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

Pull networking updates from David Miller:
 "Here is what we have this merge window:

   1) Support SW steering for mlx5 Connect-X6Dx, from Yevgeny Kliteynik.

   2) Add RSS multi group support to octeontx2-pf driver, from Geetha
      Sowjanya.

   3) Add support for KS8851 PHY. From Marek Vasut.

   4) Add support for GarfieldPeak bluetooth controller from Kiran K.

   5) Add support for half-duplex tcan4x5x can controllers.

   6) Add batch skb rx processing to bcrm63xx_enet, from Sieng Piaw
      Liew.

   7) Rework RX port offload infrastructure, particularly wrt, UDP
      tunneling, from Jakub Kicinski.

   8) Add BCM72116 PHY support, from Florian Fainelli.

   9) Remove Dsa specific notifiers, they are unnecessary. From Vladimir
      Oltean.

  10) Add support for picosecond rx delay in dwmac-meson8b chips. From
      Martin Blumenstingl.

  11) Support TSO on xfrm interfaces from Eyal Birger.

  12) Add support for MP_PRIO to mptcp stack, from Geliang Tang.

  13) Support BCM4908 integrated switch, from Rafał Miłecki.

  14) Support for directly accessing kernel module variables via module
      BTF info, from Andrii Naryiko.

  15) Add DASH (esktop and mobile Architecture for System Hardware)
      support to r8169 driver, from Heiner Kallweit.

  16) Add rx vlan filtering to dpaa2-eth, from Ionut-robert Aron.

  17) Add support for 100 base0x SFP devices, from Bjarni Jonasson.

  18) Support link aggregation in DSA, from Tobias Waldekranz.

  19) Support for bitwidse atomics in bpf, from Brendan Jackman.

  20) SmartEEE support in at803x driver, from Russell King.

  21) Add support for flow based tunneling to GTP, from Pravin B Shelar.

  22) Allow arbitrary number of interconnrcts in ipa, from Alex Elder.

  23) TLS RX offload for bonding, from Tariq Toukan.

  24) RX decap offklload support in mac80211, from Felix Fietkou.

  25) devlink health saupport in octeontx2-af, from George Cherian.

  26) Add TTL attr to SCM_TIMESTAMP_OPT_STATS, from Yousuk Seung

  27) Delegated actionss support in mptcp, from Paolo Abeni.

  28) Support receive timestamping when doin zerocopy tcp receive. From
      Arjun Ray.

  29) HTB offload support for mlx5, from Maxim Mikityanskiy.

  30) UDP GRO forwarding, from Maxim Mikityanskiy.

  31) TAPRIO offloading in dsa hellcreek driver, from Kurt Kanzenbach.

  32) Weighted random twos choice algorithm for ipvs, from Darby Payne.

  33) Fix netdev registration deadlock, from Johannes Berg.

  34) Various conversions to new tasklet api, from EmilRenner Berthing.

  35) Bulk skb allocations in veth, from Lorenzo Bianconi.

  36) New ethtool interface for lane setting, from Danielle Ratson.

  37) Offload failiure notifications for routes, from Amit Cohen.

  38) BCM4908 support, from Rafał Miłecki.

  39) Support several new iwlwifi chips, from Ihab Zhaika.

  40) Flow drector support for ipv6 in i40e, from Przemyslaw Patynowski.

  41) Support for mhi prrotocols, from Loic Poulain.

  42) Optimize bpf program stats.

  43) Implement RFC6056, for better port randomization, from Eric
      Dumazet.

  44) hsr tag offloading support from George McCollister.

  45) Netpoll support in qede, from Bhaskar Upadhaya.

  46) 2005/400g speed support in bonding 3ad mode, from Nikolay
      Aleksandrov.

  47) Netlink event support in mptcp, from Florian Westphal.

  48) Better skbuff caching, from Alexander Lobakin.

  49) MRP (Media Redundancy Protocol) offloading in DSA and a few
      drivers, from Horatiu Vultur.

  50) mqprio saupport in mvneta, from Maxime Chevallier.

  51) Remove of_phy_attach, no longer needed, from Florian Fainelli"

* git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1766 commits)
  octeontx2-pf: Fix otx2_get_fecparam()
  cteontx2-pf: cn10k: Prevent harmless double shift bugs
  net: stmmac: Add PCI bus info to ethtool driver query output
  ptp: ptp_clockmatrix: clean-up - parenthesis around a == b are unnecessary
  ptp: ptp_clockmatrix: Simplify code - remove unnecessary `err` variable.
  ptp: ptp_clockmatrix: Coding style - tighten vertical spacing.
  ptp: ptp_clockmatrix: Clean-up dev_*() messages.
  ptp: ptp_clockmatrix: Remove unused header declarations.
  ptp: ptp_clockmatrix: Add alignment of 1 PPS to idtcm_perout_enable.
  ptp: ptp_clockmatrix: Add wait_for_sys_apll_dpll_lock.
  net: stmmac: dwmac-sun8i: Add a shutdown callback
  net: stmmac: dwmac-sun8i: Minor probe function cleanup
  net: stmmac: dwmac-sun8i: Use reset_control_reset
  net: stmmac: dwmac-sun8i: Remove unnecessary PHY power check
  net: stmmac: dwmac-sun8i: Return void from PHY unpower
  r8169: use macro pm_ptr
  net: mdio: Remove of_phy_attach()
  net: mscc: ocelot: select PACKING in the Kconfig
  net: re-solve some conflicts after net -> net-next merge
  net: dsa: tag_rtl4_a: Support also egress tags
  ...

1 files changed, 110 insertions, 13 deletions

diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 77d7c1bb2923..4c24daa43bac 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -19,7 +19,8 @@
 
 /* ld/ldx fields */
 #define BPF_DW		0x18	/* double word (64-bit) */
-#define BPF_XADD	0xc0	/* exclusive add */
+#define BPF_ATOMIC	0xc0	/* atomic memory ops - op type in immediate */
+#define BPF_XADD	0xc0	/* exclusive add - legacy name */
 
 /* alu/jmp fields */
 #define BPF_MOV		0xb0	/* mov reg to reg */
@@ -43,6 +44,11 @@
 #define BPF_CALL	0x80	/* function call */
 #define BPF_EXIT	0x90	/* function return */
 
+/* atomic op type fields (stored in immediate) */
+#define BPF_FETCH	0x01	/* not an opcode on its own, used to build others */
+#define BPF_XCHG	(0xe0 | BPF_FETCH)	/* atomic exchange */
+#define BPF_CMPXCHG	(0xf0 | BPF_FETCH)	/* atomic compare-and-write */
+
 /* Register numbers */
 enum {
 	BPF_REG_0 = 0,
@@ -1650,22 +1656,30 @@ union bpf_attr {
  * 		networking traffic statistics as it provides a global socket
  * 		identifier that can be assumed unique.
  * 	Return
- * 		A 8-byte long non-decreasing number on success, or 0 if the
- * 		socket field is missing inside *skb*.
+ * 		A 8-byte long unique number on success, or 0 if the socket
+ * 		field is missing inside *skb*.
  *
  * u64 bpf_get_socket_cookie(struct bpf_sock_addr *ctx)
  * 	Description
  * 		Equivalent to bpf_get_socket_cookie() helper that accepts
  * 		*skb*, but gets socket from **struct bpf_sock_addr** context.
  * 	Return
- * 		A 8-byte long non-decreasing number.
+ * 		A 8-byte long unique number.
  *
  * u64 bpf_get_socket_cookie(struct bpf_sock_ops *ctx)
  * 	Description
  * 		Equivalent to **bpf_get_socket_cookie**\ () helper that accepts
  * 		*skb*, but gets socket from **struct bpf_sock_ops** context.
  * 	Return
- * 		A 8-byte long non-decreasing number.
+ * 		A 8-byte long unique number.
+ *
+ * u64 bpf_get_socket_cookie(struct sock *sk)
+ * 	Description
+ * 		Equivalent to **bpf_get_socket_cookie**\ () helper that accepts
+ * 		*sk*, but gets socket from a BTF **struct sock**. This helper
+ * 		also works for sleepable programs.
+ * 	Return
+ * 		A 8-byte long unique number or 0 if *sk* is NULL.
  *
  * u32 bpf_get_socket_uid(struct sk_buff *skb)
  * 	Return
@@ -2225,6 +2239,9 @@ union bpf_attr {
  *		* > 0 one of **BPF_FIB_LKUP_RET_** codes explaining why the
  *		  packet is not forwarded or needs assist from full stack
  *
+ *		If lookup fails with BPF_FIB_LKUP_RET_FRAG_NEEDED, then the MTU
+ *		was exceeded and output params->mtu_result contains the MTU.
+ *
  * long bpf_sock_hash_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags)
  *	Description
  *		Add an entry to, or update a sockhash *map* referencing sockets.
@@ -2448,7 +2465,7 @@ union bpf_attr {
  *		running simultaneously.
  *
  *		A user should care about the synchronization by himself.
- *		For example, by using the **BPF_STX_XADD** instruction to alter
+ *		For example, by using the **BPF_ATOMIC** instructions to alter
  *		the shared data.
  *	Return
  *		A pointer to the local storage area.
@@ -2993,10 +3010,10 @@ union bpf_attr {
  * 		string length is larger than *size*, just *size*-1 bytes are
  * 		copied and the last byte is set to NUL.
  *
- * 		On success, the length of the copied string is returned. This
- * 		makes this helper useful in tracing programs for reading
- * 		strings, and more importantly to get its length at runtime. See
- * 		the following snippet:
+ * 		On success, returns the number of bytes that were written,
+ * 		including the terminal NUL. This makes this helper useful in
+ * 		tracing programs for reading strings, and more importantly to
+ * 		get its length at runtime. See the following snippet:
  *
  * 		::
  *
@@ -3024,7 +3041,7 @@ union bpf_attr {
  * 		**->mm->env_start**: using this helper and the return value,
  * 		one can quickly iterate at the right offset of the memory area.
  * 	Return
- * 		On success, the strictly positive length of the string,
+ * 		On success, the strictly positive length of the output string,
  * 		including the trailing NUL character. On error, a negative
  * 		value.
  *
@@ -3830,6 +3847,69 @@ union bpf_attr {
  *	Return
  *		A pointer to a struct socket on success or NULL if the file is
  *		not a socket.
+ *
+ * long bpf_check_mtu(void *ctx, u32 ifindex, u32 *mtu_len, s32 len_diff, u64 flags)
+ *	Description
+
+ *		Check ctx packet size against exceeding MTU of net device (based
+ *		on *ifindex*).  This helper will likely be used in combination
+ *		with helpers that adjust/change the packet size.
+ *
+ *		The argument *len_diff* can be used for querying with a planned
+ *		size change. This allows to check MTU prior to changing packet
+ *		ctx. Providing an *len_diff* adjustment that is larger than the
+ *		actual packet size (resulting in negative packet size) will in
+ *		principle not exceed the MTU, why it is not considered a
+ *		failure.  Other BPF-helpers are needed for performing the
+ *		planned size change, why the responsability for catch a negative
+ *		packet size belong in those helpers.
+ *
+ *		Specifying *ifindex* zero means the MTU check is performed
+ *		against the current net device.  This is practical if this isn't
+ *		used prior to redirect.
+ *
+ *		The Linux kernel route table can configure MTUs on a more
+ *		specific per route level, which is not provided by this helper.
+ *		For route level MTU checks use the **bpf_fib_lookup**\ ()
+ *		helper.
+ *
+ *		*ctx* is either **struct xdp_md** for XDP programs or
+ *		**struct sk_buff** for tc cls_act programs.
+ *
+ *		The *flags* argument can be a combination of one or more of the
+ *		following values:
+ *
+ *		**BPF_MTU_CHK_SEGS**
+ *			This flag will only works for *ctx* **struct sk_buff**.
+ *			If packet context contains extra packet segment buffers
+ *			(often knows as GSO skb), then MTU check is harder to
+ *			check at this point, because in transmit path it is
+ *			possible for the skb packet to get re-segmented
+ *			(depending on net device features).  This could still be
+ *			a MTU violation, so this flag enables performing MTU
+ *			check against segments, with a different violation
+ *			return code to tell it apart. Check cannot use len_diff.
+ *
+ *		On return *mtu_len* pointer contains the MTU value of the net
+ *		device.  Remember the net device configured MTU is the L3 size,
+ *		which is returned here and XDP and TX length operate at L2.
+ *		Helper take this into account for you, but remember when using
+ *		MTU value in your BPF-code.  On input *mtu_len* must be a valid
+ *		pointer and be initialized (to zero), else verifier will reject
+ *		BPF program.
+ *
+ *	Return
+ *		* 0 on success, and populate MTU value in *mtu_len* pointer.
+ *
+ *		* < 0 if any input argument is invalid (*mtu_len* not updated)
+ *
+ *		MTU violations return positive values, but also populate MTU
+ *		value in *mtu_len* pointer, as this can be needed for
+ *		implementing PMTU handing:
+ *
+ *		* **BPF_MTU_CHK_RET_FRAG_NEEDED**
+ *		* **BPF_MTU_CHK_RET_SEGS_TOOBIG**
+ *
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -3995,6 +4075,7 @@ union bpf_attr {
 	FN(ktime_get_coarse_ns),	\
 	FN(ima_inode_hash),		\
 	FN(sock_from_file),		\
+	FN(check_mtu),			\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper
@@ -4495,6 +4576,7 @@ struct bpf_prog_info {
 	__aligned_u64 prog_tags;
 	__u64 run_time_ns;
 	__u64 run_cnt;
+	__u64 recursion_misses;
 } __attribute__((aligned(8)));
 
 struct bpf_map_info {
@@ -4975,9 +5057,13 @@ struct bpf_fib_lookup {
 	__be16	sport;
 	__be16	dport;
 
-	/* total length of packet from network header - used for MTU check */
-	__u16	tot_len;
+	union {	/* used for MTU check */
+		/* input to lookup */
+		__u16	tot_len; /* L3 length from network hdr (iph->tot_len) */
 
+		/* output: MTU value */
+		__u16	mtu_result;
+	};
 	/* input: L3 device index for lookup
 	 * output: device index from FIB lookup
 	 */
@@ -5023,6 +5109,17 @@ struct bpf_redir_neigh {
 	};
 };
 
+/* bpf_check_mtu flags*/
+enum  bpf_check_mtu_flags {
+	BPF_MTU_CHK_SEGS  = (1U << 0),
+};
+
+enum bpf_check_mtu_ret {
+	BPF_MTU_CHK_RET_SUCCESS,      /* check and lookup successful */
+	BPF_MTU_CHK_RET_FRAG_NEEDED,  /* fragmentation required to fwd */
+	BPF_MTU_CHK_RET_SEGS_TOOBIG,  /* GSO re-segmentation needed to fwd */
+};
+
 enum bpf_task_fd_type {
 	BPF_FD_TYPE_RAW_TRACEPOINT,	/* tp name */
 	BPF_FD_TYPE_TRACEPOINT,		/* tp name */