Merge tag 'net-6.6-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from netfilter and bpf.

  Current release - regressions:

   - bpf: adjust size_index according to the value of KMALLOC_MIN_SIZE

   - netfilter: fix entries val in rule reset audit log

   - eth: stmmac: fix incorrect rxq|txq_stats reference

  Previous releases - regressions:

   - ipv4: fix null-deref in ipv4_link_failure

   - netfilter:
      - fix several GC related issues
      - fix race between IPSET_CMD_CREATE and IPSET_CMD_SWAP

   - eth: team: fix null-ptr-deref when team device type is changed

   - eth: i40e: fix VF VLAN offloading when port VLAN is configured

   - eth: ionic: fix 16bit math issue when PAGE_SIZE >= 64KB

  Previous releases - always broken:

   - core: fix ETH_P_1588 flow dissector

   - mptcp: fix several connection hang-up conditions

   - bpf:
      - avoid deadlock when using queue and stack maps from NMI
      - add override check to kprobe multi link attach

   - hsr: properly parse HSRv1 supervisor frames.

   - eth: igc: fix infinite initialization loop with early XDP redirect

   - eth: octeon_ep: fix tx dma unmap len values in SG

   - eth: hns3: fix GRE checksum offload issue"

* tag 'net-6.6-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (87 commits)
  sfc: handle error pointers returned by rhashtable_lookup_get_insert_fast()
  igc: Expose tx-usecs coalesce setting to user
  octeontx2-pf: Do xdp_do_flush() after redirects.
  bnxt_en: Flush XDP for bnxt_poll_nitroa0()'s NAPI
  net: ena: Flush XDP packets on error.
  net/handshake: Fix memory leak in __sock_create() and sock_alloc_file()
  net: hinic: Fix warning-hinic_set_vlan_fliter() warn: variable dereferenced before check 'hwdev'
  netfilter: ipset: Fix race between IPSET_CMD_CREATE and IPSET_CMD_SWAP
  netfilter: nf_tables: fix memleak when more than 255 elements expired
  netfilter: nf_tables: disable toggling dormant table state more than once
  vxlan: Add missing entries to vxlan_get_size()
  net: rds: Fix possible NULL-pointer dereference
  team: fix null-ptr-deref when team device type is changed
  net: bridge: use DEV_STATS_INC()
  net: hns3: add 5ms delay before clear firmware reset irq source
  net: hns3: fix fail to delete tc flower rules during reset issue
  net: hns3: only enable unicast promisc when mac table full
  net: hns3: fix GRE checksum offload issue
  net: hns3: add cmdq check for vf periodic service task
  net: stmmac: fix incorrect rxq|txq_stats reference
  ...

6 files changed, 142 insertions, 20 deletions

diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 1095bbe29859..8090d7fb11ef 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -8501,7 +8501,7 @@ bool btf_nested_type_is_trusted(struct bpf_verifier_log *log,
 	tname = btf_name_by_offset(btf, walk_type->name_off);
 
 	ret = snprintf(safe_tname, sizeof(safe_tname), "%s%s", tname, suffix);
-	if (ret < 0)
+	if (ret >= sizeof(safe_tname))
 		return false;
 
 	safe_id = btf_find_by_name_kind(btf, safe_tname, BTF_INFO_KIND(walk_type->info));
diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c
index 5b2741aa0d9b..03b3d4492980 100644
--- a/kernel/bpf/cgroup.c
+++ b/kernel/bpf/cgroup.c
@@ -785,7 +785,8 @@ found:
  *                          to descendants
  * @cgrp: The cgroup which descendants to traverse
  * @link: A link for which to replace BPF program
- * @type: Type of attach operation
+ * @new_prog: &struct bpf_prog for the target BPF program with its refcnt
+ *            incremented
  *
  * Must be called with cgroup_mutex held.
  */
@@ -1334,7 +1335,7 @@ int cgroup_bpf_prog_query(const union bpf_attr *attr,
  * __cgroup_bpf_run_filter_skb() - Run a program for packet filtering
  * @sk: The socket sending or receiving traffic
  * @skb: The skb that is being sent or received
- * @type: The type of program to be executed
+ * @atype: The type of program to be executed
  *
  * If no socket is passed, or the socket is not of type INET or INET6,
  * this function does nothing and returns 0.
@@ -1424,7 +1425,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_skb);
 /**
  * __cgroup_bpf_run_filter_sk() - Run a program on a sock
  * @sk: sock structure to manipulate
- * @type: The type of program to be executed
+ * @atype: The type of program to be executed
  *
  * socket is passed is expected to be of type INET or INET6.
  *
@@ -1449,7 +1450,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sk);
  *                                       provided by user sockaddr
  * @sk: sock struct that will use sockaddr
  * @uaddr: sockaddr struct provided by user
- * @type: The type of program to be executed
+ * @atype: The type of program to be executed
  * @t_ctx: Pointer to attach type specific context
  * @flags: Pointer to u32 which contains higher bits of BPF program
  *         return value (OR'ed together).
@@ -1496,7 +1497,7 @@ EXPORT_SYMBOL(__cgroup_bpf_run_filter_sock_addr);
  * @sock_ops: bpf_sock_ops_kern struct to pass to program. Contains
  * sk with connection information (IP addresses, etc.) May not contain
  * cgroup info if it is a req sock.
- * @type: The type of program to be executed
+ * @atype: The type of program to be executed
  *
  * socket passed is expected to be of type INET or INET6.
  *
@@ -1670,7 +1671,7 @@ const struct bpf_verifier_ops cg_dev_verifier_ops = {
  * @ppos: value-result argument: value is position at which read from or write
  *	to sysctl is happening, result is new position if program overrode it,
  *	initial value otherwise
- * @type: type of program to be executed
+ * @atype: type of program to be executed
  *
  * Program is run when sysctl is being accessed, either read or written, and
  * can allow or deny such access.
diff --git a/kernel/bpf/memalloc.c b/kernel/bpf/memalloc.c
index 9c49ae53deaf..cf1941516643 100644
--- a/kernel/bpf/memalloc.c
+++ b/kernel/bpf/memalloc.c
@@ -459,8 +459,7 @@ static void notrace irq_work_raise(struct bpf_mem_cache *c)
  * Typical case will be between 11K and 116K closer to 11K.
  * bpf progs can and should share bpf_mem_cache when possible.
  */
-
-static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
+static void init_refill_work(struct bpf_mem_cache *c)
 {
 	init_irq_work(&c->refill_work, bpf_mem_refill);
 	if (c->unit_size <= 256) {
@@ -476,7 +475,10 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
 		c->high_watermark = max(96 * 256 / c->unit_size, 3);
 	}
 	c->batch = max((c->high_watermark - c->low_watermark) / 4 * 3, 1);
+}
 
+static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
+{
 	/* To avoid consuming memory assume that 1st run of bpf
 	 * prog won't be doing more than 4 map_update_elem from
 	 * irq disabled region
@@ -484,6 +486,31 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
 	alloc_bulk(c, c->unit_size <= 256 ? 4 : 1, cpu_to_node(cpu), false);
 }
 
+static int check_obj_size(struct bpf_mem_cache *c, unsigned int idx)
+{
+	struct llist_node *first;
+	unsigned int obj_size;
+
+	/* For per-cpu allocator, the size of free objects in free list doesn't
+	 * match with unit_size and now there is no way to get the size of
+	 * per-cpu pointer saved in free object, so just skip the checking.
+	 */
+	if (c->percpu_size)
+		return 0;
+
+	first = c->free_llist.first;
+	if (!first)
+		return 0;
+
+	obj_size = ksize(first);
+	if (obj_size != c->unit_size) {
+		WARN_ONCE(1, "bpf_mem_cache[%u]: unexpected object size %u, expect %u\n",
+			  idx, obj_size, c->unit_size);
+		return -EINVAL;
+	}
+	return 0;
+}
+
 /* When size != 0 bpf_mem_cache for each cpu.
  * This is typical bpf hash map use case when all elements have equal size.
  *
@@ -494,10 +521,10 @@ static void prefill_mem_cache(struct bpf_mem_cache *c, int cpu)
 int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 {
 	static u16 sizes[NUM_CACHES] = {96, 192, 16, 32, 64, 128, 256, 512, 1024, 2048, 4096};
+	int cpu, i, err, unit_size, percpu_size = 0;
 	struct bpf_mem_caches *cc, __percpu *pcc;
 	struct bpf_mem_cache *c, __percpu *pc;
 	struct obj_cgroup *objcg = NULL;
-	int cpu, i, unit_size, percpu_size = 0;
 
 	if (size) {
 		pc = __alloc_percpu_gfp(sizeof(*pc), 8, GFP_KERNEL);
@@ -521,6 +548,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 			c->objcg = objcg;
 			c->percpu_size = percpu_size;
 			c->tgt = c;
+			init_refill_work(c);
 			prefill_mem_cache(c, cpu);
 		}
 		ma->cache = pc;
@@ -534,6 +562,7 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 	pcc = __alloc_percpu_gfp(sizeof(*cc), 8, GFP_KERNEL);
 	if (!pcc)
 		return -ENOMEM;
+	err = 0;
 #ifdef CONFIG_MEMCG_KMEM
 	objcg = get_obj_cgroup_from_current();
 #endif
@@ -544,11 +573,30 @@ int bpf_mem_alloc_init(struct bpf_mem_alloc *ma, int size, bool percpu)
 			c->unit_size = sizes[i];
 			c->objcg = objcg;
 			c->tgt = c;
+
+			init_refill_work(c);
+			/* Another bpf_mem_cache will be used when allocating
+			 * c->unit_size in bpf_mem_alloc(), so doesn't prefill
+			 * for the bpf_mem_cache because these free objects will
+			 * never be used.
+			 */
+			if (i != bpf_mem_cache_idx(c->unit_size))
+				continue;
 			prefill_mem_cache(c, cpu);
+			err = check_obj_size(c, i);
+			if (err)
+				goto out;
 		}
 	}
+
+out:
 	ma->caches = pcc;
-	return 0;
+	/* refill_work is either zeroed or initialized, so it is safe to
+	 * call irq_work_sync().
+	 */
+	if (err)
+		bpf_mem_alloc_destroy(ma);
+	return err;
 }
 
 static void drain_mem_cache(struct bpf_mem_cache *c)
@@ -916,3 +964,41 @@ void notrace *bpf_mem_cache_alloc_flags(struct bpf_mem_alloc *ma, gfp_t flags)
 
 	return !ret ? NULL : ret + LLIST_NODE_SZ;
 }
+
+/* Most of the logic is taken from setup_kmalloc_cache_index_table() */
+static __init int bpf_mem_cache_adjust_size(void)
+{
+	unsigned int size, index;
+
+	/* Normally KMALLOC_MIN_SIZE is 8-bytes, but it can be
+	 * up-to 256-bytes.
+	 */
+	size = KMALLOC_MIN_SIZE;
+	if (size <= 192)
+		index = size_index[(size - 1) / 8];
+	else
+		index = fls(size - 1) - 1;
+	for (size = 8; size < KMALLOC_MIN_SIZE && size <= 192; size += 8)
+		size_index[(size - 1) / 8] = index;
+
+	/* The minimal alignment is 64-bytes, so disable 96-bytes cache and
+	 * use 128-bytes cache instead.
+	 */
+	if (KMALLOC_MIN_SIZE >= 64) {
+		index = size_index[(128 - 1) / 8];
+		for (size = 64 + 8; size <= 96; size += 8)
+			size_index[(size - 1) / 8] = index;
+	}
+
+	/* The minimal alignment is 128-bytes, so disable 192-bytes cache and
+	 * use 256-bytes cache instead.
+	 */
+	if (KMALLOC_MIN_SIZE >= 128) {
+		index = fls(256 - 1) - 1;
+		for (size = 128 + 8; size <= 192; size += 8)
+			size_index[(size - 1) / 8] = index;
+	}
+
+	return 0;
+}
+subsys_initcall(bpf_mem_cache_adjust_size);
diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c
index 3e4f2ec1af06..87d6693d8233 100644
--- a/kernel/bpf/offload.c
+++ b/kernel/bpf/offload.c
@@ -199,12 +199,14 @@ static int __bpf_prog_dev_bound_init(struct bpf_prog *prog, struct net_device *n
 	offload->netdev = netdev;
 
 	ondev = bpf_offload_find_netdev(offload->netdev);
+	/* When program is offloaded require presence of "true"
+	 * bpf_offload_netdev, avoid the one created for !ondev case below.
+	 */
+	if (bpf_prog_is_offloaded(prog->aux) && (!ondev || !ondev->offdev)) {
+		err = -EINVAL;
+		goto err_free;
+	}
 	if (!ondev) {
-		if (bpf_prog_is_offloaded(prog->aux)) {
-			err = -EINVAL;
-			goto err_free;
-		}
-
 		/* When only binding to the device, explicitly
 		 * create an entry in the hashtable.
 		 */
diff --git a/kernel/bpf/queue_stack_maps.c b/kernel/bpf/queue_stack_maps.c
index 8d2ddcb7566b..d869f51ea93a 100644
--- a/kernel/bpf/queue_stack_maps.c
+++ b/kernel/bpf/queue_stack_maps.c
@@ -98,7 +98,12 @@ static long __queue_map_get(struct bpf_map *map, void *value, bool delete)
 	int err = 0;
 	void *ptr;
 
-	raw_spin_lock_irqsave(&qs->lock, flags);
+	if (in_nmi()) {
+		if (!raw_spin_trylock_irqsave(&qs->lock, flags))
+			return -EBUSY;
+	} else {
+		raw_spin_lock_irqsave(&qs->lock, flags);
+	}
 
 	if (queue_stack_map_is_empty(qs)) {
 		memset(value, 0, qs->map.value_size);
@@ -128,7 +133,12 @@ static long __stack_map_get(struct bpf_map *map, void *value, bool delete)
 	void *ptr;
 	u32 index;
 
-	raw_spin_lock_irqsave(&qs->lock, flags);
+	if (in_nmi()) {
+		if (!raw_spin_trylock_irqsave(&qs->lock, flags))
+			return -EBUSY;
+	} else {
+		raw_spin_lock_irqsave(&qs->lock, flags);
+	}
 
 	if (queue_stack_map_is_empty(qs)) {
 		memset(value, 0, qs->map.value_size);
@@ -193,7 +203,12 @@ static long queue_stack_map_push_elem(struct bpf_map *map, void *value,
 	if (flags & BPF_NOEXIST || flags > BPF_EXIST)
 		return -EINVAL;
 
-	raw_spin_lock_irqsave(&qs->lock, irq_flags);
+	if (in_nmi()) {
+		if (!raw_spin_trylock_irqsave(&qs->lock, irq_flags))
+			return -EBUSY;
+	} else {
+		raw_spin_lock_irqsave(&qs->lock, irq_flags);
+	}
 
 	if (queue_stack_map_is_full(qs)) {
 		if (!replace) {
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index a7264b2c17ad..868008f56fec 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2853,6 +2853,17 @@ static int get_modules_for_addrs(struct module ***mods, unsigned long *addrs, u3
 	return arr.mods_cnt;
 }
 
+static int addrs_check_error_injection_list(unsigned long *addrs, u32 cnt)
+{
+	u32 i;
+
+	for (i = 0; i < cnt; i++) {
+		if (!within_error_injection_list(addrs[i]))
+			return -EINVAL;
+	}
+	return 0;
+}
+
 int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *prog)
 {
 	struct bpf_kprobe_multi_link *link = NULL;
@@ -2930,6 +2941,11 @@ int bpf_kprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 			goto error;
 	}
 
+	if (prog->kprobe_override && addrs_check_error_injection_list(addrs, cnt)) {
+		err = -EINVAL;
+		goto error;
+	}
+
 	link = kzalloc(sizeof(*link), GFP_KERNEL);
 	if (!link) {
 		err = -ENOMEM;
@@ -3207,8 +3223,10 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
 		rcu_read_lock();
 		task = get_pid_task(find_vpid(pid), PIDTYPE_PID);
 		rcu_read_unlock();
-		if (!task)
+		if (!task) {
+			err = -ESRCH;
 			goto error_path_put;
+		}
 	}
 
 	err = -ENOMEM;