Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::3:7 as permitted sender) client-ip=2620:137:e000::3:7;
Received-SPF: Pass (protection.outlook.com: domain of amd.com designates
 165.204.84.17 as permitted sender) receiver=protection.outlook.com;
 client-ip=165.204.84.17; helo=SATLEXMB04.amd.com; pr=C
From:   Brett Creeley <brett.creeley@amd.com>
To:     <jgg@ziepe.ca>, <yishaih@nvidia.com>,
        <shameerali.kolothum.thodi@huawei.com>, <kevin.tian@intel.com>,
        <alex.williamson@redhat.com>, <kvm@vger.kernel.org>,
        <linux-kernel@vger.kernel.org>
CC:     <shannon.nelson@amd.com>, <brett.creeley@amd.com>
Subject: [PATCH v2 vfio 2/6] vfio/pds: Only use a single SGL for both seq and ack
Date:   Thu, 16 Nov 2023 16:12:03 -0800
Message-ID: <20231117001207.2793-3-brett.creeley@amd.com>
In-Reply-To: <20231117001207.2793-1-brett.creeley@amd.com>
References: <20231117001207.2793-1-brett.creeley@amd.com>
MIME-Version: 1.0
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 17 Nov 2023 00:12:25.4143
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: 4f77ca3e-faf6-4953-59c3-08dbe701e0be
X-MS-Exchange-CrossTenant-Id: 3dd8961f-e488-4e60-8e11-a82d994e183d
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=3dd8961f-e488-4e60-8e11-a82d994e183d;Ip=[165.204.84.17];Helo=[SATLEXMB04.amd.com]
X-MS-Exchange-CrossTenant-AuthSource: SN1PEPF0002BA4D.namprd03.prod.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: SJ2PR12MB8064
X-Spam-Status: No, score=-1.2 required=5.0 tests=BAYES_00,DKIMWL_WL_HIGH,
        DKIM_SIGNED,DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,FORGED_SPF_HELO,
        RCVD_IN_DNSWL_BLOCKED,RCVD_IN_MSPIKE_H2,SPF_HELO_PASS,SPF_NONE,
        T_SCC_BODY_TEXT_LINE,URIBL_BLOCKED autolearn=no autolearn_force=no
        version=3.4.6
X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on
        lindbergh.monkeyblade.net
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org
X-Greylist: Sender passed SPF test, not delayed by milter-greylist-4.6.4 (snail.vger.email [0.0.0.0]); Thu, 16 Nov 2023 16:12:44 -0800 (PST)

Since the seq/ack operations never happen in parallel there
is no need for multiple scatter gather lists per region.
The current implementation is wasting memory. Fix this by
only using a single scatter-gather list for both the seq
and ack operations.

Signed-off-by: Brett Creeley <brett.creeley@amd.com>
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
---
 drivers/vfio/pci/pds/dirty.c | 68 +++++++++++++-----------------------
 drivers/vfio/pci/pds/dirty.h |  6 ++--
 2 files changed, 28 insertions(+), 46 deletions(-)

diff --git a/drivers/vfio/pci/pds/dirty.c b/drivers/vfio/pci/pds/dirty.c
index 27607d7b9030..4462f6edb0ed 100644
--- a/drivers/vfio/pci/pds/dirty.c
+++ b/drivers/vfio/pci/pds/dirty.c
@@ -100,35 +100,35 @@ static void pds_vfio_dirty_free_bitmaps(struct pds_vfio_dirty *dirty)
 }
 
 static void __pds_vfio_dirty_free_sgl(struct pds_vfio_pci_device *pds_vfio,
-				      struct pds_vfio_bmp_info *bmp_info)
+				      struct pds_vfio_dirty *dirty)
 {
 	struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev;
 	struct device *pdsc_dev = &pci_physfn(pdev)->dev;
 
-	dma_unmap_single(pdsc_dev, bmp_info->sgl_addr,
-			 bmp_info->num_sge * sizeof(struct pds_lm_sg_elem),
+	dma_unmap_single(pdsc_dev, dirty->sgl_addr,
+			 dirty->num_sge * sizeof(struct pds_lm_sg_elem),
 			 DMA_BIDIRECTIONAL);
-	kfree(bmp_info->sgl);
+	kfree(dirty->sgl);
 
-	bmp_info->num_sge = 0;
-	bmp_info->sgl = NULL;
-	bmp_info->sgl_addr = 0;
+	dirty->num_sge = 0;
+	dirty->sgl = NULL;
+	dirty->sgl_addr = 0;
 }
 
 static void pds_vfio_dirty_free_sgl(struct pds_vfio_pci_device *pds_vfio)
 {
-	if (pds_vfio->dirty.host_seq.sgl)
-		__pds_vfio_dirty_free_sgl(pds_vfio, &pds_vfio->dirty.host_seq);
-	if (pds_vfio->dirty.host_ack.sgl)
-		__pds_vfio_dirty_free_sgl(pds_vfio, &pds_vfio->dirty.host_ack);
+	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
+
+	if (dirty->sgl)
+		__pds_vfio_dirty_free_sgl(pds_vfio, dirty);
 }
 
-static int __pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio,
-				      struct pds_vfio_bmp_info *bmp_info,
-				      u32 page_count)
+static int pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio,
+				    u32 page_count)
 {
 	struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev;
 	struct device *pdsc_dev = &pci_physfn(pdev)->dev;
+	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
 	struct pds_lm_sg_elem *sgl;
 	dma_addr_t sgl_addr;
 	size_t sgl_size;
@@ -147,30 +147,9 @@ static int __pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio,
 		return -EIO;
 	}
 
-	bmp_info->sgl = sgl;
-	bmp_info->num_sge = max_sge;
-	bmp_info->sgl_addr = sgl_addr;
-
-	return 0;
-}
-
-static int pds_vfio_dirty_alloc_sgl(struct pds_vfio_pci_device *pds_vfio,
-				    u32 page_count)
-{
-	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
-	int err;
-
-	err = __pds_vfio_dirty_alloc_sgl(pds_vfio, &dirty->host_seq,
-					 page_count);
-	if (err)
-		return err;
-
-	err = __pds_vfio_dirty_alloc_sgl(pds_vfio, &dirty->host_ack,
-					 page_count);
-	if (err) {
-		__pds_vfio_dirty_free_sgl(pds_vfio, &dirty->host_seq);
-		return err;
-	}
+	dirty->sgl = sgl;
+	dirty->num_sge = max_sge;
+	dirty->sgl_addr = sgl_addr;
 
 	return 0;
 }
@@ -328,6 +307,8 @@ static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio,
 	u8 dma_dir = read_seq ? DMA_FROM_DEVICE : DMA_TO_DEVICE;
 	struct pci_dev *pdev = pds_vfio->vfio_coredev.pdev;
 	struct device *pdsc_dev = &pci_physfn(pdev)->dev;
+	struct pds_vfio_dirty *dirty = &pds_vfio->dirty;
+	struct pds_lm_sg_elem *sgl;
 	unsigned long long npages;
 	struct sg_table sg_table;
 	struct scatterlist *sg;
@@ -374,8 +355,9 @@ static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio,
 	if (err)
 		goto out_free_sg_table;
 
+	sgl = pds_vfio->dirty.sgl;
 	for_each_sgtable_dma_sg(&sg_table, sg, i) {
-		struct pds_lm_sg_elem *sg_elem = &bmp_info->sgl[i];
+		struct pds_lm_sg_elem *sg_elem = &sgl[i];
 
 		sg_elem->addr = cpu_to_le64(sg_dma_address(sg));
 		sg_elem->len = cpu_to_le32(sg_dma_len(sg));
@@ -383,15 +365,15 @@ static int pds_vfio_dirty_seq_ack(struct pds_vfio_pci_device *pds_vfio,
 
 	num_sge = sg_table.nents;
 	size = num_sge * sizeof(struct pds_lm_sg_elem);
-	dma_sync_single_for_device(pdsc_dev, bmp_info->sgl_addr, size, dma_dir);
-	err = pds_vfio_dirty_seq_ack_cmd(pds_vfio, bmp_info->sgl_addr, num_sge,
+	dma_sync_single_for_device(pdsc_dev, dirty->sgl_addr, size, dma_dir);
+	err = pds_vfio_dirty_seq_ack_cmd(pds_vfio, dirty->sgl_addr, num_sge,
 					 offset, bmp_bytes, read_seq);
 	if (err)
 		dev_err(&pdev->dev,
 			"Dirty bitmap %s failed offset %u bmp_bytes %u num_sge %u DMA 0x%llx: %pe\n",
 			bmp_type_str, offset, bmp_bytes,
-			num_sge, bmp_info->sgl_addr, ERR_PTR(err));
-	dma_sync_single_for_cpu(pdsc_dev, bmp_info->sgl_addr, size, dma_dir);
+			num_sge, dirty->sgl_addr, ERR_PTR(err));
+	dma_sync_single_for_cpu(pdsc_dev, dirty->sgl_addr, size, dma_dir);
 
 	dma_unmap_sgtable(pdsc_dev, &sg_table, dma_dir, 0);
 out_free_sg_table:
diff --git a/drivers/vfio/pci/pds/dirty.h b/drivers/vfio/pci/pds/dirty.h
index f78da25d75ca..9de5aac58190 100644
--- a/drivers/vfio/pci/pds/dirty.h
+++ b/drivers/vfio/pci/pds/dirty.h
@@ -7,9 +7,6 @@
 struct pds_vfio_bmp_info {
 	unsigned long *bmp;
 	u32 bmp_bytes;
-	struct pds_lm_sg_elem *sgl;
-	dma_addr_t sgl_addr;
-	u16 num_sge;
 };
 
 struct pds_vfio_dirty {
@@ -18,6 +15,9 @@ struct pds_vfio_dirty {
 	u64 region_size;
 	u64 region_start;
 	u64 region_page_size;
+	struct pds_lm_sg_elem *sgl;
+	dma_addr_t sgl_addr;
+	u16 num_sge;
 	bool is_enabled;
 };
 
-- 
2.17.1