Re: [net-next v1 07/16] netdev: netdevice devmem allocator

2023-12-08 Thread Mina Almasry 
On Fri, Dec 8, 2023 at 9:56 AM David Ahern  wrote:
>
> On 12/7/23 5:52 PM, Mina Almasry wrote:
> > diff --git a/net/core/dev.c b/net/core/dev.c
> > index b8c8be5a912e..30667e4c3b95 100644
> > --- a/net/core/dev.c
> > +++ b/net/core/dev.c
> > @@ -2120,6 +2120,41 @@ static int netdev_restart_rx_queue(struct net_device 
> > *dev, int rxq_idx)
> >   return err;
> >  }
> >
> > +struct page_pool_iov *netdev_alloc_dmabuf(struct netdev_dmabuf_binding 
> > *binding)
> > +{
> > + struct dmabuf_genpool_chunk_owner *owner;
> > + struct page_pool_iov *ppiov;
> > + unsigned long dma_addr;
> > + ssize_t offset;
> > + ssize_t index;
> > +
> > + dma_addr = gen_pool_alloc_owner(binding->chunk_pool, PAGE_SIZE,
>
> Any reason not to allow allocation sizes other than PAGE_SIZE? e.g.,
> 2048 for smaller MTUs or 8192 for larger ones. It can be a property of
> page_pool and constant across allocations vs allowing different size for
> each allocation.

Only for simplicity. Supporting non-PAGE_SIZE is certainly possible,
but in my estimation it's a huge can of worms worthy of itss own
series. I find this series complicated to implement and review and
support as-is, and if reasonable I would like to punt that as a future
improvement.

At the minimum, I think the needed changes are:

1. The memory provider needs to report to the page pool the alloc size.
2. The page_pool needs to handle non-PAGE_SIZE memory regions.
3. The drivers need to handle non-PAGE_SIZE memory regions. Drivers
today handle fragged pages, but that is different because it's a
PAGE_SIZE region that is fragged. This is a non-PAGE_SIZE region in
the first place.
4. Any PAGE_SIZE assumptions in the entire net stack need to be removed.

At Google we mostly use page aligned MTUs so we're likely not that
interested in sub PAGE_SIZE allocations, but we are interested in n *
PAGE_SIZE allocations, but, I hope, in a separate followup effort.

-- 
Thanks,
Mina

Re: [net-next v1 07/16] netdev: netdevice devmem allocator

2023-12-08 Thread David Ahern 
On 12/7/23 5:52 PM, Mina Almasry wrote:
> diff --git a/net/core/dev.c b/net/core/dev.c
> index b8c8be5a912e..30667e4c3b95 100644
> --- a/net/core/dev.c
> +++ b/net/core/dev.c
> @@ -2120,6 +2120,41 @@ static int netdev_restart_rx_queue(struct net_device 
> *dev, int rxq_idx)
>   return err;
>  }
>  
> +struct page_pool_iov *netdev_alloc_dmabuf(struct netdev_dmabuf_binding 
> *binding)
> +{
> + struct dmabuf_genpool_chunk_owner *owner;
> + struct page_pool_iov *ppiov;
> + unsigned long dma_addr;
> + ssize_t offset;
> + ssize_t index;
> +
> + dma_addr = gen_pool_alloc_owner(binding->chunk_pool, PAGE_SIZE,

Any reason not to allow allocation sizes other than PAGE_SIZE? e.g.,
2048 for smaller MTUs or 8192 for larger ones. It can be a property of
page_pool and constant across allocations vs allowing different size for
each allocation.

[net-next v1 07/16] netdev: netdevice devmem allocator

2023-12-07 Thread Mina Almasry 
Implement netdev devmem allocator. The allocator takes a given struct
netdev_dmabuf_binding as input and allocates page_pool_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 page_pool_iov
struct.

page_pool_iov are refcounted and are freed back to the binding when the
refcount drops to 0.

Signed-off-by: Willem de Bruijn 
Signed-off-by: Kaiyuan Zhang 
Signed-off-by: Mina Almasry 

---

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

---
 include/net/devmem.h| 13 
 include/net/page_pool/helpers.h | 28 +
 net/core/dev.c  | 37 -
 3 files changed, 77 insertions(+), 1 deletion(-)

diff --git a/include/net/devmem.h b/include/net/devmem.h
index 29ff125f9815..29bc337c7743 100644
--- a/include/net/devmem.h
+++ b/include/net/devmem.h
@@ -48,6 +48,9 @@ struct netdev_dmabuf_binding {
 };
 
 #ifdef CONFIG_DMA_SHARED_BUFFER
+struct page_pool_iov *
+netdev_alloc_dmabuf(struct netdev_dmabuf_binding *binding);
+void netdev_free_dmabuf(struct page_pool_iov *ppiov);
 void __netdev_dmabuf_binding_free(struct netdev_dmabuf_binding *binding);
 int netdev_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
   struct netdev_dmabuf_binding **out);
@@ -55,6 +58,16 @@ void netdev_unbind_dmabuf(struct netdev_dmabuf_binding 
*binding);
 int netdev_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
struct netdev_dmabuf_binding *binding);
 #else
+static inline struct page_pool_iov *
+netdev_alloc_dmabuf(struct netdev_dmabuf_binding *binding)
+{
+   return NULL;
+}
+
+static inline void netdev_free_dmabuf(struct page_pool_iov *ppiov)
+{
+}
+
 static inline void
 __netdev_dmabuf_binding_free(struct netdev_dmabuf_binding *binding)
 {
diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h
index 7dc65774cde5..8bfc2d43efd4 100644
--- a/include/net/page_pool/helpers.h
+++ b/include/net/page_pool/helpers.h
@@ -79,6 +79,34 @@ static inline u64 *page_pool_ethtool_stats_get(u64 *data, 
void *stats)
 }
 #endif
 
+/* page_pool_iov support */
+
+static inline struct dmabuf_genpool_chunk_owner *
+page_pool_iov_owner(const struct page_pool_iov *ppiov)
+{
+   return ppiov->owner;
+}
+
+static inline unsigned int page_pool_iov_idx(const struct page_pool_iov *ppiov)
+{
+   return ppiov - page_pool_iov_owner(ppiov)->ppiovs;
+}
+
+static inline dma_addr_t
+page_pool_iov_dma_addr(const struct page_pool_iov *ppiov)
+{
+   struct dmabuf_genpool_chunk_owner *owner = page_pool_iov_owner(ppiov);
+
+   return owner->base_dma_addr +
+  ((dma_addr_t)page_pool_iov_idx(ppiov) << PAGE_SHIFT);
+}
+
+static inline struct netdev_dmabuf_binding *
+page_pool_iov_binding(const struct page_pool_iov *ppiov)
+{
+   return page_pool_iov_owner(ppiov)->binding;
+}
+
 /**
  * page_pool_dev_alloc_pages() - allocate a page.
  * @pool:  pool from which to allocate
diff --git a/net/core/dev.c b/net/core/dev.c
index b8c8be5a912e..30667e4c3b95 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -155,8 +155,8 @@
 #include 
 #include 
 #include 
-#include 
 #include 
+#include 
 
 #include "dev.h"
 #include "net-sysfs.h"
@@ -2120,6 +2120,41 @@ static int netdev_restart_rx_queue(struct net_device 
*dev, int rxq_idx)
return err;
 }
 
+struct page_pool_iov *netdev_alloc_dmabuf(struct netdev_dmabuf_binding 
*binding)
+{
+   struct dmabuf_genpool_chunk_owner *owner;
+   struct page_pool_iov *ppiov;
+   unsigned long dma_addr;
+   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;
+   ppiov = &owner->ppiovs[index];
+
+   netdev_dmabuf_binding_get(binding);
+
+   return ppiov;
+}
+
+void netdev_free_dmabuf(struct page_pool_iov *ppiov)
+{
+   struct netdev_dmabuf_binding *binding = page_pool_iov_binding(ppiov);
+   unsigned long dma_addr = page_pool_iov_dma_addr(ppiov);
+
+   refcount_set(&ppiov->refcount, 1);
+
+   if (gen_pool_has_addr(binding->chunk_pool, dma_addr, PAGE_SIZE))
+   gen_pool_free(binding->chunk_pool, dma_addr, PAGE_SIZE);
+
+   netdev_dmabuf_binding_put(binding);
+}
+
 /* Protected by rtnl_lock() */
 static DEFINE_XARRAY_FLAGS(netdev_dmabuf_bindings, XA_FLAGS_ALLOC1);
 
-- 
2.43.0.472.g3155946c3a-goog