Merge branch 'locking-introduce-nested-bh-locking'

Sebastian Andrzej Siewior says:

====================
locking: Introduce nested-BH locking.

Disabling bottoms halves acts as per-CPU BKL. On PREEMPT_RT code within
local_bh_disable() section remains preemtible. As a result high prior
tasks (or threaded interrupts) will be blocked by lower-prio task (or
threaded interrupts) which are long running which includes softirq
sections.

The proposed way out is to introduce explicit per-CPU locks for
resources which are protected by local_bh_disable() and use those only
on PREEMPT_RT so there is no additional overhead for !PREEMPT_RT builds.

The series introduces the infrastructure and converts large parts of
networking which is largest stake holder here. Once this done the
per-CPU lock from local_bh_disable() on PREEMPT_RT can be lifted.

Performance testing. Baseline is net-next as of commit 93bda33046
("Merge branch'net-constify-ctl_table-arguments-of-utility-functions'")
plus v6.10-rc1. A 10GiG link is used between two hosts. The command
   xdp-bench redirect-cpu --cpu 3 --remote-action drop eth1 -e

was invoked on the receiving side with a ixgbe. The sending side uses
pktgen_sample03_burst_single_flow.sh on i40e.

Baseline:
| eth1->?                 9,018,604 rx/s                  0 err,drop/s
|   receive total         9,018,604 pkt/s                 0 drop/s                0 error/s
|     cpu:7               9,018,604 pkt/s                 0 drop/s                0 error/s
|   enqueue to cpu 3      9,018,602 pkt/s                 0 drop/s             7.00 bulk-avg
|     cpu:7->3            9,018,602 pkt/s                 0 drop/s             7.00 bulk-avg
|   kthread total         9,018,606 pkt/s                 0 drop/s          214,698 sched
|     cpu:3               9,018,606 pkt/s                 0 drop/s          214,698 sched
|     xdp_stats                   0 pass/s        9,018,606 drop/s                0 redir/s
|       cpu:3                     0 pass/s        9,018,606 drop/s                0 redir/s
|   redirect_err                  0 error/s
|   xdp_exception                 0 hit/s

perf top --sort cpu,symbol --no-children:
|   18.14%  007  [k] bpf_prog_4f0ffbb35139c187_cpumap_l4_hash
|   13.29%  007  [k] ixgbe_poll
|   12.66%  003  [k] cpu_map_kthread_run
|    7.23%  003  [k] page_frag_free
|    6.76%  007  [k] xdp_do_redirect
|    3.76%  007  [k] cpu_map_redirect
|    3.13%  007  [k] bq_flush_to_queue
|    2.51%  003  [k] xdp_return_frame
|    1.93%  007  [k] try_to_wake_up
|    1.78%  007  [k] _raw_spin_lock
|    1.74%  007  [k] cpu_map_enqueue
|    1.56%  003  [k] bpf_prog_57cd311f2e27366b_cpumap_drop

With this series applied:
| eth1->?                10,329,340 rx/s                  0 err,drop/s
|   receive total        10,329,340 pkt/s                 0 drop/s                0 error/s
|     cpu:6              10,329,340 pkt/s                 0 drop/s                0 error/s
|   enqueue to cpu 3     10,329,338 pkt/s                 0 drop/s             8.00 bulk-avg
|     cpu:6->3           10,329,338 pkt/s                 0 drop/s             8.00 bulk-avg
|   kthread total        10,329,321 pkt/s                 0 drop/s           96,297 sched
|     cpu:3              10,329,321 pkt/s                 0 drop/s           96,297 sched
|     xdp_stats                   0 pass/s       10,329,321 drop/s                0 redir/s
|       cpu:3                     0 pass/s       10,329,321 drop/s                0 redir/s
|   redirect_err                  0 error/s
|   xdp_exception                 0 hit/s

perf top --sort cpu,symbol --no-children:
|   20.90%  006  [k] bpf_prog_4f0ffbb35139c187_cpumap_l4_hash
|   12.62%  006  [k] ixgbe_poll
|    9.82%  003  [k] page_frag_free
|    8.73%  003  [k] cpu_map_bpf_prog_run_xdp
|    6.63%  006  [k] xdp_do_redirect
|    4.94%  003  [k] cpu_map_kthread_run
|    4.28%  006  [k] cpu_map_redirect
|    4.03%  006  [k] bq_flush_to_queue
|    3.01%  003  [k] xdp_return_frame
|    1.95%  006  [k] _raw_spin_lock
|    1.94%  003  [k] bpf_prog_57cd311f2e27366b_cpumap_drop

This diff appears to be noise.

v8: https://lore.kernel.org/all/20240619072253.504963-1-bigeasy@linutronix.de
v7: https://lore.kernel.org/all/20240618072526.379909-1-bigeasy@linutronix.de
v6: https://lore.kernel.org/all/20240612170303.3896084-1-bigeasy@linutronix.de
v5: https://lore.kernel.org/all/20240607070427.1379327-1-bigeasy@linutronix.de
v4: https://lore.kernel.org/all/20240604154425.878636-1-bigeasy@linutronix.de
v3: https://lore.kernel.org/all/20240529162927.403425-1-bigeasy@linutronix.de
v2: https://lore.kernel.org/all/20240503182957.1042122-1-bigeasy@linutronix.de
v1: https://lore.kernel.org/all/20231215171020.687342-1-bigeasy@linutronix.de
====================

Link: https://patch.msgid.link/20240620132727.660738-1-bigeasy@linutronix.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

include/linux/filter.h

@@ -733,21 +733,101 @@ struct bpf_nh_params {
 	};
 };
 
+/* flags for bpf_redirect_info kern_flags */
+#define BPF_RI_F_RF_NO_DIRECT	BIT(0)	/* no napi_direct on return_frame */
+#define BPF_RI_F_RI_INIT	BIT(1)
+#define BPF_RI_F_CPU_MAP_INIT	BIT(2)
+#define BPF_RI_F_DEV_MAP_INIT	BIT(3)
+#define BPF_RI_F_XSK_MAP_INIT	BIT(4)
+
 struct bpf_redirect_info {
 	u64 tgt_index;
 	void *tgt_value;
 	struct bpf_map *map;
 	u32 flags;
-	u32 kern_flags;
 	u32 map_id;
 	enum bpf_map_type map_type;
 	struct bpf_nh_params nh;
+	u32 kern_flags;
 };
 
-DECLARE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info);
+struct bpf_net_context {
+	struct bpf_redirect_info ri;
+	struct list_head cpu_map_flush_list;
+	struct list_head dev_map_flush_list;
+	struct list_head xskmap_map_flush_list;
+};
 
-/* flags for bpf_redirect_info kern_flags */
-#define BPF_RI_F_RF_NO_DIRECT	BIT(0)	/* no napi_direct on return_frame */
+static inline struct bpf_net_context *bpf_net_ctx_set(struct bpf_net_context *bpf_net_ctx)
+{
+	struct task_struct *tsk = current;
+
+	if (tsk->bpf_net_context != NULL)
+		return NULL;
+	bpf_net_ctx->ri.kern_flags = 0;
+
+	tsk->bpf_net_context = bpf_net_ctx;
+	return bpf_net_ctx;
+}
+
+static inline void bpf_net_ctx_clear(struct bpf_net_context *bpf_net_ctx)
+{
+	if (bpf_net_ctx)
+		current->bpf_net_context = NULL;
+}
+
+static inline struct bpf_net_context *bpf_net_ctx_get(void)
+{
+	return current->bpf_net_context;
+}
+
+static inline struct bpf_redirect_info *bpf_net_ctx_get_ri(void)
+{
+	struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get();
+
+	if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_RI_INIT)) {
+		memset(&bpf_net_ctx->ri, 0, offsetof(struct bpf_net_context, ri.nh));
+		bpf_net_ctx->ri.kern_flags |= BPF_RI_F_RI_INIT;
+	}
+
+	return &bpf_net_ctx->ri;
+}
+
+static inline struct list_head *bpf_net_ctx_get_cpu_map_flush_list(void)
+{
+	struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get();
+
+	if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_CPU_MAP_INIT)) {
+		INIT_LIST_HEAD(&bpf_net_ctx->cpu_map_flush_list);
+		bpf_net_ctx->ri.kern_flags |= BPF_RI_F_CPU_MAP_INIT;
+	}
+
+	return &bpf_net_ctx->cpu_map_flush_list;
+}
+
+static inline struct list_head *bpf_net_ctx_get_dev_flush_list(void)
+{
+	struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get();
+
+	if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_DEV_MAP_INIT)) {
+		INIT_LIST_HEAD(&bpf_net_ctx->dev_map_flush_list);
+		bpf_net_ctx->ri.kern_flags |= BPF_RI_F_DEV_MAP_INIT;
+	}
+
+	return &bpf_net_ctx->dev_map_flush_list;
+}
+
+static inline struct list_head *bpf_net_ctx_get_xskmap_flush_list(void)
+{
+	struct bpf_net_context *bpf_net_ctx = bpf_net_ctx_get();
+
+	if (!(bpf_net_ctx->ri.kern_flags & BPF_RI_F_XSK_MAP_INIT)) {
+		INIT_LIST_HEAD(&bpf_net_ctx->xskmap_map_flush_list);
+		bpf_net_ctx->ri.kern_flags |= BPF_RI_F_XSK_MAP_INIT;
+	}
+
+	return &bpf_net_ctx->xskmap_map_flush_list;
+}
 
 /* Compute the linear packet data range [data, data_end) which
  * will be accessed by various program types (cls_bpf, act_bpf,
@@ -1018,25 +1098,23 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off,
 				       const struct bpf_insn *patch, u32 len);
 int bpf_remove_insns(struct bpf_prog *prog, u32 off, u32 cnt);
 
-void bpf_clear_redirect_map(struct bpf_map *map);
-
 static inline bool xdp_return_frame_no_direct(void)
 {
-	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
 
 	return ri->kern_flags & BPF_RI_F_RF_NO_DIRECT;
 }
 
 static inline void xdp_set_return_frame_no_direct(void)
 {
-	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
 
 	ri->kern_flags |= BPF_RI_F_RF_NO_DIRECT;
 }
 
 static inline void xdp_clear_return_frame_no_direct(void)
 {
-	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
 
 	ri->kern_flags &= ~BPF_RI_F_RF_NO_DIRECT;
 }
@@ -1592,7 +1670,7 @@ static __always_inline long __bpf_xdp_redirect_map(struct bpf_map *map, u64 inde
 						   u64 flags, const u64 flag_mask,
 						   void *lookup_elem(struct bpf_map *map, u32 key))
 {
-	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
 	const u64 action_mask = XDP_ABORTED | XDP_DROP | XDP_PASS | XDP_TX;
 
 	/* Lower bits of the flags are used as return code on lookup failure */

include/linux/local_lock.h

@@ -51,4 +51,25 @@
 #define local_unlock_irqrestore(lock, flags)			\
 	__local_unlock_irqrestore(lock, flags)
 
+DEFINE_GUARD(local_lock, local_lock_t __percpu*,
+	     local_lock(_T),
+	     local_unlock(_T))
+DEFINE_GUARD(local_lock_irq, local_lock_t __percpu*,
+	     local_lock_irq(_T),
+	     local_unlock_irq(_T))
+DEFINE_LOCK_GUARD_1(local_lock_irqsave, local_lock_t __percpu,
+		    local_lock_irqsave(_T->lock, _T->flags),
+		    local_unlock_irqrestore(_T->lock, _T->flags),
+		    unsigned long flags)
+
+#define local_lock_nested_bh(_lock)				\
+	__local_lock_nested_bh(_lock)
+
+#define local_unlock_nested_bh(_lock)				\
+	__local_unlock_nested_bh(_lock)
+
+DEFINE_GUARD(local_lock_nested_bh, local_lock_t __percpu*,
+	     local_lock_nested_bh(_T),
+	     local_unlock_nested_bh(_T))
+
 #endif

include/linux/local_lock_internal.h

@@ -62,6 +62,17 @@ do {								\
 	local_lock_debug_init(lock);				\
 } while (0)
 
+#define __spinlock_nested_bh_init(lock)				\
+do {								\
+	static struct lock_class_key __key;			\
+								\
+	debug_check_no_locks_freed((void *)lock, sizeof(*lock));\
+	lockdep_init_map_type(&(lock)->dep_map, #lock, &__key,  \
+			      0, LD_WAIT_CONFIG, LD_WAIT_INV,	\
+			      LD_LOCK_NORMAL);			\
+	local_lock_debug_init(lock);				\
+} while (0)
+
 #define __local_lock(lock)					\
 	do {							\
 		preempt_disable();				\
@@ -98,6 +109,15 @@ do {								\
 		local_irq_restore(flags);			\
 	} while (0)
 
+#define __local_lock_nested_bh(lock)				\
+	do {							\
+		lockdep_assert_in_softirq();			\
+		local_lock_acquire(this_cpu_ptr(lock));	\
+	} while (0)
+
+#define __local_unlock_nested_bh(lock)				\
+	local_lock_release(this_cpu_ptr(lock))
+
 #else /* !CONFIG_PREEMPT_RT */
 
 /*
@@ -138,4 +158,15 @@ typedef spinlock_t local_lock_t;
 
 #define __local_unlock_irqrestore(lock, flags)	__local_unlock(lock)
 
+#define __local_lock_nested_bh(lock)				\
+do {								\
+	lockdep_assert_in_softirq_func();			\
+	spin_lock(this_cpu_ptr(lock));				\
+} while (0)
+
+#define __local_unlock_nested_bh(lock)				\
+do {								\
+	spin_unlock(this_cpu_ptr((lock)));			\
+} while (0)
+
 #endif /* CONFIG_PREEMPT_RT */

include/linux/lockdep.h

@@ -600,6 +600,8 @@ do {									\
 		     (!in_softirq() || in_irq() || in_nmi()));		\
 } while (0)
 
+extern void lockdep_assert_in_softirq_func(void);
+
 #else
 # define might_lock(lock) do { } while (0)
 # define might_lock_read(lock) do { } while (0)
@@ -613,6 +615,7 @@ do {									\
 # define lockdep_assert_preemption_enabled() do { } while (0)
 # define lockdep_assert_preemption_disabled() do { } while (0)
 # define lockdep_assert_in_softirq() do { } while (0)
+# define lockdep_assert_in_softirq_func() do { } while (0)
 #endif
 
 #ifdef CONFIG_PROVE_RAW_LOCK_NESTING

include/linux/netdevice.h

@@ -43,6 +43,7 @@
 
 #include <linux/netdev_features.h>
 #include <linux/neighbour.h>
+#include <linux/netdevice_xmit.h>
 #include <uapi/linux/netdevice.h>
 #include <uapi/linux/if_bonding.h>
 #include <uapi/linux/pkt_cls.h>
@@ -3201,6 +3202,7 @@ static inline bool dev_has_header(const struct net_device *dev)
 struct softnet_data {
 	struct list_head	poll_list;
 	struct sk_buff_head	process_queue;
+	local_lock_t		process_queue_bh_lock;
 
 	/* stats */
 	unsigned int		processed;
@@ -3223,13 +3225,7 @@ struct softnet_data {
 	struct sk_buff_head	xfrm_backlog;
 #endif
 	/* written and read only by owning cpu: */
-	struct {
-		u16 recursion;
-		u8  more;
-#ifdef CONFIG_NET_EGRESS
-		u8  skip_txqueue;
-#endif
-	} xmit;
+	struct netdev_xmit xmit;
 #ifdef CONFIG_RPS
 	/* input_queue_head should be written by cpu owning this struct,
 	 * and only read by other cpus. Worth using a cache line.
@@ -3257,10 +3253,18 @@ struct softnet_data {
 
 DECLARE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
 
+#ifndef CONFIG_PREEMPT_RT
 static inline int dev_recursion_level(void)
 {
 	return this_cpu_read(softnet_data.xmit.recursion);
 }
+#else
+static inline int dev_recursion_level(void)
+{
+	return current->net_xmit.recursion;
+}
+
+#endif
 
 void __netif_schedule(struct Qdisc *q);
 void netif_schedule_queue(struct netdev_queue *txq);
@@ -4872,18 +4876,35 @@ static inline ktime_t netdev_get_tstamp(struct net_device *dev,
 	return hwtstamps->hwtstamp;
 }
 
-static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops,
-					      struct sk_buff *skb, struct net_device *dev,
-					      bool more)
+#ifndef CONFIG_PREEMPT_RT
+static inline void netdev_xmit_set_more(bool more)
 {
 	__this_cpu_write(softnet_data.xmit.more, more);
-	return ops->ndo_start_xmit(skb, dev);
 }
 
 static inline bool netdev_xmit_more(void)
 {
 	return __this_cpu_read(softnet_data.xmit.more);
 }
+#else
+static inline void netdev_xmit_set_more(bool more)
+{
+	current->net_xmit.more = more;
+}
+
+static inline bool netdev_xmit_more(void)
+{
+	return current->net_xmit.more;
+}
+#endif
+
+static inline netdev_tx_t __netdev_start_xmit(const struct net_device_ops *ops,
+					      struct sk_buff *skb, struct net_device *dev,
+					      bool more)
+{
+	netdev_xmit_set_more(more);
+	return ops->ndo_start_xmit(skb, dev);
+}
 
 static inline netdev_tx_t netdev_start_xmit(struct sk_buff *skb, struct net_device *dev,
 					    struct netdev_queue *txq, bool more)

include/linux/netdevice_xmit.h

@@ -0,0 +1,13 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#ifndef _LINUX_NETDEVICE_XMIT_H
+#define _LINUX_NETDEVICE_XMIT_H
+
+struct netdev_xmit {
+	u16 recursion;
+	u8  more;
+#ifdef CONFIG_NET_EGRESS
+	u8  skip_txqueue;
+#endif
+};
+
+#endif

include/linux/sched.h

@@ -36,6 +36,7 @@
 #include <linux/signal_types.h>
 #include <linux/syscall_user_dispatch_types.h>
 #include <linux/mm_types_task.h>
+#include <linux/netdevice_xmit.h>
 #include <linux/task_io_accounting.h>
 #include <linux/posix-timers_types.h>
 #include <linux/restart_block.h>
@@ -53,6 +54,7 @@ struct bio_list;
 struct blk_plug;
 struct bpf_local_storage;
 struct bpf_run_ctx;
+struct bpf_net_context;
 struct capture_control;
 struct cfs_rq;
 struct fs_struct;
@@ -975,7 +977,9 @@ struct task_struct {
 	/* delay due to memory thrashing */
 	unsigned                        in_thrashing:1;
 #endif
-
+#ifdef CONFIG_PREEMPT_RT
+	struct netdev_xmit		net_xmit;
+#endif
 	unsigned long			atomic_flags; /* Flags requiring atomic access. */
 
 	struct restart_block		restart_block;
@@ -1506,6 +1510,8 @@ struct task_struct {
 	/* Used for BPF run context */
 	struct bpf_run_ctx		*bpf_ctx;
 #endif
+	/* Used by BPF for per-TASK xdp storage */
+	struct bpf_net_context		*bpf_net_context;
 
 #ifdef CONFIG_GCC_PLUGIN_STACKLEAK
 	unsigned long			lowest_stack;

include/net/seg6_local.h

@@ -19,6 +19,7 @@ extern int seg6_lookup_nexthop(struct sk_buff *skb, struct in6_addr *nhaddr,
 extern bool seg6_bpf_has_valid_srh(struct sk_buff *skb);
 
 struct seg6_bpf_srh_state {
+	local_lock_t bh_lock;
 	struct ipv6_sr_hdr *srh;
 	u16 hdrlen;
 	bool valid;

include/net/sock.h

@@ -544,6 +544,11 @@ struct sock {
 	netns_tracker		ns_tracker;
 };
 
+struct sock_bh_locked {
+	struct sock *sock;
+	local_lock_t bh_lock;
+};
+
 enum sk_pacing {
 	SK_PACING_NONE		= 0,
 	SK_PACING_NEEDED	= 1,

kernel/bpf/cpumap.c

@@ -79,8 +79,6 @@ struct bpf_cpu_map {
 	struct bpf_cpu_map_entry __rcu **cpu_map;
 };
 
-static DEFINE_PER_CPU(struct list_head, cpu_map_flush_list);
-
 static struct bpf_map *cpu_map_alloc(union bpf_attr *attr)
 {
 	u32 value_size = attr->value_size;
@@ -240,12 +238,14 @@ static int cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames,
 				int xdp_n, struct xdp_cpumap_stats *stats,
 				struct list_head *list)
 {
+	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
 	int nframes;
 
 	if (!rcpu->prog)
 		return xdp_n;
 
 	rcu_read_lock_bh();
+	bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
 
 	nframes = cpu_map_bpf_prog_run_xdp(rcpu, frames, xdp_n, stats);
 
@@ -255,6 +255,7 @@ static int cpu_map_bpf_prog_run(struct bpf_cpu_map_entry *rcpu, void **frames,
 	if (unlikely(!list_empty(list)))
 		cpu_map_bpf_prog_run_skb(rcpu, list, stats);
 
+	bpf_net_ctx_clear(bpf_net_ctx);
 	rcu_read_unlock_bh(); /* resched point, may call do_softirq() */
 
 	return nframes;
@@ -706,7 +707,7 @@ static void bq_flush_to_queue(struct xdp_bulk_queue *bq)
  */
 static void bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf)
 {
-	struct list_head *flush_list = this_cpu_ptr(&cpu_map_flush_list);
+	struct list_head *flush_list = bpf_net_ctx_get_cpu_map_flush_list();
 	struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq);
 
 	if (unlikely(bq->count == CPU_MAP_BULK_SIZE))
@@ -758,7 +759,7 @@ int cpu_map_generic_redirect(struct bpf_cpu_map_entry *rcpu,
 
 void __cpu_map_flush(void)
 {
-	struct list_head *flush_list = this_cpu_ptr(&cpu_map_flush_list);
+	struct list_head *flush_list = bpf_net_ctx_get_cpu_map_flush_list();
 	struct xdp_bulk_queue *bq, *tmp;
 
 	list_for_each_entry_safe(bq, tmp, flush_list, flush_node) {
@@ -772,20 +773,9 @@ void __cpu_map_flush(void)
 #ifdef CONFIG_DEBUG_NET
 bool cpu_map_check_flush(void)
 {
-	if (list_empty(this_cpu_ptr(&cpu_map_flush_list)))
+	if (list_empty(bpf_net_ctx_get_cpu_map_flush_list()))
 		return false;
 	__cpu_map_flush();
 	return true;
 }
 #endif
-
-static int __init cpu_map_init(void)
-{
-	int cpu;
-
-	for_each_possible_cpu(cpu)
-		INIT_LIST_HEAD(&per_cpu(cpu_map_flush_list, cpu));
-	return 0;
-}
-
-subsys_initcall(cpu_map_init);

kernel/bpf/devmap.c

@@ -83,7 +83,6 @@ struct bpf_dtab {
 	u32 n_buckets;
 };
 
-static DEFINE_PER_CPU(struct list_head, dev_flush_list);
 static DEFINE_SPINLOCK(dev_map_lock);
 static LIST_HEAD(dev_map_list);
 
@@ -196,7 +195,14 @@ static void dev_map_free(struct bpf_map *map)
 	list_del_rcu(&dtab->list);
 	spin_unlock(&dev_map_lock);
 
-	bpf_clear_redirect_map(map);
+	/* bpf_redirect_info->map is assigned in __bpf_xdp_redirect_map()
+	 * during NAPI callback and cleared after the XDP redirect. There is no
+	 * explicit RCU read section which protects bpf_redirect_info->map but
+	 * local_bh_disable() also marks the beginning an RCU section. This
+	 * makes the complete softirq callback RCU protected. Thus after
+	 * following synchronize_rcu() there no bpf_redirect_info->map == map
+	 * assignment.
+	 */
 	synchronize_rcu();
 
 	/* Make sure prior __dev_map_entry_free() have completed. */
@@ -408,7 +414,7 @@ static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags)
  */
 void __dev_flush(void)
 {
-	struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
+	struct list_head *flush_list = bpf_net_ctx_get_dev_flush_list();
 	struct xdp_dev_bulk_queue *bq, *tmp;
 
 	list_for_each_entry_safe(bq, tmp, flush_list, flush_node) {
@@ -422,7 +428,7 @@ void __dev_flush(void)
 #ifdef CONFIG_DEBUG_NET
 bool dev_check_flush(void)
 {
-	if (list_empty(this_cpu_ptr(&dev_flush_list)))
+	if (list_empty(bpf_net_ctx_get_dev_flush_list()))
 		return false;
 	__dev_flush();
 	return true;
@@ -453,7 +459,7 @@ static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key)
 static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf,
 		       struct net_device *dev_rx, struct bpf_prog *xdp_prog)
 {
-	struct list_head *flush_list = this_cpu_ptr(&dev_flush_list);
+	struct list_head *flush_list = bpf_net_ctx_get_dev_flush_list();
 	struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq);
 
 	if (unlikely(bq->count == DEV_MAP_BULK_SIZE))
@@ -1153,15 +1159,11 @@ static struct notifier_block dev_map_notifier = {
 
 static int __init dev_map_init(void)
 {
-	int cpu;
-
 	/* Assure tracepoint shadow struct _bpf_dtab_netdev is in sync */
 	BUILD_BUG_ON(offsetof(struct bpf_dtab_netdev, dev) !=
 		     offsetof(struct _bpf_dtab_netdev, dev));
 	register_netdevice_notifier(&dev_map_notifier);
 
-	for_each_possible_cpu(cpu)
-		INIT_LIST_HEAD(&per_cpu(dev_flush_list, cpu));
 	return 0;
 }
 

kernel/fork.c

@@ -2355,6 +2355,7 @@ __latent_entropy struct task_struct *copy_process(
 	RCU_INIT_POINTER(p->bpf_storage, NULL);
 	p->bpf_ctx = NULL;
 #endif
+	p->bpf_net_context =  NULL;
 
 	/* Perform scheduler related setup. Assign this task to a CPU. */
 	retval = sched_fork(clone_flags, p);

kernel/locking/spinlock.c

@@ -413,3 +413,11 @@ notrace int in_lock_functions(unsigned long addr)
 	&& addr < (unsigned long)__lock_text_end;
 }
 EXPORT_SYMBOL(in_lock_functions);
+
+#if defined(CONFIG_PROVE_LOCKING) && defined(CONFIG_PREEMPT_RT)
+void notrace lockdep_assert_in_softirq_func(void)
+{
+	lockdep_assert_in_softirq();
+}
+EXPORT_SYMBOL(lockdep_assert_in_softirq_func);
+#endif

net/bpf/test_run.c

@@ -283,9 +283,10 @@ static int xdp_recv_frames(struct xdp_frame **frames, int nframes,
 static int xdp_test_run_batch(struct xdp_test_data *xdp, struct bpf_prog *prog,
 			      u32 repeat)
 {
-	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
 	int err = 0, act, ret, i, nframes = 0, batch_sz;
 	struct xdp_frame **frames = xdp->frames;
+	struct bpf_redirect_info *ri;
 	struct xdp_page_head *head;
 	struct xdp_frame *frm;
 	bool redirect = false;
@@ -295,6 +296,8 @@ static int xdp_test_run_batch(struct xdp_test_data *xdp, struct bpf_prog *prog,
 	batch_sz = min_t(u32, repeat, xdp->batch_size);
 
 	local_bh_disable();
+	bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
+	ri = bpf_net_ctx_get_ri();
 	xdp_set_return_frame_no_direct();
 
 	for (i = 0; i < batch_sz; i++) {
@@ -359,6 +362,7 @@ static int xdp_test_run_batch(struct xdp_test_data *xdp, struct bpf_prog *prog,
 	}
 
 	xdp_clear_return_frame_no_direct();
+	bpf_net_ctx_clear(bpf_net_ctx);
 	local_bh_enable();
 	return err;
 }
@@ -394,6 +398,7 @@ static int bpf_test_run_xdp_live(struct bpf_prog *prog, struct xdp_buff *ctx,
 static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat,
 			u32 *retval, u32 *time, bool xdp)
 {
+	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
 	struct bpf_prog_array_item item = {.prog = prog};
 	struct bpf_run_ctx *old_ctx;
 	struct bpf_cg_run_ctx run_ctx;
@@ -419,10 +424,14 @@ static int bpf_test_run(struct bpf_prog *prog, void *ctx, u32 repeat,
 	do {
 		run_ctx.prog_item = &item;
 		local_bh_disable();
+		bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
+
 		if (xdp)
 			*retval = bpf_prog_run_xdp(prog, ctx);
 		else
 			*retval = bpf_prog_run(prog, ctx);
+
+		bpf_net_ctx_clear(bpf_net_ctx);
 		local_bh_enable();
 	} while (bpf_test_timer_continue(&t, 1, repeat, &ret, time));
 	bpf_reset_run_ctx(old_ctx);

net/bridge/br_netfilter_hooks.c

@@ -137,6 +137,7 @@ static inline bool is_pppoe_ipv6(const struct sk_buff *skb,
 #define NF_BRIDGE_MAX_MAC_HEADER_LENGTH (PPPOE_SES_HLEN + ETH_HLEN)
 
 struct brnf_frag_data {
+	local_lock_t bh_lock;
 	char mac[NF_BRIDGE_MAX_MAC_HEADER_LENGTH];
 	u8 encap_size;
 	u8 size;
@@ -144,7 +145,9 @@ struct brnf_frag_data {
 	__be16 vlan_proto;
 };
 
-static DEFINE_PER_CPU(struct brnf_frag_data, brnf_frag_data_storage);
+static DEFINE_PER_CPU(struct brnf_frag_data, brnf_frag_data_storage) = {
+	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};
 
 static void nf_bridge_info_free(struct sk_buff *skb)
 {
@@ -850,6 +853,7 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff
 {
 	struct nf_bridge_info *nf_bridge = nf_bridge_info_get(skb);
 	unsigned int mtu, mtu_reserved;
+	int ret;
 
 	mtu_reserved = nf_bridge_mtu_reduction(skb);
 	mtu = skb->dev->mtu;
@@ -882,6 +886,7 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff
 
 		IPCB(skb)->frag_max_size = nf_bridge->frag_max_size;
 
+		local_lock_nested_bh(&brnf_frag_data_storage.bh_lock);
 		data = this_cpu_ptr(&brnf_frag_data_storage);
 
 		if (skb_vlan_tag_present(skb)) {
@@ -897,7 +902,9 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff
 		skb_copy_from_linear_data_offset(skb, -data->size, data->mac,
 						 data->size);
 
-		return br_nf_ip_fragment(net, sk, skb, br_nf_push_frag_xmit);
+		ret = br_nf_ip_fragment(net, sk, skb, br_nf_push_frag_xmit);
+		local_unlock_nested_bh(&brnf_frag_data_storage.bh_lock);
+		return ret;
 	}
 	if (IS_ENABLED(CONFIG_NF_DEFRAG_IPV6) &&
 	    skb->protocol == htons(ETH_P_IPV6)) {
@@ -909,6 +916,7 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff
 
 		IP6CB(skb)->frag_max_size = nf_bridge->frag_max_size;
 
+		local_lock_nested_bh(&brnf_frag_data_storage.bh_lock);
 		data = this_cpu_ptr(&brnf_frag_data_storage);
 		data->encap_size = nf_bridge_encap_header_len(skb);
 		data->size = ETH_HLEN + data->encap_size;
@@ -916,8 +924,12 @@ static int br_nf_dev_queue_xmit(struct net *net, struct sock *sk, struct sk_buff
 		skb_copy_from_linear_data_offset(skb, -data->size, data->mac,
 						 data->size);
 
-		if (v6ops)
-			return v6ops->fragment(net, sk, skb, br_nf_push_frag_xmit);
+		if (v6ops) {
+			ret = v6ops->fragment(net, sk, skb, br_nf_push_frag_xmit);
+			local_unlock_nested_bh(&brnf_frag_data_storage.bh_lock);
+			return ret;
+		}
+		local_unlock_nested_bh(&brnf_frag_data_storage.bh_lock);
 
 		kfree_skb(skb);
 		return -EMSGSIZE;

net/core/dev.c

@@ -229,7 +229,7 @@ static inline void backlog_lock_irq_save(struct softnet_data *sd,
 {
 	if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads())
 		spin_lock_irqsave(&sd->input_pkt_queue.lock, *flags);
-	else if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+	else
 		local_irq_save(*flags);
 }
 
@@ -237,7 +237,7 @@ static inline void backlog_lock_irq_disable(struct softnet_data *sd)
 {
 	if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads())
 		spin_lock_irq(&sd->input_pkt_queue.lock);
-	else if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+	else
 		local_irq_disable();
 }
 
@@ -246,7 +246,7 @@ static inline void backlog_unlock_irq_restore(struct softnet_data *sd,
 {
 	if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads())
 		spin_unlock_irqrestore(&sd->input_pkt_queue.lock, *flags);
-	else if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+	else
 		local_irq_restore(*flags);
 }
 
@@ -254,7 +254,7 @@ static inline void backlog_unlock_irq_enable(struct softnet_data *sd)
 {
 	if (IS_ENABLED(CONFIG_RPS) || use_backlog_threads())
 		spin_unlock_irq(&sd->input_pkt_queue.lock);
-	else if (!IS_ENABLED(CONFIG_PREEMPT_RT))
+	else
 		local_irq_enable();
 }
 
@@ -449,7 +449,9 @@ static RAW_NOTIFIER_HEAD(netdev_chain);
  *	queue in the local softnet handler.
  */
 
-DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data);
+DEFINE_PER_CPU_ALIGNED(struct softnet_data, softnet_data) = {
+	.process_queue_bh_lock = INIT_LOCAL_LOCK(process_queue_bh_lock),
+};
 EXPORT_PER_CPU_SYMBOL(softnet_data);
 
 /* Page_pool has a lockless array/stack to alloc/recycle pages.
@@ -3940,6 +3942,7 @@ netdev_tx_queue_mapping(struct net_device *dev, struct sk_buff *skb)
 	return netdev_get_tx_queue(dev, netdev_cap_txqueue(dev, qm));
 }
 
+#ifndef CONFIG_PREEMPT_RT
 static bool netdev_xmit_txqueue_skipped(void)
 {
 	return __this_cpu_read(softnet_data.xmit.skip_txqueue);
@@ -3950,6 +3953,19 @@ void netdev_xmit_skip_txqueue(bool skip)
 	__this_cpu_write(softnet_data.xmit.skip_txqueue, skip);
 }
 EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue);
+
+#else
+static bool netdev_xmit_txqueue_skipped(void)
+{
+	return current->net_xmit.skip_txqueue;
+}
+
+void netdev_xmit_skip_txqueue(bool skip)
+{
+	current->net_xmit.skip_txqueue = skip;
+}
+EXPORT_SYMBOL_GPL(netdev_xmit_skip_txqueue);
+#endif
 #endif /* CONFIG_NET_EGRESS */
 
 #ifdef CONFIG_NET_XGRESS
@@ -4029,10 +4045,13 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 {
 	struct bpf_mprog_entry *entry = rcu_dereference_bh(skb->dev->tcx_ingress);
 	enum skb_drop_reason drop_reason = SKB_DROP_REASON_TC_INGRESS;
+	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
 	int sch_ret;
 
 	if (!entry)
 		return skb;
+
+	bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
 	if (*pt_prev) {
 		*ret = deliver_skb(skb, *pt_prev, orig_dev);
 		*pt_prev = NULL;
@@ -4061,10 +4080,12 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 			break;
 		}
 		*ret = NET_RX_SUCCESS;
+		bpf_net_ctx_clear(bpf_net_ctx);
 		return NULL;
 	case TC_ACT_SHOT:
 		kfree_skb_reason(skb, drop_reason);
 		*ret = NET_RX_DROP;
+		bpf_net_ctx_clear(bpf_net_ctx);
 		return NULL;
 	/* used by tc_run */
 	case TC_ACT_STOLEN:
@@ -4074,8 +4095,10 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret,
 		fallthrough;
 	case TC_ACT_CONSUMED:
 		*ret = NET_RX_SUCCESS;
+		bpf_net_ctx_clear(bpf_net_ctx);
 		return NULL;
 	}
+	bpf_net_ctx_clear(bpf_net_ctx);
 
 	return skb;
 }
@@ -4085,11 +4108,14 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 {
 	struct bpf_mprog_entry *entry = rcu_dereference_bh(dev->tcx_egress);
 	enum skb_drop_reason drop_reason = SKB_DROP_REASON_TC_EGRESS;
+	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
 	int sch_ret;
 
 	if (!entry)
 		return skb;
 
+	bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
+
 	/* qdisc_skb_cb(skb)->pkt_len & tcx_set_ingress() was
 	 * already set by the caller.
 	 */
@@ -4105,10 +4131,12 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 		/* No need to push/pop skb's mac_header here on egress! */
 		skb_do_redirect(skb);
 		*ret = NET_XMIT_SUCCESS;
+		bpf_net_ctx_clear(bpf_net_ctx);
 		return NULL;
 	case TC_ACT_SHOT:
 		kfree_skb_reason(skb, drop_reason);
 		*ret = NET_XMIT_DROP;
+		bpf_net_ctx_clear(bpf_net_ctx);
 		return NULL;
 	/* used by tc_run */
 	case TC_ACT_STOLEN:
@@ -4118,8 +4146,10 @@ sch_handle_egress(struct sk_buff *skb, int *ret, struct net_device *dev)
 		fallthrough;
 	case TC_ACT_CONSUMED:
 		*ret = NET_XMIT_SUCCESS;
+		bpf_net_ctx_clear(bpf_net_ctx);
 		return NULL;
 	}
+	bpf_net_ctx_clear(bpf_net_ctx);
 
 	return skb;
 }
@@ -5935,6 +5965,7 @@ static void flush_backlog(struct work_struct *work)
 	}
 	backlog_unlock_irq_enable(sd);
 
+	local_lock_nested_bh(&softnet_data.process_queue_bh_lock);
 	skb_queue_walk_safe(&sd->process_queue, skb, tmp) {
 		if (skb->dev->reg_state == NETREG_UNREGISTERING) {
 			__skb_unlink(skb, &sd->process_queue);
@@ -5942,6 +5973,7 @@ static void flush_backlog(struct work_struct *work)
 			rps_input_queue_head_incr(sd);
 		}
 	}
+	local_unlock_nested_bh(&softnet_data.process_queue_bh_lock);
 	local_bh_enable();
 }
 
@@ -6063,7 +6095,9 @@ static int process_backlog(struct napi_struct *napi, int quota)
 	while (again) {
 		struct sk_buff *skb;
 
+		local_lock_nested_bh(&softnet_data.process_queue_bh_lock);
 		while ((skb = __skb_dequeue(&sd->process_queue))) {
+			local_unlock_nested_bh(&softnet_data.process_queue_bh_lock);
 			rcu_read_lock();
 			__netif_receive_skb(skb);
 			rcu_read_unlock();
@@ -6072,7 +6106,9 @@ static int process_backlog(struct napi_struct *napi, int quota)
 				return work;
 			}
 
+			local_lock_nested_bh(&softnet_data.process_queue_bh_lock);
 		}
+		local_unlock_nested_bh(&softnet_data.process_queue_bh_lock);
 
 		backlog_lock_irq_disable(sd);
 		if (skb_queue_empty(&sd->input_pkt_queue)) {
@@ -6087,8 +6123,10 @@ static int process_backlog(struct napi_struct *napi, int quota)
 			napi->state &= NAPIF_STATE_THREADED;
 			again = false;
 		} else {
+			local_lock_nested_bh(&softnet_data.process_queue_bh_lock);
 			skb_queue_splice_tail_init(&sd->input_pkt_queue,
 						   &sd->process_queue);
+			local_unlock_nested_bh(&softnet_data.process_queue_bh_lock);
 		}
 		backlog_unlock_irq_enable(sd);
 	}
@@ -6301,6 +6339,7 @@ enum {
 static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock,
 			   unsigned flags, u16 budget)
 {
+	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
 	bool skip_schedule = false;
 	unsigned long timeout;
 	int rc;
@@ -6318,6 +6357,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock,
 	clear_bit(NAPI_STATE_IN_BUSY_POLL, &napi->state);
 
 	local_bh_disable();
+	bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
 
 	if (flags & NAPI_F_PREFER_BUSY_POLL) {
 		napi->defer_hard_irqs_count = READ_ONCE(napi->dev->napi_defer_hard_irqs);
@@ -6340,6 +6380,7 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock,
 	netpoll_poll_unlock(have_poll_lock);
 	if (rc == budget)
 		__busy_poll_stop(napi, skip_schedule);
+	bpf_net_ctx_clear(bpf_net_ctx);
 	local_bh_enable();
 }
 
@@ -6349,6 +6390,7 @@ static void __napi_busy_loop(unsigned int napi_id,
 {
 	unsigned long start_time = loop_end ? busy_loop_current_time() : 0;
 	int (*napi_poll)(struct napi_struct *napi, int budget);
+	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
 	void *have_poll_lock = NULL;
 	struct napi_struct *napi;
 
@@ -6367,6 +6409,7 @@ static void __napi_busy_loop(unsigned int napi_id,
 		int work = 0;
 
 		local_bh_disable();
+		bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
 		if (!napi_poll) {
 			unsigned long val = READ_ONCE(napi->state);
 
@@ -6397,6 +6440,7 @@ static void __napi_busy_loop(unsigned int napi_id,
 			__NET_ADD_STATS(dev_net(napi->dev),
 					LINUX_MIB_BUSYPOLLRXPACKETS, work);
 		skb_defer_free_flush(this_cpu_ptr(&softnet_data));
+		bpf_net_ctx_clear(bpf_net_ctx);
 		local_bh_enable();
 
 		if (!loop_end || loop_end(loop_end_arg, start_time))
@@ -6824,6 +6868,7 @@ static int napi_thread_wait(struct napi_struct *napi)
 
 static void napi_threaded_poll_loop(struct napi_struct *napi)
 {
+	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
 	struct softnet_data *sd;
 	unsigned long last_qs = jiffies;
 
@@ -6832,6 +6877,8 @@ static void napi_threaded_poll_loop(struct napi_struct *napi)
 		void *have;
 
 		local_bh_disable();
+		bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
+
 		sd = this_cpu_ptr(&softnet_data);
 		sd->in_napi_threaded_poll = true;
 
@@ -6847,6 +6894,7 @@ static void napi_threaded_poll_loop(struct napi_struct *napi)
 			net_rps_action_and_irq_enable(sd);
 		}
 		skb_defer_free_flush(sd);
+		bpf_net_ctx_clear(bpf_net_ctx);
 		local_bh_enable();
 
 		if (!repoll)
@@ -6872,10 +6920,12 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
 	struct softnet_data *sd = this_cpu_ptr(&softnet_data);
 	unsigned long time_limit = jiffies +
 		usecs_to_jiffies(READ_ONCE(net_hotdata.netdev_budget_usecs));
+	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
 	int budget = READ_ONCE(net_hotdata.netdev_budget);
 	LIST_HEAD(list);
 	LIST_HEAD(repoll);
 
+	bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
 start:
 	sd->in_net_rx_action = true;
 	local_irq_disable();
@@ -6928,7 +6978,8 @@ static __latent_entropy void net_rx_action(struct softirq_action *h)
 		sd->in_net_rx_action = false;
 
 	net_rps_action_and_irq_enable(sd);
-end:;
+end:
+	bpf_net_ctx_clear(bpf_net_ctx);
 }
 
 struct netdev_adjacent {

net/core/dev.h

@@ -150,6 +150,8 @@ struct napi_struct *napi_by_id(unsigned int napi_id);
 void kick_defer_list_purge(struct softnet_data *sd, unsigned int cpu);
 
 #define XMIT_RECURSION_LIMIT	8
+
+#ifndef CONFIG_PREEMPT_RT
 static inline bool dev_xmit_recursion(void)
 {
 	return unlikely(__this_cpu_read(softnet_data.xmit.recursion) >
@@ -165,6 +167,22 @@ static inline void dev_xmit_recursion_dec(void)
 {
 	__this_cpu_dec(softnet_data.xmit.recursion);
 }
+#else
+static inline bool dev_xmit_recursion(void)
+{
+	return unlikely(current->net_xmit.recursion > XMIT_RECURSION_LIMIT);
+}
+
+static inline void dev_xmit_recursion_inc(void)
+{
+	current->net_xmit.recursion++;
+}
+
+static inline void dev_xmit_recursion_dec(void)
+{
+	current->net_xmit.recursion--;
+}
+#endif
 
 int dev_set_hwtstamp_phylib(struct net_device *dev,
 			    struct kernel_hwtstamp_config *cfg,

net/core/filter.c

@@ -1658,9 +1658,12 @@ struct bpf_scratchpad {
 		__be32 diff[MAX_BPF_STACK / sizeof(__be32)];
 		u8     buff[MAX_BPF_STACK];
 	};
+	local_lock_t	bh_lock;
 };
 
-static DEFINE_PER_CPU(struct bpf_scratchpad, bpf_sp);
+static DEFINE_PER_CPU(struct bpf_scratchpad, bpf_sp) = {
+	.bh_lock	= INIT_LOCAL_LOCK(bh_lock),
+};
 
 static inline int __bpf_try_make_writable(struct sk_buff *skb,
 					  unsigned int write_len)
@@ -2021,6 +2024,7 @@ BPF_CALL_5(bpf_csum_diff, __be32 *, from, u32, from_size,
 	struct bpf_scratchpad *sp = this_cpu_ptr(&bpf_sp);
 	u32 diff_size = from_size + to_size;
 	int i, j = 0;
+	__wsum ret;
 
 	/* This is quite flexible, some examples:
 	 *
@@ -2034,12 +2038,15 @@ BPF_CALL_5(bpf_csum_diff, __be32 *, from, u32, from_size,
 		     diff_size > sizeof(sp->diff)))
 		return -EINVAL;
 
+	local_lock_nested_bh(&bpf_sp.bh_lock);
 	for (i = 0; i < from_size / sizeof(__be32); i++, j++)
 		sp->diff[j] = ~from[i];
 	for (i = 0; i <   to_size / sizeof(__be32); i++, j++)
 		sp->diff[j] = to[i];
 
-	return csum_partial(sp->diff, diff_size, seed);
+	ret = csum_partial(sp->diff, diff_size, seed);
+	local_unlock_nested_bh(&bpf_sp.bh_lock);
+	return ret;
 }
 
 static const struct bpf_func_proto bpf_csum_diff_proto = {
@@ -2476,9 +2483,6 @@ static const struct bpf_func_proto bpf_clone_redirect_proto = {
 	.arg3_type      = ARG_ANYTHING,
 };
 
-DEFINE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info);
-EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info);
-
 static struct net_device *skb_get_peer_dev(struct net_device *dev)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
@@ -2491,7 +2495,7 @@ static struct net_device *skb_get_peer_dev(struct net_device *dev)
 
 int skb_do_redirect(struct sk_buff *skb)
 {
-	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
 	struct net *net = dev_net(skb->dev);
 	struct net_device *dev;
 	u32 flags = ri->flags;
@@ -2524,7 +2528,7 @@ int skb_do_redirect(struct sk_buff *skb)
 
 BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags)
 {
-	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
 
 	if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL)))
 		return TC_ACT_SHOT;
@@ -2545,7 +2549,7 @@ static const struct bpf_func_proto bpf_redirect_proto = {
 
 BPF_CALL_2(bpf_redirect_peer, u32, ifindex, u64, flags)
 {
-	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
 
 	if (unlikely(flags))
 		return TC_ACT_SHOT;
@@ -2567,7 +2571,7 @@ static const struct bpf_func_proto bpf_redirect_peer_proto = {
 BPF_CALL_4(bpf_redirect_neigh, u32, ifindex, struct bpf_redir_neigh *, params,
 	   int, plen, u64, flags)
 {
-	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
 
 	if (unlikely((plen && plen < sizeof(*params)) || flags))
 		return TC_ACT_SHOT;
@@ -4293,30 +4297,13 @@ void xdp_do_check_flushed(struct napi_struct *napi)
 }
 #endif
 
-void bpf_clear_redirect_map(struct bpf_map *map)
-{
-	struct bpf_redirect_info *ri;
-	int cpu;
-
-	for_each_possible_cpu(cpu) {
-		ri = per_cpu_ptr(&bpf_redirect_info, cpu);
-		/* Avoid polluting remote cacheline due to writes if
-		 * not needed. Once we pass this test, we need the
-		 * cmpxchg() to make sure it hasn't been changed in
-		 * the meantime by remote CPU.
-		 */
-		if (unlikely(READ_ONCE(ri->map) == map))
-			cmpxchg(&ri->map, map, NULL);
-	}
-}
-
 DEFINE_STATIC_KEY_FALSE(bpf_master_redirect_enabled_key);
 EXPORT_SYMBOL_GPL(bpf_master_redirect_enabled_key);
 
 u32 xdp_master_redirect(struct xdp_buff *xdp)
 {
+	struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
 	struct net_device *master, *slave;
-	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 
 	master = netdev_master_upper_dev_get_rcu(xdp->rxq->dev);
 	slave = master->netdev_ops->ndo_xdp_get_xmit_slave(master, xdp);
@@ -4388,7 +4375,7 @@ static __always_inline int __xdp_do_redirect_frame(struct bpf_redirect_info *ri,
 			map = READ_ONCE(ri->map);
 
 			/* The map pointer is cleared when the map is being torn
-			 * down by bpf_clear_redirect_map()
+			 * down by dev_map_free()
 			 */
 			if (unlikely(!map)) {
 				err = -ENOENT;
@@ -4433,7 +4420,7 @@ static __always_inline int __xdp_do_redirect_frame(struct bpf_redirect_info *ri,
 int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 		    struct bpf_prog *xdp_prog)
 {
-	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
 	enum bpf_map_type map_type = ri->map_type;
 
 	if (map_type == BPF_MAP_TYPE_XSKMAP)
@@ -4447,7 +4434,7 @@ EXPORT_SYMBOL_GPL(xdp_do_redirect);
 int xdp_do_redirect_frame(struct net_device *dev, struct xdp_buff *xdp,
 			  struct xdp_frame *xdpf, struct bpf_prog *xdp_prog)
 {
-	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
 	enum bpf_map_type map_type = ri->map_type;
 
 	if (map_type == BPF_MAP_TYPE_XSKMAP)
@@ -4464,7 +4451,7 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
 				       enum bpf_map_type map_type, u32 map_id,
 				       u32 flags)
 {
-	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
 	struct bpf_map *map;
 	int err;
 
@@ -4476,7 +4463,7 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
 			map = READ_ONCE(ri->map);
 
 			/* The map pointer is cleared when the map is being torn
-			 * down by bpf_clear_redirect_map()
+			 * down by dev_map_free()
 			 */
 			if (unlikely(!map)) {
 				err = -ENOENT;
@@ -4518,7 +4505,7 @@ static int xdp_do_generic_redirect_map(struct net_device *dev,
 int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
 			    struct xdp_buff *xdp, struct bpf_prog *xdp_prog)
 {
-	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
 	enum bpf_map_type map_type = ri->map_type;
 	void *fwd = ri->tgt_value;
 	u32 map_id = ri->map_id;
@@ -4554,7 +4541,7 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb,
 
 BPF_CALL_2(bpf_xdp_redirect, u32, ifindex, u64, flags)
 {
-	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
+	struct bpf_redirect_info *ri = bpf_net_ctx_get_ri();
 
 	if (unlikely(flags))
 		return XDP_ABORTED;
@@ -6455,6 +6442,7 @@ BPF_CALL_4(bpf_lwt_seg6_store_bytes, struct sk_buff *, skb, u32, offset,
 	void *srh_tlvs, *srh_end, *ptr;
 	int srhoff = 0;
 
+	lockdep_assert_held(&srh_state->bh_lock);
 	if (srh == NULL)
 		return -EINVAL;
 
@@ -6511,6 +6499,7 @@ BPF_CALL_4(bpf_lwt_seg6_action, struct sk_buff *, skb,
 	int hdroff = 0;
 	int err;
 
+	lockdep_assert_held(&srh_state->bh_lock);
 	switch (action) {
 	case SEG6_LOCAL_ACTION_END_X:
 		if (!seg6_bpf_has_valid_srh(skb))
@@ -6587,6 +6576,7 @@ BPF_CALL_3(bpf_lwt_seg6_adjust_srh, struct sk_buff *, skb, u32, offset,
 	int srhoff = 0;
 	int ret;
 
+	lockdep_assert_held(&srh_state->bh_lock);
 	if (unlikely(srh == NULL))
 		return -EINVAL;
 

net/core/lwt_bpf.c

@@ -38,13 +38,14 @@ static inline struct bpf_lwt *bpf_lwt_lwtunnel(struct lwtunnel_state *lwt)
 static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt,
 		       struct dst_entry *dst, bool can_redirect)
 {
+	struct bpf_net_context __bpf_net_ctx, *bpf_net_ctx;
 	int ret;
 
-	/* Migration disable and BH disable are needed to protect per-cpu
-	 * redirect_info between BPF prog and skb_do_redirect().
+	/* Disabling BH is needed to protect per-CPU bpf_redirect_info between
+	 * BPF prog and skb_do_redirect().
 	 */
-	migrate_disable();
 	local_bh_disable();
+	bpf_net_ctx = bpf_net_ctx_set(&__bpf_net_ctx);
 	bpf_compute_data_pointers(skb);
 	ret = bpf_prog_run_save_cb(lwt->prog, skb);
 
@@ -77,8 +78,8 @@ static int run_lwt_bpf(struct sk_buff *skb, struct bpf_lwt_prog *lwt,
 		break;
 	}
 
+	bpf_net_ctx_clear(bpf_net_ctx);
 	local_bh_enable();
-	migrate_enable();
 
 	return ret;
 }

net/core/skbuff.c

@@ -277,6 +277,7 @@ static void *page_frag_alloc_1k(struct page_frag_1k *nc, gfp_t gfp_mask)
 #endif
 
 struct napi_alloc_cache {
+	local_lock_t bh_lock;
 	struct page_frag_cache page;
 	struct page_frag_1k page_small;
 	unsigned int skb_count;
@@ -284,7 +285,9 @@ struct napi_alloc_cache {
 };
 
 static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache);
-static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache);
+static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache) = {
+	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};
 
 /* Double check that napi_get_frags() allocates skbs with
  * skb->head being backed by slab, not a page fragment.
@@ -306,11 +309,16 @@ void napi_get_frags_check(struct napi_struct *napi)
 void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask)
 {
 	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
+	void *data;
 
 	fragsz = SKB_DATA_ALIGN(fragsz);
 
-	return __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC,
+	local_lock_nested_bh(&napi_alloc_cache.bh_lock);
+	data = __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC,
 				       align_mask);
+	local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
+	return data;
+
 }
 EXPORT_SYMBOL(__napi_alloc_frag_align);
 
@@ -318,19 +326,15 @@ void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask)
 {
 	void *data;
 
-	fragsz = SKB_DATA_ALIGN(fragsz);
 	if (in_hardirq() || irqs_disabled()) {
 		struct page_frag_cache *nc = this_cpu_ptr(&netdev_alloc_cache);
 
+		fragsz = SKB_DATA_ALIGN(fragsz);
 		data = __page_frag_alloc_align(nc, fragsz, GFP_ATOMIC,
 					       align_mask);
 	} else {
-		struct napi_alloc_cache *nc;
-
 		local_bh_disable();
-		nc = this_cpu_ptr(&napi_alloc_cache);
-		data = __page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC,
-					       align_mask);
+		data = __napi_alloc_frag_align(fragsz, align_mask);
 		local_bh_enable();
 	}
 	return data;
@@ -342,16 +346,20 @@ static struct sk_buff *napi_skb_cache_get(void)
 	struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache);
 	struct sk_buff *skb;
 
+	local_lock_nested_bh(&napi_alloc_cache.bh_lock);
 	if (unlikely(!nc->skb_count)) {
 		nc->skb_count = kmem_cache_alloc_bulk(net_hotdata.skbuff_cache,
 						      GFP_ATOMIC,
 						      NAPI_SKB_CACHE_BULK,
 						      nc->skb_cache);
-		if (unlikely(!nc->skb_count))
+		if (unlikely(!nc->skb_count)) {
+			local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
 			return NULL;
+		}
 	}
 
 	skb = nc->skb_cache[--nc->skb_count];
+	local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
 	kasan_mempool_unpoison_object(skb, kmem_cache_size(net_hotdata.skbuff_cache));
 
 	return skb;
@@ -744,9 +752,13 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int len,
 		pfmemalloc = nc->pfmemalloc;
 	} else {
 		local_bh_disable();
+		local_lock_nested_bh(&napi_alloc_cache.bh_lock);
+
 		nc = this_cpu_ptr(&napi_alloc_cache.page);
 		data = page_frag_alloc(nc, len, gfp_mask);
 		pfmemalloc = nc->pfmemalloc;
+
+		local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
 		local_bh_enable();
 	}
 
@@ -810,11 +822,11 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len)
 		goto skb_success;
 	}
 
-	nc = this_cpu_ptr(&napi_alloc_cache);
-
 	if (sk_memalloc_socks())
 		gfp_mask |= __GFP_MEMALLOC;
 
+	local_lock_nested_bh(&napi_alloc_cache.bh_lock);
+	nc = this_cpu_ptr(&napi_alloc_cache);
 	if (NAPI_HAS_SMALL_PAGE_FRAG && len <= SKB_WITH_OVERHEAD(1024)) {
 		/* we are artificially inflating the allocation size, but
 		 * that is not as bad as it may look like, as:
@@ -836,6 +848,7 @@ struct sk_buff *napi_alloc_skb(struct napi_struct *napi, unsigned int len)
 		data = page_frag_alloc(&nc->page, len, gfp_mask);
 		pfmemalloc = nc->page.pfmemalloc;
 	}
+	local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
 
 	if (unlikely(!data))
 		return NULL;
@@ -1435,6 +1448,7 @@ static void napi_skb_cache_put(struct sk_buff *skb)
 	if (!kasan_mempool_poison_object(skb))
 		return;
 
+	local_lock_nested_bh(&napi_alloc_cache.bh_lock);
 	nc->skb_cache[nc->skb_count++] = skb;
 
 	if (unlikely(nc->skb_count == NAPI_SKB_CACHE_SIZE)) {
@@ -1446,6 +1460,7 @@ static void napi_skb_cache_put(struct sk_buff *skb)
 				     nc->skb_cache + NAPI_SKB_CACHE_HALF);
 		nc->skb_count = NAPI_SKB_CACHE_HALF;
 	}
+	local_unlock_nested_bh(&napi_alloc_cache.bh_lock);
 }
 
 void __napi_kfree_skb(struct sk_buff *skb, enum skb_drop_reason reason)

net/ipv4/tcp_ipv4.c

@@ -93,7 +93,9 @@ static int tcp_v4_md5_hash_hdr(char *md5_hash, const struct tcp_md5sig_key *key,
 struct inet_hashinfo tcp_hashinfo;
 EXPORT_SYMBOL(tcp_hashinfo);
 
-static DEFINE_PER_CPU(struct sock *, ipv4_tcp_sk);
+static DEFINE_PER_CPU(struct sock_bh_locked, ipv4_tcp_sk) = {
+	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};
 
 static u32 tcp_v4_init_seq(const struct sk_buff *skb)
 {
@@ -882,7 +884,9 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb,
 	arg.tos = ip_hdr(skb)->tos;
 	arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL);
 	local_bh_disable();
-	ctl_sk = this_cpu_read(ipv4_tcp_sk);
+	local_lock_nested_bh(&ipv4_tcp_sk.bh_lock);
+	ctl_sk = this_cpu_read(ipv4_tcp_sk.sock);
+
 	sock_net_set(ctl_sk, net);
 	if (sk) {
 		ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
@@ -907,6 +911,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb,
 	sock_net_set(ctl_sk, &init_net);
 	__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
 	__TCP_INC_STATS(net, TCP_MIB_OUTRSTS);
+	local_unlock_nested_bh(&ipv4_tcp_sk.bh_lock);
 	local_bh_enable();
 
 #ifdef CONFIG_TCP_MD5SIG
@@ -1002,7 +1007,8 @@ static void tcp_v4_send_ack(const struct sock *sk,
 	arg.tos = tos;
 	arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL);
 	local_bh_disable();
-	ctl_sk = this_cpu_read(ipv4_tcp_sk);
+	local_lock_nested_bh(&ipv4_tcp_sk.bh_lock);
+	ctl_sk = this_cpu_read(ipv4_tcp_sk.sock);
 	sock_net_set(ctl_sk, net);
 	ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ?
 			   inet_twsk(sk)->tw_mark : READ_ONCE(sk->sk_mark);
@@ -1017,6 +1023,7 @@ static void tcp_v4_send_ack(const struct sock *sk,
 
 	sock_net_set(ctl_sk, &init_net);
 	__TCP_INC_STATS(net, TCP_MIB_OUTSEGS);
+	local_unlock_nested_bh(&ipv4_tcp_sk.bh_lock);
 	local_bh_enable();
 }
 
@@ -3615,7 +3622,7 @@ void __init tcp_v4_init(void)
 
 		sk->sk_clockid = CLOCK_MONOTONIC;
 
-		per_cpu(ipv4_tcp_sk, cpu) = sk;
+		per_cpu(ipv4_tcp_sk.sock, cpu) = sk;
 	}
 	if (register_pernet_subsys(&tcp_sk_ops))
 		panic("Failed to create the TCP control socket.\n");

net/ipv4/tcp_sigpool.c

@@ -10,7 +10,14 @@
 #include <net/tcp.h>
 
 static size_t __scratch_size;
-static DEFINE_PER_CPU(void __rcu *, sigpool_scratch);
+struct sigpool_scratch {
+	local_lock_t bh_lock;
+	void __rcu *pad;
+};
+
+static DEFINE_PER_CPU(struct sigpool_scratch, sigpool_scratch) = {
+	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
+};
 
 struct sigpool_entry {
 	struct crypto_ahash	*hash;
@@ -72,7 +79,7 @@ static int sigpool_reserve_scratch(size_t size)
 			break;
 		}
 
-		old_scratch = rcu_replace_pointer(per_cpu(sigpool_scratch, cpu),
+		old_scratch = rcu_replace_pointer(per_cpu(sigpool_scratch.pad, cpu),
 					scratch, lockdep_is_held(&cpool_mutex));
 		if (!cpu_online(cpu) || !old_scratch) {
 			kfree(old_scratch);
@@ -93,7 +100,7 @@ static void sigpool_scratch_free(void)
 	int cpu;
 
 	for_each_possible_cpu(cpu)
-		kfree(rcu_replace_pointer(per_cpu(sigpool_scratch, cpu),
+		kfree(rcu_replace_pointer(per_cpu(sigpool_scratch.pad, cpu),
 					  NULL, lockdep_is_held(&cpool_mutex)));
 	__scratch_size = 0;
 }
@@ -277,7 +284,8 @@ int tcp_sigpool_start(unsigned int id, struct tcp_sigpool *c) __cond_acquires(RC
 	/* Pairs with tcp_sigpool_reserve_scratch(), scratch area is
 	 * valid (allocated) until tcp_sigpool_end().
 	 */
-	c->scratch = rcu_dereference_bh(*this_cpu_ptr(&sigpool_scratch));
+	local_lock_nested_bh(&sigpool_scratch.bh_lock);
+	c->scratch = rcu_dereference_bh(*this_cpu_ptr(&sigpool_scratch.pad));
 	return 0;
 }
 EXPORT_SYMBOL_GPL(tcp_sigpool_start);
@@ -286,6 +294,7 @@ void tcp_sigpool_end(struct tcp_sigpool *c) __releases(RCU_BH)
 {
 	struct crypto_ahash *hash = crypto_ahash_reqtfm(c->req);
 
+	local_unlock_nested_bh(&sigpool_scratch.bh_lock);
 	rcu_read_unlock_bh();
 	ahash_request_free(c->req);
 	crypto_free_ahash(hash);

net/ipv6/seg6_local.c

@@ -1380,7 +1380,9 @@ static int input_action_end_b6_encap(struct sk_buff *skb,
 	return err;
 }
 
-DEFINE_PER_CPU(struct seg6_bpf_srh_state, seg6_bpf_srh_states);
+DEFINE_PER_CPU(struct seg6_bpf_srh_state, seg6_bpf_srh_states) = {
+	.bh_lock	= INIT_LOCAL_LOCK(bh_lock),
+};
 
 bool seg6_bpf_has_valid_srh(struct sk_buff *skb)
 {
@@ -1388,6 +1390,7 @@ bool seg6_bpf_has_valid_srh(struct sk_buff *skb)
 		this_cpu_ptr(&seg6_bpf_srh_states);
 	struct ipv6_sr_hdr *srh = srh_state->srh;
 
+	lockdep_assert_held(&srh_state->bh_lock);
 	if (unlikely(srh == NULL))
 		return false;
 
@@ -1408,8 +1411,7 @@ bool seg6_bpf_has_valid_srh(struct sk_buff *skb)
 static int input_action_end_bpf(struct sk_buff *skb,
 				struct seg6_local_lwt *slwt)
 {
-	struct seg6_bpf_srh_state *srh_state =
-		this_cpu_ptr(&seg6_bpf_srh_states);
+	struct seg6_bpf_srh_state *srh_state;
 	struct ipv6_sr_hdr *srh;
 	int ret;
 
@@ -1420,10 +1422,14 @@ static int input_action_end_bpf(struct sk_buff *skb,
 	}
 	advance_nextseg(srh, &ipv6_hdr(skb)->daddr);
 
-	/* preempt_disable is needed to protect the per-CPU buffer srh_state,
-	 * which is also accessed by the bpf_lwt_seg6_* helpers
+	/* The access to the per-CPU buffer srh_state is protected by running
+	 * always in softirq context (with disabled BH). On PREEMPT_RT the
+	 * required locking is provided by the following local_lock_nested_bh()
+	 * statement. It is also accessed by the bpf_lwt_seg6_* helpers via
+	 * bpf_prog_run_save_cb().
 	 */
-	preempt_disable();
+	local_lock_nested_bh(&seg6_bpf_srh_states.bh_lock);
+	srh_state = this_cpu_ptr(&seg6_bpf_srh_states);
 	srh_state->srh = srh;
 	srh_state->hdrlen = srh->hdrlen << 3;
 	srh_state->valid = true;
@@ -1446,15 +1452,15 @@ static int input_action_end_bpf(struct sk_buff *skb,
 
 	if (srh_state->srh && !seg6_bpf_has_valid_srh(skb))
 		goto drop;
+	local_unlock_nested_bh(&seg6_bpf_srh_states.bh_lock);
 
-	preempt_enable();
 	if (ret != BPF_REDIRECT)
 		seg6_lookup_nexthop(skb, NULL, 0);
 
 	return dst_input(skb);
 
 drop:
-	preempt_enable();
+	local_unlock_nested_bh(&seg6_bpf_srh_states.bh_lock);
 	kfree_skb(skb);
 	return -EINVAL;
 }

net/xdp/xsk.c

@@ -35,8 +35,6 @@
 #define TX_BATCH_SIZE 32
 #define MAX_PER_SOCKET_BUDGET (TX_BATCH_SIZE)
 
-static DEFINE_PER_CPU(struct list_head, xskmap_flush_list);
-
 void xsk_set_rx_need_wakeup(struct xsk_buff_pool *pool)
 {
 	if (pool->cached_need_wakeup & XDP_WAKEUP_RX)
@@ -372,7 +370,7 @@ static int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp)
 
 int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp)
 {
-	struct list_head *flush_list = this_cpu_ptr(&xskmap_flush_list);
+	struct list_head *flush_list = bpf_net_ctx_get_xskmap_flush_list();
 	int err;
 
 	err = xsk_rcv(xs, xdp);
@@ -387,7 +385,7 @@ int __xsk_map_redirect(struct xdp_sock *xs, struct xdp_buff *xdp)
 
 void __xsk_map_flush(void)
 {
-	struct list_head *flush_list = this_cpu_ptr(&xskmap_flush_list);
+	struct list_head *flush_list = bpf_net_ctx_get_xskmap_flush_list();
 	struct xdp_sock *xs, *tmp;
 
 	list_for_each_entry_safe(xs, tmp, flush_list, flush_node) {
@@ -399,7 +397,7 @@ void __xsk_map_flush(void)
 #ifdef CONFIG_DEBUG_NET
 bool xsk_map_check_flush(void)
 {
-	if (list_empty(this_cpu_ptr(&xskmap_flush_list)))
+	if (list_empty(bpf_net_ctx_get_xskmap_flush_list()))
 		return false;
 	__xsk_map_flush();
 	return true;
@@ -1772,7 +1770,7 @@ static struct pernet_operations xsk_net_ops = {
 
 static int __init xsk_init(void)
 {
-	int err, cpu;
+	int err;
 
 	err = proto_register(&xsk_proto, 0 /* no slab */);
 	if (err)
@@ -1790,8 +1788,6 @@ static int __init xsk_init(void)
 	if (err)
 		goto out_pernet;
 
-	for_each_possible_cpu(cpu)
-		INIT_LIST_HEAD(&per_cpu(xskmap_flush_list, cpu));
 	return 0;
 
 out_pernet: