rtnetlink: introduce nlmsg_new_large and use it in rtnl_getlink

if a PF has 256 or more VFs, ip link command will allocate an order 3
memory or more, and maybe trigger OOM due to memory fragment,
the VFs needed memory size is computed in rtnl_vfinfo_size.

so introduce nlmsg_new_large which calls netlink_alloc_large_skb in
which vmalloc is used for large memory, to avoid the failure of
allocating memory

    ip invoked oom-killer: gfp_mask=0xc2cc0(GFP_KERNEL|__GFP_NOWARN|\
	__GFP_COMP|__GFP_NOMEMALLOC), order=3, oom_score_adj=0
    CPU: 74 PID: 204414 Comm: ip Kdump: loaded Tainted: P           OE
    Call Trace:
    dump_stack+0x57/0x6a
    dump_header+0x4a/0x210
    oom_kill_process+0xe4/0x140
    out_of_memory+0x3e8/0x790
    __alloc_pages_slowpath.constprop.116+0x953/0xc50
    __alloc_pages_nodemask+0x2af/0x310
    kmalloc_large_node+0x38/0xf0
    __kmalloc_node_track_caller+0x417/0x4d0
    __kmalloc_reserve.isra.61+0x2e/0x80
    __alloc_skb+0x82/0x1c0
    rtnl_getlink+0x24f/0x370
    rtnetlink_rcv_msg+0x12c/0x350
    netlink_rcv_skb+0x50/0x100
    netlink_unicast+0x1b2/0x280
    netlink_sendmsg+0x355/0x4a0
    sock_sendmsg+0x5b/0x60
    ____sys_sendmsg+0x1ea/0x250
    ___sys_sendmsg+0x88/0xd0
    __sys_sendmsg+0x5e/0xa0
    do_syscall_64+0x33/0x40
    entry_SYSCALL_64_after_hwframe+0x44/0xa9
    RIP: 0033:0x7f95a65a5b70

Cc: Yunsheng Lin <linyunsheng@huawei.com>
Signed-off-by: Li RongQing <lirongqing@baidu.com>
Link: https://lore.kernel.org/r/20231115120108.3711-1-lirongqing@baidu.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

4 files changed, 17 insertions, 3 deletions

diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 75d7de34c908..abe91ed6b9aa 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -351,5 +351,6 @@ bool netlink_ns_capable(const struct sk_buff *skb,
 			struct user_namespace *ns, int cap);
 bool netlink_capable(const struct sk_buff *skb, int cap);
 bool netlink_net_capable(const struct sk_buff *skb, int cap);
+struct sk_buff *netlink_alloc_large_skb(unsigned int size, int broadcast);
 
 #endif	/* __LINUX_NETLINK_H */
diff --git a/include/net/netlink.h b/include/net/netlink.h
index 83bdf787aeee..167b91348e57 100644
--- a/include/net/netlink.h
+++ b/include/net/netlink.h
@@ -1011,6 +1011,20 @@ static inline struct sk_buff *nlmsg_new(size_t payload, gfp_t flags)
 }
 
 /**
+ * nlmsg_new_large - Allocate a new netlink message with non-contiguous
+ * physical memory
+ * @payload: size of the message payload
+ *
+ * The allocated skb is unable to have frag page for shinfo->frags*,
+ * as the NULL setting for skb->head in netlink_skb_destructor() will
+ * bypass most of the handling in skb_release_data()
+ */
+static inline struct sk_buff *nlmsg_new_large(size_t payload)
+{
+	return netlink_alloc_large_skb(nlmsg_total_size(payload), 0);
+}
+
+/**
  * nlmsg_end - Finalize a netlink message
  * @skb: socket buffer the message is stored in
  * @nlh: netlink message header
diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
index e8431c6c8490..592164c2a540 100644
--- a/net/core/rtnetlink.c
+++ b/net/core/rtnetlink.c
@@ -3849,7 +3849,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh,
 		goto out;
 
 	err = -ENOBUFS;
-	nskb = nlmsg_new(if_nlmsg_size(dev, ext_filter_mask), GFP_KERNEL);
+	nskb = nlmsg_new_large(if_nlmsg_size(dev, ext_filter_mask));
 	if (nskb == NULL)
 		goto out;
 
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index eb086b06d60d..177126fb0484 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -1204,8 +1204,7 @@ struct sock *netlink_getsockbyfilp(struct file *filp)
 	return sock;
 }
 
-static struct sk_buff *netlink_alloc_large_skb(unsigned int size,
-					       int broadcast)
+struct sk_buff *netlink_alloc_large_skb(unsigned int size, int broadcast)
 {
 	struct sk_buff *skb;
 	void *data;