/*-
* BSD LICENSE
*
- * Copyright(c) 2010-2012 Intel Corporation. All rights reserved.
+ * Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
* 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.
- *
- * version: DPDK.L.1.2.3-3
*/
#include <string.h>
#include <sys/types.h>
+#include <sys/file.h>
#include <dirent.h>
#include <stdint.h>
#include <stdlib.h>
#include <stdio.h>
+#include <fnmatch.h>
#include <inttypes.h>
#include <stdarg.h>
+#include <unistd.h>
#include <errno.h>
#include <sys/queue.h>
-#include "rte_memory.h"
-#include "rte_memzone.h"
-#include "rte_tailq.h"
-#include "rte_eal.h"
-#include "rte_launch.h"
-#include "rte_per_lcore.h"
-#include "rte_lcore.h"
-#include "rte_debug.h"
-#include "rte_log.h"
-#include "rte_common.h"
+#include <rte_memory.h>
+#include <rte_memzone.h>
+#include <rte_tailq.h>
+#include <rte_eal.h>
+#include <rte_launch.h>
+#include <rte_per_lcore.h>
+#include <rte_lcore.h>
+#include <rte_debug.h>
+#include <rte_log.h>
+#include <rte_common.h>
#include "rte_string_fns.h"
#include "eal_internal_cfg.h"
#include "eal_hugepages.h"
+#include "eal_filesystem.h"
static const char sys_dir_path[] = "/sys/kernel/mm/hugepages";
static int32_t
get_num_hugepages(const char *subdir)
{
- const char nr_hp_file[] = "nr_hugepages";
- char path[BUFSIZ];
- unsigned num_pages = 0;
+ char path[PATH_MAX];
+ long unsigned num_pages = 0;
+ const char *nr_hp_file;
+
+ /* if secondary process, just look at the number of hugepages,
+ * otherwise look at number of free hugepages */
+ if (internal_config.process_type == RTE_PROC_SECONDARY)
+ nr_hp_file = "nr_hugepages";
+ else
+ nr_hp_file = "free_hugepages";
rte_snprintf(path, sizeof(path), "%s/%s/%s",
sys_dir_path, subdir, nr_hp_file);
- FILE *fd = fopen(path, "r");
- if (fd == NULL || fscanf(fd, "%u", &num_pages) != 1)
- rte_panic("Error reading file '%s'\n", path);
- fclose(fd);
- return num_pages;
+ if (eal_parse_sysfs_value(path, &num_pages) < 0)
+ return 0;
+
+ if (num_pages == 0)
+ RTE_LOG(WARNING, EAL, "No free hugepages reported in %s\n",
+ subdir);
+
+ return (int32_t)num_pages;
}
static uint64_t
swap_hpi(struct hugepage_info *a, struct hugepage_info *b)
{
char buf[sizeof(*a)];
- memcpy(buf, a, sizeof(*a));
- memcpy(a, b, sizeof(*a));
- memcpy(b, buf, sizeof(*a));
+ memcpy(buf, a, sizeof(buf));
+ memcpy(a, b, sizeof(buf));
+ memcpy(b, buf, sizeof(buf));
}
+/*
+ * Clear the hugepage directory of whatever hugepage files
+ * there are. Checks if the file is locked (i.e.
+ * if it's in use by another DPDK process).
+ */
+static int
+clear_hugedir(const char * hugedir)
+{
+ DIR *dir;
+ struct dirent *dirent;
+ int dir_fd, fd, lck_result;
+ const char filter[] = "*map_*"; /* matches hugepage files */
+
+ /* open directory */
+ dir = opendir(hugedir);
+ if (!dir) {
+ RTE_LOG(INFO, EAL, "Unable to open hugepage directory %s\n",
+ hugedir);
+ goto error;
+ }
+ dir_fd = dirfd(dir);
+
+ dirent = readdir(dir);
+ if (!dirent) {
+ RTE_LOG(INFO, EAL, "Unable to read hugepage directory %s\n",
+ hugedir);
+ goto error;
+ }
+
+ while(dirent != NULL){
+ /* skip files that don't match the hugepage pattern */
+ if (fnmatch(filter, dirent->d_name, 0) > 0) {
+ dirent = readdir(dir);
+ continue;
+ }
+
+ /* try and lock the file */
+ fd = openat(dir_fd, dirent->d_name, O_RDONLY);
+
+ /* skip to next file */
+ if (fd == -1) {
+ dirent = readdir(dir);
+ continue;
+ }
+
+ /* non-blocking lock */
+ lck_result = flock(fd, LOCK_EX | LOCK_NB);
+
+ /* if lock succeeds, unlock and remove the file */
+ if (lck_result != -1) {
+ flock(fd, LOCK_UN);
+ unlinkat(dir_fd, dirent->d_name, 0);
+ }
+ close (fd);
+ dirent = readdir(dir);
+ }
+
+ closedir(dir);
+ return 0;
+
+error:
+ if (dir)
+ closedir(dir);
+
+ RTE_LOG(INFO, EAL, "Error while clearing hugepage dir: %s\n",
+ strerror(errno));
+
+ return -1;
+}
+
+/*
+ * when we initialize the hugepage info, everything goes
+ * to socket 0 by default. it will later get sorted by memory
+ * initialization procedure.
+ */
int
eal_hugepage_info_init(void)
{
struct hugepage_info *hpi = \
&internal_config.hugepage_info[num_sizes];
hpi->hugepage_sz = rte_str_to_size(&dirent->d_name[dirent_start_len]);
- hpi->num_pages = get_num_hugepages(dirent->d_name);
hpi->hugedir = get_hugepage_dir(hpi->hugepage_sz);
+
+ /* first, check if we have a mountpoint */
if (hpi->hugedir == NULL){
- RTE_LOG(INFO, EAL, "%u hugepages of size %llu reserved, "\
- "but no mounted hugetlbfs found for that size\n",
- hpi->num_pages,
- (unsigned long long)hpi->hugepage_sz);
- hpi->num_pages = 0;
- } else
+ int32_t num_pages;
+ if ((num_pages = get_num_hugepages(dirent->d_name)) > 0)
+ RTE_LOG(INFO, EAL, "%u hugepages of size %llu reserved, "\
+ "but no mounted hugetlbfs found for that size\n",
+ (unsigned)num_pages,
+ (unsigned long long)hpi->hugepage_sz);
+ } else {
+ /* try to obtain a writelock */
+ hpi->lock_descriptor = open(hpi->hugedir, O_RDONLY);
+
+ /* if blocking lock failed */
+ if (flock(hpi->lock_descriptor, LOCK_EX) == -1) {
+ RTE_LOG(CRIT, EAL, "Failed to lock hugepage directory!\n");
+ return -1;
+ }
+ /* clear out the hugepages dir from unused pages */
+ if (clear_hugedir(hpi->hugedir) == -1)
+ return -1;
+
+ /* for now, put all pages into socket 0,
+ * later they will be sorted */
+ hpi->num_pages[0] = get_num_hugepages(dirent->d_name);
+
+#ifndef RTE_ARCH_X86_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
+
num_sizes++;
+ }
}
dirent = readdir(dir);
}
/* now we have all info, check we have at least one valid size */
for (i = 0; i < num_sizes; i++)
if (internal_config.hugepage_info[i].hugedir != NULL &&
- internal_config.hugepage_info[i].num_pages > 0)
+ internal_config.hugepage_info[i].num_pages[0] > 0)
return 0;
+
/* no valid hugepage mounts available, return error */
return -1;
}