+/* 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--;
+ }
+}
+
+static int
+mempool_ops_alloc_once(struct rte_mempool *mp)
+{
+ 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;
+ }
+ return 0;
+}
+
+/* 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 i = 0;
+ size_t off;
+ struct rte_mempool_memhdr *memhdr;
+ int ret;
+
+ ret = mempool_ops_alloc_once(mp);
+ if (ret != 0)
+ return ret;
+
+ /* mempool is already populated */
+ if (mp->populated_size >= mp->size)
+ 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_NO_CACHE_ALIGN)
+ off = RTE_PTR_ALIGN_CEIL(vaddr, 8) - vaddr;
+ else
+ off = RTE_PTR_ALIGN_CEIL(vaddr, RTE_MEMPOOL_ALIGN) - vaddr;
+
+ if (off > len) {
+ ret = -EINVAL;
+ goto fail;
+ }
+
+ i = rte_mempool_ops_populate(mp, mp->size - mp->populated_size,
+ (char *)vaddr + off,
+ (iova == RTE_BAD_IOVA) ? RTE_BAD_IOVA : (iova + off),
+ len - off, mempool_add_elem, NULL);
+
+ /* not enough room to store one object */
+ if (i == 0) {
+ ret = -EINVAL;
+ goto fail;
+ }
+
+ STAILQ_INSERT_TAIL(&mp->mem_list, memhdr, next);
+ mp->nb_mem_chunks++;
+ return i;
+
+fail:
+ rte_free(memhdr);
+ return ret;
+}
+
+/* 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;
+
+ if (mp->flags & MEMPOOL_F_NO_IOVA_CONTIG)
+ return rte_mempool_populate_iova(mp, addr, RTE_BAD_IOVA,
+ len, free_cb, opaque);
+
+ for (off = 0; off < 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 = RTE_MIN(
+ (size_t)(RTE_PTR_ALIGN_CEIL(addr + off + 1, pg_sz) -
+ (addr + off)),
+ len - off);
+ off + phys_len < len;
+ phys_len = RTE_MIN(phys_len + pg_sz, len - off)) {
+ rte_iova_t iova_tmp;
+
+ iova_tmp = rte_mem_virt2iova(addr + off + phys_len);
+
+ if (iova_tmp == RTE_BAD_IOVA ||
+ 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;
+}
+
+/* Get the minimal page size used in a mempool before populating it. */
+int
+rte_mempool_get_page_size(struct rte_mempool *mp, size_t *pg_sz)
+{
+ bool need_iova_contig_obj;
+ bool alloc_in_ext_mem;
+ int ret;
+
+ /* check if we can retrieve a valid socket ID */
+ ret = rte_malloc_heap_socket_is_external(mp->socket_id);
+ if (ret < 0)
+ return -EINVAL;
+ alloc_in_ext_mem = (ret == 1);
+ need_iova_contig_obj = !(mp->flags & MEMPOOL_F_NO_IOVA_CONTIG);
+
+ if (!need_iova_contig_obj)
+ *pg_sz = 0;
+ else if (rte_eal_has_hugepages() || alloc_in_ext_mem)
+ *pg_sz = get_min_page_size(mp->socket_id);
+ else
+ *pg_sz = getpagesize();
+
+ return 0;
+}
+
+/* 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;
+ ssize_t mem_size;
+ size_t align, pg_sz, pg_shift = 0;
+ rte_iova_t iova;
+ unsigned mz_id, n;
+ int ret;
+ bool need_iova_contig_obj;
+
+ ret = mempool_ops_alloc_once(mp);
+ if (ret != 0)
+ return ret;
+
+ /* mempool must not be populated */
+ if (mp->nb_mem_chunks != 0)
+ return -EEXIST;
+
+ /*
+ * the following section calculates page shift and page size values.
+ *
+ * these values impact the result of calc_mem_size operation, which
+ * returns the amount of memory that should be allocated to store the
+ * desired number of objects. when not zero, it allocates more memory
+ * for the padding between objects, to ensure that an object does not
+ * cross a page boundary. in other words, page size/shift are to be set
+ * to zero if mempool elements won't care about page boundaries.
+ * there are several considerations for page size and page shift here.
+ *
+ * if we don't need our mempools to have physically contiguous objects,
+ * then just set page shift and page size to 0, because the user has
+ * indicated that there's no need to care about anything.
+ *
+ * if we do need contiguous objects (if a mempool driver has its
+ * own calc_size() method returning min_chunk_size = mem_size),
+ * there is also an option to reserve the entire mempool memory
+ * as one contiguous block of memory.
+ *
+ * if we require contiguous objects, but not necessarily the entire
+ * mempool reserved space to be contiguous, pg_sz will be != 0,
+ * and the default ops->populate() will take care of not placing
+ * objects across pages.
+ *
+ * if our IO addresses are physical, we may get memory from bigger
+ * pages, or we might get memory from smaller pages, and how much of it
+ * we require depends on whether we want bigger or smaller pages.
+ * However, requesting each and every memory size is too much work, so
+ * what we'll do instead is walk through the page sizes available, pick
+ * the smallest one and set up page shift to match that one. We will be
+ * wasting some space this way, but it's much nicer than looping around
+ * trying to reserve each and every page size.
+ *
+ * If we fail to get enough contiguous memory, then we'll go and
+ * reserve space in smaller chunks.
+ */
+
+ need_iova_contig_obj = !(mp->flags & MEMPOOL_F_NO_IOVA_CONTIG);
+ ret = rte_mempool_get_page_size(mp, &pg_sz);
+ if (ret < 0)
+ return ret;
+
+ if (pg_sz != 0)
+ pg_shift = rte_bsf32(pg_sz);
+
+ for (mz_id = 0, n = mp->size; n > 0; mz_id++, n -= ret) {
+ size_t min_chunk_size;
+
+ mem_size = rte_mempool_ops_calc_mem_size(
+ mp, n, pg_shift, &min_chunk_size, &align);
+
+ if (mem_size < 0) {
+ ret = mem_size;
+ goto fail;
+ }
+
+ 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;
+ }
+
+ /* if we're trying to reserve contiguous memory, add appropriate
+ * memzone flag.
+ */
+ if (min_chunk_size == (size_t)mem_size)
+ mz_flags |= RTE_MEMZONE_IOVA_CONTIG;
+
+ mz = rte_memzone_reserve_aligned(mz_name, mem_size,
+ mp->socket_id, mz_flags, align);
+
+ /* don't try reserving with 0 size if we were asked to reserve
+ * IOVA-contiguous memory.
+ */
+ if (min_chunk_size < (size_t)mem_size && mz == NULL) {
+ /* not enough memory, retry with the biggest zone we
+ * have
+ */
+ mz = rte_memzone_reserve_aligned(mz_name, 0,
+ mp->socket_id, mz_flags, align);
+ }
+ if (mz == NULL) {
+ ret = -rte_errno;
+ goto fail;
+ }
+
+ if (mz->len < min_chunk_size) {
+ rte_memzone_free(mz);
+ ret = -ENOMEM;
+ goto fail;
+ }
+
+ if (need_iova_contig_obj)
+ iova = mz->iova;
+ else
+ iova = RTE_BAD_IOVA;
+
+ if (pg_sz == 0 || (mz_flags & RTE_MEMZONE_IOVA_CONTIG))
+ 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 ssize_t
+get_anon_size(const struct rte_mempool *mp)
+{
+ ssize_t size;
+ size_t pg_sz, pg_shift;
+ size_t min_chunk_size;
+ size_t align;
+
+ pg_sz = getpagesize();
+ pg_shift = rte_bsf32(pg_sz);
+ size = rte_mempool_ops_calc_mem_size(mp, mp->size, pg_shift,
+ &min_chunk_size, &align);
+
+ 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)
+{
+ ssize_t size;