Merge tag 'net-5.16-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from bpf, can and netfilter.

  Current release - regressions:

   - bpf, sockmap: re-evaluate proto ops when psock is removed from
     sockmap

  Current release - new code bugs:

   - bpf: fix bpf_check_mod_kfunc_call for built-in modules

   - ice: fixes for TC classifier offloads

   - vrf: don't run conntrack on vrf with !dflt qdisc

  Previous releases - regressions:

   - bpf: fix the off-by-two error in range markings

   - seg6: fix the iif in the IPv6 socket control block

   - devlink: fix netns refcount leak in devlink_nl_cmd_reload()

   - dsa: mv88e6xxx: fix "don't use PHY_DETECT on internal PHY's"

   - dsa: mv88e6xxx: allow use of PHYs on CPU and DSA ports

  Previous releases - always broken:

   - ethtool: do not perform operations on net devices being
     unregistered

   - udp: use datalen to cap max gso segments

   - ice: fix races in stats collection

   - fec: only clear interrupt of handling queue in fec_enet_rx_queue()

   - m_can: pci: fix incorrect reference clock rate

   - m_can: disable and ignore ELO interrupt

   - mvpp2: fix XDP rx queues registering

  Misc:

   - treewide: add missing includes masked by cgroup -> bpf.h
     dependency"

* tag 'net-5.16-rc5' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (82 commits)
  net: dsa: mv88e6xxx: allow use of PHYs on CPU and DSA ports
  net: wwan: iosm: fixes unable to send AT command during mbim tx
  net: wwan: iosm: fixes net interface nonfunctional after fw flash
  net: wwan: iosm: fixes unnecessary doorbell send
  net: dsa: felix: Fix memory leak in felix_setup_mmio_filtering
  MAINTAINERS: s390/net: remove myself as maintainer
  net/sched: fq_pie: prevent dismantle issue
  net: mana: Fix memory leak in mana_hwc_create_wq
  seg6: fix the iif in the IPv6 socket control block
  nfp: Fix memory leak in nfp_cpp_area_cache_add()
  nfc: fix potential NULL pointer deref in nfc_genl_dump_ses_done
  nfc: fix segfault in nfc_genl_dump_devices_done
  udp: using datalen to cap max gso segments
  net: dsa: mv88e6xxx: error handling for serdes_power functions
  can: kvaser_usb: get CAN clock frequency from device
  can: kvaser_pciefd: kvaser_pciefd_rx_error_frame(): increase correct stats->{rx,tx}_errors counter
  net: mvpp2: fix XDP rx queues registering
  vmxnet3: fix minimum vectors alloc issue
  net, neigh: clear whole pneigh_entry at alloc time
  net: dsa: mv88e6xxx: fix "don't use PHY_DETECT on internal PHY's"
  ...

9 files changed, 38 insertions, 32 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index e7a163a3146b..755f38e893be 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -732,6 +732,7 @@ int bpf_trampoline_unlink_prog(struct bpf_prog *prog, struct bpf_trampoline *tr)
 struct bpf_trampoline *bpf_trampoline_get(u64 key,
 					  struct bpf_attach_target_info *tgt_info);
 void bpf_trampoline_put(struct bpf_trampoline *tr);
+int arch_prepare_bpf_dispatcher(void *image, s64 *funcs, int num_funcs);
 #define BPF_DISPATCHER_INIT(_name) {				\
 	.mutex = __MUTEX_INITIALIZER(_name.mutex),		\
 	.func = &_name##_func,					\
@@ -1352,28 +1353,16 @@ extern struct mutex bpf_stats_enabled_mutex;
  * kprobes, tracepoints) to prevent deadlocks on map operations as any of
  * these events can happen inside a region which holds a map bucket lock
  * and can deadlock on it.
- *
- * Use the preemption safe inc/dec variants on RT because migrate disable
- * is preemptible on RT and preemption in the middle of the RMW operation
- * might lead to inconsistent state. Use the raw variants for non RT
- * kernels as migrate_disable() maps to preempt_disable() so the slightly
- * more expensive save operation can be avoided.
  */
 static inline void bpf_disable_instrumentation(void)
 {
 	migrate_disable();
-	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		this_cpu_inc(bpf_prog_active);
-	else
-		__this_cpu_inc(bpf_prog_active);
+	this_cpu_inc(bpf_prog_active);
 }
 
 static inline void bpf_enable_instrumentation(void)
 {
-	if (IS_ENABLED(CONFIG_PREEMPT_RT))
-		this_cpu_dec(bpf_prog_active);
-	else
-		__this_cpu_dec(bpf_prog_active);
+	this_cpu_dec(bpf_prog_active);
 	migrate_enable();
 }
 
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 203eef993d76..0e1b6281fd8f 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -245,7 +245,10 @@ struct kfunc_btf_id_set {
 	struct module *owner;
 };
 
-struct kfunc_btf_id_list;
+struct kfunc_btf_id_list {
+	struct list_head list;
+	struct mutex mutex;
+};
 
 #ifdef CONFIG_DEBUG_INFO_BTF_MODULES
 void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
@@ -254,6 +257,9 @@ void unregister_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
 				 struct kfunc_btf_id_set *s);
 bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist, u32 kfunc_id,
 			      struct module *owner);
+
+extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list;
+extern struct kfunc_btf_id_list prog_test_kfunc_list;
 #else
 static inline void register_kfunc_btf_id_set(struct kfunc_btf_id_list *l,
 					     struct kfunc_btf_id_set *s)
@@ -268,13 +274,13 @@ static inline bool bpf_check_mod_kfunc_call(struct kfunc_btf_id_list *klist,
 {
 	return false;
 }
+
+static struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list __maybe_unused;
+static struct kfunc_btf_id_list prog_test_kfunc_list __maybe_unused;
 #endif
 
 #define DEFINE_KFUNC_BTF_ID_SET(set, name)                                     \
 	struct kfunc_btf_id_set name = { LIST_HEAD_INIT(name.list), (set),     \
 					 THIS_MODULE }
 
-extern struct kfunc_btf_id_list bpf_tcp_ca_kfunc_list;
-extern struct kfunc_btf_id_list prog_test_kfunc_list;
-
 #endif
diff --git a/include/linux/cacheinfo.h b/include/linux/cacheinfo.h
index 2f909ed084c6..4ff37cb763ae 100644
--- a/include/linux/cacheinfo.h
+++ b/include/linux/cacheinfo.h
@@ -3,7 +3,6 @@
 #define _LINUX_CACHEINFO_H
 
 #include <linux/bitops.h>
-#include <linux/cpu.h>
 #include <linux/cpumask.h>
 #include <linux/smp.h>
 
diff --git a/include/linux/device/driver.h b/include/linux/device/driver.h
index a498ebcf4993..15e7c5e15d62 100644
--- a/include/linux/device/driver.h
+++ b/include/linux/device/driver.h
@@ -18,6 +18,7 @@
 #include <linux/klist.h>
 #include <linux/pm.h>
 #include <linux/device/bus.h>
+#include <linux/module.h>
 
 /**
  * enum probe_type - device driver probe type to try
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 24b7ed2677af..7f1e88e3e2b5 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -6,6 +6,7 @@
 #define __LINUX_FILTER_H__
 
 #include <linux/atomic.h>
+#include <linux/bpf.h>
 #include <linux/refcount.h>
 #include <linux/compat.h>
 #include <linux/skbuff.h>
@@ -26,7 +27,6 @@
 
 #include <asm/byteorder.h>
 #include <uapi/linux/filter.h>
-#include <uapi/linux/bpf.h>
 
 struct sk_buff;
 struct sock;
@@ -640,9 +640,6 @@ static __always_inline u32 bpf_prog_run(const struct bpf_prog *prog, const void
  * This uses migrate_disable/enable() explicitly to document that the
  * invocation of a BPF program does not require reentrancy protection
  * against a BPF program which is invoked from a preempting task.
- *
- * For non RT enabled kernels migrate_disable/enable() maps to
- * preempt_disable/enable(), i.e. it disables also preemption.
  */
 static inline u32 bpf_prog_run_pin_on_cpu(const struct bpf_prog *prog,
 					  const void *ctx)
diff --git a/include/linux/phy.h b/include/linux/phy.h
index 96e43fbb2dd8..cbf03a5f9cf5 100644
--- a/include/linux/phy.h
+++ b/include/linux/phy.h
@@ -538,11 +538,12 @@ struct macsec_ops;
  * @mac_managed_pm: Set true if MAC driver takes of suspending/resuming PHY
  * @state: State of the PHY for management purposes
  * @dev_flags: Device-specific flags used by the PHY driver.
- *		Bits [15:0] are free to use by the PHY driver to communicate
- *			    driver specific behavior.
- *		Bits [23:16] are currently reserved for future use.
- *		Bits [31:24] are reserved for defining generic
- *			     PHY driver behavior.
+ *
+ *      - Bits [15:0] are free to use by the PHY driver to communicate
+ *        driver specific behavior.
+ *      - Bits [23:16] are currently reserved for future use.
+ *      - Bits [31:24] are reserved for defining generic
+ *        PHY driver behavior.
  * @irq: IRQ number of the PHY's interrupt (-1 if none)
  * @phy_timer: The timer for handling the state machine
  * @phylink: Pointer to phylink instance for this PHY
diff --git a/include/net/bond_alb.h b/include/net/bond_alb.h
index f6af76c87a6c..191c36afa1f4 100644
--- a/include/net/bond_alb.h
+++ b/include/net/bond_alb.h
@@ -126,7 +126,7 @@ struct tlb_slave_info {
 struct alb_bond_info {
 	struct tlb_client_info	*tx_hashtbl; /* Dynamically allocated */
 	u32			unbalanced_load;
-	int			tx_rebalance_counter;
+	atomic_t		tx_rebalance_counter;
 	int			lp_counter;
 	/* -------- rlb parameters -------- */
 	int rlb_enabled;
diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
index 7994455ec714..c4898fcbf923 100644
--- a/include/net/busy_poll.h
+++ b/include/net/busy_poll.h
@@ -136,6 +136,19 @@ static inline void sk_mark_napi_id(struct sock *sk, const struct sk_buff *skb)
 	sk_rx_queue_update(sk, skb);
 }
 
+/* Variant of sk_mark_napi_id() for passive flow setup,
+ * as sk->sk_napi_id and sk->sk_rx_queue_mapping content
+ * needs to be set.
+ */
+static inline void sk_mark_napi_id_set(struct sock *sk,
+				       const struct sk_buff *skb)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	WRITE_ONCE(sk->sk_napi_id, skb->napi_id);
+#endif
+	sk_rx_queue_set(sk, skb);
+}
+
 static inline void __sk_mark_napi_id_once(struct sock *sk, unsigned int napi_id)
 {
 #ifdef CONFIG_NET_RX_BUSY_POLL
diff --git a/include/net/netfilter/nf_conntrack.h b/include/net/netfilter/nf_conntrack.h
index cc663c68ddc4..d24b0a34c8f0 100644
--- a/include/net/netfilter/nf_conntrack.h
+++ b/include/net/netfilter/nf_conntrack.h
@@ -276,14 +276,14 @@ static inline bool nf_is_loopback_packet(const struct sk_buff *skb)
 /* jiffies until ct expires, 0 if already expired */
 static inline unsigned long nf_ct_expires(const struct nf_conn *ct)
 {
-	s32 timeout = ct->timeout - nfct_time_stamp;
+	s32 timeout = READ_ONCE(ct->timeout) - nfct_time_stamp;
 
 	return timeout > 0 ? timeout : 0;
 }
 
 static inline bool nf_ct_is_expired(const struct nf_conn *ct)
 {
-	return (__s32)(ct->timeout - nfct_time_stamp) <= 0;
+	return (__s32)(READ_ONCE(ct->timeout) - nfct_time_stamp) <= 0;
 }
 
 /* use after obtaining a reference count */
@@ -302,7 +302,7 @@ static inline bool nf_ct_should_gc(const struct nf_conn *ct)
 static inline void nf_ct_offload_timeout(struct nf_conn *ct)
 {
 	if (nf_ct_expires(ct) < NF_CT_DAY / 2)
-		ct->timeout = nfct_time_stamp + NF_CT_DAY;
+		WRITE_ONCE(ct->timeout, nfct_time_stamp + NF_CT_DAY);
 }
 
 struct kernel_param;