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;
+
+ assert(mr->ms_bmp_n == 1);
+ assert(mr->ms_n == 1);
+ 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;
static int
mr_insert_dev_cache(struct rte_eth_dev *dev, struct mlx4_mr *mr)
{
- struct priv *priv = dev->data->dev_private;
+ struct mlx4_priv *priv = dev->data->dev_private;
unsigned int n;
DEBUG("port %u inserting MR(%p) to global cache",
dev->data->port_id, (void *)mr);
for (n = 0; n < mr->ms_bmp_n; ) {
- struct mlx4_mr_cache entry = { 0, };
+ struct mlx4_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)
mr_lookup_dev_list(struct rte_eth_dev *dev, struct mlx4_mr_cache *entry,
uintptr_t addr)
{
- struct priv *priv = dev->data->dev_private;
+ struct mlx4_priv *priv = dev->data->dev_private;
struct mlx4_mr *mr;
/* Iterate all the existing MRs. */
if (mr->ms_n == 0)
continue;
for (n = 0; n < mr->ms_bmp_n; ) {
- struct mlx4_mr_cache ret = { 0, };
+ struct mlx4_mr_cache ret;
+ memset(&ret, 0, sizeof(ret));
n = mr_find_next_chunk(mr, &ret, n);
if (addr >= ret.start && addr < ret.end) {
/* Found. */
mr_lookup_dev(struct rte_eth_dev *dev, struct mlx4_mr_cache *entry,
uintptr_t addr)
{
- struct priv *priv = dev->data->dev_private;
+ struct mlx4_priv *priv = dev->data->dev_private;
uint16_t idx;
uint32_t lkey = UINT32_MAX;
struct mlx4_mr *mr;
}
/**
- * Releass resources of detached MR having no online entry.
+ * Release resources of detached MR having no online entry.
*
* @param dev
* Pointer to Ethernet device.
static void
mlx4_mr_garbage_collect(struct rte_eth_dev *dev)
{
- struct priv *priv = dev->data->dev_private;
+ struct mlx4_priv *priv = dev->data->dev_private;
struct mlx4_mr *mr_next;
struct mlx4_mr_list free_list = LIST_HEAD_INITIALIZER(free_list);
+ /* Must be called from the primary process. */
+ 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.
}
/**
- * Create a new global Memroy Region (MR) for a missing virtual address.
- * Register entire virtually contiguous memory chunk around the address.
+ * 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.
* Searched LKey on success, UINT32_MAX on failure and rte_errno is set.
*/
static uint32_t
-mlx4_mr_create(struct rte_eth_dev *dev, struct mlx4_mr_cache *entry,
- uintptr_t addr)
+mlx4_mr_create_secondary(struct rte_eth_dev *dev, struct mlx4_mr_cache *entry,
+ uintptr_t addr)
{
- struct priv *priv = dev->data->dev_private;
+ struct mlx4_priv *priv = dev->data->dev_private;
+ int ret;
+
+ DEBUG("port %u requesting MR creation for address (%p)",
+ dev->data->port_id, (void *)addr);
+ ret = mlx4_mp_req_mr_create(dev, 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->mr.rwlock);
+ /* Fill in output data. */
+ mr_lookup_dev(dev, entry, addr);
+ /* Lookup can't fail. */
+ assert(entry->lkey != UINT32_MAX);
+ rte_rwlock_read_unlock(&priv->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
+mlx4_mr_create_primary(struct rte_eth_dev *dev, struct mlx4_mr_cache *entry,
+ uintptr_t addr)
+{
+ struct mlx4_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;
*/
mlx4_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
+ * 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.
+ * 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 (!rte_memseg_contig_walk(mr_find_contig_memsegs_cb, &data)) {
+ if (!priv->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)) {
WARN("port %u unable to find virtually contiguous"
" chunk for address (%p)."
" rte_memseg_contig_walk() failed.",
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) {
- WARN("port %u unable to initialize bitamp for a new MR of"
+ WARN("port %u unable to initialize bitmap for a new MR of"
" address (%p).",
dev->data->port_id, (void *)addr);
rte_errno = EINVAL;
*/
for (n = 0; n < ms_n; ++n) {
uintptr_t start;
- struct mlx4_mr_cache ret = { 0, };
+ struct mlx4_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(dev, &ret, start) == UINT32_MAX) {
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
+mlx4_mr_create(struct rte_eth_dev *dev, struct mlx4_mr_cache *entry,
+ uintptr_t addr)
+{
+ uint32_t ret = 0;
+
+ switch (rte_eal_process_type()) {
+ case RTE_PROC_PRIMARY:
+ ret = mlx4_mr_create_primary(dev, entry, addr);
+ break;
+ case RTE_PROC_SECONDARY:
+ ret = mlx4_mr_create_secondary(dev, entry, addr);
+ break;
+ default:
+ break;
+ }
+ return ret;
+}
+
/**
* Rebuild the global B-tree cache of device from the original MR list.
*
static void
mr_rebuild_dev_cache(struct rte_eth_dev *dev)
{
- struct priv *priv = dev->data->dev_private;
+ struct mlx4_priv *priv = dev->data->dev_private;
struct mlx4_mr *mr;
DEBUG("port %u rebuild dev cache[]", dev->data->port_id);
static void
mlx4_mr_mem_event_free_cb(struct rte_eth_dev *dev, const void *addr, size_t len)
{
- struct priv *priv = dev->data->dev_private;
+ struct mlx4_priv *priv = dev->data->dev_private;
const struct rte_memseg_list *msl;
struct mlx4_mr *mr;
int ms_n;
mr = mr_lookup_dev_list(dev, &entry, start);
if (mr == NULL)
continue;
+ assert(mr->msl); /* Can't be external memory. */
ms = rte_mem_virt2memseg((void *)start, msl);
assert(ms != NULL);
assert(msl->page_sz == ms->hugepage_sz);
mlx4_mr_mem_event_cb(enum rte_mem_event event_type, const void *addr,
size_t len, void *arg __rte_unused)
{
- struct priv *priv;
+ struct mlx4_priv *priv;
+ struct mlx4_dev_list *dev_list = &mlx4_shared_data->mem_event_cb_list;
+ /* Must be called from the primary process. */
+ assert(rte_eal_process_type() == RTE_PROC_PRIMARY);
switch (event_type) {
case RTE_MEM_EVENT_FREE:
- rte_rwlock_read_lock(&mlx4_mem_event_rwlock);
+ rte_rwlock_read_lock(&mlx4_shared_data->mem_event_rwlock);
/* Iterate all the existing mlx4 devices. */
- LIST_FOREACH(priv, &mlx4_mem_event_cb_list, mem_event_cb)
- mlx4_mr_mem_event_free_cb(priv->dev, addr, len);
- rte_rwlock_read_unlock(&mlx4_mem_event_rwlock);
+ LIST_FOREACH(priv, dev_list, mem_event_cb)
+ mlx4_mr_mem_event_free_cb(ETH_DEV(priv), addr, len);
+ rte_rwlock_read_unlock(&mlx4_shared_data->mem_event_rwlock);
break;
case RTE_MEM_EVENT_ALLOC:
default:
mlx4_mr_lookup_dev(struct rte_eth_dev *dev, struct mlx4_mr_ctrl *mr_ctrl,
struct mlx4_mr_cache *entry, uintptr_t addr)
{
- struct priv *priv = dev->data->dev_private;
+ struct mlx4_priv *priv = dev->data->dev_private;
struct mlx4_mr_btree *bt = &mr_ctrl->cache_bh;
uint16_t idx;
uint32_t lkey;
mlx4_rx_addr2mr_bh(struct rxq *rxq, uintptr_t addr)
{
struct mlx4_mr_ctrl *mr_ctrl = &rxq->mr_ctrl;
- struct priv *priv = rxq->priv;
+ struct mlx4_priv *priv = rxq->priv;
- DEBUG("Rx queue %u: miss on top-half, mru=%u, head=%u, addr=%p",
- rxq->stats.idx, mr_ctrl->mru, mr_ctrl->head, (void *)addr);
- return mlx4_mr_addr2mr_bh(priv->dev, mr_ctrl, addr);
+ return mlx4_mr_addr2mr_bh(ETH_DEV(priv), mr_ctrl, addr);
}
/**
* @return
* Searched LKey on success, UINT32_MAX on no match.
*/
-uint32_t
+static uint32_t
mlx4_tx_addr2mr_bh(struct txq *txq, uintptr_t addr)
{
struct mlx4_mr_ctrl *mr_ctrl = &txq->mr_ctrl;
- struct priv *priv = txq->priv;
+ struct mlx4_priv *priv = txq->priv;
+
+ return mlx4_mr_addr2mr_bh(ETH_DEV(priv), mr_ctrl, addr);
+}
+
+/**
+ * Bottom-half of LKey search on Tx. If it can't be searched in the memseg
+ * list, register the mempool of the mbuf as externally allocated memory.
+ *
+ * @param txq
+ * Pointer to Tx queue structure.
+ * @param mb
+ * Pointer to mbuf.
+ *
+ * @return
+ * Searched LKey on success, UINT32_MAX on no match.
+ */
+uint32_t
+mlx4_tx_mb2mr_bh(struct txq *txq, struct rte_mbuf *mb)
+{
+ uintptr_t addr = (uintptr_t)mb->buf_addr;
+ uint32_t lkey;
- DEBUG("Tx queue %u: miss on top-half, mru=%u, head=%u, addr=%p",
- txq->stats.idx, mr_ctrl->mru, mr_ctrl->head, (void *)addr);
- return mlx4_mr_addr2mr_bh(priv->dev, mr_ctrl, addr);
+ lkey = mlx4_tx_addr2mr_bh(txq, addr);
+ if (lkey == UINT32_MAX && rte_errno == ENXIO) {
+ /* Mempool may have externally allocated memory. */
+ return mlx4_tx_update_ext_mp(txq, addr, mlx4_mb2mp(mb));
+ }
+ return lkey;
}
/**
(void *)mr_ctrl, mr_ctrl->cur_gen);
}
+/**
+ * Called during rte_mempool_mem_iter() by mlx4_mr_update_ext_mp().
+ *
+ * Externally allocated chunk is registered and a MR is created for the chunk.
+ * The MR object is added to the global list. If memseg list of a MR object
+ * (mr->msl) is null, the MR object can be regarded as externally allocated
+ * memory.
+ *
+ * Once external memory is registered, it should be static. If the memory is
+ * freed and the virtual address range has different physical memory mapped
+ * again, it may cause crash on device due to the wrong translation entry. PMD
+ * can't track the free event of the external memory for now.
+ */
+static void
+mlx4_mr_update_ext_mp_cb(struct rte_mempool *mp, void *opaque,
+ struct rte_mempool_memhdr *memhdr,
+ unsigned mem_idx __rte_unused)
+{
+ struct mr_update_mp_data *data = opaque;
+ struct rte_eth_dev *dev = data->dev;
+ struct mlx4_priv *priv = dev->data->dev_private;
+ struct mlx4_mr_ctrl *mr_ctrl = data->mr_ctrl;
+ struct mlx4_mr *mr = NULL;
+ uintptr_t addr = (uintptr_t)memhdr->addr;
+ size_t len = memhdr->len;
+ struct mlx4_mr_cache entry;
+ uint32_t lkey;
+
+ assert(rte_eal_process_type() == RTE_PROC_PRIMARY);
+ /* If already registered, it should return. */
+ rte_rwlock_read_lock(&priv->mr.rwlock);
+ lkey = mr_lookup_dev(dev, &entry, addr);
+ rte_rwlock_read_unlock(&priv->mr.rwlock);
+ if (lkey != UINT32_MAX)
+ return;
+ mr = rte_zmalloc_socket(NULL,
+ RTE_ALIGN_CEIL(sizeof(*mr),
+ RTE_CACHE_LINE_SIZE),
+ RTE_CACHE_LINE_SIZE, mp->socket_id);
+ if (mr == NULL) {
+ WARN("port %u unable to allocate memory for a new MR of"
+ " mempool (%s).",
+ dev->data->port_id, mp->name);
+ data->ret = -1;
+ return;
+ }
+ DEBUG("port %u register MR for chunk #%d of mempool (%s)",
+ dev->data->port_id, mem_idx, mp->name);
+ mr->ibv_mr = mlx4_glue->reg_mr(priv->pd, (void *)addr, len,
+ IBV_ACCESS_LOCAL_WRITE);
+ if (mr->ibv_mr == NULL) {
+ WARN("port %u fail to create a verbs MR for address (%p)",
+ dev->data->port_id, (void *)addr);
+ rte_free(mr);
+ data->ret = -1;
+ return;
+ }
+ mr->msl = NULL; /* Mark it is external memory. */
+ mr->ms_bmp = NULL;
+ mr->ms_n = 1;
+ mr->ms_bmp_n = 1;
+ rte_rwlock_write_lock(&priv->mr.rwlock);
+ LIST_INSERT_HEAD(&priv->mr.mr_list, mr, mr);
+ 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);
+ /* Insert to the global cache table. */
+ mr_insert_dev_cache(dev, mr);
+ rte_rwlock_write_unlock(&priv->mr.rwlock);
+ /* Insert to the local cache table */
+ mlx4_mr_addr2mr_bh(dev, mr_ctrl, addr);
+}
+
+/**
+ * Register MR for entire memory chunks in a Mempool having externally allocated
+ * memory and fill in local cache.
+ *
+ * @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.
+ */
+static uint32_t
+mlx4_mr_update_ext_mp(struct rte_eth_dev *dev, struct mlx4_mr_ctrl *mr_ctrl,
+ struct rte_mempool *mp)
+{
+ struct mr_update_mp_data data = {
+ .dev = dev,
+ .mr_ctrl = mr_ctrl,
+ .ret = 0,
+ };
+
+ rte_mempool_mem_iter(mp, mlx4_mr_update_ext_mp_cb, &data);
+ return data.ret;
+}
+
+/**
+ * Register MR entire memory chunks in a Mempool having externally allocated
+ * memory and search LKey of the address to return.
+ *
+ * @param dev
+ * Pointer to Ethernet device.
+ * @param addr
+ * Search key.
+ * @param mp
+ * Pointer to registering Mempool where addr belongs.
+ *
+ * @return
+ * LKey for address on success, UINT32_MAX on failure.
+ */
+uint32_t
+mlx4_tx_update_ext_mp(struct txq *txq, uintptr_t addr, struct rte_mempool *mp)
+{
+ struct mlx4_mr_ctrl *mr_ctrl = &txq->mr_ctrl;
+ struct mlx4_priv *priv = txq->priv;
+
+ if (rte_eal_process_type() != RTE_PROC_PRIMARY) {
+ WARN("port %u using address (%p) from unregistered mempool"
+ " having externally allocated memory"
+ " in secondary process, please create mempool"
+ " prior to rte_eth_dev_start()",
+ PORT_ID(priv), (void *)addr);
+ return UINT32_MAX;
+ }
+ mlx4_mr_update_ext_mp(ETH_DEV(priv), mr_ctrl, mp);
+ return mlx4_tx_addr2mr_bh(txq, addr);
+}
+
/* Called during rte_mempool_mem_iter() by mlx4_mr_update_mp(). */
static void
mlx4_mr_update_mp_cb(struct rte_mempool *mp __rte_unused, void *opaque,
};
rte_mempool_mem_iter(mp, mlx4_mr_update_mp_cb, &data);
+ if (data.ret < 0 && rte_errno == ENXIO) {
+ /* Mempool may have externally allocated memory. */
+ return mlx4_mr_update_ext_mp(dev, mr_ctrl, mp);
+ }
return data.ret;
}
void
mlx4_mr_dump_dev(struct rte_eth_dev *dev)
{
- struct priv *priv = dev->data->dev_private;
+ struct mlx4_priv *priv = dev->data->dev_private;
struct mlx4_mr *mr;
int mr_n = 0;
int chunk_n = 0;
if (mr->ms_n == 0)
continue;
for (n = 0; n < mr->ms_bmp_n; ) {
- struct mlx4_mr_cache ret = { 0, };
+ struct mlx4_mr_cache ret;
+ memset(&ret, 0, sizeof(ret));
n = mr_find_next_chunk(mr, &ret, n);
if (!ret.end)
break;
void
mlx4_mr_release(struct rte_eth_dev *dev)
{
- struct priv *priv = dev->data->dev_private;
- struct mlx4_mr *mr_next = LIST_FIRST(&priv->mr.mr_list);
+ struct mlx4_priv *priv = dev->data->dev_private;
+ struct mlx4_mr *mr_next;
/* Remove from memory callback device list. */
- rte_rwlock_write_lock(&mlx4_mem_event_rwlock);
+ rte_rwlock_write_lock(&mlx4_shared_data->mem_event_rwlock);
LIST_REMOVE(priv, mem_event_cb);
- rte_rwlock_write_unlock(&mlx4_mem_event_rwlock);
+ rte_rwlock_write_unlock(&mlx4_shared_data->mem_event_rwlock);
#ifndef NDEBUG
mlx4_mr_dump_dev(dev);
#endif
rte_rwlock_write_lock(&priv->mr.rwlock);
/* Detach from MR list and move to free list. */
+ mr_next = LIST_FIRST(&priv->mr.mr_list);
while (mr_next != NULL) {
struct mlx4_mr *mr = mr_next;
git.droids-corp.org / dpdk.git / blobdiff