summaryrefslogtreecommitdiffstats
path: root/drivers/net/mlx5/mlx5_mr.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/net/mlx5/mlx5_mr.c')
-rw-r--r--drivers/net/mlx5/mlx5_mr.c1316
1 files changed, 1064 insertions, 252 deletions
diff --git a/drivers/net/mlx5/mlx5_mr.c b/drivers/net/mlx5/mlx5_mr.c
index 857dfcd8..1d1bcb5f 100644
--- a/drivers/net/mlx5/mlx5_mr.c
+++ b/drivers/net/mlx5/mlx5_mr.c
@@ -1,6 +1,6 @@
/* SPDX-License-Identifier: BSD-3-Clause
* Copyright 2016 6WIND S.A.
- * Copyright 2016 Mellanox.
+ * Copyright 2016 Mellanox Technologies, Ltd
*/
#ifdef PEDANTIC
@@ -13,362 +13,1174 @@
#include <rte_mempool.h>
#include <rte_malloc.h>
+#include <rte_rwlock.h>
#include "mlx5.h"
+#include "mlx5_mr.h"
#include "mlx5_rxtx.h"
#include "mlx5_glue.h"
-struct mlx5_check_mempool_data {
+struct mr_find_contig_memsegs_data {
+ uintptr_t addr;
+ uintptr_t start;
+ uintptr_t end;
+ const struct rte_memseg_list *msl;
+};
+
+struct mr_update_mp_data {
+ struct rte_eth_dev *dev;
+ struct mlx5_mr_ctrl *mr_ctrl;
int ret;
- char *start;
- char *end;
};
-/* Called by mlx5_check_mempool() when iterating the memory chunks. */
-static void
-mlx5_check_mempool_cb(struct rte_mempool *mp,
- void *opaque, struct rte_mempool_memhdr *memhdr,
- unsigned int mem_idx)
+/**
+ * Expand B-tree table to a given size. Can't be called with holding
+ * memory_hotplug_lock or priv->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_check_mempool_data *data = opaque;
+ struct mlx5_mr_cache *lkp_tbl;
+ uint16_t n;
+ uint16_t base = 0;
- (void)mp;
- (void)mem_idx;
+ assert(bt != NULL);
+ lkp_tbl = *bt->table;
+ n = bt->len;
+ /* First entry must be NULL for comparison. */
+ assert(bt->len > 0 || (lkp_tbl[0].start == 0 &&
+ lkp_tbl[0].lkey == UINT32_MAX));
+ /* Binary search. */
+ do {
+ register uint16_t delta = n >> 1;
- /* It already failed, skip the next chunks. */
- if (data->ret != 0)
- return;
- /* It is the first chunk. */
- if (data->start == NULL && data->end == NULL) {
- data->start = memhdr->addr;
- data->end = data->start + memhdr->len;
- return;
+ if (addr < lkp_tbl[base + delta].start) {
+ n = delta;
+ } else {
+ base += delta;
+ n -= delta;
+ }
+ } while (n > 1);
+ 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;
+
+ assert(bt != NULL);
+ assert(bt->len <= bt->size);
+ 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 (data->end == memhdr->addr) {
- data->end += memhdr->len;
- return;
+ /* 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;
}
- if (data->start == (char *)memhdr->addr + memhdr->len) {
- data->start -= memhdr->len;
+ 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)
+{
+#ifndef NDEBUG
+ 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);
}
- /* Error, mempool is not virtually contiguous. */
- data->ret = -1;
+#endif
}
/**
- * Check if a mempool can be used: it must be virtually contiguous.
+ * Find virtually contiguous memory chunk in a given MR.
*
- * @param[in] mp
- * Pointer to memory pool.
- * @param[out] start
- * Pointer to the start address of the mempool virtual memory area
- * @param[out] end
- * Pointer to the end address of the mempool virtual memory area
+ * @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
- * 0 on success (mempool is virtually contiguous), -1 on error.
+ * Next index to go on lookup.
*/
-static int mlx5_check_mempool(struct rte_mempool *mp, uintptr_t *start,
- uintptr_t *end)
+static int
+mr_find_next_chunk(struct mlx5_mr *mr, struct mlx5_mr_cache *entry,
+ int base_idx)
{
- struct mlx5_check_mempool_data data;
+ uintptr_t start = 0;
+ uintptr_t end = 0;
+ uint32_t idx = 0;
- memset(&data, 0, sizeof(data));
- rte_mempool_mem_iter(mp, mlx5_check_mempool_cb, &data);
- *start = (uintptr_t)data.start;
- *end = (uintptr_t)data.end;
+ 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;
- return data.ret;
+ msl = mr->msl;
+ ms = rte_fbarray_get(&msl->memseg_arr,
+ mr->ms_base_idx + idx);
+ 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;
}
/**
- * Register a Memory Region (MR) <-> Memory Pool (MP) association in
- * txq->mp2mr[]. If mp2mr[] is full, remove an entry first.
+ * 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.
*
- * This function should only be called by txq_mp2mr().
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param mr
+ * Pointer to MR to insert.
*
- * @param priv
- * Pointer to private structure.
- * @param txq
- * Pointer to TX queue structure.
- * @param[in] mp
- * Memory Pool for which a Memory Region lkey must be returned.
- * @param idx
- * Index of the next available entry.
+ * @return
+ * 0 on success, -1 on failure.
+ */
+static int
+mr_insert_dev_cache(struct rte_eth_dev *dev, struct mlx5_mr *mr)
+{
+ struct priv *priv = dev->data->dev_private;
+ unsigned int n;
+
+ DRV_LOG(DEBUG, "port %u inserting MR(%p) to global cache",
+ dev->data->port_id, (void *)mr);
+ for (n = 0; n < mr->ms_bmp_n; ) {
+ struct mlx5_mr_cache entry = { 0, };
+
+ /* Find a contiguous chunk and advance the index. */
+ n = mr_find_next_chunk(mr, &entry, n);
+ if (!entry.end)
+ break;
+ if (mr_btree_insert(&priv->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 dev
+ * Pointer to Ethernet device.
+ * @param[out] entry
+ * Pointer to returning MR cache entry. If no match, this will not be updated.
+ * @param addr
+ * Search key.
*
* @return
- * mr on success, NULL on failure.
+ * Found MR on match, NULL otherwise.
*/
-struct mlx5_mr*
-priv_txq_mp2mr_reg(struct priv *priv, struct mlx5_txq_data *txq,
- struct rte_mempool *mp, unsigned int idx)
+static struct mlx5_mr *
+mr_lookup_dev_list(struct rte_eth_dev *dev, struct mlx5_mr_cache *entry,
+ uintptr_t addr)
{
- struct mlx5_txq_ctrl *txq_ctrl =
- container_of(txq, struct mlx5_txq_ctrl, txq);
+ struct priv *priv = dev->data->dev_private;
struct mlx5_mr *mr;
- /* Add a new entry, register MR first. */
- DEBUG("%p: discovered new memory pool \"%s\" (%p)",
- (void *)txq_ctrl, mp->name, (void *)mp);
- mr = priv_mr_get(priv, mp);
- if (mr == NULL) {
- if (rte_eal_process_type() != RTE_PROC_PRIMARY) {
- DEBUG("Using unregistered mempool 0x%p(%s) in secondary process,"
- " please create mempool before rte_eth_dev_start()",
- (void *)mp, mp->name);
- return NULL;
+ /* Iterate all the existing MRs. */
+ LIST_FOREACH(mr, &priv->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 = { 0, };
+
+ n = mr_find_next_chunk(mr, &ret, n);
+ if (addr >= ret.start && addr < ret.end) {
+ /* Found. */
+ *entry = ret;
+ return mr;
+ }
}
- mr = priv_mr_new(priv, mp);
- }
- if (unlikely(mr == NULL)) {
- DEBUG("%p: unable to configure MR, ibv_reg_mr() failed.",
- (void *)txq_ctrl);
- return NULL;
- }
- if (unlikely(idx == RTE_DIM(txq->mp2mr))) {
- /* Table is full, remove oldest entry. */
- DEBUG("%p: MR <-> MP table full, dropping oldest entry.",
- (void *)txq_ctrl);
- --idx;
- priv_mr_release(priv, txq->mp2mr[0]);
- memmove(&txq->mp2mr[0], &txq->mp2mr[1],
- (sizeof(txq->mp2mr) - sizeof(txq->mp2mr[0])));
}
- /* Store the new entry. */
- txq_ctrl->txq.mp2mr[idx] = mr;
- DEBUG("%p: new MR lkey for MP \"%s\" (%p): 0x%08" PRIu32,
- (void *)txq_ctrl, mp->name, (void *)mp,
- txq_ctrl->txq.mp2mr[idx]->lkey);
- return mr;
+ return NULL;
}
/**
- * Register a Memory Region (MR) <-> Memory Pool (MP) association in
- * txq->mp2mr[]. If mp2mr[] is full, remove an entry first.
- *
- * This function should only be called by txq_mp2mr().
+ * Look up address on device.
*
- * @param txq
- * Pointer to TX queue structure.
- * @param[in] mp
- * Memory Pool for which a Memory Region lkey must be returned.
- * @param idx
- * Index of the next available entry.
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param[out] entry
+ * Pointer to returning MR cache entry. If no match, this will not be updated.
+ * @param addr
+ * Search key.
*
* @return
- * mr on success, NULL on failure.
+ * Searched LKey on success, UINT32_MAX on failure and rte_errno is set.
*/
-struct mlx5_mr*
-mlx5_txq_mp2mr_reg(struct mlx5_txq_data *txq, struct rte_mempool *mp,
- unsigned int idx)
+static uint32_t
+mr_lookup_dev(struct rte_eth_dev *dev, struct mlx5_mr_cache *entry,
+ uintptr_t addr)
{
- struct mlx5_txq_ctrl *txq_ctrl =
- container_of(txq, struct mlx5_txq_ctrl, txq);
+ struct priv *priv = dev->data->dev_private;
+ uint16_t idx;
+ uint32_t lkey = UINT32_MAX;
struct mlx5_mr *mr;
- priv_lock(txq_ctrl->priv);
- mr = priv_txq_mp2mr_reg(txq_ctrl->priv, txq, mp, idx);
- priv_unlock(txq_ctrl->priv);
- return 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(priv->mr.cache.overflow)) {
+ lkey = mr_btree_lookup(&priv->mr.cache, &idx, addr);
+ if (lkey != UINT32_MAX)
+ *entry = (*priv->mr.cache.table)[idx];
+ } else {
+ /* Falling back to the slowest path. */
+ mr = mr_lookup_dev_list(dev, entry, addr);
+ if (mr != NULL)
+ lkey = entry->lkey;
+ }
+ assert(lkey == UINT32_MAX || (addr >= entry->start &&
+ addr < entry->end));
+ return lkey;
}
-struct mlx5_mp2mr_mbuf_check_data {
- int ret;
-};
+/**
+ * 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);
+}
/**
- * Callback function for rte_mempool_obj_iter() to check whether a given
- * mempool object looks like a mbuf.
- *
- * @param[in] mp
- * The mempool pointer
- * @param[in] arg
- * Context data (struct txq_mp2mr_mbuf_check_data). Contains the
- * return value.
- * @param[in] obj
- * Object address.
- * @param index
- * Object index, unused.
+ * Releass resources of detached MR having no online entry.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
*/
static void
-txq_mp2mr_mbuf_check(struct rte_mempool *mp, void *arg, void *obj,
- uint32_t index __rte_unused)
+mlx5_mr_garbage_collect(struct rte_eth_dev *dev)
{
- struct mlx5_mp2mr_mbuf_check_data *data = arg;
- struct rte_mbuf *buf = obj;
+ struct priv *priv = dev->data->dev_private;
+ struct mlx5_mr *mr_next;
+ struct mlx5_mr_list free_list = LIST_HEAD_INITIALIZER(free_list);
+ /* Must be called from the primary process. */
+ assert(rte_eal_process_type() == RTE_PROC_PRIMARY);
/*
- * Check whether mbuf structure fits element size and whether mempool
- * pointer is valid.
+ * MR can't be freed with holding the lock because rte_free() could call
+ * memory free callback function. This will be a deadlock situation.
*/
- if (sizeof(*buf) > mp->elt_size || buf->pool != mp)
- data->ret = -1;
+ rte_rwlock_write_lock(&priv->mr.rwlock);
+ /* Detach the whole free list and release it after unlocking. */
+ free_list = priv->mr.mr_free_list;
+ LIST_INIT(&priv->mr.mr_free_list);
+ rte_rwlock_write_unlock(&priv->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;
}
/**
- * Iterator function for rte_mempool_walk() to register existing mempools and
- * fill the MP to MR cache of a TX queue.
+ * Create a new global Memroy Region (MR) for a missing virtual address.
+ * Register entire virtually contiguous memory chunk around the address.
+ *
+ * @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.
*
- * @param[in] mp
- * Memory Pool to register.
- * @param *arg
- * Pointer to TX queue structure.
+ * @return
+ * Searched LKey on success, UINT32_MAX on failure and rte_errno is set.
*/
-void
-mlx5_mp2mr_iter(struct rte_mempool *mp, void *arg)
+static uint32_t
+mlx5_mr_create(struct rte_eth_dev *dev, struct mlx5_mr_cache *entry,
+ uintptr_t addr)
{
- struct priv *priv = (struct priv *)arg;
- struct mlx5_mp2mr_mbuf_check_data data = {
- .ret = 0,
+ struct priv *priv = dev->data->dev_private;
+ struct rte_mem_config *mcfg = rte_eal_get_configuration()->mem_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 mlx5_mr *mr;
+ struct mr_find_contig_memsegs_data data_re;
- /* Register mempool only if the first element looks like a mbuf. */
- if (rte_mempool_obj_iter(mp, txq_mp2mr_mbuf_check, &data) == 0 ||
- data.ret == -1)
- return;
- mr = priv_mr_get(priv, mp);
- if (mr) {
- priv_mr_release(priv, mr);
- return;
+ DRV_LOG(DEBUG, "port %u creating a MR using address (%p)",
+ dev->data->port_id, (void *)addr);
+ if (rte_eal_process_type() != RTE_PROC_PRIMARY) {
+ DRV_LOG(WARNING,
+ "port %u using address (%p) of unregistered mempool"
+ " in secondary process, please create mempool"
+ " before rte_eth_dev_start()",
+ dev->data->port_id, (void *)addr);
+ rte_errno = EPERM;
+ goto err_nolock;
+ }
+ /*
+ * Release detached MRs if any. This can't be called with holding either
+ * memory_hotplug_lock or priv->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(dev);
+ /*
+ * 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 speicified 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.
+ */
+ 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. */
+ assert(rte_is_aligned((void *)data.start, data.msl->page_sz));
+ 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;
+ 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 bitamp 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_rwlock_read_lock(&mcfg->memory_hotplug_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_rwlock_read_unlock(&mcfg->memory_hotplug_lock);
+ mr_free(mr);
+ goto alloc_resources;
+ }
+ assert(data.msl == data_re.msl);
+ rte_rwlock_write_lock(&priv->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(dev, 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(&priv->mr.cache, entry);
+ DEBUG("port %u found MR for %p on final lookup, abort",
+ dev->data->port_id, (void *)addr);
+ rte_rwlock_write_unlock(&priv->mr.rwlock);
+ rte_rwlock_read_unlock(&mcfg->memory_hotplug_lock);
+ /*
+ * Must be unlocked before calling rte_free() because
+ * mlx5_mr_mem_event_free_cb() can be called inside.
+ */
+ mr_free(mr);
+ return entry->lkey;
}
- priv_mr_new(priv, mp);
+ /*
+ * 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 = { 0, };
+
+ start = data_re.start + n * msl->page_sz;
+ /* Exclude memsegs already registered by other MRs. */
+ if (mr_lookup_dev(dev, &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;
+ 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(priv->pd, (void *)data.start, len,
+ IBV_ACCESS_LOCAL_WRITE);
+ 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;
+ }
+ assert((uintptr_t)mr->ibv_mr->addr == data.start);
+ assert(mr->ibv_mr->length == len);
+ LIST_INSERT_HEAD(&priv->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(dev, mr);
+ /* Fill in output data. */
+ mr_lookup_dev(dev, entry, addr);
+ /* Lookup can't fail. */
+ assert(entry->lkey != UINT32_MAX);
+ rte_rwlock_write_unlock(&priv->mr.rwlock);
+ rte_rwlock_read_unlock(&mcfg->memory_hotplug_lock);
+ return entry->lkey;
+err_mrlock:
+ rte_rwlock_write_unlock(&priv->mr.rwlock);
+err_memlock:
+ rte_rwlock_read_unlock(&mcfg->memory_hotplug_lock);
+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;
}
/**
- * Register a new memory region from the mempool and store it in the memory
- * region list.
+ * Rebuild the global B-tree cache of device from the original MR list.
*
- * @param priv
- * Pointer to private structure.
- * @param mp
- * Pointer to the memory pool to register.
- * @return
- * The memory region on success.
+ * @param dev
+ * Pointer to Ethernet device.
*/
-struct mlx5_mr*
-priv_mr_new(struct priv *priv, struct rte_mempool *mp)
+static void
+mr_rebuild_dev_cache(struct rte_eth_dev *dev)
{
- const struct rte_memseg *ms = rte_eal_get_physmem_layout();
- uintptr_t start;
- uintptr_t end;
- unsigned int i;
+ struct priv *priv = dev->data->dev_private;
struct mlx5_mr *mr;
- mr = rte_zmalloc_socket(__func__, sizeof(*mr), 0, mp->socket_id);
- if (!mr) {
- DEBUG("unable to configure MR, ibv_reg_mr() failed.");
- return NULL;
+ DRV_LOG(DEBUG, "port %u rebuild dev cache[]", dev->data->port_id);
+ /* Flush cache to rebuild. */
+ priv->mr.cache.len = 1;
+ priv->mr.cache.overflow = 0;
+ /* Iterate all the existing MRs. */
+ LIST_FOREACH(mr, &priv->mr.mr_list, mr)
+ if (mr_insert_dev_cache(dev, 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
+ * result, the MR would be fragmented. If it becomes empty, the MR will be freed
+ * later by mlx5_mr_garbage_collect(). Even if this callback is called from a
+ * secondary process, the garbage collector will be called in primary process
+ * as the secondary process can't call mlx5_mr_create().
+ *
+ * The global cache must be rebuilt if there's any change and this event has to
+ * be propagated to dataplane threads to flush the local caches.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param addr
+ * Address of freed memory.
+ * @param len
+ * Size of freed memory.
+ */
+static void
+mlx5_mr_mem_event_free_cb(struct rte_eth_dev *dev, const void *addr, size_t len)
+{
+ struct priv *priv = dev->data->dev_private;
+ const struct rte_memseg_list *msl;
+ struct mlx5_mr *mr;
+ int ms_n;
+ int i;
+ int rebuild = 0;
+
+ DEBUG("port %u free callback: addr=%p, len=%zu",
+ dev->data->port_id, addr, len);
+ msl = rte_mem_virt2memseg_list(addr);
+ /* addr and len must be page-aligned. */
+ assert((uintptr_t)addr == RTE_ALIGN((uintptr_t)addr, msl->page_sz));
+ assert(len == RTE_ALIGN(len, msl->page_sz));
+ ms_n = len / msl->page_sz;
+ rte_rwlock_write_lock(&priv->mr.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;
+ 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(dev, &entry, start);
+ if (mr == NULL)
+ continue;
+ ms = rte_mem_virt2memseg((void *)start, msl);
+ assert(ms != NULL);
+ assert(msl->page_sz == ms->hugepage_sz);
+ ms_idx = rte_fbarray_find_idx(&msl->memseg_arr, ms);
+ pos = ms_idx - mr->ms_base_idx;
+ assert(rte_bitmap_get(mr->ms_bmp, pos));
+ assert(pos < mr->ms_bmp_n);
+ DEBUG("port %u MR(%p): clear bitmap[%u] for addr %p",
+ dev->data->port_id, (void *)mr, pos, (void *)start);
+ rte_bitmap_clear(mr->ms_bmp, pos);
+ if (--mr->ms_n == 0) {
+ LIST_REMOVE(mr, mr);
+ LIST_INSERT_HEAD(&priv->mr.mr_free_list, mr, mr);
+ DEBUG("port %u remove MR(%p) from list",
+ dev->data->port_id, (void *)mr);
+ }
+ /*
+ * MR is fragmented or will be freed. the global cache must be
+ * rebuilt.
+ */
+ rebuild = 1;
}
- if (mlx5_check_mempool(mp, &start, &end) != 0) {
- ERROR("mempool %p: not virtually contiguous",
- (void *)mp);
- return NULL;
+ if (rebuild) {
+ mr_rebuild_dev_cache(dev);
+ /*
+ * Flush local caches by propagating invalidation across cores.
+ * rte_smp_wmb() is enough to synchronize this event. If one of
+ * freed memsegs is seen by other core, that means the memseg
+ * has been allocated by allocator, which will come after this
+ * free call. Therefore, this store instruction (incrementing
+ * generation below) will be guaranteed to be seen by other core
+ * before the core sees the newly allocated memory.
+ */
+ ++priv->mr.dev_gen;
+ DEBUG("broadcasting local cache flush, gen=%d",
+ priv->mr.dev_gen);
+ rte_smp_wmb();
}
- DEBUG("mempool %p area start=%p end=%p size=%zu",
- (void *)mp, (void *)start, (void *)end,
- (size_t)(end - start));
- /* Save original addresses for exact MR lookup. */
- mr->start = start;
- mr->end = end;
- /* Round start and end to page boundary if found in memory segments. */
- for (i = 0; (i < RTE_MAX_MEMSEG) && (ms[i].addr != NULL); ++i) {
- uintptr_t addr = (uintptr_t)ms[i].addr;
- size_t len = ms[i].len;
- unsigned int align = ms[i].hugepage_sz;
-
- if ((start > addr) && (start < addr + len))
- start = RTE_ALIGN_FLOOR(start, align);
- if ((end > addr) && (end < addr + len))
- end = RTE_ALIGN_CEIL(end, align);
+ rte_rwlock_write_unlock(&priv->mr.rwlock);
+}
+
+/**
+ * Callback for memory event. This can be called from both primary and secondary
+ * process.
+ *
+ * @param event_type
+ * Memory event type.
+ * @param addr
+ * Address of memory.
+ * @param len
+ * Size of memory.
+ */
+void
+mlx5_mr_mem_event_cb(enum rte_mem_event event_type, const void *addr,
+ size_t len, void *arg __rte_unused)
+{
+ struct priv *priv;
+ struct mlx5_dev_list *dev_list = &mlx5_shared_data->mem_event_cb_list;
+
+ switch (event_type) {
+ case RTE_MEM_EVENT_FREE:
+ rte_rwlock_write_lock(&mlx5_shared_data->mem_event_rwlock);
+ /* Iterate all the existing mlx5 devices. */
+ LIST_FOREACH(priv, dev_list, mem_event_cb)
+ mlx5_mr_mem_event_free_cb(ETH_DEV(priv), addr, len);
+ rte_rwlock_write_unlock(&mlx5_shared_data->mem_event_rwlock);
+ break;
+ case RTE_MEM_EVENT_ALLOC:
+ default:
+ break;
}
- DEBUG("mempool %p using start=%p end=%p size=%zu for MR",
- (void *)mp, (void *)start, (void *)end,
- (size_t)(end - start));
- mr->mr = mlx5_glue->reg_mr(priv->pd, (void *)start, end - start,
- IBV_ACCESS_LOCAL_WRITE);
- mr->mp = mp;
- mr->lkey = rte_cpu_to_be_32(mr->mr->lkey);
- rte_atomic32_inc(&mr->refcnt);
- DEBUG("%p: new Memory Region %p refcnt: %d", (void *)priv,
- (void *)mr, rte_atomic32_read(&mr->refcnt));
- LIST_INSERT_HEAD(&priv->mr, mr, next);
- return mr;
}
/**
- * Search the memory region object in the memory region list.
+ * 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.
*
- * @param priv
- * Pointer to private structure.
- * @param mp
- * Pointer to the memory pool to register.
* @return
- * The memory region on success.
+ * Searched LKey on success, UINT32_MAX on no match.
*/
-struct mlx5_mr*
-priv_mr_get(struct priv *priv, struct rte_mempool *mp)
+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_mr *mr;
+ struct priv *priv = dev->data->dev_private;
+ struct mlx5_mr_btree *bt = &mr_ctrl->cache_bh;
+ uint16_t idx;
+ uint32_t lkey;
- assert(mp);
- if (LIST_EMPTY(&priv->mr))
- return NULL;
- LIST_FOREACH(mr, &priv->mr, next) {
- if (mr->mp == mp) {
- rte_atomic32_inc(&mr->refcnt);
- DEBUG("Memory Region %p refcnt: %d",
- (void *)mr, rte_atomic32_read(&mr->refcnt));
- return mr;
- }
+ /* 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(&priv->mr.rwlock);
+ lkey = mr_btree_lookup(&priv->mr.cache, &idx, addr);
+ if (lkey != UINT32_MAX) {
+ /* Found. */
+ *entry = (*priv->mr.cache.table)[idx];
+ rte_rwlock_read_unlock(&priv->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;
}
- return NULL;
+ rte_rwlock_read_unlock(&priv->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;
}
/**
- * Release the memory region object.
+ * 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 mr
- * Pointer to memory region to release.
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param mr_ctrl
+ * Pointer to per-queue MR control structure.
+ * @param addr
+ * Search key.
*
* @return
- * 0 on success, errno on failure.
+ * Searched LKey on success, UINT32_MAX on no match.
*/
-int
-priv_mr_release(struct priv *priv, struct mlx5_mr *mr)
+static uint32_t
+mlx5_mr_addr2mr_bh(struct rte_eth_dev *dev, struct mlx5_mr_ctrl *mr_ctrl,
+ uintptr_t addr)
{
- (void)priv;
- assert(mr);
- DEBUG("Memory Region %p refcnt: %d",
- (void *)mr, rte_atomic32_read(&mr->refcnt));
- if (rte_atomic32_dec_and_test(&mr->refcnt)) {
- claim_zero(mlx5_glue->dereg_mr(mr->mr));
- LIST_REMOVE(mr, next);
- rte_free(mr);
- return 0;
+ 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;
}
- return EBUSY;
+ /* 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;
}
/**
- * Verify the flow list is empty
+ * Bottom-half of LKey search on Rx.
*
- * @param priv
- * Pointer to private structure.
+ * @param rxq
+ * Pointer to Rx queue structure.
+ * @param addr
+ * Search key.
*
- * @return the number of object not released.
+ * @return
+ * Searched LKey on success, UINT32_MAX on no match.
+ */
+uint32_t
+mlx5_rx_addr2mr_bh(struct mlx5_rxq_data *rxq, uintptr_t addr)
+{
+ struct mlx5_rxq_ctrl *rxq_ctrl =
+ container_of(rxq, struct mlx5_rxq_ctrl, rxq);
+ struct mlx5_mr_ctrl *mr_ctrl = &rxq->mr_ctrl;
+ struct priv *priv = rxq_ctrl->priv;
+
+ DRV_LOG(DEBUG,
+ "Rx queue %u: miss on top-half, mru=%u, head=%u, addr=%p",
+ rxq_ctrl->idx, mr_ctrl->mru, mr_ctrl->head, (void *)addr);
+ return mlx5_mr_addr2mr_bh(ETH_DEV(priv), mr_ctrl, addr);
+}
+
+/**
+ * Bottom-half of LKey search on Tx.
+ *
+ * @param txq
+ * Pointer to Tx queue structure.
+ * @param addr
+ * Search key.
+ *
+ * @return
+ * Searched LKey on success, UINT32_MAX on no match.
+ */
+uint32_t
+mlx5_tx_addr2mr_bh(struct mlx5_txq_data *txq, uintptr_t addr)
+{
+ struct mlx5_txq_ctrl *txq_ctrl =
+ container_of(txq, struct mlx5_txq_ctrl, txq);
+ struct mlx5_mr_ctrl *mr_ctrl = &txq->mr_ctrl;
+ struct priv *priv = txq_ctrl->priv;
+
+ DRV_LOG(DEBUG,
+ "Tx queue %u: miss on top-half, mru=%u, head=%u, addr=%p",
+ txq_ctrl->idx, mr_ctrl->mru, mr_ctrl->head, (void *)addr);
+ return mlx5_mr_addr2mr_bh(ETH_DEV(priv), mr_ctrl, addr);
+}
+
+/**
+ * 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);
+}
+
+/* Called during rte_mempool_mem_iter() by mlx5_mr_update_mp(). */
+static void
+mlx5_mr_update_mp_cb(struct rte_mempool *mp __rte_unused, void *opaque,
+ struct rte_mempool_memhdr *memhdr,
+ unsigned mem_idx __rte_unused)
+{
+ struct mr_update_mp_data *data = opaque;
+ 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);
+ if (lkey == UINT32_MAX)
+ data->ret = -1;
+}
+
+/**
+ * Register entire memory chunks in a Mempool.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param mr_ctrl
+ * Pointer to per-queue MR control structure.
+ * @param mp
+ * Pointer to registering Mempool.
+ *
+ * @return
+ * 0 on success, -1 on failure.
*/
int
-priv_mr_verify(struct priv *priv)
+mlx5_mr_update_mp(struct rte_eth_dev *dev, struct mlx5_mr_ctrl *mr_ctrl,
+ struct rte_mempool *mp)
{
- int ret = 0;
+ struct mr_update_mp_data data = {
+ .dev = dev,
+ .mr_ctrl = mr_ctrl,
+ .ret = 0,
+ };
+
+ rte_mempool_mem_iter(mp, mlx5_mr_update_mp_cb, &data);
+ return data.ret;
+}
+
+/**
+ * Dump all the created MRs and the global cache entries.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ */
+void
+mlx5_mr_dump_dev(struct rte_eth_dev *dev __rte_unused)
+{
+#ifndef NDEBUG
+ struct priv *priv = dev->data->dev_private;
struct mlx5_mr *mr;
+ int mr_n = 0;
+ int chunk_n = 0;
- LIST_FOREACH(mr, &priv->mr, next) {
- DEBUG("%p: mr %p still referenced", (void *)priv,
- (void *)mr);
- ++ret;
+ rte_rwlock_read_lock(&priv->mr.rwlock);
+ /* Iterate all the existing MRs. */
+ LIST_FOREACH(mr, &priv->mr.mr_list, mr) {
+ unsigned int n;
+
+ DEBUG("port %u MR[%u], LKey = 0x%x, ms_n = %u, ms_bmp_n = %u",
+ dev->data->port_id, 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);
+ }
}
- return ret;
+ DEBUG("port %u dumping global cache", dev->data->port_id);
+ mlx5_mr_btree_dump(&priv->mr.cache);
+ rte_rwlock_read_unlock(&priv->mr.rwlock);
+#endif
+}
+
+/**
+ * Release all the created MRs and resources. Remove device from memory callback
+ * list.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ */
+void
+mlx5_mr_release(struct rte_eth_dev *dev)
+{
+ struct priv *priv = dev->data->dev_private;
+ struct mlx5_mr *mr_next = LIST_FIRST(&priv->mr.mr_list);
+
+ /* Remove from memory callback device list. */
+ rte_rwlock_write_lock(&mlx5_shared_data->mem_event_rwlock);
+ LIST_REMOVE(priv, mem_event_cb);
+ rte_rwlock_write_unlock(&mlx5_shared_data->mem_event_rwlock);
+ if (rte_log_get_level(mlx5_logtype) == RTE_LOG_DEBUG)
+ mlx5_mr_dump_dev(dev);
+ rte_rwlock_write_lock(&priv->mr.rwlock);
+ /* Detach from MR list and move to free list. */
+ while (mr_next != NULL) {
+ struct mlx5_mr *mr = mr_next;
+
+ mr_next = LIST_NEXT(mr, mr);
+ LIST_REMOVE(mr, mr);
+ LIST_INSERT_HEAD(&priv->mr.mr_free_list, mr, mr);
+ }
+ LIST_INIT(&priv->mr.mr_list);
+ /* Free global cache. */
+ mlx5_mr_btree_free(&priv->mr.cache);
+ rte_rwlock_write_unlock(&priv->mr.rwlock);
+ /* Free all remaining MRs. */
+ mlx5_mr_garbage_collect(dev);
}