-/*-
- * BSD LICENSE
- *
- * Copyright(c) 2010-2014 Intel Corporation. All rights reserved.
- * Copyright(c) 2016 6WIND S.A.
- * 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
- * notice, this list of conditions and the following disclaimer in
- * the documentation and/or other materials provided with the
- * distribution.
- * * 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
- * 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.
+/* SPDX-License-Identifier: BSD-3-Clause
+ * Copyright(c) 2010-2014 Intel Corporation.
+ * Copyright(c) 2016 6WIND S.A.
*/
+#include <stdbool.h>
#include <stdio.h>
#include <string.h>
#include <stdint.h>
#include <inttypes.h>
#include <errno.h>
#include <sys/queue.h>
+#include <sys/mman.h>
#include <rte_common.h>
#include <rte_log.h>
#include <rte_per_lcore.h>
#include <rte_lcore.h>
#include <rte_branch_prediction.h>
-#include <rte_ring.h>
#include <rte_errno.h>
#include <rte_string_fns.h>
#include <rte_spinlock.h>
+#include <rte_tailq.h>
#include "rte_mempool.h"
return new_obj_size * RTE_MEMPOOL_ALIGN;
}
+struct pagesz_walk_arg {
+ int socket_id;
+ size_t min;
+};
+
+static int
+find_min_pagesz(const struct rte_memseg_list *msl, void *arg)
+{
+ struct pagesz_walk_arg *wa = arg;
+ bool valid;
+
+ /*
+ * we need to only look at page sizes available for a particular socket
+ * ID. so, we either need an exact match on socket ID (can match both
+ * native and external memory), or, if SOCKET_ID_ANY was specified as a
+ * socket ID argument, we must only look at native memory and ignore any
+ * page sizes associated with external memory.
+ */
+ valid = msl->socket_id == wa->socket_id;
+ valid |= wa->socket_id == SOCKET_ID_ANY && msl->external == 0;
+
+ if (valid && msl->page_sz < wa->min)
+ wa->min = msl->page_sz;
+
+ return 0;
+}
+
+static size_t
+get_min_page_size(int socket_id)
+{
+ struct pagesz_walk_arg wa;
+
+ wa.min = SIZE_MAX;
+ wa.socket_id = socket_id;
+
+ rte_memseg_list_walk(find_min_pagesz, &wa);
+
+ return wa.min == SIZE_MAX ? (size_t) getpagesize() : wa.min;
+}
+
+
static void
-mempool_add_elem(struct rte_mempool *mp, void *obj, phys_addr_t physaddr)
+mempool_add_elem(struct rte_mempool *mp, __rte_unused void *opaque,
+ void *obj, rte_iova_t iova)
{
struct rte_mempool_objhdr *hdr;
struct rte_mempool_objtlr *tlr __rte_unused;
/* set mempool ptr in header */
hdr = RTE_PTR_SUB(obj, sizeof(*hdr));
hdr->mp = mp;
- hdr->physaddr = physaddr;
+ hdr->iova = iova;
STAILQ_INSERT_TAIL(&mp->elt_list, hdr, next);
mp->populated_size++;
tlr = __mempool_get_trailer(obj);
tlr->cookie = RTE_MEMPOOL_TRAILER_COOKIE;
#endif
-
- /* enqueue in ring */
- rte_ring_sp_enqueue(mp->ring, obj);
}
/* call obj_cb() for each mempool element */
sz->header_size = RTE_ALIGN_CEIL(sz->header_size,
RTE_MEMPOOL_ALIGN);
+#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
sz->trailer_size = sizeof(struct rte_mempool_objtlr);
+#else
+ sz->trailer_size = 0;
+#endif
/* element size is 8 bytes-aligned at least */
sz->elt_size = RTE_ALIGN_CEIL(elt_size, sizeof(uint64_t));
sz->trailer_size = new_size - sz->header_size - sz->elt_size;
}
- if (! rte_eal_has_hugepages()) {
- /*
- * compute trailer size so that pool elements fit exactly in
- * a standard page
- */
- int page_size = getpagesize();
- int new_size = page_size - sz->header_size - sz->elt_size;
- if (new_size < 0 || (unsigned int)new_size < sz->trailer_size) {
- printf("When hugepages are disabled, pool objects "
- "can't exceed PAGE_SIZE: %d + %d + %d > %d\n",
- sz->header_size, sz->elt_size, sz->trailer_size,
- page_size);
- return 0;
- }
- sz->trailer_size = new_size;
- }
-
/* this is the size of an object, including header and trailer */
sz->total_size = sz->header_size + sz->elt_size + sz->trailer_size;
return sz->total_size;
}
-
-/*
- * 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)
-{
- size_t n, pg_num, pg_sz, sz;
-
- pg_sz = (size_t)1 << pg_shift;
-
- if ((n = pg_sz / total_elt_sz) > 0) {
- pg_num = (elt_num + n - 1) / n;
- sz = pg_num << pg_shift;
- } else {
- sz = RTE_ALIGN_CEIL(total_elt_sz, pg_sz) * elt_num;
- }
-
- return sz;
-}
-
-/*
- * 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 phys_addr_t paddr[], uint32_t pg_num,
- uint32_t pg_shift)
-{
- uint32_t elt_cnt = 0;
- phys_addr_t start, end;
- uint32_t paddr_idx;
- size_t pg_sz = (size_t)1 << pg_shift;
-
- /* if paddr is NULL, assume contiguous memory */
- if (paddr == NULL) {
- start = 0;
- end = pg_sz * pg_num;
- paddr_idx = pg_num;
- } else {
- start = paddr[0];
- end = paddr[0] + pg_sz;
- paddr_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 (paddr_idx < pg_num) {
- /* no room to store one obj, add a page */
- if (end == paddr[paddr_idx]) {
- end += pg_sz;
- } else {
- start = paddr[paddr_idx];
- end = paddr[paddr_idx] + pg_sz;
- }
- paddr_idx++;
-
- } else {
- /* no more page, return how many elements fit */
- return -(size_t)elt_cnt;
- }
- }
-
- return (size_t)paddr_idx << pg_shift;
-}
-
-#ifndef RTE_LIBRTE_XEN_DOM0
-/* stub if DOM0 support not configured */
-struct rte_mempool *
-rte_dom0_mempool_create(const char *name __rte_unused,
- unsigned n __rte_unused,
- unsigned elt_size __rte_unused,
- unsigned cache_size __rte_unused,
- unsigned private_data_size __rte_unused,
- rte_mempool_ctor_t *mp_init __rte_unused,
- void *mp_init_arg __rte_unused,
- rte_mempool_obj_ctor_t *obj_init __rte_unused,
- void *obj_init_arg __rte_unused,
- int socket_id __rte_unused,
- unsigned flags __rte_unused)
-{
- rte_errno = EINVAL;
- return NULL;
-}
-#endif
-
-/* create the mempool */
-struct rte_mempool *
-rte_mempool_create(const char *name, unsigned n, unsigned elt_size,
- unsigned cache_size, unsigned private_data_size,
- rte_mempool_ctor_t *mp_init, void *mp_init_arg,
- rte_mempool_obj_ctor_t *obj_init, void *obj_init_arg,
- int socket_id, unsigned flags)
-{
- if (rte_xen_dom0_supported())
- return rte_dom0_mempool_create(name, n, elt_size,
- cache_size, private_data_size,
- mp_init, mp_init_arg,
- obj_init, obj_init_arg,
- socket_id, flags);
- else
- return rte_mempool_xmem_create(name, n, elt_size,
- cache_size, private_data_size,
- mp_init, mp_init_arg,
- obj_init, obj_init_arg,
- socket_id, flags,
- NULL, NULL, MEMPOOL_PG_NUM_DEFAULT,
- MEMPOOL_PG_SHIFT_MAX);
-}
-
-/* create the internal ring */
-static int
-rte_mempool_ring_create(struct rte_mempool *mp)
+/* free a memchunk allocated with rte_memzone_reserve() */
+static void
+rte_mempool_memchunk_mz_free(__rte_unused struct rte_mempool_memhdr *memhdr,
+ void *opaque)
{
- int rg_flags = 0;
- char rg_name[RTE_RING_NAMESIZE];
- struct rte_ring *r;
-
- snprintf(rg_name, sizeof(rg_name), RTE_MEMPOOL_MZ_FORMAT, mp->name);
-
- /* ring flags */
- if (mp->flags & MEMPOOL_F_SP_PUT)
- rg_flags |= RING_F_SP_ENQ;
- if (mp->flags & MEMPOOL_F_SC_GET)
- rg_flags |= RING_F_SC_DEQ;
-
- /* Allocate the ring that will be used to store objects.
- * Ring functions will return appropriate errors if we are
- * running as a secondary process etc., so no checks made
- * in this function for that condition.
- */
- r = rte_ring_create(rg_name, rte_align32pow2(mp->size + 1),
- mp->socket_id, rg_flags);
- if (r == NULL)
- return -rte_errno;
-
- mp->ring = r;
- return 0;
+ const struct rte_memzone *mz = opaque;
+ rte_memzone_free(mz);
}
/* Free memory chunks used by a mempool. Objects must be in pool */
void *elt;
while (!STAILQ_EMPTY(&mp->elt_list)) {
- rte_ring_sc_dequeue(mp->ring, &elt);
+ 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.
*/
-static int
-rte_mempool_populate_phys(struct rte_mempool *mp, char *vaddr,
- phys_addr_t paddr, size_t len)
+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;
+
+ ret = mempool_ops_alloc_once(mp);
+ if (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;
-
memhdr = rte_zmalloc("MEMPOOL_MEMHDR", sizeof(*memhdr), 0);
if (memhdr == NULL)
return -ENOMEM;
memhdr->mp = mp;
memhdr->addr = vaddr;
- memhdr->phys_addr = paddr;
+ 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_CACHE_LINE_SIZE) - vaddr;
- while (off + total_elt_sz <= len && mp->populated_size < mp->size) {
- off += mp->header_size;
- mempool_add_elem(mp, (char *)vaddr + off, paddr + off);
- off += mp->elt_size + mp->trailer_size;
- i++;
+ 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)
- return -EINVAL;
+ 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;
}
-/* Add objects in the pool, using a table of physical pages. Return the
- * number of objects added, or a negative value on error.
+/* Populate the mempool with a virtual area. Return the number of
+ * objects added, or a negative value on error.
*/
-static 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)
+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)
{
- uint32_t i, n;
+ rte_iova_t iova;
+ size_t off, phys_len;
int ret, cnt = 0;
- size_t pg_sz = (size_t)1 << pg_shift;
+
+ 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 (!alloc_in_ext_mem && rte_eal_iova_mode() == RTE_IOVA_VA)
+ *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;
- for (i = 0; i < pg_num && mp->populated_size < mp->size; i += n) {
+ /*
+ * 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, there is also an option to reserve
+ * the entire mempool memory as one contiguous block of memory, in
+ * which case the page shift and alignment wouldn't matter as well.
+ *
+ * if we require contiguous objects, but not necessarily the entire
+ * mempool reserved space to be contiguous, then there are two options.
+ *
+ * if our IO addresses are virtual, not actual physical (IOVA as VA
+ * case), then no page shift needed - our memory allocation will give us
+ * contiguous IO memory as far as the hardware is concerned, so
+ * act as if we're getting contiguous memory.
+ *
+ * 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.
+ *
+ * We also have to take into account the fact that memory that we're
+ * going to allocate from can belong to an externally allocated memory
+ * area, in which case the assumption of IOVA as VA mode being
+ * synonymous with IOVA contiguousness will not hold.
+ */
+
+ 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;
- /* populate with the largest group of contiguous pages */
- for (n = 1; (i + n) < pg_num &&
- paddr[i] + pg_sz == paddr[i+n]; n++)
- ;
+ 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);
- ret = rte_mempool_populate_phys(mp, vaddr + i * pg_sz,
- paddr[i], n * pg_sz);
+ /* 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_mempool_free_memchunks(mp);
- return ret;
+ rte_memzone_free(mz);
+ goto fail;
}
- cnt += ret;
}
- return cnt;
+
+ 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;
+
+ /*
+ * Calculate size since memhdr->len has contiguous chunk length
+ * which may be smaller if anon map is split into many contiguous
+ * chunks. Result must be the same as we calculated on populate.
+ */
+ size = get_anon_size(memhdr->mp);
+ if (size < 0)
+ return;
+
+ munmap(opaque, size);
+}
+
+/* populate the mempool with an anonymous mapping */
+int
+rte_mempool_populate_anon(struct rte_mempool *mp)
+{
+ ssize_t size;
+ int ret;
+ char *addr;
+
+ /* mempool is already populated, error */
+ if ((!STAILQ_EMPTY(&mp->mem_list)) || mp->nb_mem_chunks != 0) {
+ rte_errno = EINVAL;
+ return 0;
+ }
+
+ ret = mempool_ops_alloc_once(mp);
+ if (ret != 0)
+ return ret;
+
+ size = get_anon_size(mp);
+ if (size < 0) {
+ rte_errno = -size;
+ return 0;
+ }
+
+ /* get chunk of virtually continuous memory */
+ 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_mcfg_tailq_write_lock();
+ /* 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_mcfg_tailq_write_unlock();
+
+ 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;
}
/*
- * Create the mempool over already allocated chunk of memory.
- * That external memory buffer can consists of physically disjoint pages.
- * Setting vaddr to NULL, makes mempool to fallback to original behaviour
- * and allocate space for mempool and it's elements as one big chunk of
- * physically continuos memory.
- * */
+ * 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_xmem_create(const char *name, unsigned n, unsigned elt_size,
- unsigned cache_size, unsigned private_data_size,
- rte_mempool_ctor_t *mp_init, void *mp_init_arg,
- rte_mempool_obj_cb_t *obj_init, void *obj_init_arg,
- int socket_id, unsigned flags, void *vaddr,
- const phys_addr_t paddr[], uint32_t pg_num, uint32_t pg_shift)
+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;
+ const struct rte_memzone *mz = NULL;
size_t mempool_size;
- int mz_flags = RTE_MEMZONE_1GB|RTE_MEMZONE_SIZE_HINT_ONLY;
- void *obj;
+ unsigned int mz_flags = RTE_MEMZONE_1GB|RTE_MEMZONE_SIZE_HINT_ONLY;
struct rte_mempool_objsz objsz;
- void *startaddr;
- int page_size = getpagesize();
+ unsigned lcore_id;
int ret;
/* compilation-time checks */
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;
- }
-
- /* check that we have both VA and PA */
- if (vaddr != NULL && paddr == NULL) {
+ /* asked for zero items */
+ if (n == 0) {
rte_errno = EINVAL;
return NULL;
}
- /* Check that pg_num and pg_shift parameters are valid. */
- if (pg_num == 0 || pg_shift > MEMPOOL_PG_SHIFT_MAX) {
+ /* asked cache too big */
+ if (cache_size > RTE_MEMPOOL_CACHE_MAX_SIZE ||
+ CALC_CACHE_FLUSHTHRESH(cache_size) > n) {
rte_errno = EINVAL;
return NULL;
}
return NULL;
}
- rte_rwlock_write_lock(RTE_EAL_MEMPOOL_RWLOCK);
+ rte_mcfg_mempool_write_lock();
/*
* reserve a memory zone for this mempool: private data is
private_data_size = (private_data_size +
RTE_MEMPOOL_ALIGN_MASK) & (~RTE_MEMPOOL_ALIGN_MASK);
- if (! rte_eal_has_hugepages()) {
- /*
- * expand private data size to a whole page, so that the
- * first pool element will start on a new standard page
- */
- int head = sizeof(struct rte_mempool);
- int new_size = (private_data_size + head) % page_size;
- if (new_size)
- private_data_size += page_size - new_size;
- }
/* try to allocate tailq entry */
te = rte_zmalloc("MEMPOOL_TAILQ_ENTRY", sizeof(*te), 0);
goto exit_unlock;
}
- /*
- * If user provided an external memory buffer, then use it to
- * store mempool objects. Otherwise reserve a memzone that is large
- * enough to hold mempool header and metadata plus mempool objects.
- */
mempool_size = MEMPOOL_HEADER_SIZE(mp, cache_size);
mempool_size += private_data_size;
mempool_size = RTE_ALIGN_CEIL(mempool_size, RTE_MEMPOOL_ALIGN);
- if (vaddr == NULL)
- mempool_size += (size_t)objsz.total_size * n;
-
- if (! rte_eal_has_hugepages()) {
- /*
- * we want the memory pool to start on a page boundary,
- * because pool elements crossing page boundaries would
- * result in discontiguous physical addresses
- */
- mempool_size += page_size;
- }
- snprintf(mz_name, sizeof(mz_name), RTE_MEMPOOL_MZ_FORMAT, name);
+ ret = snprintf(mz_name, sizeof(mz_name), RTE_MEMPOOL_MZ_FORMAT, name);
+ if (ret < 0 || ret >= (int)sizeof(mz_name)) {
+ rte_errno = ENAMETOOLONG;
+ goto exit_unlock;
+ }
mz = rte_memzone_reserve(mz_name, mempool_size, socket_id, mz_flags);
if (mz == NULL)
goto exit_unlock;
- if (rte_eal_has_hugepages()) {
- startaddr = (void*)mz->addr;
- } else {
- /* align memory pool start address on a page boundary */
- unsigned long addr = (unsigned long)mz->addr;
- if (addr & (page_size - 1)) {
- addr += page_size;
- addr &= ~(page_size - 1);
- }
- startaddr = (void*)addr;
- }
-
/* init the mempool structure */
- mp = startaddr;
- memset(mp, 0, sizeof(*mp));
- snprintf(mp->name, sizeof(mp->name), "%s", name);
- mp->phys_addr = mz->phys_addr;
- mp->socket_id = socket_id;
+ mp = mz->addr;
+ memset(mp, 0, MEMPOOL_HEADER_SIZE(mp, cache_size));
+ ret = strlcpy(mp->name, name, sizeof(mp->name));
+ if (ret < 0 || ret >= (int)sizeof(mp->name)) {
+ rte_errno = ENAMETOOLONG;
+ goto exit_unlock;
+ }
+ mp->mz = mz;
mp->size = n;
mp->flags = flags;
+ mp->socket_id = socket_id;
mp->elt_size = objsz.elt_size;
mp->header_size = objsz.header_size;
mp->trailer_size = objsz.trailer_size;
+ /* Size of default caches, zero means disabled. */
mp->cache_size = cache_size;
- mp->cache_flushthresh = CALC_CACHE_FLUSHTHRESH(cache_size);
mp->private_data_size = private_data_size;
STAILQ_INIT(&mp->elt_list);
STAILQ_INIT(&mp->mem_list);
- if (rte_mempool_ring_create(mp) < 0)
- goto exit_unlock;
-
/*
* local_cache pointer is set even if cache_size is zero.
* The local_cache points to just past the elt_pa[] array.
mp->local_cache = (struct rte_mempool_cache *)
RTE_PTR_ADD(mp, MEMPOOL_HEADER_SIZE(mp, 0));
- /* call the initializer */
- if (mp_init)
- mp_init(mp, mp_init_arg);
-
- /* mempool elements allocated together with mempool */
- if (vaddr == NULL) {
- /* calculate address of the first elt for continuous mempool. */
- obj = (char *)mp + MEMPOOL_HEADER_SIZE(mp, cache_size) +
- private_data_size;
- obj = RTE_PTR_ALIGN_CEIL(obj, RTE_MEMPOOL_ALIGN);
-
- ret = rte_mempool_populate_phys(mp, obj,
- mp->phys_addr + ((char *)obj - (char *)mp),
- objsz.total_size * n);
- if (ret != (int)mp->size)
- goto exit_unlock;
- } else {
- ret = rte_mempool_populate_phys_tab(mp, vaddr,
- paddr, pg_num, pg_shift);
- if (ret != (int)mp->size)
- goto exit_unlock;
- }
-
- /* call the initializer */
- if (obj_init)
- rte_mempool_obj_iter(mp, obj_init, obj_init_arg);
+ /* Init all default caches. */
+ if (cache_size != 0) {
+ for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++)
+ mempool_cache_init(&mp->local_cache[lcore_id],
+ cache_size);
+ }
- te->data = (void *) mp;
+ te->data = mp;
- rte_rwlock_write_lock(RTE_EAL_TAILQ_RWLOCK);
+ rte_mcfg_tailq_write_lock();
TAILQ_INSERT_TAIL(mempool_list, te, next);
- rte_rwlock_write_unlock(RTE_EAL_TAILQ_RWLOCK);
- rte_rwlock_write_unlock(RTE_EAL_MEMPOOL_RWLOCK);
+ rte_mcfg_tailq_write_unlock();
+ rte_mcfg_mempool_write_unlock();
return mp;
exit_unlock:
- rte_rwlock_write_unlock(RTE_EAL_MEMPOOL_RWLOCK);
- if (mp != NULL) {
- rte_mempool_free_memchunks(mp);
- rte_ring_free(mp->ring);
- }
+ rte_mcfg_mempool_write_unlock();
rte_free(te);
+ rte_mempool_free(mp);
+ return NULL;
+}
+/* create the mempool */
+struct rte_mempool *
+rte_mempool_create(const char *name, unsigned n, unsigned elt_size,
+ unsigned cache_size, unsigned private_data_size,
+ rte_mempool_ctor_t *mp_init, void *mp_init_arg,
+ rte_mempool_obj_cb_t *obj_init, void *obj_init_arg,
+ int socket_id, unsigned flags)
+{
+ int ret;
+ struct rte_mempool *mp;
+
+ mp = rte_mempool_create_empty(name, n, elt_size, cache_size,
+ private_data_size, socket_id, flags);
+ if (mp == NULL)
+ return NULL;
+
+ /*
+ * Since we have 4 combinations of the SP/SC/MP/MC examine the flags to
+ * set the correct index into the table of ops structs.
+ */
+ if ((flags & MEMPOOL_F_SP_PUT) && (flags & MEMPOOL_F_SC_GET))
+ ret = rte_mempool_set_ops_byname(mp, "ring_sp_sc", NULL);
+ else if (flags & MEMPOOL_F_SP_PUT)
+ ret = rte_mempool_set_ops_byname(mp, "ring_sp_mc", NULL);
+ else if (flags & MEMPOOL_F_SC_GET)
+ ret = rte_mempool_set_ops_byname(mp, "ring_mp_sc", NULL);
+ else
+ ret = rte_mempool_set_ops_byname(mp, "ring_mp_mc", NULL);
+
+ if (ret)
+ goto fail;
+
+ /* call the mempool priv initializer */
+ if (mp_init)
+ mp_init(mp, mp_init_arg);
+
+ if (rte_mempool_populate_default(mp) < 0)
+ goto fail;
+
+ /* call the object initializers */
+ if (obj_init)
+ rte_mempool_obj_iter(mp, obj_init, obj_init_arg);
+
+ return mp;
+
+ fail:
+ rte_mempool_free(mp);
return NULL;
}
/* Return the number of entries in the mempool */
-unsigned
-rte_mempool_count(const struct rte_mempool *mp)
+unsigned int
+rte_mempool_avail_count(const struct rte_mempool *mp)
{
unsigned count;
unsigned lcore_id;
- count = rte_ring_count(mp->ring);
+ count = rte_mempool_ops_get_count(mp);
if (mp->cache_size == 0)
return count;
return count;
}
+/* return the number of entries allocated from the mempool */
+unsigned int
+rte_mempool_in_use_count(const struct rte_mempool *mp)
+{
+ return mp->size - rte_mempool_avail_count(mp);
+}
+
/* dump the cache status */
static unsigned
rte_mempool_dump_cache(FILE *f, const struct rte_mempool *mp)
unsigned count = 0;
unsigned cache_count;
- fprintf(f, " cache infos:\n");
+ fprintf(f, " internal cache infos:\n");
fprintf(f, " cache_size=%"PRIu32"\n", mp->cache_size);
if (mp->cache_size == 0)
for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
cache_count = mp->local_cache[lcore_id].len;
- fprintf(f, " cache_count[%u]=%u\n", lcore_id, cache_count);
+ fprintf(f, " cache_count[%u]=%"PRIu32"\n",
+ lcore_id, cache_count);
count += cache_count;
}
fprintf(f, " total_cache_count=%u\n", count);
/* Force to drop the "const" attribute. This is done only when
* DEBUG is enabled */
tmp = (void *) obj_table_const;
- obj_table = (void **) tmp;
+ obj_table = tmp;
while (n--) {
obj = obj_table[n];
if (free == 0) {
if (cookie != RTE_MEMPOOL_HEADER_COOKIE1) {
- rte_log_set_history(0);
RTE_LOG(CRIT, MEMPOOL,
"obj=%p, mempool=%p, cookie=%" PRIx64 "\n",
obj, (const void *) mp, cookie);
hdr->cookie = RTE_MEMPOOL_HEADER_COOKIE2;
} else if (free == 1) {
if (cookie != RTE_MEMPOOL_HEADER_COOKIE2) {
- rte_log_set_history(0);
RTE_LOG(CRIT, MEMPOOL,
"obj=%p, mempool=%p, cookie=%" PRIx64 "\n",
obj, (const void *) mp, cookie);
} else if (free == 2) {
if (cookie != RTE_MEMPOOL_HEADER_COOKIE1 &&
cookie != RTE_MEMPOOL_HEADER_COOKIE2) {
- rte_log_set_history(0);
RTE_LOG(CRIT, MEMPOOL,
"obj=%p, mempool=%p, cookie=%" PRIx64 "\n",
obj, (const void *) mp, cookie);
tlr = __mempool_get_trailer(obj);
cookie = tlr->cookie;
if (cookie != RTE_MEMPOOL_TRAILER_COOKIE) {
- rte_log_set_history(0);
RTE_LOG(CRIT, MEMPOOL,
"obj=%p, mempool=%p, cookie=%" PRIx64 "\n",
obj, (const void *) mp, cookie);
#endif
}
+void
+rte_mempool_contig_blocks_check_cookies(const struct rte_mempool *mp,
+ void * const *first_obj_table_const, unsigned int n, int free)
+{
+#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
+ struct rte_mempool_info info;
+ const size_t total_elt_sz =
+ mp->header_size + mp->elt_size + mp->trailer_size;
+ unsigned int i, j;
+
+ rte_mempool_ops_get_info(mp, &info);
+
+ for (i = 0; i < n; ++i) {
+ void *first_obj = first_obj_table_const[i];
+
+ for (j = 0; j < info.contig_block_size; ++j) {
+ void *obj;
+
+ obj = (void *)((uintptr_t)first_obj + j * total_elt_sz);
+ rte_mempool_check_cookies(mp, &obj, 1, free);
+ }
+ }
+#else
+ RTE_SET_USED(mp);
+ RTE_SET_USED(first_obj_table_const);
+ RTE_SET_USED(n);
+ RTE_SET_USED(free);
+#endif
+}
+
#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
static void
mempool_obj_audit(struct rte_mempool *mp, __rte_unused void *opaque,
return;
for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
- if (mp->local_cache[lcore_id].len > mp->cache_flushthresh) {
+ const struct rte_mempool_cache *cache;
+ cache = &mp->local_cache[lcore_id];
+ if (cache->len > cache->flushthresh) {
RTE_LOG(CRIT, MEMPOOL, "badness on cache[%u]\n",
lcore_id);
rte_panic("MEMPOOL: invalid cache len\n");
rte_mempool_dump(FILE *f, struct rte_mempool *mp)
{
#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
+ struct rte_mempool_info info;
struct rte_mempool_debug_stats sum;
unsigned lcore_id;
#endif
fprintf(f, "mempool <%s>@%p\n", mp->name, mp);
fprintf(f, " flags=%x\n", mp->flags);
- fprintf(f, " ring=<%s>@%p\n", mp->ring->name, mp->ring);
- fprintf(f, " phys_addr=0x%" PRIx64 "\n", mp->phys_addr);
+ fprintf(f, " pool=%p\n", mp->pool_data);
+ fprintf(f, " iova=0x%" PRIx64 "\n", mp->mz->iova);
fprintf(f, " nb_mem_chunks=%u\n", mp->nb_mem_chunks);
fprintf(f, " size=%"PRIu32"\n", mp->size);
fprintf(f, " populated_size=%"PRIu32"\n", mp->populated_size);
}
cache_count = rte_mempool_dump_cache(f, mp);
- common_count = rte_ring_count(mp->ring);
+ common_count = rte_mempool_ops_get_count(mp);
if ((cache_count + common_count) > mp->size)
common_count = mp->size - cache_count;
fprintf(f, " common_pool_count=%u\n", common_count);
/* sum and dump statistics */
#ifdef RTE_LIBRTE_MEMPOOL_DEBUG
+ rte_mempool_ops_get_info(mp, &info);
memset(&sum, 0, sizeof(sum));
for (lcore_id = 0; lcore_id < RTE_MAX_LCORE; lcore_id++) {
sum.put_bulk += mp->stats[lcore_id].put_bulk;
sum.get_success_objs += mp->stats[lcore_id].get_success_objs;
sum.get_fail_bulk += mp->stats[lcore_id].get_fail_bulk;
sum.get_fail_objs += mp->stats[lcore_id].get_fail_objs;
+ sum.get_success_blks += mp->stats[lcore_id].get_success_blks;
+ sum.get_fail_blks += mp->stats[lcore_id].get_fail_blks;
}
fprintf(f, " stats:\n");
fprintf(f, " put_bulk=%"PRIu64"\n", sum.put_bulk);
fprintf(f, " get_success_objs=%"PRIu64"\n", sum.get_success_objs);
fprintf(f, " get_fail_bulk=%"PRIu64"\n", sum.get_fail_bulk);
fprintf(f, " get_fail_objs=%"PRIu64"\n", sum.get_fail_objs);
+ if (info.contig_block_size > 0) {
+ fprintf(f, " get_success_blks=%"PRIu64"\n",
+ sum.get_success_blks);
+ fprintf(f, " get_fail_blks=%"PRIu64"\n", sum.get_fail_blks);
+ }
#else
fprintf(f, " no statistics available\n");
#endif
mempool_list = RTE_TAILQ_CAST(rte_mempool_tailq.head, rte_mempool_list);
- rte_rwlock_read_lock(RTE_EAL_MEMPOOL_RWLOCK);
+ rte_mcfg_mempool_read_lock();
TAILQ_FOREACH(te, mempool_list, next) {
mp = (struct rte_mempool *) te->data;
rte_mempool_dump(f, mp);
}
- rte_rwlock_read_unlock(RTE_EAL_MEMPOOL_RWLOCK);
+ rte_mcfg_mempool_read_unlock();
}
/* search a mempool from its name */
mempool_list = RTE_TAILQ_CAST(rte_mempool_tailq.head, rte_mempool_list);
- rte_rwlock_read_lock(RTE_EAL_MEMPOOL_RWLOCK);
+ rte_mcfg_mempool_read_lock();
TAILQ_FOREACH(te, mempool_list, next) {
mp = (struct rte_mempool *) te->data;
break;
}
- rte_rwlock_read_unlock(RTE_EAL_MEMPOOL_RWLOCK);
+ rte_mcfg_mempool_read_unlock();
if (te == NULL) {
rte_errno = ENOENT;
{
struct rte_tailq_entry *te = NULL;
struct rte_mempool_list *mempool_list;
+ void *tmp_te;
mempool_list = RTE_TAILQ_CAST(rte_mempool_tailq.head, rte_mempool_list);
- rte_rwlock_read_lock(RTE_EAL_MEMPOOL_RWLOCK);
+ rte_mcfg_mempool_read_lock();
- TAILQ_FOREACH(te, mempool_list, next) {
+ TAILQ_FOREACH_SAFE(te, mempool_list, next, tmp_te) {
(*func)((struct rte_mempool *) te->data, arg);
}
- rte_rwlock_read_unlock(RTE_EAL_MEMPOOL_RWLOCK);
+ rte_mcfg_mempool_read_unlock();
}
git.droids-corp.org / dpdk.git / blobdiff