/* create the ring */
struct odp_ring *odp_ring_create(const char *name, unsigned count,
int socket_id, unsigned flags)
{
char mz_name[ODP_MEMZONE_NAMESIZE];
struct odp_ring *r;
struct odp_tailq_entry *te;
const struct odp_mm_district *mz;
ssize_t ring_size;
int mz_flags = 0;
struct odp_ring_list *ring_list = NULL;
ring_list = ODP_TAILQ_CAST(odp_ring_tailq.head, odp_ring_list);
ring_size = odp_ring_get_memsize(count);
if (ring_size < 0) {
odp_err = ring_size;
return NULL;
}
te = malloc(sizeof(*te));
if (te == NULL) {
ODP_PRINT("Cannot reserve memory for tailq\n");
odp_err = ENOMEM;
return NULL;
}
snprintf(mz_name, sizeof(mz_name), "%s%s", ODP_RING_MZ_PREFIX, name);
odp_rwlock_write_lock(ODP_TAILQ_RWLOCK);
/* reserve a memory zone for this ring. If we can't get odp_config or
* we are secondary process, the mm_district_reserve function will set
* odp_err for us appropriately-hence no check in this this function */
mz = odp_mm_district_reserve(mz_name, mz_name, ring_size,
socket_id, mz_flags);
if (mz != NULL) {
r = mz->addr;
/* no need to check return value here, we already checked the
* arguments above */
odp_ring_init(r, name, count, flags);
te->data = (void *)r;
TAILQ_INSERT_TAIL(ring_list, te, next);
} else {
r = NULL;
ODP_PRINT("Cannot reserve memory\n");
free(te);
}
odp_rwlock_write_unlock(ODP_TAILQ_RWLOCK);
return r;
}
odp_shm_t odp_shm_reserve(const char *name, uint64_t size, uint64_t align,
uint32_t flags)
{
uint32_t i;
odp_shm_block_t *block;
void *addr;
int fd = -1;
int map_flag = MAP_SHARED;
/* If already exists: O_EXCL: error, O_TRUNC: truncate to zero */
int oflag = O_RDWR | O_CREAT | O_TRUNC;
uint64_t alloc_size;
uint64_t page_sz;
#ifdef MAP_HUGETLB
uint64_t huge_sz;
int need_huge_page = 0;
uint64_t alloc_hp_size;
#endif
const struct odp_mm_district *zone = NULL;
char memdistrict_name[ODP_SHM_NAME_LEN + 8];
page_sz = odp_sys_page_size();
alloc_size = size + align;
#ifdef MAP_HUGETLB
huge_sz = odp_sys_huge_page_size();
need_huge_page = (huge_sz && alloc_size > page_sz);
/* munmap for huge pages requires sizes round up by page */
alloc_hp_size = (size + align + (huge_sz - 1)) & (-huge_sz);
#endif
if (flags & ODP_SHM_PROC) {
/* Creates a file to /dev/shm */
fd = shm_open(name, oflag,
S_IRUSR | S_IWUSR | S_IRGRP | S_IROTH);
if (fd == -1) {
ODP_DBG("%s: shm_open failed.\n", name);
return ODP_SHM_INVALID;
}
} else if (flags & ODP_SHM_MONOPOLIZE_CNTNUS_PHY) {
int pid = getpid();
snprintf(memdistrict_name, sizeof(memdistrict_name),
"%s_%d", name, pid);
zone = odp_mm_district_reserve(memdistrict_name, name,
alloc_size, 0,
ODP_MEMZONE_2MB |
ODP_MEMZONE_SIZE_HINT_ONLY);
if (zone == NULL) {
ODP_DBG("odp_mm_district_reseve %s failed.\n", name);
return ODP_SHM_INVALID;
}
} else if (flags & ODP_SHM_SHARE_CNTNUS_PHY) {
zone = odp_mm_district_reserve(name, name,
alloc_size, 0,
ODP_MEMZONE_2MB |
ODP_MEMZONE_SIZE_HINT_ONLY);
if (zone == NULL) {
ODP_DBG("odp_mm_district_reseve %s failed.\n", name);
return ODP_SHM_INVALID;
}
} else {
map_flag |= MAP_ANONYMOUS;
}
odp_spinlock_lock(&odp_shm_tbl->lock);
if (find_block(name, NULL)) {
/* Found a block with the same name */
odp_spinlock_unlock(&odp_shm_tbl->lock);
ODP_DBG("name %s already used.\n", name);
return ODP_SHM_INVALID;
}
for (i = 0; i < ODP_CONFIG_SHM_BLOCKS; i++)
if (odp_shm_tbl->block[i].addr == NULL)
/* Found free block */
break;
if (i > ODP_CONFIG_SHM_BLOCKS - 1) {
/* Table full */
odp_spinlock_unlock(&odp_shm_tbl->lock);
ODP_DBG("%s: no more blocks.\n", name);
return ODP_SHM_INVALID;
}
block = &odp_shm_tbl->block[i];
block->hdl = to_handle(i);
addr = MAP_FAILED;
#ifdef MAP_HUGETLB
/* Try first huge pages */
if (need_huge_page) {
if ((flags & ODP_SHM_PROC) &&
(ftruncate(fd, alloc_hp_size) == -1)) {
odp_spinlock_unlock(&odp_shm_tbl->lock);
ODP_DBG("%s: ftruncate huge pages failed.\n", name);
return ODP_SHM_INVALID;
}
addr = mmap(NULL, alloc_hp_size, PROT_READ | PROT_WRITE,
map_flag | MAP_HUGETLB, fd, 0);
if (addr == MAP_FAILED) {
ODP_DBG(" %s: No huge pages, fall back to normal pages,"
"check: /proc/sys/vm/nr_hugepages.\n",
name);
} else {
block->alloc_size = alloc_hp_size;
block->huge = 1;
block->page_sz = huge_sz;
}
}
#endif
if (flags & ODP_SHM_MONOPOLIZE_CNTNUS_PHY ||
flags & ODP_SHM_SHARE_CNTNUS_PHY)
addr = zone->addr;
/* Use normal pages for small or failed huge page allocations */
if (addr == MAP_FAILED) {
if ((flags & ODP_SHM_PROC) &&
(ftruncate(fd, alloc_size) == -1)) {
odp_spinlock_unlock(&odp_shm_tbl->lock);
ODP_ERR("%s: ftruncate failed.\n", name);
return ODP_SHM_INVALID;
}
addr = mmap(NULL, alloc_size, PROT_READ | PROT_WRITE,
map_flag, fd, 0);
if (addr == MAP_FAILED) {
odp_spinlock_unlock(&odp_shm_tbl->lock);
ODP_DBG("%s mmap failed.\n", name);
return ODP_SHM_INVALID;
}
block->alloc_size = alloc_size;
block->huge = 0;
block->page_sz = page_sz;
}
if (flags & ODP_SHM_MONOPOLIZE_CNTNUS_PHY ||
flags & ODP_SHM_SHARE_CNTNUS_PHY) {
block->alloc_size = alloc_size;
block->huge = 1;
block->page_sz = ODP_MEMZONE_2MB;
block->addr_orig = addr;
/* move to correct alignment */
addr = ODP_ALIGN_ROUNDUP_PTR(zone->addr, align);
strncpy(block->name, name, ODP_SHM_NAME_LEN - 1);
block->name[ODP_SHM_NAME_LEN - 1] = 0;
block->size = size;
block->align = align;
block->flags = flags;
block->fd = -1;
block->addr = addr;
} else {
block->addr_orig = addr;
/* move to correct alignment */
addr = ODP_ALIGN_ROUNDUP_PTR(addr, align);
strncpy(block->name, name, ODP_SHM_NAME_LEN - 1);
block->name[ODP_SHM_NAME_LEN - 1] = 0;
block->size = size;
block->align = align;
block->flags = flags;
block->fd = fd;
block->addr = addr;
}
odp_spinlock_unlock(&odp_shm_tbl->lock);
return block->hdl;
}