Merge git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next

Pull networking updates from David Miller:

 1) Support IPV6 RA Captive Portal Identifier, from Maciej Żenczykowski.

 2) Use bio_vec in the networking instead of custom skb_frag_t, from
    Matthew Wilcox.

 3) Make use of xmit_more in r8169 driver, from Heiner Kallweit.

 4) Add devmap_hash to xdp, from Toke Høiland-Jørgensen.

 5) Support all variants of 5750X bnxt_en chips, from Michael Chan.

 6) More RTNL avoidance work in the core and mlx5 driver, from Vlad
    Buslov.

 7) Add TCP syn cookies bpf helper, from Petar Penkov.

 8) Add 'nettest' to selftests and use it, from David Ahern.

 9) Add extack support to drop_monitor, add packet alert mode and
    support for HW drops, from Ido Schimmel.

10) Add VLAN offload to stmmac, from Jose Abreu.

11) Lots of devm_platform_ioremap_resource() conversions, from
    YueHaibing.

12) Add IONIC driver, from Shannon Nelson.

13) Several kTLS cleanups, from Jakub Kicinski.

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1930 commits)
  mlxsw: spectrum_buffers: Add the ability to query the CPU port's shared buffer
  mlxsw: spectrum: Register CPU port with devlink
  mlxsw: spectrum_buffers: Prevent changing CPU port's configuration
  net: ena: fix incorrect update of intr_delay_resolution
  net: ena: fix retrieval of nonadaptive interrupt moderation intervals
  net: ena: fix update of interrupt moderation register
  net: ena: remove all old adaptive rx interrupt moderation code from ena_com
  net: ena: remove ena_restore_ethtool_params() and relevant fields
  net: ena: remove old adaptive interrupt moderation code from ena_netdev
  net: ena: remove code duplication in ena_com_update_nonadaptive_moderation_interval _*()
  net: ena: enable the interrupt_moderation in driver_supported_features
  net: ena: reimplement set/get_coalesce()
  net: ena: switch to dim algorithm for rx adaptive interrupt moderation
  net: ena: add intr_moder_rx_interval to struct ena_com_dev and use it
  net: phy: adin: implement Energy Detect Powerdown mode via phy-tunable
  ethtool: implement Energy Detect Powerdown support via phy-tunable
  xen-netfront: do not assume sk_buff_head list is empty in error handling
  s390/ctcm: Delete unnecessary checks before the macro call “dev_kfree_skb”
  net: ena: don't wake up tx queue when down
  drop_monitor: Better sanitize notified packets
  ...

1 files changed, 119 insertions, 3 deletions

diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 69796d264f06..c9398ce7960f 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -16,6 +16,13 @@
 struct net_device;
 struct xsk_queue;
 
+/* Masks for xdp_umem_page flags.
+ * The low 12-bits of the addr will be 0 since this is the page address, so we
+ * can use them for flags.
+ */
+#define XSK_NEXT_PG_CONTIG_SHIFT 0
+#define XSK_NEXT_PG_CONTIG_MASK (1ULL << XSK_NEXT_PG_CONTIG_SHIFT)
+
 struct xdp_umem_page {
 	void *addr;
 	dma_addr_t dma;
@@ -27,6 +34,13 @@ struct xdp_umem_fq_reuse {
 	u64 handles[];
 };
 
+/* Flags for the umem flags field.
+ *
+ * The NEED_WAKEUP flag is 1 due to the reuse of the flags field for public
+ * flags. See inlude/uapi/include/linux/if_xdp.h.
+ */
+#define XDP_UMEM_USES_NEED_WAKEUP (1 << 1)
+
 struct xdp_umem {
 	struct xsk_queue *fq;
 	struct xsk_queue *cq;
@@ -41,15 +55,27 @@ struct xdp_umem {
 	struct work_struct work;
 	struct page **pgs;
 	u32 npgs;
+	u16 queue_id;
+	u8 need_wakeup;
+	u8 flags;
 	int id;
 	struct net_device *dev;
 	struct xdp_umem_fq_reuse *fq_reuse;
-	u16 queue_id;
 	bool zc;
 	spinlock_t xsk_list_lock;
 	struct list_head xsk_list;
 };
 
+/* Nodes are linked in the struct xdp_sock map_list field, and used to
+ * track which maps a certain socket reside in.
+ */
+struct xsk_map;
+struct xsk_map_node {
+	struct list_head node;
+	struct xsk_map *map;
+	struct xdp_sock **map_entry;
+};
+
 struct xdp_sock {
 	/* struct sock must be the first member of struct xdp_sock */
 	struct sock sk;
@@ -75,6 +101,9 @@ struct xdp_sock {
 	/* Protects generic receive. */
 	spinlock_t rx_lock;
 	u64 rx_dropped;
+	struct list_head map_list;
+	/* Protects map_list */
+	spinlock_t map_list_lock;
 };
 
 struct xdp_buff;
@@ -95,15 +124,47 @@ struct xdp_umem_fq_reuse *xsk_reuseq_swap(struct xdp_umem *umem,
 					  struct xdp_umem_fq_reuse *newq);
 void xsk_reuseq_free(struct xdp_umem_fq_reuse *rq);
 struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, u16 queue_id);
+void xsk_set_rx_need_wakeup(struct xdp_umem *umem);
+void xsk_set_tx_need_wakeup(struct xdp_umem *umem);
+void xsk_clear_rx_need_wakeup(struct xdp_umem *umem);
+void xsk_clear_tx_need_wakeup(struct xdp_umem *umem);
+bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem);
+
+void xsk_map_try_sock_delete(struct xsk_map *map, struct xdp_sock *xs,
+			     struct xdp_sock **map_entry);
+int xsk_map_inc(struct xsk_map *map);
+void xsk_map_put(struct xsk_map *map);
+
+static inline u64 xsk_umem_extract_addr(u64 addr)
+{
+	return addr & XSK_UNALIGNED_BUF_ADDR_MASK;
+}
+
+static inline u64 xsk_umem_extract_offset(u64 addr)
+{
+	return addr >> XSK_UNALIGNED_BUF_OFFSET_SHIFT;
+}
+
+static inline u64 xsk_umem_add_offset_to_addr(u64 addr)
+{
+	return xsk_umem_extract_addr(addr) + xsk_umem_extract_offset(addr);
+}
 
 static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr)
 {
-	return umem->pages[addr >> PAGE_SHIFT].addr + (addr & (PAGE_SIZE - 1));
+	unsigned long page_addr;
+
+	addr = xsk_umem_add_offset_to_addr(addr);
+	page_addr = (unsigned long)umem->pages[addr >> PAGE_SHIFT].addr;
+
+	return (char *)(page_addr & PAGE_MASK) + (addr & ~PAGE_MASK);
 }
 
 static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr)
 {
-	return umem->pages[addr >> PAGE_SHIFT].dma + (addr & (PAGE_SIZE - 1));
+	addr = xsk_umem_add_offset_to_addr(addr);
+
+	return umem->pages[addr >> PAGE_SHIFT].dma + (addr & ~PAGE_MASK);
 }
 
 /* Reuse-queue aware version of FILL queue helpers */
@@ -144,6 +205,19 @@ static inline void xsk_umem_fq_reuse(struct xdp_umem *umem, u64 addr)
 
 	rq->handles[rq->length++] = addr;
 }
+
+/* Handle the offset appropriately depending on aligned or unaligned mode.
+ * For unaligned mode, we store the offset in the upper 16-bits of the address.
+ * For aligned mode, we simply add the offset to the address.
+ */
+static inline u64 xsk_umem_adjust_offset(struct xdp_umem *umem, u64 address,
+					 u64 offset)
+{
+	if (umem->flags & XDP_UMEM_UNALIGNED_CHUNK_FLAG)
+		return address + (offset << XSK_UNALIGNED_BUF_OFFSET_SHIFT);
+	else
+		return address + offset;
+}
 #else
 static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 {
@@ -213,6 +287,21 @@ static inline struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev,
 	return NULL;
 }
 
+static inline u64 xsk_umem_extract_addr(u64 addr)
+{
+	return 0;
+}
+
+static inline u64 xsk_umem_extract_offset(u64 addr)
+{
+	return 0;
+}
+
+static inline u64 xsk_umem_add_offset_to_addr(u64 addr)
+{
+	return 0;
+}
+
 static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr)
 {
 	return NULL;
@@ -241,6 +330,33 @@ static inline void xsk_umem_fq_reuse(struct xdp_umem *umem, u64 addr)
 {
 }
 
+static inline void xsk_set_rx_need_wakeup(struct xdp_umem *umem)
+{
+}
+
+static inline void xsk_set_tx_need_wakeup(struct xdp_umem *umem)
+{
+}
+
+static inline void xsk_clear_rx_need_wakeup(struct xdp_umem *umem)
+{
+}
+
+static inline void xsk_clear_tx_need_wakeup(struct xdp_umem *umem)
+{
+}
+
+static inline bool xsk_umem_uses_need_wakeup(struct xdp_umem *umem)
+{
+	return false;
+}
+
+static inline u64 xsk_umem_adjust_offset(struct xdp_umem *umem, u64 handle,
+					 u64 offset)
+{
+	return 0;
+}
+
 #endif /* CONFIG_XDP_SOCKETS */
 
 #endif /* _LINUX_XDP_SOCK_H */