From: Vu Pham Date: Mon, 13 Apr 2020 21:17:48 +0000 (-0700) Subject: common/mlx5: refactor memory management X-Git-Url: http://git.droids-corp.org/?a=commitdiff_plain;h=b8dc6b0e29d86bfda4b635aa6e12469728c46e63;p=dpdk.git common/mlx5: refactor memory management Refactor common memory btree and cache management to common driver. Replace some input parameters of MR APIs to more common data structure like PD, port_id, share_cache,... so that multiple PMD drivers can use those MR APIs. Modify mlx5 net pmd driver to use MR management APIs from common driver. Signed-off-by: Vu Pham Acked-by: Viacheslav Ovsiienko --- diff --git a/drivers/common/mlx5/Makefile b/drivers/common/mlx5/Makefile index 13cc7392b9..0c67755225 100644 --- a/drivers/common/mlx5/Makefile +++ b/drivers/common/mlx5/Makefile @@ -18,6 +18,7 @@ SRCS-y += mlx5_devx_cmds.c SRCS-y += mlx5_common.c SRCS-y += mlx5_nl.c SRCS-y += mlx5_common_mp.c +SRCS-y += mlx5_common_mr.c ifeq ($(CONFIG_RTE_IBVERBS_LINK_DLOPEN),y) INSTALL-y-lib += $(LIB_GLUE) endif diff --git a/drivers/common/mlx5/meson.build b/drivers/common/mlx5/meson.build index ee587d57fa..347d282193 100644 --- a/drivers/common/mlx5/meson.build +++ b/drivers/common/mlx5/meson.build @@ -55,6 +55,7 @@ sources = files( 'mlx5_common.c', 'mlx5_nl.c', 'mlx5_common_mp.c', + 'mlx5_common_mr.c', ) if not dlopen_ibverbs sources += files('mlx5_glue.c') diff --git a/drivers/common/mlx5/mlx5_common_mr.c b/drivers/common/mlx5/mlx5_common_mr.c new file mode 100644 index 0000000000..9d4a06dd5b --- /dev/null +++ b/drivers/common/mlx5/mlx5_common_mr.c @@ -0,0 +1,1108 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright 2016 6WIND S.A. + * Copyright 2020 Mellanox Technologies, Ltd + */ +#include +#include +#include +#include +#include + +#include "mlx5_glue.h" +#include "mlx5_common_mp.h" +#include "mlx5_common_mr.h" +#include "mlx5_common_utils.h" + +struct mr_find_contig_memsegs_data { + uintptr_t addr; + uintptr_t start; + uintptr_t end; + const struct rte_memseg_list *msl; +}; + +/** + * Expand B-tree table to a given size. Can't be called with holding + * memory_hotplug_lock or share_cache.rwlock due to rte_realloc(). + * + * @param bt + * Pointer to B-tree structure. + * @param n + * Number of entries for expansion. + * + * @return + * 0 on success, -1 on failure. + */ +static int +mr_btree_expand(struct mlx5_mr_btree *bt, int n) +{ + void *mem; + int ret = 0; + + if (n <= bt->size) + return ret; + /* + * Downside of directly using rte_realloc() is that SOCKET_ID_ANY is + * used inside if there's no room to expand. Because this is a quite + * rare case and a part of very slow path, it is very acceptable. + * Initially cache_bh[] will be given practically enough space and once + * it is expanded, expansion wouldn't be needed again ever. + */ + mem = rte_realloc(bt->table, n * sizeof(struct mr_cache_entry), 0); + if (mem == NULL) { + /* Not an error, B-tree search will be skipped. */ + DRV_LOG(WARNING, "failed to expand MR B-tree (%p) table", + (void *)bt); + ret = -1; + } else { + DRV_LOG(DEBUG, "expanded MR B-tree table (size=%u)", n); + bt->table = mem; + bt->size = n; + } + return ret; +} + +/** + * Look up LKey from given B-tree lookup table, store the last index and return + * searched LKey. + * + * @param bt + * Pointer to B-tree structure. + * @param[out] idx + * Pointer to index. Even on search failure, returns index where it stops + * searching so that index can be used when inserting a new entry. + * @param addr + * Search key. + * + * @return + * Searched LKey on success, UINT32_MAX on no match. + */ +static uint32_t +mr_btree_lookup(struct mlx5_mr_btree *bt, uint16_t *idx, uintptr_t addr) +{ + struct mr_cache_entry *lkp_tbl; + uint16_t n; + uint16_t base = 0; + + MLX5_ASSERT(bt != NULL); + lkp_tbl = *bt->table; + n = bt->len; + /* First entry must be NULL for comparison. */ + MLX5_ASSERT(bt->len > 0 || (lkp_tbl[0].start == 0 && + lkp_tbl[0].lkey == UINT32_MAX)); + /* Binary search. */ + do { + register uint16_t delta = n >> 1; + + if (addr < lkp_tbl[base + delta].start) { + n = delta; + } else { + base += delta; + n -= delta; + } + } while (n > 1); + MLX5_ASSERT(addr >= lkp_tbl[base].start); + *idx = base; + if (addr < lkp_tbl[base].end) + return lkp_tbl[base].lkey; + /* Not found. */ + return UINT32_MAX; +} + +/** + * Insert an entry to B-tree lookup table. + * + * @param bt + * Pointer to B-tree structure. + * @param entry + * Pointer to new entry to insert. + * + * @return + * 0 on success, -1 on failure. + */ +static int +mr_btree_insert(struct mlx5_mr_btree *bt, struct mr_cache_entry *entry) +{ + struct mr_cache_entry *lkp_tbl; + uint16_t idx = 0; + size_t shift; + + MLX5_ASSERT(bt != NULL); + MLX5_ASSERT(bt->len <= bt->size); + MLX5_ASSERT(bt->len > 0); + lkp_tbl = *bt->table; + /* Find out the slot for insertion. */ + if (mr_btree_lookup(bt, &idx, entry->start) != UINT32_MAX) { + DRV_LOG(DEBUG, + "abort insertion to B-tree(%p): already exist at" + " idx=%u [0x%" PRIxPTR ", 0x%" PRIxPTR ") lkey=0x%x", + (void *)bt, idx, entry->start, entry->end, entry->lkey); + /* Already exist, return. */ + return 0; + } + /* If table is full, return error. */ + if (unlikely(bt->len == bt->size)) { + bt->overflow = 1; + return -1; + } + /* Insert entry. */ + ++idx; + shift = (bt->len - idx) * sizeof(struct mr_cache_entry); + if (shift) + memmove(&lkp_tbl[idx + 1], &lkp_tbl[idx], shift); + lkp_tbl[idx] = *entry; + bt->len++; + DRV_LOG(DEBUG, + "inserted B-tree(%p)[%u]," + " [0x%" PRIxPTR ", 0x%" PRIxPTR ") lkey=0x%x", + (void *)bt, idx, entry->start, entry->end, entry->lkey); + return 0; +} + +/** + * Initialize B-tree and allocate memory for lookup table. + * + * @param bt + * Pointer to B-tree structure. + * @param n + * Number of entries to allocate. + * @param socket + * NUMA socket on which memory must be allocated. + * + * @return + * 0 on success, a negative errno value otherwise and rte_errno is set. + */ +int +mlx5_mr_btree_init(struct mlx5_mr_btree *bt, int n, int socket) +{ + if (bt == NULL) { + rte_errno = EINVAL; + return -rte_errno; + } + MLX5_ASSERT(!bt->table && !bt->size); + memset(bt, 0, sizeof(*bt)); + bt->table = rte_calloc_socket("B-tree table", + n, sizeof(struct mr_cache_entry), + 0, socket); + if (bt->table == NULL) { + rte_errno = ENOMEM; + DEBUG("failed to allocate memory for btree cache on socket %d", + socket); + return -rte_errno; + } + bt->size = n; + /* First entry must be NULL for binary search. */ + (*bt->table)[bt->len++] = (struct mr_cache_entry) { + .lkey = UINT32_MAX, + }; + DEBUG("initialized B-tree %p with table %p", + (void *)bt, (void *)bt->table); + return 0; +} + +/** + * Free B-tree resources. + * + * @param bt + * Pointer to B-tree structure. + */ +void +mlx5_mr_btree_free(struct mlx5_mr_btree *bt) +{ + if (bt == NULL) + return; + DEBUG("freeing B-tree %p with table %p", + (void *)bt, (void *)bt->table); + rte_free(bt->table); + memset(bt, 0, sizeof(*bt)); +} + +/** + * Dump all the entries in a B-tree + * + * @param bt + * Pointer to B-tree structure. + */ +void +mlx5_mr_btree_dump(struct mlx5_mr_btree *bt __rte_unused) +{ +#ifdef RTE_LIBRTE_MLX5_DEBUG + int idx; + struct mr_cache_entry *lkp_tbl; + + if (bt == NULL) + return; + lkp_tbl = *bt->table; + for (idx = 0; idx < bt->len; ++idx) { + struct mr_cache_entry *entry = &lkp_tbl[idx]; + + DEBUG("B-tree(%p)[%u]," + " [0x%" PRIxPTR ", 0x%" PRIxPTR ") lkey=0x%x", + (void *)bt, idx, entry->start, entry->end, entry->lkey); + } +#endif +} + +/** + * Find virtually contiguous memory chunk in a given MR. + * + * @param dev + * Pointer to MR structure. + * @param[out] entry + * Pointer to returning MR cache entry. If not found, this will not be + * updated. + * @param start_idx + * Start index of the memseg bitmap. + * + * @return + * Next index to go on lookup. + */ +static int +mr_find_next_chunk(struct mlx5_mr *mr, struct mr_cache_entry *entry, + int base_idx) +{ + uintptr_t start = 0; + uintptr_t end = 0; + uint32_t idx = 0; + + /* MR for external memory doesn't have memseg list. */ + if (mr->msl == NULL) { + struct ibv_mr *ibv_mr = mr->ibv_mr; + + MLX5_ASSERT(mr->ms_bmp_n == 1); + MLX5_ASSERT(mr->ms_n == 1); + MLX5_ASSERT(base_idx == 0); + /* + * Can't search it from memseg list but get it directly from + * verbs MR as there's only one chunk. + */ + entry->start = (uintptr_t)ibv_mr->addr; + entry->end = (uintptr_t)ibv_mr->addr + mr->ibv_mr->length; + entry->lkey = rte_cpu_to_be_32(mr->ibv_mr->lkey); + /* Returning 1 ends iteration. */ + return 1; + } + for (idx = base_idx; idx < mr->ms_bmp_n; ++idx) { + if (rte_bitmap_get(mr->ms_bmp, idx)) { + const struct rte_memseg_list *msl; + const struct rte_memseg *ms; + + msl = mr->msl; + ms = rte_fbarray_get(&msl->memseg_arr, + mr->ms_base_idx + idx); + MLX5_ASSERT(msl->page_sz == ms->hugepage_sz); + if (!start) + start = ms->addr_64; + end = ms->addr_64 + ms->hugepage_sz; + } else if (start) { + /* Passed the end of a fragment. */ + break; + } + } + if (start) { + /* Found one chunk. */ + entry->start = start; + entry->end = end; + entry->lkey = rte_cpu_to_be_32(mr->ibv_mr->lkey); + } + return idx; +} + +/** + * Insert a MR to the global B-tree cache. It may fail due to low-on-memory. + * Then, this entry will have to be searched by mr_lookup_list() in + * mlx5_mr_create() on miss. + * + * @param share_cache + * Pointer to a global shared MR cache. + * @param mr + * Pointer to MR to insert. + * + * @return + * 0 on success, -1 on failure. + */ +int +mlx5_mr_insert_cache(struct mlx5_mr_share_cache *share_cache, + struct mlx5_mr *mr) +{ + unsigned int n; + + DRV_LOG(DEBUG, "Inserting MR(%p) to global cache(%p)", + (void *)mr, (void *)share_cache); + for (n = 0; n < mr->ms_bmp_n; ) { + struct mr_cache_entry entry; + + memset(&entry, 0, sizeof(entry)); + /* Find a contiguous chunk and advance the index. */ + n = mr_find_next_chunk(mr, &entry, n); + if (!entry.end) + break; + if (mr_btree_insert(&share_cache->cache, &entry) < 0) { + /* + * Overflowed, but the global table cannot be expanded + * because of deadlock. + */ + return -1; + } + } + return 0; +} + +/** + * Look up address in the original global MR list. + * + * @param share_cache + * Pointer to a global shared MR cache. + * @param[out] entry + * Pointer to returning MR cache entry. If no match, this will not be updated. + * @param addr + * Search key. + * + * @return + * Found MR on match, NULL otherwise. + */ +struct mlx5_mr * +mlx5_mr_lookup_list(struct mlx5_mr_share_cache *share_cache, + struct mr_cache_entry *entry, uintptr_t addr) +{ + struct mlx5_mr *mr; + + /* Iterate all the existing MRs. */ + LIST_FOREACH(mr, &share_cache->mr_list, mr) { + unsigned int n; + + if (mr->ms_n == 0) + continue; + for (n = 0; n < mr->ms_bmp_n; ) { + struct mr_cache_entry ret; + + memset(&ret, 0, sizeof(ret)); + n = mr_find_next_chunk(mr, &ret, n); + if (addr >= ret.start && addr < ret.end) { + /* Found. */ + *entry = ret; + return mr; + } + } + } + return NULL; +} + +/** + * Look up address on global MR cache. + * + * @param share_cache + * Pointer to a global shared MR cache. + * @param[out] entry + * Pointer to returning MR cache entry. If no match, this will not be updated. + * @param addr + * Search key. + * + * @return + * Searched LKey on success, UINT32_MAX on failure and rte_errno is set. + */ +uint32_t +mlx5_mr_lookup_cache(struct mlx5_mr_share_cache *share_cache, + struct mr_cache_entry *entry, uintptr_t addr) +{ + uint16_t idx; + uint32_t lkey = UINT32_MAX; + struct mlx5_mr *mr; + + /* + * If the global cache has overflowed since it failed to expand the + * B-tree table, it can't have all the existing MRs. Then, the address + * has to be searched by traversing the original MR list instead, which + * is very slow path. Otherwise, the global cache is all inclusive. + */ + if (!unlikely(share_cache->cache.overflow)) { + lkey = mr_btree_lookup(&share_cache->cache, &idx, addr); + if (lkey != UINT32_MAX) + *entry = (*share_cache->cache.table)[idx]; + } else { + /* Falling back to the slowest path. */ + mr = mlx5_mr_lookup_list(share_cache, entry, addr); + if (mr != NULL) + lkey = entry->lkey; + } + MLX5_ASSERT(lkey == UINT32_MAX || (addr >= entry->start && + addr < entry->end)); + return lkey; +} + +/** + * Free MR resources. MR lock must not be held to avoid a deadlock. rte_free() + * can raise memory free event and the callback function will spin on the lock. + * + * @param mr + * Pointer to MR to free. + */ +static void +mr_free(struct mlx5_mr *mr) +{ + if (mr == NULL) + return; + DRV_LOG(DEBUG, "freeing MR(%p):", (void *)mr); + if (mr->ibv_mr != NULL) + claim_zero(mlx5_glue->dereg_mr(mr->ibv_mr)); + if (mr->ms_bmp != NULL) + rte_bitmap_free(mr->ms_bmp); + rte_free(mr); +} + +void +mlx5_mr_rebuild_cache(struct mlx5_mr_share_cache *share_cache) +{ + struct mlx5_mr *mr; + + DRV_LOG(DEBUG, "Rebuild dev cache[] %p", (void *)share_cache); + /* Flush cache to rebuild. */ + share_cache->cache.len = 1; + share_cache->cache.overflow = 0; + /* Iterate all the existing MRs. */ + LIST_FOREACH(mr, &share_cache->mr_list, mr) + if (mlx5_mr_insert_cache(share_cache, mr) < 0) + return; +} + +/** + * Release resources of detached MR having no online entry. + * + * @param share_cache + * Pointer to a global shared MR cache. + */ +static void +mlx5_mr_garbage_collect(struct mlx5_mr_share_cache *share_cache) +{ + struct mlx5_mr *mr_next; + struct mlx5_mr_list free_list = LIST_HEAD_INITIALIZER(free_list); + + /* Must be called from the primary process. */ + MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_PRIMARY); + /* + * MR can't be freed with holding the lock because rte_free() could call + * memory free callback function. This will be a deadlock situation. + */ + rte_rwlock_write_lock(&share_cache->rwlock); + /* Detach the whole free list and release it after unlocking. */ + free_list = share_cache->mr_free_list; + LIST_INIT(&share_cache->mr_free_list); + rte_rwlock_write_unlock(&share_cache->rwlock); + /* Release resources. */ + mr_next = LIST_FIRST(&free_list); + while (mr_next != NULL) { + struct mlx5_mr *mr = mr_next; + + mr_next = LIST_NEXT(mr, mr); + mr_free(mr); + } +} + +/* Called during rte_memseg_contig_walk() by mlx5_mr_create(). */ +static int +mr_find_contig_memsegs_cb(const struct rte_memseg_list *msl, + const struct rte_memseg *ms, size_t len, void *arg) +{ + struct mr_find_contig_memsegs_data *data = arg; + + if (data->addr < ms->addr_64 || data->addr >= ms->addr_64 + len) + return 0; + /* Found, save it and stop walking. */ + data->start = ms->addr_64; + data->end = ms->addr_64 + len; + data->msl = msl; + return 1; +} + +/** + * Create a new global Memory Region (MR) for a missing virtual address. + * This API should be called on a secondary process, then a request is sent to + * the primary process in order to create a MR for the address. As the global MR + * list is on the shared memory, following LKey lookup should succeed unless the + * request fails. + * + * @param pd + * Pointer to ibv_pd of a device (net, regex, vdpa,...). + * @param share_cache + * Pointer to a global shared MR cache. + * @param[out] entry + * Pointer to returning MR cache entry, found in the global cache or newly + * created. If failed to create one, this will not be updated. + * @param addr + * Target virtual address to register. + * @param mr_ext_memseg_en + * Configurable flag about external memory segment enable or not. + * + * @return + * Searched LKey on success, UINT32_MAX on failure and rte_errno is set. + */ +static uint32_t +mlx5_mr_create_secondary(struct ibv_pd *pd __rte_unused, + struct mlx5_mp_id *mp_id, + struct mlx5_mr_share_cache *share_cache, + struct mr_cache_entry *entry, uintptr_t addr, + unsigned int mr_ext_memseg_en __rte_unused) +{ + int ret; + + DEBUG("port %u requesting MR creation for address (%p)", + mp_id->port_id, (void *)addr); + ret = mlx5_mp_req_mr_create(mp_id, addr); + if (ret) { + DEBUG("Fail to request MR creation for address (%p)", + (void *)addr); + return UINT32_MAX; + } + rte_rwlock_read_lock(&share_cache->rwlock); + /* Fill in output data. */ + mlx5_mr_lookup_cache(share_cache, entry, addr); + /* Lookup can't fail. */ + MLX5_ASSERT(entry->lkey != UINT32_MAX); + rte_rwlock_read_unlock(&share_cache->rwlock); + DEBUG("MR CREATED by primary process for %p:\n" + " [0x%" PRIxPTR ", 0x%" PRIxPTR "), lkey=0x%x", + (void *)addr, entry->start, entry->end, entry->lkey); + return entry->lkey; +} + +/** + * Create a new global Memory Region (MR) for a missing virtual address. + * Register entire virtually contiguous memory chunk around the address. + * + * @param pd + * Pointer to ibv_pd of a device (net, regex, vdpa,...). + * @param share_cache + * Pointer to a global shared MR cache. + * @param[out] entry + * Pointer to returning MR cache entry, found in the global cache or newly + * created. If failed to create one, this will not be updated. + * @param addr + * Target virtual address to register. + * @param mr_ext_memseg_en + * Configurable flag about external memory segment enable or not. + * + * @return + * Searched LKey on success, UINT32_MAX on failure and rte_errno is set. + */ +uint32_t +mlx5_mr_create_primary(struct ibv_pd *pd, + struct mlx5_mr_share_cache *share_cache, + struct mr_cache_entry *entry, uintptr_t addr, + unsigned int mr_ext_memseg_en) +{ + struct mr_find_contig_memsegs_data data = {.addr = addr, }; + struct mr_find_contig_memsegs_data data_re; + const struct rte_memseg_list *msl; + const struct rte_memseg *ms; + struct mlx5_mr *mr = NULL; + int ms_idx_shift = -1; + uint32_t bmp_size; + void *bmp_mem; + uint32_t ms_n; + uint32_t n; + size_t len; + + DRV_LOG(DEBUG, "Creating a MR using address (%p)", (void *)addr); + /* + * Release detached MRs if any. This can't be called with holding either + * memory_hotplug_lock or share_cache->rwlock. MRs on the free list have + * been detached by the memory free event but it couldn't be released + * inside the callback due to deadlock. As a result, releasing resources + * is quite opportunistic. + */ + mlx5_mr_garbage_collect(share_cache); + /* + * If enabled, find out a contiguous virtual address chunk in use, to + * which the given address belongs, in order to register maximum range. + * In the best case where mempools are not dynamically recreated and + * '--socket-mem' is specified as an EAL option, it is very likely to + * have only one MR(LKey) per a socket and per a hugepage-size even + * though the system memory is highly fragmented. As the whole memory + * chunk will be pinned by kernel, it can't be reused unless entire + * chunk is freed from EAL. + * + * If disabled, just register one memseg (page). Then, memory + * consumption will be minimized but it may drop performance if there + * are many MRs to lookup on the datapath. + */ + if (!mr_ext_memseg_en) { + data.msl = rte_mem_virt2memseg_list((void *)addr); + data.start = RTE_ALIGN_FLOOR(addr, data.msl->page_sz); + data.end = data.start + data.msl->page_sz; + } else if (!rte_memseg_contig_walk(mr_find_contig_memsegs_cb, &data)) { + DRV_LOG(WARNING, + "Unable to find virtually contiguous" + " chunk for address (%p)." + " rte_memseg_contig_walk() failed.", (void *)addr); + rte_errno = ENXIO; + goto err_nolock; + } +alloc_resources: + /* Addresses must be page-aligned. */ + MLX5_ASSERT(data.msl); + MLX5_ASSERT(rte_is_aligned((void *)data.start, data.msl->page_sz)); + MLX5_ASSERT(rte_is_aligned((void *)data.end, data.msl->page_sz)); + msl = data.msl; + ms = rte_mem_virt2memseg((void *)data.start, msl); + len = data.end - data.start; + MLX5_ASSERT(ms); + MLX5_ASSERT(msl->page_sz == ms->hugepage_sz); + /* Number of memsegs in the range. */ + ms_n = len / msl->page_sz; + DEBUG("Extending %p to [0x%" PRIxPTR ", 0x%" PRIxPTR ")," + " page_sz=0x%" PRIx64 ", ms_n=%u", + (void *)addr, data.start, data.end, msl->page_sz, ms_n); + /* Size of memory for bitmap. */ + bmp_size = rte_bitmap_get_memory_footprint(ms_n); + mr = rte_zmalloc_socket(NULL, + RTE_ALIGN_CEIL(sizeof(*mr), + RTE_CACHE_LINE_SIZE) + + bmp_size, + RTE_CACHE_LINE_SIZE, msl->socket_id); + if (mr == NULL) { + DEBUG("Unable to allocate memory for a new MR of" + " address (%p).", (void *)addr); + rte_errno = ENOMEM; + goto err_nolock; + } + mr->msl = msl; + /* + * Save the index of the first memseg and initialize memseg bitmap. To + * see if a memseg of ms_idx in the memseg-list is still valid, check: + * rte_bitmap_get(mr->bmp, ms_idx - mr->ms_base_idx) + */ + mr->ms_base_idx = rte_fbarray_find_idx(&msl->memseg_arr, ms); + bmp_mem = RTE_PTR_ALIGN_CEIL(mr + 1, RTE_CACHE_LINE_SIZE); + mr->ms_bmp = rte_bitmap_init(ms_n, bmp_mem, bmp_size); + if (mr->ms_bmp == NULL) { + DEBUG("Unable to initialize bitmap for a new MR of" + " address (%p).", (void *)addr); + rte_errno = EINVAL; + goto err_nolock; + } + /* + * Should recheck whether the extended contiguous chunk is still valid. + * Because memory_hotplug_lock can't be held if there's any memory + * related calls in a critical path, resource allocation above can't be + * locked. If the memory has been changed at this point, try again with + * just single page. If not, go on with the big chunk atomically from + * here. + */ + rte_mcfg_mem_read_lock(); + data_re = data; + if (len > msl->page_sz && + !rte_memseg_contig_walk(mr_find_contig_memsegs_cb, &data_re)) { + DEBUG("Unable to find virtually contiguous" + " chunk for address (%p)." + " rte_memseg_contig_walk() failed.", (void *)addr); + rte_errno = ENXIO; + goto err_memlock; + } + if (data.start != data_re.start || data.end != data_re.end) { + /* + * The extended contiguous chunk has been changed. Try again + * with single memseg instead. + */ + data.start = RTE_ALIGN_FLOOR(addr, msl->page_sz); + data.end = data.start + msl->page_sz; + rte_mcfg_mem_read_unlock(); + mr_free(mr); + goto alloc_resources; + } + MLX5_ASSERT(data.msl == data_re.msl); + rte_rwlock_write_lock(&share_cache->rwlock); + /* + * Check the address is really missing. If other thread already created + * one or it is not found due to overflow, abort and return. + */ + if (mlx5_mr_lookup_cache(share_cache, entry, addr) != UINT32_MAX) { + /* + * Insert to the global cache table. It may fail due to + * low-on-memory. Then, this entry will have to be searched + * here again. + */ + mr_btree_insert(&share_cache->cache, entry); + DEBUG("Found MR for %p on final lookup, abort", (void *)addr); + rte_rwlock_write_unlock(&share_cache->rwlock); + rte_mcfg_mem_read_unlock(); + /* + * Must be unlocked before calling rte_free() because + * mlx5_mr_mem_event_free_cb() can be called inside. + */ + mr_free(mr); + return entry->lkey; + } + /* + * Trim start and end addresses for verbs MR. Set bits for registering + * memsegs but exclude already registered ones. Bitmap can be + * fragmented. + */ + for (n = 0; n < ms_n; ++n) { + uintptr_t start; + struct mr_cache_entry ret; + + memset(&ret, 0, sizeof(ret)); + start = data_re.start + n * msl->page_sz; + /* Exclude memsegs already registered by other MRs. */ + if (mlx5_mr_lookup_cache(share_cache, &ret, start) == + UINT32_MAX) { + /* + * Start from the first unregistered memseg in the + * extended range. + */ + if (ms_idx_shift == -1) { + mr->ms_base_idx += n; + data.start = start; + ms_idx_shift = n; + } + data.end = start + msl->page_sz; + rte_bitmap_set(mr->ms_bmp, n - ms_idx_shift); + ++mr->ms_n; + } + } + len = data.end - data.start; + mr->ms_bmp_n = len / msl->page_sz; + MLX5_ASSERT(ms_idx_shift + mr->ms_bmp_n <= ms_n); + /* + * Finally create a verbs MR for the memory chunk. ibv_reg_mr() can be + * called with holding the memory lock because it doesn't use + * mlx5_alloc_buf_extern() which eventually calls rte_malloc_socket() + * through mlx5_alloc_verbs_buf(). + */ + mr->ibv_mr = mlx5_glue->reg_mr(pd, (void *)data.start, len, + IBV_ACCESS_LOCAL_WRITE | + IBV_ACCESS_RELAXED_ORDERING); + if (mr->ibv_mr == NULL) { + DEBUG("Fail to create a verbs MR for address (%p)", + (void *)addr); + rte_errno = EINVAL; + goto err_mrlock; + } + MLX5_ASSERT((uintptr_t)mr->ibv_mr->addr == data.start); + MLX5_ASSERT(mr->ibv_mr->length == len); + LIST_INSERT_HEAD(&share_cache->mr_list, mr, mr); + DEBUG("MR CREATED (%p) for %p:\n" + " [0x%" PRIxPTR ", 0x%" PRIxPTR ")," + " lkey=0x%x base_idx=%u ms_n=%u, ms_bmp_n=%u", + (void *)mr, (void *)addr, data.start, data.end, + rte_cpu_to_be_32(mr->ibv_mr->lkey), + mr->ms_base_idx, mr->ms_n, mr->ms_bmp_n); + /* Insert to the global cache table. */ + mlx5_mr_insert_cache(share_cache, mr); + /* Fill in output data. */ + mlx5_mr_lookup_cache(share_cache, entry, addr); + /* Lookup can't fail. */ + MLX5_ASSERT(entry->lkey != UINT32_MAX); + rte_rwlock_write_unlock(&share_cache->rwlock); + rte_mcfg_mem_read_unlock(); + return entry->lkey; +err_mrlock: + rte_rwlock_write_unlock(&share_cache->rwlock); +err_memlock: + rte_mcfg_mem_read_unlock(); +err_nolock: + /* + * In case of error, as this can be called in a datapath, a warning + * message per an error is preferable instead. Must be unlocked before + * calling rte_free() because mlx5_mr_mem_event_free_cb() can be called + * inside. + */ + mr_free(mr); + return UINT32_MAX; +} + +/** + * Create a new global Memory Region (MR) for a missing virtual address. + * This can be called from primary and secondary process. + * + * @param pd + * Pointer to ibv_pd of a device (net, regex, vdpa,...). + * @param share_cache + * Pointer to a global shared MR cache. + * @param[out] entry + * Pointer to returning MR cache entry, found in the global cache or newly + * created. If failed to create one, this will not be updated. + * @param addr + * Target virtual address to register. + * + * @return + * Searched LKey on success, UINT32_MAX on failure and rte_errno is set. + */ +static uint32_t +mlx5_mr_create(struct ibv_pd *pd, struct mlx5_mp_id *mp_id, + struct mlx5_mr_share_cache *share_cache, + struct mr_cache_entry *entry, uintptr_t addr, + unsigned int mr_ext_memseg_en) +{ + uint32_t ret = 0; + + switch (rte_eal_process_type()) { + case RTE_PROC_PRIMARY: + ret = mlx5_mr_create_primary(pd, share_cache, entry, + addr, mr_ext_memseg_en); + break; + case RTE_PROC_SECONDARY: + ret = mlx5_mr_create_secondary(pd, mp_id, share_cache, entry, + addr, mr_ext_memseg_en); + break; + default: + break; + } + return ret; +} + +/** + * Look up address in the global MR cache table. If not found, create a new MR. + * Insert the found/created entry to local bottom-half cache table. + * + * @param pd + * Pointer to ibv_pd of a device (net, regex, vdpa,...). + * @param share_cache + * Pointer to a global shared MR cache. + * @param mr_ctrl + * Pointer to per-queue MR control structure. + * @param[out] entry + * Pointer to returning MR cache entry, found in the global cache or newly + * created. If failed to create one, this is not written. + * @param addr + * Search key. + * + * @return + * Searched LKey on success, UINT32_MAX on no match. + */ +static uint32_t +mr_lookup_caches(struct ibv_pd *pd, struct mlx5_mp_id *mp_id, + struct mlx5_mr_share_cache *share_cache, + struct mlx5_mr_ctrl *mr_ctrl, + struct mr_cache_entry *entry, uintptr_t addr, + unsigned int mr_ext_memseg_en) +{ + struct mlx5_mr_btree *bt = &mr_ctrl->cache_bh; + uint32_t lkey; + uint16_t idx; + + /* If local cache table is full, try to double it. */ + if (unlikely(bt->len == bt->size)) + mr_btree_expand(bt, bt->size << 1); + /* Look up in the global cache. */ + rte_rwlock_read_lock(&share_cache->rwlock); + lkey = mr_btree_lookup(&share_cache->cache, &idx, addr); + if (lkey != UINT32_MAX) { + /* Found. */ + *entry = (*share_cache->cache.table)[idx]; + rte_rwlock_read_unlock(&share_cache->rwlock); + /* + * Update local cache. Even if it fails, return the found entry + * to update top-half cache. Next time, this entry will be found + * in the global cache. + */ + mr_btree_insert(bt, entry); + return lkey; + } + rte_rwlock_read_unlock(&share_cache->rwlock); + /* First time to see the address? Create a new MR. */ + lkey = mlx5_mr_create(pd, mp_id, share_cache, entry, addr, + mr_ext_memseg_en); + /* + * Update the local cache if successfully created a new global MR. Even + * if failed to create one, there's no action to take in this datapath + * code. As returning LKey is invalid, this will eventually make HW + * fail. + */ + if (lkey != UINT32_MAX) + mr_btree_insert(bt, entry); + return lkey; +} + +/** + * Bottom-half of LKey search on datapath. First search in cache_bh[] and if + * misses, search in the global MR cache table and update the new entry to + * per-queue local caches. + * + * @param pd + * Pointer to ibv_pd of a device (net, regex, vdpa,...). + * @param share_cache + * Pointer to a global shared MR cache. + * @param mr_ctrl + * Pointer to per-queue MR control structure. + * @param addr + * Search key. + * + * @return + * Searched LKey on success, UINT32_MAX on no match. + */ +uint32_t mlx5_mr_addr2mr_bh(struct ibv_pd *pd, struct mlx5_mp_id *mp_id, + struct mlx5_mr_share_cache *share_cache, + struct mlx5_mr_ctrl *mr_ctrl, + uintptr_t addr, unsigned int mr_ext_memseg_en) +{ + uint32_t lkey; + uint16_t bh_idx = 0; + /* Victim in top-half cache to replace with new entry. */ + struct mr_cache_entry *repl = &mr_ctrl->cache[mr_ctrl->head]; + + /* Binary-search MR translation table. */ + lkey = mr_btree_lookup(&mr_ctrl->cache_bh, &bh_idx, addr); + /* Update top-half cache. */ + if (likely(lkey != UINT32_MAX)) { + *repl = (*mr_ctrl->cache_bh.table)[bh_idx]; + } else { + /* + * If missed in local lookup table, search in the global cache + * and local cache_bh[] will be updated inside if possible. + * Top-half cache entry will also be updated. + */ + lkey = mr_lookup_caches(pd, mp_id, share_cache, mr_ctrl, + repl, addr, mr_ext_memseg_en); + if (unlikely(lkey == UINT32_MAX)) + return UINT32_MAX; + } + /* Update the most recently used entry. */ + mr_ctrl->mru = mr_ctrl->head; + /* Point to the next victim, the oldest. */ + mr_ctrl->head = (mr_ctrl->head + 1) % MLX5_MR_CACHE_N; + return lkey; +} + +/** + * Release all the created MRs and resources on global MR cache of a device. + * list. + * + * @param share_cache + * Pointer to a global shared MR cache. + */ +void +mlx5_mr_release_cache(struct mlx5_mr_share_cache *share_cache) +{ + struct mlx5_mr *mr_next; + + rte_rwlock_write_lock(&share_cache->rwlock); + /* Detach from MR list and move to free list. */ + mr_next = LIST_FIRST(&share_cache->mr_list); + while (mr_next != NULL) { + struct mlx5_mr *mr = mr_next; + + mr_next = LIST_NEXT(mr, mr); + LIST_REMOVE(mr, mr); + LIST_INSERT_HEAD(&share_cache->mr_free_list, mr, mr); + } + LIST_INIT(&share_cache->mr_list); + /* Free global cache. */ + mlx5_mr_btree_free(&share_cache->cache); + rte_rwlock_write_unlock(&share_cache->rwlock); + /* Free all remaining MRs. */ + mlx5_mr_garbage_collect(share_cache); +} + +/** + * Flush all of the local cache entries. + * + * @param mr_ctrl + * Pointer to per-queue MR local cache. + */ +void +mlx5_mr_flush_local_cache(struct mlx5_mr_ctrl *mr_ctrl) +{ + /* Reset the most-recently-used index. */ + mr_ctrl->mru = 0; + /* Reset the linear search array. */ + mr_ctrl->head = 0; + memset(mr_ctrl->cache, 0, sizeof(mr_ctrl->cache)); + /* Reset the B-tree table. */ + mr_ctrl->cache_bh.len = 1; + mr_ctrl->cache_bh.overflow = 0; + /* Update the generation number. */ + mr_ctrl->cur_gen = *mr_ctrl->dev_gen_ptr; + DRV_LOG(DEBUG, "mr_ctrl(%p): flushed, cur_gen=%d", + (void *)mr_ctrl, mr_ctrl->cur_gen); +} + +/** + * Creates a memory region for external memory, that is memory which is not + * part of the DPDK memory segments. + * + * @param pd + * Pointer to ibv_pd of a device (net, regex, vdpa,...). + * @param addr + * Starting virtual address of memory. + * @param len + * Length of memory segment being mapped. + * @param socked_id + * Socket to allocate heap memory for the control structures. + * + * @return + * Pointer to MR structure on success, NULL otherwise. + */ +struct mlx5_mr * +mlx5_create_mr_ext(struct ibv_pd *pd, uintptr_t addr, size_t len, int socket_id) +{ + struct mlx5_mr *mr = NULL; + + mr = rte_zmalloc_socket(NULL, + RTE_ALIGN_CEIL(sizeof(*mr), + RTE_CACHE_LINE_SIZE), + RTE_CACHE_LINE_SIZE, socket_id); + if (mr == NULL) + return NULL; + mr->ibv_mr = mlx5_glue->reg_mr(pd, (void *)addr, len, + IBV_ACCESS_LOCAL_WRITE | + IBV_ACCESS_RELAXED_ORDERING); + if (mr->ibv_mr == NULL) { + DRV_LOG(WARNING, + "Fail to create a verbs MR for address (%p)", + (void *)addr); + rte_free(mr); + return NULL; + } + mr->msl = NULL; /* Mark it is external memory. */ + mr->ms_bmp = NULL; + mr->ms_n = 1; + mr->ms_bmp_n = 1; + DRV_LOG(DEBUG, + "MR CREATED (%p) for external memory %p:\n" + " [0x%" PRIxPTR ", 0x%" PRIxPTR ")," + " lkey=0x%x base_idx=%u ms_n=%u, ms_bmp_n=%u", + (void *)mr, (void *)addr, + addr, addr + len, rte_cpu_to_be_32(mr->ibv_mr->lkey), + mr->ms_base_idx, mr->ms_n, mr->ms_bmp_n); + return mr; +} + +/** + * Dump all the created MRs and the global cache entries. + * + * @param sh + * Pointer to Ethernet device shared context. + */ +void +mlx5_mr_dump_cache(struct mlx5_mr_share_cache *share_cache __rte_unused) +{ +#ifdef RTE_LIBRTE_MLX5_DEBUG + struct mlx5_mr *mr; + int mr_n = 0; + int chunk_n = 0; + + rte_rwlock_read_lock(&share_cache->rwlock); + /* Iterate all the existing MRs. */ + LIST_FOREACH(mr, &share_cache->mr_list, mr) { + unsigned int n; + + DEBUG("MR[%u], LKey = 0x%x, ms_n = %u, ms_bmp_n = %u", + mr_n++, rte_cpu_to_be_32(mr->ibv_mr->lkey), + mr->ms_n, mr->ms_bmp_n); + if (mr->ms_n == 0) + continue; + for (n = 0; n < mr->ms_bmp_n; ) { + struct mr_cache_entry ret = { 0, }; + + n = mr_find_next_chunk(mr, &ret, n); + if (!ret.end) + break; + DEBUG(" chunk[%u], [0x%" PRIxPTR ", 0x%" PRIxPTR ")", + chunk_n++, ret.start, ret.end); + } + } + DEBUG("Dumping global cache %p", (void *)share_cache); + mlx5_mr_btree_dump(&share_cache->cache); + rte_rwlock_read_unlock(&share_cache->rwlock); +#endif +} diff --git a/drivers/common/mlx5/mlx5_common_mr.h b/drivers/common/mlx5/mlx5_common_mr.h new file mode 100644 index 0000000000..e805f96375 --- /dev/null +++ b/drivers/common/mlx5/mlx5_common_mr.h @@ -0,0 +1,160 @@ +/* SPDX-License-Identifier: BSD-3-Clause + * Copyright 2018 6WIND S.A. + * Copyright 2018 Mellanox Technologies, Ltd + */ + +#ifndef RTE_PMD_MLX5_COMMON_MR_H_ +#define RTE_PMD_MLX5_COMMON_MR_H_ + +#include +#include +#include + +/* Verbs header. */ +/* ISO C doesn't support unnamed structs/unions, disabling -pedantic. */ +#ifdef PEDANTIC +#pragma GCC diagnostic ignored "-Wpedantic" +#endif +#include +#include +#ifdef PEDANTIC +#pragma GCC diagnostic error "-Wpedantic" +#endif + +#include +#include +#include + +#include "mlx5_common_mp.h" + +/* Size of per-queue MR cache array for linear search. */ +#define MLX5_MR_CACHE_N 8 +#define MLX5_MR_BTREE_CACHE_N 256 + +/* Memory Region object. */ +struct mlx5_mr { + LIST_ENTRY(mlx5_mr) mr; /**< Pointer to the prev/next entry. */ + struct ibv_mr *ibv_mr; /* Verbs Memory Region. */ + const struct rte_memseg_list *msl; + int ms_base_idx; /* Start index of msl->memseg_arr[]. */ + int ms_n; /* Number of memsegs in use. */ + uint32_t ms_bmp_n; /* Number of bits in memsegs bit-mask. */ + struct rte_bitmap *ms_bmp; /* Bit-mask of memsegs belonged to MR. */ +}; + +/* Cache entry for Memory Region. */ +struct mr_cache_entry { + uintptr_t start; /* Start address of MR. */ + uintptr_t end; /* End address of MR. */ + uint32_t lkey; /* rte_cpu_to_be_32(ibv_mr->lkey). */ +} __rte_packed; + +/* MR Cache table for Binary search. */ +struct mlx5_mr_btree { + uint16_t len; /* Number of entries. */ + uint16_t size; /* Total number of entries. */ + int overflow; /* Mark failure of table expansion. */ + struct mr_cache_entry (*table)[]; +} __rte_packed; + +/* Per-queue MR control descriptor. */ +struct mlx5_mr_ctrl { + uint32_t *dev_gen_ptr; /* Generation number of device to poll. */ + uint32_t cur_gen; /* Generation number saved to flush caches. */ + uint16_t mru; /* Index of last hit entry in top-half cache. */ + uint16_t head; /* Index of the oldest entry in top-half cache. */ + struct mr_cache_entry cache[MLX5_MR_CACHE_N]; /* Cache for top-half. */ + struct mlx5_mr_btree cache_bh; /* Cache for bottom-half. */ +} __rte_packed; + +LIST_HEAD(mlx5_mr_list, mlx5_mr); + +/* Global per-device MR cache. */ +struct mlx5_mr_share_cache { + uint32_t dev_gen; /* Generation number to flush local caches. */ + rte_rwlock_t rwlock; /* MR cache Lock. */ + struct mlx5_mr_btree cache; /* Global MR cache table. */ + struct mlx5_mr_list mr_list; /* Registered MR list. */ + struct mlx5_mr_list mr_free_list; /* Freed MR list. */ +} __rte_packed; + +/** + * Look up LKey from given lookup table by linear search. Firstly look up the + * last-hit entry. If miss, the entire array is searched. If found, update the + * last-hit index and return LKey. + * + * @param lkp_tbl + * Pointer to lookup table. + * @param[in,out] cached_idx + * Pointer to last-hit index. + * @param n + * Size of lookup table. + * @param addr + * Search key. + * + * @return + * Searched LKey on success, UINT32_MAX on no match. + */ +static __rte_always_inline uint32_t +mlx5_mr_lookup_lkey(struct mr_cache_entry *lkp_tbl, uint16_t *cached_idx, + uint16_t n, uintptr_t addr) +{ + uint16_t idx; + + if (likely(addr >= lkp_tbl[*cached_idx].start && + addr < lkp_tbl[*cached_idx].end)) + return lkp_tbl[*cached_idx].lkey; + for (idx = 0; idx < n && lkp_tbl[idx].start != 0; ++idx) { + if (addr >= lkp_tbl[idx].start && + addr < lkp_tbl[idx].end) { + /* Found. */ + *cached_idx = idx; + return lkp_tbl[idx].lkey; + } + } + return UINT32_MAX; +} + +__rte_experimental +int mlx5_mr_btree_init(struct mlx5_mr_btree *bt, int n, int socket); +__rte_experimental +void mlx5_mr_btree_free(struct mlx5_mr_btree *bt); +__rte_experimental +void mlx5_mr_btree_dump(struct mlx5_mr_btree *bt __rte_unused); +__rte_experimental +uint32_t mlx5_mr_addr2mr_bh(struct ibv_pd *pd, struct mlx5_mp_id *mp_id, + struct mlx5_mr_share_cache *share_cache, + struct mlx5_mr_ctrl *mr_ctrl, + uintptr_t addr, unsigned int mr_ext_memseg_en); +__rte_experimental +void mlx5_mr_release_cache(struct mlx5_mr_share_cache *mr_cache); +__rte_experimental +void mlx5_mr_dump_cache(struct mlx5_mr_share_cache *share_cache __rte_unused); +__rte_experimental +void mlx5_mr_rebuild_cache(struct mlx5_mr_share_cache *share_cache); +__rte_experimental +void mlx5_mr_flush_local_cache(struct mlx5_mr_ctrl *mr_ctrl); +__rte_experimental +int +mlx5_mr_insert_cache(struct mlx5_mr_share_cache *share_cache, + struct mlx5_mr *mr); +__rte_experimental +uint32_t +mlx5_mr_lookup_cache(struct mlx5_mr_share_cache *share_cache, + struct mr_cache_entry *entry, uintptr_t addr); +__rte_experimental +struct mlx5_mr * +mlx5_mr_lookup_list(struct mlx5_mr_share_cache *share_cache, + struct mr_cache_entry *entry, uintptr_t addr); +__rte_experimental +struct mlx5_mr * +mlx5_create_mr_ext(struct ibv_pd *pd, uintptr_t addr, size_t len, + int socket_id); +__rte_experimental +uint32_t +mlx5_mr_create_primary(struct ibv_pd *pd, + struct mlx5_mr_share_cache *share_cache, + struct mr_cache_entry *entry, uintptr_t addr, + unsigned int mr_ext_memseg_en); + +#endif /* RTE_PMD_MLX5_COMMON_MR_H_ */ diff --git a/drivers/common/mlx5/rte_common_mlx5_version.map b/drivers/common/mlx5/rte_common_mlx5_version.map index 265703d1c9..b58a378278 100644 --- a/drivers/common/mlx5/rte_common_mlx5_version.map +++ b/drivers/common/mlx5/rte_common_mlx5_version.map @@ -61,4 +61,18 @@ EXPERIMENTAL { mlx5_mp_req_mr_create; mlx5_mp_req_queue_state_modify; mlx5_mp_req_verbs_cmd_fd; + + mlx5_mr_btree_init; + mlx5_mr_btree_free; + mlx5_mr_btree_dump; + mlx5_mr_addr2mr_bh; + mlx5_mr_release_cache; + mlx5_mr_dump_cache; + mlx5_mr_rebuild_cache; + mlx5_mr_insert_cache; + mlx5_mr_lookup_cache; + mlx5_mr_lookup_list; + mlx5_create_mr_ext; + mlx5_mr_create_primary; + mlx5_mr_flush_local_cache; }; diff --git a/drivers/net/mlx5/mlx5.c b/drivers/net/mlx5/mlx5.c index d87c384422..f8b134ca66 100644 --- a/drivers/net/mlx5/mlx5.c +++ b/drivers/net/mlx5/mlx5.c @@ -623,7 +623,7 @@ mlx5_alloc_shared_ibctx(const struct mlx5_dev_spawn_data *spawn, * At this point the device is not added to the memory * event list yet, context is just being created. */ - err = mlx5_mr_btree_init(&sh->mr.cache, + err = mlx5_mr_btree_init(&sh->share_cache.cache, MLX5_MR_BTREE_CACHE_N * 2, spawn->pci_dev->device.numa_node); if (err) { @@ -695,7 +695,7 @@ mlx5_free_shared_ibctx(struct mlx5_ibv_shared *sh) LIST_REMOVE(sh, mem_event_cb); rte_rwlock_write_unlock(&mlx5_shared_data->mem_event_rwlock); /* Release created Memory Regions. */ - mlx5_mr_release(sh); + mlx5_mr_release_cache(&sh->share_cache); /* Remove context from the global device list. */ LIST_REMOVE(sh, next); /* diff --git a/drivers/net/mlx5/mlx5.h b/drivers/net/mlx5/mlx5.h index dd16da7f75..01112f78a5 100644 --- a/drivers/net/mlx5/mlx5.h +++ b/drivers/net/mlx5/mlx5.h @@ -37,10 +37,10 @@ #include #include #include +#include #include "mlx5_defs.h" #include "mlx5_utils.h" -#include "mlx5_mr.h" #include "mlx5_autoconf.h" /** Key string for IPC. */ @@ -199,8 +199,6 @@ struct mlx5_verbs_alloc_ctx { const void *obj; /* Pointer to the DPDK object. */ }; -LIST_HEAD(mlx5_mr_list, mlx5_mr); - /* Flow drop context necessary due to Verbs API. */ struct mlx5_drop { struct mlx5_hrxq *hrxq; /* Hash Rx queue queue. */ @@ -411,13 +409,7 @@ struct mlx5_ibv_shared { struct ibv_device_attr_ex device_attr; /* Device properties. */ LIST_ENTRY(mlx5_ibv_shared) mem_event_cb; /**< Called by memory event callback. */ - struct { - uint32_t dev_gen; /* Generation number to flush local caches. */ - rte_rwlock_t rwlock; /* MR Lock. */ - struct mlx5_mr_btree cache; /* Global MR cache table. */ - struct mlx5_mr_list mr_list; /* Registered MR list. */ - struct mlx5_mr_list mr_free_list; /* Freed MR list. */ - } mr; + struct mlx5_mr_share_cache share_cache; /* Shared DV/DR flow data section. */ pthread_mutex_t dv_mutex; /* DV context mutex. */ uint32_t dv_meta_mask; /* flow META metadata supported mask. */ diff --git a/drivers/net/mlx5/mlx5_mp.c b/drivers/net/mlx5/mlx5_mp.c index 43684dbc3a..7ad322d474 100644 --- a/drivers/net/mlx5/mlx5_mp.c +++ b/drivers/net/mlx5/mlx5_mp.c @@ -11,6 +11,7 @@ #include #include +#include #include "mlx5.h" #include "mlx5_rxtx.h" @@ -25,7 +26,7 @@ mlx5_mp_primary_handle(const struct rte_mp_msg *mp_msg, const void *peer) (const struct mlx5_mp_param *)mp_msg->param; struct rte_eth_dev *dev; struct mlx5_priv *priv; - struct mlx5_mr_cache entry; + struct mr_cache_entry entry; uint32_t lkey; int ret; @@ -40,7 +41,10 @@ mlx5_mp_primary_handle(const struct rte_mp_msg *mp_msg, const void *peer) switch (param->type) { case MLX5_MP_REQ_CREATE_MR: mp_init_msg(&priv->mp_id, &mp_res, param->type); - lkey = mlx5_mr_create_primary(dev, &entry, param->args.addr); + lkey = mlx5_mr_create_primary(priv->sh->pd, + &priv->sh->share_cache, + &entry, param->args.addr, + priv->config.mr_ext_memseg_en); if (lkey == UINT32_MAX) res->result = -rte_errno; ret = rte_mp_reply(&mp_res, peer); diff --git a/drivers/net/mlx5/mlx5_mr.c b/drivers/net/mlx5/mlx5_mr.c index 9151992a72..2b4b3e2891 100644 --- a/drivers/net/mlx5/mlx5_mr.c +++ b/drivers/net/mlx5/mlx5_mr.c @@ -18,6 +18,8 @@ #include #include +#include +#include #include "mlx5.h" #include "mlx5_mr.h" @@ -36,834 +38,6 @@ struct mr_update_mp_data { int ret; }; -/** - * Expand B-tree table to a given size. Can't be called with holding - * memory_hotplug_lock or sh->mr.rwlock due to rte_realloc(). - * - * @param bt - * Pointer to B-tree structure. - * @param n - * Number of entries for expansion. - * - * @return - * 0 on success, -1 on failure. - */ -static int -mr_btree_expand(struct mlx5_mr_btree *bt, int n) -{ - void *mem; - int ret = 0; - - if (n <= bt->size) - return ret; - /* - * Downside of directly using rte_realloc() is that SOCKET_ID_ANY is - * used inside if there's no room to expand. Because this is a quite - * rare case and a part of very slow path, it is very acceptable. - * Initially cache_bh[] will be given practically enough space and once - * it is expanded, expansion wouldn't be needed again ever. - */ - mem = rte_realloc(bt->table, n * sizeof(struct mlx5_mr_cache), 0); - if (mem == NULL) { - /* Not an error, B-tree search will be skipped. */ - DRV_LOG(WARNING, "failed to expand MR B-tree (%p) table", - (void *)bt); - ret = -1; - } else { - DRV_LOG(DEBUG, "expanded MR B-tree table (size=%u)", n); - bt->table = mem; - bt->size = n; - } - return ret; -} - -/** - * Look up LKey from given B-tree lookup table, store the last index and return - * searched LKey. - * - * @param bt - * Pointer to B-tree structure. - * @param[out] idx - * Pointer to index. Even on search failure, returns index where it stops - * searching so that index can be used when inserting a new entry. - * @param addr - * Search key. - * - * @return - * Searched LKey on success, UINT32_MAX on no match. - */ -static uint32_t -mr_btree_lookup(struct mlx5_mr_btree *bt, uint16_t *idx, uintptr_t addr) -{ - struct mlx5_mr_cache *lkp_tbl; - uint16_t n; - uint16_t base = 0; - - MLX5_ASSERT(bt != NULL); - lkp_tbl = *bt->table; - n = bt->len; - /* First entry must be NULL for comparison. */ - MLX5_ASSERT(bt->len > 0 || (lkp_tbl[0].start == 0 && - lkp_tbl[0].lkey == UINT32_MAX)); - /* Binary search. */ - do { - register uint16_t delta = n >> 1; - - if (addr < lkp_tbl[base + delta].start) { - n = delta; - } else { - base += delta; - n -= delta; - } - } while (n > 1); - MLX5_ASSERT(addr >= lkp_tbl[base].start); - *idx = base; - if (addr < lkp_tbl[base].end) - return lkp_tbl[base].lkey; - /* Not found. */ - return UINT32_MAX; -} - -/** - * Insert an entry to B-tree lookup table. - * - * @param bt - * Pointer to B-tree structure. - * @param entry - * Pointer to new entry to insert. - * - * @return - * 0 on success, -1 on failure. - */ -static int -mr_btree_insert(struct mlx5_mr_btree *bt, struct mlx5_mr_cache *entry) -{ - struct mlx5_mr_cache *lkp_tbl; - uint16_t idx = 0; - size_t shift; - - MLX5_ASSERT(bt != NULL); - MLX5_ASSERT(bt->len <= bt->size); - MLX5_ASSERT(bt->len > 0); - lkp_tbl = *bt->table; - /* Find out the slot for insertion. */ - if (mr_btree_lookup(bt, &idx, entry->start) != UINT32_MAX) { - DRV_LOG(DEBUG, - "abort insertion to B-tree(%p): already exist at" - " idx=%u [0x%" PRIxPTR ", 0x%" PRIxPTR ") lkey=0x%x", - (void *)bt, idx, entry->start, entry->end, entry->lkey); - /* Already exist, return. */ - return 0; - } - /* If table is full, return error. */ - if (unlikely(bt->len == bt->size)) { - bt->overflow = 1; - return -1; - } - /* Insert entry. */ - ++idx; - shift = (bt->len - idx) * sizeof(struct mlx5_mr_cache); - if (shift) - memmove(&lkp_tbl[idx + 1], &lkp_tbl[idx], shift); - lkp_tbl[idx] = *entry; - bt->len++; - DRV_LOG(DEBUG, - "inserted B-tree(%p)[%u]," - " [0x%" PRIxPTR ", 0x%" PRIxPTR ") lkey=0x%x", - (void *)bt, idx, entry->start, entry->end, entry->lkey); - return 0; -} - -/** - * Initialize B-tree and allocate memory for lookup table. - * - * @param bt - * Pointer to B-tree structure. - * @param n - * Number of entries to allocate. - * @param socket - * NUMA socket on which memory must be allocated. - * - * @return - * 0 on success, a negative errno value otherwise and rte_errno is set. - */ -int -mlx5_mr_btree_init(struct mlx5_mr_btree *bt, int n, int socket) -{ - if (bt == NULL) { - rte_errno = EINVAL; - return -rte_errno; - } - MLX5_ASSERT(!bt->table && !bt->size); - memset(bt, 0, sizeof(*bt)); - bt->table = rte_calloc_socket("B-tree table", - n, sizeof(struct mlx5_mr_cache), - 0, socket); - if (bt->table == NULL) { - rte_errno = ENOMEM; - DEBUG("failed to allocate memory for btree cache on socket %d", - socket); - return -rte_errno; - } - bt->size = n; - /* First entry must be NULL for binary search. */ - (*bt->table)[bt->len++] = (struct mlx5_mr_cache) { - .lkey = UINT32_MAX, - }; - DEBUG("initialized B-tree %p with table %p", - (void *)bt, (void *)bt->table); - return 0; -} - -/** - * Free B-tree resources. - * - * @param bt - * Pointer to B-tree structure. - */ -void -mlx5_mr_btree_free(struct mlx5_mr_btree *bt) -{ - if (bt == NULL) - return; - DEBUG("freeing B-tree %p with table %p", - (void *)bt, (void *)bt->table); - rte_free(bt->table); - memset(bt, 0, sizeof(*bt)); -} - -/** - * Dump all the entries in a B-tree - * - * @param bt - * Pointer to B-tree structure. - */ -void -mlx5_mr_btree_dump(struct mlx5_mr_btree *bt __rte_unused) -{ -#ifdef RTE_LIBRTE_MLX5_DEBUG - int idx; - struct mlx5_mr_cache *lkp_tbl; - - if (bt == NULL) - return; - lkp_tbl = *bt->table; - for (idx = 0; idx < bt->len; ++idx) { - struct mlx5_mr_cache *entry = &lkp_tbl[idx]; - - DEBUG("B-tree(%p)[%u]," - " [0x%" PRIxPTR ", 0x%" PRIxPTR ") lkey=0x%x", - (void *)bt, idx, entry->start, entry->end, entry->lkey); - } -#endif -} - -/** - * Find virtually contiguous memory chunk in a given MR. - * - * @param dev - * Pointer to MR structure. - * @param[out] entry - * Pointer to returning MR cache entry. If not found, this will not be - * updated. - * @param start_idx - * Start index of the memseg bitmap. - * - * @return - * Next index to go on lookup. - */ -static int -mr_find_next_chunk(struct mlx5_mr *mr, struct mlx5_mr_cache *entry, - int base_idx) -{ - uintptr_t start = 0; - uintptr_t end = 0; - uint32_t idx = 0; - - /* MR for external memory doesn't have memseg list. */ - if (mr->msl == NULL) { - struct ibv_mr *ibv_mr = mr->ibv_mr; - - MLX5_ASSERT(mr->ms_bmp_n == 1); - MLX5_ASSERT(mr->ms_n == 1); - MLX5_ASSERT(base_idx == 0); - /* - * Can't search it from memseg list but get it directly from - * verbs MR as there's only one chunk. - */ - entry->start = (uintptr_t)ibv_mr->addr; - entry->end = (uintptr_t)ibv_mr->addr + mr->ibv_mr->length; - entry->lkey = rte_cpu_to_be_32(mr->ibv_mr->lkey); - /* Returning 1 ends iteration. */ - return 1; - } - for (idx = base_idx; idx < mr->ms_bmp_n; ++idx) { - if (rte_bitmap_get(mr->ms_bmp, idx)) { - const struct rte_memseg_list *msl; - const struct rte_memseg *ms; - - msl = mr->msl; - ms = rte_fbarray_get(&msl->memseg_arr, - mr->ms_base_idx + idx); - MLX5_ASSERT(msl->page_sz == ms->hugepage_sz); - if (!start) - start = ms->addr_64; - end = ms->addr_64 + ms->hugepage_sz; - } else if (start) { - /* Passed the end of a fragment. */ - break; - } - } - if (start) { - /* Found one chunk. */ - entry->start = start; - entry->end = end; - entry->lkey = rte_cpu_to_be_32(mr->ibv_mr->lkey); - } - return idx; -} - -/** - * Insert a MR to the global B-tree cache. It may fail due to low-on-memory. - * Then, this entry will have to be searched by mr_lookup_dev_list() in - * mlx5_mr_create() on miss. - * - * @param dev - * Pointer to Ethernet device shared context. - * @param mr - * Pointer to MR to insert. - * - * @return - * 0 on success, -1 on failure. - */ -static int -mr_insert_dev_cache(struct mlx5_ibv_shared *sh, struct mlx5_mr *mr) -{ - unsigned int n; - - DRV_LOG(DEBUG, "device %s inserting MR(%p) to global cache", - sh->ibdev_name, (void *)mr); - for (n = 0; n < mr->ms_bmp_n; ) { - struct mlx5_mr_cache entry; - - memset(&entry, 0, sizeof(entry)); - /* Find a contiguous chunk and advance the index. */ - n = mr_find_next_chunk(mr, &entry, n); - if (!entry.end) - break; - if (mr_btree_insert(&sh->mr.cache, &entry) < 0) { - /* - * Overflowed, but the global table cannot be expanded - * because of deadlock. - */ - return -1; - } - } - return 0; -} - -/** - * Look up address in the original global MR list. - * - * @param sh - * Pointer to Ethernet device shared context. - * @param[out] entry - * Pointer to returning MR cache entry. If no match, this will not be updated. - * @param addr - * Search key. - * - * @return - * Found MR on match, NULL otherwise. - */ -static struct mlx5_mr * -mr_lookup_dev_list(struct mlx5_ibv_shared *sh, struct mlx5_mr_cache *entry, - uintptr_t addr) -{ - struct mlx5_mr *mr; - - /* Iterate all the existing MRs. */ - LIST_FOREACH(mr, &sh->mr.mr_list, mr) { - unsigned int n; - - if (mr->ms_n == 0) - continue; - for (n = 0; n < mr->ms_bmp_n; ) { - struct mlx5_mr_cache ret; - - memset(&ret, 0, sizeof(ret)); - n = mr_find_next_chunk(mr, &ret, n); - if (addr >= ret.start && addr < ret.end) { - /* Found. */ - *entry = ret; - return mr; - } - } - } - return NULL; -} - -/** - * Look up address on device. - * - * @param dev - * Pointer to Ethernet device shared context. - * @param[out] entry - * Pointer to returning MR cache entry. If no match, this will not be updated. - * @param addr - * Search key. - * - * @return - * Searched LKey on success, UINT32_MAX on failure and rte_errno is set. - */ -static uint32_t -mr_lookup_dev(struct mlx5_ibv_shared *sh, struct mlx5_mr_cache *entry, - uintptr_t addr) -{ - uint16_t idx; - uint32_t lkey = UINT32_MAX; - struct mlx5_mr *mr; - - /* - * If the global cache has overflowed since it failed to expand the - * B-tree table, it can't have all the existing MRs. Then, the address - * has to be searched by traversing the original MR list instead, which - * is very slow path. Otherwise, the global cache is all inclusive. - */ - if (!unlikely(sh->mr.cache.overflow)) { - lkey = mr_btree_lookup(&sh->mr.cache, &idx, addr); - if (lkey != UINT32_MAX) - *entry = (*sh->mr.cache.table)[idx]; - } else { - /* Falling back to the slowest path. */ - mr = mr_lookup_dev_list(sh, entry, addr); - if (mr != NULL) - lkey = entry->lkey; - } - MLX5_ASSERT(lkey == UINT32_MAX || (addr >= entry->start && - addr < entry->end)); - return lkey; -} - -/** - * Free MR resources. MR lock must not be held to avoid a deadlock. rte_free() - * can raise memory free event and the callback function will spin on the lock. - * - * @param mr - * Pointer to MR to free. - */ -static void -mr_free(struct mlx5_mr *mr) -{ - if (mr == NULL) - return; - DRV_LOG(DEBUG, "freeing MR(%p):", (void *)mr); - if (mr->ibv_mr != NULL) - claim_zero(mlx5_glue->dereg_mr(mr->ibv_mr)); - if (mr->ms_bmp != NULL) - rte_bitmap_free(mr->ms_bmp); - rte_free(mr); -} - -/** - * Release resources of detached MR having no online entry. - * - * @param sh - * Pointer to Ethernet device shared context. - */ -static void -mlx5_mr_garbage_collect(struct mlx5_ibv_shared *sh) -{ - struct mlx5_mr *mr_next; - struct mlx5_mr_list free_list = LIST_HEAD_INITIALIZER(free_list); - - /* Must be called from the primary process. */ - MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_PRIMARY); - /* - * MR can't be freed with holding the lock because rte_free() could call - * memory free callback function. This will be a deadlock situation. - */ - rte_rwlock_write_lock(&sh->mr.rwlock); - /* Detach the whole free list and release it after unlocking. */ - free_list = sh->mr.mr_free_list; - LIST_INIT(&sh->mr.mr_free_list); - rte_rwlock_write_unlock(&sh->mr.rwlock); - /* Release resources. */ - mr_next = LIST_FIRST(&free_list); - while (mr_next != NULL) { - struct mlx5_mr *mr = mr_next; - - mr_next = LIST_NEXT(mr, mr); - mr_free(mr); - } -} - -/* Called during rte_memseg_contig_walk() by mlx5_mr_create(). */ -static int -mr_find_contig_memsegs_cb(const struct rte_memseg_list *msl, - const struct rte_memseg *ms, size_t len, void *arg) -{ - struct mr_find_contig_memsegs_data *data = arg; - - if (data->addr < ms->addr_64 || data->addr >= ms->addr_64 + len) - return 0; - /* Found, save it and stop walking. */ - data->start = ms->addr_64; - data->end = ms->addr_64 + len; - data->msl = msl; - return 1; -} - -/** - * Create a new global Memory Region (MR) for a missing virtual address. - * This API should be called on a secondary process, then a request is sent to - * the primary process in order to create a MR for the address. As the global MR - * list is on the shared memory, following LKey lookup should succeed unless the - * request fails. - * - * @param dev - * Pointer to Ethernet device. - * @param[out] entry - * Pointer to returning MR cache entry, found in the global cache or newly - * created. If failed to create one, this will not be updated. - * @param addr - * Target virtual address to register. - * - * @return - * Searched LKey on success, UINT32_MAX on failure and rte_errno is set. - */ -static uint32_t -mlx5_mr_create_secondary(struct rte_eth_dev *dev, struct mlx5_mr_cache *entry, - uintptr_t addr) -{ - struct mlx5_priv *priv = dev->data->dev_private; - int ret; - - DEBUG("port %u requesting MR creation for address (%p)", - dev->data->port_id, (void *)addr); - ret = mlx5_mp_req_mr_create(&priv->mp_id, addr); - if (ret) { - DEBUG("port %u fail to request MR creation for address (%p)", - dev->data->port_id, (void *)addr); - return UINT32_MAX; - } - rte_rwlock_read_lock(&priv->sh->mr.rwlock); - /* Fill in output data. */ - mr_lookup_dev(priv->sh, entry, addr); - /* Lookup can't fail. */ - MLX5_ASSERT(entry->lkey != UINT32_MAX); - rte_rwlock_read_unlock(&priv->sh->mr.rwlock); - DEBUG("port %u MR CREATED by primary process for %p:\n" - " [0x%" PRIxPTR ", 0x%" PRIxPTR "), lkey=0x%x", - dev->data->port_id, (void *)addr, - entry->start, entry->end, entry->lkey); - return entry->lkey; -} - -/** - * Create a new global Memory Region (MR) for a missing virtual address. - * Register entire virtually contiguous memory chunk around the address. - * This must be called from the primary process. - * - * @param dev - * Pointer to Ethernet device. - * @param[out] entry - * Pointer to returning MR cache entry, found in the global cache or newly - * created. If failed to create one, this will not be updated. - * @param addr - * Target virtual address to register. - * - * @return - * Searched LKey on success, UINT32_MAX on failure and rte_errno is set. - */ -uint32_t -mlx5_mr_create_primary(struct rte_eth_dev *dev, struct mlx5_mr_cache *entry, - uintptr_t addr) -{ - struct mlx5_priv *priv = dev->data->dev_private; - struct mlx5_ibv_shared *sh = priv->sh; - struct mlx5_dev_config *config = &priv->config; - const struct rte_memseg_list *msl; - const struct rte_memseg *ms; - struct mlx5_mr *mr = NULL; - size_t len; - uint32_t ms_n; - uint32_t bmp_size; - void *bmp_mem; - int ms_idx_shift = -1; - unsigned int n; - struct mr_find_contig_memsegs_data data = { - .addr = addr, - }; - struct mr_find_contig_memsegs_data data_re; - - DRV_LOG(DEBUG, "port %u creating a MR using address (%p)", - dev->data->port_id, (void *)addr); - /* - * Release detached MRs if any. This can't be called with holding either - * memory_hotplug_lock or sh->mr.rwlock. MRs on the free list have - * been detached by the memory free event but it couldn't be released - * inside the callback due to deadlock. As a result, releasing resources - * is quite opportunistic. - */ - mlx5_mr_garbage_collect(sh); - /* - * If enabled, find out a contiguous virtual address chunk in use, to - * which the given address belongs, in order to register maximum range. - * In the best case where mempools are not dynamically recreated and - * '--socket-mem' is specified as an EAL option, it is very likely to - * have only one MR(LKey) per a socket and per a hugepage-size even - * though the system memory is highly fragmented. As the whole memory - * chunk will be pinned by kernel, it can't be reused unless entire - * chunk is freed from EAL. - * - * If disabled, just register one memseg (page). Then, memory - * consumption will be minimized but it may drop performance if there - * are many MRs to lookup on the datapath. - */ - if (!config->mr_ext_memseg_en) { - data.msl = rte_mem_virt2memseg_list((void *)addr); - data.start = RTE_ALIGN_FLOOR(addr, data.msl->page_sz); - data.end = data.start + data.msl->page_sz; - } else if (!rte_memseg_contig_walk(mr_find_contig_memsegs_cb, &data)) { - DRV_LOG(WARNING, - "port %u unable to find virtually contiguous" - " chunk for address (%p)." - " rte_memseg_contig_walk() failed.", - dev->data->port_id, (void *)addr); - rte_errno = ENXIO; - goto err_nolock; - } -alloc_resources: - /* Addresses must be page-aligned. */ - MLX5_ASSERT(rte_is_aligned((void *)data.start, data.msl->page_sz)); - MLX5_ASSERT(rte_is_aligned((void *)data.end, data.msl->page_sz)); - msl = data.msl; - ms = rte_mem_virt2memseg((void *)data.start, msl); - len = data.end - data.start; - MLX5_ASSERT(msl->page_sz == ms->hugepage_sz); - /* Number of memsegs in the range. */ - ms_n = len / msl->page_sz; - DEBUG("port %u extending %p to [0x%" PRIxPTR ", 0x%" PRIxPTR ")," - " page_sz=0x%" PRIx64 ", ms_n=%u", - dev->data->port_id, (void *)addr, - data.start, data.end, msl->page_sz, ms_n); - /* Size of memory for bitmap. */ - bmp_size = rte_bitmap_get_memory_footprint(ms_n); - mr = rte_zmalloc_socket(NULL, - RTE_ALIGN_CEIL(sizeof(*mr), - RTE_CACHE_LINE_SIZE) + - bmp_size, - RTE_CACHE_LINE_SIZE, msl->socket_id); - if (mr == NULL) { - DEBUG("port %u unable to allocate memory for a new MR of" - " address (%p).", - dev->data->port_id, (void *)addr); - rte_errno = ENOMEM; - goto err_nolock; - } - mr->msl = msl; - /* - * Save the index of the first memseg and initialize memseg bitmap. To - * see if a memseg of ms_idx in the memseg-list is still valid, check: - * rte_bitmap_get(mr->bmp, ms_idx - mr->ms_base_idx) - */ - mr->ms_base_idx = rte_fbarray_find_idx(&msl->memseg_arr, ms); - bmp_mem = RTE_PTR_ALIGN_CEIL(mr + 1, RTE_CACHE_LINE_SIZE); - mr->ms_bmp = rte_bitmap_init(ms_n, bmp_mem, bmp_size); - if (mr->ms_bmp == NULL) { - DEBUG("port %u unable to initialize bitmap for a new MR of" - " address (%p).", - dev->data->port_id, (void *)addr); - rte_errno = EINVAL; - goto err_nolock; - } - /* - * Should recheck whether the extended contiguous chunk is still valid. - * Because memory_hotplug_lock can't be held if there's any memory - * related calls in a critical path, resource allocation above can't be - * locked. If the memory has been changed at this point, try again with - * just single page. If not, go on with the big chunk atomically from - * here. - */ - rte_mcfg_mem_read_lock(); - data_re = data; - if (len > msl->page_sz && - !rte_memseg_contig_walk(mr_find_contig_memsegs_cb, &data_re)) { - DEBUG("port %u unable to find virtually contiguous" - " chunk for address (%p)." - " rte_memseg_contig_walk() failed.", - dev->data->port_id, (void *)addr); - rte_errno = ENXIO; - goto err_memlock; - } - if (data.start != data_re.start || data.end != data_re.end) { - /* - * The extended contiguous chunk has been changed. Try again - * with single memseg instead. - */ - data.start = RTE_ALIGN_FLOOR(addr, msl->page_sz); - data.end = data.start + msl->page_sz; - rte_mcfg_mem_read_unlock(); - mr_free(mr); - goto alloc_resources; - } - MLX5_ASSERT(data.msl == data_re.msl); - rte_rwlock_write_lock(&sh->mr.rwlock); - /* - * Check the address is really missing. If other thread already created - * one or it is not found due to overflow, abort and return. - */ - if (mr_lookup_dev(sh, entry, addr) != UINT32_MAX) { - /* - * Insert to the global cache table. It may fail due to - * low-on-memory. Then, this entry will have to be searched - * here again. - */ - mr_btree_insert(&sh->mr.cache, entry); - DEBUG("port %u found MR for %p on final lookup, abort", - dev->data->port_id, (void *)addr); - rte_rwlock_write_unlock(&sh->mr.rwlock); - rte_mcfg_mem_read_unlock(); - /* - * Must be unlocked before calling rte_free() because - * mlx5_mr_mem_event_free_cb() can be called inside. - */ - mr_free(mr); - return entry->lkey; - } - /* - * Trim start and end addresses for verbs MR. Set bits for registering - * memsegs but exclude already registered ones. Bitmap can be - * fragmented. - */ - for (n = 0; n < ms_n; ++n) { - uintptr_t start; - struct mlx5_mr_cache ret; - - memset(&ret, 0, sizeof(ret)); - start = data_re.start + n * msl->page_sz; - /* Exclude memsegs already registered by other MRs. */ - if (mr_lookup_dev(sh, &ret, start) == UINT32_MAX) { - /* - * Start from the first unregistered memseg in the - * extended range. - */ - if (ms_idx_shift == -1) { - mr->ms_base_idx += n; - data.start = start; - ms_idx_shift = n; - } - data.end = start + msl->page_sz; - rte_bitmap_set(mr->ms_bmp, n - ms_idx_shift); - ++mr->ms_n; - } - } - len = data.end - data.start; - mr->ms_bmp_n = len / msl->page_sz; - MLX5_ASSERT(ms_idx_shift + mr->ms_bmp_n <= ms_n); - /* - * Finally create a verbs MR for the memory chunk. ibv_reg_mr() can be - * called with holding the memory lock because it doesn't use - * mlx5_alloc_buf_extern() which eventually calls rte_malloc_socket() - * through mlx5_alloc_verbs_buf(). - */ - mr->ibv_mr = mlx5_glue->reg_mr(sh->pd, (void *)data.start, len, - IBV_ACCESS_LOCAL_WRITE | - IBV_ACCESS_RELAXED_ORDERING); - if (mr->ibv_mr == NULL) { - DEBUG("port %u fail to create a verbs MR for address (%p)", - dev->data->port_id, (void *)addr); - rte_errno = EINVAL; - goto err_mrlock; - } - MLX5_ASSERT((uintptr_t)mr->ibv_mr->addr == data.start); - MLX5_ASSERT(mr->ibv_mr->length == len); - LIST_INSERT_HEAD(&sh->mr.mr_list, mr, mr); - DEBUG("port %u MR CREATED (%p) for %p:\n" - " [0x%" PRIxPTR ", 0x%" PRIxPTR ")," - " lkey=0x%x base_idx=%u ms_n=%u, ms_bmp_n=%u", - dev->data->port_id, (void *)mr, (void *)addr, - data.start, data.end, rte_cpu_to_be_32(mr->ibv_mr->lkey), - mr->ms_base_idx, mr->ms_n, mr->ms_bmp_n); - /* Insert to the global cache table. */ - mr_insert_dev_cache(sh, mr); - /* Fill in output data. */ - mr_lookup_dev(sh, entry, addr); - /* Lookup can't fail. */ - MLX5_ASSERT(entry->lkey != UINT32_MAX); - rte_rwlock_write_unlock(&sh->mr.rwlock); - rte_mcfg_mem_read_unlock(); - return entry->lkey; -err_mrlock: - rte_rwlock_write_unlock(&sh->mr.rwlock); -err_memlock: - rte_mcfg_mem_read_unlock(); -err_nolock: - /* - * In case of error, as this can be called in a datapath, a warning - * message per an error is preferable instead. Must be unlocked before - * calling rte_free() because mlx5_mr_mem_event_free_cb() can be called - * inside. - */ - mr_free(mr); - return UINT32_MAX; -} - -/** - * Create a new global Memory Region (MR) for a missing virtual address. - * This can be called from primary and secondary process. - * - * @param dev - * Pointer to Ethernet device. - * @param[out] entry - * Pointer to returning MR cache entry, found in the global cache or newly - * created. If failed to create one, this will not be updated. - * @param addr - * Target virtual address to register. - * - * @return - * Searched LKey on success, UINT32_MAX on failure and rte_errno is set. - */ -static uint32_t -mlx5_mr_create(struct rte_eth_dev *dev, struct mlx5_mr_cache *entry, - uintptr_t addr) -{ - uint32_t ret = 0; - - switch (rte_eal_process_type()) { - case RTE_PROC_PRIMARY: - ret = mlx5_mr_create_primary(dev, entry, addr); - break; - case RTE_PROC_SECONDARY: - ret = mlx5_mr_create_secondary(dev, entry, addr); - break; - default: - break; - } - return ret; -} - -/** - * Rebuild the global B-tree cache of device from the original MR list. - * - * @param sh - * Pointer to Ethernet device shared context. - */ -static void -mr_rebuild_dev_cache(struct mlx5_ibv_shared *sh) -{ - struct mlx5_mr *mr; - - DRV_LOG(DEBUG, "device %s rebuild dev cache[]", sh->ibdev_name); - /* Flush cache to rebuild. */ - sh->mr.cache.len = 1; - sh->mr.cache.overflow = 0; - /* Iterate all the existing MRs. */ - LIST_FOREACH(mr, &sh->mr.mr_list, mr) - if (mr_insert_dev_cache(sh, mr) < 0) - return; -} - /** * Callback for memory free event. Iterate freed memsegs and check whether it * belongs to an existing MR. If found, clear the bit from bitmap of MR. As a @@ -900,18 +74,18 @@ mlx5_mr_mem_event_free_cb(struct mlx5_ibv_shared *sh, RTE_ALIGN((uintptr_t)addr, msl->page_sz)); MLX5_ASSERT(len == RTE_ALIGN(len, msl->page_sz)); ms_n = len / msl->page_sz; - rte_rwlock_write_lock(&sh->mr.rwlock); + rte_rwlock_write_lock(&sh->share_cache.rwlock); /* Clear bits of freed memsegs from MR. */ for (i = 0; i < ms_n; ++i) { const struct rte_memseg *ms; - struct mlx5_mr_cache entry; + struct mr_cache_entry entry; uintptr_t start; int ms_idx; uint32_t pos; /* Find MR having this memseg. */ start = (uintptr_t)addr + i * msl->page_sz; - mr = mr_lookup_dev_list(sh, &entry, start); + mr = mlx5_mr_lookup_list(&sh->share_cache, &entry, start); if (mr == NULL) continue; MLX5_ASSERT(mr->msl); /* Can't be external memory. */ @@ -927,7 +101,7 @@ mlx5_mr_mem_event_free_cb(struct mlx5_ibv_shared *sh, rte_bitmap_clear(mr->ms_bmp, pos); if (--mr->ms_n == 0) { LIST_REMOVE(mr, mr); - LIST_INSERT_HEAD(&sh->mr.mr_free_list, mr, mr); + LIST_INSERT_HEAD(&sh->share_cache.mr_free_list, mr, mr); DEBUG("device %s remove MR(%p) from list", sh->ibdev_name, (void *)mr); } @@ -938,7 +112,7 @@ mlx5_mr_mem_event_free_cb(struct mlx5_ibv_shared *sh, rebuild = 1; } if (rebuild) { - mr_rebuild_dev_cache(sh); + mlx5_mr_rebuild_cache(&sh->share_cache); /* * Flush local caches by propagating invalidation across cores. * rte_smp_wmb() is enough to synchronize this event. If one of @@ -948,12 +122,12 @@ mlx5_mr_mem_event_free_cb(struct mlx5_ibv_shared *sh, * generation below) will be guaranteed to be seen by other core * before the core sees the newly allocated memory. */ - ++sh->mr.dev_gen; + ++sh->share_cache.dev_gen; DEBUG("broadcasting local cache flush, gen=%d", - sh->mr.dev_gen); + sh->share_cache.dev_gen); rte_smp_wmb(); } - rte_rwlock_write_unlock(&sh->mr.rwlock); + rte_rwlock_write_unlock(&sh->share_cache.rwlock); } /** @@ -990,111 +164,6 @@ mlx5_mr_mem_event_cb(enum rte_mem_event event_type, const void *addr, } } -/** - * Look up address in the global MR cache table. If not found, create a new MR. - * Insert the found/created entry to local bottom-half cache table. - * - * @param dev - * Pointer to Ethernet device. - * @param mr_ctrl - * Pointer to per-queue MR control structure. - * @param[out] entry - * Pointer to returning MR cache entry, found in the global cache or newly - * created. If failed to create one, this is not written. - * @param addr - * Search key. - * - * @return - * Searched LKey on success, UINT32_MAX on no match. - */ -static uint32_t -mlx5_mr_lookup_dev(struct rte_eth_dev *dev, struct mlx5_mr_ctrl *mr_ctrl, - struct mlx5_mr_cache *entry, uintptr_t addr) -{ - struct mlx5_priv *priv = dev->data->dev_private; - struct mlx5_ibv_shared *sh = priv->sh; - struct mlx5_mr_btree *bt = &mr_ctrl->cache_bh; - uint16_t idx; - uint32_t lkey; - - /* If local cache table is full, try to double it. */ - if (unlikely(bt->len == bt->size)) - mr_btree_expand(bt, bt->size << 1); - /* Look up in the global cache. */ - rte_rwlock_read_lock(&sh->mr.rwlock); - lkey = mr_btree_lookup(&sh->mr.cache, &idx, addr); - if (lkey != UINT32_MAX) { - /* Found. */ - *entry = (*sh->mr.cache.table)[idx]; - rte_rwlock_read_unlock(&sh->mr.rwlock); - /* - * Update local cache. Even if it fails, return the found entry - * to update top-half cache. Next time, this entry will be found - * in the global cache. - */ - mr_btree_insert(bt, entry); - return lkey; - } - rte_rwlock_read_unlock(&sh->mr.rwlock); - /* First time to see the address? Create a new MR. */ - lkey = mlx5_mr_create(dev, entry, addr); - /* - * Update the local cache if successfully created a new global MR. Even - * if failed to create one, there's no action to take in this datapath - * code. As returning LKey is invalid, this will eventually make HW - * fail. - */ - if (lkey != UINT32_MAX) - mr_btree_insert(bt, entry); - return lkey; -} - -/** - * Bottom-half of LKey search on datapath. Firstly search in cache_bh[] and if - * misses, search in the global MR cache table and update the new entry to - * per-queue local caches. - * - * @param dev - * Pointer to Ethernet device. - * @param mr_ctrl - * Pointer to per-queue MR control structure. - * @param addr - * Search key. - * - * @return - * Searched LKey on success, UINT32_MAX on no match. - */ -static uint32_t -mlx5_mr_addr2mr_bh(struct rte_eth_dev *dev, struct mlx5_mr_ctrl *mr_ctrl, - uintptr_t addr) -{ - uint32_t lkey; - uint16_t bh_idx = 0; - /* Victim in top-half cache to replace with new entry. */ - struct mlx5_mr_cache *repl = &mr_ctrl->cache[mr_ctrl->head]; - - /* Binary-search MR translation table. */ - lkey = mr_btree_lookup(&mr_ctrl->cache_bh, &bh_idx, addr); - /* Update top-half cache. */ - if (likely(lkey != UINT32_MAX)) { - *repl = (*mr_ctrl->cache_bh.table)[bh_idx]; - } else { - /* - * If missed in local lookup table, search in the global cache - * and local cache_bh[] will be updated inside if possible. - * Top-half cache entry will also be updated. - */ - lkey = mlx5_mr_lookup_dev(dev, mr_ctrl, repl, addr); - if (unlikely(lkey == UINT32_MAX)) - return UINT32_MAX; - } - /* Update the most recently used entry. */ - mr_ctrl->mru = mr_ctrl->head; - /* Point to the next victim, the oldest. */ - mr_ctrl->head = (mr_ctrl->head + 1) % MLX5_MR_CACHE_N; - return lkey; -} - /** * Bottom-half of LKey search on Rx. * @@ -1114,7 +183,9 @@ mlx5_rx_addr2mr_bh(struct mlx5_rxq_data *rxq, uintptr_t addr) struct mlx5_mr_ctrl *mr_ctrl = &rxq->mr_ctrl; struct mlx5_priv *priv = rxq_ctrl->priv; - return mlx5_mr_addr2mr_bh(ETH_DEV(priv), mr_ctrl, addr); + return mlx5_mr_addr2mr_bh(priv->sh->pd, &priv->mp_id, + &priv->sh->share_cache, mr_ctrl, addr, + priv->config.mr_ext_memseg_en); } /** @@ -1136,7 +207,9 @@ mlx5_tx_addr2mr_bh(struct mlx5_txq_data *txq, uintptr_t addr) struct mlx5_mr_ctrl *mr_ctrl = &txq->mr_ctrl; struct mlx5_priv *priv = txq_ctrl->priv; - return mlx5_mr_addr2mr_bh(ETH_DEV(priv), mr_ctrl, addr); + return mlx5_mr_addr2mr_bh(priv->sh->pd, &priv->mp_id, + &priv->sh->share_cache, mr_ctrl, addr, + priv->config.mr_ext_memseg_en); } /** @@ -1165,82 +238,6 @@ mlx5_tx_mb2mr_bh(struct mlx5_txq_data *txq, struct rte_mbuf *mb) return lkey; } -/** - * Flush all of the local cache entries. - * - * @param mr_ctrl - * Pointer to per-queue MR control structure. - */ -void -mlx5_mr_flush_local_cache(struct mlx5_mr_ctrl *mr_ctrl) -{ - /* Reset the most-recently-used index. */ - mr_ctrl->mru = 0; - /* Reset the linear search array. */ - mr_ctrl->head = 0; - memset(mr_ctrl->cache, 0, sizeof(mr_ctrl->cache)); - /* Reset the B-tree table. */ - mr_ctrl->cache_bh.len = 1; - mr_ctrl->cache_bh.overflow = 0; - /* Update the generation number. */ - mr_ctrl->cur_gen = *mr_ctrl->dev_gen_ptr; - DRV_LOG(DEBUG, "mr_ctrl(%p): flushed, cur_gen=%d", - (void *)mr_ctrl, mr_ctrl->cur_gen); -} - -/** - * Creates a memory region for external memory, that is memory which is not - * part of the DPDK memory segments. - * - * @param dev - * Pointer to the ethernet device. - * @param addr - * Starting virtual address of memory. - * @param len - * Length of memory segment being mapped. - * @param socked_id - * Socket to allocate heap memory for the control structures. - * - * @return - * Pointer to MR structure on success, NULL otherwise. - */ -static struct mlx5_mr * -mlx5_create_mr_ext(struct rte_eth_dev *dev, uintptr_t addr, size_t len, - int socket_id) -{ - struct mlx5_priv *priv = dev->data->dev_private; - struct mlx5_mr *mr = NULL; - - mr = rte_zmalloc_socket(NULL, - RTE_ALIGN_CEIL(sizeof(*mr), - RTE_CACHE_LINE_SIZE), - RTE_CACHE_LINE_SIZE, socket_id); - if (mr == NULL) - return NULL; - mr->ibv_mr = mlx5_glue->reg_mr(priv->sh->pd, (void *)addr, len, - IBV_ACCESS_LOCAL_WRITE | - IBV_ACCESS_RELAXED_ORDERING); - if (mr->ibv_mr == NULL) { - DRV_LOG(WARNING, - "port %u fail to create a verbs MR for address (%p)", - dev->data->port_id, (void *)addr); - rte_free(mr); - return NULL; - } - mr->msl = NULL; /* Mark it is external memory. */ - mr->ms_bmp = NULL; - mr->ms_n = 1; - mr->ms_bmp_n = 1; - DRV_LOG(DEBUG, - "port %u MR CREATED (%p) for external memory %p:\n" - " [0x%" PRIxPTR ", 0x%" PRIxPTR ")," - " lkey=0x%x base_idx=%u ms_n=%u, ms_bmp_n=%u", - dev->data->port_id, (void *)mr, (void *)addr, - addr, addr + len, rte_cpu_to_be_32(mr->ibv_mr->lkey), - mr->ms_base_idx, mr->ms_n, mr->ms_bmp_n); - return mr; -} - /** * Called during rte_mempool_mem_iter() by mlx5_mr_update_ext_mp(). * @@ -1267,19 +264,19 @@ mlx5_mr_update_ext_mp_cb(struct rte_mempool *mp, void *opaque, struct mlx5_mr *mr = NULL; uintptr_t addr = (uintptr_t)memhdr->addr; size_t len = memhdr->len; - struct mlx5_mr_cache entry; + struct mr_cache_entry entry; uint32_t lkey; MLX5_ASSERT(rte_eal_process_type() == RTE_PROC_PRIMARY); /* If already registered, it should return. */ - rte_rwlock_read_lock(&sh->mr.rwlock); - lkey = mr_lookup_dev(sh, &entry, addr); - rte_rwlock_read_unlock(&sh->mr.rwlock); + rte_rwlock_read_lock(&sh->share_cache.rwlock); + lkey = mlx5_mr_lookup_cache(&sh->share_cache, &entry, addr); + rte_rwlock_read_unlock(&sh->share_cache.rwlock); if (lkey != UINT32_MAX) return; DRV_LOG(DEBUG, "port %u register MR for chunk #%d of mempool (%s)", dev->data->port_id, mem_idx, mp->name); - mr = mlx5_create_mr_ext(dev, addr, len, mp->socket_id); + mr = mlx5_create_mr_ext(sh->pd, addr, len, mp->socket_id); if (!mr) { DRV_LOG(WARNING, "port %u unable to allocate a new MR of" @@ -1288,13 +285,14 @@ mlx5_mr_update_ext_mp_cb(struct rte_mempool *mp, void *opaque, data->ret = -1; return; } - rte_rwlock_write_lock(&sh->mr.rwlock); - LIST_INSERT_HEAD(&sh->mr.mr_list, mr, mr); + rte_rwlock_write_lock(&sh->share_cache.rwlock); + LIST_INSERT_HEAD(&sh->share_cache.mr_list, mr, mr); /* Insert to the global cache table. */ - mr_insert_dev_cache(sh, mr); - rte_rwlock_write_unlock(&sh->mr.rwlock); + mlx5_mr_insert_cache(&sh->share_cache, mr); + rte_rwlock_write_unlock(&sh->share_cache.rwlock); /* Insert to the local cache table */ - mlx5_mr_addr2mr_bh(dev, mr_ctrl, addr); + mlx5_mr_addr2mr_bh(sh->pd, &priv->mp_id, &sh->share_cache, + mr_ctrl, addr, priv->config.mr_ext_memseg_en); } /** @@ -1351,19 +349,19 @@ mlx5_dma_map(struct rte_pci_device *pdev, void *addr, return -1; } priv = dev->data->dev_private; - mr = mlx5_create_mr_ext(dev, (uintptr_t)addr, len, SOCKET_ID_ANY); + sh = priv->sh; + mr = mlx5_create_mr_ext(sh->pd, (uintptr_t)addr, len, SOCKET_ID_ANY); if (!mr) { DRV_LOG(WARNING, "port %u unable to dma map", dev->data->port_id); rte_errno = EINVAL; return -1; } - sh = priv->sh; - rte_rwlock_write_lock(&sh->mr.rwlock); - LIST_INSERT_HEAD(&sh->mr.mr_list, mr, mr); + rte_rwlock_write_lock(&sh->share_cache.rwlock); + LIST_INSERT_HEAD(&sh->share_cache.mr_list, mr, mr); /* Insert to the global cache table. */ - mr_insert_dev_cache(sh, mr); - rte_rwlock_write_unlock(&sh->mr.rwlock); + mlx5_mr_insert_cache(&sh->share_cache, mr); + rte_rwlock_write_unlock(&sh->share_cache.rwlock); return 0; } @@ -1390,7 +388,7 @@ mlx5_dma_unmap(struct rte_pci_device *pdev, void *addr, struct mlx5_priv *priv; struct mlx5_ibv_shared *sh; struct mlx5_mr *mr; - struct mlx5_mr_cache entry; + struct mr_cache_entry entry; dev = pci_dev_to_eth_dev(pdev); if (!dev) { @@ -1401,10 +399,10 @@ mlx5_dma_unmap(struct rte_pci_device *pdev, void *addr, } priv = dev->data->dev_private; sh = priv->sh; - rte_rwlock_read_lock(&sh->mr.rwlock); - mr = mr_lookup_dev_list(sh, &entry, (uintptr_t)addr); + rte_rwlock_read_lock(&sh->share_cache.rwlock); + mr = mlx5_mr_lookup_list(&sh->share_cache, &entry, (uintptr_t)addr); if (!mr) { - rte_rwlock_read_unlock(&sh->mr.rwlock); + rte_rwlock_read_unlock(&sh->share_cache.rwlock); DRV_LOG(WARNING, "address 0x%" PRIxPTR " wasn't registered " "to PCI device %p", (uintptr_t)addr, (void *)pdev); @@ -1412,10 +410,10 @@ mlx5_dma_unmap(struct rte_pci_device *pdev, void *addr, return -1; } LIST_REMOVE(mr, mr); - LIST_INSERT_HEAD(&sh->mr.mr_free_list, mr, mr); + LIST_INSERT_HEAD(&sh->share_cache.mr_free_list, mr, mr); DEBUG("port %u remove MR(%p) from list", dev->data->port_id, (void *)mr); - mr_rebuild_dev_cache(sh); + mlx5_mr_rebuild_cache(&sh->share_cache); /* * Flush local caches by propagating invalidation across cores. * rte_smp_wmb() is enough to synchronize this event. If one of @@ -1425,10 +423,11 @@ mlx5_dma_unmap(struct rte_pci_device *pdev, void *addr, * generation below) will be guaranteed to be seen by other core * before the core sees the newly allocated memory. */ - ++sh->mr.dev_gen; - DEBUG("broadcasting local cache flush, gen=%d", sh->mr.dev_gen); + ++sh->share_cache.dev_gen; + DEBUG("broadcasting local cache flush, gen=%d", + sh->share_cache.dev_gen); rte_smp_wmb(); - rte_rwlock_read_unlock(&sh->mr.rwlock); + rte_rwlock_read_unlock(&sh->share_cache.rwlock); return 0; } @@ -1503,14 +502,19 @@ mlx5_mr_update_mp_cb(struct rte_mempool *mp __rte_unused, void *opaque, unsigned mem_idx __rte_unused) { struct mr_update_mp_data *data = opaque; + struct rte_eth_dev *dev = data->dev; + struct mlx5_priv *priv = dev->data->dev_private; + uint32_t lkey; /* Stop iteration if failed in the previous walk. */ if (data->ret < 0) return; /* Register address of the chunk and update local caches. */ - lkey = mlx5_mr_addr2mr_bh(data->dev, data->mr_ctrl, - (uintptr_t)memhdr->addr); + lkey = mlx5_mr_addr2mr_bh(priv->sh->pd, &priv->mp_id, + &priv->sh->share_cache, data->mr_ctrl, + (uintptr_t)memhdr->addr, + priv->config.mr_ext_memseg_en); if (lkey == UINT32_MAX) data->ret = -1; } @@ -1545,76 +549,3 @@ mlx5_mr_update_mp(struct rte_eth_dev *dev, struct mlx5_mr_ctrl *mr_ctrl, } return data.ret; } - -/** - * Dump all the created MRs and the global cache entries. - * - * @param sh - * Pointer to Ethernet device shared context. - */ -void -mlx5_mr_dump_dev(struct mlx5_ibv_shared *sh __rte_unused) -{ -#ifdef RTE_LIBRTE_MLX5_DEBUG - struct mlx5_mr *mr; - int mr_n = 0; - int chunk_n = 0; - - rte_rwlock_read_lock(&sh->mr.rwlock); - /* Iterate all the existing MRs. */ - LIST_FOREACH(mr, &sh->mr.mr_list, mr) { - unsigned int n; - - DEBUG("device %s MR[%u], LKey = 0x%x, ms_n = %u, ms_bmp_n = %u", - sh->ibdev_name, mr_n++, - rte_cpu_to_be_32(mr->ibv_mr->lkey), - mr->ms_n, mr->ms_bmp_n); - if (mr->ms_n == 0) - continue; - for (n = 0; n < mr->ms_bmp_n; ) { - struct mlx5_mr_cache ret = { 0, }; - - n = mr_find_next_chunk(mr, &ret, n); - if (!ret.end) - break; - DEBUG(" chunk[%u], [0x%" PRIxPTR ", 0x%" PRIxPTR ")", - chunk_n++, ret.start, ret.end); - } - } - DEBUG("device %s dumping global cache", sh->ibdev_name); - mlx5_mr_btree_dump(&sh->mr.cache); - rte_rwlock_read_unlock(&sh->mr.rwlock); -#endif -} - -/** - * Release all the created MRs and resources for shared device context. - * list. - * - * @param sh - * Pointer to Ethernet device shared context. - */ -void -mlx5_mr_release(struct mlx5_ibv_shared *sh) -{ - struct mlx5_mr *mr_next; - - if (rte_log_can_log(mlx5_logtype, RTE_LOG_DEBUG)) - mlx5_mr_dump_dev(sh); - rte_rwlock_write_lock(&sh->mr.rwlock); - /* Detach from MR list and move to free list. */ - mr_next = LIST_FIRST(&sh->mr.mr_list); - while (mr_next != NULL) { - struct mlx5_mr *mr = mr_next; - - mr_next = LIST_NEXT(mr, mr); - LIST_REMOVE(mr, mr); - LIST_INSERT_HEAD(&sh->mr.mr_free_list, mr, mr); - } - LIST_INIT(&sh->mr.mr_list); - /* Free global cache. */ - mlx5_mr_btree_free(&sh->mr.cache); - rte_rwlock_write_unlock(&sh->mr.rwlock); - /* Free all remaining MRs. */ - mlx5_mr_garbage_collect(sh); -} diff --git a/drivers/net/mlx5/mlx5_mr.h b/drivers/net/mlx5/mlx5_mr.h index 48264c8294..0c5877b3d6 100644 --- a/drivers/net/mlx5/mlx5_mr.h +++ b/drivers/net/mlx5/mlx5_mr.h @@ -24,99 +24,16 @@ #include #include #include +#include -/* Memory Region object. */ -struct mlx5_mr { - LIST_ENTRY(mlx5_mr) mr; /**< Pointer to the prev/next entry. */ - struct ibv_mr *ibv_mr; /* Verbs Memory Region. */ - const struct rte_memseg_list *msl; - int ms_base_idx; /* Start index of msl->memseg_arr[]. */ - int ms_n; /* Number of memsegs in use. */ - uint32_t ms_bmp_n; /* Number of bits in memsegs bit-mask. */ - struct rte_bitmap *ms_bmp; /* Bit-mask of memsegs belonged to MR. */ -}; - -/* Cache entry for Memory Region. */ -struct mlx5_mr_cache { - uintptr_t start; /* Start address of MR. */ - uintptr_t end; /* End address of MR. */ - uint32_t lkey; /* rte_cpu_to_be_32(ibv_mr->lkey). */ -} __rte_packed; - -/* MR Cache table for Binary search. */ -struct mlx5_mr_btree { - uint16_t len; /* Number of entries. */ - uint16_t size; /* Total number of entries. */ - int overflow; /* Mark failure of table expansion. */ - struct mlx5_mr_cache (*table)[]; -} __rte_packed; - -/* Per-queue MR control descriptor. */ -struct mlx5_mr_ctrl { - uint32_t *dev_gen_ptr; /* Generation number of device to poll. */ - uint32_t cur_gen; /* Generation number saved to flush caches. */ - uint16_t mru; /* Index of last hit entry in top-half cache. */ - uint16_t head; /* Index of the oldest entry in top-half cache. */ - struct mlx5_mr_cache cache[MLX5_MR_CACHE_N]; /* Cache for top-half. */ - struct mlx5_mr_btree cache_bh; /* Cache for bottom-half. */ -} __rte_packed; - -struct mlx5_ibv_shared; -extern struct mlx5_dev_list mlx5_mem_event_cb_list; -extern rte_rwlock_t mlx5_mem_event_rwlock; +#include /* First entry must be NULL for comparison. */ #define mlx5_mr_btree_len(bt) ((bt)->len - 1) -int mlx5_mr_btree_init(struct mlx5_mr_btree *bt, int n, int socket); -void mlx5_mr_btree_free(struct mlx5_mr_btree *bt); -uint32_t mlx5_mr_create_primary(struct rte_eth_dev *dev, - struct mlx5_mr_cache *entry, uintptr_t addr); void mlx5_mr_mem_event_cb(enum rte_mem_event event_type, const void *addr, size_t len, void *arg); int mlx5_mr_update_mp(struct rte_eth_dev *dev, struct mlx5_mr_ctrl *mr_ctrl, struct rte_mempool *mp); -void mlx5_mr_release(struct mlx5_ibv_shared *sh); - -/* Debug purpose functions. */ -void mlx5_mr_btree_dump(struct mlx5_mr_btree *bt); -void mlx5_mr_dump_dev(struct mlx5_ibv_shared *sh); - -/** - * Look up LKey from given lookup table by linear search. Firstly look up the - * last-hit entry. If miss, the entire array is searched. If found, update the - * last-hit index and return LKey. - * - * @param lkp_tbl - * Pointer to lookup table. - * @param[in,out] cached_idx - * Pointer to last-hit index. - * @param n - * Size of lookup table. - * @param addr - * Search key. - * - * @return - * Searched LKey on success, UINT32_MAX on no match. - */ -static __rte_always_inline uint32_t -mlx5_mr_lookup_cache(struct mlx5_mr_cache *lkp_tbl, uint16_t *cached_idx, - uint16_t n, uintptr_t addr) -{ - uint16_t idx; - - if (likely(addr >= lkp_tbl[*cached_idx].start && - addr < lkp_tbl[*cached_idx].end)) - return lkp_tbl[*cached_idx].lkey; - for (idx = 0; idx < n && lkp_tbl[idx].start != 0; ++idx) { - if (addr >= lkp_tbl[idx].start && - addr < lkp_tbl[idx].end) { - /* Found. */ - *cached_idx = idx; - return lkp_tbl[idx].lkey; - } - } - return UINT32_MAX; -} #endif /* RTE_PMD_MLX5_MR_H_ */ diff --git a/drivers/net/mlx5/mlx5_rxtx.c b/drivers/net/mlx5/mlx5_rxtx.c index 42d7da8a4b..3e583d49a6 100644 --- a/drivers/net/mlx5/mlx5_rxtx.c +++ b/drivers/net/mlx5/mlx5_rxtx.c @@ -33,6 +33,7 @@ #include "mlx5_defs.h" #include "mlx5.h" +#include "mlx5_mr.h" #include "mlx5_utils.h" #include "mlx5_rxtx.h" #include "mlx5_autoconf.h" diff --git a/drivers/net/mlx5/mlx5_rxtx.h b/drivers/net/mlx5/mlx5_rxtx.h index d155c241eb..537d449c88 100644 --- a/drivers/net/mlx5/mlx5_rxtx.h +++ b/drivers/net/mlx5/mlx5_rxtx.h @@ -34,11 +34,11 @@ #include #include #include +#include #include "mlx5_defs.h" #include "mlx5_utils.h" #include "mlx5.h" -#include "mlx5_mr.h" #include "mlx5_autoconf.h" /* Support tunnel matching. */ @@ -598,8 +598,8 @@ mlx5_rx_addr2mr(struct mlx5_rxq_data *rxq, uintptr_t addr) uint32_t lkey; /* Linear search on MR cache array. */ - lkey = mlx5_mr_lookup_cache(mr_ctrl->cache, &mr_ctrl->mru, - MLX5_MR_CACHE_N, addr); + lkey = mlx5_mr_lookup_lkey(mr_ctrl->cache, &mr_ctrl->mru, + MLX5_MR_CACHE_N, addr); if (likely(lkey != UINT32_MAX)) return lkey; /* Take slower bottom-half (Binary Search) on miss. */ @@ -630,8 +630,8 @@ mlx5_tx_mb2mr(struct mlx5_txq_data *txq, struct rte_mbuf *mb) if (unlikely(*mr_ctrl->dev_gen_ptr != mr_ctrl->cur_gen)) mlx5_mr_flush_local_cache(mr_ctrl); /* Linear search on MR cache array. */ - lkey = mlx5_mr_lookup_cache(mr_ctrl->cache, &mr_ctrl->mru, - MLX5_MR_CACHE_N, addr); + lkey = mlx5_mr_lookup_lkey(mr_ctrl->cache, &mr_ctrl->mru, + MLX5_MR_CACHE_N, addr); if (likely(lkey != UINT32_MAX)) return lkey; /* Take slower bottom-half on miss. */ diff --git a/drivers/net/mlx5/mlx5_rxtx_vec.h b/drivers/net/mlx5/mlx5_rxtx_vec.h index ea925156f0..6ddcbfb0ad 100644 --- a/drivers/net/mlx5/mlx5_rxtx_vec.h +++ b/drivers/net/mlx5/mlx5_rxtx_vec.h @@ -13,6 +13,8 @@ #include "mlx5_autoconf.h" +#include "mlx5_mr.h" + /* HW checksum offload capabilities of vectorized Tx. */ #define MLX5_VEC_TX_CKSUM_OFFLOAD_CAP \ (DEV_TX_OFFLOAD_IPV4_CKSUM | \ diff --git a/drivers/net/mlx5/mlx5_trigger.c b/drivers/net/mlx5/mlx5_trigger.c index 438b705952..759670408b 100644 --- a/drivers/net/mlx5/mlx5_trigger.c +++ b/drivers/net/mlx5/mlx5_trigger.c @@ -11,6 +11,7 @@ #include #include "mlx5.h" +#include "mlx5_mr.h" #include "mlx5_rxtx.h" #include "mlx5_utils.h" #include "rte_pmd_mlx5.h" diff --git a/drivers/net/mlx5/mlx5_txq.c b/drivers/net/mlx5/mlx5_txq.c index 0653f4cf30..29e5cabab6 100644 --- a/drivers/net/mlx5/mlx5_txq.c +++ b/drivers/net/mlx5/mlx5_txq.c @@ -30,6 +30,7 @@ #include #include #include +#include #include "mlx5_defs.h" #include "mlx5_utils.h" @@ -1289,7 +1290,7 @@ mlx5_txq_new(struct rte_eth_dev *dev, uint16_t idx, uint16_t desc, goto error; } /* Save pointer of global generation number to check memory event. */ - tmpl->txq.mr_ctrl.dev_gen_ptr = &priv->sh->mr.dev_gen; + tmpl->txq.mr_ctrl.dev_gen_ptr = &priv->sh->share_cache.dev_gen; MLX5_ASSERT(desc > MLX5_TX_COMP_THRESH); tmpl->txq.offloads = conf->offloads | dev->data->dev_conf.txmode.offloads;