X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_eal%2Flinuxapp%2Feal%2Feal_vfio.c;h=58f0123e29aee6ee63fcf634a88d9303c838772b;hb=7ba49d39f14c;hp=6e2e84ca7d3b247eb7349dbcb52901691e32be0a;hpb=94c0776b1badd1ee715d60f07391058f23494365;p=dpdk.git

diff --git a/lib/librte_eal/linuxapp/eal/eal_vfio.c b/lib/librte_eal/linuxapp/eal/eal_vfio.c
index 6e2e84ca7d..58f0123e29 100644
--- a/lib/librte_eal/linuxapp/eal/eal_vfio.c
+++ b/lib/librte_eal/linuxapp/eal/eal_vfio.c
@@ -39,6 +39,7 @@
 #include <rte_log.h>
 #include <rte_memory.h>
 #include <rte_eal_memconfig.h>
+#include <rte_vfio.h>
 
 #include "eal_filesystem.h"
 #include "eal_vfio.h"
@@ -68,8 +69,8 @@ vfio_get_group_fd(int iommu_group_no)
 {
 	int i;
 	int vfio_group_fd;
-	int group_idx = -1;
 	char filename[PATH_MAX];
+	struct vfio_group *cur_grp;
 
 	/* check if we already have the group descriptor open */
 	for (i = 0; i < VFIO_MAX_GROUPS; i++)
@@ -85,12 +86,12 @@ vfio_get_group_fd(int iommu_group_no)
 	/* Now lets get an index for the new group */
 	for (i = 0; i < VFIO_MAX_GROUPS; i++)
 		if (vfio_cfg.vfio_groups[i].group_no == -1) {
-			group_idx = i;
+			cur_grp = &vfio_cfg.vfio_groups[i];
 			break;
 		}
 
 	/* This should not happen */
-	if (group_idx == -1) {
+	if (i == VFIO_MAX_GROUPS) {
 		RTE_LOG(ERR, EAL, "No VFIO group free slot found\n");
 		return -1;
 	}
@@ -123,8 +124,8 @@ vfio_get_group_fd(int iommu_group_no)
 			/* noiommu group found */
 		}
 
-		vfio_cfg.vfio_groups[group_idx].group_no = iommu_group_no;
-		vfio_cfg.vfio_groups[group_idx].fd = vfio_group_fd;
+		cur_grp->group_no = iommu_group_no;
+		cur_grp->fd = vfio_group_fd;
 		vfio_cfg.vfio_active_groups++;
 		return vfio_group_fd;
 	}
@@ -157,9 +158,12 @@ vfio_get_group_fd(int iommu_group_no)
 			return 0;
 		case SOCKET_OK:
 			vfio_group_fd = vfio_mp_sync_receive_fd(socket_fd);
-			/* if we got the fd, return it */
+			/* if we got the fd, store it and return it */
 			if (vfio_group_fd > 0) {
 				close(socket_fd);
+				cur_grp->group_no = iommu_group_no;
+				cur_grp->fd = vfio_group_fd;
+				vfio_cfg.vfio_active_groups++;
 				return vfio_group_fd;
 			}
 			/* fall-through on error */
@@ -172,6 +176,55 @@ vfio_get_group_fd(int iommu_group_no)
 	return -1;
 }
 
+
+static int
+get_vfio_group_idx(int vfio_group_fd)
+{
+	int i;
+	for (i = 0; i < VFIO_MAX_GROUPS; i++)
+		if (vfio_cfg.vfio_groups[i].fd == vfio_group_fd)
+			return i;
+	return -1;
+}
+
+static void
+vfio_group_device_get(int vfio_group_fd)
+{
+	int i;
+
+	i = get_vfio_group_idx(vfio_group_fd);
+	if (i < 0 || i > (VFIO_MAX_GROUPS - 1))
+		RTE_LOG(ERR, EAL, "  wrong vfio_group index (%d)\n", i);
+	else
+		vfio_cfg.vfio_groups[i].devices++;
+}
+
+static void
+vfio_group_device_put(int vfio_group_fd)
+{
+	int i;
+
+	i = get_vfio_group_idx(vfio_group_fd);
+	if (i < 0 || i > (VFIO_MAX_GROUPS - 1))
+		RTE_LOG(ERR, EAL, "  wrong vfio_group index (%d)\n", i);
+	else
+		vfio_cfg.vfio_groups[i].devices--;
+}
+
+static int
+vfio_group_device_count(int vfio_group_fd)
+{
+	int i;
+
+	i = get_vfio_group_idx(vfio_group_fd);
+	if (i < 0 || i > (VFIO_MAX_GROUPS - 1)) {
+		RTE_LOG(ERR, EAL, "  wrong vfio_group index (%d)\n", i);
+		return -1;
+	}
+
+	return vfio_cfg.vfio_groups[i].devices;
+}
+
 int
 clear_group(int vfio_group_fd)
 {
@@ -180,14 +233,14 @@ clear_group(int vfio_group_fd)
 
 	if (internal_config.process_type == RTE_PROC_PRIMARY) {
 
-		for (i = 0; i < VFIO_MAX_GROUPS; i++)
-			if (vfio_cfg.vfio_groups[i].fd == vfio_group_fd) {
-				vfio_cfg.vfio_groups[i].group_no = -1;
-				vfio_cfg.vfio_groups[i].fd = -1;
-				vfio_cfg.vfio_active_groups--;
-				return 0;
-			}
-		return -1;
+		i = get_vfio_group_idx(vfio_group_fd);
+		if (i < 0)
+			return -1;
+		vfio_cfg.vfio_groups[i].group_no = -1;
+		vfio_cfg.vfio_groups[i].fd = -1;
+		vfio_cfg.vfio_groups[i].devices = 0;
+		vfio_cfg.vfio_active_groups--;
+		return 0;
 	}
 
 	/* This is just for SECONDARY processes */
@@ -231,7 +284,7 @@ clear_group(int vfio_group_fd)
 }
 
 int
-vfio_setup_device(const char *sysfs_base, const char *dev_addr,
+rte_vfio_setup_device(const char *sysfs_base, const char *dev_addr,
 		int *vfio_dev_fd, struct vfio_device_info *device_info)
 {
 	struct vfio_group_status group_status = {
@@ -298,33 +351,37 @@ vfio_setup_device(const char *sysfs_base, const char *dev_addr,
 			clear_group(vfio_group_fd);
 			return -1;
 		}
-	}
 
-	/*
-	 * pick an IOMMU type and set up DMA mappings for container
-	 *
-	 * needs to be done only once, only when first group is assigned to
-	 * a container and only in primary process. Note this can happen several
-	 * times with the hotplug functionality.
-	 */
-	if (internal_config.process_type == RTE_PROC_PRIMARY &&
-			vfio_cfg.vfio_active_groups == 1) {
-		/* select an IOMMU type which we will be using */
-		const struct vfio_iommu_type *t =
+		/*
+		 * pick an IOMMU type and set up DMA mappings for container
+		 *
+		 * needs to be done only once, only when first group is
+		 * assigned to a container and only in primary process.
+		 * Note this can happen several times with the hotplug
+		 * functionality.
+		 */
+		if (internal_config.process_type == RTE_PROC_PRIMARY &&
+				vfio_cfg.vfio_active_groups == 1) {
+			/* select an IOMMU type which we will be using */
+			const struct vfio_iommu_type *t =
 				vfio_set_iommu_type(vfio_cfg.vfio_container_fd);
-		if (!t) {
-			RTE_LOG(ERR, EAL, "  %s failed to select IOMMU type\n", dev_addr);
-			close(vfio_group_fd);
-			clear_group(vfio_group_fd);
-			return -1;
-		}
-		ret = t->dma_map_func(vfio_cfg.vfio_container_fd);
-		if (ret) {
-			RTE_LOG(ERR, EAL, "  %s DMA remapping failed, "
-					"error %i (%s)\n", dev_addr, errno, strerror(errno));
-			close(vfio_group_fd);
-			clear_group(vfio_group_fd);
-			return -1;
+			if (!t) {
+				RTE_LOG(ERR, EAL,
+					"  %s failed to select IOMMU type\n",
+					dev_addr);
+				close(vfio_group_fd);
+				clear_group(vfio_group_fd);
+				return -1;
+			}
+			ret = t->dma_map_func(vfio_cfg.vfio_container_fd);
+			if (ret) {
+				RTE_LOG(ERR, EAL,
+					"  %s DMA remapping failed, error %i (%s)\n",
+					dev_addr, errno, strerror(errno));
+				close(vfio_group_fd);
+				clear_group(vfio_group_fd);
+				return -1;
+			}
 		}
 	}
 
@@ -353,12 +410,13 @@ vfio_setup_device(const char *sysfs_base, const char *dev_addr,
 		clear_group(vfio_group_fd);
 		return -1;
 	}
+	vfio_group_device_get(vfio_group_fd);
 
 	return 0;
 }
 
 int
-vfio_release_device(const char *sysfs_base, const char *dev_addr,
+rte_vfio_release_device(const char *sysfs_base, const char *dev_addr,
 		    int vfio_dev_fd)
 {
 	struct vfio_group_status group_status = {
@@ -390,23 +448,37 @@ vfio_release_device(const char *sysfs_base, const char *dev_addr,
 	 * code will unset the container and the IOMMU mappings.
 	 */
 
-	if (close(vfio_group_fd) < 0)
-		RTE_LOG(INFO, EAL, "Error when closing vfio_group_fd for %s\n",
-				   dev_addr);
-
-	if (close(vfio_dev_fd) < 0)
+	/* Closing a device */
+	if (close(vfio_dev_fd) < 0) {
 		RTE_LOG(INFO, EAL, "Error when closing vfio_dev_fd for %s\n",
 				   dev_addr);
+		return -1;
+	}
 
-	if (clear_group(vfio_group_fd) < 0)
-		RTE_LOG(INFO, EAL, "Error when clearing group for %s\n",
-				   dev_addr);
+	/* An VFIO group can have several devices attached. Just when there is
+	 * no devices remaining should the group be closed.
+	 */
+	vfio_group_device_put(vfio_group_fd);
+	if (!vfio_group_device_count(vfio_group_fd)) {
+
+		if (close(vfio_group_fd) < 0) {
+			RTE_LOG(INFO, EAL, "Error when closing vfio_group_fd for %s\n",
+				dev_addr);
+			return -1;
+		}
+
+		if (clear_group(vfio_group_fd) < 0) {
+			RTE_LOG(INFO, EAL, "Error when clearing group for %s\n",
+					   dev_addr);
+			return -1;
+		}
+	}
 
 	return 0;
 }
 
 int
-vfio_enable(const char *modname)
+rte_vfio_enable(const char *modname)
 {
 	/* initialize group list */
 	int i;
@@ -415,12 +487,13 @@ vfio_enable(const char *modname)
 	for (i = 0; i < VFIO_MAX_GROUPS; i++) {
 		vfio_cfg.vfio_groups[i].fd = -1;
 		vfio_cfg.vfio_groups[i].group_no = -1;
+		vfio_cfg.vfio_groups[i].devices = 0;
 	}
 
 	/* inform the user that we are probing for VFIO */
 	RTE_LOG(INFO, EAL, "Probing VFIO support...\n");
 
-	/* check if vfio-pci module is loaded */
+	/* check if vfio module is loaded */
 	vfio_available = rte_eal_check_module(modname);
 
 	/* return error directly */
@@ -450,7 +523,7 @@ vfio_enable(const char *modname)
 }
 
 int
-vfio_is_enabled(const char *modname)
+rte_vfio_is_enabled(const char *modname)
 {
 	const int mod_available = rte_eal_check_module(modname);
 	return vfio_cfg.vfio_enabled && mod_available;
@@ -637,7 +710,10 @@ vfio_type1_dma_map(int vfio_container_fd)
 		dma_map.argsz = sizeof(struct vfio_iommu_type1_dma_map);
 		dma_map.vaddr = ms[i].addr_64;
 		dma_map.size = ms[i].len;
-		dma_map.iova = ms[i].phys_addr;
+		if (rte_eal_iova_mode() == RTE_IOVA_VA)
+			dma_map.iova = dma_map.vaddr;
+		else
+			dma_map.iova = ms[i].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);
@@ -690,10 +766,19 @@ vfio_spapr_dma_map(int vfio_container_fd)
 		return -1;
 	}
 
-	/* calculate window size based on number of hugepages configured */
-	create.window_size = rte_eal_get_physmem_size();
+	/* create DMA window from 0 to max(phys_addr + len) */
+	for (i = 0; i < RTE_MAX_MEMSEG; i++) {
+		if (ms[i].addr == NULL)
+			break;
+
+		create.window_size = RTE_MAX(create.window_size,
+				ms[i].iova + ms[i].len);
+	}
+
+	/* sPAPR requires window size to be a power of 2 */
+	create.window_size = rte_align64pow2(create.window_size);
 	create.page_shift = __builtin_ctzll(ms->hugepage_sz);
-	create.levels = 2;
+	create.levels = 1;
 
 	ret = ioctl(vfio_container_fd, VFIO_IOMMU_SPAPR_TCE_CREATE, &create);
 	if (ret) {
@@ -702,6 +787,11 @@ vfio_spapr_dma_map(int vfio_container_fd)
 		return -1;
 	}
 
+	if (create.start_addr != 0) {
+		RTE_LOG(ERR, EAL, "  DMA window start address != 0\n");
+		return -1;
+	}
+
 	/* map all DPDK segments for DMA. use 1:1 PA to IOVA mapping */
 	for (i = 0; i < RTE_MAX_MEMSEG; i++) {
 		struct vfio_iommu_type1_dma_map dma_map;
@@ -723,7 +813,10 @@ vfio_spapr_dma_map(int vfio_container_fd)
 		dma_map.argsz = sizeof(struct vfio_iommu_type1_dma_map);
 		dma_map.vaddr = ms[i].addr_64;
 		dma_map.size = ms[i].len;
-		dma_map.iova = ms[i].phys_addr;
+		if (rte_eal_iova_mode() == RTE_IOVA_VA)
+			dma_map.iova = dma_map.vaddr;
+		else
+			dma_map.iova = ms[i].iova;
 		dma_map.flags = VFIO_DMA_MAP_FLAG_READ |
 				 VFIO_DMA_MAP_FLAG_WRITE;
 
@@ -747,4 +840,23 @@ vfio_noiommu_dma_map(int __rte_unused vfio_container_fd)
 	return 0;
 }
 
+int
+rte_vfio_noiommu_is_enabled(void)
+{
+	int fd, ret, cnt __rte_unused;
+	char c;
+
+	ret = -1;
+	fd = open(VFIO_NOIOMMU_MODE, O_RDONLY);
+	if (fd < 0)
+		return -1;
+
+	cnt = read(fd, &c, 1);
+	if (c == 'Y')
+		ret = 1;
+
+	close(fd);
+	return ret;
+}
+
 #endif