+
+/*
+ * Calculate maximum amount of memory required to store given number of objects.
+ */
+size_t
+rte_mempool_xmem_size(uint32_t elt_num, size_t total_elt_sz, uint32_t pg_shift,
+ unsigned int flags)
+{
+ size_t obj_per_page, pg_num, pg_sz;
+ unsigned int mask;
+
+ mask = MEMPOOL_F_CAPA_BLK_ALIGNED_OBJECTS | MEMPOOL_F_CAPA_PHYS_CONTIG;
+ if ((flags & mask) == mask)
+ /* alignment need one additional object */
+ elt_num += 1;
+
+ if (total_elt_sz == 0)
+ return 0;
+
+ if (pg_shift == 0)
+ return total_elt_sz * elt_num;
+
+ pg_sz = (size_t)1 << pg_shift;
+ obj_per_page = pg_sz / total_elt_sz;
+ if (obj_per_page == 0)
+ return RTE_ALIGN_CEIL(total_elt_sz, pg_sz) * elt_num;
+
+ pg_num = (elt_num + obj_per_page - 1) / obj_per_page;
+ return pg_num << pg_shift;
+}
+
+/*
+ * Calculate how much memory would be actually required with the
+ * given memory footprint to store required number of elements.
+ */
+ssize_t
+rte_mempool_xmem_usage(__rte_unused void *vaddr, uint32_t elt_num,
+ size_t total_elt_sz, const rte_iova_t iova[], uint32_t pg_num,
+ uint32_t pg_shift, unsigned int flags)
+{
+ uint32_t elt_cnt = 0;
+ rte_iova_t start, end;
+ uint32_t iova_idx;
+ size_t pg_sz = (size_t)1 << pg_shift;
+ unsigned int mask;
+
+ mask = MEMPOOL_F_CAPA_BLK_ALIGNED_OBJECTS | MEMPOOL_F_CAPA_PHYS_CONTIG;
+ if ((flags & mask) == mask)
+ /* alignment need one additional object */
+ elt_num += 1;
+
+ /* if iova is NULL, assume contiguous memory */
+ if (iova == NULL) {
+ start = 0;
+ end = pg_sz * pg_num;
+ iova_idx = pg_num;
+ } else {
+ start = iova[0];
+ end = iova[0] + pg_sz;
+ iova_idx = 1;
+ }
+ while (elt_cnt < elt_num) {
+
+ if (end - start >= total_elt_sz) {
+ /* enough contiguous memory, add an object */
+ start += total_elt_sz;
+ elt_cnt++;
+ } else if (iova_idx < pg_num) {
+ /* no room to store one obj, add a page */
+ if (end == iova[iova_idx]) {
+ end += pg_sz;
+ } else {
+ start = iova[iova_idx];
+ end = iova[iova_idx] + pg_sz;
+ }
+ iova_idx++;
+
+ } else {
+ /* no more page, return how many elements fit */
+ return -(size_t)elt_cnt;
+ }
+ }
+
+ return (size_t)iova_idx << pg_shift;
+}
+
+/* free a memchunk allocated with rte_memzone_reserve() */
+static void
+rte_mempool_memchunk_mz_free(__rte_unused struct rte_mempool_memhdr *memhdr,
+ void *opaque)
+{
+ const struct rte_memzone *mz = opaque;
+ rte_memzone_free(mz);
+}
+
+/* Free memory chunks used by a mempool. Objects must be in pool */
+static void
+rte_mempool_free_memchunks(struct rte_mempool *mp)
+{
+ struct rte_mempool_memhdr *memhdr;
+ void *elt;
+
+ while (!STAILQ_EMPTY(&mp->elt_list)) {
+ rte_mempool_ops_dequeue_bulk(mp, &elt, 1);
+ (void)elt;
+ STAILQ_REMOVE_HEAD(&mp->elt_list, next);
+ mp->populated_size--;
+ }
+
+ while (!STAILQ_EMPTY(&mp->mem_list)) {
+ memhdr = STAILQ_FIRST(&mp->mem_list);
+ STAILQ_REMOVE_HEAD(&mp->mem_list, next);
+ if (memhdr->free_cb != NULL)
+ memhdr->free_cb(memhdr, memhdr->opaque);
+ rte_free(memhdr);
+ mp->nb_mem_chunks--;
+ }
+}
+
+/* Add objects in the pool, using a physically contiguous memory
+ * zone. Return the number of objects added, or a negative value
+ * on error.
+ */
+int
+rte_mempool_populate_iova(struct rte_mempool *mp, char *vaddr,
+ rte_iova_t iova, size_t len, rte_mempool_memchunk_free_cb_t *free_cb,
+ void *opaque)
+{
+ unsigned total_elt_sz;
+ unsigned i = 0;
+ size_t off;
+ struct rte_mempool_memhdr *memhdr;
+ int ret;
+
+ /* create the internal ring if not already done */
+ if ((mp->flags & MEMPOOL_F_POOL_CREATED) == 0) {
+ ret = rte_mempool_ops_alloc(mp);
+ if (ret != 0)
+ return ret;
+ mp->flags |= MEMPOOL_F_POOL_CREATED;
+ }
+
+ /* Notify memory area to mempool */
+ ret = rte_mempool_ops_register_memory_area(mp, vaddr, iova, len);
+ if (ret != -ENOTSUP && ret < 0)
+ return ret;
+
+ /* mempool is already populated */
+ if (mp->populated_size >= mp->size)
+ return -ENOSPC;
+
+ total_elt_sz = mp->header_size + mp->elt_size + mp->trailer_size;
+
+ /* Detect pool area has sufficient space for elements */
+ if (mp->flags & MEMPOOL_F_CAPA_PHYS_CONTIG) {
+ if (len < total_elt_sz * mp->size) {
+ RTE_LOG(ERR, MEMPOOL,
+ "pool area %" PRIx64 " not enough\n",
+ (uint64_t)len);
+ return -ENOSPC;
+ }
+ }
+
+ memhdr = rte_zmalloc("MEMPOOL_MEMHDR", sizeof(*memhdr), 0);
+ if (memhdr == NULL)
+ return -ENOMEM;
+
+ memhdr->mp = mp;
+ memhdr->addr = vaddr;
+ memhdr->iova = iova;
+ memhdr->len = len;
+ memhdr->free_cb = free_cb;
+ memhdr->opaque = opaque;
+
+ if (mp->flags & MEMPOOL_F_CAPA_BLK_ALIGNED_OBJECTS)
+ /* align object start address to a multiple of total_elt_sz */
+ off = total_elt_sz - ((uintptr_t)vaddr % total_elt_sz);
+ else if (mp->flags & MEMPOOL_F_NO_CACHE_ALIGN)
+ off = RTE_PTR_ALIGN_CEIL(vaddr, 8) - vaddr;
+ else
+ off = RTE_PTR_ALIGN_CEIL(vaddr, RTE_CACHE_LINE_SIZE) - vaddr;
+
+ while (off + total_elt_sz <= len && mp->populated_size < mp->size) {
+ off += mp->header_size;
+ if (iova == RTE_BAD_IOVA)
+ mempool_add_elem(mp, (char *)vaddr + off,
+ RTE_BAD_IOVA);
+ else
+ mempool_add_elem(mp, (char *)vaddr + off, iova + off);
+ off += mp->elt_size + mp->trailer_size;
+ i++;
+ }
+
+ /* not enough room to store one object */
+ if (i == 0)
+ return -EINVAL;
+
+ STAILQ_INSERT_TAIL(&mp->mem_list, memhdr, next);
+ mp->nb_mem_chunks++;
+ return i;
+}
+
+int
+rte_mempool_populate_phys(struct rte_mempool *mp, char *vaddr,
+ phys_addr_t paddr, size_t len, rte_mempool_memchunk_free_cb_t *free_cb,
+ void *opaque)
+{
+ return rte_mempool_populate_iova(mp, vaddr, paddr, len, free_cb, opaque);
+}
+
+/* Add objects in the pool, using a table of physical pages. Return the
+ * number of objects added, or a negative value on error.
+ */
+int
+rte_mempool_populate_iova_tab(struct rte_mempool *mp, char *vaddr,
+ const rte_iova_t iova[], uint32_t pg_num, uint32_t pg_shift,
+ rte_mempool_memchunk_free_cb_t *free_cb, void *opaque)
+{
+ uint32_t i, n;
+ int ret, cnt = 0;
+ size_t pg_sz = (size_t)1 << pg_shift;
+
+ /* mempool must not be populated */
+ if (mp->nb_mem_chunks != 0)
+ return -EEXIST;
+
+ if (mp->flags & MEMPOOL_F_NO_PHYS_CONTIG)
+ return rte_mempool_populate_iova(mp, vaddr, RTE_BAD_IOVA,
+ pg_num * pg_sz, free_cb, opaque);
+
+ for (i = 0; i < pg_num && mp->populated_size < mp->size; i += n) {
+
+ /* populate with the largest group of contiguous pages */
+ for (n = 1; (i + n) < pg_num &&
+ iova[i + n - 1] + pg_sz == iova[i + n]; n++)
+ ;
+
+ ret = rte_mempool_populate_iova(mp, vaddr + i * pg_sz,
+ iova[i], n * pg_sz, free_cb, opaque);
+ if (ret < 0) {
+ rte_mempool_free_memchunks(mp);
+ return ret;
+ }
+ /* no need to call the free callback for next chunks */
+ free_cb = NULL;
+ cnt += ret;
+ }
+ return cnt;
+}
+
+int
+rte_mempool_populate_phys_tab(struct rte_mempool *mp, char *vaddr,
+ const phys_addr_t paddr[], uint32_t pg_num, uint32_t pg_shift,
+ rte_mempool_memchunk_free_cb_t *free_cb, void *opaque)
+{
+ return rte_mempool_populate_iova_tab(mp, vaddr, paddr, pg_num, pg_shift,
+ free_cb, opaque);
+}
+
+/* Populate the mempool with a virtual area. Return the number of
+ * objects added, or a negative value on error.
+ */
+int
+rte_mempool_populate_virt(struct rte_mempool *mp, char *addr,
+ size_t len, size_t pg_sz, rte_mempool_memchunk_free_cb_t *free_cb,
+ void *opaque)
+{
+ rte_iova_t iova;
+ size_t off, phys_len;
+ int ret, cnt = 0;
+
+ /* mempool must not be populated */
+ if (mp->nb_mem_chunks != 0)
+ return -EEXIST;
+ /* address and len must be page-aligned */
+ if (RTE_PTR_ALIGN_CEIL(addr, pg_sz) != addr)
+ return -EINVAL;
+ if (RTE_ALIGN_CEIL(len, pg_sz) != len)
+ return -EINVAL;
+
+ if (mp->flags & MEMPOOL_F_NO_PHYS_CONTIG)
+ return rte_mempool_populate_iova(mp, addr, RTE_BAD_IOVA,
+ len, free_cb, opaque);
+
+ for (off = 0; off + pg_sz <= len &&
+ mp->populated_size < mp->size; off += phys_len) {
+
+ iova = rte_mem_virt2iova(addr + off);
+
+ if (iova == RTE_BAD_IOVA && rte_eal_has_hugepages()) {
+ ret = -EINVAL;
+ goto fail;
+ }
+
+ /* populate with the largest group of contiguous pages */
+ for (phys_len = pg_sz; off + phys_len < len; phys_len += pg_sz) {
+ rte_iova_t iova_tmp;
+
+ iova_tmp = rte_mem_virt2iova(addr + off + phys_len);
+
+ if (iova_tmp != iova + phys_len)
+ break;
+ }
+
+ ret = rte_mempool_populate_iova(mp, addr + off, iova,
+ phys_len, free_cb, opaque);
+ if (ret < 0)
+ goto fail;
+ /* no need to call the free callback for next chunks */
+ free_cb = NULL;
+ cnt += ret;
+ }
+
+ return cnt;
+
+ fail:
+ rte_mempool_free_memchunks(mp);
+ return ret;
+}
+
+/* Default function to populate the mempool: allocate memory in memzones,
+ * and populate them. Return the number of objects added, or a negative
+ * value on error.
+ */
+int
+rte_mempool_populate_default(struct rte_mempool *mp)
+{
+ unsigned int mz_flags = RTE_MEMZONE_1GB|RTE_MEMZONE_SIZE_HINT_ONLY;
+ char mz_name[RTE_MEMZONE_NAMESIZE];
+ const struct rte_memzone *mz;
+ size_t size, total_elt_sz, align, pg_sz, pg_shift;
+ rte_iova_t iova;
+ unsigned mz_id, n;
+ unsigned int mp_flags;
+ int ret;
+
+ /* mempool must not be populated */
+ if (mp->nb_mem_chunks != 0)
+ return -EEXIST;
+
+ /* Get mempool capabilities */
+ mp_flags = 0;
+ ret = rte_mempool_ops_get_capabilities(mp, &mp_flags);
+ if ((ret < 0) && (ret != -ENOTSUP))
+ return ret;
+
+ /* update mempool capabilities */
+ mp->flags |= mp_flags;
+
+ if (rte_eal_has_hugepages()) {
+ pg_shift = 0; /* not needed, zone is physically contiguous */
+ pg_sz = 0;
+ align = RTE_CACHE_LINE_SIZE;
+ } else {
+ pg_sz = getpagesize();
+ pg_shift = rte_bsf32(pg_sz);
+ align = pg_sz;
+ }
+
+ total_elt_sz = mp->header_size + mp->elt_size + mp->trailer_size;
+ for (mz_id = 0, n = mp->size; n > 0; mz_id++, n -= ret) {
+ size = rte_mempool_xmem_size(n, total_elt_sz, pg_shift,
+ mp->flags);
+
+ ret = snprintf(mz_name, sizeof(mz_name),
+ RTE_MEMPOOL_MZ_FORMAT "_%d", mp->name, mz_id);
+ if (ret < 0 || ret >= (int)sizeof(mz_name)) {
+ ret = -ENAMETOOLONG;
+ goto fail;
+ }
+
+ mz = rte_memzone_reserve_aligned(mz_name, size,
+ mp->socket_id, mz_flags, align);
+ /* not enough memory, retry with the biggest zone we have */
+ if (mz == NULL)
+ mz = rte_memzone_reserve_aligned(mz_name, 0,
+ mp->socket_id, mz_flags, align);
+ if (mz == NULL) {
+ ret = -rte_errno;
+ goto fail;
+ }
+
+ if (mp->flags & MEMPOOL_F_NO_PHYS_CONTIG)
+ iova = RTE_BAD_IOVA;
+ else
+ iova = mz->iova;
+
+ if (rte_eal_has_hugepages())
+ ret = rte_mempool_populate_iova(mp, mz->addr,
+ iova, mz->len,
+ rte_mempool_memchunk_mz_free,
+ (void *)(uintptr_t)mz);
+ else
+ ret = rte_mempool_populate_virt(mp, mz->addr,
+ mz->len, pg_sz,
+ rte_mempool_memchunk_mz_free,
+ (void *)(uintptr_t)mz);
+ if (ret < 0) {
+ rte_memzone_free(mz);
+ goto fail;
+ }
+ }
+
+ return mp->size;
+
+ fail:
+ rte_mempool_free_memchunks(mp);
+ return ret;
+}
+
+/* return the memory size required for mempool objects in anonymous mem */
+static size_t
+get_anon_size(const struct rte_mempool *mp)
+{
+ size_t size, total_elt_sz, pg_sz, pg_shift;
+
+ pg_sz = getpagesize();
+ pg_shift = rte_bsf32(pg_sz);
+ total_elt_sz = mp->header_size + mp->elt_size + mp->trailer_size;
+ size = rte_mempool_xmem_size(mp->size, total_elt_sz, pg_shift,
+ mp->flags);
+
+ return size;
+}
+
+/* unmap a memory zone mapped by rte_mempool_populate_anon() */
+static void
+rte_mempool_memchunk_anon_free(struct rte_mempool_memhdr *memhdr,
+ void *opaque)
+{
+ munmap(opaque, get_anon_size(memhdr->mp));
+}
+
+/* populate the mempool with an anonymous mapping */
+int
+rte_mempool_populate_anon(struct rte_mempool *mp)
+{
+ size_t size;
+ int ret;
+ char *addr;
+
+ /* mempool is already populated, error */
+ if (!STAILQ_EMPTY(&mp->mem_list)) {
+ rte_errno = EINVAL;
+ return 0;
+ }
+
+ /* get chunk of virtually continuous memory */
+ size = get_anon_size(mp);
+ addr = mmap(NULL, size, PROT_READ | PROT_WRITE,
+ MAP_SHARED | MAP_ANONYMOUS, -1, 0);
+ if (addr == MAP_FAILED) {
+ rte_errno = errno;
+ return 0;
+ }
+ /* can't use MMAP_LOCKED, it does not exist on BSD */
+ if (mlock(addr, size) < 0) {
+ rte_errno = errno;
+ munmap(addr, size);
+ return 0;
+ }
+
+ ret = rte_mempool_populate_virt(mp, addr, size, getpagesize(),
+ rte_mempool_memchunk_anon_free, addr);
+ if (ret == 0)
+ goto fail;
+
+ return mp->populated_size;
+
+ fail:
+ rte_mempool_free_memchunks(mp);
+ return 0;
+}
+
+/* free a mempool */
+void
+rte_mempool_free(struct rte_mempool *mp)
+{
+ struct rte_mempool_list *mempool_list = NULL;
+ struct rte_tailq_entry *te;
+
+ if (mp == NULL)
+ return;
+
+ mempool_list = RTE_TAILQ_CAST(rte_mempool_tailq.head, rte_mempool_list);
+ rte_rwlock_write_lock(RTE_EAL_TAILQ_RWLOCK);
+ /* find out tailq entry */
+ TAILQ_FOREACH(te, mempool_list, next) {
+ if (te->data == (void *)mp)
+ break;
+ }
+
+ if (te != NULL) {
+ TAILQ_REMOVE(mempool_list, te, next);
+ rte_free(te);
+ }
+ rte_rwlock_write_unlock(RTE_EAL_TAILQ_RWLOCK);
+
+ rte_mempool_free_memchunks(mp);
+ rte_mempool_ops_free(mp);
+ rte_memzone_free(mp->mz);
+}
+
+static void
+mempool_cache_init(struct rte_mempool_cache *cache, uint32_t size)
+{
+ cache->size = size;
+ cache->flushthresh = CALC_CACHE_FLUSHTHRESH(size);
+ cache->len = 0;
+}
+
+/*
+ * Create and initialize a cache for objects that are retrieved from and
+ * returned to an underlying mempool. This structure is identical to the
+ * local_cache[lcore_id] pointed to by the mempool structure.
+ */
+struct rte_mempool_cache *
+rte_mempool_cache_create(uint32_t size, int socket_id)
+{
+ struct rte_mempool_cache *cache;
+
+ if (size == 0 || size > RTE_MEMPOOL_CACHE_MAX_SIZE) {
+ rte_errno = EINVAL;
+ return NULL;
+ }
+
+ cache = rte_zmalloc_socket("MEMPOOL_CACHE", sizeof(*cache),
+ RTE_CACHE_LINE_SIZE, socket_id);
+ if (cache == NULL) {
+ RTE_LOG(ERR, MEMPOOL, "Cannot allocate mempool cache.\n");
+ rte_errno = ENOMEM;
+ return NULL;
+ }
+
+ mempool_cache_init(cache, size);
+
+ return cache;
+}
+
+/*
+ * Free a cache. It's the responsibility of the user to make sure that any
+ * remaining objects in the cache are flushed to the corresponding
+ * mempool.
+ */
+void
+rte_mempool_cache_free(struct rte_mempool_cache *cache)
+{
+ rte_free(cache);
+}
+
+/* create an empty mempool */
+struct rte_mempool *
+rte_mempool_create_empty(const char *name, unsigned n, unsigned elt_size,
+ unsigned cache_size, unsigned private_data_size,
+ int socket_id, unsigned flags)
+{
+ char mz_name[RTE_MEMZONE_NAMESIZE];
+ struct rte_mempool_list *mempool_list;
+ struct rte_mempool *mp = NULL;
+ struct rte_tailq_entry *te = NULL;
+ const struct rte_memzone *mz = NULL;
+ size_t mempool_size;
+ unsigned int mz_flags = RTE_MEMZONE_1GB|RTE_MEMZONE_SIZE_HINT_ONLY;
+ struct rte_mempool_objsz objsz;
+ unsigned lcore_id;
+ int ret;
+
+ /* compilation-time checks */
+ RTE_BUILD_BUG_ON((sizeof(struct rte_mempool) &
+ RTE_CACHE_LINE_MASK) != 0);
+ RTE_BUILD_BUG_ON((sizeof(struct rte_mempool_cache) &
+ RTE_CACHE_LINE_MASK) != 0);
+#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
+ RTE_BUILD_BUG_ON((sizeof(struct rte_mempool_debug_stats) &
+ RTE_CACHE_LINE_MASK) != 0);
+ RTE_BUILD_BUG_ON((offsetof(struct rte_mempool, stats) &
+ RTE_CACHE_LINE_MASK) != 0);
+#endif
+
+ mempool_list = RTE_TAILQ_CAST(rte_mempool_tailq.head, rte_mempool_list);
+
+ /* asked cache too big */
+ if (cache_size > RTE_MEMPOOL_CACHE_MAX_SIZE ||
+ CALC_CACHE_FLUSHTHRESH(cache_size) > n) {
+ rte_errno = EINVAL;
+ return NULL;
+ }
+
+ /* "no cache align" imply "no spread" */
+ if (flags & MEMPOOL_F_NO_CACHE_ALIGN)
+ flags |= MEMPOOL_F_NO_SPREAD;
+
+ /* calculate mempool object sizes. */
+ if (!rte_mempool_calc_obj_size(elt_size, flags, &objsz)) {
+ rte_errno = EINVAL;
+ return NULL;
+ }
+
+ rte_rwlock_write_lock(RTE_EAL_MEMPOOL_RWLOCK);