/*-
* BSD LICENSE
- *
+ *
* 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
* 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
* * 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
#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>
static uint64_t baseaddr_offset;
+static unsigned proc_pagemap_readable;
+
#define RANDOMIZE_VA_SPACE_FILE "/proc/sys/kernel/randomize_va_space"
/* Lock page in physical memory and prevent from swapping. */
uint64_t page, physaddr;
unsigned long virt_pfn;
int page_size;
+ off_t offset;
+
+ /* Cannot parse /proc/self/pagemap, no need to log errors everywhere */
+ if (!proc_pagemap_readable)
+ return RTE_BAD_PHYS_ADDR;
/* standard page size */
page_size = getpagesize();
return RTE_BAD_PHYS_ADDR;
}
- off_t offset;
virt_pfn = (unsigned long)virtaddr / page_size;
offset = sizeof(uint64_t) * virt_pfn;
if (lseek(fd, offset, SEEK_SET) == (off_t) -1) {
}
/*
- * Try to mmap *size bytes in /dev/zero. If it is succesful, return the
+ * Try to mmap *size bytes in /dev/zero. If it is successful, return the
* pointer to the mmap'd area and keep *size unmodified. Else, retry
* with a smaller zone: decrease *size by hugepage_sz until it reaches
* 0. In this case, return NULL. Note: this function returns an address
}
else addr = NULL;
- RTE_LOG(INFO, EAL, "Ask a virtual area of 0x%zx bytes\n", *size);
+ RTE_LOG(DEBUG, EAL, "Ask a virtual area of 0x%zx bytes\n", *size);
fd = open("/dev/zero", O_RDONLY);
if (fd < 0){
if (addr == MAP_FAILED) {
close(fd);
- RTE_LOG(INFO, EAL, "Cannot get a virtual area\n");
+ RTE_LOG(ERR, EAL, "Cannot get a virtual area: %s\n",
+ strerror(errno));
return NULL;
}
aligned_addr &= (~(hugepage_sz - 1));
addr = (void *)(aligned_addr);
- RTE_LOG(INFO, EAL, "Virtual area found at %p (size = 0x%zx)\n",
+ RTE_LOG(DEBUG, EAL, "Virtual area found at %p (size = 0x%zx)\n",
addr, *size);
/* increment offset */
#endif
for (i = 0; i < hpi->num_pages[0]; i++) {
- size_t hugepage_sz = hpi->hugepage_sz;
+ uint64_t hugepage_sz = hpi->hugepage_sz;
if (orig) {
hugepg_tbl[i].file_id = i;
#endif
hugepg_tbl[i].filepath[sizeof(hugepg_tbl[i].filepath) - 1] = '\0';
}
-#ifndef RTE_ARCH_X86_64
- /* for 32-bit systems, don't remap 1G pages, just reuse original
- * map address as final map address.
+#ifndef RTE_ARCH_64
+ /* for 32-bit systems, don't remap 1G and 16G pages, just reuse
+ * original map address as final map address.
*/
- else if (hugepage_sz == RTE_PGSIZE_1G){
+ else if ((hugepage_sz == RTE_PGSIZE_1G)
+ || (hugepage_sz == RTE_PGSIZE_16G)) {
hugepg_tbl[i].final_va = hugepg_tbl[i].orig_va;
hugepg_tbl[i].orig_va = NULL;
continue;
* physical block: count the number of
* contiguous physical pages. */
for (j = i+1; j < hpi->num_pages[0] ; j++) {
+#ifdef RTE_ARCH_PPC_64
+ /* The physical addresses are sorted in
+ * descending order on PPC64 */
+ if (hugepg_tbl[j].physaddr !=
+ hugepg_tbl[j-1].physaddr - hugepage_sz)
+ break;
+#else
if (hugepg_tbl[j].physaddr !=
hugepg_tbl[j-1].physaddr + hugepage_sz)
break;
+#endif
}
num_pages = j - i;
vma_len = num_pages * hugepage_sz;
while (i < hpi->num_pages[0]) {
-#ifndef RTE_ARCH_X86_64
- /* for 32-bit systems, don't remap 1G pages, just reuse original
- * map address as final map address.
+#ifndef RTE_ARCH_64
+ /* for 32-bit systems, don't remap 1G pages and 16G pages,
+ * just reuse original map address as final map address.
*/
- if (hugepage_sz == RTE_PGSIZE_1G){
+ if ((hugepage_sz == RTE_PGSIZE_1G)
+ || (hugepage_sz == RTE_PGSIZE_16G)) {
hugepg_tbl[i].final_va = hugepg_tbl[i].orig_va;
hugepg_tbl[i].orig_va = NULL;
i++;
* physical block: count the number of
* contiguous physical pages. */
for (j = i+1; j < hpi->num_pages[0] ; j++) {
- if (hugepg_tbl[j].physaddr != hugepg_tbl[j-1].physaddr + hugepage_sz)
+#ifdef RTE_ARCH_PPC_64
+ /* The physical addresses are sorted in descending
+ * order on PPC64 */
+ if (hugepg_tbl[j].physaddr !=
+ hugepg_tbl[j-1].physaddr - hugepage_sz)
+ break;
+#else
+ if (hugepg_tbl[j].physaddr !=
+ hugepg_tbl[j-1].physaddr + hugepage_sz)
break;
+#endif
}
num_pages = j - i;
vma_len = num_pages * hugepage_sz;
return -1;
}
- rte_snprintf(hugepg_tbl[page_idx].filepath, MAX_HUGEPAGE_PATH, "%s",
+ snprintf(hugepg_tbl[page_idx].filepath, MAX_HUGEPAGE_PATH, "%s",
filepath);
physaddr = rte_mem_virt2phy(vma_addr);
f = fopen("/proc/self/numa_maps", "r");
if (f == NULL) {
- RTE_LOG(INFO, EAL, "cannot open /proc/self/numa_maps,"
+ RTE_LOG(NOTICE, EAL, "cannot open /proc/self/numa_maps,"
" consider that all memory is in socket_id 0\n");
return 0;
}
- rte_snprintf(hugedir_str, sizeof(hugedir_str),
- "%s/", hpi->hugedir);
+ snprintf(hugedir_str, sizeof(hugedir_str),
+ "%s/%s", hpi->hugedir, internal_config.hugefile_prefix);
/* parse numa map */
while (fgets(buf, sizeof(buf), f) != NULL) {
}
/*
- * Sort the hugepg_tbl by physical address (lower addresses first). We
- * use a slow algorithm, but we won't have millions of pages, and this
- * is only done at init time.
+ * Sort the hugepg_tbl by physical address (lower addresses first on x86,
+ * higher address first on powerpc). We use a slow algorithm, but we won't
+ * have millions of pages, and this is only done at init time.
*/
static int
sort_by_physaddr(struct hugepage_file *hugepg_tbl, struct hugepage_info *hpi)
{
unsigned i, j;
- int smallest_idx;
- uint64_t smallest_addr;
+ int compare_idx;
+ uint64_t compare_addr;
struct hugepage_file tmp;
for (i = 0; i < hpi->num_pages[0]; i++) {
- smallest_addr = 0;
- smallest_idx = -1;
+ compare_addr = 0;
+ compare_idx = -1;
/*
* browse all entries starting at 'i', and find the
*/
for (j=i; j< hpi->num_pages[0]; j++) {
- if (smallest_addr == 0 ||
- hugepg_tbl[j].physaddr < smallest_addr) {
- smallest_addr = hugepg_tbl[j].physaddr;
- smallest_idx = j;
+ if (compare_addr == 0 ||
+#ifdef RTE_ARCH_PPC_64
+ hugepg_tbl[j].physaddr > compare_addr) {
+#else
+ hugepg_tbl[j].physaddr < compare_addr) {
+#endif
+ compare_addr = hugepg_tbl[j].physaddr;
+ compare_idx = j;
}
}
/* should not happen */
- if (smallest_idx == -1) {
+ if (compare_idx == -1) {
RTE_LOG(ERR, EAL, "%s(): error in physaddr sorting\n", __func__);
return -1;
}
/* swap the 2 entries in the table */
- memcpy(&tmp, &hugepg_tbl[smallest_idx], sizeof(struct hugepage_file));
- memcpy(&hugepg_tbl[smallest_idx], &hugepg_tbl[i],
- sizeof(struct hugepage_file));
+ memcpy(&tmp, &hugepg_tbl[compare_idx],
+ sizeof(struct hugepage_file));
+ memcpy(&hugepg_tbl[compare_idx], &hugepg_tbl[i],
+ sizeof(struct hugepage_file));
memcpy(&hugepg_tbl[i], &tmp, sizeof(struct hugepage_file));
}
return 0;
size += hpi->hugepage_sz * hpi->num_pages[socket];
}
- return (size);
+ return size;
}
/*
0x100000);
available = requested -
((unsigned) (memory[socket] / 0x100000));
- RTE_LOG(INFO, EAL, "Not enough memory available on socket %u! "
+ RTE_LOG(ERR, EAL, "Not enough memory available on socket %u! "
"Requested: %uMB, available: %uMB\n", socket,
requested, available);
return -1;
if (total_mem > 0) {
requested = (unsigned) (internal_config.memory / 0x100000);
available = requested - (unsigned) (total_mem / 0x100000);
- RTE_LOG(INFO, EAL, "Not enough memory available! Requested: %uMB,"
+ RTE_LOG(ERR, EAL, "Not enough memory available! Requested: %uMB,"
" available: %uMB\n", requested, available);
return -1;
}
/* hugetlbfs can be disabled */
if (internal_config.no_hugetlbfs) {
- addr = malloc(internal_config.memory);
+ addr = mmap(NULL, internal_config.memory, PROT_READ | PROT_WRITE,
+ MAP_PRIVATE | MAP_ANONYMOUS, 0, 0);
+ if (addr == MAP_FAILED) {
+ RTE_LOG(ERR, EAL, "%s: mmap() failed: %s\n", __func__,
+ strerror(errno));
+ return -1;
+ }
mcfg->memseg[0].phys_addr = (phys_addr_t)(uintptr_t)addr;
mcfg->memseg[0].addr = addr;
+ mcfg->memseg[0].hugepage_sz = RTE_PGSIZE_4K;
mcfg->memseg[0].len = internal_config.memory;
- mcfg->memseg[0].socket_id = SOCKET_ID_ANY;
+ mcfg->memseg[0].socket_id = 0;
return 0;
}
int socket = tmp_hp[i].socket_id;
/* find a hugepage info with right size and increment num_pages */
- for (j = 0; j < (int) internal_config.num_hugepage_sizes; j++) {
+ const int nb_hpsizes = RTE_MIN(MAX_HUGEPAGE_SIZES,
+ (int)internal_config.num_hugepage_sizes);
+ for (j = 0; j < nb_hpsizes; j++) {
if (tmp_hp[i].size ==
internal_config.hugepage_info[j].hugepage_sz) {
#ifdef RTE_EAL_SINGLE_FILE_SEGMENTS
for (i = 0; i < (int) internal_config.num_hugepage_sizes; i++) {
for (j = 0; j < RTE_MAX_NUMA_NODES; j++) {
if (used_hp[i].num_pages[j] > 0) {
- RTE_LOG(INFO, EAL,
- "Requesting %u pages of size %uMB"
- " from socket %i\n",
- used_hp[i].num_pages[j],
- (unsigned)
- (used_hp[i].hugepage_sz / 0x100000),
- j);
+ RTE_LOG(DEBUG, EAL,
+ "Requesting %u pages of size %uMB"
+ " from socket %i\n",
+ used_hp[i].num_pages[j],
+ (unsigned)
+ (used_hp[i].hugepage_sz / 0x100000),
+ j);
}
}
}
new_memseg = 1;
else if (hugepage[i].size != hugepage[i-1].size)
new_memseg = 1;
+
+#ifdef RTE_ARCH_PPC_64
+ /* On PPC64 architecture, the mmap always start from higher
+ * virtual address to lower address. Here, both the physical
+ * address and virtual address are in descending order */
+ else if ((hugepage[i-1].physaddr - hugepage[i].physaddr) !=
+ hugepage[i].size)
+ new_memseg = 1;
+ else if (((unsigned long)hugepage[i-1].final_va -
+ (unsigned long)hugepage[i].final_va) != hugepage[i].size)
+ new_memseg = 1;
+#else
else if ((hugepage[i].physaddr - hugepage[i-1].physaddr) !=
hugepage[i].size)
new_memseg = 1;
else if (((unsigned long)hugepage[i].final_va -
(unsigned long)hugepage[i-1].final_va) != hugepage[i].size)
new_memseg = 1;
+#endif
if (new_memseg) {
j += 1;
}
/* continuation of previous memseg */
else {
+#ifdef RTE_ARCH_PPC_64
+ /* Use the phy and virt address of the last page as segment
+ * address for IBM Power architecture */
+ mcfg->memseg[j].phys_addr = hugepage[i].physaddr;
+ mcfg->memseg[j].addr = hugepage[i].final_va;
+#endif
mcfg->memseg[j].len += mcfg->memseg[j].hugepage_sz;
}
hugepage[i].memseg_id = j;
"of memory.\n",
i, nr_hugefiles, RTE_STR(CONFIG_RTE_MAX_MEMSEG),
RTE_MAX_MEMSEG);
- return (-ENOMEM);
+ return -ENOMEM;
}
return 0;
return 0;
}
+static int
+test_proc_pagemap_readable(void)
+{
+ int fd = open("/proc/self/pagemap", O_RDONLY);
+
+ if (fd < 0)
+ return 0;
+ /* Is readable */
+ close(fd);
+
+ return 1;
+}
/* init memory subsystem */
int
rte_eal_memory_init(void)
{
RTE_LOG(INFO, EAL, "Setting up memory...\n");
+
+ proc_pagemap_readable = test_proc_pagemap_readable();
+ if (!proc_pagemap_readable)
+ RTE_LOG(ERR, EAL,
+ "Cannot open /proc/self/pagemap: %s. "
+ "virt2phys address translation will not work\n",
+ strerror(errno));
+
const int retval = rte_eal_process_type() == RTE_PROC_PRIMARY ?
rte_eal_hugepage_init() :
rte_eal_hugepage_attach();
git.droids-corp.org / dpdk.git / blobdiff