[NET]: convert network timestamps to ktime_t

We currently use a special structure (struct skb_timeval) and plain
'struct timeval' to store packet timestamps in sk_buffs and struct
sock.

This has some drawbacks :
- Fixed resolution of micro second.
- Waste of space on 64bit platforms where sizeof(struct timeval)=16

I suggest using ktime_t that is a nice abstraction of high resolution
time services, currently capable of nanosecond resolution.

As sizeof(ktime_t) is 8 bytes, using ktime_t in 'struct sock' permits
a 8 byte shrink of this structure on 64bit architectures. Some other
structures also benefit from this size reduction (struct ipq in
ipv4/ip_fragment.c, struct frag_queue in ipv6/reassembly.c, ...)

Once this ktime infrastructure adopted, we can more easily provide
nanosecond resolution on top of it. (ioctl SIOCGSTAMPNS and/or
SO_TIMESTAMPNS/SCM_TIMESTAMPNS)

Note : this patch includes a bug correction in
compat_sock_get_timestamp() where a "err = 0;" was missing (so this
syscall returned -ENOENT instead of 0)

Signed-off-by: Eric Dumazet <dada1@cosmosbay.com>
CC: Stephen Hemminger <shemminger@linux-foundation.org>
CC: John find <linux.kernel@free.fr>
Signed-off-by: David S. Miller <davem@davemloft.net>

3 files changed, 13 insertions, 9 deletions

diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c
index b6f055380373..e10be7d7752d 100644
--- a/net/ipv4/ip_fragment.c
+++ b/net/ipv4/ip_fragment.c
@@ -92,7 +92,7 @@ struct ipq {
         spinlock_t      lock;
         atomic_t        refcnt;
         struct timer_list timer;        /* when will this queue expire?         */
-        struct timeval  stamp;
+        ktime_t         stamp;
         int             iif;
         unsigned int    rid;
         struct inet_peer *peer;
@@ -592,7 +592,7 @@ static void ip_frag_queue(struct ipq *qp, struct sk_buff *skb)
         if (skb->dev)
                 qp->iif = skb->dev->ifindex;
         skb->dev = NULL;
-        skb_get_timestamp(skb, &qp->stamp);
+        qp->stamp = skb->tstamp;
         qp->meat += skb->len;
         atomic_add(skb->truesize, &ip_frag_mem);
         if (offset == 0)
@@ -674,7 +674,7 @@ static struct sk_buff *ip_frag_reasm(struct ipq *qp, struct net_device *dev)
 
         head->next = NULL;
         head->dev = dev;
-        skb_set_timestamp(head, &qp->stamp);
+        head->tstamp = qp->stamp;
 
         iph = head->nh.iph;
         iph->frag_off = 0;
@@ -734,7 +734,7 @@ struct sk_buff *ip_defrag(struct sk_buff *skb, u32 user)
         return NULL;
 }
 
-void ipfrag_init(void)
+void __init ipfrag_init(void)
 {
         ipfrag_hash_rnd = (u32) ((num_physpages ^ (num_physpages>>7)) ^
                                  (jiffies ^ (jiffies >> 6)));
diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c
index a14798a850d7..5842f1aa973a 100644
--- a/net/ipv4/netfilter/ip_queue.c
+++ b/net/ipv4/netfilter/ip_queue.c
@@ -197,6 +197,7 @@ ipq_build_packet_message(struct ipq_queue_entry *entry, int *errp)
         struct sk_buff *skb;
         struct ipq_packet_msg *pmsg;
         struct nlmsghdr *nlh;
+        struct timeval tv;
 
         read_lock_bh(&queue_lock);
 
@@ -241,8 +242,9 @@ ipq_build_packet_message(struct ipq_queue_entry *entry, int *errp)
 
         pmsg->packet_id       = (unsigned long )entry;
         pmsg->data_len        = data_len;
-        pmsg->timestamp_sec   = entry->skb->tstamp.off_sec;
-        pmsg->timestamp_usec  = entry->skb->tstamp.off_usec;
+        tv = ktime_to_timeval(entry->skb->tstamp);
+        pmsg->timestamp_sec   = tv.tv_sec;
+        pmsg->timestamp_usec  = tv.tv_usec;
         pmsg->mark            = entry->skb->mark;
         pmsg->hook            = entry->info->hook;
         pmsg->hw_protocol     = entry->skb->protocol;
diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c
index 9acc018766f2..9718b666a380 100644
--- a/net/ipv4/netfilter/ipt_ULOG.c
+++ b/net/ipv4/netfilter/ipt_ULOG.c
@@ -187,6 +187,7 @@ static void ipt_ulog_packet(unsigned int hooknum,
         ulog_packet_msg_t *pm;
         size_t size, copy_len;
         struct nlmsghdr *nlh;
+        struct timeval tv;
 
         /* ffs == find first bit set, necessary because userspace
          * is already shifting groupnumber, but we need unshifted.
@@ -232,13 +233,14 @@ static void ipt_ulog_packet(unsigned int hooknum,
         pm = NLMSG_DATA(nlh);
 
         /* We might not have a timestamp, get one */
-        if (skb->tstamp.off_sec == 0)
+        if (skb->tstamp.tv64 == 0)
                 __net_timestamp((struct sk_buff *)skb);
 
         /* copy hook, prefix, timestamp, payload, etc. */
         pm->data_len = copy_len;
-        put_unaligned(skb->tstamp.off_sec, &pm->timestamp_sec);
-        put_unaligned(skb->tstamp.off_usec, &pm->timestamp_usec);
+        tv = ktime_to_timeval(skb->tstamp);
+        put_unaligned(tv.tv_sec, &pm->timestamp_sec);
+        put_unaligned(tv.tv_usec, &pm->timestamp_usec);
         put_unaligned(skb->mark, &pm->mark);
         pm->hook = hooknum;
         if (prefix != NULL)