[net-next,v9,05/14] netdev: netdevice devmem allocator

Commit Message

Mina Almasry May 10, 2024, 11:21 p.m. UTC

Implement netdev devmem allocator. The allocator takes a given struct
netdev_dmabuf_binding as input and allocates net_iov from that
binding.

The allocation simply delegates to the binding's genpool for the
allocation logic and wraps the returned memory region in a net_iov
struct.

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

---

v8:
- Rename netdev_dmabuf_binding -> net_devmem_dmabuf_binding to avoid
  patch-by-patch build error.
- Move niov->pp_magic/pp/pp_ref_counter usage to later patch to avoid
  patch-by-patch build error.

v7:
- netdev_ -> net_devmem_* naming (Yunsheng).

v6:
- Add comment on net_iov_dma_addr to explain why we don't use
  niov->dma_addr (Pavel)
- Refactor new functions into net/core/devmem.c (Pavel)

v1:
- Rename devmem -> dmabuf (David).

---
 include/net/devmem.h | 13 +++++++++++++
 include/net/netmem.h | 40 ++++++++++++++++++++++++++++++++++++++++
 net/core/devmem.c    | 36 ++++++++++++++++++++++++++++++++++++
 3 files changed, 89 insertions(+)

Comments

David Wei May 18, 2024, 12:39 a.m. UTC | #1

On 2024-05-10 16:21, Mina Almasry wrote:
> +/* This returns the absolute dma_addr_t calculated from
> + * net_iov_owner(niov)->owner->base_dma_addr, not the page_pool-owned
> + * niov->dma_addr.
> + *
> + * The absolute dma_addr_t is a dma_addr_t that is always uncompressed.
> + *
> + * The page_pool-owner niov->dma_addr is the absolute dma_addr compressed into
> + * an unsigned long. Special handling is done when the unsigned long is 32-bit
> + * but the dma_addr_t is 64-bit.
> + *
> + * In general code looking for the dma_addr_t should use net_iov_dma_addr(),
> + * while page_pool code looking for the unsigned long dma_addr which mirrors
> + * the field in struct page should use niov->dma_addr.
> + */
> +static inline dma_addr_t net_iov_dma_addr(const struct net_iov *niov)
> +{
> +	struct dmabuf_genpool_chunk_owner *owner = net_iov_owner(niov);
> +
> +	return owner->base_dma_addr +
> +	       ((dma_addr_t)net_iov_idx(niov) << PAGE_SHIFT);
> +}

This part feels like devmem TCP specific, yet the function is in
netmem.h. Please consider moving it into devmem.{h,c} which makes it
less likely that people not reading your comment will try using it.

> +
> +static inline struct net_devmem_dmabuf_binding *
> +net_iov_binding(const struct net_iov *niov)
> +{
> +	return net_iov_owner(niov)->binding;
> +}
> +
>  /* netmem */
>  
>  /**
> diff --git a/net/core/devmem.c b/net/core/devmem.c
> index d82f92d7cf9ce..1f90e23a81441 100644
> --- a/net/core/devmem.c
> +++ b/net/core/devmem.c
> @@ -54,6 +54,42 @@ void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding)
>  	kfree(binding);
>  }
>  
> +struct net_iov *
> +net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding)
> +{
> +	struct dmabuf_genpool_chunk_owner *owner;
> +	unsigned long dma_addr;
> +	struct net_iov *niov;
> +	ssize_t offset;
> +	ssize_t index;
> +
> +	dma_addr = gen_pool_alloc_owner(binding->chunk_pool, PAGE_SIZE,
> +					(void **)&owner);
> +	if (!dma_addr)
> +		return NULL;
> +
> +	offset = dma_addr - owner->base_dma_addr;
> +	index = offset / PAGE_SIZE;
> +	niov = &owner->niovs[index];
> +
> +	niov->dma_addr = 0;
> +
> +	net_devmem_dmabuf_binding_get(binding);
> +
> +	return niov;
> +}
> +
> +void net_devmem_free_dmabuf(struct net_iov *niov)
> +{
> +	struct net_devmem_dmabuf_binding *binding = net_iov_binding(niov);
> +	unsigned long dma_addr = net_iov_dma_addr(niov);
> +
> +	if (gen_pool_has_addr(binding->chunk_pool, dma_addr, PAGE_SIZE))
> +		gen_pool_free(binding->chunk_pool, dma_addr, PAGE_SIZE);
> +
> +	net_devmem_dmabuf_binding_put(binding);
> +}
> +
>  /* Protected by rtnl_lock() */
>  static DEFINE_XARRAY_FLAGS(net_devmem_dmabuf_bindings, XA_FLAGS_ALLOC1);
>

Patch

diff --git a/include/net/devmem.h b/include/net/devmem.h
index fa03bdabdffd9..cd3186f5d1fbd 100644
--- a/include/net/devmem.h
+++ b/include/net/devmem.h
@@ -68,7 +68,20 @@  int net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
 void net_devmem_unbind_dmabuf(struct net_devmem_dmabuf_binding *binding);
 int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
 				    struct net_devmem_dmabuf_binding *binding);
+struct net_iov *
+net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding);
+void net_devmem_free_dmabuf(struct net_iov *ppiov);
 #else
+static inline struct net_iov *
+net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding)
+{
+	return NULL;
+}
+
+static inline void net_devmem_free_dmabuf(struct net_iov *ppiov)
+{
+}
+
 static inline void
 __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding)
 {
diff --git a/include/net/netmem.h b/include/net/netmem.h
index 72e932a1a9489..33014370a8858 100644
--- a/include/net/netmem.h
+++ b/include/net/netmem.h
@@ -14,8 +14,48 @@ 
 
 struct net_iov {
 	struct dmabuf_genpool_chunk_owner *owner;
+	unsigned long dma_addr;
 };
 
+static inline struct dmabuf_genpool_chunk_owner *
+net_iov_owner(const struct net_iov *niov)
+{
+	return niov->owner;
+}
+
+static inline unsigned int net_iov_idx(const struct net_iov *niov)
+{
+	return niov - net_iov_owner(niov)->niovs;
+}
+
+/* This returns the absolute dma_addr_t calculated from
+ * net_iov_owner(niov)->owner->base_dma_addr, not the page_pool-owned
+ * niov->dma_addr.
+ *
+ * The absolute dma_addr_t is a dma_addr_t that is always uncompressed.
+ *
+ * The page_pool-owner niov->dma_addr is the absolute dma_addr compressed into
+ * an unsigned long. Special handling is done when the unsigned long is 32-bit
+ * but the dma_addr_t is 64-bit.
+ *
+ * In general code looking for the dma_addr_t should use net_iov_dma_addr(),
+ * while page_pool code looking for the unsigned long dma_addr which mirrors
+ * the field in struct page should use niov->dma_addr.
+ */
+static inline dma_addr_t net_iov_dma_addr(const struct net_iov *niov)
+{
+	struct dmabuf_genpool_chunk_owner *owner = net_iov_owner(niov);
+
+	return owner->base_dma_addr +
+	       ((dma_addr_t)net_iov_idx(niov) << PAGE_SHIFT);
+}
+
+static inline struct net_devmem_dmabuf_binding *
+net_iov_binding(const struct net_iov *niov)
+{
+	return net_iov_owner(niov)->binding;
+}
+
 /* netmem */
 
 /**
diff --git a/net/core/devmem.c b/net/core/devmem.c
index d82f92d7cf9ce..1f90e23a81441 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -54,6 +54,42 @@  void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding)
 	kfree(binding);
 }
 
+struct net_iov *
+net_devmem_alloc_dmabuf(struct net_devmem_dmabuf_binding *binding)
+{
+	struct dmabuf_genpool_chunk_owner *owner;
+	unsigned long dma_addr;
+	struct net_iov *niov;
+	ssize_t offset;
+	ssize_t index;
+
+	dma_addr = gen_pool_alloc_owner(binding->chunk_pool, PAGE_SIZE,
+					(void **)&owner);
+	if (!dma_addr)
+		return NULL;
+
+	offset = dma_addr - owner->base_dma_addr;
+	index = offset / PAGE_SIZE;
+	niov = &owner->niovs[index];
+
+	niov->dma_addr = 0;
+
+	net_devmem_dmabuf_binding_get(binding);
+
+	return niov;
+}
+
+void net_devmem_free_dmabuf(struct net_iov *niov)
+{
+	struct net_devmem_dmabuf_binding *binding = net_iov_binding(niov);
+	unsigned long dma_addr = net_iov_dma_addr(niov);
+
+	if (gen_pool_has_addr(binding->chunk_pool, dma_addr, PAGE_SIZE))
+		gen_pool_free(binding->chunk_pool, dma_addr, PAGE_SIZE);
+
+	net_devmem_dmabuf_binding_put(binding);
+}
+
 /* Protected by rtnl_lock() */
 static DEFINE_XARRAY_FLAGS(net_devmem_dmabuf_bindings, XA_FLAGS_ALLOC1);