From nobody Sun Nov 24 11:18:10 2024 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 7285C224FD; Sun, 10 Nov 2024 13:48:54 +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=1731246534; cv=none; b=RaWmzfTC2Y4XgdKKxnvA9XQ2xbQPfii1VwmOQp0M80/zjdTriJupKQfQpsdqMcZkirja035GTYjM+s9+/lIZPVvYdpMBJPTmDMtT3YgmJHsAmEl2fqx5WubqQ9ce6FTlKXgV94k/rEtc5nhiJLY6yVBoYo5OtyEgCKW1L6YEz/c= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1731246534; c=relaxed/simple; bh=yQhv7OsMUuLcCzwFb2IuGE/7J/s/H43wVWXYFohPjQ4=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=VvTksxyHOCMEMVdgRPSnXdJm6JwV9ksvVn/8dDAk9dDNHqwiKgzyDheV8SAVqABnWDTvULpjK52vJB68GrlNPx+Bg2qL9+CPBGko/9RHOK11ZQBdEVK0AWOA1wG3shwyIZTCrsakLhGynuQI8Ti+JmCOd3jqNwoouzGJJDr5o2c= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=kernel.org header.i=@kernel.org header.b=OjWwiAEX; 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="OjWwiAEX" Received: by smtp.kernel.org (Postfix) with ESMTPSA id B859EC4CED0; Sun, 10 Nov 2024 13:48:52 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernel.org; s=k20201202; t=1731246534; bh=yQhv7OsMUuLcCzwFb2IuGE/7J/s/H43wVWXYFohPjQ4=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=OjWwiAEXIKNGEq9ubbVxlpYxBRTIX7s8JykKAw/u9ZDUSbOLEfzLQGUhtRNkI1C8K 4X1AkMJHKMu5AN2XXjzSvwFwuDv3YHvPdwihAwYYdBwp9NHSskWFGhFcyTPzq2HfoW G0TvHYkO3PVF9soa8opjvJd4BhOhJ02Rkd5tGXc2r48GpwUE6f4NoME5cgaXJA+V28 2v04fHrsRI/hiUiGk92+9INbmvwmkwzCuDho3IAF4LVQbHuqnRvnMFra7DEENy6hAV n4b+5Xf21Ypd01Spb24zc5vbnyH+Y/mJYuHJuG+xmE8YVhWPyyzhlYrkPuK+MxniSc Mx4l72ngt0gsA== From: Leon Romanovsky To: Jens Axboe , Jason Gunthorpe , Robin Murphy , Joerg Roedel , Will Deacon , Christoph Hellwig , Sagi Grimberg Cc: Leon Romanovsky , Keith Busch , Bjorn Helgaas , Logan Gunthorpe , Yishai Hadas , Shameer Kolothum , Kevin Tian , Alex Williamson , Marek Szyprowski , =?UTF-8?q?J=C3=A9r=C3=B4me=20Glisse?= , Andrew Morton , Jonathan Corbet , linux-doc@vger.kernel.org, linux-kernel@vger.kernel.org, linux-block@vger.kernel.org, linux-rdma@vger.kernel.org, iommu@lists.linux.dev, linux-nvme@lists.infradead.org, linux-pci@vger.kernel.org, kvm@vger.kernel.org, linux-mm@kvack.org, Randy Dunlap Subject: [PATCH v3 16/17] vfio/mlx5: Rewrite create mkey flow to allow better code reuse Date: Sun, 10 Nov 2024 15:47:03 +0200 Message-ID: <66d11399f97397a98935070240ccf644b1c8957f.1731244445.git.leon@kernel.org> X-Mailer: git-send-email 2.47.0 In-Reply-To: References: Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" From: Leon Romanovsky Change the creation of mkey to be performed in multiple steps: data allocation, DMA setup and actual call to HW to create that mkey. In this new flow, the whole input to MKEY command is saved to eliminate the need to keep array of pointers for DMA addresses for receive list and in the future patches for send list too. In addition to memory size reduce and elimination of unnecessary data movements to set MKEY input, the code is prepared for future reuse. Signed-off-by: Leon Romanovsky --- drivers/vfio/pci/mlx5/cmd.c | 156 ++++++++++++++++++++---------------- drivers/vfio/pci/mlx5/cmd.h | 4 +- 2 files changed, 90 insertions(+), 70 deletions(-) diff --git a/drivers/vfio/pci/mlx5/cmd.c b/drivers/vfio/pci/mlx5/cmd.c index fdc3e515741f..1832a6c1f35d 100644 --- a/drivers/vfio/pci/mlx5/cmd.c +++ b/drivers/vfio/pci/mlx5/cmd.c @@ -313,39 +313,21 @@ static int mlx5vf_cmd_get_vhca_id(struct mlx5_core_de= v *mdev, u16 function_id, return ret; } =20 -static int _create_mkey(struct mlx5_core_dev *mdev, u32 pdn, - struct mlx5_vhca_data_buffer *buf, - struct mlx5_vhca_recv_buf *recv_buf, - u32 *mkey) +static u32 *alloc_mkey_in(u32 npages, u32 pdn) { - size_t npages =3D buf ? buf->npages : recv_buf->npages; - int err =3D 0, inlen; - __be64 *mtt; + int inlen; void *mkc; u32 *in; =20 inlen =3D MLX5_ST_SZ_BYTES(create_mkey_in) + - sizeof(*mtt) * round_up(npages, 2); + sizeof(__be64) * round_up(npages, 2); =20 - in =3D kvzalloc(inlen, GFP_KERNEL); + in =3D kvzalloc(inlen, GFP_KERNEL_ACCOUNT); if (!in) - return -ENOMEM; + return NULL; =20 MLX5_SET(create_mkey_in, in, translations_octword_actual_size, DIV_ROUND_UP(npages, 2)); - mtt =3D (__be64 *)MLX5_ADDR_OF(create_mkey_in, in, klm_pas_mtt); - - if (buf) { - struct sg_dma_page_iter dma_iter; - - for_each_sgtable_dma_page(&buf->table.sgt, &dma_iter, 0) - *mtt++ =3D cpu_to_be64(sg_page_iter_dma_address(&dma_iter)); - } else { - int i; - - for (i =3D 0; i < npages; i++) - *mtt++ =3D cpu_to_be64(recv_buf->dma_addrs[i]); - } =20 mkc =3D MLX5_ADDR_OF(create_mkey_in, in, memory_key_mkey_entry); MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_MTT); @@ -359,9 +341,29 @@ static int _create_mkey(struct mlx5_core_dev *mdev, u3= 2 pdn, MLX5_SET(mkc, mkc, log_page_size, PAGE_SHIFT); MLX5_SET(mkc, mkc, translations_octword_size, DIV_ROUND_UP(npages, 2)); MLX5_SET64(mkc, mkc, len, npages * PAGE_SIZE); - err =3D mlx5_core_create_mkey(mdev, mkey, in, inlen); - kvfree(in); - return err; + + return in; +} + +static int create_mkey(struct mlx5_core_dev *mdev, u32 npages, + struct mlx5_vhca_data_buffer *buf, u32 *mkey_in, + u32 *mkey) +{ + __be64 *mtt; + int inlen; + + mtt =3D (__be64 *)MLX5_ADDR_OF(create_mkey_in, mkey_in, klm_pas_mtt); + if (buf) { + struct sg_dma_page_iter dma_iter; + + for_each_sgtable_dma_page(&buf->table.sgt, &dma_iter, 0) + *mtt++ =3D cpu_to_be64(sg_page_iter_dma_address(&dma_iter)); + } + + inlen =3D MLX5_ST_SZ_BYTES(create_mkey_in) + + sizeof(__be64) * round_up(npages, 2); + + return mlx5_core_create_mkey(mdev, mkey, mkey_in, inlen); } =20 static int mlx5vf_dma_data_buffer(struct mlx5_vhca_data_buffer *buf) @@ -374,20 +376,28 @@ static int mlx5vf_dma_data_buffer(struct mlx5_vhca_da= ta_buffer *buf) if (mvdev->mdev_detach) return -ENOTCONN; =20 - if (buf->dmaed || !buf->npages) + if (buf->mkey_in || !buf->npages) return -EINVAL; =20 ret =3D dma_map_sgtable(mdev->device, &buf->table.sgt, buf->dma_dir, 0); if (ret) return ret; =20 - ret =3D _create_mkey(mdev, buf->migf->pdn, buf, NULL, &buf->mkey); - if (ret) + buf->mkey_in =3D alloc_mkey_in(buf->npages, buf->migf->pdn); + if (!buf->mkey_in) { + ret =3D -ENOMEM; goto err; + } =20 - buf->dmaed =3D true; + ret =3D create_mkey(mdev, buf->npages, buf, buf->mkey_in, &buf->mkey); + if (ret) + goto err_create_mkey; =20 return 0; + +err_create_mkey: + kvfree(buf->mkey_in); + buf->mkey_in =3D NULL; err: dma_unmap_sgtable(mdev->device, &buf->table.sgt, buf->dma_dir, 0); return ret; @@ -401,8 +411,9 @@ void mlx5vf_free_data_buffer(struct mlx5_vhca_data_buff= er *buf) lockdep_assert_held(&migf->mvdev->state_mutex); WARN_ON(migf->mvdev->mdev_detach); =20 - if (buf->dmaed) { + if (buf->mkey_in) { mlx5_core_destroy_mkey(migf->mvdev->mdev, buf->mkey); + kvfree(buf->mkey_in); dma_unmap_sgtable(migf->mvdev->mdev->device, &buf->table.sgt, buf->dma_dir, 0); } @@ -779,7 +790,7 @@ int mlx5vf_cmd_load_vhca_state(struct mlx5vf_pci_core_d= evice *mvdev, if (mvdev->mdev_detach) return -ENOTCONN; =20 - if (!buf->dmaed) { + if (!buf->mkey_in) { err =3D mlx5vf_dma_data_buffer(buf); if (err) return err; @@ -1380,56 +1391,54 @@ static int alloc_recv_pages(struct mlx5_vhca_recv_b= uf *recv_buf, kvfree(recv_buf->page_list); return -ENOMEM; } +static void unregister_dma_pages(struct mlx5_core_dev *mdev, u32 npages, + u32 *mkey_in) +{ + dma_addr_t addr; + __be64 *mtt; + int i; + + mtt =3D (__be64 *)MLX5_ADDR_OF(create_mkey_in, mkey_in, klm_pas_mtt); + for (i =3D npages - 1; i >=3D 0; i--) { + addr =3D be64_to_cpu(mtt[i]); + dma_unmap_single(mdev->device, addr, PAGE_SIZE, + DMA_FROM_DEVICE); + } +} =20 -static int register_dma_recv_pages(struct mlx5_core_dev *mdev, - struct mlx5_vhca_recv_buf *recv_buf) +static int register_dma_pages(struct mlx5_core_dev *mdev, u32 npages, + struct page **page_list, u32 *mkey_in) { - int i, j; + dma_addr_t addr; + __be64 *mtt; + int i; =20 - recv_buf->dma_addrs =3D kvcalloc(recv_buf->npages, - sizeof(*recv_buf->dma_addrs), - GFP_KERNEL_ACCOUNT); - if (!recv_buf->dma_addrs) - return -ENOMEM; + mtt =3D (__be64 *)MLX5_ADDR_OF(create_mkey_in, mkey_in, klm_pas_mtt); =20 - for (i =3D 0; i < recv_buf->npages; i++) { - recv_buf->dma_addrs[i] =3D dma_map_page(mdev->device, - recv_buf->page_list[i], - 0, PAGE_SIZE, - DMA_FROM_DEVICE); - if (dma_mapping_error(mdev->device, recv_buf->dma_addrs[i])) + for (i =3D 0; i < npages; i++) { + addr =3D dma_map_page(mdev->device, page_list[i], 0, PAGE_SIZE, + DMA_FROM_DEVICE); + if (dma_mapping_error(mdev->device, addr)) goto error; + + *mtt++ =3D cpu_to_be64(addr); } + return 0; =20 error: - for (j =3D 0; j < i; j++) - dma_unmap_single(mdev->device, recv_buf->dma_addrs[j], - PAGE_SIZE, DMA_FROM_DEVICE); - - kvfree(recv_buf->dma_addrs); + unregister_dma_pages(mdev, i, mkey_in); return -ENOMEM; } =20 -static void unregister_dma_recv_pages(struct mlx5_core_dev *mdev, - struct mlx5_vhca_recv_buf *recv_buf) -{ - int i; - - for (i =3D 0; i < recv_buf->npages; i++) - dma_unmap_single(mdev->device, recv_buf->dma_addrs[i], - PAGE_SIZE, DMA_FROM_DEVICE); - - kvfree(recv_buf->dma_addrs); -} - static void mlx5vf_free_qp_recv_resources(struct mlx5_core_dev *mdev, struct mlx5_vhca_qp *qp) { struct mlx5_vhca_recv_buf *recv_buf =3D &qp->recv_buf; =20 mlx5_core_destroy_mkey(mdev, recv_buf->mkey); - unregister_dma_recv_pages(mdev, recv_buf); + unregister_dma_pages(mdev, recv_buf->npages, recv_buf->mkey_in); + kvfree(recv_buf->mkey_in); free_recv_pages(&qp->recv_buf); } =20 @@ -1445,18 +1454,29 @@ static int mlx5vf_alloc_qp_recv_resources(struct ml= x5_core_dev *mdev, if (err < 0) return err; =20 - err =3D register_dma_recv_pages(mdev, recv_buf); - if (err) + recv_buf->mkey_in =3D alloc_mkey_in(npages, pdn); + if (!recv_buf->mkey_in) { + err =3D -ENOMEM; goto end; + } + + err =3D register_dma_pages(mdev, npages, recv_buf->page_list, + recv_buf->mkey_in); + if (err) + goto err_register_dma; =20 - err =3D _create_mkey(mdev, pdn, NULL, recv_buf, &recv_buf->mkey); + err =3D create_mkey(mdev, npages, NULL, recv_buf->mkey_in, + &recv_buf->mkey); if (err) goto err_create_mkey; =20 return 0; =20 err_create_mkey: - unregister_dma_recv_pages(mdev, recv_buf); + unregister_dma_pages(mdev, npages, recv_buf->mkey_in); +err_register_dma: + kvfree(recv_buf->mkey_in); + recv_buf->mkey_in =3D NULL; end: free_recv_pages(recv_buf); return err; diff --git a/drivers/vfio/pci/mlx5/cmd.h b/drivers/vfio/pci/mlx5/cmd.h index 7d4a833b6900..25dd6ff54591 100644 --- a/drivers/vfio/pci/mlx5/cmd.h +++ b/drivers/vfio/pci/mlx5/cmd.h @@ -58,8 +58,8 @@ struct mlx5_vhca_data_buffer { u64 length; u32 npages; u32 mkey; + u32 *mkey_in; enum dma_data_direction dma_dir; - u8 dmaed:1; u8 stop_copy_chunk_num; struct list_head buf_elm; struct mlx5_vf_migration_file *migf; @@ -133,8 +133,8 @@ struct mlx5_vhca_cq { struct mlx5_vhca_recv_buf { u32 npages; struct page **page_list; - dma_addr_t *dma_addrs; u32 next_rq_offset; + u32 *mkey_in; u32 mkey; }; =20 --=20 2.47.0