/*-
* BSD LICENSE
- *
- * Copyright(c) 2010-2013 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.
- *
*/
#include <string.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>
static const char sys_dir_path[] = "/sys/kernel/mm/hugepages";
-static int32_t
+/* this function is only called from eal_hugepage_info_init which itself
+ * is only called from a primary process */
+static uint32_t
get_num_hugepages(const char *subdir)
{
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";
+ long unsigned resv_pages, num_pages = 0;
+ const char *nr_hp_file = "free_hugepages";
+ const char *nr_rsvd_file = "resv_hugepages";
+
+ /* first, check how many reserved pages kernel reports */
+ snprintf(path, sizeof(path), "%s/%s/%s",
+ sys_dir_path, subdir, nr_rsvd_file);
+ if (eal_parse_sysfs_value(path, &resv_pages) < 0)
+ return 0;
- rte_snprintf(path, sizeof(path), "%s/%s/%s",
+ snprintf(path, sizeof(path), "%s/%s/%s",
sys_dir_path, subdir, nr_hp_file);
-
if (eal_parse_sysfs_value(path, &num_pages) < 0)
return 0;
if (num_pages == 0)
- RTE_LOG(ERR, EAL, "Error - no free hugepages available!\n");
+ RTE_LOG(WARNING, EAL, "No free hugepages reported in %s\n",
+ subdir);
+
+ /* adjust num_pages */
+ if (num_pages >= resv_pages)
+ num_pages -= resv_pages;
+ else if (resv_pages)
+ num_pages = 0;
+
+ /* we want to return a uint32_t and more than this looks suspicious
+ * anyway ... */
+ if (num_pages > UINT32_MAX)
+ num_pages = UINT32_MAX;
- return (int32_t)num_pages;
+ return num_pages;
}
static uint64_t
return retval;
}
-static inline void
-swap_hpi(struct hugepage_info *a, struct hugepage_info *b)
-{
- char 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.
/* open directory */
dir = opendir(hugedir);
if (!dir) {
- RTE_LOG(INFO, EAL, "Unable to open hugepage directory %s\n",
+ RTE_LOG(ERR, EAL, "Unable to open hugepage directory %s\n",
hugedir);
goto error;
}
dirent = readdir(dir);
if (!dirent) {
- RTE_LOG(INFO, EAL, "Unable to read hugepage directory %s\n",
+ RTE_LOG(ERR, EAL, "Unable to read hugepage directory %s\n",
hugedir);
goto error;
}
if (dir)
closedir(dir);
- RTE_LOG(INFO, EAL, "Error while clearing hugepage dir: %s\n",
+ RTE_LOG(ERR, EAL, "Error while clearing hugepage dir: %s\n",
strerror(errno));
return -1;
}
+static int
+compare_hpi(const void *a, const void *b)
+{
+ const struct hugepage_info *hpi_a = a;
+ const struct hugepage_info *hpi_b = b;
+
+ return hpi_b->hugepage_sz - hpi_a->hugepage_sz;
+}
+
/*
* when we initialize the hugepage info, everything goes
* to socket 0 by default. it will later get sorted by memory
const char dirent_start_text[] = "hugepages-";
const size_t dirent_start_len = sizeof(dirent_start_text) - 1;
unsigned i, num_sizes = 0;
+ DIR *dir;
+ struct dirent *dirent;
- DIR *dir = opendir(sys_dir_path);
- if (dir == NULL)
- rte_panic("Cannot open directory %s to read system hugepage info\n",
- sys_dir_path);
+ dir = opendir(sys_dir_path);
+ if (dir == NULL) {
+ RTE_LOG(ERR, EAL,
+ "Cannot open directory %s to read system hugepage info\n",
+ sys_dir_path);
+ return -1;
+ }
- struct dirent *dirent = readdir(dir);
- while(dirent != NULL){
- if (strncmp(dirent->d_name, dirent_start_text, dirent_start_len) == 0){
- struct hugepage_info *hpi = \
- &internal_config.hugepage_info[num_sizes];
- hpi->hugepage_sz = rte_str_to_size(&dirent->d_name[dirent_start_len]);
- 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",
- (unsigned) get_num_hugepages(dirent->d_name),
- (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
+ for (dirent = readdir(dir); dirent != NULL; dirent = readdir(dir)) {
+ struct hugepage_info *hpi;
- num_sizes++;
- }
+ if (strncmp(dirent->d_name, dirent_start_text,
+ dirent_start_len) != 0)
+ continue;
+
+ if (num_sizes >= MAX_HUGEPAGE_SIZES)
+ break;
+
+ hpi = &internal_config.hugepage_info[num_sizes];
+ hpi->hugepage_sz =
+ rte_str_to_size(&dirent->d_name[dirent_start_len]);
+ hpi->hugedir = get_hugepage_dir(hpi->hugepage_sz);
+
+ /* first, check if we have a mountpoint */
+ if (hpi->hugedir == NULL) {
+ uint32_t num_pages;
+
+ num_pages = get_num_hugepages(dirent->d_name);
+ if (num_pages > 0)
+ RTE_LOG(NOTICE, EAL,
+ "%" PRIu32 " hugepages of size "
+ "%" PRIu64 " reserved, but no mounted "
+ "hugetlbfs found for that size\n",
+ num_pages, hpi->hugepage_sz);
+ continue;
}
- dirent = readdir(dir);
+
+ /* 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");
+ break;
+ }
+ /* clear out the hugepages dir from unused pages */
+ if (clear_hugedir(hpi->hugedir) == -1)
+ break;
+
+ /* 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_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++;
}
closedir(dir);
+
+ /* something went wrong, and we broke from the for loop above */
+ if (dirent != NULL)
+ return -1;
+
internal_config.num_hugepage_sizes = num_sizes;
/* sort the page directory entries by size, largest to smallest */
- for (i = 0; i < num_sizes; i++){
- unsigned j;
- for (j = i+1; j < num_sizes; j++)
- if (internal_config.hugepage_info[j-1].hugepage_sz < \
- internal_config.hugepage_info[j].hugepage_sz)
- swap_hpi(&internal_config.hugepage_info[j-1],
- &internal_config.hugepage_info[j]);
- }
+ qsort(&internal_config.hugepage_info[0], num_sizes,
+ sizeof(internal_config.hugepage_info[0]), compare_hpi);
/* 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] > 0)
+ internal_config.hugepage_info[i].num_pages[0] > 0)
return 0;
/* no valid hugepage mounts available, return error */