[RFC,net-next,v5,08/14] memory-provider: dmabuf devmem memory provider

Commit Message

Mina Almasry Dec. 18, 2023, 2:40 a.m. UTC

Implement a memory provider that allocates dmabuf devmem in the form of
net_iov.

The provider receives a reference to the struct netdev_dmabuf_binding
via the pool->mp_priv pointer. The driver needs to set this pointer for
the provider in the net_iov.

The provider obtains a reference on the netdev_dmabuf_binding which
guarantees the binding and the underlying mapping remains alive until
the provider is destroyed.

Usage of PP_FLAG_DMA_MAP is required for this memory provide such that
the page_pool can provide the driver with the dma-addrs of the devmem.

Support for PP_FLAG_DMA_SYNC_DEV is omitted for simplicity & p.order !=
0.

Signed-off-by: Willem de Bruijn <[e-mail]>
Signed-off-by: Kaiyuan Zhang <[e-mail]>
Signed-off-by: Mina Almasry <[e-mail]>

---

v2:
- Disable devmem for p.order != 0

v1:
- static_branch check in page_is_page_pool_iov() (Willem & Paolo).
- PP_DEVMEM -> PP_IOV (David).
- Require PP_FLAG_DMA_MAP (Jakub).


memory provider

---
 include/net/netmem.h          | 14 ++++++
 include/net/page_pool/types.h |  2 +
 net/core/page_pool.c          | 93 +++++++++++++++++++++++++++++++++++
 3 files changed, 109 insertions(+)

Comments

Pavel Begunkov Feb. 13, 2024, 1:19 p.m. UTC | #1

On 12/18/23 02:40, Mina Almasry wrote:
> Implement a memory provider that allocates dmabuf devmem in the form of
> net_iov.
> 
> The provider receives a reference to the struct netdev_dmabuf_binding
> via the pool->mp_priv pointer. The driver needs to set this pointer for
> the provider in the net_iov.
> 
> The provider obtains a reference on the netdev_dmabuf_binding which
> guarantees the binding and the underlying mapping remains alive until
> the provider is destroyed.
> 
> Usage of PP_FLAG_DMA_MAP is required for this memory provide such that
> the page_pool can provide the driver with the dma-addrs of the devmem.
> 
> Support for PP_FLAG_DMA_SYNC_DEV is omitted for simplicity & p.order !=
> 0.
> 
> Signed-off-by: Willem de Bruijn <[e-mail]>
> Signed-off-by: Kaiyuan Zhang <[e-mail]>
> Signed-off-by: Mina Almasry <[e-mail]>
> 
> ---
...
> +
> +static bool mp_dmabuf_devmem_release_page(struct page_pool *pool,
> +					  struct netmem *netmem)
> +{
> +	WARN_ON_ONCE(!netmem_is_net_iov(netmem));
> +
> +	page_pool_clear_pp_info(netmem);
> +
> +	netdev_free_dmabuf(netmem_to_net_iov(netmem));
> +
> +	/* We don't want the page pool put_page()ing our net_iovs. */
> +	return false;
> +}
> +
> +const struct memory_provider_ops dmabuf_devmem_ops = {
> +	.init			= mp_dmabuf_devmem_init,
> +	.destroy		= mp_dmabuf_devmem_destroy,
> +	.alloc_pages		= mp_dmabuf_devmem_alloc_pages,
> +	.release_page		= mp_dmabuf_devmem_release_page,
> +};
> +EXPORT_SYMBOL(dmabuf_devmem_ops);

It might make sense to move all these functions together with
new code from core/dev.c into a new file

Patch

diff --git a/include/net/netmem.h b/include/net/netmem.h
index 7557aecc0f78..ab3824b7b789 100644
--- a/include/net/netmem.h
+++ b/include/net/netmem.h
@@ -97,6 +97,20 @@  static inline bool netmem_is_net_iov(const struct netmem *netmem)
 #endif
 }
 
+static inline struct net_iov *netmem_to_net_iov(struct netmem *netmem)
+{
+	if (netmem_is_net_iov(netmem))
+		return (struct net_iov *)((unsigned long)netmem & ~NET_IOV);
+
+	DEBUG_NET_WARN_ON_ONCE(true);
+	return NULL;
+}
+
+static inline struct netmem *net_iov_to_netmem(struct net_iov *niov)
+{
+	return (struct netmem *)((unsigned long)niov | NET_IOV);
+}
+
 static inline struct page *netmem_to_page(struct netmem *netmem)
 {
 	if (WARN_ON_ONCE(netmem_is_net_iov(netmem)))
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index 433ae9ae658b..3ddef7d7ba74 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -134,6 +134,8 @@  struct memory_provider_ops {
 	bool (*release_page)(struct page_pool *pool, struct netmem *netmem);
 };
 
+extern const struct memory_provider_ops dmabuf_devmem_ops;
+
 struct page_pool {
 	struct page_pool_params_fast p;
 
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index 173158a3dd61..231840112956 100644
--- a/net/core/page_pool.c
+++ b/net/core/page_pool.c
@@ -12,6 +12,7 @@ 
 
 #include <net/page_pool/helpers.h>
 #include <net/xdp.h>
+#include <net/netdev_rx_queue.h>
 
 #include <linux/dma-direction.h>
 #include <linux/dma-mapping.h>
@@ -20,12 +21,15 @@ 
 #include <linux/poison.h>
 #include <linux/ethtool.h>
 #include <linux/netdevice.h>
+#include <linux/genalloc.h>
+#include <net/devmem.h>
 
 #include <trace/events/page_pool.h>
 
 #include "page_pool_priv.h"
 
 DEFINE_STATIC_KEY_FALSE(page_pool_mem_providers);
+EXPORT_SYMBOL(page_pool_mem_providers);
 
 #define DEFER_TIME (msecs_to_jiffies(1000))
 #define DEFER_WARN_INTERVAL (60 * HZ)
@@ -175,6 +179,7 @@  static void page_pool_producer_unlock(struct page_pool *pool,
 static int page_pool_init(struct page_pool *pool,
 			  const struct page_pool_params *params)
 {
+	struct netdev_dmabuf_binding *binding = NULL;
 	unsigned int ring_qsize = 1024; /* Default */
 	int err;
 
@@ -237,6 +242,14 @@  static int page_pool_init(struct page_pool *pool,
 	/* Driver calling page_pool_create() also call page_pool_destroy() */
 	refcount_set(&pool->user_cnt, 1);
 
+	if (pool->p.queue)
+		binding = READ_ONCE(pool->p.queue->binding);
+
+	if (binding) {
+		pool->mp_ops = &dmabuf_devmem_ops;
+		pool->mp_priv = binding;
+	}
+
 	if (pool->mp_ops) {
 		err = pool->mp_ops->init(pool);
 		if (err) {
@@ -1055,3 +1068,83 @@  void page_pool_update_nid(struct page_pool *pool, int new_nid)
 	}
 }
 EXPORT_SYMBOL(page_pool_update_nid);
+
+/*** "Dmabuf devmem memory provider" ***/
+
+static int mp_dmabuf_devmem_init(struct page_pool *pool)
+{
+	struct netdev_dmabuf_binding *binding = pool->mp_priv;
+
+	if (!binding)
+		return -EINVAL;
+
+	if (!(pool->p.flags & PP_FLAG_DMA_MAP))
+		return -EOPNOTSUPP;
+
+	if (pool->p.flags & PP_FLAG_DMA_SYNC_DEV)
+		return -EOPNOTSUPP;
+
+	if (pool->p.order != 0)
+		return -E2BIG;
+
+	netdev_dmabuf_binding_get(binding);
+	return 0;
+}
+
+static struct netmem *mp_dmabuf_devmem_alloc_pages(struct page_pool *pool,
+						   gfp_t gfp)
+{
+	struct netdev_dmabuf_binding *binding = pool->mp_priv;
+	struct netmem *netmem;
+	struct net_iov *niov;
+	dma_addr_t dma_addr;
+
+	niov = netdev_alloc_dmabuf(binding);
+	if (!niov)
+		return NULL;
+
+	dma_addr = net_iov_dma_addr(niov);
+
+	netmem = net_iov_to_netmem(niov);
+
+	page_pool_set_pp_info(pool, netmem);
+
+	if (page_pool_set_dma_addr_netmem(netmem, dma_addr))
+		goto err_free;
+
+	pool->pages_state_hold_cnt++;
+	trace_page_pool_state_hold(pool, netmem, pool->pages_state_hold_cnt);
+	return netmem;
+
+err_free:
+	netdev_free_dmabuf(niov);
+	return NULL;
+}
+
+static void mp_dmabuf_devmem_destroy(struct page_pool *pool)
+{
+	struct netdev_dmabuf_binding *binding = pool->mp_priv;
+
+	netdev_dmabuf_binding_put(binding);
+}
+
+static bool mp_dmabuf_devmem_release_page(struct page_pool *pool,
+					  struct netmem *netmem)
+{
+	WARN_ON_ONCE(!netmem_is_net_iov(netmem));
+
+	page_pool_clear_pp_info(netmem);
+
+	netdev_free_dmabuf(netmem_to_net_iov(netmem));
+
+	/* We don't want the page pool put_page()ing our net_iovs. */
+	return false;
+}
+
+const struct memory_provider_ops dmabuf_devmem_ops = {
+	.init			= mp_dmabuf_devmem_init,
+	.destroy		= mp_dmabuf_devmem_destroy,
+	.alloc_pages		= mp_dmabuf_devmem_alloc_pages,
+	.release_page		= mp_dmabuf_devmem_release_page,
+};
+EXPORT_SYMBOL(dmabuf_devmem_ops);