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 <willemb@xxxxxxxxxx>
Signed-off-by: Kaiyuan Zhang <kaiyuanz@xxxxxxxxxx>
Signed-off-by: Mina Almasry <almasrymina@xxxxxxxxxx>
---
v8:
- Use skb_frag_size instead of frag->bv_len to fix patch-by-patch build
error
v6:
- refactor new memory provider functions into net/core/devmem.c (Pavel)
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).
---
include/net/netmem.h | 15 ++++++
include/net/page_pool/helpers.h | 22 +++++++++
include/net/page_pool/types.h | 2 +
net/core/devmem.c | 83 +++++++++++++++++++++++++++++++++
net/core/page_pool.c | 38 +++++++--------
5 files changed, 138 insertions(+), 22 deletions(-)
diff --git a/include/net/netmem.h b/include/net/netmem.h
index 74eeaa34883e..34aa1c80c1ca 100644
--- a/include/net/netmem.h
+++ b/include/net/netmem.h
@@ -126,6 +126,21 @@ static inline struct page *netmem_to_page(netmem_ref netmem)
return (__force struct page *)netmem;
}
+static inline struct net_iov *netmem_to_net_iov(netmem_ref netmem)
+{
+ if (netmem_is_net_iov(netmem))
+ return (struct net_iov *)((__force unsigned long)netmem &
+ ~NET_IOV);
+
+ DEBUG_NET_WARN_ON_ONCE(true);
+ return NULL;
+}
+
+static inline netmem_ref net_iov_to_netmem(struct net_iov *niov)
+{
+ return (__force netmem_ref)((unsigned long)niov | NET_IOV);
+}
+
static inline netmem_ref page_to_netmem(struct page *page)
{
return (__force netmem_ref)page;
diff --git a/include/net/page_pool/helpers.h b/include/net/page_pool/helpers.h
index c6a55eddefae..eb736506c3ce 100644
--- a/include/net/page_pool/helpers.h
+++ b/include/net/page_pool/helpers.h
@@ -453,4 +453,26 @@ static inline void page_pool_nid_changed(struct page_pool *pool, int new_nid)
page_pool_update_nid(pool, new_nid);
}
+static inline void page_pool_set_pp_info(struct page_pool *pool,
+ netmem_ref netmem)
+{
+ netmem_set_pp(netmem, pool);
+ netmem_or_pp_magic(netmem, PP_SIGNATURE);
+
+ /* Ensuring all pages have been split into one fragment initially:
+ * page_pool_set_pp_info() is only called once for every page when it
+ * is allocated from the page allocator and page_pool_fragment_page()
+ * is dirtying the same cache line as the page->pp_magic above, so
+ * the overhead is negligible.
+ */
+ page_pool_fragment_netmem(netmem, 1);
+ if (pool->has_init_callback)
+ pool->slow.init_callback(netmem, pool->slow.init_arg);
+}
+
+static inline void page_pool_clear_pp_info(netmem_ref netmem)
+{
+ netmem_clear_pp_magic(netmem);
+ netmem_set_pp(netmem, NULL);
+}
#endif /* _NET_PAGE_POOL_HELPERS_H */
diff --git a/include/net/page_pool/types.h b/include/net/page_pool/types.h
index f04af1613f59..5b58c9e185a4 100644
--- a/include/net/page_pool/types.h
+++ b/include/net/page_pool/types.h
@@ -141,6 +141,8 @@ struct pp_memory_provider_params {
void *mp_priv;
};
+extern const struct memory_provider_ops dmabuf_devmem_ops;
+
struct page_pool {
struct page_pool_params_fast p;
diff --git a/net/core/devmem.c b/net/core/devmem.c
index c25ede5f6fb9..01337de7d6a4 100644
--- a/net/core/devmem.c
+++ b/net/core/devmem.c
@@ -204,6 +204,7 @@ int net_devmem_bind_dmabuf_to_queue(struct net_device *dev, u32 rxq_idx,
* the driver may read this config while it's creating its * rx-queues.
* WRITE_ONCE() here to match the READ_ONCE() in the driver.
*/
+ WRITE_ONCE(rxq->mp_params.mp_ops, &dmabuf_devmem_ops);
WRITE_ONCE(rxq->mp_params.mp_priv, binding);
err = net_devmem_restart_rx_queue(dev, rxq_idx);
@@ -340,3 +341,85 @@ int net_devmem_bind_dmabuf(struct net_device *dev, unsigned int dmabuf_fd,
return err;
}
#endif
+
+/*** "Dmabuf devmem memory provider" ***/
+
+static int mp_dmabuf_devmem_init(struct page_pool *pool)
+{
+ struct net_devmem_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;
+
+ net_devmem_dmabuf_binding_get(binding);
+ return 0;
+}
+
+static netmem_ref mp_dmabuf_devmem_alloc_pages(struct page_pool *pool,
+ gfp_t gfp)
+{
+ struct net_devmem_dmabuf_binding *binding = pool->mp_priv;
+ netmem_ref netmem;
+ struct net_iov *niov;
+ dma_addr_t dma_addr;
+
+ niov = net_devmem_alloc_dmabuf(binding);
+ if (!niov)
+ return 0;
+
+ 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:
+ net_devmem_free_dmabuf(niov);
+ return 0;
+}
+
+static void mp_dmabuf_devmem_destroy(struct page_pool *pool)
+{
+ struct net_devmem_dmabuf_binding *binding = pool->mp_priv;
+
+ net_devmem_dmabuf_binding_put(binding);
+}
+
+static bool mp_dmabuf_devmem_release_page(struct page_pool *pool,
+ netmem_ref netmem)
+{
+ WARN_ON_ONCE(!netmem_is_net_iov(netmem));
+ WARN_ON_ONCE(atomic_long_read(netmem_get_pp_ref_count_ref(netmem)) !=
+ 1);
+
+ page_pool_clear_pp_info(netmem);
+
+ net_devmem_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);
diff --git a/net/core/page_pool.c b/net/core/page_pool.c
index c7bffd08218b..a0544b680e8a 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)
@@ -178,7 +182,9 @@ static int page_pool_init(struct page_pool *pool,
const struct page_pool_params *params,
int cpuid)
{
+ const struct memory_provider_ops *mp_ops = NULL;
unsigned int ring_qsize = 1024; /* Default */
+ void *mp_priv = NULL;
int err;
memcpy(&pool->p, ¶ms->fast, sizeof(pool->p));
@@ -251,6 +257,16 @@ 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) {
+ mp_ops = READ_ONCE(pool->p.queue->mp_params.mp_ops);
+ mp_priv = READ_ONCE(pool->p.queue->mp_params.mp_priv);
+ }
+
+ if (mp_ops && mp_priv) {
+ pool->mp_ops = mp_ops;
+ pool->mp_priv = mp_priv;
+ }
+
if (pool->mp_ops) {
err = pool->mp_ops->init(pool);
if (err) {
@@ -444,28 +460,6 @@ static bool page_pool_dma_map(struct page_pool *pool, netmem_ref netmem)
return false;
}
-static void page_pool_set_pp_info(struct page_pool *pool, netmem_ref netmem)
-{
- netmem_set_pp(netmem, pool);
- netmem_or_pp_magic(netmem, PP_SIGNATURE);
-
- /* Ensuring all pages have been split into one fragment initially:
- * page_pool_set_pp_info() is only called once for every page when it
- * is allocated from the page allocator and page_pool_fragment_page()
- * is dirtying the same cache line as the page->pp_magic above, so
- * the overhead is negligible.
- */
- page_pool_fragment_netmem(netmem, 1);
- if (pool->has_init_callback)
- pool->slow.init_callback(netmem, pool->slow.init_arg);
-}
-
-static void page_pool_clear_pp_info(netmem_ref netmem)
-{
- netmem_clear_pp_magic(netmem);
- netmem_set_pp(netmem, NULL);
-}
-
static struct page *__page_pool_alloc_page_order(struct page_pool *pool,
gfp_t gfp)
{
--
2.44.0.478.gd926399ef9-goog
