Support running DPDK without hugetlbfs mountpoint

index 019f84c18..2c8b2c218 100644
@@ -434,39 +434,52 @@ rte_fbarray_init(struct rte_fbarray *arr, const char *name, unsigned int len,
 	if (data == NULL)
 		goto fail;
 
-	eal_get_fbarray_path(path, sizeof(path), name);
+	if (internal_config.no_shconf) {
+		/* remap virtual area as writable */
+		void *new_data = mmap(data, mmap_len, PROT_READ | PROT_WRITE,
+				MAP_FIXED | MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+		if (new_data == MAP_FAILED) {
+			RTE_LOG(DEBUG, EAL, "%s(): couldn't remap anonymous memory: %s\n",
+					__func__, strerror(errno));
+			goto fail;
+		}
+	} else {
+		eal_get_fbarray_path(path, sizeof(path), name);
 
-	/*
-	 * Each fbarray is unique to process namespace, i.e. the filename
-	 * depends on process prefix. Try to take out a lock and see if we
-	 * succeed. If we don't, someone else is using it already.
-	 */
-	fd = open(path, O_CREAT | O_RDWR, 0600);
-	if (fd < 0) {
-		RTE_LOG(DEBUG, EAL, "%s(): couldn't open %s: %s\n", __func__,
-				path, strerror(errno));
-		rte_errno = errno;
-		goto fail;
-	} else if (flock(fd, LOCK_EX | LOCK_NB)) {
-		RTE_LOG(DEBUG, EAL, "%s(): couldn't lock %s: %s\n", __func__,
-				path, strerror(errno));
-		rte_errno = EBUSY;
-		goto fail;
-	}
+		/*
+		 * Each fbarray is unique to process namespace, i.e. the
+		 * filename depends on process prefix. Try to take out a lock
+		 * and see if we succeed. If we don't, someone else is using it
+		 * already.
+		 */
+		fd = open(path, O_CREAT | O_RDWR, 0600);
+		if (fd < 0) {
+			RTE_LOG(DEBUG, EAL, "%s(): couldn't open %s: %s\n",
+					__func__, path, strerror(errno));
+			rte_errno = errno;
+			goto fail;
+		} else if (flock(fd, LOCK_EX | LOCK_NB)) {
+			RTE_LOG(DEBUG, EAL, "%s(): couldn't lock %s: %s\n",
+					__func__, path, strerror(errno));
+			rte_errno = EBUSY;
+			goto fail;
+		}
 
-	/* take out a non-exclusive lock, so that other processes could still
-	 * attach to it, but no other process could reinitialize it.
-	 */
-	if (flock(fd, LOCK_SH | LOCK_NB)) {
-		rte_errno = errno;
-		goto fail;
-	}
+		/* take out a non-exclusive lock, so that other processes could
+		 * still attach to it, but no other process could reinitialize
+		 * it.
+		 */
+		if (flock(fd, LOCK_SH | LOCK_NB)) {
+			rte_errno = errno;
+			goto fail;
+		}
 
-	if (resize_and_map(fd, data, mmap_len))
-		goto fail;
+		if (resize_and_map(fd, data, mmap_len))
+			goto fail;
 
-	/* we've mmap'ed the file, we can now close the fd */
-	close(fd);
+		/* we've mmap'ed the file, we can now close the fd */
+		close(fd);
+	}
 
 	/* initialize the data */
 	memset(data, 0, mmap_len);

index 707d8ab30..31b5394cc 100644
@@ -626,6 +626,14 @@ rte_mp_channel_init(void)
 	int dir_fd;
 	pthread_t mp_handle_tid, async_reply_handle_tid;
 
+	/* in no shared files mode, we do not have secondary processes support,
+	 * so no need to initialize IPC.
+	 */
+	if (internal_config.no_shconf) {
+		RTE_LOG(DEBUG, EAL, "No shared files mode enabled, IPC will be disabled\n");
+		return 0;
+	}
+
 	/* create filter path */
 	create_socket_path("*", path, sizeof(path));
 	strlcpy(mp_filter, basename(path), sizeof(mp_filter));

@@ -988,6 +996,12 @@ rte_mp_request_sync(struct rte_mp_msg *req, struct rte_mp_reply *reply,
 
 	if (check_input(req) == false)
 		return -1;
+
+	if (internal_config.no_shconf) {
+		RTE_LOG(DEBUG, EAL, "No shared files mode enabled, IPC is disabled\n");
+		return 0;
+	}
+
 	if (gettimeofday(&now, NULL) < 0) {
 		RTE_LOG(ERR, EAL, "Faile to get current time\n");
 		rte_errno = errno;

@@ -1072,6 +1086,12 @@ rte_mp_request_async(struct rte_mp_msg *req, const struct timespec *ts,
 
 	if (check_input(req) == false)
 		return -1;
+
+	if (internal_config.no_shconf) {
+		RTE_LOG(DEBUG, EAL, "No shared files mode enabled, IPC is disabled\n");
+		return 0;
+	}
+
 	if (gettimeofday(&now, NULL) < 0) {
 		RTE_LOG(ERR, EAL, "Faile to get current time\n");
 		rte_errno = errno;

@@ -1213,5 +1233,10 @@ rte_mp_reply(struct rte_mp_msg *msg, const char *peer)
 		return -1;
 	}
 
+	if (internal_config.no_shconf) {
+		RTE_LOG(DEBUG, EAL, "No shared files mode enabled, IPC is disabled\n");
+		return 0;
+	}
+
 	return mp_send(msg, peer, MP_REP);
 }

index 836feb672..1e8f5df23 100644
@@ -101,6 +101,10 @@ eal_hugepage_info_init(void)
 	hpi->num_pages[0] = num_buffers;
 	hpi->lock_descriptor = fd;
 
+	/* for no shared files mode, do not create shared memory config */
+	if (internal_config.no_shconf)
+		return 0;
+
 	tmp_hpi = create_shared_memory(eal_hugepage_info_path(),
 			sizeof(internal_config.hugepage_info));
 	if (tmp_hpi == NULL ) {

index 7eca711ba..7f8e2fd9c 100644
@@ -446,6 +446,10 @@ eal_hugepage_info_init(void)
 	if (hugepage_info_init() < 0)
 		return -1;
 
+	/* for no shared files mode, we're done */
+	if (internal_config.no_shconf)
+		return 0;
+
 	hpi = &internal_config.hugepage_info[0];
 
 	tmp_hpi = create_shared_memory(eal_hugepage_info_path(),

index c917de1c2..cb784e1c3 100644
@@ -521,7 +521,18 @@ static void *
 create_shared_memory(const char *filename, const size_t mem_size)
 {
 	void *retval;
-	int fd = open(filename, O_CREAT | O_RDWR, 0666);
+	int fd;
+
+	/* if no shared files mode is used, create anonymous memory instead */
+	if (internal_config.no_shconf) {
+		retval = mmap(NULL, mem_size, PROT_READ | PROT_WRITE,
+				MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+		if (retval == MAP_FAILED)
+			return NULL;
+		return retval;
+	}
+
+	fd = open(filename, O_CREAT | O_RDWR, 0666);
 	if (fd < 0)
 		return NULL;
 	if (ftruncate(fd, mem_size) < 0) {

index dc279542d..13b6f8ae1 100644
@@ -601,7 +601,8 @@ rte_eal_init(int argc, char **argv)
 	}
 
 	/* create runtime data directory */
-	if (eal_create_runtime_dir() < 0) {
+	if (internal_config.no_shconf == 0 &&
+			eal_create_runtime_dir() < 0) {
 		rte_eal_init_alert("Cannot create runtime directory\n");
 		rte_errno = EACCES;
 		return -1;

index 8655b8691..a8d291520 100644
@@ -818,7 +818,8 @@ rte_eal_init(int argc, char **argv)
 	}
 
 	/* create runtime data directory */
-	if (eal_create_runtime_dir() < 0) {
+	if (internal_config.no_shconf == 0 &&
+			eal_create_runtime_dir() < 0) {
 		rte_eal_init_alert("Cannot create runtime directory\n");
 		rte_errno = EACCES;
 		return -1;

index 8c11f98c9..f1b6d9744 100644
@@ -512,6 +512,13 @@ alloc_seg(struct rte_memseg *ms, void *addr, int socket_id,
 				__func__, strerror(errno));
 			goto resized;
 		}
+		if (internal_config.hugepage_unlink) {
+			if (unlink(path)) {
+				RTE_LOG(DEBUG, EAL, "%s(): unlink() failed: %s\n",
+					__func__, strerror(errno));
+				goto resized;
+			}
+		}
 	}
 
 	/*

@@ -592,7 +599,8 @@ alloc_seg(struct rte_memseg *ms, void *addr, int socket_id,
 		/* ignore failure, can't make it any worse */
 	} else {
 		/* only remove file if we can take out a write lock */
-		if (lock(fd, LOCK_EX) == 1)
+		if (internal_config.hugepage_unlink == 0 &&
+				lock(fd, LOCK_EX) == 1)
 			unlink(path);
 		close(fd);
 	}

@@ -617,6 +625,12 @@ free_seg(struct rte_memseg *ms, struct hugepage_info *hi,
 		return -1;
 	}
 
+	/* if we've already unlinked the page, nothing needs to be done */
+	if (internal_config.hugepage_unlink) {
+		memset(ms, 0, sizeof(*ms));
+		return 0;
+	}
+
 	/* if we are not in single file segments mode, we're going to unmap the
 	 * segment and thus drop the lock on original fd, but hugepage dir is
 	 * now locked so we can take out another one without races.

index ecebb2923..b175b1446 100644
@@ -66,6 +66,7 @@ eal_long_options[] = {
 	{OPT_NO_HUGE,           0, NULL, OPT_NO_HUGE_NUM          },
 	{OPT_NO_PCI,            0, NULL, OPT_NO_PCI_NUM           },
 	{OPT_NO_SHCONF,         0, NULL, OPT_NO_SHCONF_NUM        },
+	{OPT_IN_MEMORY,         0, NULL, OPT_IN_MEMORY_NUM        },
 	{OPT_PCI_BLACKLIST,     1, NULL, OPT_PCI_BLACKLIST_NUM    },
 	{OPT_PCI_WHITELIST,     1, NULL, OPT_PCI_WHITELIST_NUM    },
 	{OPT_PROC_TYPE,         1, NULL, OPT_PROC_TYPE_NUM        },

@@ -1165,6 +1166,13 @@ eal_parse_common_option(int opt, const char *optarg,
 		conf->no_shconf = 1;
 		break;
 
+	case OPT_IN_MEMORY_NUM:
+		conf->in_memory = 1;
+		/* in-memory is a superset of noshconf and huge-unlink */
+		conf->no_shconf = 1;
+		conf->hugepage_unlink = 1;
+		break;
+
 	case OPT_PROC_TYPE_NUM:
 		conf->process_type = eal_parse_proc_type(optarg);
 		break;

@@ -1316,12 +1324,19 @@ eal_check_common_options(struct internal_config *internal_cfg)
 			"be specified together with --"OPT_NO_HUGE"\n");
 		return -1;
 	}
-
-	if (internal_cfg->no_hugetlbfs && internal_cfg->hugepage_unlink) {
+	if (internal_cfg->no_hugetlbfs && internal_cfg->hugepage_unlink &&
+			!internal_cfg->in_memory) {
 		RTE_LOG(ERR, EAL, "Option --"OPT_HUGE_UNLINK" cannot "
 			"be specified together with --"OPT_NO_HUGE"\n");
 		return -1;
 	}
+	if (internal_cfg->single_file_segments &&
+			internal_cfg->hugepage_unlink) {
+		RTE_LOG(ERR, EAL, "Option --"OPT_SINGLE_FILE_SEGMENTS" is "
+			"not compatible with neither --"OPT_IN_MEMORY" nor "
+			"--"OPT_HUGE_UNLINK"\n");
+		return -1;
+	}
 
 	return 0;
 }

@@ -1370,6 +1385,8 @@ eal_common_usage(void)
 	       "                      Set specific log level\n"
 	       "  -v                  Display version information on startup\n"
 	       "  -h, --help          This help\n"
+	       "  --"OPT_IN_MEMORY"   Operate entirely in memory. This will \n"
+	       "                      disable secondary process support\n"
 	       "\nEAL options for DEBUG use only:\n"
 	       "  --"OPT_HUGE_UNLINK"       Unlink hugepage files after init\n"
 	       "  --"OPT_NO_HUGE"           Use malloc instead of hugetlbfs\n"

index c4cbf3acd..f90d94206 100644
@@ -41,6 +41,10 @@ struct internal_config {
 	volatile unsigned vmware_tsc_map; /**< true to use VMware TSC mapping
 										* instead of native TSC */
 	volatile unsigned no_shconf;      /**< true if there is no shared config */
+	volatile unsigned in_memory;
+	/**< true if DPDK should operate entirely in-memory and not create any
+	 * shared files or runtime data.
+	 */
 	volatile unsigned create_uio_dev; /**< true to create /dev/uioX devices */
 	volatile enum rte_proc_type_t process_type; /**< multi-process proc type */
 	/** true to try allocating memory on specific sockets */

index 211ae06ae..dcde4054e 100644
@@ -45,6 +45,8 @@ enum {
 	OPT_NO_PCI_NUM,
 #define OPT_NO_SHCONF         "no-shconf"
 	OPT_NO_SHCONF_NUM,
+#define OPT_IN_MEMORY         "in-memory"
+	OPT_IN_MEMORY_NUM,
 #define OPT_SOCKET_MEM        "socket-mem"
 	OPT_SOCKET_MEM_NUM,
 #define OPT_SYSLOG            "syslog"

index 7f8e2fd9c..3a7d4b222 100644
@@ -18,6 +18,8 @@
 #include <sys/queue.h>
 #include <sys/stat.h>
 
+#include <linux/mman.h> /* for hugetlb-related flags */
+
 #include <rte_memory.h>
 #include <rte_eal.h>
 #include <rte_launch.h>

@@ -313,11 +315,49 @@ compare_hpi(const void *a, const void *b)
 	return hpi_b->hugepage_sz - hpi_a->hugepage_sz;
 }
 
+static void
+calc_num_pages(struct hugepage_info *hpi, struct dirent *dirent)
+{
+	uint64_t total_pages = 0;
+	unsigned int i;
+
+	/*
+	 * first, try to put all hugepages into relevant sockets, but
+	 * if first attempts fails, fall back to collecting all pages
+	 * in one socket and sorting them later
+	 */
+	total_pages = 0;
+	/* we also don't want to do this for legacy init */
+	if (!internal_config.legacy_mem)
+		for (i = 0; i < rte_socket_count(); i++) {
+			int socket = rte_socket_id_by_idx(i);
+			unsigned int num_pages =
+					get_num_hugepages_on_node(
+						dirent->d_name, socket);
+			hpi->num_pages[socket] = num_pages;
+			total_pages += num_pages;
+		}
+	/*
+	 * we failed to sort memory from the get go, so fall
+	 * back to old way
+	 */
+	if (total_pages == 0) {
+		hpi->num_pages[0] = get_num_hugepages(dirent->d_name);
+
+#ifndef RTE_ARCH_64
+		/* for 32-bit systems, limit number of hugepages to
+		 * 1GB per page size */
+		hpi->num_pages[0] = RTE_MIN(hpi->num_pages[0],
+				RTE_PGSIZE_1G / hpi->hugepage_sz);
+#endif
+	}
+}
+
 static int
 hugepage_info_init(void)
 {	const char dirent_start_text[] = "hugepages-";
 	const size_t dirent_start_len = sizeof(dirent_start_text) - 1;
-	unsigned int i, total_pages, num_sizes = 0;
+	unsigned int i, num_sizes = 0;
 	DIR *dir;
 	struct dirent *dirent;
 

@@ -355,6 +395,22 @@ hugepage_info_init(void)
 					"%" PRIu64 " reserved, but no mounted "
 					"hugetlbfs found for that size\n",
 					num_pages, hpi->hugepage_sz);
+			/* if we have kernel support for reserving hugepages
+			 * through mmap, and we're in in-memory mode, treat this
+			 * page size as valid. we cannot be in legacy mode at
+			 * this point because we've checked this earlier in the
+			 * init process.
+			 */
+#ifdef MAP_HUGE_SHIFT
+			if (internal_config.in_memory) {
+				RTE_LOG(DEBUG, EAL, "In-memory mode enabled, "
+					"hugepages of size %" PRIu64 " bytes "
+					"will be allocated anonymously\n",
+					hpi->hugepage_sz);
+				calc_num_pages(hpi, dirent);
+				num_sizes++;
+			}
+#endif
 			continue;
 		}
 

@@ -371,35 +427,7 @@ hugepage_info_init(void)
 		if (clear_hugedir(hpi->hugedir) == -1)
 			break;
 
-		/*
-		 * first, try to put all hugepages into relevant sockets, but
-		 * if first attempts fails, fall back to collecting all pages
-		 * in one socket and sorting them later
-		 */
-		total_pages = 0;
-		/* we also don't want to do this for legacy init */
-		if (!internal_config.legacy_mem)
-			for (i = 0; i < rte_socket_count(); i++) {
-				int socket = rte_socket_id_by_idx(i);
-				unsigned int num_pages =
-						get_num_hugepages_on_node(
-							dirent->d_name, socket);
-				hpi->num_pages[socket] = num_pages;
-				total_pages += num_pages;
-			}
-		/*
-		 * we failed to sort memory from the get go, so fall
-		 * back to old way
-		 */
-		if (total_pages == 0)
-			hpi->num_pages[0] = get_num_hugepages(dirent->d_name);
-
-#ifndef RTE_ARCH_64
-		/* for 32-bit systems, limit number of hugepages to
-		 * 1GB per page size */
-		hpi->num_pages[0] = RTE_MIN(hpi->num_pages[0],
-					    RTE_PGSIZE_1G / hpi->hugepage_sz);
-#endif
+		calc_num_pages(hpi, dirent);
 
 		num_sizes++;
 	}

@@ -423,8 +451,7 @@ hugepage_info_init(void)
 
 		for (j = 0; j < RTE_MAX_NUMA_NODES; j++)
 			num_pages += hpi->num_pages[j];
-		if (strnlen(hpi->hugedir, sizeof(hpi->hugedir)) != 0 &&
-				num_pages > 0)
+		if (num_pages > 0)
 			return 0;
 	}
 

197 lines not on this page · raw message

index cb784e1c3..a98d8c036 100644
@@ -1060,8 +1060,7 @@ get_socket_mem_size(int socket)
 
 	for (i = 0; i < internal_config.num_hugepage_sizes; i++){
 		struct hugepage_info *hpi = &internal_config.hugepage_info[i];
-		if (strnlen(hpi->hugedir, sizeof(hpi->hugedir)) != 0)
-			size += hpi->hugepage_sz * hpi->num_pages[socket];
+		size += hpi->hugepage_sz * hpi->num_pages[socket];
 	}
 
 	return size;

index 977174c4f..43caf3ced 100644
@@ -705,39 +705,52 @@ rte_fbarray_init(struct rte_fbarray *arr, const char *name, unsigned int len,
 	if (data == NULL)
 		goto fail;
 
-	eal_get_fbarray_path(path, sizeof(path), name);
+	if (internal_config.no_shconf) {
+		/* remap virtual area as writable */
+		void *new_data = mmap(data, mmap_len, PROT_READ | PROT_WRITE,
+				MAP_FIXED | MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+		if (new_data == MAP_FAILED) {
+			RTE_LOG(DEBUG, EAL, "%s(): couldn't remap anonymous memory: %s\n",
+					__func__, strerror(errno));
+			goto fail;
+		}
+	} else {
+		eal_get_fbarray_path(path, sizeof(path), name);
 
-	/*
-	 * Each fbarray is unique to process namespace, i.e. the filename
-	 * depends on process prefix. Try to take out a lock and see if we
-	 * succeed. If we don't, someone else is using it already.
-	 */
-	fd = open(path, O_CREAT | O_RDWR, 0600);
-	if (fd < 0) {
-		RTE_LOG(DEBUG, EAL, "%s(): couldn't open %s: %s\n", __func__,
-				path, strerror(errno));
-		rte_errno = errno;
-		goto fail;
-	} else if (flock(fd, LOCK_EX | LOCK_NB)) {
-		RTE_LOG(DEBUG, EAL, "%s(): couldn't lock %s: %s\n", __func__,
-				path, strerror(errno));
-		rte_errno = EBUSY;
-		goto fail;
-	}
+		/*
+		 * Each fbarray is unique to process namespace, i.e. the
+		 * filename depends on process prefix. Try to take out a lock
+		 * and see if we succeed. If we don't, someone else is using it
+		 * already.
+		 */
+		fd = open(path, O_CREAT | O_RDWR, 0600);
+		if (fd < 0) {
+			RTE_LOG(DEBUG, EAL, "%s(): couldn't open %s: %s\n",
+					__func__, path, strerror(errno));
+			rte_errno = errno;
+			goto fail;
+		} else if (flock(fd, LOCK_EX | LOCK_NB)) {
+			RTE_LOG(DEBUG, EAL, "%s(): couldn't lock %s: %s\n",
+					__func__, path, strerror(errno));
+			rte_errno = EBUSY;
+			goto fail;
+		}
 
-	/* take out a non-exclusive lock, so that other processes could still
-	 * attach to it, but no other process could reinitialize it.
-	 */
-	if (flock(fd, LOCK_SH | LOCK_NB)) {
-		rte_errno = errno;
-		goto fail;
-	}
+		/* take out a non-exclusive lock, so that other processes could
+		 * still attach to it, but no other process could reinitialize
+		 * it.
+		 */
+		if (flock(fd, LOCK_SH | LOCK_NB)) {
+			rte_errno = errno;
+			goto fail;
+		}
 
-	if (resize_and_map(fd, data, mmap_len))
-		goto fail;
+		if (resize_and_map(fd, data, mmap_len))
+			goto fail;
 
-	/* we've mmap'ed the file, we can now close the fd */
-	close(fd);
+		/* we've mmap'ed the file, we can now close the fd */
+		close(fd);
+	}
 
 	/* initialize the data */
 	memset(data, 0, mmap_len);

index f010ef59e..c19b4b406 100644
@@ -626,6 +626,14 @@ rte_mp_channel_init(void)
 	int dir_fd;
 	pthread_t mp_handle_tid, async_reply_handle_tid;
 
+	/* in no shared files mode, we do not have secondary processes support,
+	 * so no need to initialize IPC.
+	 */
+	if (internal_config.no_shconf) {
+		RTE_LOG(DEBUG, EAL, "No shared files mode enabled, IPC will be disabled\n");
+		return 0;
+	}
+
 	/* create filter path */
 	create_socket_path("*", path, sizeof(path));
 	strlcpy(mp_filter, basename(path), sizeof(mp_filter));

@@ -988,6 +996,12 @@ rte_mp_request_sync(struct rte_mp_msg *req, struct rte_mp_reply *reply,
 
 	if (check_input(req) == false)
 		return -1;
+
+	if (internal_config.no_shconf) {
+		RTE_LOG(DEBUG, EAL, "No shared files mode enabled, IPC is disabled\n");
+		return 0;
+	}
+
 	if (gettimeofday(&now, NULL) < 0) {
 		RTE_LOG(ERR, EAL, "Faile to get current time\n");
 		rte_errno = errno;

@@ -1072,6 +1086,12 @@ rte_mp_request_async(struct rte_mp_msg *req, const struct timespec *ts,
 
 	if (check_input(req) == false)
 		return -1;
+
+	if (internal_config.no_shconf) {
+		RTE_LOG(DEBUG, EAL, "No shared files mode enabled, IPC is disabled\n");
+		return 0;
+	}
+
 	if (gettimeofday(&now, NULL) < 0) {
 		RTE_LOG(ERR, EAL, "Faile to get current time\n");
 		rte_errno = errno;

@@ -1213,5 +1233,10 @@ rte_mp_reply(struct rte_mp_msg *msg, const char *peer)
 		return -1;
 	}
 
+	if (internal_config.no_shconf) {
+		RTE_LOG(DEBUG, EAL, "No shared files mode enabled, IPC is disabled\n");
+		return 0;
+	}
+
 	return mp_send(msg, peer, MP_REP);
 }

index 836feb672..1e8f5df23 100644
@@ -101,6 +101,10 @@ eal_hugepage_info_init(void)
 	hpi->num_pages[0] = num_buffers;
 	hpi->lock_descriptor = fd;
 
+	/* for no shared files mode, do not create shared memory config */
+	if (internal_config.no_shconf)
+		return 0;
+
 	tmp_hpi = create_shared_memory(eal_hugepage_info_path(),
 			sizeof(internal_config.hugepage_info));
 	if (tmp_hpi == NULL ) {

index 7eca711ba..7f8e2fd9c 100644
@@ -446,6 +446,10 @@ eal_hugepage_info_init(void)
 	if (hugepage_info_init() < 0)
 		return -1;
 
+	/* for no shared files mode, we're done */
+	if (internal_config.no_shconf)
+		return 0;
+
 	hpi = &internal_config.hugepage_info[0];
 
 	tmp_hpi = create_shared_memory(eal_hugepage_info_path(),

index 5d3c8831b..ddfa8b133 100644
@@ -521,7 +521,18 @@ static void *
 create_shared_memory(const char *filename, const size_t mem_size)
 {
 	void *retval;
-	int fd = open(filename, O_CREAT | O_RDWR, 0666);
+	int fd;
+
+	/* if no shared files mode is used, create anonymous memory instead */
+	if (internal_config.no_shconf) {
+		retval = mmap(NULL, mem_size, PROT_READ | PROT_WRITE,
+				MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+		if (retval == MAP_FAILED)
+			return NULL;
+		return retval;
+	}
+
+	fd = open(filename, O_CREAT | O_RDWR, 0666);
 	if (fd < 0)
 		return NULL;
 	if (ftruncate(fd, mem_size) < 0) {

index dc279542d..13b6f8ae1 100644
@@ -601,7 +601,8 @@ rte_eal_init(int argc, char **argv)
 	}
 
 	/* create runtime data directory */
-	if (eal_create_runtime_dir() < 0) {
+	if (internal_config.no_shconf == 0 &&
+			eal_create_runtime_dir() < 0) {
 		rte_eal_init_alert("Cannot create runtime directory\n");
 		rte_errno = EACCES;
 		return -1;

index ec7cea55d..191960caa 100644
@@ -832,7 +832,8 @@ rte_eal_init(int argc, char **argv)
 	}
 
 	/* create runtime data directory */
-	if (eal_create_runtime_dir() < 0) {
+	if (internal_config.no_shconf == 0 &&
+			eal_create_runtime_dir() < 0) {
 		rte_eal_init_alert("Cannot create runtime directory\n");
 		rte_errno = EACCES;
 		return -1;

index 45ea01a8b..df5d53648 100644
@@ -1332,6 +1332,12 @@ eal_check_common_options(struct internal_config *internal_cfg)
 			" is only supported in non-legacy memory mode\n");
 		return -1;
 	}
+	if (internal_cfg->single_file_segments &&
+			internal_cfg->hugepage_unlink) {
+		RTE_LOG(ERR, EAL, "Option --"OPT_SINGLE_FILE_SEGMENTS" is "
+			"not compatible with --"OPT_HUGE_UNLINK"\n");
+		return -1;
+	}
 
 	return 0;
 }

index 69604f823..d610923b8 100644
@@ -489,6 +489,13 @@ alloc_seg(struct rte_memseg *ms, void *addr, int socket_id,
 				__func__, strerror(errno));
 			goto resized;
 		}
+		if (internal_config.hugepage_unlink) {
+			if (unlink(path)) {
+				RTE_LOG(DEBUG, EAL, "%s(): unlink() failed: %s\n",
+					__func__, strerror(errno));
+				goto resized;
+			}
+		}
 	}
 
 	/*

@@ -587,7 +594,8 @@ alloc_seg(struct rte_memseg *ms, void *addr, int socket_id,
 		/* ignore failure, can't make it any worse */
 	} else {
 		/* only remove file if we can take out a write lock */
-		if (lock(fd, LOCK_EX) == 1)
+		if (internal_config.hugepage_unlink == 0 &&
+				lock(fd, LOCK_EX) == 1)
 			unlink(path);
 		close(fd);
 	}

@@ -612,6 +620,12 @@ free_seg(struct rte_memseg *ms, struct hugepage_info *hi,
 		return -1;
 	}
 
+	/* if we've already unlinked the page, nothing needs to be done */
+	if (internal_config.hugepage_unlink) {
+		memset(ms, 0, sizeof(*ms));
+		return 0;
+	}
+
 	/* if we are not in single file segments mode, we're going to unmap the
 	 * segment and thus drop the lock on original fd, but hugepage dir is
 	 * now locked so we can take out another one without races.

index df5d53648..f308b57c3 100644
@@ -66,6 +66,7 @@ eal_long_options[] = {
 	{OPT_NO_HUGE,           0, NULL, OPT_NO_HUGE_NUM          },
 	{OPT_NO_PCI,            0, NULL, OPT_NO_PCI_NUM           },
 	{OPT_NO_SHCONF,         0, NULL, OPT_NO_SHCONF_NUM        },
+	{OPT_IN_MEMORY,         0, NULL, OPT_IN_MEMORY_NUM        },
 	{OPT_PCI_BLACKLIST,     1, NULL, OPT_PCI_BLACKLIST_NUM    },
 	{OPT_PCI_WHITELIST,     1, NULL, OPT_PCI_WHITELIST_NUM    },
 	{OPT_PROC_TYPE,         1, NULL, OPT_PROC_TYPE_NUM        },

@@ -1170,6 +1171,13 @@ eal_parse_common_option(int opt, const char *optarg,
 		conf->no_shconf = 1;
 		break;
 
+	case OPT_IN_MEMORY_NUM:
+		conf->in_memory = 1;
+		/* in-memory is a superset of noshconf and huge-unlink */
+		conf->no_shconf = 1;
+		conf->hugepage_unlink = 1;
+		break;
+
 	case OPT_PROC_TYPE_NUM:
 		conf->process_type = eal_parse_proc_type(optarg);
 		break;

@@ -1321,8 +1329,8 @@ eal_check_common_options(struct internal_config *internal_cfg)
 			"be specified together with --"OPT_NO_HUGE"\n");
 		return -1;
 	}
-
-	if (internal_cfg->no_hugetlbfs && internal_cfg->hugepage_unlink) {
+	if (internal_cfg->no_hugetlbfs && internal_cfg->hugepage_unlink &&
+			!internal_cfg->in_memory) {
 		RTE_LOG(ERR, EAL, "Option --"OPT_HUGE_UNLINK" cannot "
 			"be specified together with --"OPT_NO_HUGE"\n");
 		return -1;

@@ -1330,12 +1338,12 @@ eal_check_common_options(struct internal_config *internal_cfg)
 	if (internal_config.force_socket_limits && internal_config.legacy_mem) {
 		RTE_LOG(ERR, EAL, "Option --"OPT_SOCKET_LIMIT
 			" is only supported in non-legacy memory mode\n");
-		return -1;
 	}
 	if (internal_cfg->single_file_segments &&
 			internal_cfg->hugepage_unlink) {
 		RTE_LOG(ERR, EAL, "Option --"OPT_SINGLE_FILE_SEGMENTS" is "
-			"not compatible with --"OPT_HUGE_UNLINK"\n");
+			"not compatible with neither --"OPT_IN_MEMORY" nor "
+			"--"OPT_HUGE_UNLINK"\n");
 		return -1;
 	}
 

@@ -1386,6 +1394,8 @@ eal_common_usage(void)
 	       "                      Set specific log level\n"
 	       "  -v                  Display version information on startup\n"
 	       "  -h, --help          This help\n"
+	       "  --"OPT_IN_MEMORY"   Operate entirely in memory. This will \n"
+	       "                      disable secondary process support\n"
 	       "\nEAL options for DEBUG use only:\n"
 	       "  --"OPT_HUGE_UNLINK"       Unlink hugepage files after init\n"
 	       "  --"OPT_NO_HUGE"           Use malloc instead of hugetlbfs\n"

index d66cd0313..00ee6e06e 100644
@@ -41,6 +41,10 @@ struct internal_config {
 	volatile unsigned vmware_tsc_map; /**< true to use VMware TSC mapping
 										* instead of native TSC */
 	volatile unsigned no_shconf;      /**< true if there is no shared config */
+	volatile unsigned in_memory;
+	/**< true if DPDK should operate entirely in-memory and not create any
+	 * shared files or runtime data.
+	 */
 	volatile unsigned create_uio_dev; /**< true to create /dev/uioX devices */
 	volatile enum rte_proc_type_t process_type; /**< multi-process proc type */
 	/** true to try allocating memory on specific sockets */

index 6d92f64a8..96e166787 100644
@@ -45,6 +45,8 @@ enum {
 	OPT_NO_PCI_NUM,
 #define OPT_NO_SHCONF         "no-shconf"
 	OPT_NO_SHCONF_NUM,
+#define OPT_IN_MEMORY         "in-memory"
+	OPT_IN_MEMORY_NUM,
 #define OPT_SOCKET_MEM        "socket-mem"
 	OPT_SOCKET_MEM_NUM,
 #define OPT_SOCKET_LIMIT        "socket-limit"

index 7f8e2fd9c..3a7d4b222 100644
@@ -18,6 +18,8 @@
 #include <sys/queue.h>
 #include <sys/stat.h>
 
+#include <linux/mman.h> /* for hugetlb-related flags */
+
 #include <rte_memory.h>
 #include <rte_eal.h>
 #include <rte_launch.h>

@@ -313,11 +315,49 @@ compare_hpi(const void *a, const void *b)
 	return hpi_b->hugepage_sz - hpi_a->hugepage_sz;
 }
 
+static void
+calc_num_pages(struct hugepage_info *hpi, struct dirent *dirent)
+{
+	uint64_t total_pages = 0;
+	unsigned int i;
+
+	/*
+	 * first, try to put all hugepages into relevant sockets, but
+	 * if first attempts fails, fall back to collecting all pages
+	 * in one socket and sorting them later
+	 */
+	total_pages = 0;
+	/* we also don't want to do this for legacy init */
+	if (!internal_config.legacy_mem)
+		for (i = 0; i < rte_socket_count(); i++) {
+			int socket = rte_socket_id_by_idx(i);
+			unsigned int num_pages =
+					get_num_hugepages_on_node(
+						dirent->d_name, socket);
+			hpi->num_pages[socket] = num_pages;
+			total_pages += num_pages;
+		}
+	/*
+	 * we failed to sort memory from the get go, so fall
+	 * back to old way
+	 */
+	if (total_pages == 0) {
+		hpi->num_pages[0] = get_num_hugepages(dirent->d_name);
+
+#ifndef RTE_ARCH_64
+		/* for 32-bit systems, limit number of hugepages to
+		 * 1GB per page size */
+		hpi->num_pages[0] = RTE_MIN(hpi->num_pages[0],
+				RTE_PGSIZE_1G / hpi->hugepage_sz);
+#endif
+	}
+}
+
 static int
 hugepage_info_init(void)
 {	const char dirent_start_text[] = "hugepages-";
 	const size_t dirent_start_len = sizeof(dirent_start_text) - 1;
-	unsigned int i, total_pages, num_sizes = 0;
+	unsigned int i, num_sizes = 0;
 	DIR *dir;
 	struct dirent *dirent;
 

@@ -355,6 +395,22 @@ hugepage_info_init(void)
 					"%" PRIu64 " reserved, but no mounted "
 					"hugetlbfs found for that size\n",
 					num_pages, hpi->hugepage_sz);
+			/* if we have kernel support for reserving hugepages
+			 * through mmap, and we're in in-memory mode, treat this
+			 * page size as valid. we cannot be in legacy mode at
+			 * this point because we've checked this earlier in the
+			 * init process.
+			 */
+#ifdef MAP_HUGE_SHIFT
+			if (internal_config.in_memory) {
+				RTE_LOG(DEBUG, EAL, "In-memory mode enabled, "
+					"hugepages of size %" PRIu64 " bytes "
+					"will be allocated anonymously\n",
+					hpi->hugepage_sz);
+				calc_num_pages(hpi, dirent);
+				num_sizes++;
+			}
+#endif
 			continue;
 		}
 

@@ -371,35 +427,7 @@ hugepage_info_init(void)
 		if (clear_hugedir(hpi->hugedir) == -1)
 			break;
 
-		/*
-		 * first, try to put all hugepages into relevant sockets, but
-		 * if first attempts fails, fall back to collecting all pages
-		 * in one socket and sorting them later
-		 */
-		total_pages = 0;
-		/* we also don't want to do this for legacy init */
-		if (!internal_config.legacy_mem)
-			for (i = 0; i < rte_socket_count(); i++) {
-				int socket = rte_socket_id_by_idx(i);
-				unsigned int num_pages =
-						get_num_hugepages_on_node(
-							dirent->d_name, socket);
-				hpi->num_pages[socket] = num_pages;
-				total_pages += num_pages;
-			}
-		/*
-		 * we failed to sort memory from the get go, so fall
-		 * back to old way
-		 */
-		if (total_pages == 0)
-			hpi->num_pages[0] = get_num_hugepages(dirent->d_name);
-
-#ifndef RTE_ARCH_64
-		/* for 32-bit systems, limit number of hugepages to
-		 * 1GB per page size */
-		hpi->num_pages[0] = RTE_MIN(hpi->num_pages[0],
-					    RTE_PGSIZE_1G / hpi->hugepage_sz);
-#endif
+		calc_num_pages(hpi, dirent);
 
 		num_sizes++;
 	}

@@ -423,8 +451,7 @@ hugepage_info_init(void)
 
 		for (j = 0; j < RTE_MAX_NUMA_NODES; j++)
 			num_pages += hpi->num_pages[j];
-		if (strnlen(hpi->hugedir, sizeof(hpi->hugedir)) != 0 &&
-				num_pages > 0)
+		if (num_pages > 0)
 			return 0;
 	}
 

199 lines not on this page · raw message

index ddfa8b133..dbf19499e 100644
@@ -1088,8 +1088,7 @@ get_socket_mem_size(int socket)
 
 	for (i = 0; i < internal_config.num_hugepage_sizes; i++){
 		struct hugepage_info *hpi = &internal_config.hugepage_info[i];
-		if (strnlen(hpi->hugedir, sizeof(hpi->hugedir)) != 0)
-			size += hpi->hugepage_sz * hpi->num_pages[socket];
+		size += hpi->hugepage_sz * hpi->num_pages[socket];
 	}
 
 	return size;

index 977174c4f..43caf3ced 100644
@@ -705,39 +705,52 @@ rte_fbarray_init(struct rte_fbarray *arr, const char *name, unsigned int len,
 	if (data == NULL)
 		goto fail;
 
-	eal_get_fbarray_path(path, sizeof(path), name);
+	if (internal_config.no_shconf) {
+		/* remap virtual area as writable */
+		void *new_data = mmap(data, mmap_len, PROT_READ | PROT_WRITE,
+				MAP_FIXED | MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+		if (new_data == MAP_FAILED) {
+			RTE_LOG(DEBUG, EAL, "%s(): couldn't remap anonymous memory: %s\n",
+					__func__, strerror(errno));
+			goto fail;
+		}
+	} else {
+		eal_get_fbarray_path(path, sizeof(path), name);
 
-	/*
-	 * Each fbarray is unique to process namespace, i.e. the filename
-	 * depends on process prefix. Try to take out a lock and see if we
-	 * succeed. If we don't, someone else is using it already.
-	 */
-	fd = open(path, O_CREAT | O_RDWR, 0600);
-	if (fd < 0) {
-		RTE_LOG(DEBUG, EAL, "%s(): couldn't open %s: %s\n", __func__,
-				path, strerror(errno));
-		rte_errno = errno;
-		goto fail;
-	} else if (flock(fd, LOCK_EX | LOCK_NB)) {
-		RTE_LOG(DEBUG, EAL, "%s(): couldn't lock %s: %s\n", __func__,
-				path, strerror(errno));
-		rte_errno = EBUSY;
-		goto fail;
-	}
+		/*
+		 * Each fbarray is unique to process namespace, i.e. the
+		 * filename depends on process prefix. Try to take out a lock
+		 * and see if we succeed. If we don't, someone else is using it
+		 * already.
+		 */
+		fd = open(path, O_CREAT | O_RDWR, 0600);
+		if (fd < 0) {
+			RTE_LOG(DEBUG, EAL, "%s(): couldn't open %s: %s\n",
+					__func__, path, strerror(errno));
+			rte_errno = errno;
+			goto fail;
+		} else if (flock(fd, LOCK_EX | LOCK_NB)) {
+			RTE_LOG(DEBUG, EAL, "%s(): couldn't lock %s: %s\n",
+					__func__, path, strerror(errno));
+			rte_errno = EBUSY;
+			goto fail;
+		}
 
-	/* take out a non-exclusive lock, so that other processes could still
-	 * attach to it, but no other process could reinitialize it.
-	 */
-	if (flock(fd, LOCK_SH | LOCK_NB)) {
-		rte_errno = errno;
-		goto fail;
-	}
+		/* take out a non-exclusive lock, so that other processes could
+		 * still attach to it, but no other process could reinitialize
+		 * it.
+		 */
+		if (flock(fd, LOCK_SH | LOCK_NB)) {
+			rte_errno = errno;
+			goto fail;
+		}
 
-	if (resize_and_map(fd, data, mmap_len))
-		goto fail;
+		if (resize_and_map(fd, data, mmap_len))
+			goto fail;
 
-	/* we've mmap'ed the file, we can now close the fd */
-	close(fd);
+		/* we've mmap'ed the file, we can now close the fd */
+		close(fd);
+	}
 
 	/* initialize the data */
 	memset(data, 0, mmap_len);

index f010ef59e..c19b4b406 100644
@@ -626,6 +626,14 @@ rte_mp_channel_init(void)
 	int dir_fd;
 	pthread_t mp_handle_tid, async_reply_handle_tid;
 
+	/* in no shared files mode, we do not have secondary processes support,
+	 * so no need to initialize IPC.
+	 */
+	if (internal_config.no_shconf) {
+		RTE_LOG(DEBUG, EAL, "No shared files mode enabled, IPC will be disabled\n");
+		return 0;
+	}
+
 	/* create filter path */
 	create_socket_path("*", path, sizeof(path));
 	strlcpy(mp_filter, basename(path), sizeof(mp_filter));

@@ -988,6 +996,12 @@ rte_mp_request_sync(struct rte_mp_msg *req, struct rte_mp_reply *reply,
 
 	if (check_input(req) == false)
 		return -1;
+
+	if (internal_config.no_shconf) {
+		RTE_LOG(DEBUG, EAL, "No shared files mode enabled, IPC is disabled\n");
+		return 0;
+	}
+
 	if (gettimeofday(&now, NULL) < 0) {
 		RTE_LOG(ERR, EAL, "Faile to get current time\n");
 		rte_errno = errno;

@@ -1072,6 +1086,12 @@ rte_mp_request_async(struct rte_mp_msg *req, const struct timespec *ts,
 
 	if (check_input(req) == false)
 		return -1;
+
+	if (internal_config.no_shconf) {
+		RTE_LOG(DEBUG, EAL, "No shared files mode enabled, IPC is disabled\n");
+		return 0;
+	}
+
 	if (gettimeofday(&now, NULL) < 0) {
 		RTE_LOG(ERR, EAL, "Faile to get current time\n");
 		rte_errno = errno;

@@ -1213,5 +1233,10 @@ rte_mp_reply(struct rte_mp_msg *msg, const char *peer)
 		return -1;
 	}
 
+	if (internal_config.no_shconf) {
+		RTE_LOG(DEBUG, EAL, "No shared files mode enabled, IPC is disabled\n");
+		return 0;
+	}
+
 	return mp_send(msg, peer, MP_REP);
 }

index 836feb672..1e8f5df23 100644
@@ -101,6 +101,10 @@ eal_hugepage_info_init(void)
 	hpi->num_pages[0] = num_buffers;
 	hpi->lock_descriptor = fd;
 
+	/* for no shared files mode, do not create shared memory config */
+	if (internal_config.no_shconf)
+		return 0;
+
 	tmp_hpi = create_shared_memory(eal_hugepage_info_path(),
 			sizeof(internal_config.hugepage_info));
 	if (tmp_hpi == NULL ) {

index 7eca711ba..7f8e2fd9c 100644
@@ -446,6 +446,10 @@ eal_hugepage_info_init(void)
 	if (hugepage_info_init() < 0)
 		return -1;
 
+	/* for no shared files mode, we're done */
+	if (internal_config.no_shconf)
+		return 0;
+
 	hpi = &internal_config.hugepage_info[0];
 
 	tmp_hpi = create_shared_memory(eal_hugepage_info_path(),

index 5d3c8831b..ddfa8b133 100644
@@ -521,7 +521,18 @@ static void *
 create_shared_memory(const char *filename, const size_t mem_size)
 {
 	void *retval;
-	int fd = open(filename, O_CREAT | O_RDWR, 0666);
+	int fd;
+
+	/* if no shared files mode is used, create anonymous memory instead */
+	if (internal_config.no_shconf) {
+		retval = mmap(NULL, mem_size, PROT_READ | PROT_WRITE,
+				MAP_PRIVATE | MAP_ANONYMOUS, -1, 0);
+		if (retval == MAP_FAILED)
+			return NULL;
+		return retval;
+	}
+
+	fd = open(filename, O_CREAT | O_RDWR, 0666);
 	if (fd < 0)
 		return NULL;
 	if (ftruncate(fd, mem_size) < 0) {

index dc279542d..13b6f8ae1 100644
@@ -601,7 +601,8 @@ rte_eal_init(int argc, char **argv)
 	}
 
 	/* create runtime data directory */
-	if (eal_create_runtime_dir() < 0) {
+	if (internal_config.no_shconf == 0 &&
+			eal_create_runtime_dir() < 0) {
 		rte_eal_init_alert("Cannot create runtime directory\n");
 		rte_errno = EACCES;
 		return -1;

index ec7cea55d..191960caa 100644
@@ -832,7 +832,8 @@ rte_eal_init(int argc, char **argv)
 	}
 
 	/* create runtime data directory */
-	if (eal_create_runtime_dir() < 0) {
+	if (internal_config.no_shconf == 0 &&
+			eal_create_runtime_dir() < 0) {
 		rte_eal_init_alert("Cannot create runtime directory\n");
 		rte_errno = EACCES;
 		return -1;

index 45ea01a8b..df5d53648 100644
@@ -1332,6 +1332,12 @@ eal_check_common_options(struct internal_config *internal_cfg)
 			" is only supported in non-legacy memory mode\n");
 		return -1;
 	}
+	if (internal_cfg->single_file_segments &&
+			internal_cfg->hugepage_unlink) {
+		RTE_LOG(ERR, EAL, "Option --"OPT_SINGLE_FILE_SEGMENTS" is "
+			"not compatible with --"OPT_HUGE_UNLINK"\n");
+		return -1;
+	}
 
 	return 0;
 }

index 69604f823..d610923b8 100644
@@ -489,6 +489,13 @@ alloc_seg(struct rte_memseg *ms, void *addr, int socket_id,
 				__func__, strerror(errno));
 			goto resized;
 		}
+		if (internal_config.hugepage_unlink) {
+			if (unlink(path)) {
+				RTE_LOG(DEBUG, EAL, "%s(): unlink() failed: %s\n",
+					__func__, strerror(errno));
+				goto resized;
+			}
+		}
 	}
 
 	/*

@@ -587,7 +594,8 @@ alloc_seg(struct rte_memseg *ms, void *addr, int socket_id,
 		/* ignore failure, can't make it any worse */
 	} else {
 		/* only remove file if we can take out a write lock */
-		if (lock(fd, LOCK_EX) == 1)
+		if (internal_config.hugepage_unlink == 0 &&
+				lock(fd, LOCK_EX) == 1)
 			unlink(path);
 		close(fd);
 	}

@@ -612,6 +620,12 @@ free_seg(struct rte_memseg *ms, struct hugepage_info *hi,
 		return -1;
 	}
 
+	/* if we've already unlinked the page, nothing needs to be done */
+	if (internal_config.hugepage_unlink) {
+		memset(ms, 0, sizeof(*ms));
+		return 0;
+	}
+
 	/* if we are not in single file segments mode, we're going to unmap the
 	 * segment and thus drop the lock on original fd, but hugepage dir is
 	 * now locked so we can take out another one without races.

index df5d53648..f308b57c3 100644
@@ -66,6 +66,7 @@ eal_long_options[] = {
 	{OPT_NO_HUGE,           0, NULL, OPT_NO_HUGE_NUM          },
 	{OPT_NO_PCI,            0, NULL, OPT_NO_PCI_NUM           },
 	{OPT_NO_SHCONF,         0, NULL, OPT_NO_SHCONF_NUM        },
+	{OPT_IN_MEMORY,         0, NULL, OPT_IN_MEMORY_NUM        },
 	{OPT_PCI_BLACKLIST,     1, NULL, OPT_PCI_BLACKLIST_NUM    },
 	{OPT_PCI_WHITELIST,     1, NULL, OPT_PCI_WHITELIST_NUM    },
 	{OPT_PROC_TYPE,         1, NULL, OPT_PROC_TYPE_NUM        },

@@ -1170,6 +1171,13 @@ eal_parse_common_option(int opt, const char *optarg,
 		conf->no_shconf = 1;
 		break;
 
+	case OPT_IN_MEMORY_NUM:
+		conf->in_memory = 1;
+		/* in-memory is a superset of noshconf and huge-unlink */
+		conf->no_shconf = 1;
+		conf->hugepage_unlink = 1;
+		break;
+
 	case OPT_PROC_TYPE_NUM:
 		conf->process_type = eal_parse_proc_type(optarg);
 		break;

@@ -1321,8 +1329,8 @@ eal_check_common_options(struct internal_config *internal_cfg)
 			"be specified together with --"OPT_NO_HUGE"\n");
 		return -1;
 	}
-
-	if (internal_cfg->no_hugetlbfs && internal_cfg->hugepage_unlink) {
+	if (internal_cfg->no_hugetlbfs && internal_cfg->hugepage_unlink &&
+			!internal_cfg->in_memory) {
 		RTE_LOG(ERR, EAL, "Option --"OPT_HUGE_UNLINK" cannot "
 			"be specified together with --"OPT_NO_HUGE"\n");
 		return -1;

@@ -1330,12 +1338,12 @@ eal_check_common_options(struct internal_config *internal_cfg)
 	if (internal_config.force_socket_limits && internal_config.legacy_mem) {
 		RTE_LOG(ERR, EAL, "Option --"OPT_SOCKET_LIMIT
 			" is only supported in non-legacy memory mode\n");
-		return -1;
 	}
 	if (internal_cfg->single_file_segments &&
 			internal_cfg->hugepage_unlink) {
 		RTE_LOG(ERR, EAL, "Option --"OPT_SINGLE_FILE_SEGMENTS" is "
-			"not compatible with --"OPT_HUGE_UNLINK"\n");
+			"not compatible with neither --"OPT_IN_MEMORY" nor "
+			"--"OPT_HUGE_UNLINK"\n");
 		return -1;
 	}
 

@@ -1386,6 +1394,8 @@ eal_common_usage(void)
 	       "                      Set specific log level\n"
 	       "  -v                  Display version information on startup\n"
 	       "  -h, --help          This help\n"
+	       "  --"OPT_IN_MEMORY"   Operate entirely in memory. This will \n"
+	       "                      disable secondary process support\n"
 	       "\nEAL options for DEBUG use only:\n"
 	       "  --"OPT_HUGE_UNLINK"       Unlink hugepage files after init\n"
 	       "  --"OPT_NO_HUGE"           Use malloc instead of hugetlbfs\n"

index d66cd0313..00ee6e06e 100644
@@ -41,6 +41,10 @@ struct internal_config {
 	volatile unsigned vmware_tsc_map; /**< true to use VMware TSC mapping
 										* instead of native TSC */
 	volatile unsigned no_shconf;      /**< true if there is no shared config */
+	volatile unsigned in_memory;
+	/**< true if DPDK should operate entirely in-memory and not create any
+	 * shared files or runtime data.
+	 */
 	volatile unsigned create_uio_dev; /**< true to create /dev/uioX devices */
 	volatile enum rte_proc_type_t process_type; /**< multi-process proc type */
 	/** true to try allocating memory on specific sockets */

index 6d92f64a8..96e166787 100644
@@ -45,6 +45,8 @@ enum {
 	OPT_NO_PCI_NUM,
 #define OPT_NO_SHCONF         "no-shconf"
 	OPT_NO_SHCONF_NUM,
+#define OPT_IN_MEMORY         "in-memory"
+	OPT_IN_MEMORY_NUM,
 #define OPT_SOCKET_MEM        "socket-mem"
 	OPT_SOCKET_MEM_NUM,
 #define OPT_SOCKET_LIMIT        "socket-limit"

index 7f8e2fd9c..3a7d4b222 100644
@@ -18,6 +18,8 @@
 #include <sys/queue.h>
 #include <sys/stat.h>
 
+#include <linux/mman.h> /* for hugetlb-related flags */
+
 #include <rte_memory.h>
 #include <rte_eal.h>
 #include <rte_launch.h>

@@ -313,11 +315,49 @@ compare_hpi(const void *a, const void *b)
 	return hpi_b->hugepage_sz - hpi_a->hugepage_sz;
 }
 
+static void
+calc_num_pages(struct hugepage_info *hpi, struct dirent *dirent)
+{
+	uint64_t total_pages = 0;
+	unsigned int i;
+
+	/*
+	 * first, try to put all hugepages into relevant sockets, but
+	 * if first attempts fails, fall back to collecting all pages
+	 * in one socket and sorting them later
+	 */
+	total_pages = 0;
+	/* we also don't want to do this for legacy init */
+	if (!internal_config.legacy_mem)
+		for (i = 0; i < rte_socket_count(); i++) {
+			int socket = rte_socket_id_by_idx(i);
+			unsigned int num_pages =
+					get_num_hugepages_on_node(
+						dirent->d_name, socket);
+			hpi->num_pages[socket] = num_pages;
+			total_pages += num_pages;
+		}
+	/*
+	 * we failed to sort memory from the get go, so fall
+	 * back to old way
+	 */
+	if (total_pages == 0) {
+		hpi->num_pages[0] = get_num_hugepages(dirent->d_name);
+
+#ifndef RTE_ARCH_64
+		/* for 32-bit systems, limit number of hugepages to
+		 * 1GB per page size */
+		hpi->num_pages[0] = RTE_MIN(hpi->num_pages[0],
+				RTE_PGSIZE_1G / hpi->hugepage_sz);
+#endif
+	}
+}
+
 static int
 hugepage_info_init(void)
 {	const char dirent_start_text[] = "hugepages-";
 	const size_t dirent_start_len = sizeof(dirent_start_text) - 1;
-	unsigned int i, total_pages, num_sizes = 0;
+	unsigned int i, num_sizes = 0;
 	DIR *dir;
 	struct dirent *dirent;
 

@@ -355,6 +395,22 @@ hugepage_info_init(void)
 					"%" PRIu64 " reserved, but no mounted "
 					"hugetlbfs found for that size\n",
 					num_pages, hpi->hugepage_sz);
+			/* if we have kernel support for reserving hugepages
+			 * through mmap, and we're in in-memory mode, treat this
+			 * page size as valid. we cannot be in legacy mode at
+			 * this point because we've checked this earlier in the
+			 * init process.
+			 */
+#ifdef MAP_HUGE_SHIFT
+			if (internal_config.in_memory) {
+				RTE_LOG(DEBUG, EAL, "In-memory mode enabled, "
+					"hugepages of size %" PRIu64 " bytes "
+					"will be allocated anonymously\n",
+					hpi->hugepage_sz);
+				calc_num_pages(hpi, dirent);
+				num_sizes++;
+			}
+#endif
 			continue;
 		}
 

@@ -371,35 +427,7 @@ hugepage_info_init(void)
 		if (clear_hugedir(hpi->hugedir) == -1)
 			break;
 
-		/*
-		 * first, try to put all hugepages into relevant sockets, but
-		 * if first attempts fails, fall back to collecting all pages
-		 * in one socket and sorting them later
-		 */
-		total_pages = 0;
-		/* we also don't want to do this for legacy init */
-		if (!internal_config.legacy_mem)
-			for (i = 0; i < rte_socket_count(); i++) {
-				int socket = rte_socket_id_by_idx(i);
-				unsigned int num_pages =
-						get_num_hugepages_on_node(
-							dirent->d_name, socket);
-				hpi->num_pages[socket] = num_pages;
-				total_pages += num_pages;
-			}
-		/*
-		 * we failed to sort memory from the get go, so fall
-		 * back to old way
-		 */
-		if (total_pages == 0)
-			hpi->num_pages[0] = get_num_hugepages(dirent->d_name);
-
-#ifndef RTE_ARCH_64
-		/* for 32-bit systems, limit number of hugepages to
-		 * 1GB per page size */
-		hpi->num_pages[0] = RTE_MIN(hpi->num_pages[0],
-					    RTE_PGSIZE_1G / hpi->hugepage_sz);
-#endif
+		calc_num_pages(hpi, dirent);
 
 		num_sizes++;
 	}

@@ -423,8 +451,7 @@ hugepage_info_init(void)
 
 		for (j = 0; j < RTE_MAX_NUMA_NODES; j++)
 			num_pages += hpi->num_pages[j];
-		if (strnlen(hpi->hugedir, sizeof(hpi->hugedir)) != 0 &&
-				num_pages > 0)
+		if (num_pages > 0)
 			return 0;
 	}
 

215 lines not on this page · raw message

index ddfa8b133..dbf19499e 100644
@@ -1088,8 +1088,7 @@ get_socket_mem_size(int socket)
 
 	for (i = 0; i < internal_config.num_hugepage_sizes; i++){
 		struct hugepage_info *hpi = &internal_config.hugepage_info[i];
-		if (strnlen(hpi->hugedir, sizeof(hpi->hugedir)) != 0)
-			size += hpi->hugepage_sz * hpi->num_pages[socket];
+		size += hpi->hugepage_sz * hpi->num_pages[socket];
 	}
 
 	return size;