diff mbox series

[net-next,v16,04/13] netdev: netdevice devmem allocator

Message ID 20240710001749.1388631-5-almasrymina@google.com
State Superseded
Headers show
Series Device Memory TCP | expand

Commit Message

Mina Almasry July 10, 2024, 12:17 a.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 <willemb@google.com>
Signed-off-by: Kaiyuan Zhang <kaiyuanz@google.com>
Signed-off-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>

---

v11:
- Fix extraneous inline directive (Paolo)

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 | 18 ++++++++++++++++++
 net/core/devmem.c    | 44 ++++++++++++++++++++++++++++++++++++++++++++
 3 files changed, 75 insertions(+)

Comments

Jakub Kicinski July 10, 2024, 4:36 p.m. UTC | #1 
On Wed, 10 Jul 2024 00:17:37 +0000 Mina Almasry wrote:
> +	net_devmem_dmabuf_binding_get(binding);

Why does every iov need to hold a ref? pp holds a ref and does its own
accounting, so it won't disappear unless all the pages are returned.
Mina Almasry July 10, 2024, 7:29 p.m. UTC | #2 
On Wed, Jul 10, 2024 at 9:37 AM Jakub Kicinski <kuba@kernel.org> wrote:
>
> On Wed, 10 Jul 2024 00:17:37 +0000 Mina Almasry wrote:
> > +     net_devmem_dmabuf_binding_get(binding);
>
> Why does every iov need to hold a ref? pp holds a ref and does its own
> accounting, so it won't disappear unless all the pages are returned.

I guess it doesn't really need to, but this is the design/approach I
went with, and I actually prefer it a bit. The design is borrowed from
how struct dev_pagemap does this, IIRC. Every page allocated from the
pgmap holds a reference to the pgmap to ensure the pgmap doesn't go
away while some page that originated from it is out in the wild, and
similarly I did so in the binding here.

We could assume that the page_pool is accounting iovs for us, but that
is not always true, right? page_pool_return_page() disconnects a
netmem from the page_pool and AFAIU the page_pool can go away while
there is such a netmem still in use in the net stack. Currently this
can't happen with iovs because I currently don't support non-pp
refcounting for iovs (so they're always recyclable), but you have a
comment on the other patch asking why that works; depending on how we
converge on that conversation, the details of how the pp refcounting
could change.

It's nice to know that the binding refcounting will work regardless of
the details of how the pp refcounting works. IMHO having the binding
rely on the pp refcounting to ensure all the iovs are freed introduces
some fragility.

Additionally IMO the net_devmem_dmabuf_binding_get/put aren't so
expensive to want to optimize out, right? The allocation is a slow
path anyway and the fast path recycles netmem.

--
Thanks,
Mina
diff mbox series

Patch

diff --git a/include/net/devmem.h b/include/net/devmem.h
index d090c3b205d8e..51b25ba193c96 100644
--- a/include/net/devmem.h
+++ b/include/net/devmem.h
@@ -68,7 +68,20 @@  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 41e96c2f94b5c..664df8325ece5 100644
--- a/include/net/netmem.h
+++ b/include/net/netmem.h
@@ -14,8 +14,26 @@ 
 
 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;
+}
+
+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 1a603d5ec9278..e0ec4e406467c 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -32,6 +32,14 @@  static void net_devmem_dmabuf_free_chunk_owner(struct gen_pool *genpool,
 	kfree(owner);
 }
 
+static dma_addr_t net_devmem_get_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);
+}
+
 void __net_devmem_dmabuf_binding_free(struct net_devmem_dmabuf_binding *binding)
 {
 	size_t size, avail;
@@ -54,6 +62,42 @@  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_devmem_get_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);