net/sched: account classifier filter allocations to memcg

Allocations in the tc classifier *_change() paths (filter objects,
per-CPU counters, and per-filter aux data) use plain GFP_KERNEL without
__GFP_ACCOUNT, allowing unprivileged users to pin kernel memory outside
memcg charging. The shared tcf_exts_init_ex() action array allocation in
cls_api.c was also uncharged; this patch closes it along with the
per-classifier filter-object/percpu/aux allocations that remain
unaccounted.

Add GFP_KERNEL_ACCOUNT to:
- the shared tcf_exts_init_ex() action array (cls_api.c), common to every
  filter of every classifier (32 pointers, 256 bytes);
- the filter-object, per-CPU-counter, and per-filter aux allocations in
  cls_basic, cls_bpf, cls_cgroup, cls_flow, cls_flower, cls_fw,
  cls_matchall, cls_route and cls_u32;
- the u32_init_knode() replace-path knode allocation (cls_u32.c), which
  allocates the same struct tc_u_knode + sel.keys on every replace of an
  existing knode and was missed by the create-path-only conversion.

Also fix the cls_basic error path: basic_change() inserts fnew into the
IDR before allocating the per-CPU counter. If alloc_percpu() fails the
errout path kfree'd fnew without idr_remove, leaving a dangling pointer
in the IDR. With GFP_KERNEL_ACCOUNT the percpu alloc becomes failable
on demand (memcg at memory.max), making the dead path attacker-reachable
and burning the handle permanently. Add the idr_remove on the percpu
failure path, matching the basic_set_parms failure-path pattern.

Note: vega@nebusec.ai provided a poc for basic_cls, but it was easy to
extend to the other classifiers.

Conditions to recreate the bug:
- CONFIG_NET_SCHED, CONFIG_NET_CLS_* (the classifier being used),
  CONFIG_NET_CLS_ACT, CONFIG_MEMCG, CONFIG_USER_NS, CONFIG_NET_NS.
- Unprivileged user in a fresh user+network namespace (unshare -Urn),
  or root with CAP_NET_ADMIN.
- Create a large number of tc filters (e.g. tc filter add dev lo
  ingress ... <classifier> ...) while watching a memcg-limited cgroup:
  system slab grows far faster than memory.current, pinning kernel
  memory outside memcg charging.

Fixes: 0da974f4f3 ("[NET]: Conversions from kmalloc+memset to k(z|c)alloc.")
Reported-by: vega@nebusec.ai
Signed-off-by: Jamal Hadi Salim <jhs@mojatatu.com>
Reviewed-by: Breno Leitao <leitao@debian.org>
Link: https://patch.msgid.link/20260819143733.57538-1-jhs@mojatatu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

net/sched/cls_api.c

@@ -3372,7 +3372,8 @@ int tcf_exts_init_ex(struct tcf_exts *exts, struct net *net, int action,
 	 * This reference might be taken later from tcf_exts_get_net().
 	 */
 	exts->net = net;
-	exts->actions = kzalloc_objs(struct tc_action *, TCA_ACT_MAX_PRIO);
+	exts->actions = kzalloc_objs(struct tc_action *, TCA_ACT_MAX_PRIO,
+				     GFP_KERNEL_ACCOUNT);
 	if (!exts->actions)
 		return -ENOMEM;
 #endif

net/sched/cls_basic.c

@@ -193,7 +193,7 @@ static int basic_change(struct net *net, struct sk_buff *in_skb,
 			return -EINVAL;
 	}
 
-	fnew = kzalloc_obj(*fnew);
+	fnew = kzalloc_obj(*fnew, GFP_KERNEL_ACCOUNT);
 	if (!fnew)
 		return -ENOBUFS;
 
@@ -212,9 +212,11 @@ static int basic_change(struct net *net, struct sk_buff *in_skb,
 	if (err)
 		goto errout;
 	fnew->handle = handle;
-	fnew->pf = alloc_percpu(struct tc_basic_pcnt);
+	fnew->pf = alloc_percpu_gfp(struct tc_basic_pcnt, GFP_KERNEL_ACCOUNT);
 	if (!fnew->pf) {
 		err = -ENOMEM;
+		if (!fold)
+			idr_remove(&head->handle_idr, fnew->handle);
 		goto errout;
 	}
 

net/sched/cls_bpf.c

@@ -352,7 +352,7 @@ static int cls_bpf_prog_from_ops(struct nlattr **tb, struct cls_bpf_prog *prog)
 	if (bpf_size != nla_len(tb[TCA_BPF_OPS]))
 		return -EINVAL;
 
-	bpf_ops = kmemdup(nla_data(tb[TCA_BPF_OPS]), bpf_size, GFP_KERNEL);
+	bpf_ops = kmemdup(nla_data(tb[TCA_BPF_OPS]), bpf_size, GFP_KERNEL_ACCOUNT);
 	if (bpf_ops == NULL)
 		return -ENOMEM;
 
@@ -403,7 +403,7 @@ static int cls_bpf_prog_from_efd(struct nlattr **tb, struct cls_bpf_prog *prog,
 	}
 
 	if (tb[TCA_BPF_NAME]) {
-		name = nla_memdup(tb[TCA_BPF_NAME], GFP_KERNEL);
+		name = nla_memdup(tb[TCA_BPF_NAME], GFP_KERNEL_ACCOUNT);
 		if (!name) {
 			bpf_prog_put(fp);
 			return -ENOMEM;
@@ -443,7 +443,7 @@ static int cls_bpf_change(struct net *net, struct sk_buff *in_skb,
 	if (ret < 0)
 		return ret;
 
-	prog = kzalloc_obj(*prog);
+	prog = kzalloc_obj(*prog, GFP_KERNEL_ACCOUNT);
 	if (!prog)
 		return -ENOBUFS;
 

net/sched/cls_cgroup.c

@@ -95,7 +95,7 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb,
 	if (head && handle != head->handle)
 		return -ENOENT;
 
-	new = kzalloc_obj(*head);
+	new = kzalloc_obj(*head, GFP_KERNEL_ACCOUNT);
 	if (!new)
 		return -ENOBUFS;
 

net/sched/cls_flow.c

@@ -438,7 +438,7 @@ static int flow_change(struct net *net, struct sk_buff *in_skb,
 			return -EOPNOTSUPP;
 	}
 
-	fnew = kzalloc_obj(*fnew);
+	fnew = kzalloc_obj(*fnew, GFP_KERNEL_ACCOUNT);
 	if (!fnew)
 		return -ENOBUFS;
 

net/sched/cls_flower.c

@@ -2233,7 +2233,7 @@ static struct fl_flow_mask *fl_create_new_mask(struct cls_fl_head *head,
 	struct fl_flow_mask *newmask;
 	int err;
 
-	newmask = kzalloc_obj(*newmask);
+	newmask = kzalloc_obj(*newmask, GFP_KERNEL_ACCOUNT);
 	if (!newmask)
 		return ERR_PTR(-ENOMEM);
 
@@ -2394,7 +2394,7 @@ static int fl_change(struct net *net, struct sk_buff *in_skb,
 		goto errout_tb;
 	}
 
-	fnew = kzalloc_obj(*fnew);
+	fnew = kzalloc_obj(*fnew, GFP_KERNEL_ACCOUNT);
 	if (!fnew) {
 		err = -ENOBUFS;
 		goto errout_tb;

net/sched/cls_fw.c

@@ -276,7 +276,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
 		if (f->id != handle && handle)
 			return -EINVAL;
 
-		fnew = kzalloc_obj(struct fw_filter);
+		fnew = kzalloc_obj(struct fw_filter, GFP_KERNEL_ACCOUNT);
 		if (!fnew)
 			return -ENOBUFS;
 
@@ -330,7 +330,7 @@ static int fw_change(struct net *net, struct sk_buff *in_skb,
 		rcu_assign_pointer(tp->root, head);
 	}
 
-	f = kzalloc_obj(struct fw_filter);
+	f = kzalloc_obj(struct fw_filter, GFP_KERNEL_ACCOUNT);
 	if (f == NULL)
 		return -ENOBUFS;
 

net/sched/cls_matchall.c

@@ -189,7 +189,7 @@ static int mall_change(struct net *net, struct sk_buff *in_skb,
 			return -EINVAL;
 	}
 
-	new = kzalloc_obj(*new);
+	new = kzalloc_obj(*new, GFP_KERNEL_ACCOUNT);
 	if (!new)
 		return -ENOBUFS;
 
@@ -201,7 +201,7 @@ static int mall_change(struct net *net, struct sk_buff *in_skb,
 		handle = 1;
 	new->handle = handle;
 	new->flags = userflags;
-	new->pf = alloc_percpu(struct tc_matchall_pcnt);
+	new->pf = alloc_percpu_gfp(struct tc_matchall_pcnt, GFP_KERNEL_ACCOUNT);
 	if (!new->pf) {
 		err = -ENOMEM;
 		goto err_alloc_percpu;

net/sched/cls_route.c

@@ -455,7 +455,7 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp,
 	h1 = to_hash(nhandle);
 	b = rtnl_dereference(head->table[h1]);
 	if (!b) {
-		b = kzalloc_obj(struct route4_bucket);
+		b = kzalloc_obj(struct route4_bucket, GFP_KERNEL_ACCOUNT);
 		if (b == NULL)
 			return -ENOBUFS;
 
@@ -524,7 +524,7 @@ static int route4_change(struct net *net, struct sk_buff *in_skb,
 			return -EINVAL;
 
 	err = -ENOBUFS;
-	f = kzalloc_obj(struct route4_filter);
+	f = kzalloc_obj(struct route4_filter, GFP_KERNEL_ACCOUNT);
 	if (!f)
 		goto errout;
 

net/sched/cls_u32.c

@@ -825,7 +825,7 @@ static struct tc_u_knode *u32_init_knode(struct net *net, struct tcf_proto *tp,
 	struct tc_u32_sel *s = &n->sel;
 	struct tc_u_knode *new;
 
-	new = kzalloc_flex(*new, sel.keys, s->nkeys);
+	new = kzalloc_flex(*new, sel.keys, s->nkeys, GFP_KERNEL_ACCOUNT);
 	if (!new)
 		return NULL;
 
@@ -1114,15 +1114,16 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 		goto erridr;
 	}
 
-	n = kzalloc_flex(*n, sel.keys, s->nkeys);
+	n = kzalloc_flex(*n, sel.keys, s->nkeys, GFP_KERNEL_ACCOUNT);
 	if (n == NULL) {
 		err = -ENOBUFS;
 		goto erridr;
 	}
 
 #ifdef CONFIG_CLS_U32_PERF
-	n->pf = __alloc_percpu(struct_size(n->pf, kcnts, s->nkeys),
-			       __alignof__(struct tc_u32_pcnt));
+	n->pf = __alloc_percpu_gfp(struct_size(n->pf, kcnts, s->nkeys),
+				   __alignof__(struct tc_u32_pcnt),
+				   GFP_KERNEL_ACCOUNT);
 	if (!n->pf) {
 		err = -ENOBUFS;
 		goto errfree;
@@ -1144,7 +1145,7 @@ static int u32_change(struct net *net, struct sk_buff *in_skb,
 		goto errout;
 
 #ifdef CONFIG_CLS_U32_MARK
-	n->pcpu_success = alloc_percpu(u32);
+	n->pcpu_success = alloc_percpu_gfp(u32, GFP_KERNEL_ACCOUNT);
 	if (!n->pcpu_success) {
 		err = -ENOMEM;
 		goto errout;