Merge branch 'for-bfields' of git://linux-nfs.org/~tomtucker/xprt-switch-2.6 into for-2.6.27

11 files changed, 48 insertions, 73 deletions

diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c
index 6de4bd195d28..1e8be246ad15 100644
--- a/net/dccp/ackvec.c
+++ b/net/dccp/ackvec.c
@@ -290,12 +290,12 @@ int dccp_ackvec_add(struct dccp_ackvec *av, const struct sock *sk,
 
                 while (1) {
                         const u8 len = dccp_ackvec_len(av, index);
-                        const u8 state = dccp_ackvec_state(av, index);
+                        const u8 av_state = dccp_ackvec_state(av, index);
                         /*
                          * valid packets not yet in av_buf have a reserved
                          * entry, with a len equal to 0.
                          */
-                        if (state == DCCP_ACKVEC_STATE_NOT_RECEIVED &&
+                        if (av_state == DCCP_ACKVEC_STATE_NOT_RECEIVED &&
                             len == 0 && delta == 0) { /* Found our
                                                          reserved seat! */
                                 dccp_pr_debug("Found %llu reserved seat!\n",
@@ -325,31 +325,6 @@ out_duplicate:
         return -EILSEQ;
 }
 
-#ifdef CONFIG_IP_DCCP_DEBUG
-void dccp_ackvector_print(const u64 ackno, const unsigned char *vector, int len)
-{
-        dccp_pr_debug_cat("ACK vector len=%d, ackno=%llu |", len,
-                         (unsigned long long)ackno);
-
-        while (len--) {
-                const u8 state = (*vector & DCCP_ACKVEC_STATE_MASK) >> 6;
-                const u8 rl = *vector & DCCP_ACKVEC_LEN_MASK;
-
-                dccp_pr_debug_cat("%d,%d|", state, rl);
-                ++vector;
-        }
-
-        dccp_pr_debug_cat("\n");
-}
-
-void dccp_ackvec_print(const struct dccp_ackvec *av)
-{
-        dccp_ackvector_print(av->av_buf_ackno,
-                             av->av_buf + av->av_buf_head,
-                             av->av_vec_len);
-}
-#endif
-
 static void dccp_ackvec_throw_record(struct dccp_ackvec *av,
                                      struct dccp_ackvec_record *avr)
 {
diff --git a/net/dccp/ccids/ccid3.c b/net/dccp/ccids/ccid3.c
index cd61dea2eea1..a1929f33d703 100644
--- a/net/dccp/ccids/ccid3.c
+++ b/net/dccp/ccids/ccid3.c
@@ -159,8 +159,8 @@ static void ccid3_hc_tx_update_x(struct sock *sk, ktime_t *stamp)
         } else if (ktime_us_delta(now, hctx->ccid3hctx_t_ld)
                                 - (s64)hctx->ccid3hctx_rtt >= 0) {
 
-                hctx->ccid3hctx_x =
-                        max(min(2 * hctx->ccid3hctx_x, min_rate),
+                hctx->ccid3hctx_x = min(2 * hctx->ccid3hctx_x, min_rate);
+                hctx->ccid3hctx_x = max(hctx->ccid3hctx_x,
                             scaled_div(((__u64)hctx->ccid3hctx_s) << 6,
                                        hctx->ccid3hctx_rtt));
                 hctx->ccid3hctx_t_ld = now;
@@ -193,22 +193,17 @@ static inline void ccid3_hc_tx_update_s(struct ccid3_hc_tx_sock *hctx, int len)
 
 /*
  *      Update Window Counter using the algorithm from [RFC 4342, 8.1].
- *      The algorithm is not applicable if RTT < 4 microseconds.
+ *      As elsewhere, RTT > 0 is assumed by using dccp_sample_rtt().
  */
 static inline void ccid3_hc_tx_update_win_count(struct ccid3_hc_tx_sock *hctx,
                                                 ktime_t now)
 {
-        u32 quarter_rtts;
-
-        if (unlikely(hctx->ccid3hctx_rtt < 4))  /* avoid divide-by-zero */
-                return;
-
-        quarter_rtts = ktime_us_delta(now, hctx->ccid3hctx_t_last_win_count);
-        quarter_rtts /= hctx->ccid3hctx_rtt / 4;
+        u32 delta = ktime_us_delta(now, hctx->ccid3hctx_t_last_win_count),
+            quarter_rtts = (4 * delta) / hctx->ccid3hctx_rtt;
 
         if (quarter_rtts > 0) {
                 hctx->ccid3hctx_t_last_win_count = now;
-                hctx->ccid3hctx_last_win_count  += min_t(u32, quarter_rtts, 5);
+                hctx->ccid3hctx_last_win_count  += min(quarter_rtts, 5U);
                 hctx->ccid3hctx_last_win_count  &= 0xF;         /* mod 16 */
         }
 }
@@ -334,8 +329,14 @@ static int ccid3_hc_tx_send_packet(struct sock *sk, struct sk_buff *skb)
                         hctx->ccid3hctx_x    = rfc3390_initial_rate(sk);
                         hctx->ccid3hctx_t_ld = now;
                 } else {
-                        /* Sender does not have RTT sample: X_pps = 1 pkt/sec */
-                        hctx->ccid3hctx_x = hctx->ccid3hctx_s;
+                        /*
+                         * Sender does not have RTT sample:
+                         * - set fallback RTT (RFC 4340, 3.4) since a RTT value
+                         *   is needed in several parts (e.g.  window counter);
+                         * - set sending rate X_pps = 1pps as per RFC 3448, 4.2.
+                         */
+                        hctx->ccid3hctx_rtt = DCCP_FALLBACK_RTT;
+                        hctx->ccid3hctx_x   = hctx->ccid3hctx_s;
                         hctx->ccid3hctx_x <<= 6;
                 }
                 ccid3_update_send_interval(hctx);
diff --git a/net/dccp/ccids/lib/tfrc.c b/net/dccp/ccids/lib/tfrc.c
index d1dfbb8de64c..97ecec0a8e76 100644
--- a/net/dccp/ccids/lib/tfrc.c
+++ b/net/dccp/ccids/lib/tfrc.c
@@ -14,14 +14,6 @@ module_param(tfrc_debug, bool, 0444);
 MODULE_PARM_DESC(tfrc_debug, "Enable debug messages");
 #endif
 
-extern int  tfrc_tx_packet_history_init(void);
-extern void tfrc_tx_packet_history_exit(void);
-extern int  tfrc_rx_packet_history_init(void);
-extern void tfrc_rx_packet_history_exit(void);
-
-extern int  tfrc_li_init(void);
-extern void tfrc_li_exit(void);
-
 static int __init tfrc_module_init(void)
 {
         int rc = tfrc_li_init();
diff --git a/net/dccp/ccids/lib/tfrc.h b/net/dccp/ccids/lib/tfrc.h
index 1fb1187bbf1c..ed9857527acf 100644
--- a/net/dccp/ccids/lib/tfrc.h
+++ b/net/dccp/ccids/lib/tfrc.h
@@ -15,7 +15,7 @@
  *  (at your option) any later version.
  */
 #include <linux/types.h>
-#include <asm/div64.h>
+#include <linux/math64.h>
 #include "../../dccp.h"
 /* internal includes that this module exports: */
 #include "loss_interval.h"
@@ -29,21 +29,19 @@ extern int tfrc_debug;
 #endif
 
 /* integer-arithmetic divisions of type (a * 1000000)/b */
-static inline u64 scaled_div(u64 a, u32 b)
+static inline u64 scaled_div(u64 a, u64 b)
 {
         BUG_ON(b==0);
-        a *= 1000000;
-        do_div(a, b);
-        return a;
+        return div64_u64(a * 1000000, b);
 }
 
-static inline u32 scaled_div32(u64 a, u32 b)
+static inline u32 scaled_div32(u64 a, u64 b)
 {
         u64 result = scaled_div(a, b);
 
         if (result > UINT_MAX) {
-                DCCP_CRIT("Overflow: a(%llu)/b(%u) > ~0U",
-                          (unsigned long long)a, b);
+                DCCP_CRIT("Overflow: %llu/%llu > UINT_MAX",
+                          (unsigned long long)a, (unsigned long long)b);
                 return UINT_MAX;
         }
         return result;
@@ -58,7 +56,14 @@ static inline u32 tfrc_ewma(const u32 avg, const u32 newval, const u8 weight)
         return avg ? (weight * avg + (10 - weight) * newval) / 10 : newval;
 }
 
-extern u32 tfrc_calc_x(u16 s, u32 R, u32 p);
-extern u32 tfrc_calc_x_reverse_lookup(u32 fvalue);
+extern u32  tfrc_calc_x(u16 s, u32 R, u32 p);
+extern u32  tfrc_calc_x_reverse_lookup(u32 fvalue);
 
+extern int  tfrc_tx_packet_history_init(void);
+extern void tfrc_tx_packet_history_exit(void);
+extern int  tfrc_rx_packet_history_init(void);
+extern void tfrc_rx_packet_history_exit(void);
+
+extern int  tfrc_li_init(void);
+extern void tfrc_li_exit(void);
 #endif /* _TFRC_H_ */
diff --git a/net/dccp/ccids/lib/tfrc_equation.c b/net/dccp/ccids/lib/tfrc_equation.c
index e4e64b76c10c..2f20a29cffe4 100644
--- a/net/dccp/ccids/lib/tfrc_equation.c
+++ b/net/dccp/ccids/lib/tfrc_equation.c
@@ -661,7 +661,7 @@ u32 tfrc_calc_x(u16 s, u32 R, u32 p)
 
 EXPORT_SYMBOL_GPL(tfrc_calc_x);
 
-/*
+/**
  *  tfrc_calc_x_reverse_lookup  -  try to find p given f(p)
  *
  *  @fvalue: function value to match, scaled by 1000000
@@ -676,11 +676,11 @@ u32 tfrc_calc_x_reverse_lookup(u32 fvalue)
 
         /* Error cases. */
         if (fvalue < tfrc_calc_x_lookup[0][1]) {
-                DCCP_WARN("fvalue %d smaller than resolution\n", fvalue);
-                return tfrc_calc_x_lookup[0][1];
+                DCCP_WARN("fvalue %u smaller than resolution\n", fvalue);
+                return TFRC_SMALLEST_P;
         }
         if (fvalue > tfrc_calc_x_lookup[TFRC_CALC_X_ARRSIZE - 1][0]) {
-                DCCP_WARN("fvalue %d exceeds bounds!\n", fvalue);
+                DCCP_WARN("fvalue %u exceeds bounds!\n", fvalue);
                 return 1000000;
         }
 
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index b348dd70c685..37d27bcb361f 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -589,7 +589,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
         if (sk_acceptq_is_full(sk) && inet_csk_reqsk_queue_young(sk) > 1)
                 goto drop;
 
-        req = reqsk_alloc(&dccp_request_sock_ops);
+        req = inet_reqsk_alloc(&dccp_request_sock_ops);
         if (req == NULL)
                 goto drop;
 
@@ -605,7 +605,6 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
         ireq = inet_rsk(req);
         ireq->loc_addr = ip_hdr(skb)->daddr;
         ireq->rmt_addr = ip_hdr(skb)->saddr;
-        ireq->opt       = NULL;
 
         /*
          * Step 3: Process LISTEN state
@@ -739,8 +738,8 @@ int dccp_invalid_packet(struct sk_buff *skb)
          * If P.type is not Data, Ack, or DataAck and P.X == 0 (the packet
          * has short sequence numbers), drop packet and return
          */
-        if (dh->dccph_type >= DCCP_PKT_DATA    &&
-            dh->dccph_type <= DCCP_PKT_DATAACK && dh->dccph_x == 0)  {
+        if ((dh->dccph_type < DCCP_PKT_DATA    ||
+            dh->dccph_type > DCCP_PKT_DATAACK) && dh->dccph_x == 0)  {
                 DCCP_WARN("P.type (%s) not Data || [Data]Ack, while P.X == 0\n",
                           dccp_packet_name(dh->dccph_type));
                 return 1;
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 9b1129bb7ece..f7fe2a572d7b 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -421,7 +421,6 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
         ireq6 = inet6_rsk(req);
         ipv6_addr_copy(&ireq6->rmt_addr, &ipv6_hdr(skb)->saddr);
         ipv6_addr_copy(&ireq6->loc_addr, &ipv6_hdr(skb)->daddr);
-        ireq6->pktopts  = NULL;
 
         if (ipv6_opt_accepted(sk, skb) ||
             np->rxopt.bits.rxinfo || np->rxopt.bits.rxoinfo ||
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 33ad48321b08..66dca5bba858 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -165,12 +165,12 @@ out_free:
                 /* See dccp_v4_conn_request */
                 newdmsk->dccpms_sequence_window = req->rcv_wnd;
 
-                newdp->dccps_gar = newdp->dccps_isr = dreq->dreq_isr;
-                dccp_update_gsr(newsk, dreq->dreq_isr);
-
-                newdp->dccps_iss = dreq->dreq_iss;
+                newdp->dccps_gar = newdp->dccps_iss = dreq->dreq_iss;
                 dccp_update_gss(newsk, dreq->dreq_iss);
 
+                newdp->dccps_isr = dreq->dreq_isr;
+                dccp_update_gsr(newsk, dreq->dreq_isr);
+
                 /*
                  * SWL and AWL are initially adjusted so that they are not less than
                  * the initial Sequence Numbers received and sent, respectively:
diff --git a/net/dccp/options.c b/net/dccp/options.c
index d2a84a2fecee..43bc24e761d0 100644
--- a/net/dccp/options.c
+++ b/net/dccp/options.c
@@ -107,9 +107,11 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq,
                  *
                  * CCID-specific options are ignored during connection setup, as
                  * negotiation may still be in progress (see RFC 4340, 10.3).
+                 * The same applies to Ack Vectors, as these depend on the CCID.
                  *
                  */
-                if (dreq != NULL && opt >= 128)
+                if (dreq != NULL && (opt >= 128 ||
+                    opt == DCCPO_ACK_VECTOR_0 || opt == DCCPO_ACK_VECTOR_1))
                         goto ignore_option;
 
                 switch (opt) {
diff --git a/net/dccp/output.c b/net/dccp/output.c
index 1f8a9b64c083..fe20068c5d8e 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -508,6 +508,7 @@ void dccp_send_ack(struct sock *sk)
 
 EXPORT_SYMBOL_GPL(dccp_send_ack);
 
+#if 0
 /* FIXME: Is this still necessary (11.3) - currently nowhere used by DCCP. */
 void dccp_send_delayed_ack(struct sock *sk)
 {
@@ -538,6 +539,7 @@ void dccp_send_delayed_ack(struct sock *sk)
         icsk->icsk_ack.timeout = timeout;
         sk_reset_timer(sk, &icsk->icsk_delack_timer, timeout);
 }
+#endif
 
 void dccp_send_sync(struct sock *sk, const u64 ackno,
                     const enum dccp_pkt_type pkt_type)
diff --git a/net/dccp/probe.c b/net/dccp/probe.c
index 0bcdc9250279..81368a7f5379 100644
--- a/net/dccp/probe.c
+++ b/net/dccp/probe.c
@@ -42,7 +42,7 @@ static int bufsize = 64 * 1024;
 
 static const char procname[] = "dccpprobe";
 
-struct {
+static struct {
         struct kfifo      *fifo;
         spinlock_t        lock;
         wait_queue_head_t wait;