net: netprio_cgroup: rework update socket logic

Instead of updating the sk_cgrp_prioidx struct field on every send
this only updates the field when a task is moved via cgroup
infrastructure.

This allows sockets that may be used by a kernel worker thread
to be managed. For example in the iscsi case today a user can
put iscsid in a netprio cgroup and control traffic will be sent
with the correct sk_cgrp_prioidx value set but as soon as data
is sent the kernel worker thread isssues a send and sk_cgrp_prioidx
is updated with the kernel worker threads value which is the
default case.

It seems more correct to only update the field when the user
explicitly sets it via control group infrastructure. This allows
the users to manage sockets that may be used with other threads.

Signed-off-by: John Fastabend <john.r.fastabend@intel.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

2 files changed, 56 insertions, 3 deletions

diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c
index b2e9caa1ad1a..63d15e8f80e9 100644
--- a/net/core/netprio_cgroup.c
+++ b/net/core/netprio_cgroup.c
@@ -25,6 +25,8 @@
 #include <net/sock.h>
 #include <net/netprio_cgroup.h>
 
+#include <linux/fdtable.h>
+
 #define PRIOIDX_SZ 128
 
 static unsigned long prioidx_map[PRIOIDX_SZ];
@@ -272,6 +274,56 @@ out_free_devname:
 	return ret;
 }
 
+void net_prio_attach(struct cgroup *cgrp, struct cgroup_taskset *tset)
+{
+	struct task_struct *p;
+	char *tmp = kzalloc(sizeof(char) * PATH_MAX, GFP_KERNEL);
+
+	if (!tmp) {
+		pr_warn("Unable to attach cgrp due to alloc failure!\n");
+		return;
+	}
+
+	cgroup_taskset_for_each(p, cgrp, tset) {
+		unsigned int fd;
+		struct fdtable *fdt;
+		struct files_struct *files;
+
+		task_lock(p);
+		files = p->files;
+		if (!files) {
+			task_unlock(p);
+			continue;
+		}
+
+		rcu_read_lock();
+		fdt = files_fdtable(files);
+		for (fd = 0; fd < fdt->max_fds; fd++) {
+			char *path;
+			struct file *file;
+			struct socket *sock;
+			unsigned long s;
+			int rv, err = 0;
+
+			file = fcheck_files(files, fd);
+			if (!file)
+				continue;
+
+			path = d_path(&file->f_path, tmp, PAGE_SIZE);
+			rv = sscanf(path, "socket:[%lu]", &s);
+			if (rv <= 0)
+				continue;
+
+			sock = sock_from_file(file, &err);
+			if (!err)
+				sock_update_netprioidx(sock->sk, p);
+		}
+		rcu_read_unlock();
+		task_unlock(p);
+	}
+	kfree(tmp);
+}
+
 static struct cftype ss_files[] = {
 	{
 		.name = "prioidx",
@@ -289,6 +341,7 @@ struct cgroup_subsys net_prio_subsys = {
 	.name		= "net_prio",
 	.create		= cgrp_create,
 	.destroy	= cgrp_destroy,
+	.attach		= net_prio_attach,
 #ifdef CONFIG_NETPRIO_CGROUP
 	.subsys_id	= net_prio_subsys_id,
 #endif
diff --git a/net/core/sock.c b/net/core/sock.c
index 24039ac12426..2676a88f533e 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -1180,12 +1180,12 @@ void sock_update_classid(struct sock *sk)
 }
 EXPORT_SYMBOL(sock_update_classid);
 
-void sock_update_netprioidx(struct sock *sk)
+void sock_update_netprioidx(struct sock *sk, struct task_struct *task)
 {
 	if (in_interrupt())
 		return;
 
-	sk->sk_cgrp_prioidx = task_netprioidx(current);
+	sk->sk_cgrp_prioidx = task_netprioidx(task);
 }
 EXPORT_SYMBOL_GPL(sock_update_netprioidx);
 #endif
@@ -1215,7 +1215,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 		atomic_set(&sk->sk_wmem_alloc, 1);
 
 		sock_update_classid(sk);
-		sock_update_netprioidx(sk);
+		sock_update_netprioidx(sk, current);
 	}
 
 	return sk;