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

Daniel Borkmann says:

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

The main changes are:

1) Add the ability to use unaligned chunks in the AF_XDP umem. By
   relaxing where the chunks can be placed, it allows to use an
   arbitrary buffer size and place whenever there is a free
   address in the umem. Helps more seamless DPDK AF_XDP driver
   integration. Support for i40e, ixgbe and mlx5e, from Kevin and
   Maxim.

2) Addition of a wakeup flag for AF_XDP tx and fill rings so the
   application can wake up the kernel for rx/tx processing which
   avoids busy-spinning of the latter, useful when app and driver
   is located on the same core. Support for i40e, ixgbe and mlx5e,
   from Magnus and Maxim.

3) bpftool fixes for printf()-like functions so compiler can actually
   enforce checks, bpftool build system improvements for custom output
   directories, and addition of 'bpftool map freeze' command, from Quentin.

4) Support attaching/detaching XDP programs from 'bpftool net' command,
   from Daniel.

5) Automatic xskmap cleanup when AF_XDP socket is released, and several
   barrier/{read,write}_once fixes in AF_XDP code, from Björn.

6) Relicense of bpf_helpers.h/bpf_endian.h for future libbpf
   inclusion as well as libbpf versioning improvements, from Andrii.

7) Several new BPF kselftests for verifier precision tracking, from Alexei.

8) Several BPF kselftest fixes wrt endianess to run on s390x, from Ilya.

9) And more BPF kselftest improvements all over the place, from Stanislav.

10) Add simple BPF map op cache for nfp driver to batch dumps, from Jakub.

11) AF_XDP socket umem mapping improvements for 32bit archs, from Ivan.

12) Add BPF-to-BPF call and BTF line info support for s390x JIT, from Yauheni.

13) Small optimization in arm64 JIT to spare 1 insns for BPF_MOD, from Jerin.

14) Fix an error check in bpf_tcp_gen_syncookie() helper, from Petar.

15) Various minor fixes and cleanups, from Nathan, Masahiro, Masanari,
    Peter, Wei, Yue.
====================

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

8 files changed, 187 insertions, 8 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index f9a506147c8a..5b9d22338606 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -24,6 +24,9 @@ struct seq_file;
 struct btf;
 struct btf_type;
 
+extern struct idr btf_idr;
+extern spinlock_t btf_idr_lock;
+
 /* map is generic key/value storage optionally accesible by eBPF programs */
 struct bpf_map_ops {
 	/* funcs callable from userspace (via syscall) */
@@ -647,6 +650,8 @@ void bpf_map_free_id(struct bpf_map *map, bool do_idr_lock);
 struct bpf_map *bpf_map_get_with_uref(u32 ufd);
 struct bpf_map *__bpf_map_get(struct fd f);
 struct bpf_map * __must_check bpf_map_inc(struct bpf_map *map, bool uref);
+struct bpf_map * __must_check bpf_map_inc_not_zero(struct bpf_map *map,
+						   bool uref);
 void bpf_map_put_with_uref(struct bpf_map *map);
 void bpf_map_put(struct bpf_map *map);
 int bpf_map_charge_memlock(struct bpf_map *map, u32 pages);
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 5fe99f322b1c..26a6d58ca78c 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -355,6 +355,7 @@ struct bpf_verifier_env {
 	struct bpf_verifier_stack_elem *head; /* stack of verifier states to be processed */
 	int stack_size;			/* number of states to be processed */
 	bool strict_alignment;		/* perform strict pointer alignment checks */
+	bool test_state_freq;		/* test verifier with different pruning frequency */
 	struct bpf_verifier_state *cur_state; /* current verifier state */
 	struct bpf_verifier_state_list **explored_states; /* search pruning optimization */
 	struct bpf_verifier_state_list *free_list;
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index b5d28dadf964..d7d5626002e9 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -901,6 +901,10 @@ struct netdev_bpf {
 	};
 };
 
+/* Flags for ndo_xsk_wakeup. */
+#define XDP_WAKEUP_RX (1 << 0)
+#define XDP_WAKEUP_TX (1 << 1)
+
 #ifdef CONFIG_XFRM_OFFLOAD
 struct xfrmdev_ops {
 	int	(*xdo_dev_state_add) (struct xfrm_state *x);
@@ -1227,6 +1231,12 @@ struct tlsdev_ops;
  *	that got dropped are freed/returned via xdp_return_frame().
  *	Returns negative number, means general error invoking ndo, meaning
  *	no frames were xmit'ed and core-caller will free all frames.
+ * int (*ndo_xsk_wakeup)(struct net_device *dev, u32 queue_id, u32 flags);
+ *      This function is used to wake up the softirq, ksoftirqd or kthread
+ *	responsible for sending and/or receiving packets on a specific
+ *	queue id bound to an AF_XDP socket. The flags field specifies if
+ *	only RX, only Tx, or both should be woken up using the flags
+ *	XDP_WAKEUP_RX and XDP_WAKEUP_TX.
  * struct devlink_port *(*ndo_get_devlink_port)(struct net_device *dev);
  *	Get devlink port instance associated with a given netdev.
  *	Called with a reference on the netdevice and devlink locks only,
@@ -1426,8 +1436,8 @@ struct net_device_ops {
 	int			(*ndo_xdp_xmit)(struct net_device *dev, int n,
 						struct xdp_frame **xdp,
 						u32 flags);
-	int			(*ndo_xsk_async_xmit)(struct net_device *dev,
-						      u32 queue_id);
+	int			(*ndo_xsk_wakeup)(struct net_device *dev,
+						  u32 queue_id, u32 flags);
 	struct devlink_port *	(*ndo_get_devlink_port)(struct net_device *dev);
 };
 
diff --git a/include/linux/tnum.h b/include/linux/tnum.h
index c7dc2b5902c0..c17af77f3fae 100644
--- a/include/linux/tnum.h
+++ b/include/linux/tnum.h
@@ -5,6 +5,10 @@
  * propagate the unknown bits such that the tnum result represents all the
  * possible results for possible values of the operands.
  */
+
+#ifndef _LINUX_TNUM_H
+#define _LINUX_TNUM_H
+
 #include <linux/types.h>
 
 struct tnum {
@@ -81,3 +85,5 @@ bool tnum_in(struct tnum a, struct tnum b);
 int tnum_strn(char *str, size_t size, struct tnum a);
 /* Format a tnum as tristate binary expansion */
 int tnum_sbin(char *str, size_t size, struct tnum a);
+
+#endif /* _LINUX_TNUM_H */
diff --git a/include/net/bpf_sk_storage.h b/include/net/bpf_sk_storage.h
index b9dcb02e756b..8e4f831d2e52 100644
--- a/include/net/bpf_sk_storage.h
+++ b/include/net/bpf_sk_storage.h
@@ -10,4 +10,14 @@ void bpf_sk_storage_free(struct sock *sk);
 extern const struct bpf_func_proto bpf_sk_storage_get_proto;
 extern const struct bpf_func_proto bpf_sk_storage_delete_proto;
 
+#ifdef CONFIG_BPF_SYSCALL
+int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk);
+#else
+static inline int bpf_sk_storage_clone(const struct sock *sk,
+				       struct sock *newsk)
+{
+	return 0;
+}
+#endif
+
 #endif /* _BPF_SK_STORAGE_H */
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 */
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 0e66371bea13..77c6be96d676 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -106,6 +106,7 @@ enum bpf_cmd {
 	BPF_TASK_FD_QUERY,
 	BPF_MAP_LOOKUP_AND_DELETE_ELEM,
 	BPF_MAP_FREEZE,
+	BPF_BTF_GET_NEXT_ID,
 };
 
 enum bpf_map_type {
@@ -284,6 +285,9 @@ enum bpf_attach_type {
  */
 #define BPF_F_TEST_RND_HI32	(1U << 2)
 
+/* The verifier internal test flag. Behavior is undefined */
+#define BPF_F_TEST_STATE_FREQ	(1U << 3)
+
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
  * two extensions:
  *
@@ -337,6 +341,9 @@ enum bpf_attach_type {
 #define BPF_F_RDONLY_PROG	(1U << 7)
 #define BPF_F_WRONLY_PROG	(1U << 8)
 
+/* Clone map from listener for newly accepted socket */
+#define BPF_F_CLONE		(1U << 9)
+
 /* flags for BPF_PROG_QUERY */
 #define BPF_F_QUERY_EFFECTIVE	(1U << 0)
 
@@ -576,6 +583,8 @@ union bpf_attr {
  * 		limited to five).
  *
  * 		Each time the helper is called, it appends a line to the trace.
+ * 		Lines are discarded while *\/sys/kernel/debug/tracing/trace* is
+ * 		open, use *\/sys/kernel/debug/tracing/trace_pipe* to avoid this.
  * 		The format of the trace is customizable, and the exact output
  * 		one will get depends on the options set in
  * 		*\/sys/kernel/debug/tracing/trace_options* (see also the
@@ -1014,7 +1023,7 @@ union bpf_attr {
  * 		The realm of the route for the packet associated to *skb*, or 0
  * 		if none was found.
  *
- * int bpf_perf_event_output(struct pt_reg *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
+ * int bpf_perf_event_output(struct pt_regs *ctx, struct bpf_map *map, u64 flags, void *data, u64 size)
  * 	Description
  * 		Write raw *data* blob into a special BPF perf event held by
  * 		*map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf
@@ -1076,7 +1085,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_get_stackid(struct pt_reg *ctx, struct bpf_map *map, u64 flags)
+ * int bpf_get_stackid(struct pt_regs *ctx, struct bpf_map *map, u64 flags)
  * 	Description
  * 		Walk a user or a kernel stack and return its id. To achieve
  * 		this, the helper needs *ctx*, which is a pointer to the context
@@ -1725,7 +1734,7 @@ union bpf_attr {
  * 	Return
  * 		0 on success, or a negative error in case of failure.
  *
- * int bpf_override_return(struct pt_reg *regs, u64 rc)
+ * int bpf_override_return(struct pt_regs *regs, u64 rc)
  * 	Description
  * 		Used for error injection, this helper uses kprobes to override
  * 		the return value of the probed function, and to set it to *rc*.
diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
index faaa5ca2a117..be328c59389d 100644
--- a/include/uapi/linux/if_xdp.h
+++ b/include/uapi/linux/if_xdp.h
@@ -16,6 +16,18 @@
 #define XDP_SHARED_UMEM	(1 << 0)
 #define XDP_COPY	(1 << 1) /* Force copy-mode */
 #define XDP_ZEROCOPY	(1 << 2) /* Force zero-copy mode */
+/* If this option is set, the driver might go sleep and in that case
+ * the XDP_RING_NEED_WAKEUP flag in the fill and/or Tx rings will be
+ * set. If it is set, the application need to explicitly wake up the
+ * driver with a poll() (Rx and Tx) or sendto() (Tx only). If you are
+ * running the driver and the application on the same core, you should
+ * use this option so that the kernel will yield to the user space
+ * application.
+ */
+#define XDP_USE_NEED_WAKEUP (1 << 3)
+
+/* Flags for xsk_umem_config flags */
+#define XDP_UMEM_UNALIGNED_CHUNK_FLAG (1 << 0)
 
 struct sockaddr_xdp {
 	__u16 sxdp_family;
@@ -25,10 +37,14 @@ struct sockaddr_xdp {
 	__u32 sxdp_shared_umem_fd;
 };
 
+/* XDP_RING flags */
+#define XDP_RING_NEED_WAKEUP (1 << 0)
+
 struct xdp_ring_offset {
 	__u64 producer;
 	__u64 consumer;
 	__u64 desc;
+	__u64 flags;
 };
 
 struct xdp_mmap_offsets {
@@ -53,6 +69,7 @@ struct xdp_umem_reg {
 	__u64 len; /* Length of packet data area */
 	__u32 chunk_size;
 	__u32 headroom;
+	__u32 flags;
 };
 
 struct xdp_statistics {
@@ -74,6 +91,11 @@ struct xdp_options {
 #define XDP_UMEM_PGOFF_FILL_RING	0x100000000ULL
 #define XDP_UMEM_PGOFF_COMPLETION_RING	0x180000000ULL
 
+/* Masks for unaligned chunks mode */
+#define XSK_UNALIGNED_BUF_OFFSET_SHIFT 48
+#define XSK_UNALIGNED_BUF_ADDR_MASK \
+	((1ULL << XSK_UNALIGNED_BUF_OFFSET_SHIFT) - 1)
+
 /* Rx/Tx descriptor */
 struct xdp_desc {
 	__u64 addr;