* BSD LICENSE
*
* Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
+ * Copyright(c) 2013 6WIND.
* All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*/
-/* BSD LICENSE
- *
- * Copyright(c) 2013 6WIND.
- *
- * 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 6WIND S.A. 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.
- */
#define _FILE_OFFSET_BITS 64
#include <errno.h>
#include <stdarg.h>
+#include <stdbool.h>
#include <stdlib.h>
#include <stdio.h>
#include <stdint.h>
static uint64_t baseaddr_offset;
-static unsigned proc_pagemap_readable;
+static bool phys_addrs_available = true;
#define RANDOMIZE_VA_SPACE_FILE "/proc/sys/kernel/randomize_va_space"
static void
-test_proc_pagemap_readable(void)
+test_phys_addrs_available(void)
{
- int fd = open("/proc/self/pagemap", O_RDONLY);
+ uint64_t tmp;
+ phys_addr_t physaddr;
- if (fd < 0) {
+ /* For dom0, phys addresses can always be available */
+ if (rte_xen_dom0_supported())
+ return;
+
+ physaddr = rte_mem_virt2phy(&tmp);
+ if (physaddr == RTE_BAD_PHYS_ADDR) {
RTE_LOG(ERR, EAL,
- "Cannot open /proc/self/pagemap: %s. "
- "virt2phys address translation will not work\n",
+ "Cannot obtain physical addresses: %s. "
+ "Only vfio will function.\n",
strerror(errno));
- return;
+ phys_addrs_available = false;
}
-
- /* Is readable */
- close(fd);
- proc_pagemap_readable = 1;
}
/* Lock page in physical memory and prevent from swapping. */
}
/* Cannot parse /proc/self/pagemap, no need to log errors everywhere */
- if (!proc_pagemap_readable)
+ if (!phys_addrs_available)
return RTE_BAD_PHYS_ADDR;
/* standard page size */
* the pfn (page frame number) are bits 0-54 (see
* pagemap.txt in linux Documentation)
*/
+ if ((page & 0x7fffffffffffffULL) == 0)
+ return RTE_BAD_PHYS_ADDR;
+
physaddr = ((page & 0x7fffffffffffffULL) * page_size)
+ ((unsigned long)virtaddr % page_size);
static int
find_physaddrs(struct hugepage_file *hugepg_tbl, struct hugepage_info *hpi)
{
- unsigned i;
+ unsigned int i;
phys_addr_t addr;
for (i = 0; i < hpi->num_pages[0]; i++) {
return 0;
}
+/*
+ * For each hugepage in hugepg_tbl, fill the physaddr value sequentially.
+ */
+static int
+set_physaddrs(struct hugepage_file *hugepg_tbl, struct hugepage_info *hpi)
+{
+ unsigned int i;
+ static phys_addr_t addr;
+
+ for (i = 0; i < hpi->num_pages[0]; i++) {
+ hugepg_tbl[i].physaddr = addr;
+ addr += hugepg_tbl[i].size;
+ }
+ return 0;
+}
+
/*
* Check whether address-space layout randomization is enabled in
* the kernel. This is important for multi-process as it can prevent
}
do {
addr = mmap(addr,
- (*size) + hugepage_sz, PROT_READ, MAP_PRIVATE, fd, 0);
+ (*size) + hugepage_sz, PROT_READ,
+#ifdef RTE_ARCH_PPC_64
+ MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB,
+#else
+ MAP_PRIVATE,
+#endif
+ fd, 0);
if (addr == MAP_FAILED)
*size -= hugepage_sz;
} while (addr == MAP_FAILED && *size > 0);
cmp_physaddr(const void *a, const void *b)
{
#ifndef RTE_ARCH_PPC_64
- const struct hugepage_file *p1 = (const struct hugepage_file *)a;
- const struct hugepage_file *p2 = (const struct hugepage_file *)b;
+ const struct hugepage_file *p1 = a;
+ const struct hugepage_file *p2 = b;
#else
/* PowerPC needs memory sorted in reverse order from x86 */
- const struct hugepage_file *p1 = (const struct hugepage_file *)b;
- const struct hugepage_file *p2 = (const struct hugepage_file *)a;
+ const struct hugepage_file *p1 = b;
+ const struct hugepage_file *p2 = a;
#endif
if (p1->physaddr < p2->physaddr)
return -1;
int nr_hugefiles, nr_hugepages = 0;
void *addr;
- test_proc_pagemap_readable();
+ test_phys_addrs_available();
memset(used_hp, 0, sizeof(used_hp));
continue;
}
- /* find physical addresses and sockets for each hugepage */
- if (find_physaddrs(&tmp_hp[hp_offset], hpi) < 0){
- RTE_LOG(DEBUG, EAL, "Failed to find phys addr for %u MB pages\n",
- (unsigned)(hpi->hugepage_sz / 0x100000));
- goto fail;
+ if (phys_addrs_available) {
+ /* find physical addresses for each hugepage */
+ if (find_physaddrs(&tmp_hp[hp_offset], hpi) < 0) {
+ RTE_LOG(DEBUG, EAL, "Failed to find phys addr "
+ "for %u MB pages\n",
+ (unsigned int)(hpi->hugepage_sz / 0x100000));
+ goto fail;
+ }
+ } else {
+ /* set physical addresses for each hugepage */
+ if (set_physaddrs(&tmp_hp[hp_offset], hpi) < 0) {
+ RTE_LOG(DEBUG, EAL, "Failed to set phys addr "
+ "for %u MB pages\n",
+ (unsigned int)(hpi->hugepage_sz / 0x100000));
+ goto fail;
+ }
}
if (find_numasocket(&tmp_hp[hp_offset], hpi) < 0){
struct hugepage_file *hp = NULL;
unsigned num_hp = 0;
unsigned i, s = 0; /* s used to track the segment number */
- off_t size;
+ unsigned max_seg = RTE_MAX_MEMSEG;
+ off_t size = 0;
int fd, fd_zero = -1, fd_hugepage = -1;
if (aslr_enabled() > 0) {
"into secondary processes\n");
}
- test_proc_pagemap_readable();
+ test_phys_addrs_available();
if (internal_config.xen_dom0_support) {
#ifdef RTE_LIBRTE_XEN_DOM0
* use mmap to get identical addresses as the primary process.
*/
base_addr = mmap(mcfg->memseg[s].addr, mcfg->memseg[s].len,
- PROT_READ, MAP_PRIVATE, fd_zero, 0);
+ PROT_READ,
+#ifdef RTE_ARCH_PPC_64
+ MAP_PRIVATE | MAP_ANONYMOUS | MAP_HUGETLB,
+#else
+ MAP_PRIVATE,
+#endif
+ fd_zero, 0);
if (base_addr == MAP_FAILED ||
base_addr != mcfg->memseg[s].addr) {
- RTE_LOG(ERR, EAL, "Could not mmap %llu bytes "
- "in /dev/zero to requested address [%p]: '%s'\n",
- (unsigned long long)mcfg->memseg[s].len,
- mcfg->memseg[s].addr, strerror(errno));
+ max_seg = s;
+ if (base_addr != MAP_FAILED) {
+ /* errno is stale, don't use */
+ RTE_LOG(ERR, EAL, "Could not mmap %llu bytes "
+ "in /dev/zero at [%p], got [%p] - "
+ "please use '--base-virtaddr' option\n",
+ (unsigned long long)mcfg->memseg[s].len,
+ mcfg->memseg[s].addr, base_addr);
+ munmap(base_addr, mcfg->memseg[s].len);
+ } else {
+ RTE_LOG(ERR, EAL, "Could not mmap %llu bytes "
+ "in /dev/zero at [%p]: '%s'\n",
+ (unsigned long long)mcfg->memseg[s].len,
+ mcfg->memseg[s].addr, strerror(errno));
+ }
if (aslr_enabled() > 0) {
RTE_LOG(ERR, EAL, "It is recommended to "
"disable ASLR in the kernel "
return 0;
error:
- s = 0;
- while (s < RTE_MAX_MEMSEG && mcfg->memseg[s].len > 0) {
- munmap(mcfg->memseg[s].addr, mcfg->memseg[s].len);
- s++;
- }
+ for (i = 0; i < max_seg && mcfg->memseg[i].len > 0; i++)
+ munmap(mcfg->memseg[i].addr, mcfg->memseg[i].len);
if (hp != NULL && hp != MAP_FAILED)
munmap(hp, size);
if (fd_zero >= 0)
close(fd_hugepage);
return -1;
}
+
+bool
+rte_eal_using_phys_addrs(void)
+{
+ return phys_addrs_available;
+}
git.droids-corp.org / dpdk.git / blobdiff