summaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorYongseok Koh <yskoh@mellanox.com>2019-04-01 14:17:55 -0700
committerFerruh Yigit <ferruh.yigit@intel.com>2019-04-05 17:45:22 +0200
commitc18cf501a7af30715ba9984b0d05ab4cd9298b05 (patch)
tree6e1dc7eca6908a47eea6119c5dfa6a40e7340c17
parentdceb5029425175c93d5d56677393cbc7a44f29e5 (diff)
downloaddpdk-c18cf501a7af30715ba9984b0d05ab4cd9298b05.zip
dpdk-c18cf501a7af30715ba9984b0d05ab4cd9298b05.tar.gz
dpdk-c18cf501a7af30715ba9984b0d05ab4cd9298b05.tar.xz
net/mlx5: enable secondary process to register DMA memory
The Memory Region (MR) for DMA memory can't be created from secondary process due to lib/driver limitation. Whenever it is needed, secondary process can make a request to primary process through the EAL IPC channel (rte_mp_msg) which is established on initialization. Once a MR is created by primary process, it is immediately visible to secondary process because the MR list is global per a device. Thus, secondary process can look up the list after the request is successfully returned. Signed-off-by: Yongseok Koh <yskoh@mellanox.com> Acked-by: Shahaf Shuler <shahafs@mellanox.com>
-rw-r--r--doc/guides/nics/mlx5.rst1
-rw-r--r--drivers/net/mlx5/mlx5.h6
-rw-r--r--drivers/net/mlx5/mlx5_mp.c50
-rw-r--r--drivers/net/mlx5/mlx5_mr.c96
-rw-r--r--drivers/net/mlx5/mlx5_mr.h2
5 files changed, 142 insertions, 13 deletions
diff --git a/doc/guides/nics/mlx5.rst b/doc/guides/nics/mlx5.rst
index e5e3d90..5fa6b62 100644
--- a/doc/guides/nics/mlx5.rst
+++ b/doc/guides/nics/mlx5.rst
@@ -85,7 +85,6 @@ Limitations
- For secondary process:
- Forked secondary process not supported.
- - All mempools must be initialized before rte_eth_dev_start().
- External memory unregistered in EAL memseg list cannot be used for DMA
unless such memory has been registered by ``mlx5_mr_update_ext_mp()`` in
primary process and remapped to the same virtual address in secondary
diff --git a/drivers/net/mlx5/mlx5.h b/drivers/net/mlx5/mlx5.h
index b3445f1..47a7d75 100644
--- a/drivers/net/mlx5/mlx5.h
+++ b/drivers/net/mlx5/mlx5.h
@@ -59,6 +59,7 @@ enum {
/* Request types for IPC. */
enum mlx5_mp_req_type {
MLX5_MP_REQ_VERBS_CMD_FD = 1,
+ MLX5_MP_REQ_CREATE_MR,
MLX5_MP_REQ_START_RXTX,
MLX5_MP_REQ_STOP_RXTX,
};
@@ -68,6 +69,10 @@ struct mlx5_mp_param {
enum mlx5_mp_req_type type;
int port_id;
int result;
+ RTE_STD_C11
+ union {
+ uintptr_t addr; /* MLX5_MP_REQ_CREATE_MR */
+ } args;
};
/** Request timeout for IPC. */
@@ -467,6 +472,7 @@ void mlx5_flow_delete_drop_queue(struct rte_eth_dev *dev);
/* mlx5_mp.c */
void mlx5_mp_req_start_rxtx(struct rte_eth_dev *dev);
void mlx5_mp_req_stop_rxtx(struct rte_eth_dev *dev);
+int mlx5_mp_req_mr_create(struct rte_eth_dev *dev, uintptr_t addr);
int mlx5_mp_req_verbs_cmd_fd(struct rte_eth_dev *dev);
void mlx5_mp_init_primary(void);
void mlx5_mp_uninit_primary(void);
diff --git a/drivers/net/mlx5/mlx5_mp.c b/drivers/net/mlx5/mlx5_mp.c
index 45dcc30..cea74ad 100644
--- a/drivers/net/mlx5/mlx5_mp.c
+++ b/drivers/net/mlx5/mlx5_mp.c
@@ -58,6 +58,8 @@ 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;
+ uint32_t lkey;
int ret;
assert(rte_eal_process_type() == RTE_PROC_PRIMARY);
@@ -69,6 +71,13 @@ mp_primary_handle(const struct rte_mp_msg *mp_msg, const void *peer)
dev = &rte_eth_devices[param->port_id];
priv = dev->data->dev_private;
switch (param->type) {
+ case MLX5_MP_REQ_CREATE_MR:
+ mp_init_msg(dev, &mp_res, param->type);
+ lkey = mlx5_mr_create_primary(dev, &entry, param->args.addr);
+ if (lkey == UINT32_MAX)
+ res->result = -rte_errno;
+ ret = rte_mp_reply(&mp_res, peer);
+ break;
case MLX5_MP_REQ_VERBS_CMD_FD:
mp_init_msg(dev, &mp_res, param->type);
mp_res.num_fds = 1;
@@ -221,6 +230,47 @@ mlx5_mp_req_stop_rxtx(struct rte_eth_dev *dev)
}
/**
+ * Request Memory Region creation to the primary process.
+ *
+ * @param[in] dev
+ * Pointer to Ethernet structure.
+ * @param addr
+ * Target virtual address to register.
+ *
+ * @return
+ * 0 on success, a negative errno value otherwise and rte_errno is set.
+ */
+int
+mlx5_mp_req_mr_create(struct rte_eth_dev *dev, uintptr_t addr)
+{
+ struct rte_mp_msg mp_req;
+ struct rte_mp_msg *mp_res;
+ struct rte_mp_reply mp_rep;
+ struct mlx5_mp_param *req = (struct mlx5_mp_param *)mp_req.param;
+ struct mlx5_mp_param *res;
+ struct timespec ts = {.tv_sec = MLX5_MP_REQ_TIMEOUT_SEC, .tv_nsec = 0};
+ int ret;
+
+ assert(rte_eal_process_type() == RTE_PROC_SECONDARY);
+ mp_init_msg(dev, &mp_req, MLX5_MP_REQ_CREATE_MR);
+ req->args.addr = addr;
+ ret = rte_mp_request_sync(&mp_req, &mp_rep, &ts);
+ if (ret) {
+ DRV_LOG(ERR, "port %u request to primary process failed",
+ dev->data->port_id);
+ return -rte_errno;
+ }
+ assert(mp_rep.nb_received == 1);
+ mp_res = &mp_rep.msgs[0];
+ res = (struct mlx5_mp_param *)mp_res->param;
+ ret = res->result;
+ if (ret)
+ rte_errno = -ret;
+ free(mp_rep.msgs);
+ return ret;
+}
+
+/**
* Request Verbs command file descriptor for mmap to the primary process.
*
* @param[in] dev
diff --git a/drivers/net/mlx5/mlx5_mr.c b/drivers/net/mlx5/mlx5_mr.c
index 78d8297..44b6591 100644
--- a/drivers/net/mlx5/mlx5_mr.c
+++ b/drivers/net/mlx5/mlx5_mr.c
@@ -517,7 +517,10 @@ mr_find_contig_memsegs_cb(const struct rte_memseg_list *msl,
/**
* Create a new global Memroy Region (MR) for a missing virtual address.
- * Register entire virtually contiguous memory chunk around the 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.
@@ -531,8 +534,52 @@ mr_find_contig_memsegs_cb(const struct rte_memseg_list *msl,
* 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)
+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(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 Memroy 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_dev_config *config = &priv->config;
@@ -553,15 +600,6 @@ mlx5_mr_create(struct rte_eth_dev *dev, struct mlx5_mr_cache *entry,
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
@@ -773,6 +811,40 @@ err_nolock:
}
/**
+ * Create a new global Memroy 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 dev
diff --git a/drivers/net/mlx5/mlx5_mr.h b/drivers/net/mlx5/mlx5_mr.h
index a57003f..786f6a3 100644
--- a/drivers/net/mlx5/mlx5_mr.h
+++ b/drivers/net/mlx5/mlx5_mr.h
@@ -70,6 +70,8 @@ extern rte_rwlock_t mlx5_mem_event_rwlock;
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,