filter: optimize sk_run_filter

Remove pc variable to avoid arithmetic to compute fentry at each filter
instruction. Jumps directly manipulate fentry pointer.

As the last instruction of filter[] is guaranteed to be a RETURN, and
all jumps are before the last instruction, we dont need to check filter
bounds (number of instructions in filter array) at each iteration, so we
remove it from sk_run_filter() params.

On x86_32 remove f_k var introduced in commit 57fe93b374a6b871
(filter: make sure filters dont read uninitialized memory)

Note : We could use a CONFIG_ARCH_HAS_{FEW|MANY}_REGISTERS in order to
avoid too many ifdefs in this code.

This helps compiler to use cpu registers to hold fentry and A
accumulator.

On x86_32, this saves 401 bytes, and more important, sk_run_filter()
runs much faster because less register pressure (One less conditional
branch per BPF instruction)

# size net/core/filter.o net/core/filter_pre.o
   text    data     bss     dec     hex filename
   2948       0       0    2948     b84 net/core/filter.o
   3349       0       0    3349     d15 net/core/filter_pre.o

on x86_64 :
# size net/core/filter.o net/core/filter_pre.o
   text    data     bss     dec     hex filename
   5173       0       0    5173    1435 net/core/filter.o
   5224       0       0    5224    1468 net/core/filter_pre.o

Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
Acked-by: Changli Gao <xiaosuo@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 4 insertions, 8 deletions

diff --git a/drivers/net/ppp_generic.c b/drivers/net/ppp_generic.c
index 09cf56d0416a..0c91598ae280 100644
--- a/drivers/net/ppp_generic.c
+++ b/drivers/net/ppp_generic.c
@@ -1136,8 +1136,7 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb)
                    a four-byte PPP header on each packet */
                 *skb_push(skb, 2) = 1;
                 if (ppp->pass_filter &&
-                    sk_run_filter(skb, ppp->pass_filter,
-                                  ppp->pass_len) == 0) {
+                    sk_run_filter(skb, ppp->pass_filter) == 0) {
                         if (ppp->debug & 1)
                                 printk(KERN_DEBUG "PPP: outbound frame not passed\n");
                         kfree_skb(skb);
@@ -1145,8 +1144,7 @@ ppp_send_frame(struct ppp *ppp, struct sk_buff *skb)
                 }
                 /* if this packet passes the active filter, record the time */
                 if (!(ppp->active_filter &&
-                      sk_run_filter(skb, ppp->active_filter,
-                                    ppp->active_len) == 0))
+                      sk_run_filter(skb, ppp->active_filter) == 0))
                         ppp->last_xmit = jiffies;
                 skb_pull(skb, 2);
 #else
@@ -1758,8 +1756,7 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb)
 
                         *skb_push(skb, 2) = 0;
                         if (ppp->pass_filter &&
-                            sk_run_filter(skb, ppp->pass_filter,
-                                          ppp->pass_len) == 0) {
+                            sk_run_filter(skb, ppp->pass_filter) == 0) {
                                 if (ppp->debug & 1)
                                         printk(KERN_DEBUG "PPP: inbound frame "
                                                "not passed\n");
@@ -1767,8 +1764,7 @@ ppp_receive_nonmp_frame(struct ppp *ppp, struct sk_buff *skb)
                                 return;
                         }
                         if (!(ppp->active_filter &&
-                              sk_run_filter(skb, ppp->active_filter,
-                                            ppp->active_len) == 0))
+                              sk_run_filter(skb, ppp->active_filter) == 0))
                                 ppp->last_recv = jiffies;
                         __skb_pull(skb, 2);
                 } else