net: Reference bpf_redirect_info via task_struct on PREEMPT_RT.

The XDP redirect process is two staged:
- bpf_prog_run_xdp() is invoked to run a eBPF program which inspects the
  packet and makes decisions. While doing that, the per-CPU variable
  bpf_redirect_info is used.

- Afterwards xdp_do_redirect() is invoked and accesses bpf_redirect_info
  and it may also access other per-CPU variables like xskmap_flush_list.

At the very end of the NAPI callback, xdp_do_flush() is invoked which
does not access bpf_redirect_info but will touch the individual per-CPU
lists.

The per-CPU variables are only used in the NAPI callback hence disabling
bottom halves is the only protection mechanism. Users from preemptible
context (like cpu_map_kthread_run()) explicitly disable bottom halves
for protections reasons.
Without locking in local_bh_disable() on PREEMPT_RT this data structure
requires explicit locking.

PREEMPT_RT has forced-threaded interrupts enabled and every
NAPI-callback runs in a thread. If each thread has its own data
structure then locking can be avoided.

Create a struct bpf_net_context which contains struct bpf_redirect_info.
Define the variable on stack, use bpf_net_ctx_set() to save a pointer to
it, bpf_net_ctx_clear() removes it again.
The bpf_net_ctx_set() may nest. For instance a function can be used from
within NET_RX_SOFTIRQ/ net_rx_action which uses bpf_net_ctx_set() and
NET_TX_SOFTIRQ which does not. Therefore only the first invocations
updates the pointer.
Use bpf_net_ctx_get_ri() as a wrapper to retrieve the current struct
bpf_redirect_info. The returned data structure is zero initialized to
ensure nothing is leaked from stack. This is done on first usage of the
struct. bpf_net_ctx_set() sets bpf_redirect_info::kern_flags to 0 to
note that initialisation is required. First invocation of
bpf_net_ctx_get_ri() will memset() the data structure and update
bpf_redirect_info::kern_flags.
bpf_redirect_info::nh is excluded from memset because it is only used
once BPF_F_NEIGH is set which also sets the nh member. The kern_flags is
moved past nh to exclude it from memset.

The pointer to bpf_net_context is saved task's task_struct. Using
always the bpf_net_context approach has the advantage that there is
almost zero differences between PREEMPT_RT and non-PREEMPT_RT builds.

Cc: Andrii Nakryiko <[email protected]>
Cc: Eduard Zingerman <[email protected]>
Cc: Hao Luo <[email protected]>
Cc: Jiri Olsa <[email protected]>
Cc: John Fastabend <[email protected]>
Cc: KP Singh <[email protected]>
Cc: Martin KaFai Lau <[email protected]>
Cc: Song Liu <[email protected]>
Cc: Stanislav Fomichev <[email protected]>
Cc: Yonghong Song <[email protected]>
Acked-by: Alexei Starovoitov <[email protected]>
Acked-by: Jesper Dangaard Brouer <[email protected]>
Reviewed-by: Toke Høiland-Jørgensen <[email protected]>
Signed-off-by: Sebastian Andrzej Siewior <[email protected]>
Link: https://patch.msgid.link/[email protected]
Signed-off-by: Jakub Kicinski <[email protected]>

Author: Sebastian Andrzej Siewior

include/linux/filter.h

@@ -733,21 +733,59 @@ 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)
+
 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;
+};
 
-/* 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;
+}
 
 /* Compute the linear packet data range [data, data_end) which
  * will be accessed by various program types (cls_bpf, act_bpf,
@@ -1018,25 +1056,23 @@ 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 +1628,7 @@ 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/sched.h

@@ -54,6 +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;
@@ -1509,6 +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;

kernel/bpf/cpumap.c

@@ -240,12 +240,14 @@ 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 +257,7 @@ 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;

kernel/bpf/devmap.c

@@ -196,7 +196,14 @@ 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. */

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);

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/core/dev.c

@@ -4045,10 +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;
@@ -4077,10 +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:
@@ -4090,8 +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;
 }
@@ -4101,11 +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.
 	 */
@@ -4121,10 +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:
@@ -4134,8 +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;
 }
@@ -6325,6 +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;
@@ -6342,6 +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);
@@ -6364,6 +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();
 }
 
@@ -6373,6 +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;
 
@@ -6391,6 +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);
 
@@ -6421,6 +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))
@@ -6848,6 +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;
 
@@ -6856,6 +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;
 
@@ -6871,6 +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)
@@ -6896,10 +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();
@@ -6952,7 +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 {