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

Daniel Borkmann says:

====================
pull-request: bpf-next 2018-09-01

The following pull-request contains BPF updates for your *net-next* tree.

The main changes are:

1) Add AF_XDP zero-copy support for i40e driver (!), from Björn and Magnus.

2) BPF verifier improvements by giving each register its own liveness
   chain which allows to simplify and getting rid of skip_callee() logic,
   from Edward.

3) Add bpf fs pretty print support for percpu arraymap, percpu hashmap
   and percpu lru hashmap. Also add generic percpu formatted print on
   bpftool so the same can be dumped there, from Yonghong.

4) Add bpf_{set,get}sockopt() helper support for TCP_SAVE_SYN and
   TCP_SAVED_SYN options to allow reflection of tos/tclass from received
   SYN packet, from Nikita.

5) Misc improvements to the BPF sockmap test cases in terms of cgroup v2
   interaction and removal of incorrect shutdown() calls, from John.

6) Few cleanups in xdp_umem_assign_dev() and xdpsock samples, from Prashant.
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 78 insertions, 13 deletions

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 38b04f559ad3..b42b60a83e19 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -41,6 +41,7 @@ enum bpf_reg_liveness {
 };
 
 struct bpf_reg_state {
+	/* Ordering of fields matters.  See states_equal() */
 	enum bpf_reg_type type;
 	union {
 		/* valid when type == PTR_TO_PACKET */
@@ -59,7 +60,6 @@ struct bpf_reg_state {
 	 * came from, when one is tested for != NULL.
 	 */
 	u32 id;
-	/* Ordering of fields matters.  See states_equal() */
 	/* For scalar types (SCALAR_VALUE), this represents our knowledge of
 	 * the actual value.
 	 * For pointer types, this represents the variable part of the offset
@@ -76,15 +76,15 @@ struct bpf_reg_state {
 	s64 smax_value; /* maximum possible (s64)value */
 	u64 umin_value; /* minimum possible (u64)value */
 	u64 umax_value; /* maximum possible (u64)value */
+	/* parentage chain for liveness checking */
+	struct bpf_reg_state *parent;
 	/* Inside the callee two registers can be both PTR_TO_STACK like
 	 * R1=fp-8 and R2=fp-8, but one of them points to this function stack
 	 * while another to the caller's stack. To differentiate them 'frameno'
 	 * is used which is an index in bpf_verifier_state->frame[] array
 	 * pointing to bpf_func_state.
-	 * This field must be second to last, for states_equal() reasons.
 	 */
 	u32 frameno;
-	/* This field must be last, for states_equal() reasons. */
 	enum bpf_reg_liveness live;
 };
 
@@ -107,7 +107,6 @@ struct bpf_stack_state {
  */
 struct bpf_func_state {
 	struct bpf_reg_state regs[MAX_BPF_REG];
-	struct bpf_verifier_state *parent;
 	/* index of call instruction that called into this func */
 	int callsite;
 	/* stack frame number of this function state from pov of
@@ -129,7 +128,6 @@ struct bpf_func_state {
 struct bpf_verifier_state {
 	/* call stack tracking */
 	struct bpf_func_state *frame[MAX_CALL_FRAMES];
-	struct bpf_verifier_state *parent;
 	u32 curframe;
 };
 
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ca5ab98053c8..4271f6b4e419 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -535,6 +535,32 @@ static inline void napi_synchronize(const struct napi_struct *n)
 		barrier();
 }
 
+/**
+ *	napi_if_scheduled_mark_missed - if napi is running, set the
+ *	NAPIF_STATE_MISSED
+ *	@n: NAPI context
+ *
+ * If napi is running, set the NAPIF_STATE_MISSED, and return true if
+ * NAPI is scheduled.
+ **/
+static inline bool napi_if_scheduled_mark_missed(struct napi_struct *n)
+{
+	unsigned long val, new;
+
+	do {
+		val = READ_ONCE(n->state);
+		if (val & NAPIF_STATE_DISABLE)
+			return true;
+
+		if (!(val & NAPIF_STATE_SCHED))
+			return false;
+
+		new = val | NAPIF_STATE_MISSED;
+	} while (cmpxchg(&n->state, val, new) != val);
+
+	return true;
+}
+
 enum netdev_queue_state_t {
 	__QUEUE_STATE_DRV_XOFF,
 	__QUEUE_STATE_STACK_XOFF,
diff --git a/include/net/xdp.h b/include/net/xdp.h
index 76b95256c266..0f25b3675c5c 100644
--- a/include/net/xdp.h
+++ b/include/net/xdp.h
@@ -91,6 +91,8 @@ static inline void xdp_scrub_frame(struct xdp_frame *frame)
 	frame->dev_rx = NULL;
 }
 
+struct xdp_frame *xdp_convert_zc_to_xdp_frame(struct xdp_buff *xdp);
+
 /* Convert xdp_buff to xdp_frame */
 static inline
 struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp)
@@ -99,9 +101,8 @@ struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp)
 	int metasize;
 	int headroom;
 
-	/* TODO: implement clone, copy, use "native" MEM_TYPE */
 	if (xdp->rxq->mem.type == MEM_TYPE_ZERO_COPY)
-		return NULL;
+		return xdp_convert_zc_to_xdp_frame(xdp);
 
 	/* Assure headroom is available for storing info */
 	headroom = xdp->data - xdp->data_hard_start;
@@ -135,6 +136,7 @@ void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq);
 bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq);
 int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq,
 			       enum xdp_mem_type type, void *allocator);
+void xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq);
 
 /* Drivers not supporting XDP metadata can use this helper, which
  * rejects any room expansion for metadata as a result.
diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h
index 7161856bcf9c..932ca0dad6f3 100644
--- a/include/net/xdp_sock.h
+++ b/include/net/xdp_sock.h
@@ -16,11 +16,6 @@
 struct net_device;
 struct xsk_queue;
 
-struct xdp_umem_props {
-	u64 chunk_mask;
-	u64 size;
-};
-
 struct xdp_umem_page {
 	void *addr;
 	dma_addr_t dma;
@@ -30,7 +25,8 @@ struct xdp_umem {
 	struct xsk_queue *fq;
 	struct xsk_queue *cq;
 	struct xdp_umem_page *pages;
-	struct xdp_umem_props props;
+	u64 chunk_mask;
+	u64 size;
 	u32 headroom;
 	u32 chunk_size_nohr;
 	struct user_struct *user;
@@ -79,6 +75,16 @@ void xsk_umem_discard_addr(struct xdp_umem *umem);
 void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries);
 bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma, u32 *len);
 void xsk_umem_consume_tx_done(struct xdp_umem *umem);
+
+static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr)
+{
+	return umem->pages[addr >> PAGE_SHIFT].addr + (addr & (PAGE_SIZE - 1));
+}
+
+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));
+}
 #else
 static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 {
@@ -98,6 +104,39 @@ static inline bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs)
 {
 	return false;
 }
+
+static inline u64 *xsk_umem_peek_addr(struct xdp_umem *umem, u64 *addr)
+{
+	return NULL;
+}
+
+static inline void xsk_umem_discard_addr(struct xdp_umem *umem)
+{
+}
+
+static inline void xsk_umem_complete_tx(struct xdp_umem *umem, u32 nb_entries)
+{
+}
+
+static inline bool xsk_umem_consume_tx(struct xdp_umem *umem, dma_addr_t *dma,
+				       u32 *len)
+{
+	return false;
+}
+
+static inline void xsk_umem_consume_tx_done(struct xdp_umem *umem)
+{
+}
+
+static inline char *xdp_umem_get_data(struct xdp_umem *umem, u64 addr)
+{
+	return NULL;
+}
+
+static inline dma_addr_t xdp_umem_get_dma(struct xdp_umem *umem, u64 addr)
+{
+	return 0;
+}
 #endif /* CONFIG_XDP_SOCKETS */
 
 #endif /* _LINUX_XDP_SOCK_H */