X-Git-Url: http://git.droids-corp.org/?a=blobdiff_plain;f=lib%2Flibrte_eal%2Fcommon%2Fmalloc_heap.c;h=634ca212f2fe65781c423366d37268d9b63cbb84;hb=a8f8ae1cf9b68f6398b49019ca07a215a57bba41;hp=256c25edf4da87eb8adf0672589dff091b52bbe4;hpb=7d75c31014f751efe465f22d4acae956e8e992a0;p=dpdk.git diff --git a/lib/librte_eal/common/malloc_heap.c b/lib/librte_eal/common/malloc_heap.c index 256c25edf4..634ca212f2 100644 --- a/lib/librte_eal/common/malloc_heap.c +++ b/lib/librte_eal/common/malloc_heap.c @@ -20,11 +20,13 @@ #include #include #include +#include #include #include #include "eal_internal_cfg.h" #include "eal_memalloc.h" +#include "eal_memcfg.h" #include "malloc_elem.h" #include "malloc_heap.h" #include "malloc_mp.h" @@ -94,7 +96,7 @@ malloc_heap_add_memory(struct malloc_heap *heap, struct rte_memseg_list *msl, { struct malloc_elem *elem = start; - malloc_elem_init(elem, heap, msl, len); + malloc_elem_init(elem, heap, msl, len, elem, len); malloc_elem_insert(elem); @@ -192,7 +194,9 @@ find_biggest_element(struct malloc_heap *heap, size_t *size, for (elem = LIST_FIRST(&heap->free_head[idx]); !!elem; elem = LIST_NEXT(elem, free_list)) { size_t cur_size; - if (!check_hugepage_sz(flags, elem->msl->page_sz)) + if ((flags & RTE_MEMZONE_SIZE_HINT_ONLY) == 0 && + !check_hugepage_sz(flags, + elem->msl->page_sz)) continue; if (contig) { cur_size = @@ -286,6 +290,7 @@ alloc_pages_on_heap(struct malloc_heap *heap, uint64_t pg_sz, size_t elt_size, int socket, unsigned int flags, size_t align, size_t bound, bool contig, struct rte_memseg **ms, int n_segs) { + struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config; struct rte_memseg_list *msl; struct malloc_elem *elem = NULL; size_t alloc_sz; @@ -318,6 +323,46 @@ alloc_pages_on_heap(struct malloc_heap *heap, uint64_t pg_sz, size_t elt_size, goto fail; } + /* + * Once we have all the memseg lists configured, if there is a dma mask + * set, check iova addresses are not out of range. Otherwise the device + * setting the dma mask could have problems with the mapped memory. + * + * There are two situations when this can happen: + * 1) memory initialization + * 2) dynamic memory allocation + * + * For 1), an error when checking dma mask implies app can not be + * executed. For 2) implies the new memory can not be added. + */ + if (mcfg->dma_maskbits && + rte_mem_check_dma_mask_thread_unsafe(mcfg->dma_maskbits)) { + /* + * Currently this can only happen if IOMMU is enabled + * and the address width supported by the IOMMU hw is + * not enough for using the memory mapped IOVAs. + * + * If IOVA is VA, advice to try with '--iova-mode pa' + * which could solve some situations when IOVA VA is not + * really needed. + */ + RTE_LOG(ERR, EAL, + "%s(): couldn't allocate memory due to IOVA exceeding limits of current DMA mask\n", + __func__); + + /* + * If IOVA is VA and it is possible to run with IOVA PA, + * because user is root, give and advice for solving the + * problem. + */ + if ((rte_eal_iova_mode() == RTE_IOVA_VA) && + rte_eal_using_phys_addrs()) + RTE_LOG(ERR, EAL, + "%s(): Please try initializing EAL with --iova-mode=pa parameter\n", + __func__); + goto fail; + } + /* add newly minted memsegs to malloc heap */ elem = malloc_heap_add_memory(heap, msl, map_addr, alloc_sz); @@ -442,10 +487,9 @@ try_expand_heap(struct malloc_heap *heap, uint64_t pg_sz, size_t elt_size, int socket, unsigned int flags, size_t align, size_t bound, bool contig) { - struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config; int ret; - rte_rwlock_write_lock(&mcfg->memory_hotplug_lock); + rte_mcfg_mem_write_lock(); if (rte_eal_process_type() == RTE_PROC_PRIMARY) { ret = try_expand_heap_primary(heap, pg_sz, elt_size, socket, @@ -455,7 +499,7 @@ try_expand_heap(struct malloc_heap *heap, uint64_t pg_sz, size_t elt_size, flags, align, bound, contig); } - rte_rwlock_write_unlock(&mcfg->memory_hotplug_lock); + rte_mcfg_mem_write_unlock(); return ret; } @@ -778,7 +822,6 @@ malloc_heap_free_pages(void *aligned_start, size_t aligned_len) int malloc_heap_free(struct malloc_elem *elem) { - struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config; struct malloc_heap *heap; void *start, *aligned_start, *end, *aligned_end; size_t len, aligned_len, page_sz; @@ -814,6 +857,13 @@ malloc_heap_free(struct malloc_elem *elem) if (elem->size < page_sz) goto free_unlock; + /* if user requested to match allocations, the sizes must match - if not, + * we will defer freeing these hugepages until the entire original allocation + * can be freed + */ + if (internal_config.match_allocations && elem->size != elem->orig_size) + goto free_unlock; + /* probably, but let's make sure, as we may not be using up full page */ start = elem; len = elem->size; @@ -885,7 +935,7 @@ malloc_heap_free(struct malloc_elem *elem) /* now we can finally free us some pages */ - rte_rwlock_write_lock(&mcfg->memory_hotplug_lock); + rte_mcfg_mem_write_lock(); /* * we allow secondary processes to clear the heap of this allocated @@ -940,7 +990,7 @@ malloc_heap_free(struct malloc_elem *elem) RTE_LOG(DEBUG, EAL, "Heap on socket %d was shrunk by %zdMB\n", msl->socket_id, aligned_len >> 20ULL); - rte_rwlock_write_unlock(&mcfg->memory_hotplug_lock); + rte_mcfg_mem_write_unlock(); free_unlock: rte_spinlock_unlock(&(heap->lock)); return ret; @@ -1023,9 +1073,29 @@ malloc_heap_dump(struct malloc_heap *heap, FILE *f) rte_spinlock_unlock(&heap->lock); } -int -malloc_heap_add_external_memory(struct malloc_heap *heap, void *va_addr, - rte_iova_t iova_addrs[], unsigned int n_pages, size_t page_sz) +static int +destroy_elem(struct malloc_elem *elem, size_t len) +{ + struct malloc_heap *heap = elem->heap; + + /* notify all subscribers that a memory area is going to be removed */ + eal_memalloc_mem_event_notify(RTE_MEM_EVENT_FREE, elem, len); + + /* this element can be removed */ + malloc_elem_free_list_remove(elem); + malloc_elem_hide_region(elem, elem, len); + + heap->total_size -= len; + + memset(elem, 0, sizeof(*elem)); + + return 0; +} + +struct rte_memseg_list * +malloc_heap_create_external_seg(void *va_addr, rte_iova_t iova_addrs[], + unsigned int n_pages, size_t page_sz, const char *seg_name, + unsigned int socket_id) { struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config; char fbarray_name[RTE_FBARRAY_NAME_LEN]; @@ -1045,17 +1115,17 @@ malloc_heap_add_external_memory(struct malloc_heap *heap, void *va_addr, if (msl == NULL) { RTE_LOG(ERR, EAL, "Couldn't find empty memseg list\n"); rte_errno = ENOSPC; - return -1; + return NULL; } - snprintf(fbarray_name, sizeof(fbarray_name) - 1, "%s_%p", - heap->name, va_addr); + snprintf(fbarray_name, sizeof(fbarray_name), "%s_%p", + seg_name, va_addr); /* create the backing fbarray */ if (rte_fbarray_init(&msl->memseg_arr, fbarray_name, n_pages, sizeof(struct rte_memseg)) < 0) { RTE_LOG(ERR, EAL, "Couldn't create fbarray backing the memseg list\n"); - return -1; + return NULL; } arr = &msl->memseg_arr; @@ -1071,32 +1141,127 @@ malloc_heap_add_external_memory(struct malloc_heap *heap, void *va_addr, ms->len = page_sz; ms->nchannel = rte_memory_get_nchannel(); ms->nrank = rte_memory_get_nrank(); - ms->socket_id = heap->socket_id; + ms->socket_id = socket_id; } /* set up the memseg list */ msl->base_va = va_addr; msl->page_sz = page_sz; - msl->socket_id = heap->socket_id; + msl->socket_id = socket_id; msl->len = seg_len; msl->version = 0; msl->external = 1; + return msl; +} + +struct extseg_walk_arg { + void *va_addr; + size_t len; + struct rte_memseg_list *msl; +}; + +static int +extseg_walk(const struct rte_memseg_list *msl, void *arg) +{ + struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config; + struct extseg_walk_arg *wa = arg; + + if (msl->base_va == wa->va_addr && msl->len == wa->len) { + unsigned int found_idx; + + /* msl is const */ + found_idx = msl - mcfg->memsegs; + wa->msl = &mcfg->memsegs[found_idx]; + return 1; + } + return 0; +} + +struct rte_memseg_list * +malloc_heap_find_external_seg(void *va_addr, size_t len) +{ + struct extseg_walk_arg wa; + int res; + + wa.va_addr = va_addr; + wa.len = len; + + res = rte_memseg_list_walk_thread_unsafe(extseg_walk, &wa); + + if (res != 1) { + /* 0 means nothing was found, -1 shouldn't happen */ + if (res == 0) + rte_errno = ENOENT; + return NULL; + } + return wa.msl; +} + +int +malloc_heap_destroy_external_seg(struct rte_memseg_list *msl) +{ + /* destroy the fbarray backing this memory */ + if (rte_fbarray_destroy(&msl->memseg_arr) < 0) + return -1; + + /* reset the memseg list */ + memset(msl, 0, sizeof(*msl)); + + return 0; +} + +int +malloc_heap_add_external_memory(struct malloc_heap *heap, + struct rte_memseg_list *msl) +{ /* erase contents of new memory */ - memset(va_addr, 0, seg_len); + memset(msl->base_va, 0, msl->len); /* now, add newly minted memory to the malloc heap */ - malloc_heap_add_memory(heap, msl, va_addr, seg_len); + malloc_heap_add_memory(heap, msl, msl->base_va, msl->len); - heap->total_size += seg_len; + heap->total_size += msl->len; /* all done! */ RTE_LOG(DEBUG, EAL, "Added segment for heap %s starting at %p\n", - heap->name, va_addr); + heap->name, msl->base_va); + + /* notify all subscribers that a new memory area has been added */ + eal_memalloc_mem_event_notify(RTE_MEM_EVENT_ALLOC, + msl->base_va, msl->len); return 0; } +int +malloc_heap_remove_external_memory(struct malloc_heap *heap, void *va_addr, + size_t len) +{ + struct malloc_elem *elem = heap->first; + + /* find element with specified va address */ + while (elem != NULL && elem != va_addr) { + elem = elem->next; + /* stop if we've blown past our VA */ + if (elem > (struct malloc_elem *)va_addr) { + rte_errno = ENOENT; + return -1; + } + } + /* check if element was found */ + if (elem == NULL || elem->msl->len != len) { + rte_errno = ENOENT; + return -1; + } + /* if element's size is not equal to segment len, segment is busy */ + if (elem->state == ELEM_BUSY || elem->size != len) { + rte_errno = EBUSY; + return -1; + } + return destroy_elem(elem, len); +} + int malloc_heap_create(struct malloc_heap *heap, const char *heap_name) { @@ -1155,6 +1320,10 @@ rte_eal_malloc_heap_init(void) struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_config; unsigned int i; + if (internal_config.match_allocations) { + RTE_LOG(DEBUG, EAL, "Hugepages will be freed exactly as allocated.\n"); + } + if (rte_eal_process_type() == RTE_PROC_PRIMARY) { /* assign min socket ID to external heaps */ mcfg->next_socket_id = EXTERNAL_HEAP_MIN_SOCKET_ID; @@ -1165,7 +1334,7 @@ rte_eal_malloc_heap_init(void) char heap_name[RTE_HEAP_NAME_MAX_LEN]; int socket_id = rte_socket_id_by_idx(i); - snprintf(heap_name, sizeof(heap_name) - 1, + snprintf(heap_name, sizeof(heap_name), "socket_%i", socket_id); strlcpy(heap->name, heap_name, RTE_HEAP_NAME_MAX_LEN); heap->socket_id = socket_id; @@ -1175,7 +1344,7 @@ rte_eal_malloc_heap_init(void) if (register_mp_requests()) { RTE_LOG(ERR, EAL, "Couldn't register malloc multiprocess actions\n"); - rte_rwlock_read_unlock(&mcfg->memory_hotplug_lock); + rte_mcfg_mem_read_unlock(); return -1; } @@ -1183,7 +1352,7 @@ rte_eal_malloc_heap_init(void) * even come before primary itself is fully initialized, and secondaries * do not need to initialize the heap. */ - rte_rwlock_read_unlock(&mcfg->memory_hotplug_lock); + rte_mcfg_mem_read_unlock(); /* secondary process does not need to initialize anything */ if (rte_eal_process_type() != RTE_PROC_PRIMARY)