This patch add multi-process support for dmadev.
Signed-off-by: Chengwen Feng <fengcheng...@huawei.com>
Acked-by: Bruce Richardson <bruce.richard...@intel.com>
Acked-by: Morten Brørup <m...@smartsharesystems.com>
Reviewed-by: Kevin Laatz <kevin.la...@intel.com>
Reviewed-by: Conor Walsh <conor.wa...@intel.com>
---
doc/guides/rel_notes/release_21_11.rst | 1 +
lib/dmadev/rte_dmadev.c | 168 ++++++++++++++++++++-----
lib/dmadev/rte_dmadev.h | 24 ++--
lib/dmadev/rte_dmadev_core.h | 45 +++++--
4 files changed, 185 insertions(+), 53 deletions(-)
diff --git a/doc/guides/rel_notes/release_21_11.rst
b/doc/guides/rel_notes/release_21_11.rst
index 21b3c48257..67d2bf5101 100644
--- a/doc/guides/rel_notes/release_21_11.rst
+++ b/doc/guides/rel_notes/release_21_11.rst
@@ -111,6 +111,7 @@ New Features
* Device allocation APIs.
* Control plane APIs.
* Data plane APIs.
+ * Multi-process support.
Removed Items
diff --git a/lib/dmadev/rte_dmadev.c b/lib/dmadev/rte_dmadev.c
index e0134b9eec..1338b29937 100644
--- a/lib/dmadev/rte_dmadev.c
+++ b/lib/dmadev/rte_dmadev.c
@@ -17,6 +17,13 @@
struct rte_dma_dev *rte_dma_devices;
static int16_t dma_devices_max;
+static struct {
+ /* Hold the dev_max information of the primary process. This field is
+ * set by the primary process and is read by the secondary process.
+ */
+ int16_t dev_max;
+ struct rte_dma_dev_data data[0];
+} *dma_devices_shared_data;
RTE_LOG_REGISTER_DEFAULT(rte_dma_logtype, INFO);
#define RTE_DMA_LOG(level, fmt, args...) \
@@ -76,11 +83,11 @@ dma_find_free_dev(void)
{
int16_t i;
- if (rte_dma_devices == NULL)
+ if (rte_dma_devices == NULL || dma_devices_shared_data == NULL)
return -1;
for (i = 0; i < dma_devices_max; i++) {
- if (rte_dma_devices[i].dev_name[0] == '\0')
+ if (dma_devices_shared_data->data[i].dev_name[0] == '\0')
return i;
}
@@ -97,7 +104,7 @@ dma_find(const char *name)
for (i = 0; i < dma_devices_max; i++) {
if ((rte_dma_devices[i].state != RTE_DMA_DEV_UNUSED) &&
- (!strcmp(name, rte_dma_devices[i].dev_name)))
+ (!strcmp(name, rte_dma_devices[i].data->dev_name)))
return &rte_dma_devices[i];
}
@@ -130,16 +137,65 @@ dma_process_data_prepare(void)
return 0;
}
+static int
+dma_shared_data_prepare(void)
+{
+ const char *mz_name = "rte_dma_dev_data";
+ const struct rte_memzone *mz;
+ size_t size;
+
+ if (dma_devices_shared_data != NULL)
+ return 0;
+
+ size = sizeof(*dma_devices_shared_data) +
+ sizeof(struct rte_dma_dev_data) * dma_devices_max;
+
+ if (rte_eal_process_type() == RTE_PROC_PRIMARY)
+ mz = rte_memzone_reserve(mz_name, size, rte_socket_id(), 0);
+ else
+ mz = rte_memzone_lookup(mz_name);
+ if (mz == NULL)
+ return -ENOMEM;
+
+ dma_devices_shared_data = mz->addr;
+ if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
+ memset(dma_devices_shared_data, 0, size);
+ dma_devices_shared_data->dev_max = dma_devices_max;
+ } else {
+ dma_devices_max = dma_devices_shared_data->dev_max;
+ }
+
+ return 0;
+}
+
static int
dma_data_prepare(void)
{
- if (dma_devices_max == 0)
- dma_devices_max = RTE_DMADEV_DEFAULT_MAX_DEVS;
- return dma_process_data_prepare();
+ int ret;
+
+ if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
+ if (dma_devices_max == 0)
+ dma_devices_max = RTE_DMADEV_DEFAULT_MAX_DEVS;
+ ret = dma_process_data_prepare();
+ if (ret)
+ return ret;
+ ret = dma_shared_data_prepare();
+ if (ret)
+ return ret;
+ } else {
+ ret = dma_shared_data_prepare();
+ if (ret)
+ return ret;
+ ret = dma_process_data_prepare();
+ if (ret)
+ return ret;
+ }
+
+ return 0;
}
static struct rte_dma_dev *
-dma_allocate(const char *name, int numa_node, size_t private_data_size)
+dma_allocate_primary(const char *name, int numa_node, size_t private_data_size)
{
struct rte_dma_dev *dev;
void *dev_private;
@@ -174,10 +230,55 @@ dma_allocate(const char *name, int numa_node, size_t
private_data_size)
dev = &rte_dma_devices[dev_id];
dev->dev_private = dev_private;
- rte_strscpy(dev->dev_name, name, sizeof(dev->dev_name));
- dev->dev_id = dev_id;
- dev->numa_node = numa_node;
- dev->dev_private = dev_private;
+ dev->data = &dma_devices_shared_data->data[dev_id];
+ rte_strscpy(dev->data->dev_name, name, sizeof(dev->data->dev_name));
+ dev->data->dev_id = dev_id;
+ dev->data->numa_node = numa_node;
+ dev->data->dev_private = dev_private;
+
+ return dev;
+}
+
+static struct rte_dma_dev *
+dma_attach_secondary(const char *name)
+{
+ struct rte_dma_dev *dev;
+ int16_t i;
+ int ret;
+
+ ret = dma_data_prepare();
+ if (ret < 0) {
+ RTE_DMA_LOG(ERR, "Cannot initialize dmadevs data");
+ return NULL;
+ }
+
+ for (i = 0; i < dma_devices_max; i++) {
+ if (!strcmp(dma_devices_shared_data->data[i].dev_name, name))
+ break;
+ }
+ if (i == dma_devices_max) {
+ RTE_DMA_LOG(ERR,
+ "Device %s is not driven by the primary process",
+ name);
+ return NULL;
+ }
+
+ dev = &rte_dma_devices[i];
+ dev->data = &dma_devices_shared_data->data[i];
+ dev->dev_private = dev->data->dev_private;
+
+ return dev;
+}
+
+static struct rte_dma_dev *
+dma_allocate(const char *name, int numa_node, size_t private_data_size)
+{
+ struct rte_dma_dev *dev;
+
+ if (rte_eal_process_type() == RTE_PROC_PRIMARY)
+ dev = dma_allocate_primary(name, numa_node, private_data_size);
+ else
+ dev = dma_attach_secondary(name);
return dev;
}
@@ -185,7 +286,11 @@ dma_allocate(const char *name, int numa_node, size_t
private_data_size)
static void
dma_release(struct rte_dma_dev *dev)
{
- rte_free(dev->dev_private);
+ if (rte_eal_process_type() == RTE_PROC_PRIMARY) {
+ memset(dev->data, 0, sizeof(struct rte_dma_dev_data));
+ rte_free(dev->dev_private);
+ }
+
memset(dev, 0, sizeof(struct rte_dma_dev));
}
@@ -219,7 +324,7 @@ rte_dma_pmd_release(const char *name)
return -EINVAL;
if (dev->state == RTE_DMA_DEV_READY)
- return rte_dma_close(dev->dev_id);
+ return rte_dma_close(dev->data->dev_id);
dma_release(dev);
return 0;
@@ -237,7 +342,7 @@ rte_dma_get_dev_id(const char *name)
if (dev == NULL)
return -EINVAL;
- return dev->dev_id;
+ return dev->data->dev_id;
}
bool
@@ -283,7 +388,7 @@ rte_dma_info_get(int16_t dev_id, struct rte_dma_info
*dev_info)
return ret;
dev_info->numa_node = dev->device->numa_node;
- dev_info->nb_vchans = dev->dev_conf.nb_vchans;
+ dev_info->nb_vchans = dev->data->dev_conf.nb_vchans;
return 0;
}
@@ -299,7 +404,7 @@ rte_dma_configure(int16_t dev_id, const struct rte_dma_conf
*dev_conf)
if (dev_conf == NULL)
return -EINVAL;
- if (dev->dev_started != 0) {
+ if (dev->data->dev_started != 0) {
RTE_DMA_LOG(ERR,
"Device %d must be stopped to allow configuration",
dev_id);
@@ -331,7 +436,8 @@ rte_dma_configure(int16_t dev_id, const struct rte_dma_conf
*dev_conf)
ret = (*dev->dev_ops->dev_configure)(dev, dev_conf,
sizeof(struct rte_dma_conf));
if (ret == 0)
- memcpy(&dev->dev_conf, dev_conf, sizeof(struct rte_dma_conf));
+ memcpy(&dev->data->dev_conf, dev_conf,
+ sizeof(struct rte_dma_conf));
return ret;
}
@@ -344,12 +450,12 @@ rte_dma_start(int16_t dev_id)
RTE_DMA_VALID_DEV_ID_OR_ERR_RET(dev_id, -EINVAL);
- if (dev->dev_conf.nb_vchans == 0) {
+ if (dev->data->dev_conf.nb_vchans == 0) {
RTE_DMA_LOG(ERR, "Device %d must be configured first", dev_id);
return -EINVAL;
}
- if (dev->dev_started != 0) {
+ if (dev->data->dev_started != 0) {
RTE_DMA_LOG(WARNING, "Device %d already started", dev_id);
return 0;
}
@@ -362,7 +468,7 @@ rte_dma_start(int16_t dev_id)
return ret;
mark_started:
- dev->dev_started = 1;
+ dev->data->dev_started = 1;
return 0;
}
@@ -374,7 +480,7 @@ rte_dma_stop(int16_t dev_id)
RTE_DMA_VALID_DEV_ID_OR_ERR_RET(dev_id, -EINVAL);
- if (dev->dev_started == 0) {
+ if (dev->data->dev_started == 0) {
RTE_DMA_LOG(WARNING, "Device %d already stopped", dev_id);
return 0;
}
@@ -387,7 +493,7 @@ rte_dma_stop(int16_t dev_id)
return ret;
mark_stopped:
- dev->dev_started = 0;
+ dev->data->dev_started = 0;
return 0;
}
@@ -400,7 +506,7 @@ rte_dma_close(int16_t dev_id)
RTE_DMA_VALID_DEV_ID_OR_ERR_RET(dev_id, -EINVAL);
/* Device must be stopped before it can be closed */
- if (dev->dev_started == 1) {
+ if (dev->data->dev_started == 1) {
RTE_DMA_LOG(ERR,
"Device %d must be stopped before closing", dev_id);
return -EBUSY;
@@ -427,7 +533,7 @@ rte_dma_vchan_setup(int16_t dev_id, uint16_t vchan,
if (conf == NULL)
return -EINVAL;
- if (dev->dev_started != 0) {
+ if (dev->data->dev_started != 0) {
RTE_DMA_LOG(ERR,
"Device %d must be stopped to allow configuration",
dev_id);
@@ -439,7 +545,7 @@ rte_dma_vchan_setup(int16_t dev_id, uint16_t vchan,
RTE_DMA_LOG(ERR, "Device %d get device info fail", dev_id);
return -EINVAL;
}
- if (dev->dev_conf.nb_vchans == 0) {
+ if (dev->data->dev_conf.nb_vchans == 0) {
RTE_DMA_LOG(ERR, "Device %d must be configured first", dev_id);
return -EINVAL;
}
@@ -513,7 +619,7 @@ rte_dma_stats_get(int16_t dev_id, uint16_t vchan, struct
rte_dma_stats *stats)
RTE_DMA_VALID_DEV_ID_OR_ERR_RET(dev_id, -EINVAL);
if (stats == NULL)
return -EINVAL;
- if (vchan >= dev->dev_conf.nb_vchans &&
+ if (vchan >= dev->data->dev_conf.nb_vchans &&
vchan != RTE_DMA_ALL_VCHAN) {
RTE_DMA_LOG(ERR,
"Device %d vchan %u out of range", dev_id, vchan);
@@ -532,7 +638,7 @@ rte_dma_stats_reset(int16_t dev_id, uint16_t vchan)
struct rte_dma_dev *dev = &rte_dma_devices[dev_id];
RTE_DMA_VALID_DEV_ID_OR_ERR_RET(dev_id, -EINVAL);
- if (vchan >= dev->dev_conf.nb_vchans &&
+ if (vchan >= dev->data->dev_conf.nb_vchans &&
vchan != RTE_DMA_ALL_VCHAN) {
RTE_DMA_LOG(ERR,
"Device %d vchan %u out of range", dev_id, vchan);
@@ -606,14 +712,14 @@ rte_dma_dump(int16_t dev_id, FILE *f)
}
(void)fprintf(f, "DMA Dev %d, '%s' [%s]\n",
- dev->dev_id,
- dev->dev_name,
- dev->dev_started ? "started" : "stopped");
+ dev->data->dev_id,
+ dev->data->dev_name,
+ dev->data->dev_started ? "started" : "stopped");
dma_dump_capability(f, dev_info.dev_capa);
(void)fprintf(f, " max_vchans_supported: %u\n", dev_info.max_vchans);
(void)fprintf(f, " nb_vchans_configured: %u\n", dev_info.nb_vchans);
(void)fprintf(f, " silent_mode: %s\n",
- dev->dev_conf.enable_silent ? "on" : "off");
+ dev->data->dev_conf.enable_silent ? "on" : "off");
if (dev->dev_ops->dev_dump != NULL)
return (*dev->dev_ops->dev_dump)(dev, f);
diff --git a/lib/dmadev/rte_dmadev.h b/lib/dmadev/rte_dmadev.h
index 84e30f7e61..561a1b1154 100644
--- a/lib/dmadev/rte_dmadev.h
+++ b/lib/dmadev/rte_dmadev.h
@@ -821,8 +821,8 @@ rte_dma_copy(int16_t dev_id, uint16_t vchan, rte_iova_t
src, rte_iova_t dst,
struct rte_dma_dev *dev = &rte_dma_devices[dev_id];
#ifdef RTE_DMADEV_DEBUG
- if (!rte_dma_is_valid(dev_id) || !dev->dev_started ||
- vchan >= dev->dev_conf.nb_vchans || length == 0)
+ if (!rte_dma_is_valid(dev_id) || !dev->data->dev_started ||
+ vchan >= dev->data->dev_conf.nb_vchans || length == 0)
return -EINVAL;
RTE_FUNC_PTR_OR_ERR_RET(*dev->copy, -ENOTSUP);
#endif
@@ -872,8 +872,8 @@ rte_dma_copy_sg(int16_t dev_id, uint16_t vchan, struct
rte_dma_sge *src,
struct rte_dma_dev *dev = &rte_dma_devices[dev_id];
#ifdef RTE_DMADEV_DEBUG
- if (!rte_dma_is_valid(dev_id) || !dev->dev_started ||
- vchan >= dev->dev_conf.nb_vchans ||
+ if (!rte_dma_is_valid(dev_id) || !dev->data->dev_started ||
+ vchan >= dev->data->dev_conf.nb_vchans ||
src == NULL || dst == NULL || nb_src == 0 || nb_dst == 0)
return -EINVAL;
RTE_FUNC_PTR_OR_ERR_RET(*dev->copy_sg, -ENOTSUP);
@@ -919,8 +919,8 @@ rte_dma_fill(int16_t dev_id, uint16_t vchan, uint64_t
pattern,
struct rte_dma_dev *dev = &rte_dma_devices[dev_id];
#ifdef RTE_DMADEV_DEBUG
- if (!rte_dma_is_valid(dev_id) || !dev->dev_started ||
- vchan >= dev->dev_conf.nb_vchans || length == 0)
+ if (!rte_dma_is_valid(dev_id) || !dev->data->dev_started ||
+ vchan >= dev->data->dev_conf.nb_vchans || length == 0)
return -EINVAL;
RTE_FUNC_PTR_OR_ERR_RET(*dev->fill, -ENOTSUP);
#endif
@@ -952,8 +952,8 @@ rte_dma_submit(int16_t dev_id, uint16_t vchan)
struct rte_dma_dev *dev = &rte_dma_devices[dev_id];
#ifdef RTE_DMADEV_DEBUG
- if (!rte_dma_is_valid(dev_id) || !dev->dev_started ||
- vchan >= dev->dev_conf.nb_vchans)
+ if (!rte_dma_is_valid(dev_id) || !dev->data->dev_started ||
+ vchan >= dev->data->dev_conf.nb_vchans)
return -EINVAL;
RTE_FUNC_PTR_OR_ERR_RET(*dev->submit, -ENOTSUP);
#endif
@@ -994,8 +994,8 @@ rte_dma_completed(int16_t dev_id, uint16_t vchan, const
uint16_t nb_cpls,
bool err;
#ifdef RTE_DMADEV_DEBUG
- if (!rte_dma_is_valid(dev_id) || !dev->dev_started ||
- vchan >= dev->dev_conf.nb_vchans || nb_cpls == 0)
+ if (!rte_dma_is_valid(dev_id) || !dev->data->dev_started ||
+ vchan >= dev->data->dev_conf.nb_vchans || nb_cpls == 0)
return 0;
RTE_FUNC_PTR_OR_ERR_RET(*dev->completed, 0);
#endif
@@ -1054,8 +1054,8 @@ rte_dma_completed_status(int16_t dev_id, uint16_t vchan,
uint16_t idx;
#ifdef RTE_DMADEV_DEBUG
- if (!rte_dma_is_valid(dev_id) || !dev->dev_started ||
- vchan >= dev->dev_conf.nb_vchans ||
+ if (!rte_dma_is_valid(dev_id) || !dev->data->dev_started ||
+ vchan >= dev->data->dev_conf.nb_vchans ||
nb_cpls == 0 || status == NULL)
return 0;
RTE_FUNC_PTR_OR_ERR_RET(*dev->completed_status, 0);
diff --git a/lib/dmadev/rte_dmadev_core.h b/lib/dmadev/rte_dmadev_core.h
index 5c202e35ce..019ac7af9c 100644
--- a/lib/dmadev/rte_dmadev_core.h
+++ b/lib/dmadev/rte_dmadev_core.h
@@ -118,10 +118,39 @@ struct rte_dma_dev_ops {
rte_dma_dump_t dev_dump;
};
-/** @internal
+/**
+ * @internal
+ * The data part, with no function pointers, associated with each DMA device.
+ *
+ * This structure is safe to place in shared memory to be common among
different
+ * processes in a multi-process configuration.
+ *
+ * @see struct rte_dmadev::data
+ */
+struct rte_dma_dev_data {
+ char dev_name[RTE_DEV_NAME_MAX_LEN]; /**< Unique identifier name */
+ int16_t dev_id; /**< Device [external] identifier. */
+ int16_t numa_node; /**< Local NUMA memory ID. -1 if unknown. */
+ /** PMD-specific private data.
+ * This is a copy of the 'dev_private' field in the 'struct rte_dmadev'
+ * from primary process, it is used by the secondary process to get
+ * dev_private information.
+ */
+ void *dev_private;
+ struct rte_dma_conf dev_conf; /**< DMA device configuration. */
+ uint8_t dev_started : 1; /**< Device state: STARTED(1)/STOPPED(0). */
+ uint64_t reserved[2]; /**< Reserved for future fields */
+} __rte_cache_aligned;
+
+/**
+ * @internal
* The generic data structure associated with each DMA device.
*
- * The dataplane APIs are located at the beginning of the structure.
+ * The dataplane APIs are located at the beginning of the structure, along
+ * with the pointer to where all the data elements for the particular device
+ * are stored in shared memory. This split scheme allows the function pointer
+ * and driver data to be per-process, while the actual configuration data for
+ * the device is shared.
* And the 'dev_private' field was placed in the first cache line to optimize
* performance because the PMD driver mainly depends on this field.
*/
@@ -134,20 +163,16 @@ struct rte_dma_dev {
rte_dma_completed_t completed;
rte_dma_completed_status_t completed_status;
void *reserved_cl0;
- /** Reserve space for future IO functions, while keeping dev_ops
- * pointer on the second cacheline.
+ /** Reserve space for future IO functions, while keeping data and
+ * dev_ops pointers on the second cacheline.
*/
- void *reserved_cl1[7];
+ void *reserved_cl1[6];
+ struct rte_dma_dev_data *data; /**< Pointer to device data. */
/** Functions exported by PMD. */
const struct rte_dma_dev_ops *dev_ops;
- char dev_name[RTE_DEV_NAME_MAX_LEN]; /**< Unique identifier name */
- int16_t dev_id; /**< Device [external] identifier. */
- int16_t numa_node; /**< Local NUMA memory ID. -1 if unknown. */
- struct rte_dma_conf dev_conf; /**< DMA device configuration. */
/** Device info which supplied during device initialization. */
struct rte_device *device;
enum rte_dma_dev_state state; /**< Flag indicating the device state. */
- uint8_t dev_started : 1; /**< Device state: STARTED(1)/STOPPED(0). */
uint64_t reserved[2]; /**< Reserved for future fields. */
} __rte_cache_aligned;
--
2.33.0
