1 files changed, 210 insertions, 42 deletions

diff --git a/include/net/netmem.h b/include/net/netmem.h
index 1b58faa4f20f..bccacd21b6c3 100644
--- a/include/net/netmem.h
+++ b/include/net/netmem.h
@@ -8,9 +8,54 @@
 #ifndef _NET_NETMEM_H
 #define _NET_NETMEM_H
 
+#include <linux/dma-mapping.h>
 #include <linux/mm.h>
 #include <net/net_debug.h>
 
+/* These fields in struct page are used by the page_pool and net stack:
+ *
+ *        struct {
+ *                unsigned long pp_magic;
+ *                struct page_pool *pp;
+ *                unsigned long _pp_mapping_pad;
+ *                unsigned long dma_addr;
+ *                atomic_long_t pp_ref_count;
+ *        };
+ *
+ * We mirror the page_pool fields here so the page_pool can access these
+ * fields without worrying whether the underlying fields belong to a
+ * page or netmem_desc.
+ *
+ * CAUTION: Do not update the fields in netmem_desc without also
+ * updating the anonymous aliasing union in struct net_iov.
+ */
+struct netmem_desc {
+	unsigned long _flags;
+	unsigned long pp_magic;
+	struct page_pool *pp;
+	unsigned long _pp_mapping_pad;
+	unsigned long dma_addr;
+	atomic_long_t pp_ref_count;
+};
+
+#define NETMEM_DESC_ASSERT_OFFSET(pg, desc)        \
+	static_assert(offsetof(struct page, pg) == \
+		      offsetof(struct netmem_desc, desc))
+NETMEM_DESC_ASSERT_OFFSET(flags, _flags);
+NETMEM_DESC_ASSERT_OFFSET(pp_magic, pp_magic);
+NETMEM_DESC_ASSERT_OFFSET(pp, pp);
+NETMEM_DESC_ASSERT_OFFSET(_pp_mapping_pad, _pp_mapping_pad);
+NETMEM_DESC_ASSERT_OFFSET(dma_addr, dma_addr);
+NETMEM_DESC_ASSERT_OFFSET(pp_ref_count, pp_ref_count);
+#undef NETMEM_DESC_ASSERT_OFFSET
+
+/*
+ * Since struct netmem_desc uses the space in struct page, the size
+ * should be checked, until struct netmem_desc has its own instance from
+ * slab, to avoid conflicting with other members within struct page.
+ */
+static_assert(sizeof(struct netmem_desc) <= offsetof(struct page, _refcount));
+
 /* net_iov */
 
 DECLARE_STATIC_KEY_FALSE(page_pool_mem_providers);
@@ -20,39 +65,67 @@ DECLARE_STATIC_KEY_FALSE(page_pool_mem_providers);
  */
 #define NET_IOV 0x01UL
 
-struct net_iov {
-	unsigned long __unused_padding;
-	unsigned long pp_magic;
-	struct page_pool *pp;
-	struct dmabuf_genpool_chunk_owner *owner;
-	unsigned long dma_addr;
-	atomic_long_t pp_ref_count;
+enum net_iov_type {
+	NET_IOV_DMABUF,
+	NET_IOV_IOURING,
 };
 
-/* These fields in struct page are used by the page_pool and net stack:
+/* A memory descriptor representing abstract networking I/O vectors,
+ * generally for non-pages memory that doesn't have its corresponding
+ * struct page and needs to be explicitly allocated through slab.
  *
- *        struct {
- *                unsigned long pp_magic;
- *                struct page_pool *pp;
- *                unsigned long _pp_mapping_pad;
- *                unsigned long dma_addr;
- *                atomic_long_t pp_ref_count;
- *        };
+ * net_iovs are allocated and used by networking code, and the size of
+ * the chunk is PAGE_SIZE.
  *
- * We mirror the page_pool fields here so the page_pool can access these fields
- * without worrying whether the underlying fields belong to a page or net_iov.
+ * This memory can be any form of non-struct paged memory.  Examples
+ * include imported dmabuf memory and imported io_uring memory.  See
+ * net_iov_type for all the supported types.
  *
- * The non-net stack fields of struct page are private to the mm stack and must
- * never be mirrored to net_iov.
+ * @pp_magic:	pp field, similar to the one in struct page/struct
+ *		netmem_desc.
+ * @pp:		the pp this net_iov belongs to, if any.
+ * @dma_addr:	the dma addrs of the net_iov. Needed for the network
+ *		card to send/receive this net_iov.
+ * @pp_ref_count: the pp ref count of this net_iov, exactly the same
+ *		usage as struct page/struct netmem_desc.
+ * @owner:	the net_iov_area this net_iov belongs to, if any.
+ * @type:	the type of the memory.  Different types of net_iovs are
+ *		supported.
  */
-#define NET_IOV_ASSERT_OFFSET(pg, iov)             \
-	static_assert(offsetof(struct page, pg) == \
-		      offsetof(struct net_iov, iov))
-NET_IOV_ASSERT_OFFSET(pp_magic, pp_magic);
-NET_IOV_ASSERT_OFFSET(pp, pp);
-NET_IOV_ASSERT_OFFSET(dma_addr, dma_addr);
-NET_IOV_ASSERT_OFFSET(pp_ref_count, pp_ref_count);
-#undef NET_IOV_ASSERT_OFFSET
+struct net_iov {
+	struct netmem_desc desc;
+	enum net_iov_type type;
+	struct net_iov_area *owner;
+};
+
+struct net_iov_area {
+	/* Array of net_iovs for this area. */
+	struct net_iov *niovs;
+	size_t num_niovs;
+
+	/* Offset into the dma-buf where this chunk starts.  */
+	unsigned long base_virtual;
+};
+
+static inline struct net_iov_area *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;
+}
+
+/* Initialize a niov: stamp the owning area, the memory provider type.
+ */
+static inline void net_iov_init(struct net_iov *niov,
+				struct net_iov_area *owner,
+				enum net_iov_type type)
+{
+	niov->owner = owner;
+	niov->type = type;
+}
 
 /* netmem */
 
@@ -60,8 +133,7 @@ NET_IOV_ASSERT_OFFSET(pp_ref_count, pp_ref_count);
  * typedef netmem_ref - a nonexistent type marking a reference to generic
  * network memory.
  *
- * A netmem_ref currently is always a reference to a struct page. This
- * abstraction is introduced so support for new memory types can be added.
+ * A netmem_ref can be a struct page* or a struct net_iov* underneath.
  *
  * Use the supplied helpers to obtain the underlying memory pointer and fields.
  */
@@ -88,9 +160,6 @@ static inline struct page *__netmem_to_page(netmem_ref netmem)
 	return (__force struct page *)netmem;
 }
 
-/* This conversion fails (returns NULL) if the netmem_ref is not struct page
- * backed.
- */
 static inline struct page *netmem_to_page(netmem_ref netmem)
 {
 	if (WARN_ON_ONCE(netmem_is_net_iov(netmem)))
@@ -114,10 +183,9 @@ 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;
-}
+#define page_to_netmem(p)	(_Generic((p),			\
+	const struct page * :	(__force const netmem_ref)(p),	\
+	struct page * :		(__force netmem_ref)(p)))
 
 /**
  * virt_to_netmem - convert virtual memory pointer to a netmem reference
@@ -149,9 +217,59 @@ static inline unsigned long netmem_pfn_trace(netmem_ref netmem)
 	return page_to_pfn(netmem_to_page(netmem));
 }
 
-static inline struct net_iov *__netmem_clear_lsb(netmem_ref netmem)
+/* XXX: How to extract netmem_desc from page must be changed, once
+ * netmem_desc no longer overlays on page and will be allocated through
+ * slab.
+ */
+#define __pp_page_to_nmdesc(p)	(_Generic((p),				\
+	const struct page * :	(const struct netmem_desc *)(p),	\
+	struct page * :		(struct netmem_desc *)(p)))
+
+/* CAUTION: Check if the page is a pp page before calling this helper or
+ * know it's a pp page.
+ */
+#define pp_page_to_nmdesc(p)						\
+({									\
+	DEBUG_NET_WARN_ON_ONCE(!page_pool_page_is_pp(p));		\
+	__pp_page_to_nmdesc(p);						\
+})
+
+/**
+ * __netmem_to_nmdesc - unsafely get pointer to the &netmem_desc backing
+ * @netmem
+ * @netmem: netmem reference to convert
+ *
+ * Unsafe version that can be used only when @netmem is always backed by
+ * system memory, performs faster and generates smaller object code (no
+ * check for the LSB, no WARN). When @netmem points to IOV, provokes
+ * undefined behaviour.
+ *
+ * Return: pointer to the &netmem_desc (garbage if @netmem is not backed
+ * by system memory).
+ */
+static inline struct netmem_desc *__netmem_to_nmdesc(netmem_ref netmem)
 {
-	return (struct net_iov *)((__force unsigned long)netmem & ~NET_IOV);
+	return (__force struct netmem_desc *)netmem;
+}
+
+/* netmem_to_nmdesc - convert netmem_ref to struct netmem_desc * for
+ * access to common fields.
+ * @netmem: netmem reference to get netmem_desc.
+ *
+ * All the sub types of netmem_ref (netmem_desc, net_iov) have the same
+ * pp, pp_magic, dma_addr, and pp_ref_count fields via netmem_desc.
+ *
+ * Return: the pointer to struct netmem_desc * regardless of its
+ * underlying type.
+ */
+static inline struct netmem_desc *netmem_to_nmdesc(netmem_ref netmem)
+{
+	void *p = (void *)((__force unsigned long)netmem & ~NET_IOV);
+
+	if (netmem_is_net_iov(netmem))
+		return &((struct net_iov *)p)->desc;
+
+	return __pp_page_to_nmdesc((struct page *)p);
 }
 
 /**
@@ -167,17 +285,17 @@ static inline struct net_iov *__netmem_clear_lsb(netmem_ref netmem)
  */
 static inline struct page_pool *__netmem_get_pp(netmem_ref netmem)
 {
-	return __netmem_to_page(netmem)->pp;
+	return __netmem_to_nmdesc(netmem)->pp;
 }
 
 static inline struct page_pool *netmem_get_pp(netmem_ref netmem)
 {
-	return __netmem_clear_lsb(netmem)->pp;
+	return netmem_to_nmdesc(netmem)->pp;
 }
 
 static inline atomic_long_t *netmem_get_pp_ref_count_ref(netmem_ref netmem)
 {
-	return &__netmem_clear_lsb(netmem)->pp_ref_count;
+	return &netmem_to_nmdesc(netmem)->pp_ref_count;
 }
 
 static inline bool netmem_is_pref_nid(netmem_ref netmem, int pref_nid)
@@ -242,7 +360,57 @@ static inline bool netmem_is_pfmemalloc(netmem_ref netmem)
 
 static inline unsigned long netmem_get_dma_addr(netmem_ref netmem)
 {
-	return __netmem_clear_lsb(netmem)->dma_addr;
+	return netmem_to_nmdesc(netmem)->dma_addr;
+}
+
+#if defined(CONFIG_NET_DEVMEM)
+static inline bool net_is_devmem_iov(const struct net_iov *niov)
+{
+	return niov->type == NET_IOV_DMABUF;
+}
+#else
+static inline bool net_is_devmem_iov(const struct net_iov *niov)
+{
+	return false;
+}
+#endif
+
+void __get_netmem(netmem_ref netmem);
+void __put_netmem(netmem_ref netmem);
+
+static __always_inline void get_netmem(netmem_ref netmem)
+{
+	if (netmem_is_net_iov(netmem))
+		__get_netmem(netmem);
+	else
+		get_page(netmem_to_page(netmem));
+}
+
+static __always_inline void put_netmem(netmem_ref netmem)
+{
+	if (netmem_is_net_iov(netmem))
+		__put_netmem(netmem);
+	else
+		put_page(netmem_to_page(netmem));
+}
+
+#define netmem_dma_unmap_addr_set(NETMEM, PTR, ADDR_NAME, VAL)   \
+	do {                                                     \
+		if (!netmem_is_net_iov(NETMEM))                  \
+			dma_unmap_addr_set(PTR, ADDR_NAME, VAL); \
+		else                                             \
+			dma_unmap_addr_set(PTR, ADDR_NAME, 0);   \
+	} while (0)
+
+static inline void netmem_dma_unmap_page_attrs(struct device *dev,
+					       dma_addr_t addr, size_t size,
+					       enum dma_data_direction dir,
+					       unsigned long attrs)
+{
+	if (!addr)
+		return;
+
+	dma_unmap_page_attrs(dev, addr, size, dir, attrs);
 }
 
 #endif /* _NET_NETMEM_H */