Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.18 as permitted sender) client-ip=23.128.96.18;
From:   Logan Gunthorpe <logang@deltatee.com>
To:     linux-kernel@vger.kernel.org, linux-nvme@lists.infradead.org,
        linux-block@vger.kernel.org, linux-pci@vger.kernel.org,
        linux-mm@kvack.org, iommu@lists.linux-foundation.org
Cc:     Stephen Bates <sbates@raithlin.com>,
        Christoph Hellwig <hch@lst.de>,
        Dan Williams <dan.j.williams@intel.com>,
        Jason Gunthorpe <jgg@ziepe.ca>,
        =?UTF-8?q?Christian=20K=C3=B6nig?= <christian.koenig@amd.com>,
        Ira Weiny <iweiny@intel.com>,
        John Hubbard <jhubbard@nvidia.com>,
        Don Dutile <ddutile@redhat.com>,
        Matthew Wilcox <willy@infradead.org>,
        Daniel Vetter <daniel.vetter@ffwll.ch>,
        Logan Gunthorpe <logang@deltatee.com>
Date:   Fri,  6 Nov 2020 10:00:28 -0700
Message-Id: <20201106170036.18713-8-logang@deltatee.com>
In-Reply-To: <20201106170036.18713-1-logang@deltatee.com>
References: <20201106170036.18713-1-logang@deltatee.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Subject: [RFC PATCH 07/15] iommu/dma: Support PCI P2PDMA pages in dma-iommu map_sg
Precedence: bulk

When a PCI P2PDMA page is seen, set the IOVA length of the segment
to zero so that it is not mapped into the IOVA. Then, in finalise_sg(),
apply the appropriate bus address to the segment. The IOVA is not
created if the scatterlist only consists of P2PDMA pages.

Similar to dma-direct, DMA_ATTR_P2PDMA is used to indicate caller
support seeing the high bit of the dma_length is used as a flag
to indicate P2PDMA segments.

On unmap, P2PDMA segments are skipped over when determining the
start and end IOVA addresses.

With this change, the flags variable in the dma_map_ops is
set to DMA_F_PCI_P2PDMA_SUPPORTED to indicate support for
P2PDMA pages.

Signed-off-by: Logan Gunthorpe <logang@deltatee.com>
---
 drivers/iommu/dma-iommu.c | 63 ++++++++++++++++++++++++++++++++-------
 1 file changed, 53 insertions(+), 10 deletions(-)

diff --git a/drivers/iommu/dma-iommu.c b/drivers/iommu/dma-iommu.c
index 5591d6593583..1c8402474376 100644
--- a/drivers/iommu/dma-iommu.c
+++ b/drivers/iommu/dma-iommu.c
@@ -20,6 +20,7 @@
 #include <linux/mm.h>
 #include <linux/mutex.h>
 #include <linux/pci.h>
+#include <linux/pci-p2pdma.h>
 #include <linux/swiotlb.h>
 #include <linux/scatterlist.h>
 #include <linux/vmalloc.h>
@@ -872,13 +873,16 @@ static void iommu_dma_unmap_page(struct device *dev, dma_addr_t dma_handle,
  * segment's start address to avoid concatenating across one.
  */
 static int __finalise_sg(struct device *dev, struct scatterlist *sg, int nents,
-		dma_addr_t dma_addr)
+		dma_addr_t dma_addr, unsigned long attrs)
 {
 	struct scatterlist *s, *cur = sg;
 	unsigned long seg_mask = dma_get_seg_boundary(dev);
 	unsigned int cur_len = 0, max_len = dma_get_max_seg_size(dev);
 	int i, count = 0;
 
+	if (attrs & DMA_ATTR_P2PDMA && max_len >= SG_P2PDMA_FLAG)
+		max_len = SG_P2PDMA_FLAG - 1;
+
 	/*
 	 * The Intel graphic driver is used to assume that the returned
 	 * sg list is not combound. This blocks the efforts of converting
@@ -917,6 +921,19 @@ static int __finalise_sg(struct device *dev, struct scatterlist *sg, int nents,
 		sg_dma_address(s) = DMA_MAPPING_ERROR;
 		sg_dma_len(s) = 0;
 
+		if (is_pci_p2pdma_page(sg_page(s)) && !s_iova_len) {
+			if (i > 0)
+				cur = sg_next(cur);
+
+			sg_dma_address(cur) = sg_phys(s) + s->offset -
+				pci_p2pdma_bus_offset(sg_page(s));
+			sg_dma_len(cur) = s->length | SG_P2PDMA_FLAG;
+
+			count++;
+			cur_len = 0;
+			continue;
+		}
+
 		/*
 		 * Now fill in the real DMA data. If...
 		 * - there is a valid output segment to append to
@@ -1013,11 +1030,12 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	struct iommu_dma_cookie *cookie = domain->iova_cookie;
 	struct iova_domain *iovad = &cookie->iovad;
 	struct scatterlist *s, *prev = NULL;
+	struct dev_pagemap *pgmap = NULL;
 	int prot = dma_info_to_prot(dir, dev_is_dma_coherent(dev), attrs);
 	dma_addr_t iova;
 	size_t iova_len = 0;
 	unsigned long mask = dma_get_seg_boundary(dev);
-	int i;
+	int i, map = -1;
 
 	if (unlikely(iommu_dma_deferred_attach(dev, domain)))
 		return 0;
@@ -1045,6 +1063,21 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 		s_length = iova_align(iovad, s_length + s_iova_off);
 		s->length = s_length;
 
+		if (is_pci_p2pdma_page(sg_page(s))) {
+			if (sg_page(s)->pgmap != pgmap) {
+				pgmap = sg_page(s)->pgmap;
+				map = pci_p2pdma_should_map_bus(dev, pgmap);
+			}
+
+			if (map < 0 || !(attrs & DMA_ATTR_P2PDMA))
+				goto out_restore_sg;
+
+			if (map) {
+				s->length = 0;
+				continue;
+			}
+		}
+
 		/*
 		 * Due to the alignment of our single IOVA allocation, we can
 		 * depend on these assumptions about the segment boundary mask:
@@ -1067,6 +1100,9 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 		prev = s;
 	}
 
+	if (!iova_len)
+		return __finalise_sg(dev, sg, nents, 0, attrs);
+
 	iova = iommu_dma_alloc_iova(domain, iova_len, dma_get_mask(dev), dev);
 	if (!iova)
 		goto out_restore_sg;
@@ -1078,7 +1114,7 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 	if (iommu_map_sg_atomic(domain, iova, sg, nents, prot) < iova_len)
 		goto out_free_iova;
 
-	return __finalise_sg(dev, sg, nents, iova);
+	return __finalise_sg(dev, sg, nents, iova, attrs);
 
 out_free_iova:
 	iommu_dma_free_iova(cookie, iova, iova_len, NULL);
@@ -1090,7 +1126,7 @@ static int iommu_dma_map_sg(struct device *dev, struct scatterlist *sg,
 static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 		int nents, enum dma_data_direction dir, unsigned long attrs)
 {
-	dma_addr_t start, end;
+	dma_addr_t end, start = DMA_MAPPING_ERROR;
 	struct scatterlist *tmp;
 	int i;
 
@@ -1106,14 +1142,20 @@ static void iommu_dma_unmap_sg(struct device *dev, struct scatterlist *sg,
 	 * The scatterlist segments are mapped into a single
 	 * contiguous IOVA allocation, so this is incredibly easy.
 	 */
-	start = sg_dma_address(sg);
-	for_each_sg(sg_next(sg), tmp, nents - 1, i) {
-		if (sg_dma_len(tmp) == 0)
+	for_each_sg(sg, tmp, nents, i) {
+		if ((attrs & DMA_ATTR_P2PDMA) && sg_dma_is_p2pdma(tmp))
+			continue;
+		if (sg_dma_p2pdma_len(tmp) == 0)
 			break;
-		sg = tmp;
+
+		if (start == DMA_MAPPING_ERROR)
+			start = sg_dma_address(tmp);
+
+		end = sg_dma_address(tmp) + sg_dma_len(tmp);
 	}
-	end = sg_dma_address(sg) + sg_dma_len(sg);
-	__iommu_dma_unmap(dev, start, end - start);
+
+	if (start != DMA_MAPPING_ERROR)
+		__iommu_dma_unmap(dev, start, end - start);
 }
 
 static dma_addr_t iommu_dma_map_resource(struct device *dev, phys_addr_t phys,
@@ -1334,6 +1376,7 @@ static unsigned long iommu_dma_get_merge_boundary(struct device *dev)
 }
 
 static const struct dma_map_ops iommu_dma_ops = {
+	.flags			= DMA_F_PCI_P2PDMA_SUPPORTED,
 	.alloc			= iommu_dma_alloc,
 	.free			= iommu_dma_free,
 	.alloc_pages		= dma_common_alloc_pages,
-- 
2.20.1