[dpdk-dev] [PATCH 22/23] vfio: allow to map other memory regions

[Anatoly Burakov]

Currently it is not possible to use memory that is not owned by DPDK to
perform DMA. This scenarion might be used in vhost applications (like
SPDK) where guest send its own memory table. To fill this gap provide
API to allow registering arbitrary address in VFIO container.

Signed-off-by: Pawel Wodkowski <pawelx.wodkowski at intel.com>
Signed-off-by: Anatoly Burakov <anatoly.burakov at intel.com>
---
 lib/librte_eal/linuxapp/eal/eal_vfio.c | 150 ++++++++++++++++++++++++++++-----
 lib/librte_eal/linuxapp/eal/eal_vfio.h |  11 +++
 2 files changed, 140 insertions(+), 21 deletions(-)

diff --git a/lib/librte_eal/linuxapp/eal/eal_vfio.c b/lib/librte_eal/linuxapp/eal/eal_vfio.c
index 09dfc68..15d28ad 100644
--- a/lib/librte_eal/linuxapp/eal/eal_vfio.c
+++ b/lib/librte_eal/linuxapp/eal/eal_vfio.c
@@ -40,6 +40,7 @@
 #include <rte_memory.h>
 #include <rte_eal_memconfig.h>
 #include <rte_vfio.h>
+#include <rte_iommu.h>
 
 #include "eal_filesystem.h"
 #include "eal_vfio.h"
@@ -51,17 +52,35 @@
 static struct vfio_config vfio_cfg;
 
 static int vfio_type1_dma_map(int);
+static int vfio_type1_dma_mem_map(int, uint64_t, uint64_t, uint64_t, int);
 static int vfio_spapr_dma_map(int);
 static int vfio_noiommu_dma_map(int);
+static int vfio_noiommu_dma_mem_map(int, uint64_t, uint64_t, uint64_t, int);
 
 /* IOMMU types we support */
 static const struct vfio_iommu_type iommu_types[] = {
 	/* x86 IOMMU, otherwise known as type 1 */
-	{ RTE_VFIO_TYPE1, "Type 1", &vfio_type1_dma_map},
+	{
+		.type_id = RTE_VFIO_TYPE1,
+		.name = "Type 1",
+		.dma_map_func = &vfio_type1_dma_map,
+		.dma_user_map_func = &vfio_type1_dma_mem_map
+	},
 	/* ppc64 IOMMU, otherwise known as spapr */
-	{ RTE_VFIO_SPAPR, "sPAPR", &vfio_spapr_dma_map},
+	{
+		.type_id = RTE_VFIO_SPAPR,
+		.name = "sPAPR",
+		.dma_map_func = &vfio_spapr_dma_map,
+		.dma_user_map_func = NULL
+		// TODO: work with PPC64 people on enabling this, window size!
+	},
 	/* IOMMU-less mode */
-	{ RTE_VFIO_NOIOMMU, "No-IOMMU", &vfio_noiommu_dma_map},
+	{
+		.type_id = RTE_VFIO_NOIOMMU,
+		.name = "No-IOMMU",
+		.dma_map_func = &vfio_noiommu_dma_map,
+		.dma_user_map_func = &vfio_noiommu_dma_mem_map
+	},
 };
 
 int
@@ -362,9 +381,10 @@ rte_vfio_setup_device(const char *sysfs_base, const char *dev_addr,
 		 */
 		if (internal_config.process_type == RTE_PROC_PRIMARY &&
 				vfio_cfg.vfio_active_groups == 1) {
+			const struct vfio_iommu_type *t;
+
 			/* select an IOMMU type which we will be using */
-			const struct vfio_iommu_type *t =
-				vfio_set_iommu_type(vfio_cfg.vfio_container_fd);
+			t = vfio_set_iommu_type(vfio_cfg.vfio_container_fd);
 			if (!t) {
 				RTE_LOG(ERR, EAL,
 					"  %s failed to select IOMMU type\n",
@@ -382,6 +402,8 @@ rte_vfio_setup_device(const char *sysfs_base, const char *dev_addr,
 				clear_group(vfio_group_fd);
 				return -1;
 			}
+
+			vfio_cfg.vfio_iommu_type = t;
 		}
 	}
 
@@ -694,13 +716,52 @@ vfio_get_group_no(const char *sysfs_base,
 }
 
 static int
+vfio_type1_dma_mem_map(int vfio_container_fd, uint64_t vaddr, uint64_t iova,
+		uint64_t len, int do_map)
+{
+	struct vfio_iommu_type1_dma_map dma_map;
+	struct vfio_iommu_type1_dma_unmap dma_unmap;
+	int ret;
+
+	if (do_map != 0) {
+		memset(&dma_map, 0, sizeof(dma_map));
+		dma_map.argsz = sizeof(struct vfio_iommu_type1_dma_map);
+		dma_map.vaddr = vaddr;
+		dma_map.size = len;
+		dma_map.iova = iova;
+		dma_map.flags = VFIO_DMA_MAP_FLAG_READ | VFIO_DMA_MAP_FLAG_WRITE;
+
+		ret = ioctl(vfio_container_fd, VFIO_IOMMU_MAP_DMA, &dma_map);
+		if (ret) {
+			RTE_LOG(ERR, EAL, "  cannot set up DMA remapping, error %i (%s)\n",
+				errno, strerror(errno));
+				return -1;
+		}
+
+	} else {
+		memset(&dma_unmap, 0, sizeof(dma_unmap));
+		dma_unmap.argsz = sizeof(struct vfio_iommu_type1_dma_unmap);
+		dma_unmap.size = len;
+		dma_unmap.iova = iova;
+
+		ret = ioctl(vfio_container_fd, VFIO_IOMMU_UNMAP_DMA, &dma_unmap);
+		if (ret) {
+			RTE_LOG(ERR, EAL, "  cannot clear DMA remapping, error %i (%s)\n",
+					errno, strerror(errno));
+			return -1;
+		}
+	}
+
+	return 0;
+}
+
+static int
 vfio_type1_dma_map(int vfio_container_fd)
 {
-	int i, ret;
+	int i;
 
 	/* map all DPDK segments for DMA. use 1:1 PA to IOVA mapping */
 	for (i = 0; i < RTE_MAX_MEMSEG_LISTS; i++) {
-		struct vfio_iommu_type1_dma_map dma_map;
 		const struct rte_memseg_list *msl;
 		const struct rte_fbarray *arr;
 		int ms_idx, next_idx;
@@ -727,21 +788,9 @@ vfio_type1_dma_map(int vfio_container_fd)
 			len = ms->hugepage_sz;
 			hw_addr = ms->iova;
 
-			memset(&dma_map, 0, sizeof(dma_map));
-			dma_map.argsz = sizeof(struct vfio_iommu_type1_dma_map);
-			dma_map.vaddr = addr;
-			dma_map.size = len;
-			dma_map.iova = hw_addr;
-			dma_map.flags = VFIO_DMA_MAP_FLAG_READ | VFIO_DMA_MAP_FLAG_WRITE;
-
-			ret = ioctl(vfio_container_fd, VFIO_IOMMU_MAP_DMA, &dma_map);
-
-			if (ret) {
-				RTE_LOG(ERR, EAL, "  cannot set up DMA remapping, "
-						  "error %i (%s)\n", errno,
-						  strerror(errno));
+			if (vfio_type1_dma_mem_map(vfio_container_fd, addr,
+					hw_addr, len, 1))
 				return -1;
-			}
 		}
 	}
 
@@ -892,6 +941,49 @@ vfio_noiommu_dma_map(int __rte_unused vfio_container_fd)
 	return 0;
 }
 
+static int
+vfio_noiommu_dma_mem_map(int __rte_unused vfio_container_fd,
+			 uint64_t __rte_unused vaddr,
+			 uint64_t __rte_unused iova, uint64_t __rte_unused len,
+			 int __rte_unused do_map)
+{
+	/* No-IOMMU mode does not need DMA mapping */
+	return 0;
+}
+
+static int
+vfio_dma_mem_map(uint64_t vaddr, uint64_t iova, uint64_t len, int do_map)
+{
+	const struct vfio_iommu_type *t = vfio_cfg.vfio_iommu_type;
+
+	if (!t) {
+		RTE_LOG(ERR, EAL, "  VFIO support not initialized\n");
+		return -1;
+	}
+
+	if (!t->dma_user_map_func) {
+		RTE_LOG(ERR, EAL,
+			"  VFIO custom DMA region maping not supported by IOMMU %s\n",
+			t->name);
+		return -1;
+	}
+
+	return t->dma_user_map_func(vfio_cfg.vfio_container_fd, vaddr, iova,
+			len, do_map);
+}
+
+int
+rte_iommu_dma_map(uint64_t vaddr, uint64_t iova, uint64_t len)
+{
+	return vfio_dma_mem_map(vaddr, iova, len, 1);
+}
+
+int
+rte_iommu_dma_unmap(uint64_t vaddr, uint64_t iova, uint64_t len)
+{
+	return vfio_dma_mem_map(vaddr, iova, len, 0);
+}
+
 int
 rte_vfio_noiommu_is_enabled(void)
 {
@@ -911,4 +1003,20 @@ rte_vfio_noiommu_is_enabled(void)
 	return ret;
 }
 
+#else
+
+int
+rte_iommu_dma_map(uint64_t __rte_unused vaddr, __rte_unused uint64_t iova,
+		  __rte_unused uint64_t len)
+{
+	return 0;
+}
+
+int
+rte_iommu_dma_unmap(uint64_t __rte_unused vaddr, uint64_t __rte_unused iova,
+		    __rte_unused uint64_t len)
+{
+	return 0;
+}
+
 #endif
diff --git a/lib/librte_eal/linuxapp/eal/eal_vfio.h b/lib/librte_eal/linuxapp/eal/eal_vfio.h
index ba7892b..bb669f0 100644
--- a/lib/librte_eal/linuxapp/eal/eal_vfio.h
+++ b/lib/librte_eal/linuxapp/eal/eal_vfio.h
@@ -48,6 +48,7 @@
 
 #ifdef VFIO_PRESENT
 
+#include <stdint.h>
 #include <linux/vfio.h>
 
 #define RTE_VFIO_TYPE1 VFIO_TYPE1_IOMMU
@@ -139,6 +140,7 @@ struct vfio_config {
 	int vfio_enabled;
 	int vfio_container_fd;
 	int vfio_active_groups;
+	const struct vfio_iommu_type *vfio_iommu_type;
 	struct vfio_group vfio_groups[VFIO_MAX_GROUPS];
 };
 
@@ -148,9 +150,18 @@ struct vfio_config {
  * */
 typedef int (*vfio_dma_func_t)(int);
 
+/* Custom memory region DMA mapping function prototype.
+ * Takes VFIO container fd, virtual address, phisical address, length and
+ * operation type (0 to unmap 1 for map) as a parameters.
+ * Returns 0 on success, -1 on error.
+ **/
+typedef int (*vfio_dma_user_func_t)(int fd, uint64_t vaddr, uint64_t iova,
+		uint64_t len, int do_map);
+
 struct vfio_iommu_type {
 	int type_id;
 	const char *name;
+	vfio_dma_user_func_t dma_user_map_func;
 	vfio_dma_func_t dma_map_func;
 };
 
-- 
2.7.4