page_pool: convert to use netmem

Abstract the memory type from the page_pool so we can later add support
for new memory types. Convert the page_pool to use the new netmem type
abstraction, rather than use struct page directly.

As of this patch the netmem type is a no-op abstraction: it's always a
struct page underneath. All the page pool internals are converted to
use struct netmem instead of struct page, and the page pool now exports
2 APIs:

1. The existing struct page API.
2. The new struct netmem API.

Keeping the existing API is transitional; we do not want to refactor all
the current drivers using the page pool at once.

The netmem abstraction is currently a no-op. The page_pool uses
page_to_netmem() to convert allocated pages to netmem, and uses
netmem_to_page() to convert the netmem back to pages to pass to mm APIs,

Follow up patches to this series add non-paged netmem support to the
page_pool. This change is factored out on its own to limit the code
churn to this 1 patch, for ease of code review.

Signed-off-by: Mina Almasry <almasrymina@google.com>
Reviewed-by: Pavel Begunkov <asml.silence@gmail.com>
Link: https://patch.msgid.link/20240628003253.1694510-6-almasrymina@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/linux/skbuff_ref.h

@@ -32,13 +32,13 @@ static inline void skb_frag_ref(struct sk_buff *skb, int f)
 	__skb_frag_ref(&skb_shinfo(skb)->frags[f]);
 }
 
-bool napi_pp_put_page(struct page *page);
+bool napi_pp_put_page(netmem_ref netmem);
 
 static inline void
 skb_page_unref(struct page *page, bool recycle)
 {
 #ifdef CONFIG_PAGE_POOL
-	if (recycle && napi_pp_put_page(page))
+	if (recycle && napi_pp_put_page(page_to_netmem(page)))
 		return;
 #endif
 	put_page(page);

include/net/netmem.h

@@ -38,4 +38,19 @@ static inline netmem_ref page_to_netmem(struct page *page)
 	return (__force netmem_ref)page;
 }
 
+static inline int netmem_ref_count(netmem_ref netmem)
+{
+	return page_ref_count(netmem_to_page(netmem));
+}
+
+static inline unsigned long netmem_to_pfn(netmem_ref netmem)
+{
+	return page_to_pfn(netmem_to_page(netmem));
+}
+
+static inline netmem_ref netmem_compound_head(netmem_ref netmem)
+{
+	return page_to_netmem(compound_head(netmem_to_page(netmem)));
+}
+
 #endif /* _NET_NETMEM_H */

include/net/page_pool/helpers.h

@@ -55,6 +55,8 @@
 #include <linux/dma-mapping.h>
 
 #include <net/page_pool/types.h>
+#include <net/net_debug.h>
+#include <net/netmem.h>
 
 #ifdef CONFIG_PAGE_POOL_STATS
 /* Deprecated driver-facing API, use netlink instead */
@@ -212,6 +214,11 @@ page_pool_get_dma_dir(const struct page_pool *pool)
 	return pool->p.dma_dir;
 }
 
+static inline void page_pool_fragment_netmem(netmem_ref netmem, long nr)
+{
+	atomic_long_set(&netmem_to_page(netmem)->pp_ref_count, nr);
+}
+
 /**
  * page_pool_fragment_page() - split a fresh page into fragments
  * @page:	page to split
@@ -232,11 +239,12 @@ page_pool_get_dma_dir(const struct page_pool *pool)
  */
 static inline void page_pool_fragment_page(struct page *page, long nr)
 {
-	atomic_long_set(&page->pp_ref_count, nr);
+	page_pool_fragment_netmem(page_to_netmem(page), nr);
 }
 
-static inline long page_pool_unref_page(struct page *page, long nr)
+static inline long page_pool_unref_netmem(netmem_ref netmem, long nr)
 {
+	struct page *page = netmem_to_page(netmem);
 	long ret;
 
 	/* If nr == pp_ref_count then we have cleared all remaining
@@ -279,15 +287,41 @@ static inline long page_pool_unref_page(struct page *page, long nr)
 	return ret;
 }
 
-static inline void page_pool_ref_page(struct page *page)
+static inline long page_pool_unref_page(struct page *page, long nr)
 {
-	atomic_long_inc(&page->pp_ref_count);
+	return page_pool_unref_netmem(page_to_netmem(page), nr);
 }
 
-static inline bool page_pool_is_last_ref(struct page *page)
+static inline void page_pool_ref_netmem(netmem_ref netmem)
+{
+	atomic_long_inc(&netmem_to_page(netmem)->pp_ref_count);
+}
+
+static inline void page_pool_ref_page(struct page *page)
+{
+	page_pool_ref_netmem(page_to_netmem(page));
+}
+
+static inline bool page_pool_is_last_ref(netmem_ref netmem)
 {
 	/* If page_pool_unref_page() returns 0, we were the last user */
-	return page_pool_unref_page(page, 1) == 0;
+	return page_pool_unref_netmem(netmem, 1) == 0;
+}
+
+static inline void page_pool_put_netmem(struct page_pool *pool,
+					netmem_ref netmem,
+					unsigned int dma_sync_size,
+					bool allow_direct)
+{
+	/* When page_pool isn't compiled-in, net/core/xdp.c doesn't
+	 * allow registering MEM_TYPE_PAGE_POOL, but shield linker.
+	 */
+#ifdef CONFIG_PAGE_POOL
+	if (!page_pool_is_last_ref(netmem))
+		return;
+
+	page_pool_put_unrefed_netmem(pool, netmem, dma_sync_size, allow_direct);
+#endif
 }
 
 /**
@@ -308,15 +342,15 @@ static inline void page_pool_put_page(struct page_pool *pool,
 				      unsigned int dma_sync_size,
 				      bool allow_direct)
 {
-	/* When page_pool isn't compiled-in, net/core/xdp.c doesn't
-	 * allow registering MEM_TYPE_PAGE_POOL, but shield linker.
-	 */
-#ifdef CONFIG_PAGE_POOL
-	if (!page_pool_is_last_ref(page))
-		return;
+	page_pool_put_netmem(pool, page_to_netmem(page), dma_sync_size,
+			     allow_direct);
+}
 
-	page_pool_put_unrefed_page(pool, page, dma_sync_size, allow_direct);
-#endif
+static inline void page_pool_put_full_netmem(struct page_pool *pool,
+					     netmem_ref netmem,
+					     bool allow_direct)
+{
+	page_pool_put_netmem(pool, netmem, -1, allow_direct);
 }
 
 /**
@@ -331,7 +365,7 @@ static inline void page_pool_put_page(struct page_pool *pool,
 static inline void page_pool_put_full_page(struct page_pool *pool,
 					   struct page *page, bool allow_direct)
 {
-	page_pool_put_page(pool, page, -1, allow_direct);
+	page_pool_put_netmem(pool, page_to_netmem(page), -1, allow_direct);
 }
 
 /**
@@ -365,6 +399,18 @@ static inline void page_pool_free_va(struct page_pool *pool, void *va,
 	page_pool_put_page(pool, virt_to_head_page(va), -1, allow_direct);
 }
 
+static inline dma_addr_t page_pool_get_dma_addr_netmem(netmem_ref netmem)
+{
+	struct page *page = netmem_to_page(netmem);
+
+	dma_addr_t ret = page->dma_addr;
+
+	if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA)
+		ret <<= PAGE_SHIFT;
+
+	return ret;
+}
+
 /**
  * page_pool_get_dma_addr() - Retrieve the stored DMA address.
  * @page:	page allocated from a page pool
@@ -374,16 +420,14 @@ static inline void page_pool_free_va(struct page_pool *pool, void *va,
  */
 static inline dma_addr_t page_pool_get_dma_addr(const struct page *page)
 {
-	dma_addr_t ret = page->dma_addr;
-
-	if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA)
-		ret <<= PAGE_SHIFT;
-
-	return ret;
+	return page_pool_get_dma_addr_netmem(page_to_netmem((struct page *)page));
 }
 
-static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
+static inline bool page_pool_set_dma_addr_netmem(netmem_ref netmem,
+						 dma_addr_t addr)
 {
+	struct page *page = netmem_to_page(netmem);
+
 	if (PAGE_POOL_32BIT_ARCH_WITH_64BIT_DMA) {
 		page->dma_addr = addr >> PAGE_SHIFT;
 
@@ -419,6 +463,11 @@ static inline void page_pool_dma_sync_for_cpu(const struct page_pool *pool,
 				      page_pool_get_dma_dir(pool));
 }
 
+static inline bool page_pool_set_dma_addr(struct page *page, dma_addr_t addr)
+{
+	return page_pool_set_dma_addr_netmem(page_to_netmem(page), addr);
+}
+
 static inline bool page_pool_put(struct page_pool *pool)
 {
 	return refcount_dec_and_test(&pool->user_cnt);

include/net/page_pool/types.h

@@ -6,6 +6,7 @@
 #include <linux/dma-direction.h>
 #include <linux/ptr_ring.h>
 #include <linux/types.h>
+#include <net/netmem.h>
 
 #define PP_FLAG_DMA_MAP		BIT(0) /* Should page_pool do the DMA
 					* map/unmap
@@ -40,7 +41,7 @@
 #define PP_ALLOC_CACHE_REFILL	64
 struct pp_alloc_cache {
 	u32 count;
-	struct page *cache[PP_ALLOC_CACHE_SIZE];
+	netmem_ref cache[PP_ALLOC_CACHE_SIZE];
 };
 
 /**
@@ -73,7 +74,7 @@ struct page_pool_params {
 		struct net_device *netdev;
 		unsigned int	flags;
 /* private: used by test code only */
-		void (*init_callback)(struct page *page, void *arg);
+		void (*init_callback)(netmem_ref netmem, void *arg);
 		void *init_arg;
 	);
 };
@@ -151,7 +152,7 @@ struct page_pool {
 	 */
 	__cacheline_group_begin(frag) __aligned(4 * sizeof(long));
 	long frag_users;
-	struct page *frag_page;
+	netmem_ref frag_page;
 	unsigned int frag_offset;
 	__cacheline_group_end(frag);
 
@@ -220,8 +221,12 @@ struct page_pool {
 };
 
 struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp);
+netmem_ref page_pool_alloc_netmem(struct page_pool *pool, gfp_t gfp);
 struct page *page_pool_alloc_frag(struct page_pool *pool, unsigned int *offset,
 				  unsigned int size, gfp_t gfp);
+netmem_ref page_pool_alloc_frag_netmem(struct page_pool *pool,
+				       unsigned int *offset, unsigned int size,
+				       gfp_t gfp);
 struct page_pool *page_pool_create(const struct page_pool_params *params);
 struct page_pool *page_pool_create_percpu(const struct page_pool_params *params,
 					  int cpuid);
@@ -252,6 +257,9 @@ static inline void page_pool_put_page_bulk(struct page_pool *pool, void **data,
 }
 #endif
 
+void page_pool_put_unrefed_netmem(struct page_pool *pool, netmem_ref netmem,
+				  unsigned int dma_sync_size,
+				  bool allow_direct);
 void page_pool_put_unrefed_page(struct page_pool *pool, struct page *page,
 				unsigned int dma_sync_size,
 				bool allow_direct);

include/trace/events/page_pool.h

@@ -42,51 +42,53 @@ TRACE_EVENT(page_pool_release,
 TRACE_EVENT(page_pool_state_release,
 
 	TP_PROTO(const struct page_pool *pool,
-		 const struct page *page, u32 release),
+		 netmem_ref netmem, u32 release),
 
-	TP_ARGS(pool, page, release),
+	TP_ARGS(pool, netmem, release),
 
 	TP_STRUCT__entry(
 		__field(const struct page_pool *,	pool)
-		__field(const struct page *,		page)
+		__field(unsigned long,			netmem)
 		__field(u32,				release)
 		__field(unsigned long,			pfn)
 	),
 
 	TP_fast_assign(
 		__entry->pool		= pool;
-		__entry->page		= page;
+		__entry->netmem		= (__force unsigned long)netmem;
 		__entry->release	= release;
-		__entry->pfn		= page_to_pfn(page);
+		__entry->pfn		= netmem_to_pfn(netmem);
 	),
 
-	TP_printk("page_pool=%p page=%p pfn=0x%lx release=%u",
-		  __entry->pool, __entry->page, __entry->pfn, __entry->release)
+	TP_printk("page_pool=%p netmem=%p pfn=0x%lx release=%u",
+		  __entry->pool, (void *)__entry->netmem,
+		  __entry->pfn, __entry->release)
 );
 
 TRACE_EVENT(page_pool_state_hold,
 
 	TP_PROTO(const struct page_pool *pool,
-		 const struct page *page, u32 hold),
+		 netmem_ref netmem, u32 hold),
 
-	TP_ARGS(pool, page, hold),
+	TP_ARGS(pool, netmem, hold),
 
 	TP_STRUCT__entry(
 		__field(const struct page_pool *,	pool)
-		__field(const struct page *,		page)
+		__field(unsigned long,			netmem)
 		__field(u32,				hold)
 		__field(unsigned long,			pfn)
 	),
 
 	TP_fast_assign(
 		__entry->pool	= pool;
-		__entry->page	= page;
+		__entry->netmem	= (__force unsigned long)netmem;
 		__entry->hold	= hold;
-		__entry->pfn	= page_to_pfn(page);
+		__entry->pfn	= netmem_to_pfn(netmem);
 	),
 
-	TP_printk("page_pool=%p page=%p pfn=0x%lx hold=%u",
-		  __entry->pool, __entry->page, __entry->pfn, __entry->hold)
+	TP_printk("page_pool=%p netmem=%p pfn=0x%lx hold=%u",
+		  __entry->pool, (void *)__entry->netmem,
+		  __entry->pfn, __entry->hold)
 );
 
 TRACE_EVENT(page_pool_update_nid,

net/bpf/test_run.c

@@ -127,9 +127,10 @@ struct xdp_test_data {
 #define TEST_XDP_FRAME_SIZE (PAGE_SIZE - sizeof(struct xdp_page_head))
 #define TEST_XDP_MAX_BATCH 256
 
-static void xdp_test_run_init_page(struct page *page, void *arg)
+static void xdp_test_run_init_page(netmem_ref netmem, void *arg)
 {
-	struct xdp_page_head *head = phys_to_virt(page_to_phys(page));
+	struct xdp_page_head *head =
+		phys_to_virt(page_to_phys(netmem_to_page(netmem)));
 	struct xdp_buff *new_ctx, *orig_ctx;
 	u32 headroom = XDP_PACKET_HEADROOM;
 	struct xdp_test_data *xdp = arg;

net/core/skbuff.c

@@ -1015,8 +1015,10 @@ int skb_cow_data_for_xdp(struct page_pool *pool, struct sk_buff **pskb,
 EXPORT_SYMBOL(skb_cow_data_for_xdp);
 
 #if IS_ENABLED(CONFIG_PAGE_POOL)
-bool napi_pp_put_page(struct page *page)
+bool napi_pp_put_page(netmem_ref netmem)
 {
+	struct page *page = netmem_to_page(netmem);
+
 	page = compound_head(page);
 
 	/* page->pp_magic is OR'ed with PP_SIGNATURE after the allocation
@@ -1029,7 +1031,7 @@ bool napi_pp_put_page(struct page *page)
 	if (unlikely(!is_pp_page(page)))
 		return false;
 
-	page_pool_put_full_page(page->pp, page, false);
+	page_pool_put_full_netmem(page->pp, page_to_netmem(page), false);
 
 	return true;
 }
@@ -1040,7 +1042,7 @@ static bool skb_pp_recycle(struct sk_buff *skb, void *data)
 {
 	if (!IS_ENABLED(CONFIG_PAGE_POOL) || !skb->pp_recycle)
 		return false;
-	return napi_pp_put_page(virt_to_page(data));
+	return napi_pp_put_page(page_to_netmem(virt_to_page(data)));
 }
 
 /**