde , Allen Hubbe , Krzysztof Czurylo , Tatyana Nikolova , Long Li , Konstantin Taranov , Yishai Hadas , Michal Kalderon , Bryan Tan , Vishnu Dasa , Broadcom internal kernel review list , Christian Benvenuti , Nelson Escobar , Dennis Dalessandro , Bernard Metzler , Zhu Yanjun Cc: linux-kernel@vger.kernel.org, linux-rdma@vger.kernel.org, linux-hyperv@vger.kernel.org Subject: [PATCH rdma-next 49/50] RDMA/mlx5: Reduce CQ memory footprint Date: Fri, 13 Feb 2026 12:58:25 +0200 Message-ID: <20260213-refactor-umem-v1-49-f3be85847922@nvidia.com> X-Mailer: git-send-email 2.53.0 In-Reply-To: <20260213-refactor-umem-v1-0-f3be85847922@nvidia.com> References: <20260213-refactor-umem-v1-0-f3be85847922@nvidia.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" X-Mailer: b4 0.15-dev-47773 Content-Transfer-Encoding: quoted-printable From: Leon Romanovsky There is no need to store a temporary umem pointer in the generic CQ object. Use an on=E2=80=91stack variable instead. Signed-off-by: Leon Romanovsky --- drivers/infiniband/hw/mlx5/cq.c | 64 ++++++++++++--------------------= ---- drivers/infiniband/hw/mlx5/mlx5_ib.h | 1 - 2 files changed, 21 insertions(+), 44 deletions(-) diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/c= q.c index 88f0f5e2944f..6d9b62742674 100644 --- a/drivers/infiniband/hw/mlx5/cq.c +++ b/drivers/infiniband/hw/mlx5/cq.c @@ -1218,44 +1218,13 @@ int mlx5_ib_modify_cq(struct ib_cq *cq, u16 cq_coun= t, u16 cq_period) return err; } =20 -static int resize_user(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq, - int entries, struct ib_udata *udata, - int *cqe_size) -{ - struct mlx5_ib_resize_cq ucmd; - struct ib_umem *umem; - int err; - - err =3D ib_copy_from_udata(&ucmd, udata, sizeof(ucmd)); - if (err) - return err; - - if (ucmd.reserved0 || ucmd.reserved1) - return -EINVAL; - - /* check multiplication overflow */ - if (ucmd.cqe_size && SIZE_MAX / ucmd.cqe_size <=3D entries - 1) - return -EINVAL; - - umem =3D ib_umem_get(&dev->ib_dev, ucmd.buf_addr, - (size_t)ucmd.cqe_size * entries, - IB_ACCESS_LOCAL_WRITE); - if (IS_ERR(umem)) { - err =3D PTR_ERR(umem); - return err; - } - - cq->resize_umem =3D umem; - *cqe_size =3D ucmd.cqe_size; - - return 0; -} - int mlx5_ib_resize_cq(struct ib_cq *ibcq, unsigned int entries, struct ib_udata *udata) { struct mlx5_ib_dev *dev =3D to_mdev(ibcq->device); struct mlx5_ib_cq *cq =3D to_mcq(ibcq); + struct mlx5_ib_resize_cq ucmd; + struct ib_umem *umem; unsigned long page_size; void *cqc; u32 *in; @@ -1264,8 +1233,8 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, unsigned in= t entries, __be64 *pas; unsigned int page_offset_quantized =3D 0; unsigned int page_shift; + size_t umem_size; int inlen; - int cqe_size; =20 if (entries > (1 << MLX5_CAP_GEN(dev->mdev, log_max_cq_sz))) return -EINVAL; @@ -1277,18 +1246,29 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, unsigned = int entries, if (entries =3D=3D ibcq->cqe + 1) return 0; =20 - err =3D resize_user(dev, cq, entries, udata, &cqe_size); + err =3D ib_copy_from_udata(&ucmd, udata, sizeof(ucmd)); if (err) return err; =20 + if (ucmd.reserved0 || ucmd.reserved1) + return -EINVAL; + + if (check_mul_overflow(ucmd.cqe_size, entries, &umem_size)) + return -EINVAL; + + umem =3D ib_umem_get(&dev->ib_dev, ucmd.buf_addr, umem_size, + IB_ACCESS_LOCAL_WRITE); + if (IS_ERR(umem)) + return PTR_ERR(umem); + page_size =3D mlx5_umem_find_best_cq_quantized_pgoff( - cq->resize_umem, cqc, log_page_size, MLX5_ADAPTER_PAGE_SHIFT, + umem, cqc, log_page_size, MLX5_ADAPTER_PAGE_SHIFT, page_offset, 64, &page_offset_quantized); if (!page_size) { err =3D -EINVAL; goto ex_resize; } - npas =3D ib_umem_num_dma_blocks(cq->resize_umem, page_size); + npas =3D ib_umem_num_dma_blocks(umem, page_size); page_shift =3D order_base_2(page_size); =20 inlen =3D MLX5_ST_SZ_BYTES(modify_cq_in) + @@ -1301,7 +1281,7 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, unsigned in= t entries, } =20 pas =3D (__be64 *)MLX5_ADDR_OF(modify_cq_in, in, pas); - mlx5_ib_populate_pas(cq->resize_umem, 1UL << page_shift, pas, 0); + mlx5_ib_populate_pas(umem, 1UL << page_shift, pas, 0); =20 MLX5_SET(modify_cq_in, in, modify_field_select_resize_field_select.resize_field_select.resize_fiel= d_select, @@ -1315,7 +1295,7 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, unsigned in= t entries, page_shift - MLX5_ADAPTER_PAGE_SHIFT); MLX5_SET(cqc, cqc, page_offset, page_offset_quantized); MLX5_SET(cqc, cqc, cqe_sz, - cqe_sz_to_mlx_sz(cqe_size, + cqe_sz_to_mlx_sz(ucmd.cqe_size, cq->private_flags & MLX5_IB_CQ_PR_FLAGS_CQE_128_PAD)); MLX5_SET(cqc, cqc, log_cq_size, ilog2(entries)); @@ -1329,8 +1309,7 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, unsigned in= t entries, =20 cq->ibcq.cqe =3D entries - 1; ib_umem_release(cq->ibcq.umem); - cq->ibcq.umem =3D cq->resize_umem; - cq->resize_umem =3D NULL; + cq->ibcq.umem =3D umem; =20 kvfree(in); return 0; @@ -1339,8 +1318,7 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, unsigned in= t entries, kvfree(in); =20 ex_resize: - ib_umem_release(cq->resize_umem); - cq->resize_umem =3D NULL; + ib_umem_release(umem); return err; } =20 diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/m= lx5/mlx5_ib.h index 7b34f32b5ecb..11e4b2ae0469 100644 --- a/drivers/infiniband/hw/mlx5/mlx5_ib.h +++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h @@ -575,7 +575,6 @@ struct mlx5_ib_cq { spinlock_t lock; =20 struct mlx5_ib_cq_buf *resize_buf; - struct ib_umem *resize_umem; int cqe_size; struct list_head list_send_qp; struct list_head list_recv_qp; --=20 2.52.0