/*-
 *   BSD LICENSE
 *
 *   Copyright(c) 2010-2016 Intel Corporation. All rights reserved.
 *   Copyright(c) 2012-2014 6WIND S.A.
 *   All rights reserved.
 *
 *   Redistribution and use in source and binary forms, with or without
 *   modification, are permitted provided that the following conditions
 *   are met:
 *
 *     * Redistributions of source code must retain the above copyright
 *       notice, this list of conditions and the following disclaimer.
 *     * Redistributions in binary form must reproduce the above copyright
 *       notice, this list of conditions and the following disclaimer in
 *       the documentation and/or other materials provided with the
 *       distribution.
 *     * Neither the name of Intel Corporation nor the names of its
 *       contributors may be used to endorse or promote products derived
 *       from this software without specific prior written permission.
 *
 *   THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
 *   "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
 *   LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
 *   A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
 *   OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
 *   SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
 *   LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
 *   DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
 *   THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
 *   (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
 *   OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 */

#include <stdio.h>
#include <stdlib.h>
#include <stdint.h>
#include <string.h>
#include <stdarg.h>
#include <unistd.h>
#include <pthread.h>
#include <syslog.h>
#include <getopt.h>
#include <sys/file.h>
#include <fcntl.h>
#include <stddef.h>
#include <errno.h>
#include <limits.h>
#include <errno.h>
#include <sys/mman.h>
#include <sys/queue.h>
#include <sys/stat.h>
#if defined(RTE_ARCH_X86)
#include <sys/io.h>
#endif
#include <sys/types.h>
#include <pwd.h>
#include <grp.h>

#include <rte_common.h>
#include <rte_debug.h>
#include <rte_memory.h>
#include <rte_memzone.h>
#include <rte_launch.h>
#include <rte_eal.h>
#include <rte_eal_memconfig.h>
#include <rte_per_lcore.h>
#include <rte_lcore.h>
#include <rte_log.h>
#include <rte_random.h>
#include <rte_cycles.h>
#include <rte_string_fns.h>
#include <rte_cpuflags.h>
#include <rte_interrupts.h>
#include <rte_pci.h>
#include <rte_dev.h>
#include <rte_devargs.h>
#include <rte_common.h>
#include <rte_version.h>
#include <rte_atomic.h>
#include <malloc_heap.h>

#include "eal_private.h"
#include "eal_thread.h"
#include "eal_internal_cfg.h"
#include "eal_filesystem.h"
#include "eal_hugepages.h"
#include "eal_options.h"
#include "eal_vfio.h"

#define MEMSIZE_IF_NO_HUGE_PAGE (64ULL * 1024ULL * 1024ULL)

#define SOCKET_MEM_STRLEN (RTE_MAX_NUMA_NODES * 10)

/* Allow the application to print its usage message too if set */
static rte_usage_hook_t	rte_application_usage_hook = NULL;

/* early configuration structure, when memory config is not mmapped */
static struct rte_mem_config early_mem_config;

/* define fd variable here, because file needs to be kept open for the
 * duration of the program, as we hold a write lock on it in the primary proc */
static int mem_cfg_fd = -1;

static struct flock wr_lock = {
		.l_type = F_WRLCK,
		.l_whence = SEEK_SET,
		.l_start = offsetof(struct rte_mem_config, memseg),
		.l_len = sizeof(early_mem_config.memseg),
};

/* Address of global and public configuration */
static struct rte_config rte_config = {
		.mem_config = &early_mem_config,
};

/* internal configuration (per-core) */
struct lcore_config lcore_config[RTE_MAX_LCORE];

/* internal configuration */
struct internal_config internal_config;

/* used by rte_rdtsc() */
int rte_cycles_vmware_tsc_map;

/* Return a pointer to the configuration structure */
struct rte_config *
rte_eal_get_configuration(void)
{
	return &rte_config;
}

/* parse a sysfs (or other) file containing one integer value */
int
eal_parse_sysfs_value(const char *filename, unsigned long *val)
{
	FILE *f;
	char buf[BUFSIZ];
	char *end = NULL;

	if ((f = fopen(filename, "r")) == NULL) {
		RTE_LOG(ERR, EAL, "%s(): cannot open sysfs value %s\n",
			__func__, filename);
		return -1;
	}

	if (fgets(buf, sizeof(buf), f) == NULL) {
		RTE_LOG(ERR, EAL, "%s(): cannot read sysfs value %s\n",
			__func__, filename);
		fclose(f);
		return -1;
	}
	*val = strtoul(buf, &end, 0);
	if ((buf[0] == '\0') || (end == NULL) || (*end != '\n')) {
		RTE_LOG(ERR, EAL, "%s(): cannot parse sysfs value %s\n",
				__func__, filename);
		fclose(f);
		return -1;
	}
	fclose(f);
	return 0;
}


/* create memory configuration in shared/mmap memory. Take out
 * a write lock on the memsegs, so we can auto-detect primary/secondary.
 * This means we never close the file while running (auto-close on exit).
 * We also don't lock the whole file, so that in future we can use read-locks
 * on other parts, e.g. memzones, to detect if there are running secondary
 * processes. */
static void
rte_eal_config_create(void)
{
	void *rte_mem_cfg_addr;
	int retval;

	const char *pathname = eal_runtime_config_path();

	if (internal_config.no_shconf)
		return;

	/* map the config before hugepage address so that we don't waste a page */
	if (internal_config.base_virtaddr != 0)
		rte_mem_cfg_addr = (void *)
			RTE_ALIGN_FLOOR(internal_config.base_virtaddr -
			sizeof(struct rte_mem_config), sysconf(_SC_PAGE_SIZE));
	else
		rte_mem_cfg_addr = NULL;

	if (mem_cfg_fd < 0){
		mem_cfg_fd = open(pathname, O_RDWR | O_CREAT, 0660);
		if (mem_cfg_fd < 0)
			rte_panic("Cannot open '%s' for rte_mem_config\n", pathname);
	}

	retval = ftruncate(mem_cfg_fd, sizeof(*rte_config.mem_config));
	if (retval < 0){
		close(mem_cfg_fd);
		rte_panic("Cannot resize '%s' for rte_mem_config\n", pathname);
	}

	retval = fcntl(mem_cfg_fd, F_SETLK, &wr_lock);
	if (retval < 0){
		close(mem_cfg_fd);
		rte_exit(EXIT_FAILURE, "Cannot create lock on '%s'. Is another primary "
				"process running?\n", pathname);
	}

	rte_mem_cfg_addr = mmap(rte_mem_cfg_addr, sizeof(*rte_config.mem_config),
				PROT_READ | PROT_WRITE, MAP_SHARED, mem_cfg_fd, 0);

	if (rte_mem_cfg_addr == MAP_FAILED){
		rte_panic("Cannot mmap memory for rte_config\n");
	}
	memcpy(rte_mem_cfg_addr, &early_mem_config, sizeof(early_mem_config));
	rte_config.mem_config = (struct rte_mem_config *) rte_mem_cfg_addr;

	/* store address of the config in the config itself so that secondary
	 * processes could later map the config into this exact location */
	rte_config.mem_config->mem_cfg_addr = (uintptr_t) rte_mem_cfg_addr;

}

/* attach to an existing shared memory config */
static void
rte_eal_config_attach(void)
{
	struct rte_mem_config *mem_config;

	const char *pathname = eal_runtime_config_path();

	if (internal_config.no_shconf)
		return;

	if (mem_cfg_fd < 0){
		mem_cfg_fd = open(pathname, O_RDWR);
		if (mem_cfg_fd < 0)
			rte_panic("Cannot open '%s' for rte_mem_config\n", pathname);
	}

	/* map it as read-only first */
	mem_config = (struct rte_mem_config *) mmap(NULL, sizeof(*mem_config),
			PROT_READ, MAP_SHARED, mem_cfg_fd, 0);
	if (mem_config == MAP_FAILED)
		rte_panic("Cannot mmap memory for rte_config! error %i (%s)\n",
			  errno, strerror(errno));

	rte_config.mem_config = mem_config;
}

/* reattach the shared config at exact memory location primary process has it */
static void
rte_eal_config_reattach(void)
{
	struct rte_mem_config *mem_config;
	void *rte_mem_cfg_addr;

	if (internal_config.no_shconf)
		return;

	/* save the address primary process has mapped shared config to */
	rte_mem_cfg_addr = (void *) (uintptr_t) rte_config.mem_config->mem_cfg_addr;

	/* unmap original config */
	munmap(rte_config.mem_config, sizeof(struct rte_mem_config));

	/* remap the config at proper address */
	mem_config = (struct rte_mem_config *) mmap(rte_mem_cfg_addr,
			sizeof(*mem_config), PROT_READ | PROT_WRITE, MAP_SHARED,
			mem_cfg_fd, 0);
	if (mem_config == MAP_FAILED || mem_config != rte_mem_cfg_addr) {
		if (mem_config != MAP_FAILED)
			/* errno is stale, don't use */
			rte_panic("Cannot mmap memory for rte_config at [%p], got [%p]"
				  " - please use '--base-virtaddr' option\n",
				  rte_mem_cfg_addr, mem_config);
		else
			rte_panic("Cannot mmap memory for rte_config! error %i (%s)\n",
				  errno, strerror(errno));
	}
	close(mem_cfg_fd);

	rte_config.mem_config = mem_config;
}

/* Detect if we are a primary or a secondary process */
enum rte_proc_type_t
eal_proc_type_detect(void)
{
	enum rte_proc_type_t ptype = RTE_PROC_PRIMARY;
	const char *pathname = eal_runtime_config_path();

	/* if we can open the file but not get a write-lock we are a secondary
	 * process. NOTE: if we get a file handle back, we keep that open
	 * and don't close it to prevent a race condition between multiple opens */
	if (((mem_cfg_fd = open(pathname, O_RDWR)) >= 0) &&
			(fcntl(mem_cfg_fd, F_SETLK, &wr_lock) < 0))
		ptype = RTE_PROC_SECONDARY;

	RTE_LOG(INFO, EAL, "Auto-detected process type: %s\n",
			ptype == RTE_PROC_PRIMARY ? "PRIMARY" : "SECONDARY");

	return ptype;
}

/* Sets up rte_config structure with the pointer to shared memory config.*/
static void
rte_config_init(void)
{
	rte_config.process_type = internal_config.process_type;

	switch (rte_config.process_type){
	case RTE_PROC_PRIMARY:
		rte_eal_config_create();
		break;
	case RTE_PROC_SECONDARY:
		rte_eal_config_attach();
		rte_eal_mcfg_wait_complete(rte_config.mem_config);
		rte_eal_config_reattach();
		break;
	case RTE_PROC_AUTO:
	case RTE_PROC_INVALID:
		rte_panic("Invalid process type\n");
	}
}

/* Unlocks hugepage directories that were locked by eal_hugepage_info_init */
static void
eal_hugedirs_unlock(void)
{
	int i;

	for (i = 0; i < MAX_HUGEPAGE_SIZES; i++)
	{
		/* skip uninitialized */
		if (internal_config.hugepage_info[i].lock_descriptor < 0)
			continue;
		/* unlock hugepage file */
		flock(internal_config.hugepage_info[i].lock_descriptor, LOCK_UN);
		close(internal_config.hugepage_info[i].lock_descriptor);
		/* reset the field */
		internal_config.hugepage_info[i].lock_descriptor = -1;
	}
}

/* display usage */
static void
eal_usage(const char *prgname)
{
	printf("\nUsage: %s ", prgname);
	eal_common_usage();
	printf("EAL Linux options:\n"
	       "  --"OPT_SOCKET_MEM"        Memory to allocate on sockets (comma separated values)\n"
	       "  --"OPT_HUGE_DIR"          Directory where hugetlbfs is mounted\n"
	       "  --"OPT_FILE_PREFIX"       Prefix for hugepage filenames\n"
	       "  --"OPT_BASE_VIRTADDR"     Base virtual address\n"
	       "  --"OPT_CREATE_UIO_DEV"    Create /dev/uioX (usually done by hotplug)\n"
	       "  --"OPT_VFIO_INTR"         Interrupt mode for VFIO (legacy|msi|msix)\n"
	       "  --"OPT_XEN_DOM0"          Support running on Xen dom0 without hugetlbfs\n"
	       "  --"OPT_VHOST_OWNER"       Create vhost-user sockets with this owner:group\n"
	       "  --"OPT_VHOST_PERM"        Create vhost-user sockets with these permissions\n"
	       "\n");
	/* Allow the application to print its usage message too if hook is set */
	if ( rte_application_usage_hook ) {
		printf("===== Application Usage =====\n\n");
		rte_application_usage_hook(prgname);
	}
}

/* Set a per-application usage message */
rte_usage_hook_t
rte_set_application_usage_hook( rte_usage_hook_t usage_func )
{
	rte_usage_hook_t	old_func;

	/* Will be NULL on the first call to denote the last usage routine. */
	old_func					= rte_application_usage_hook;
	rte_application_usage_hook	= usage_func;

	return old_func;
}

static int
eal_parse_socket_mem(char *socket_mem)
{
	char * arg[RTE_MAX_NUMA_NODES];
	char *end;
	int arg_num, i, len;
	uint64_t total_mem = 0;

	len = strnlen(socket_mem, SOCKET_MEM_STRLEN);
	if (len == SOCKET_MEM_STRLEN) {
		RTE_LOG(ERR, EAL, "--socket-mem is too long\n");
		return -1;
	}

	/* all other error cases will be caught later */
	if (!isdigit(socket_mem[len-1]))
		return -1;

	/* split the optarg into separate socket values */
	arg_num = rte_strsplit(socket_mem, len,
			arg, RTE_MAX_NUMA_NODES, ',');

	/* if split failed, or 0 arguments */
	if (arg_num <= 0)
		return -1;

	internal_config.force_sockets = 1;

	/* parse each defined socket option */
	errno = 0;
	for (i = 0; i < arg_num; i++) {
		end = NULL;
		internal_config.socket_mem[i] = strtoull(arg[i], &end, 10);

		/* check for invalid input */
		if ((errno != 0)  ||
				(arg[i][0] == '\0') || (end == NULL) || (*end != '\0'))
			return -1;
		internal_config.socket_mem[i] *= 1024ULL;
		internal_config.socket_mem[i] *= 1024ULL;
		total_mem += internal_config.socket_mem[i];
	}

	/* check if we have a positive amount of total memory */
	if (total_mem == 0)
		return -1;

	return 0;
}

static int
eal_parse_base_virtaddr(const char *arg)
{
	char *end;
	uint64_t addr;

	errno = 0;
	addr = strtoull(arg, &end, 16);

	/* check for errors */
	if ((errno != 0) || (arg[0] == '\0') || end == NULL || (*end != '\0'))
		return -1;

	/* make sure we don't exceed 32-bit boundary on 32-bit target */
#ifndef RTE_ARCH_64
	if (addr >= UINTPTR_MAX)
		return -1;
#endif

	/* align the addr on 16M boundary, 16MB is the minimum huge page
	 * size on IBM Power architecture. If the addr is aligned to 16MB,
	 * it can align to 2MB for x86. So this alignment can also be used
	 * on x86 */
	internal_config.base_virtaddr =
		RTE_PTR_ALIGN_CEIL((uintptr_t)addr, (size_t)RTE_PGSIZE_16M);

	return 0;
}

static int
eal_parse_vfio_intr(const char *mode)
{
	unsigned i;
	static struct {
		const char *name;
		enum rte_intr_mode value;
	} map[] = {
		{ "legacy", RTE_INTR_MODE_LEGACY },
		{ "msi", RTE_INTR_MODE_MSI },
		{ "msix", RTE_INTR_MODE_MSIX },
	};

	for (i = 0; i < RTE_DIM(map); i++) {
		if (!strcmp(mode, map[i].name)) {
			internal_config.vfio_intr_mode = map[i].value;
			return 0;
		}
	}
	return -1;
}

/* Parse the arguments for --log-level only */
static void
eal_log_level_parse(int argc, char **argv)
{
	int opt;
	char **argvopt;
	int option_index;
	const int old_optind = optind;
	const int old_optopt = optopt;
	char * const old_optarg = optarg;

	argvopt = argv;
	optind = 1;

	eal_reset_internal_config(&internal_config);

	while ((opt = getopt_long(argc, argvopt, eal_short_options,
				  eal_long_options, &option_index)) != EOF) {

		int ret;

		/* getopt is not happy, stop right now */
		if (opt == '?')
			break;

		ret = (opt == OPT_LOG_LEVEL_NUM) ?
			eal_parse_common_option(opt, optarg, &internal_config) : 0;

		/* common parser is not happy */
		if (ret < 0)
			break;
	}

	/* restore getopt lib */
	optind = old_optind;
	optopt = old_optopt;
	optarg = old_optarg;
}

/* Parse the argument given in the command line of the application */
static int
eal_parse_args(int argc, char **argv)
{
	int opt, ret;
	char **argvopt;
	int option_index;
	char *prgname = argv[0];
	const int old_optind = optind;
	const int old_optopt = optopt;
	char * const old_optarg = optarg;

	argvopt = argv;
	optind = 1;

	while ((opt = getopt_long(argc, argvopt, eal_short_options,
				  eal_long_options, &option_index)) != EOF) {

		/* getopt is not happy, stop right now */
		if (opt == '?') {
			eal_usage(prgname);
			ret = -1;
			goto out;
		}

		ret = eal_parse_common_option(opt, optarg, &internal_config);
		/* common parser is not happy */
		if (ret < 0) {
			eal_usage(prgname);
			ret = -1;
			goto out;
		}
		/* common parser handled this option */
		if (ret == 0)
			continue;

		switch (opt) {
		case 'h':
			eal_usage(prgname);
			exit(EXIT_SUCCESS);

		/* long options */
		case OPT_XEN_DOM0_NUM:
#ifdef RTE_LIBRTE_XEN_DOM0
			internal_config.xen_dom0_support = 1;
#else
			RTE_LOG(ERR, EAL, "Can't support DPDK app "
				"running on Dom0, please configure"
				" RTE_LIBRTE_XEN_DOM0=y\n");
			ret = -1;
			goto out;
#endif
			break;

		case OPT_HUGE_DIR_NUM:
			internal_config.hugepage_dir = optarg;
			break;

		case OPT_FILE_PREFIX_NUM:
			internal_config.hugefile_prefix = optarg;
			break;

		case OPT_SOCKET_MEM_NUM:
			if (eal_parse_socket_mem(optarg) < 0) {
				RTE_LOG(ERR, EAL, "invalid parameters for --"
						OPT_SOCKET_MEM "\n");
				eal_usage(prgname);
				ret = -1;
				goto out;
			}
			break;

		case OPT_BASE_VIRTADDR_NUM:
			if (eal_parse_base_virtaddr(optarg) < 0) {
				RTE_LOG(ERR, EAL, "invalid parameter for --"
						OPT_BASE_VIRTADDR "\n");
				eal_usage(prgname);
				ret = -1;
				goto out;
			}
			break;

		case OPT_VFIO_INTR_NUM:
			if (eal_parse_vfio_intr(optarg) < 0) {
				RTE_LOG(ERR, EAL, "invalid parameters for --"
						OPT_VFIO_INTR "\n");
				eal_usage(prgname);
				ret = -1;
				goto out;
			}
			break;

		case OPT_CREATE_UIO_DEV_NUM:
			internal_config.create_uio_dev = 1;
			break;

		case OPT_VHOST_OWNER_NUM:
			internal_config.vhost_sock_owner = optarg;
			break;

		case OPT_VHOST_PERM_NUM:
			internal_config.vhost_sock_perm = optarg;
			break;

		default:
			if (opt < OPT_LONG_MIN_NUM && isprint(opt)) {
				RTE_LOG(ERR, EAL, "Option %c is not supported "
					"on Linux\n", opt);
			} else if (opt >= OPT_LONG_MIN_NUM &&
				   opt < OPT_LONG_MAX_NUM) {
				RTE_LOG(ERR, EAL, "Option %s is not supported "
					"on Linux\n",
					eal_long_options[option_index].name);
			} else {
				RTE_LOG(ERR, EAL, "Option %d is not supported "
					"on Linux\n", opt);
			}
			eal_usage(prgname);
			ret = -1;
			goto out;
		}
	}

	if (eal_adjust_config(&internal_config) != 0) {
		ret = -1;
		goto out;
	}

	/* sanity checks */
	if (eal_check_common_options(&internal_config) != 0) {
		eal_usage(prgname);
		ret = -1;
		goto out;
	}

	/* --xen-dom0 doesn't make sense with --socket-mem */
	if (internal_config.xen_dom0_support && internal_config.force_sockets == 1) {
		RTE_LOG(ERR, EAL, "Options --"OPT_SOCKET_MEM" cannot be specified "
			"together with --"OPT_XEN_DOM0"\n");
		eal_usage(prgname);
		ret = -1;
		goto out;
	}

	if (optind >= 0)
		argv[optind-1] = prgname;
	ret = optind-1;

out:
	/* restore getopt lib */
	optind = old_optind;
	optopt = old_optopt;
	optarg = old_optarg;

	return ret;
}

static void
eal_check_mem_on_local_socket(void)
{
	const struct rte_memseg *ms;
	int i, socket_id;

	socket_id = rte_lcore_to_socket_id(rte_config.master_lcore);

	ms = rte_eal_get_physmem_layout();

	for (i = 0; i < RTE_MAX_MEMSEG; i++)
		if (ms[i].socket_id == socket_id &&
				ms[i].len > 0)
			return;

	RTE_LOG(WARNING, EAL, "WARNING: Master core has no "
			"memory on local socket!\n");
}

static int
sync_func(__attribute__((unused)) void *arg)
{
	return 0;
}

inline static void
rte_eal_mcfg_complete(void)
{
	/* ALL shared mem_config related INIT DONE */
	if (rte_config.process_type == RTE_PROC_PRIMARY)
		rte_config.mem_config->magic = RTE_MAGIC;
}

/*
 * Request iopl privilege for all RPL, returns 0 on success
 * iopl() call is mostly for the i386 architecture. For other architectures,
 * return -1 to indicate IO privilege can't be changed in this way.
 */
int
rte_eal_iopl_init(void)
{
#if defined(RTE_ARCH_X86)
	if (iopl(3) != 0)
		return -1;
#endif
	return 0;
}

#ifdef VFIO_PRESENT
static int rte_eal_vfio_setup(void)
{
	int vfio_enabled = 0;

	if (!internal_config.no_pci) {
		pci_vfio_enable();
		vfio_enabled |= pci_vfio_is_enabled();
	}

	if (vfio_enabled) {

		/* if we are primary process, create a thread to communicate with
		 * secondary processes. the thread will use a socket to wait for
		 * requests from secondary process to send open file descriptors,
		 * because VFIO does not allow multiple open descriptors on a group or
		 * VFIO container.
		 */
		if (internal_config.process_type == RTE_PROC_PRIMARY &&
				vfio_mp_sync_setup() < 0)
			return -1;
	}

	return 0;
}
#endif

/* Launch threads, called at application init(). */
int
rte_eal_init(int argc, char **argv)
{
	int i, fctret, ret;
	pthread_t thread_id;
	static rte_atomic32_t run_once = RTE_ATOMIC32_INIT(0);
	const char *logid;
	char cpuset[RTE_CPU_AFFINITY_STR_LEN];
	char thread_name[RTE_MAX_THREAD_NAME_LEN];

	/* checks if the machine is adequate */
	rte_cpu_check_supported();

	if (!rte_atomic32_test_and_set(&run_once))
		return -1;

	logid = strrchr(argv[0], '/');
	logid = strdup(logid ? logid + 1: argv[0]);

	thread_id = pthread_self();

	eal_log_level_parse(argc, argv);

	/* set log level as early as possible */
	rte_set_log_level(internal_config.log_level);

	if (rte_eal_cpu_init() < 0)
		rte_panic("Cannot detect lcores\n");

	fctret = eal_parse_args(argc, argv);
	if (fctret < 0)
		exit(1);

	if (internal_config.no_hugetlbfs == 0 &&
			internal_config.process_type != RTE_PROC_SECONDARY &&
			internal_config.xen_dom0_support == 0 &&
			eal_hugepage_info_init() < 0)
		rte_panic("Cannot get hugepage information\n");

	if (internal_config.memory == 0 && internal_config.force_sockets == 0) {
		if (internal_config.no_hugetlbfs)
			internal_config.memory = MEMSIZE_IF_NO_HUGE_PAGE;
	}

	if (internal_config.vmware_tsc_map == 1) {
#ifdef RTE_LIBRTE_EAL_VMWARE_TSC_MAP_SUPPORT
		rte_cycles_vmware_tsc_map = 1;
		RTE_LOG (DEBUG, EAL, "Using VMWARE TSC MAP, "
				"you must have monitor_control.pseudo_perfctr = TRUE\n");
#else
		RTE_LOG (WARNING, EAL, "Ignoring --vmware-tsc-map because "
				"RTE_LIBRTE_EAL_VMWARE_TSC_MAP_SUPPORT is not set\n");
#endif
	}

	rte_srand(rte_rdtsc());

	rte_config_init();

	if (rte_eal_log_init(logid, internal_config.syslog_facility) < 0)
		rte_panic("Cannot init logs\n");

	if (rte_eal_pci_init() < 0)
		rte_panic("Cannot init PCI\n");

#ifdef VFIO_PRESENT
	if (rte_eal_vfio_setup() < 0)
		rte_panic("Cannot init VFIO\n");
#endif

	if (rte_eal_memory_init() < 0)
		rte_panic("Cannot init memory\n");

	/* the directories are locked during eal_hugepage_info_init */
	eal_hugedirs_unlock();

	if (rte_eal_memzone_init() < 0)
		rte_panic("Cannot init memzone\n");

	if (rte_eal_tailqs_init() < 0)
		rte_panic("Cannot init tail queues for objects\n");

	if (rte_eal_alarm_init() < 0)
		rte_panic("Cannot init interrupt-handling thread\n");

	if (rte_eal_timer_init() < 0)
		rte_panic("Cannot init HPET or TSC timers\n");

	eal_check_mem_on_local_socket();

	if (eal_plugins_init() < 0)
		rte_panic("Cannot init plugins\n");

	eal_thread_init_master(rte_config.master_lcore);

	ret = eal_thread_dump_affinity(cpuset, RTE_CPU_AFFINITY_STR_LEN);

	RTE_LOG(DEBUG, EAL, "Master lcore %u is ready (tid=%x;cpuset=[%s%s])\n",
		rte_config.master_lcore, (int)thread_id, cpuset,
		ret == 0 ? "" : "...");

	if (rte_eal_dev_init() < 0)
		rte_panic("Cannot init pmd devices\n");

	if (rte_eal_intr_init() < 0)
		rte_panic("Cannot init interrupt-handling thread\n");

	RTE_LCORE_FOREACH_SLAVE(i) {

		/*
		 * create communication pipes between master thread
		 * and children
		 */
		if (pipe(lcore_config[i].pipe_master2slave) < 0)
			rte_panic("Cannot create pipe\n");
		if (pipe(lcore_config[i].pipe_slave2master) < 0)
			rte_panic("Cannot create pipe\n");

		lcore_config[i].state = WAIT;

		/* create a thread for each lcore */
		ret = pthread_create(&lcore_config[i].thread_id, NULL,
				     eal_thread_loop, NULL);
		if (ret != 0)
			rte_panic("Cannot create thread\n");

		/* Set thread_name for aid in debugging. */
		snprintf(thread_name, RTE_MAX_THREAD_NAME_LEN,
			"lcore-slave-%d", i);
		ret = rte_thread_setname(lcore_config[i].thread_id,
						thread_name);
		if (ret != 0)
			RTE_LOG(DEBUG, EAL,
				"Cannot set name for lcore thread\n");
	}

	/*
	 * Launch a dummy function on all slave lcores, so that master lcore
	 * knows they are all ready when this function returns.
	 */
	rte_eal_mp_remote_launch(sync_func, NULL, SKIP_MASTER);
	rte_eal_mp_wait_lcore();

	/* Probe & Initialize PCI devices */
	if (rte_eal_pci_probe())
		rte_panic("Cannot probe PCI\n");

	rte_eal_mcfg_complete();

	return fctret;
}

/* get core role */
enum rte_lcore_role_t
rte_eal_lcore_role(unsigned lcore_id)
{
	return rte_config.lcore_role[lcore_id];
}

enum rte_proc_type_t
rte_eal_process_type(void)
{
	return rte_config.process_type;
}

int rte_eal_has_hugepages(void)
{
	return ! internal_config.no_hugetlbfs;
}

int
rte_eal_check_module(const char *module_name)
{
	char sysfs_mod_name[PATH_MAX];
	struct stat st;
	int n;

	if (NULL == module_name)
		return -1;

	/* Check if there is sysfs mounted */
	if (stat("/sys/module", &st) != 0) {
		RTE_LOG(DEBUG, EAL, "sysfs is not mounted! error %i (%s)\n",
			errno, strerror(errno));
		return -1;
	}

	/* A module might be built-in, therefore try sysfs */
	n = snprintf(sysfs_mod_name, PATH_MAX, "/sys/module/%s", module_name);
	if (n < 0 || n > PATH_MAX) {
		RTE_LOG(DEBUG, EAL, "Could not format module path\n");
		return -1;
	}

	if (stat(sysfs_mod_name, &st) != 0) {
		RTE_LOG(DEBUG, EAL, "Module %s not found! error %i (%s)\n",
		        sysfs_mod_name, errno, strerror(errno));
		return 0;
	}

	/* Module has been found */
	return 1;
}

/* Try to double the size of '*buf', return true
 * if successful, and '*sizep' will be updated with
 * the new size. Otherwise, return false.  */
static int
enlarge_buffer(char **buf, size_t *sizep)
{
    size_t newsize = *sizep * 2;

    if (newsize > *sizep) {
        *buf = realloc(*buf, newsize);
        *sizep = newsize;
        return 1;
    }

    return 0;
}

static int
get_owners_from_str(const char *user_spec, uid_t *uid, gid_t *gid)
{
	size_t bufsize = 4096;

	char *pos = strchr(user_spec, ':');
	user_spec += strspn(user_spec, " \t\r\n");
	size_t len = pos ? (size_t)(pos - user_spec) : strlen(user_spec);

	char *buf = NULL;
	struct passwd pwd, *res;
	int e;

	buf = malloc(bufsize);
	char *user_search = NULL;
	if (len) {
		user_search = malloc(len + 1);
		memcpy(user_search, user_spec, len);
		user_search[len] = '\0';
		while ((e = getpwnam_r(user_search, &pwd, buf, bufsize, &res)) == ERANGE) {
			if (!enlarge_buffer(&buf, &bufsize)) {
				break;
			}
		}

		if (e != 0) {
			RTE_LOG(ERR, EAL,"Failed to retrive user %s's uid (%s), aborting.",
				user_search, strerror(e));
			goto release;
		}
		if (res == NULL) {
			RTE_LOG(ERR, EAL,"user %s not found,  aborting.",
				user_search);
			e = -1;
			goto release;
		}
	} else {
		/* User name is not specified, use current user.  */
		while ((e = getpwuid_r(getuid(), &pwd, buf, bufsize, &res)) == ERANGE) {
			if (!enlarge_buffer(&buf, &bufsize)) {
				break;
			}
		}

		if (e != 0) {
			RTE_LOG(ERR, EAL,"Failed to retrive current user's uid "
				"(%s), aborting.", strerror(e));
			goto release;
		}
		user_search = strdup(pwd.pw_name);
	}

	if (uid)
		*uid = pwd.pw_uid;

	free(buf);
	buf = NULL;

	if (pos) {
		char *grpstr = pos + 1;
		grpstr += strspn(grpstr, " \t\r\n");

		if (*grpstr) {
			struct group grp, *res;

			bufsize = 4096;
			buf = malloc(bufsize);
			while ((e = getgrnam_r(grpstr, &grp, buf, bufsize, &res))
					 == ERANGE) {
				if (!enlarge_buffer(&buf, &bufsize)) {
					break;
				}
			}

			if (e) {
				RTE_LOG(ERR, EAL,"Failed to get group entry for %s, "
					"(%s), aborting.", grpstr,
					strerror(e));
				goto release;
			}
			if (res == NULL) {
				RTE_LOG(ERR, EAL,"Group %s not found, aborting.",
					grpstr);
				e = -1;
				goto release;
			}

			if (gid)
				*gid = grp.gr_gid;
		}
	}

 release:
	free(buf);
	free(user_search);
	return e;
}

static void
vhost_set_permissions(const char *vhost_sock_location)
{
	unsigned long int mode = strtoul(internal_config.vhost_sock_perm, NULL, 0);
	int err = chmod(vhost_sock_location, (mode_t)mode);
	if (err) {
		RTE_LOG(ERR, EAL,"vhost-user socket cannot set"
			" permissions to %s (%s).\n",
			internal_config.vhost_sock_perm, strerror(err));
		return;
	}
	RTE_LOG(INFO, EAL,"Socket %s changed permissions"
			" to %s\n", vhost_sock_location,
			internal_config.vhost_sock_perm);
}

static void
vhost_set_ownership(const char *vhost_sock_location)
{
	uid_t vhuid=0;
	gid_t vhgid=0;

	if (get_owners_from_str(internal_config.vhost_sock_owner, &vhuid, &vhgid)) {
		RTE_LOG(ERR, EAL,"vhost-user socket unable to get"
			" specified user/group: %s\n",
			internal_config.vhost_sock_owner);
		return;
	}

	int err = chown(vhost_sock_location, vhuid, vhgid);
	if (err) {
		RTE_LOG(ERR, EAL,"vhost-user socket unable to set"
			" ownership to %s (%s).\n",
			internal_config.vhost_sock_owner, strerror(err));
		return;
	}

	RTE_LOG(INFO, EAL,"Socket %s changed ownership"
			" to %s.\n", vhost_sock_location,
			internal_config.vhost_sock_owner);
}

void
rte_eal_set_socket_permissions(const char *path)
{
	if (internal_config.vhost_sock_perm) {
		vhost_set_permissions(path);
	}

	if (internal_config.vhost_sock_owner) {
		vhost_set_ownership(path);
	}
}