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

Alexei Starovoitov says:

====================
pull-request: bpf-next 2020-12-03

The main changes are:

1) Support BTF in kernel modules, from Andrii.

2) Introduce preferred busy-polling, from Björn.

3) bpf_ima_inode_hash() and bpf_bprm_opts_set() helpers, from KP Singh.

4) Memcg-based memory accounting for bpf objects, from Roman.

5) Allow bpf_{s,g}etsockopt from cgroup bind{4,6} hooks, from Stanislav.

* https://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next: (118 commits)
  selftests/bpf: Fix invalid use of strncat in test_sockmap
  libbpf: Use memcpy instead of strncpy to please GCC
  selftests/bpf: Add fentry/fexit/fmod_ret selftest for kernel module
  selftests/bpf: Add tp_btf CO-RE reloc test for modules
  libbpf: Support attachment of BPF tracing programs to kernel modules
  libbpf: Factor out low-level BPF program loading helper
  bpf: Allow to specify kernel module BTFs when attaching BPF programs
  bpf: Remove hard-coded btf_vmlinux assumption from BPF verifier
  selftests/bpf: Add CO-RE relocs selftest relying on kernel module BTF
  selftests/bpf: Add support for marking sub-tests as skipped
  selftests/bpf: Add bpf_testmod kernel module for testing
  libbpf: Add kernel module BTF support for CO-RE relocations
  libbpf: Refactor CO-RE relocs to not assume a single BTF object
  libbpf: Add internal helper to load BTF data by FD
  bpf: Keep module's btf_data_size intact after load
  bpf: Fix bpf_put_raw_tracepoint()'s use of __module_address()
  selftests/bpf: Add Userspace tests for TCP_WINDOW_CLAMP
  bpf: Adds support for setting window clamp
  samples/bpf: Fix spelling mistake "recieving" -> "receiving"
  bpf: Fix cold build of test_progs-no_alu32
  ...
====================

Link: https://lore.kernel.org/r/20201204021936.85653-1-alexei.starovoitov@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

6 files changed, 109 insertions, 55 deletions

diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c
index 359908a7d3c1..a32037daa933 100644
--- a/net/core/bpf_sk_storage.c
+++ b/net/core/bpf_sk_storage.c
@@ -415,7 +415,7 @@ static bool bpf_sk_storage_tracing_allowed(const struct bpf_prog *prog)
 BPF_CALL_4(bpf_sk_storage_get_tracing, struct bpf_map *, map, struct sock *, sk,
 	   void *, value, u64, flags)
 {
-	if (!in_serving_softirq() && !in_task())
+	if (in_irq() || in_nmi())
 		return (unsigned long)NULL;
 
 	return (unsigned long)____bpf_sk_storage_get(map, sk, value, flags);
@@ -424,7 +424,7 @@ BPF_CALL_4(bpf_sk_storage_get_tracing, struct bpf_map *, map, struct sock *, sk,
 BPF_CALL_2(bpf_sk_storage_delete_tracing, struct bpf_map *, map,
 	   struct sock *, sk)
 {
-	if (!in_serving_softirq() && !in_task())
+	if (in_irq() || in_nmi())
 		return -EPERM;
 
 	return ____bpf_sk_storage_delete(map, sk);
diff --git a/net/core/dev.c b/net/core/dev.c
index e3f998d5c15c..ce8fea2e2788 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -6448,7 +6448,8 @@ bool napi_complete_done(struct napi_struct *n, int work_done)
 
 		WARN_ON_ONCE(!(val & NAPIF_STATE_SCHED));
 
-		new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED);
+		new = val & ~(NAPIF_STATE_MISSED | NAPIF_STATE_SCHED |
+			      NAPIF_STATE_PREFER_BUSY_POLL);
 
 		/* If STATE_MISSED was set, leave STATE_SCHED set,
 		 * because we will call napi->poll() one more time.
@@ -6485,10 +6486,30 @@ static struct napi_struct *napi_by_id(unsigned int napi_id)
 
 #if defined(CONFIG_NET_RX_BUSY_POLL)
 
-#define BUSY_POLL_BUDGET 8
+static void __busy_poll_stop(struct napi_struct *napi, bool skip_schedule)
+{
+	if (!skip_schedule) {
+		gro_normal_list(napi);
+		__napi_schedule(napi);
+		return;
+	}
+
+	if (napi->gro_bitmask) {
+		/* flush too old packets
+		 * If HZ < 1000, flush all packets.
+		 */
+		napi_gro_flush(napi, HZ >= 1000);
+	}
 
-static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock)
+	gro_normal_list(napi);
+	clear_bit(NAPI_STATE_SCHED, &napi->state);
+}
+
+static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock, bool prefer_busy_poll,
+			   u16 budget)
 {
+	bool skip_schedule = false;
+	unsigned long timeout;
 	int rc;
 
 	/* Busy polling means there is a high chance device driver hard irq
@@ -6505,29 +6526,33 @@ static void busy_poll_stop(struct napi_struct *napi, void *have_poll_lock)
 
 	local_bh_disable();
 
+	if (prefer_busy_poll) {
+		napi->defer_hard_irqs_count = READ_ONCE(napi->dev->napi_defer_hard_irqs);
+		timeout = READ_ONCE(napi->dev->gro_flush_timeout);
+		if (napi->defer_hard_irqs_count && timeout) {
+			hrtimer_start(&napi->timer, ns_to_ktime(timeout), HRTIMER_MODE_REL_PINNED);
+			skip_schedule = true;
+		}
+	}
+
 	/* All we really want here is to re-enable device interrupts.
 	 * Ideally, a new ndo_busy_poll_stop() could avoid another round.
 	 */
-	rc = napi->poll(napi, BUSY_POLL_BUDGET);
+	rc = napi->poll(napi, budget);
 	/* We can't gro_normal_list() here, because napi->poll() might have
 	 * rearmed the napi (napi_complete_done()) in which case it could
 	 * already be running on another CPU.
 	 */
-	trace_napi_poll(napi, rc, BUSY_POLL_BUDGET);
+	trace_napi_poll(napi, rc, budget);
 	netpoll_poll_unlock(have_poll_lock);
-	if (rc == BUSY_POLL_BUDGET) {
-		/* As the whole budget was spent, we still own the napi so can
-		 * safely handle the rx_list.
-		 */
-		gro_normal_list(napi);
-		__napi_schedule(napi);
-	}
+	if (rc == budget)
+		__busy_poll_stop(napi, skip_schedule);
 	local_bh_enable();
 }
 
 void napi_busy_loop(unsigned int napi_id,
 		    bool (*loop_end)(void *, unsigned long),
-		    void *loop_end_arg)
+		    void *loop_end_arg, bool prefer_busy_poll, u16 budget)
 {
 	unsigned long start_time = loop_end ? busy_loop_current_time() : 0;
 	int (*napi_poll)(struct napi_struct *napi, int budget);
@@ -6555,17 +6580,23 @@ restart:
 			 * we avoid dirtying napi->state as much as we can.
 			 */
 			if (val & (NAPIF_STATE_DISABLE | NAPIF_STATE_SCHED |
-				   NAPIF_STATE_IN_BUSY_POLL))
+				   NAPIF_STATE_IN_BUSY_POLL)) {
+				if (prefer_busy_poll)
+					set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
 				goto count;
+			}
 			if (cmpxchg(&napi->state, val,
 				    val | NAPIF_STATE_IN_BUSY_POLL |
-					  NAPIF_STATE_SCHED) != val)
+					  NAPIF_STATE_SCHED) != val) {
+				if (prefer_busy_poll)
+					set_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
 				goto count;
+			}
 			have_poll_lock = netpoll_poll_lock(napi);
 			napi_poll = napi->poll;
 		}
-		work = napi_poll(napi, BUSY_POLL_BUDGET);
-		trace_napi_poll(napi, work, BUSY_POLL_BUDGET);
+		work = napi_poll(napi, budget);
+		trace_napi_poll(napi, work, budget);
 		gro_normal_list(napi);
 count:
 		if (work > 0)
@@ -6578,7 +6609,7 @@ count:
 
 		if (unlikely(need_resched())) {
 			if (napi_poll)
-				busy_poll_stop(napi, have_poll_lock);
+				busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
 			preempt_enable();
 			rcu_read_unlock();
 			cond_resched();
@@ -6589,7 +6620,7 @@ count:
 		cpu_relax();
 	}
 	if (napi_poll)
-		busy_poll_stop(napi, have_poll_lock);
+		busy_poll_stop(napi, have_poll_lock, prefer_busy_poll, budget);
 	preempt_enable();
 out:
 	rcu_read_unlock();
@@ -6640,8 +6671,10 @@ static enum hrtimer_restart napi_watchdog(struct hrtimer *timer)
 	 * NAPI_STATE_MISSED, since we do not react to a device IRQ.
 	 */
 	if (!napi_disable_pending(napi) &&
-	    !test_and_set_bit(NAPI_STATE_SCHED, &napi->state))
+	    !test_and_set_bit(NAPI_STATE_SCHED, &napi->state)) {
+		clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &napi->state);
 		__napi_schedule_irqoff(napi);
+	}
 
 	return HRTIMER_NORESTART;
 }
@@ -6699,6 +6732,7 @@ void napi_disable(struct napi_struct *n)
 
 	hrtimer_cancel(&n->timer);
 
+	clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state);
 	clear_bit(NAPI_STATE_DISABLE, &n->state);
 }
 EXPORT_SYMBOL(napi_disable);
@@ -6771,6 +6805,19 @@ static int napi_poll(struct napi_struct *n, struct list_head *repoll)
 		goto out_unlock;
 	}
 
+	/* The NAPI context has more processing work, but busy-polling
+	 * is preferred. Exit early.
+	 */
+	if (napi_prefer_busy_poll(n)) {
+		if (napi_complete_done(n, work)) {
+			/* If timeout is not set, we need to make sure
+			 * that the NAPI is re-scheduled.
+			 */
+			napi_schedule(n);
+		}
+		goto out_unlock;
+	}
+
 	if (n->gro_bitmask) {
 		/* flush too old packets
 		 * If HZ < 1000, flush all packets.
@@ -9753,7 +9800,7 @@ static int netif_alloc_rx_queues(struct net_device *dev)
 		rx[i].dev = dev;
 
 		/* XDP RX-queue setup */
-		err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i);
+		err = xdp_rxq_info_reg(&rx[i].xdp_rxq, dev, i, 0);
 		if (err < 0)
 			goto err_rxq_info;
 	}
diff --git a/net/core/filter.c b/net/core/filter.c
index 2ca5eecebacf..77001a35768f 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4910,6 +4910,9 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname,
 				tp->notsent_lowat = val;
 				sk->sk_write_space(sk);
 				break;
+			case TCP_WINDOW_CLAMP:
+				ret = tcp_set_window_clamp(sk, val);
+				break;
 			default:
 				ret = -EINVAL;
 			}
@@ -6995,6 +6998,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_sk_storage_delete_proto;
 	case BPF_FUNC_setsockopt:
 		switch (prog->expected_attach_type) {
+		case BPF_CGROUP_INET4_BIND:
+		case BPF_CGROUP_INET6_BIND:
 		case BPF_CGROUP_INET4_CONNECT:
 		case BPF_CGROUP_INET6_CONNECT:
 			return &bpf_sock_addr_setsockopt_proto;
@@ -7003,6 +7008,8 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		}
 	case BPF_FUNC_getsockopt:
 		switch (prog->expected_attach_type) {
+		case BPF_CGROUP_INET4_BIND:
+		case BPF_CGROUP_INET6_BIND:
 		case BPF_CGROUP_INET4_CONNECT:
 		case BPF_CGROUP_INET6_CONNECT:
 			return &bpf_sock_addr_getsockopt_proto;
diff --git a/net/core/sock.c b/net/core/sock.c
index f0f096852876..4fd7e785f177 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1159,6 +1159,22 @@ set_sndbuf:
 				sk->sk_ll_usec = val;
 		}
 		break;
+	case SO_PREFER_BUSY_POLL:
+		if (valbool && !capable(CAP_NET_ADMIN))
+			ret = -EPERM;
+		else
+			WRITE_ONCE(sk->sk_prefer_busy_poll, valbool);
+		break;
+	case SO_BUSY_POLL_BUDGET:
+		if (val > READ_ONCE(sk->sk_busy_poll_budget) && !capable(CAP_NET_ADMIN)) {
+			ret = -EPERM;
+		} else {
+			if (val < 0 || val > U16_MAX)
+				ret = -EINVAL;
+			else
+				WRITE_ONCE(sk->sk_busy_poll_budget, val);
+		}
+		break;
 #endif
 
 	case SO_MAX_PACING_RATE:
@@ -1523,6 +1539,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
 	case SO_BUSY_POLL:
 		v.val = sk->sk_ll_usec;
 		break;
+	case SO_PREFER_BUSY_POLL:
+		v.val = READ_ONCE(sk->sk_prefer_busy_poll);
+		break;
 #endif
 
 	case SO_MAX_PACING_RATE:
diff --git a/net/core/sock_map.c b/net/core/sock_map.c
index ddc899e83313..64b5ec14ff50 100644
--- a/net/core/sock_map.c
+++ b/net/core/sock_map.c
@@ -27,8 +27,6 @@ struct bpf_stab {
 static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 {
 	struct bpf_stab *stab;
-	u64 cost;
-	int err;
 
 	if (!capable(CAP_NET_ADMIN))
 		return ERR_PTR(-EPERM);
@@ -39,29 +37,22 @@ static struct bpf_map *sock_map_alloc(union bpf_attr *attr)
 	    attr->map_flags & ~SOCK_CREATE_FLAG_MASK)
 		return ERR_PTR(-EINVAL);
 
-	stab = kzalloc(sizeof(*stab), GFP_USER);
+	stab = kzalloc(sizeof(*stab), GFP_USER | __GFP_ACCOUNT);
 	if (!stab)
 		return ERR_PTR(-ENOMEM);
 
 	bpf_map_init_from_attr(&stab->map, attr);
 	raw_spin_lock_init(&stab->lock);
 
-	/* Make sure page count doesn't overflow. */
-	cost = (u64) stab->map.max_entries * sizeof(struct sock *);
-	err = bpf_map_charge_init(&stab->map.memory, cost);
-	if (err)
-		goto free_stab;
-
 	stab->sks = bpf_map_area_alloc(stab->map.max_entries *
 				       sizeof(struct sock *),
 				       stab->map.numa_node);
-	if (stab->sks)
-		return &stab->map;
-	err = -ENOMEM;
-	bpf_map_charge_finish(&stab->map.memory);
-free_stab:
-	kfree(stab);
-	return ERR_PTR(err);
+	if (!stab->sks) {
+		kfree(stab);
+		return ERR_PTR(-ENOMEM);
+	}
+
+	return &stab->map;
 }
 
 int sock_map_get_from_fd(const union bpf_attr *attr, struct bpf_prog *prog)
@@ -975,8 +966,9 @@ static struct bpf_shtab_elem *sock_hash_alloc_elem(struct bpf_shtab *htab,
 		}
 	}
 
-	new = kmalloc_node(htab->elem_size, GFP_ATOMIC | __GFP_NOWARN,
-			   htab->map.numa_node);
+	new = bpf_map_kmalloc_node(&htab->map, htab->elem_size,
+				   GFP_ATOMIC | __GFP_NOWARN,
+				   htab->map.numa_node);
 	if (!new) {
 		atomic_dec(&htab->count);
 		return ERR_PTR(-ENOMEM);
@@ -1103,7 +1095,6 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr)
 {
 	struct bpf_shtab *htab;
 	int i, err;
-	u64 cost;
 
 	if (!capable(CAP_NET_ADMIN))
 		return ERR_PTR(-EPERM);
@@ -1116,7 +1107,7 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr)
 	if (attr->key_size > MAX_BPF_STACK)
 		return ERR_PTR(-E2BIG);
 
-	htab = kzalloc(sizeof(*htab), GFP_USER);
+	htab = kzalloc(sizeof(*htab), GFP_USER | __GFP_ACCOUNT);
 	if (!htab)
 		return ERR_PTR(-ENOMEM);
 
@@ -1131,21 +1122,10 @@ static struct bpf_map *sock_hash_alloc(union bpf_attr *attr)
 		goto free_htab;
 	}
 
-	cost = (u64) htab->buckets_num * sizeof(struct bpf_shtab_bucket) +
-	       (u64) htab->elem_size * htab->map.max_entries;
-	if (cost >= U32_MAX - PAGE_SIZE) {
-		err = -EINVAL;
-		goto free_htab;
-	}
-	err = bpf_map_charge_init(&htab->map.memory, cost);
-	if (err)
-		goto free_htab;
-
 	htab->buckets = bpf_map_area_alloc(htab->buckets_num *
 					   sizeof(struct bpf_shtab_bucket),
 					   htab->map.numa_node);
 	if (!htab->buckets) {
-		bpf_map_charge_finish(&htab->map.memory);
 		err = -ENOMEM;
 		goto free_htab;
 	}
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 3d330ebda893..17ffd33c6b18 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -158,7 +158,7 @@ static void xdp_rxq_info_init(struct xdp_rxq_info *xdp_rxq)
 
 /* Returns 0 on success, negative on failure */
 int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
-		     struct net_device *dev, u32 queue_index)
+		     struct net_device *dev, u32 queue_index, unsigned int napi_id)
 {
 	if (xdp_rxq->reg_state == REG_STATE_UNUSED) {
 		WARN(1, "Driver promised not to register this");
@@ -179,6 +179,7 @@ int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq,
 	xdp_rxq_info_init(xdp_rxq);
 	xdp_rxq->dev = dev;
 	xdp_rxq->queue_index = queue_index;
+	xdp_rxq->napi_id = napi_id;
 
 	xdp_rxq->reg_state = REG_STATE_REGISTERED;
 	return 0;