[PATCH v2] vfio: do not coalesce DMA mappings

[Nipun Gupta]

At the cleanup time when dma unmap is done, linux kernel
does not allow unmap of individual segments which were
coalesced together while creating the DMA map for type1 IOMMU
mappings. So, this change updates the mapping of the memory
segments(hugepages) on a per-page basis.

Signed-off-by: Nipun Gupta <nipun.gupta at amd.com>
Signed-off-by: Nikhil Agarwal <nikhil.agarwal at amd.com>
---

Changes in v2:
- Fix checkpatch errors by updated mailmap

 .mailmap                 |  4 ++--
 lib/eal/linux/eal_vfio.c | 29 -----------------------------
 2 files changed, 2 insertions(+), 31 deletions(-)

diff --git a/.mailmap b/.mailmap
index 75884b6fe2..a234c9b3de 100644
--- a/.mailmap
+++ b/.mailmap
@@ -954,7 +954,7 @@ Nicolas Chautru <nicolas.chautru at intel.com>
 Nicolas Dichtel <nicolas.dichtel at 6wind.com>
 Nicolas Harnois <nicolas.harnois at 6wind.com>
 Nicolás Pernas Maradei <nico at emutex.com> <nicolas.pernas.maradei at emutex.com>
-Nikhil Agarwal <nikhil.agarwal at linaro.org>
+Nikhil Agarwal <nikhil.agarwal at amd.com> <nikhil.agarwal at xilinx.com> <nikhil.agarwal at linaro.org>
 Nikhil Jagtap <nikhil.jagtap at gmail.com>
 Nikhil Rao <nikhil.rao at intel.com>
 Nikhil Vasoya <nikhil.vasoya at chelsio.com>
@@ -962,7 +962,7 @@ Nikita Kozlov <nikita at elyzion.net>
 Niklas Söderlund <niklas.soderlund at corigine.com>
 Nikolay Nikolaev <nicknickolaev at gmail.com>
 Ning Li <muziding001 at 163.com> <lining18 at jd.com>
-Nipun Gupta <nipun.gupta at nxp.com>
+Nipun Gupta <nipun.gupta at amd.com> <nipun.gupta at xilinx.com> <nipun.gupta at nxp.com>
 Nir Efrati <nir.efrati at intel.com>
 Nirmoy Das <ndas at suse.de>
 Nithin Dabilpuram <ndabilpuram at marvell.com> <nithin.dabilpuram at caviumnetworks.com>
diff --git a/lib/eal/linux/eal_vfio.c b/lib/eal/linux/eal_vfio.c
index 549b86ae1d..56edccb0db 100644
--- a/lib/eal/linux/eal_vfio.c
+++ b/lib/eal/linux/eal_vfio.c
@@ -1369,19 +1369,6 @@ rte_vfio_get_group_num(const char *sysfs_base,
 	return 1;
 }
 
-static int
-type1_map_contig(const struct rte_memseg_list *msl, const struct rte_memseg *ms,
-		size_t len, void *arg)
-{
-	int *vfio_container_fd = arg;
-
-	if (msl->external)
-		return 0;
-
-	return vfio_type1_dma_mem_map(*vfio_container_fd, ms->addr_64, ms->iova,
-			len, 1);
-}
-
 static int
 type1_map(const struct rte_memseg_list *msl, const struct rte_memseg *ms,
 		void *arg)
@@ -1396,10 +1383,6 @@ type1_map(const struct rte_memseg_list *msl, const struct rte_memseg *ms,
 	if (ms->iova == RTE_BAD_IOVA)
 		return 0;
 
-	/* if IOVA mode is VA, we've already mapped the internal segments */
-	if (!msl->external && rte_eal_iova_mode() == RTE_IOVA_VA)
-		return 0;
-
 	return vfio_type1_dma_mem_map(*vfio_container_fd, ms->addr_64, ms->iova,
 			ms->len, 1);
 }
@@ -1464,18 +1447,6 @@ vfio_type1_dma_mem_map(int vfio_container_fd, uint64_t vaddr, uint64_t iova,
 static int
 vfio_type1_dma_map(int vfio_container_fd)
 {
-	if (rte_eal_iova_mode() == RTE_IOVA_VA) {
-		/* with IOVA as VA mode, we can get away with mapping contiguous
-		 * chunks rather than going page-by-page.
-		 */
-		int ret = rte_memseg_contig_walk(type1_map_contig,
-				&vfio_container_fd);
-		if (ret)
-			return ret;
-		/* we have to continue the walk because we've skipped the
-		 * external segments during the config walk.
-		 */
-	}
 	return rte_memseg_walk(type1_map, &vfio_container_fd);
 }
 
-- 
2.25.1