/*-
* BSD LICENSE
- *
- * Copyright(c) 2010-2012 Intel Corporation. All rights reserved.
+ *
+ * Copyright(c) 2010-2014 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
+ *
+ * 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
+ *
+ * * 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
+ * * 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
+ * * 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
+ *
+ * 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 <stdarg.h>
#include <unistd.h>
#include <pthread.h>
+#include <syslog.h>
#include <getopt.h>
+#include <sys/file.h>
#include <fcntl.h>
+#include <dlfcn.h>
#include <stddef.h>
#include <errno.h>
#include <limits.h>
#include <errno.h>
#include <sys/mman.h>
#include <sys/queue.h>
+#if defined(RTE_ARCH_X86_64) || defined(RTE_ARCH_I686)
+#include <sys/io.h>
+#endif
#include <rte_common.h>
#include <rte_debug.h>
#include <rte_memory.h>
#include <rte_memzone.h>
#include <rte_launch.h>
-#include <rte_tailq.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_cpuflags.h>
#include <rte_interrupts.h>
#include <rte_pci.h>
+#include <rte_devargs.h>
#include <rte_common.h>
#include <rte_version.h>
+#include <rte_atomic.h>
+#include <malloc_heap.h>
+#include <rte_eth_ring.h>
#include "eal_private.h"
#include "eal_thread.h"
#include "eal_internal_cfg.h"
-#include "eal_fs_paths.h"
+#include "eal_filesystem.h"
#include "eal_hugepages.h"
+#include "eal_options.h"
-#define OPT_HUGE_DIR "huge-dir"
-#define OPT_PROC_TYPE "proc-type"
-#define OPT_NO_SHCONF "no-shconf"
-#define OPT_NO_HPET "no-hpet"
-#define OPT_NO_PCI "no-pci"
-#define OPT_NO_HUGE "no-huge"
-#define OPT_FILE_PREFIX "file-prefix"
+#define MEMSIZE_IF_NO_HUGE_PAGE (64ULL * 1024ULL * 1024ULL)
-#define RTE_EAL_BLACKLIST_SIZE 0x100
+#define SOCKET_MEM_STRLEN (RTE_MAX_NUMA_NODES * 10)
-#define MEMSIZE_IF_NO_HUGE_PAGE (64ULL * 1024ULL * 1024ULL)
+/* Allow the application to print its usage message too if set */
+static rte_usage_hook_t rte_application_usage_hook = NULL;
-#define GET_BLACKLIST_FIELD(in, fd, lim, dlm) \
-{ \
- unsigned long val; \
- char *end; \
- errno = 0; \
- val = strtoul((in), &end, 16); \
- if (errno != 0 || end[0] != (dlm) || val > (lim)) \
- return (-EINVAL); \
- (fd) = (typeof (fd))val; \
- (in) = end + 1; \
-}
+TAILQ_HEAD(shared_driver_list, shared_driver);
+
+/* Definition for shared object drivers. */
+struct shared_driver {
+ TAILQ_ENTRY(shared_driver) next;
+
+ char name[PATH_MAX];
+ void* lib_handle;
+};
+
+/* List of external loadable drivers */
+static struct shared_driver_list solib_list =
+TAILQ_HEAD_INITIALIZER(solib_list);
/* early configuration structure, when memory config is not mmapped */
static struct rte_mem_config early_mem_config;
.mem_config = &early_mem_config,
};
-static struct rte_pci_addr eal_dev_blacklist[RTE_EAL_BLACKLIST_SIZE];
-
/* 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).
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)
"process running?\n", pathname);
}
- rte_mem_cfg_addr = mmap(NULL, sizeof(*rte_config.mem_config),
- PROT_READ | PROT_WRITE, MAP_SHARED, mem_cfg_fd, 0);
+ 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;
- memcpy(rte_config.mem_config, &early_mem_config,
- sizeof(early_mem_config));
+
+ /* 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)
{
- void *rte_mem_cfg_addr;
+ 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_RDONLY);
+ mem_cfg_fd = open(pathname, O_RDWR);
if (mem_cfg_fd < 0)
rte_panic("Cannot open '%s' for rte_mem_config\n", pathname);
}
- rte_mem_cfg_addr = mmap(NULL, sizeof(*rte_config.mem_config), PROT_READ,
- MAP_SHARED, mem_cfg_fd, 0);
+ /* 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\n");
+
+ 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);
close(mem_cfg_fd);
- if (rte_mem_cfg_addr == MAP_FAILED)
+ if (mem_config == MAP_FAILED || mem_config != rte_mem_cfg_addr)
rte_panic("Cannot mmap memory for rte_config\n");
- rte_config.mem_config = (struct rte_mem_config *) rte_mem_cfg_addr;
+ rte_config.mem_config = mem_config;
}
/* Detect if we are a primary or a secondary process */
-static enum rte_proc_type_t
+enum rte_proc_type_t
eal_proc_type_detect(void)
{
enum rte_proc_type_t ptype = RTE_PROC_PRIMARY;
static void
rte_config_init(void)
{
- /* set the magic in configuration structure */
- rte_config.magic = RTE_MAGIC;
- rte_config.process_type = (internal_config.process_type == RTE_PROC_AUTO) ?
- eal_proc_type_detect() : /* for auto, detect the type */
- internal_config.process_type; /* otherwise use what's already set */
+ rte_config.process_type = internal_config.process_type;
switch (rte_config.process_type){
case RTE_PROC_PRIMARY:
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:
}
}
+/* 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 -c COREMASK -n NUM [-m NB] [-r NUM] [-b <domain:bus:devid.func>]"
- "[--proc-type primary|secondary|auto] \n\n"
- "EAL options:\n"
- " -c COREMASK: A hexadecimal bitmask of cores to run on\n"
- " -n NUM : Number of memory channels\n"
- " -v : Display version information on startup\n"
- " -b <domain:bus:devid.func>: to prevent EAL from using specified PCI device\n"
- " (multiple -b options are alowed)\n"
- " -m MB : memory to allocate (default = size of hugemem)\n"
- " -r NUM : force number of memory ranks (don't detect)\n"
- " --"OPT_HUGE_DIR" : directory where hugetlbfs is mounted\n"
- " --"OPT_PROC_TYPE": type of this process\n"
- " --"OPT_FILE_PREFIX": prefix for hugepage filenames\n"
- "\nEAL options for DEBUG use only:\n"
- " --"OPT_NO_HUGE" : use malloc instead of hugetlbfs\n"
- " --"OPT_NO_PCI" : disable pci\n"
- " --"OPT_NO_HPET" : disable hpet\n"
- " --"OPT_NO_SHCONF": no shared config (mmap'd files)\n\n",
- prgname);
+ printf("\nUsage: %s ", prgname);
+ eal_common_usage();
+ printf("EAL Linux options:\n"
+ " -d LIB.so Add driver (can be used multiple times)\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"
+ "\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;
}
-/*
- * Parse the coremask given as argument (hexadecimal string) and fill
- * the global configuration (core role and core count) with the parsed
- * value.
- */
static int
-eal_parse_coremask(const char *coremask)
+eal_parse_socket_mem(char *socket_mem)
{
- struct rte_config *cfg = rte_eal_get_configuration();
- unsigned i;
- char *end = NULL;
- unsigned long long cm;
- unsigned count = 0;
+ 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;
+ }
- /* parse hexadecimal string */
- cm = strtoull(coremask, &end, 16);
- if ((coremask[0] == '\0') || (end == NULL) || (*end != '\0') || (cm == 0))
+ /* all other error cases will be caught later */
+ if (!isdigit(socket_mem[len-1]))
return -1;
- RTE_LOG(DEBUG, EAL, "coremask set to %llx\n", cm);
- /* set core role and core count */
- for (i = 0; i < RTE_MAX_LCORE; i++) {
- if ((1ULL << i) & cm) {
- if (count == 0)
- cfg->master_lcore = i;
- cfg->lcore_role[i] = ROLE_RTE;
- count++;
- }
- else {
- cfg->lcore_role[i] = ROLE_OFF;
- }
+ /* 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 inline uint64_t
-eal_get_hugepage_mem_size(void)
+static int
+eal_parse_base_virtaddr(const char *arg)
{
- uint64_t size = 0;
- unsigned i;
+ char *end;
+ uint64_t addr;
- for (i = 0; i < internal_config.num_hugepage_sizes; i++){
- struct hugepage_info *hpi = &internal_config.hugepage_info[i];
- if (hpi->hugedir != NULL)
- size += hpi->hugepage_sz * hpi->num_pages;
- }
+ errno = 0;
+ addr = strtoull(arg, &end, 16);
- return (size);
-}
+ /* check for errors */
+ if ((errno != 0) || (arg[0] == '\0') || end == NULL || (*end != '\0'))
+ return -1;
-static enum rte_proc_type_t
-eal_parse_proc_type(const char *arg)
-{
- if (strncasecmp(arg, "primary", sizeof("primary")) == 0)
- return RTE_PROC_PRIMARY;
- if (strncasecmp(arg, "secondary", sizeof("secondary")) == 0)
- return RTE_PROC_SECONDARY;
- if (strncasecmp(arg, "auto", sizeof("auto")) == 0)
- return RTE_PROC_AUTO;
-
- return RTE_PROC_INVALID;
+ /* 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_blacklist(const char *input, struct rte_pci_addr *dev2bl)
+eal_parse_vfio_intr(const char *mode)
{
- GET_BLACKLIST_FIELD(input, dev2bl->domain, UINT16_MAX, ':');
- GET_BLACKLIST_FIELD(input, dev2bl->bus, UINT8_MAX, ':');
- GET_BLACKLIST_FIELD(input, dev2bl->devid, UINT8_MAX, '.');
- GET_BLACKLIST_FIELD(input, dev2bl->function, UINT8_MAX, 0);
- return (0);
+ 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;
}
-static ssize_t
-eal_parse_blacklist_opt(const char *optarg, size_t idx)
+static inline size_t
+eal_get_hugepage_mem_size(void)
{
- if (idx >= sizeof (eal_dev_blacklist) / sizeof (eal_dev_blacklist[0])) {
- RTE_LOG(ERR, EAL,
- "%s - too many devices to blacklist...\n",
- optarg);
- return (-EINVAL);
- } else if (eal_parse_blacklist(optarg, eal_dev_blacklist + idx) != 0) {
- RTE_LOG(ERR, EAL,
- "%s - invalid device to blacklist...\n",
- optarg);
- return (-EINVAL);
+ uint64_t size = 0;
+ unsigned i, j;
+
+ for (i = 0; i < internal_config.num_hugepage_sizes; i++) {
+ struct hugepage_info *hpi = &internal_config.hugepage_info[i];
+ if (hpi->hugedir != NULL) {
+ for (j = 0; j < RTE_MAX_NUMA_NODES; j++) {
+ size += hpi->hugepage_sz * hpi->num_pages[j];
+ }
+ }
}
- idx += 1;
- return (idx);
+ return (size < SIZE_MAX) ? (size_t)(size) : SIZE_MAX;
}
-
/* 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;
- int coremask_ok = 0;
- ssize_t blacklist_index = 0;;
char *prgname = argv[0];
- static struct option lgopts[] = {
- {OPT_NO_HUGE, 0, 0, 0},
- {OPT_NO_PCI, 0, 0, 0},
- {OPT_NO_HPET, 0, 0, 0},
- {OPT_HUGE_DIR, 1, 0, 0},
- {OPT_NO_SHCONF, 0, 0, 0},
- {OPT_PROC_TYPE, 1, 0, 0},
- {OPT_FILE_PREFIX, 1, 0, 0},
- {0, 0, 0, 0}
- };
+ struct shared_driver *solib;
argvopt = argv;
- internal_config.memory = 0;
- internal_config.force_nrank = 0;
- internal_config.force_nchannel = 0;
- internal_config.hugefile_prefix = HUGEFILE_PREFIX_DEFAULT;
- internal_config.hugepage_dir = NULL;
-#ifdef RTE_LIBEAL_USE_HPET
- internal_config.no_hpet = 0;
-#else
- internal_config.no_hpet = 1;
-#endif
+ 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 == '?') {
+ eal_usage(prgname);
+ return -1;
+ }
- while ((opt = getopt_long(argc, argvopt, "b:c:m:n:r:v",
- lgopts, &option_index)) != EOF) {
+ ret = eal_parse_common_option(opt, optarg, &internal_config);
+ /* common parser is not happy */
+ if (ret < 0) {
+ eal_usage(prgname);
+ return -1;
+ }
+ /* common parser handled this option */
+ if (ret == 0)
+ continue;
switch (opt) {
- /* blacklist */
- case 'b':
- if ((blacklist_index = eal_parse_blacklist_opt(optarg,
- blacklist_index)) < 0) {
- eal_usage(prgname);
- return (-1);
+ case 'h':
+ eal_usage(prgname);
+ exit(EXIT_SUCCESS);
+
+ /* force loading of external driver */
+ case 'd':
+ solib = malloc(sizeof(*solib));
+ if (solib == NULL) {
+ RTE_LOG(ERR, EAL, "malloc(solib) failed\n");
+ return -1;
}
+ memset(solib, 0, sizeof(*solib));
+ strncpy(solib->name, optarg, PATH_MAX-1);
+ solib->name[PATH_MAX-1] = 0;
+ TAILQ_INSERT_TAIL(&solib_list, solib, next);
+ break;
+
+ /* 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");
+ return -1;
+#endif
+ break;
+
+ case OPT_HUGE_DIR_NUM:
+ internal_config.hugepage_dir = optarg;
break;
- /* coremask */
- case 'c':
- if (eal_parse_coremask(optarg) < 0) {
- RTE_LOG(ERR, EAL, "invalid coremask\n");
+
+ 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);
return -1;
}
- coremask_ok = 1;
- break;
- /* size of memory */
- case 'm':
- internal_config.memory = atoi(optarg);
- internal_config.memory *= 1024ULL;
- internal_config.memory *= 1024ULL;
break;
- /* force number of channels */
- case 'n':
- internal_config.force_nchannel = atoi(optarg);
- if (internal_config.force_nchannel == 0 ||
- internal_config.force_nchannel > 4) {
- RTE_LOG(ERR, EAL, "invalid channel number\n");
+
+ 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);
return -1;
}
break;
- /* force number of ranks */
- case 'r':
- internal_config.force_nrank = atoi(optarg);
- if (internal_config.force_nrank == 0 ||
- internal_config.force_nrank > 16) {
- RTE_LOG(ERR, EAL, "invalid rank number\n");
+
+ 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);
return -1;
}
break;
- case 'v':
- /* since message is explicitly requested by user, we
- * write message at highest log level so it can always be seen
- * even if info or warning messages are disabled */
- RTE_LOG(CRIT, EAL, "RTE Version: '%s'\n", rte_version());
- break;
- /* long options */
- case 0:
- if (!strcmp(lgopts[option_index].name, OPT_NO_HUGE)) {
- internal_config.no_hugetlbfs = 1;
- }
- else if (!strcmp(lgopts[option_index].name, OPT_NO_PCI)) {
- internal_config.no_pci = 1;
- }
- else if (!strcmp(lgopts[option_index].name, OPT_NO_HPET)) {
- internal_config.no_hpet = 1;
- }
- else if (!strcmp(lgopts[option_index].name, OPT_NO_SHCONF)) {
- internal_config.no_shconf = 1;
- }
- else if (!strcmp(lgopts[option_index].name, OPT_HUGE_DIR)) {
- internal_config.hugepage_dir = optarg;
- }
- else if (!strcmp(lgopts[option_index].name, OPT_PROC_TYPE)) {
- internal_config.process_type = eal_parse_proc_type(optarg);
- }
- else if (!strcmp(lgopts[option_index].name, OPT_FILE_PREFIX)) {
- internal_config.hugefile_prefix = optarg;
- }
+ case OPT_CREATE_UIO_DEV_NUM:
+ internal_config.create_uio_dev = 1;
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);
return -1;
}
}
- /* sanity checks */
- if (!coremask_ok) {
- RTE_LOG(ERR, EAL, "coremask not specified\n");
- eal_usage(prgname);
+ if (eal_adjust_config(&internal_config) != 0)
return -1;
- }
- if (internal_config.process_type == RTE_PROC_AUTO){
- internal_config.process_type = eal_proc_type_detect();
- }
- if (internal_config.process_type == RTE_PROC_INVALID){
- RTE_LOG(ERR, EAL, "Invalid process type specified\n");
- eal_usage(prgname);
- return -1;
- }
- if (internal_config.process_type == RTE_PROC_PRIMARY &&
- internal_config.force_nchannel == 0) {
- RTE_LOG(ERR, EAL, "Number of memory channels (-n) not specified\n");
+
+ /* sanity checks */
+ if (eal_check_common_options(&internal_config) != 0) {
eal_usage(prgname);
return -1;
}
- if (index(internal_config.hugefile_prefix,'%') != NULL){
- RTE_LOG(ERR, EAL, "Invalid char, '%%', in '"OPT_FILE_PREFIX"' option\n");
+
+ /* --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);
return -1;
}
- if (blacklist_index > 0)
- rte_eal_pci_set_blacklist(eal_dev_blacklist, blacklist_index);
-
if (optind >= 0)
argv[optind-1] = prgname;
-
ret = optind-1;
optind = 0; /* reset getopt lib */
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_64) || defined(RTE_ARCH_I686)
+ if (iopl(3) != 0)
+ return -1;
+ return 0;
+#else
+ return -1;
+#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);
+ struct shared_driver *solib = NULL;
+ const char *logid;
+ char cpuset[RTE_CPU_AFFINITY_STR_LEN];
+
+ 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();
if (rte_eal_log_early_init() < 0)
rte_panic("Cannot init early logs\n");
+ if (rte_eal_cpu_init() < 0)
+ rte_panic("Cannot detect lcores\n");
+
fctret = eal_parse_args(argc, argv);
if (fctret < 0)
exit(1);
- if (eal_hugepage_info_init() < 0)
+ /* set log level as early as possible */
+ rte_set_log_level(internal_config.log_level);
+
+ 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) {
+ if (internal_config.memory == 0 && internal_config.force_sockets == 0) {
if (internal_config.no_hugetlbfs)
internal_config.memory = MEMSIZE_IF_NO_HUGE_PAGE;
else
internal_config.memory = eal_get_hugepage_mem_size();
}
+ 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_cpu_init() < 0)
- rte_panic("Cannot detect lcores\n");
+ if (rte_eal_pci_init() < 0)
+ rte_panic("Cannot init PCI\n");
+
+#ifdef RTE_LIBRTE_IVSHMEM
+ if (rte_eal_ivshmem_init() < 0)
+ rte_panic("Cannot init IVSHMEM\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_log_init() < 0)
+#ifdef RTE_LIBRTE_IVSHMEM
+ if (rte_eal_ivshmem_obj_init() < 0)
+ rte_panic("Cannot init IVSHMEM objects\n");
+#endif
+
+ if (rte_eal_log_init(logid, internal_config.syslog_facility) < 0)
rte_panic("Cannot init logs\n");
if (rte_eal_alarm_init() < 0)
if (rte_eal_intr_init() < 0)
rte_panic("Cannot init interrupt-handling thread\n");
- if (rte_eal_hpet_init() < 0)
- rte_panic("Cannot init HPET\n");
+ if (rte_eal_timer_init() < 0)
+ rte_panic("Cannot init HPET or TSC timers\n");
- if (rte_eal_pci_init() < 0)
- rte_panic("Cannot init PCI\n");
+ eal_check_mem_on_local_socket();
+
+ rte_eal_mcfg_complete();
+
+ TAILQ_FOREACH(solib, &solib_list, next) {
+ RTE_LOG(INFO, EAL, "open shared lib %s\n", solib->name);
+ solib->lib_handle = dlopen(solib->name, RTLD_NOW);
+ if (solib->lib_handle == NULL)
+ RTE_LOG(WARNING, EAL, "%s\n", dlerror());
+ }
+
+ eal_thread_init_master(rte_config.master_lcore);
+
+ ret = eal_thread_dump_affinity(cpuset, RTE_CPU_AFFINITY_STR_LEN);
- RTE_LOG(DEBUG, EAL, "Master core %u is ready (tid=%x)\n",
- rte_config.master_lcore, (int)thread_id);
+ 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");
RTE_LCORE_FOREACH_SLAVE(i) {
rte_panic("Cannot create thread\n");
}
- eal_thread_init_master(rte_config.master_lcore);
+ /*
+ * 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");
return fctret;
}
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 mod_name[30]; /* Any module names can be longer than 30 bytes? */
+ int ret = 0;
+ int n;
+
+ if (NULL == module_name)
+ return -1;
+
+ FILE *fd = fopen("/proc/modules", "r");
+ if (NULL == fd) {
+ RTE_LOG(ERR, EAL, "Open /proc/modules failed!"
+ " error %i (%s)\n", errno, strerror(errno));
+ return -1;
+ }
+ while (!feof(fd)) {
+ n = fscanf(fd, "%29s %*[^\n]", mod_name);
+ if ((n == 1) && !strcmp(mod_name, module_name)) {
+ ret = 1;
+ break;
+ }
+ }
+ fclose(fd);
+
+ return ret;
+}
git.droids-corp.org / dpdk.git / blobdiff