Message-ID: <0a517ddff099c14fac1ceb0e75f2f50ed183d09c.1730037276.git.leon@kernel.org>
Date: Sun, 27 Oct 2024 16:21:18 +0200
From: Leon Romanovsky <leon@...nel.org>
To: Jens Axboe <axboe@...nel.dk>,
	Jason Gunthorpe <jgg@...pe.ca>,
	Robin Murphy <robin.murphy@....com>,
	Joerg Roedel <joro@...tes.org>,
	Will Deacon <will@...nel.org>,
	Christoph Hellwig <hch@....de>,
	Sagi Grimberg <sagi@...mberg.me>
Cc: Leon Romanovsky <leonro@...dia.com>,
	Keith Busch <kbusch@...nel.org>,
	Bjorn Helgaas <bhelgaas@...gle.com>,
	Logan Gunthorpe <logang@...tatee.com>,
	Yishai Hadas <yishaih@...dia.com>,
	Shameer Kolothum <shameerali.kolothum.thodi@...wei.com>,
	Kevin Tian <kevin.tian@...el.com>,
	Alex Williamson <alex.williamson@...hat.com>,
	Marek Szyprowski <m.szyprowski@...sung.com>,
	Jérôme Glisse <jglisse@...hat.com>,
	Andrew Morton <akpm@...ux-foundation.org>,
	Jonathan Corbet <corbet@....net>,
	linux-doc@...r.kernel.org,
	linux-kernel@...r.kernel.org,
	linux-block@...r.kernel.org,
	linux-rdma@...r.kernel.org,
	iommu@...ts.linux.dev,
	linux-nvme@...ts.infradead.org,
	linux-pci@...r.kernel.org,
	kvm@...r.kernel.org,
	linux-mm@...ck.org
Subject: [PATCH 18/18] vfio/mlx5: Convert vfio to use DMA link API

From: Leon Romanovsky <leonro@...dia.com>

Remove intermediate scatter-gather table as it is not needed
if DMA link API is used. This conversion reduces drastically
the memory used to manage that table.

Signed-off-by: Leon Romanovsky <leonro@...dia.com>
---
 drivers/vfio/pci/mlx5/cmd.c  | 211 ++++++++++++++++++-----------------
 drivers/vfio/pci/mlx5/cmd.h  |   9 +-
 drivers/vfio/pci/mlx5/main.c |  31 +----
 3 files changed, 114 insertions(+), 137 deletions(-)

diff --git a/drivers/vfio/pci/mlx5/cmd.c b/drivers/vfio/pci/mlx5/cmd.c
index 34ae3e299a9e..58c490222be7 100644
--- a/drivers/vfio/pci/mlx5/cmd.c
+++ b/drivers/vfio/pci/mlx5/cmd.c
@@ -345,25 +345,81 @@ static u32 *alloc_mkey_in(u32 npages, u32 pdn)
 	return in;
 }
 
-static int create_mkey(struct mlx5_core_dev *mdev, u32 npages,
-		       struct mlx5_vhca_data_buffer *buf, u32 *mkey_in,
+static int create_mkey(struct mlx5_core_dev *mdev, u32 npages, u32 *mkey_in,
 		       u32 *mkey)
 {
+	int inlen = MLX5_ST_SZ_BYTES(create_mkey_in) +
+		sizeof(__be64) * round_up(npages, 2);
+
+	return mlx5_core_create_mkey(mdev, mkey, mkey_in, inlen);
+}
+
+static void unregister_dma_pages(struct mlx5_core_dev *mdev, u32 npages,
+				 u32 *mkey_in, struct dma_iova_state *state,
+				 enum dma_data_direction dir)
+{
+	dma_addr_t addr;
 	__be64 *mtt;
-	int inlen;
+	int i;
 
-	mtt = (__be64 *)MLX5_ADDR_OF(create_mkey_in, mkey_in, klm_pas_mtt);
-	if (buf) {
-		struct sg_dma_page_iter dma_iter;
+	WARN_ON_ONCE(dir == DMA_NONE);
 
-		for_each_sgtable_dma_page(&buf->table.sgt, &dma_iter, 0)
-			*mtt++ = cpu_to_be64(sg_page_iter_dma_address(&dma_iter));
+	if (dma_use_iova(state)) {
+		dma_iova_destroy(mdev->device, state, dir, 0);
+	} else {
+		mtt = (__be64 *)MLX5_ADDR_OF(create_mkey_in, mkey_in,
+					     klm_pas_mtt);
+		for (i = npages - 1; i >= 0; i--) {
+			addr = be64_to_cpu(mtt[i]);
+			dma_unmap_page(mdev->device, addr, PAGE_SIZE, dir);
+		}
 	}
+}
 
-	inlen = MLX5_ST_SZ_BYTES(create_mkey_in) +
-		sizeof(__be64) * round_up(npages, 2);
+static int register_dma_pages(struct mlx5_core_dev *mdev, u32 npages,
+			      struct page **page_list, u32 *mkey_in,
+			      struct dma_iova_state *state,
+			      enum dma_data_direction dir)
+{
+	dma_addr_t addr;
+	size_t mapped = 0;
+	__be64 *mtt;
+	int i, err;
 
-	return mlx5_core_create_mkey(mdev, mkey, mkey_in, inlen);
+	WARN_ON_ONCE(dir == DMA_NONE);
+
+	mtt = (__be64 *)MLX5_ADDR_OF(create_mkey_in, mkey_in, klm_pas_mtt);
+
+	if (dma_iova_try_alloc(mdev->device, state, 0, npages * PAGE_SIZE)) {
+		addr = state->addr;
+		for (i = 0; i < npages; i++) {
+			err = dma_iova_link(mdev->device, state,
+					    page_to_phys(page_list[i]), mapped,
+					    PAGE_SIZE, dir, 0);
+			if (err)
+				break;
+			*mtt++ = cpu_to_be64(addr);
+			addr += PAGE_SIZE;
+			mapped += PAGE_SIZE;
+		}
+		err = dma_iova_sync(mdev->device, state, 0, mapped, err);
+		if (err)
+			goto error;
+	} else {
+		for (i = 0; i < npages; i++) {
+			addr = dma_map_page(mdev->device, page_list[i], 0,
+					    PAGE_SIZE, dir);
+			err = dma_mapping_error(mdev->device, addr);
+			if (err)
+				goto error;
+			*mtt++ = cpu_to_be64(addr);
+		}
+	}
+	return 0;
+
+error:
+	unregister_dma_pages(mdev, i, mkey_in, state, dir);
+	return err;
 }
 
 static int mlx5vf_dma_data_buffer(struct mlx5_vhca_data_buffer *buf)
@@ -379,50 +435,57 @@ static int mlx5vf_dma_data_buffer(struct mlx5_vhca_data_buffer *buf)
 	if (buf->mkey_in || !buf->npages)
 		return -EINVAL;
 
-	ret = dma_map_sgtable(mdev->device, &buf->table.sgt, buf->dma_dir, 0);
-	if (ret)
-		return ret;
-
 	buf->mkey_in = alloc_mkey_in(buf->npages, buf->migf->pdn);
-	if (!buf->mkey_in) {
-		ret = -ENOMEM;
-		goto err;
-	}
+	if (!buf->mkey_in)
+		return -ENOMEM;
+
+	ret = register_dma_pages(mdev, buf->npages, buf->page_list,
+				 buf->mkey_in, &buf->state, buf->dma_dir);
+	if (ret)
+		goto err_register_dma;
 
-	ret = create_mkey(mdev, buf->npages, buf, buf->mkey_in, &buf->mkey);
+	ret = create_mkey(mdev, buf->npages, buf->mkey_in, &buf->mkey);
 	if (ret)
 		goto err_create_mkey;
 
 	return 0;
 
 err_create_mkey:
+	unregister_dma_pages(mdev, buf->npages, buf->mkey_in, &buf->state,
+			     buf->dma_dir);
+err_register_dma:
 	kvfree(buf->mkey_in);
 	buf->mkey_in = NULL;
-err:
-	dma_unmap_sgtable(mdev->device, &buf->table.sgt, buf->dma_dir, 0);
 	return ret;
 }
 
+static void free_page_list(u32 npages, struct page **page_list)
+{
+	int i;
+
+	/* Undo alloc_pages_bulk_array() */
+	for (i = npages - 1; i >= 0; i--)
+		__free_page(page_list[i]);
+
+	kvfree(page_list);
+}
+
 void mlx5vf_free_data_buffer(struct mlx5_vhca_data_buffer *buf)
 {
-	struct mlx5_vf_migration_file *migf = buf->migf;
-	struct sg_page_iter sg_iter;
+	struct mlx5vf_pci_core_device *mvdev = buf->migf->mvdev;
+	struct mlx5_core_dev *mdev = mvdev->mdev;
 
-	lockdep_assert_held(&migf->mvdev->state_mutex);
-	WARN_ON(migf->mvdev->mdev_detach);
+	lockdep_assert_held(&mvdev->state_mutex);
+	WARN_ON(mvdev->mdev_detach);
 
 	if (buf->mkey_in) {
-		mlx5_core_destroy_mkey(migf->mvdev->mdev, buf->mkey);
+		mlx5_core_destroy_mkey(mdev, buf->mkey);
+		unregister_dma_pages(mdev, buf->npages, buf->mkey_in,
+				     &buf->state, buf->dma_dir);
 		kvfree(buf->mkey_in);
-		dma_unmap_sgtable(migf->mvdev->mdev->device, &buf->table.sgt,
-				  buf->dma_dir, 0);
 	}
 
-	/* Undo alloc_pages_bulk_array() */
-	for_each_sgtable_page(&buf->table.sgt, &sg_iter, 0)
-		__free_page(sg_page_iter_page(&sg_iter));
-	sg_free_append_table(&buf->table);
-	kvfree(buf->page_list);
+	free_page_list(buf->npages, buf->page_list);
 	kfree(buf);
 }
 
@@ -433,7 +496,6 @@ static int mlx5vf_add_migration_pages(struct mlx5_vhca_data_buffer *buf,
 	struct page **page_list;
 	unsigned long filled;
 	unsigned int to_fill;
-	int ret;
 
 	to_fill = min_t(unsigned int, npages, PAGE_SIZE / sizeof(*buf->page_list));
 	page_list = kvzalloc(to_fill * sizeof(*buf->page_list), GFP_KERNEL_ACCOUNT);
@@ -443,22 +505,13 @@ static int mlx5vf_add_migration_pages(struct mlx5_vhca_data_buffer *buf,
 	buf->page_list = page_list;
 
 	do {
-		filled = alloc_pages_bulk_array(GFP_KERNEL_ACCOUNT, to_fill,
-				buf->page_list + buf->npages);
+		filled = alloc_pages_bulk_array(GFP_KERNEL_ACCOUNT, to_alloc,
+						buf->page_list + buf->npages);
 		if (!filled)
 			return -ENOMEM;
 
 		to_alloc -= filled;
-		ret = sg_alloc_append_table_from_pages(
-			&buf->table, buf->page_list + buf->npages, filled, 0,
-			filled << PAGE_SHIFT, UINT_MAX, SG_MAX_SINGLE_ALLOC,
-			GFP_KERNEL_ACCOUNT);
-
-		if (ret)
-			return ret;
 		buf->npages += filled;
-		to_fill = min_t(unsigned int, to_alloc,
-				PAGE_SIZE / sizeof(*buf->page_list));
 	} while (to_alloc > 0);
 
 	return 0;
@@ -1340,17 +1393,6 @@ static void mlx5vf_destroy_qp(struct mlx5_core_dev *mdev,
 	kfree(qp);
 }
 
-static void free_recv_pages(struct mlx5_vhca_recv_buf *recv_buf)
-{
-	int i;
-
-	/* Undo alloc_pages_bulk_array() */
-	for (i = 0; i < recv_buf->npages; i++)
-		__free_page(recv_buf->page_list[i]);
-
-	kvfree(recv_buf->page_list);
-}
-
 static int alloc_recv_pages(struct mlx5_vhca_recv_buf *recv_buf,
 			    unsigned int npages)
 {
@@ -1386,45 +1428,6 @@ static int alloc_recv_pages(struct mlx5_vhca_recv_buf *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 = (__be64 *)MLX5_ADDR_OF(create_mkey_in, mkey_in, klm_pas_mtt);
-	for (i = npages - 1; i >= 0; i--) {
-		addr = be64_to_cpu(mtt[i]);
-		dma_unmap_single(mdev->device, addr, PAGE_SIZE,
-				DMA_FROM_DEVICE);
-	}
-}
-
-static int register_dma_pages(struct mlx5_core_dev *mdev, u32 npages,
-			      struct page **page_list, u32 *mkey_in)
-{
-	dma_addr_t addr;
-	__be64 *mtt;
-	int i;
-
-	mtt = (__be64 *)MLX5_ADDR_OF(create_mkey_in, mkey_in, klm_pas_mtt);
-
-	for (i = 0; i < npages; i++) {
-		addr = dma_map_page(mdev->device, page_list[i], 0, PAGE_SIZE,
-				    DMA_FROM_DEVICE);
-		if (dma_mapping_error(mdev->device, addr))
-			goto error;
-
-		*mtt++ = cpu_to_be64(addr);
-	}
-
-	return 0;
-
-error:
-	unregister_dma_pages(mdev, i, mkey_in);
-	return -ENOMEM;
-}
 
 static void mlx5vf_free_qp_recv_resources(struct mlx5_core_dev *mdev,
 					  struct mlx5_vhca_qp *qp)
@@ -1432,9 +1435,10 @@ static void mlx5vf_free_qp_recv_resources(struct mlx5_core_dev *mdev,
 	struct mlx5_vhca_recv_buf *recv_buf = &qp->recv_buf;
 
 	mlx5_core_destroy_mkey(mdev, recv_buf->mkey);
-	unregister_dma_pages(mdev, recv_buf->npages, recv_buf->mkey_in);
+	unregister_dma_pages(mdev, recv_buf->npages, recv_buf->mkey_in,
+			     &recv_buf->state, DMA_FROM_DEVICE);
 	kvfree(recv_buf->mkey_in);
-	free_recv_pages(&qp->recv_buf);
+	free_page_list(recv_buf->npages, recv_buf->page_list);
 }
 
 static int mlx5vf_alloc_qp_recv_resources(struct mlx5_core_dev *mdev,
@@ -1456,24 +1460,25 @@ static int mlx5vf_alloc_qp_recv_resources(struct mlx5_core_dev *mdev,
 	}
 
 	err = register_dma_pages(mdev, npages, recv_buf->page_list,
-				 recv_buf->mkey_in);
+				 recv_buf->mkey_in, &recv_buf->state,
+				 DMA_FROM_DEVICE);
 	if (err)
 		goto err_register_dma;
 
-	err = create_mkey(mdev, npages, NULL, recv_buf->mkey_in,
-			  &recv_buf->mkey);
+	err = create_mkey(mdev, npages, recv_buf->mkey_in, &recv_buf->mkey);
 	if (err)
 		goto err_create_mkey;
 
 	return 0;
 
 err_create_mkey:
-	unregister_dma_pages(mdev, npages, recv_buf->mkey_in);
+	unregister_dma_pages(mdev, npages, recv_buf->mkey_in, &recv_buf->state,
+			     DMA_FROM_DEVICE);
 err_register_dma:
 	kvfree(recv_buf->mkey_in);
 	recv_buf->mkey_in = NULL;
 end:
-	free_recv_pages(recv_buf);
+	free_page_list(npages, recv_buf->page_list);
 	return err;
 }
 
diff --git a/drivers/vfio/pci/mlx5/cmd.h b/drivers/vfio/pci/mlx5/cmd.h
index 5b764199db53..f9c7268272e7 100644
--- a/drivers/vfio/pci/mlx5/cmd.h
+++ b/drivers/vfio/pci/mlx5/cmd.h
@@ -54,20 +54,16 @@ struct mlx5_vf_migration_header {
 
 struct mlx5_vhca_data_buffer {
 	struct page **page_list;
-	struct sg_append_table table;
+	struct dma_iova_state state;
+	enum dma_data_direction dma_dir;
 	loff_t start_pos;
 	u64 length;
 	u32 npages;
 	u32 mkey;
 	u32 *mkey_in;
-	enum dma_data_direction dma_dir;
 	u8 stop_copy_chunk_num;
 	struct list_head buf_elm;
 	struct mlx5_vf_migration_file *migf;
-	/* Optimize mlx5vf_get_migration_page() for sequential access */
-	struct scatterlist *last_offset_sg;
-	unsigned int sg_last_entry;
-	unsigned long last_offset;
 };
 
 struct mlx5vf_async_data {
@@ -134,6 +130,7 @@ struct mlx5_vhca_cq {
 struct mlx5_vhca_recv_buf {
 	u32 npages;
 	struct page **page_list;
+	struct dma_iova_state state;
 	u32 next_rq_offset;
 	u32 *mkey_in;
 	u32 mkey;
diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c
index a1dbee3be1e0..cac99e6b047d 100644
--- a/drivers/vfio/pci/mlx5/main.c
+++ b/drivers/vfio/pci/mlx5/main.c
@@ -34,35 +34,10 @@ static struct mlx5vf_pci_core_device *mlx5vf_drvdata(struct pci_dev *pdev)
 			    core_device);
 }
 
-struct page *
-mlx5vf_get_migration_page(struct mlx5_vhca_data_buffer *buf,
-			  unsigned long offset)
+struct page *mlx5vf_get_migration_page(struct mlx5_vhca_data_buffer *buf,
+				       unsigned long offset)
 {
-	unsigned long cur_offset = 0;
-	struct scatterlist *sg;
-	unsigned int i;
-
-	/* All accesses are sequential */
-	if (offset < buf->last_offset || !buf->last_offset_sg) {
-		buf->last_offset = 0;
-		buf->last_offset_sg = buf->table.sgt.sgl;
-		buf->sg_last_entry = 0;
-	}
-
-	cur_offset = buf->last_offset;
-
-	for_each_sg(buf->last_offset_sg, sg,
-			buf->table.sgt.orig_nents - buf->sg_last_entry, i) {
-		if (offset < sg->length + cur_offset) {
-			buf->last_offset_sg = sg;
-			buf->sg_last_entry += i;
-			buf->last_offset = cur_offset;
-			return nth_page(sg_page(sg),
-					(offset - cur_offset) / PAGE_SIZE);
-		}
-		cur_offset += sg->length;
-	}
-	return NULL;
+	return buf->page_list[offset / PAGE_SIZE];
 }
 
 static void mlx5vf_disable_fd(struct mlx5_vf_migration_file *migf)
-- 
2.46.2

Powered by blists - more mailing lists