summaryrefslogtreecommitdiffstats
path: root/net/dccp
diff options
context:
space:
mode:
Diffstat (limited to 'net/dccp')
-rw-r--r--net/dccp/ackvec.c9
-rw-r--r--net/dccp/ackvec.h5
-rw-r--r--net/dccp/ccid.c48
-rw-r--r--net/dccp/ccid.h23
-rw-r--r--net/dccp/ccids/ccid2.c6
-rw-r--r--net/dccp/dccp.h10
-rw-r--r--net/dccp/diag.c2
-rw-r--r--net/dccp/feat.c626
-rw-r--r--net/dccp/feat.h112
-rw-r--r--net/dccp/input.c2
-rw-r--r--net/dccp/ipv4.c5
-rw-r--r--net/dccp/ipv6.c15
-rw-r--r--net/dccp/minisocks.c8
-rw-r--r--net/dccp/options.c148
-rw-r--r--net/dccp/output.c17
-rw-r--r--net/dccp/probe.c7
-rw-r--r--net/dccp/proto.c177
-rw-r--r--net/dccp/sysctl.c7
-rw-r--r--net/dccp/timer.c12
19 files changed, 955 insertions, 284 deletions
diff --git a/net/dccp/ackvec.c b/net/dccp/ackvec.c
index 1e8be246ad15..01e4d39fa232 100644
--- a/net/dccp/ackvec.c
+++ b/net/dccp/ackvec.c
@@ -12,7 +12,6 @@
#include "ackvec.h"
#include "dccp.h"
-#include <linux/dccp.h>
#include <linux/init.h>
#include <linux/errno.h>
#include <linux/kernel.h>
@@ -68,7 +67,7 @@ int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb)
struct dccp_sock *dp = dccp_sk(sk);
struct dccp_ackvec *av = dp->dccps_hc_rx_ackvec;
/* Figure out how many options do we need to represent the ackvec */
- const u16 nr_opts = DIV_ROUND_UP(av->av_vec_len, DCCP_MAX_ACKVEC_OPT_LEN);
+ const u8 nr_opts = DIV_ROUND_UP(av->av_vec_len, DCCP_SINGLE_OPT_MAXLEN);
u16 len = av->av_vec_len + 2 * nr_opts, i;
u32 elapsed_time;
const unsigned char *tail, *from;
@@ -100,8 +99,8 @@ int dccp_insert_option_ackvec(struct sock *sk, struct sk_buff *skb)
for (i = 0; i < nr_opts; ++i) {
int copylen = len;
- if (len > DCCP_MAX_ACKVEC_OPT_LEN)
- copylen = DCCP_MAX_ACKVEC_OPT_LEN;
+ if (len > DCCP_SINGLE_OPT_MAXLEN)
+ copylen = DCCP_SINGLE_OPT_MAXLEN;
*to++ = DCCPO_ACK_VECTOR_0;
*to++ = copylen + 2;
@@ -432,7 +431,7 @@ found:
int dccp_ackvec_parse(struct sock *sk, const struct sk_buff *skb,
u64 *ackno, const u8 opt, const u8 *value, const u8 len)
{
- if (len > DCCP_MAX_ACKVEC_OPT_LEN)
+ if (len > DCCP_SINGLE_OPT_MAXLEN)
return -1;
/* dccp_ackvector_print(DCCP_SKB_CB(skb)->dccpd_ack_seq, value, len); */
diff --git a/net/dccp/ackvec.h b/net/dccp/ackvec.h
index bcb64fb4acef..4ccee030524e 100644
--- a/net/dccp/ackvec.h
+++ b/net/dccp/ackvec.h
@@ -11,15 +11,14 @@
* published by the Free Software Foundation.
*/
+#include <linux/dccp.h>
#include <linux/compiler.h>
#include <linux/ktime.h>
#include <linux/list.h>
#include <linux/types.h>
-/* Read about the ECN nonce to see why it is 253 */
-#define DCCP_MAX_ACKVEC_OPT_LEN 253
/* We can spread an ack vector across multiple options */
-#define DCCP_MAX_ACKVEC_LEN (DCCP_MAX_ACKVEC_OPT_LEN * 2)
+#define DCCP_MAX_ACKVEC_LEN (DCCP_SINGLE_OPT_MAXLEN * 2)
#define DCCP_ACKVEC_STATE_RECEIVED 0
#define DCCP_ACKVEC_STATE_ECN_MARKED (1 << 6)
diff --git a/net/dccp/ccid.c b/net/dccp/ccid.c
index 8fe931a3d7a1..647cb0614f84 100644
--- a/net/dccp/ccid.c
+++ b/net/dccp/ccid.c
@@ -13,6 +13,13 @@
#include "ccid.h"
+static u8 builtin_ccids[] = {
+ DCCPC_CCID2, /* CCID2 is supported by default */
+#if defined(CONFIG_IP_DCCP_CCID3) || defined(CONFIG_IP_DCCP_CCID3_MODULE)
+ DCCPC_CCID3,
+#endif
+};
+
static struct ccid_operations *ccids[CCID_MAX];
#if defined(CONFIG_SMP) || defined(CONFIG_PREEMPT)
static atomic_t ccids_lockct = ATOMIC_INIT(0);
@@ -86,6 +93,47 @@ static void ccid_kmem_cache_destroy(struct kmem_cache *slab)
}
}
+/* check that up to @array_len members in @ccid_array are supported */
+bool ccid_support_check(u8 const *ccid_array, u8 array_len)
+{
+ u8 i, j, found;
+
+ for (i = 0, found = 0; i < array_len; i++, found = 0) {
+ for (j = 0; !found && j < ARRAY_SIZE(builtin_ccids); j++)
+ found = (ccid_array[i] == builtin_ccids[j]);
+ if (!found)
+ return false;
+ }
+ return true;
+}
+
+/**
+ * ccid_get_builtin_ccids - Provide copy of `builtin' CCID array
+ * @ccid_array: pointer to copy into
+ * @array_len: value to return length into
+ * This function allocates memory - caller must see that it is freed after use.
+ */
+int ccid_get_builtin_ccids(u8 **ccid_array, u8 *array_len)
+{
+ *ccid_array = kmemdup(builtin_ccids, sizeof(builtin_ccids), gfp_any());
+ if (*ccid_array == NULL)
+ return -ENOBUFS;
+ *array_len = ARRAY_SIZE(builtin_ccids);
+ return 0;
+}
+
+int ccid_getsockopt_builtin_ccids(struct sock *sk, int len,
+ char __user *optval, int __user *optlen)
+{
+ if (len < sizeof(builtin_ccids))
+ return -EINVAL;
+
+ if (put_user(sizeof(builtin_ccids), optlen) ||
+ copy_to_user(optval, builtin_ccids, sizeof(builtin_ccids)))
+ return -EFAULT;
+ return 0;
+}
+
int ccid_register(struct ccid_operations *ccid_ops)
{
int err = -ENOBUFS;
diff --git a/net/dccp/ccid.h b/net/dccp/ccid.h
index fdeae7b57319..803343aed004 100644
--- a/net/dccp/ccid.h
+++ b/net/dccp/ccid.h
@@ -103,6 +103,11 @@ static inline void *ccid_priv(const struct ccid *ccid)
return (void *)ccid->ccid_priv;
}
+extern bool ccid_support_check(u8 const *ccid_array, u8 array_len);
+extern int ccid_get_builtin_ccids(u8 **ccid_array, u8 *array_len);
+extern int ccid_getsockopt_builtin_ccids(struct sock *sk, int len,
+ char __user *, int __user *);
+
extern struct ccid *ccid_new(unsigned char id, struct sock *sk, int rx,
gfp_t gfp);
@@ -111,6 +116,24 @@ extern struct ccid *ccid_hc_rx_new(unsigned char id, struct sock *sk,
extern struct ccid *ccid_hc_tx_new(unsigned char id, struct sock *sk,
gfp_t gfp);
+static inline int ccid_get_current_rx_ccid(struct dccp_sock *dp)
+{
+ struct ccid *ccid = dp->dccps_hc_rx_ccid;
+
+ if (ccid == NULL || ccid->ccid_ops == NULL)
+ return -1;
+ return ccid->ccid_ops->ccid_id;
+}
+
+static inline int ccid_get_current_tx_ccid(struct dccp_sock *dp)
+{
+ struct ccid *ccid = dp->dccps_hc_tx_ccid;
+
+ if (ccid == NULL || ccid->ccid_ops == NULL)
+ return -1;
+ return ccid->ccid_ops->ccid_id;
+}
+
extern void ccid_hc_rx_delete(struct ccid *ccid, struct sock *sk);
extern void ccid_hc_tx_delete(struct ccid *ccid, struct sock *sk);
diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c
index 9a430734530c..c9ea19a4d85e 100644
--- a/net/dccp/ccids/ccid2.c
+++ b/net/dccp/ccids/ccid2.c
@@ -25,7 +25,7 @@
/*
* This implementation should follow RFC 4341
*/
-
+#include "../feat.h"
#include "../ccid.h"
#include "../dccp.h"
#include "ccid2.h"
@@ -147,8 +147,8 @@ static void ccid2_change_l_ack_ratio(struct sock *sk, u32 val)
DCCP_WARN("Limiting Ack Ratio (%u) to %u\n", val, max_ratio);
val = max_ratio;
}
- if (val > 0xFFFF) /* RFC 4340, 11.3 */
- val = 0xFFFF;
+ if (val > DCCPF_ACK_RATIO_MAX)
+ val = DCCPF_ACK_RATIO_MAX;
if (val == dp->dccps_l_ack_ratio)
return;
diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h
index b4bc6e095a0e..33a1127270c1 100644
--- a/net/dccp/dccp.h
+++ b/net/dccp/dccp.h
@@ -49,7 +49,7 @@ extern int dccp_debug;
extern struct inet_hashinfo dccp_hashinfo;
-extern atomic_t dccp_orphan_count;
+extern struct percpu_counter dccp_orphan_count;
extern void dccp_time_wait(struct sock *sk, int state, int timeo);
@@ -98,7 +98,6 @@ extern int sysctl_dccp_retries2;
extern int sysctl_dccp_feat_sequence_window;
extern int sysctl_dccp_feat_rx_ccid;
extern int sysctl_dccp_feat_tx_ccid;
-extern int sysctl_dccp_feat_ack_ratio;
extern int sysctl_dccp_feat_send_ack_vector;
extern int sysctl_dccp_feat_send_ndp_count;
extern int sysctl_dccp_tx_qlen;
@@ -252,7 +251,8 @@ extern const char *dccp_state_name(const int state);
extern void dccp_set_state(struct sock *sk, const int state);
extern void dccp_done(struct sock *sk);
-extern void dccp_reqsk_init(struct request_sock *req, struct sk_buff *skb);
+extern int dccp_reqsk_init(struct request_sock *rq, struct dccp_sock const *dp,
+ struct sk_buff const *skb);
extern int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb);
@@ -441,6 +441,10 @@ static inline int dccp_ack_pending(const struct sock *sk)
inet_csk_ack_scheduled(sk);
}
+extern int dccp_feat_finalise_settings(struct dccp_sock *dp);
+extern int dccp_feat_server_ccid_dependencies(struct dccp_request_sock *dreq);
+extern void dccp_feat_list_purge(struct list_head *fn_list);
+
extern int dccp_insert_options(struct sock *sk, struct sk_buff *skb);
extern int dccp_insert_options_rsk(struct dccp_request_sock*, struct sk_buff*);
extern int dccp_insert_option_elapsed_time(struct sock *sk,
diff --git a/net/dccp/diag.c b/net/dccp/diag.c
index d8a3509b26f6..d1e100395efb 100644
--- a/net/dccp/diag.c
+++ b/net/dccp/diag.c
@@ -45,7 +45,7 @@ static void dccp_diag_get_info(struct sock *sk, struct inet_diag_msg *r,
dccp_get_info(sk, _info);
}
-static struct inet_diag_handler dccp_diag_handler = {
+static const struct inet_diag_handler dccp_diag_handler = {
.idiag_hashinfo = &dccp_hashinfo,
.idiag_get_info = dccp_diag_get_info,
.idiag_type = DCCPDIAG_GETSOCK,
diff --git a/net/dccp/feat.c b/net/dccp/feat.c
index 933a0ecf8d46..2c2216f64b1b 100644
--- a/net/dccp/feat.c
+++ b/net/dccp/feat.c
@@ -6,6 +6,8 @@
*
* ASSUMPTIONS
* -----------
+ * o Feature negotiation is coordinated with connection setup (as in TCP), wild
+ * changes of parameters of an established connection are not supported.
* o All currently known SP features have 1-byte quantities. If in the future
* extensions of RFCs 4340..42 define features with item lengths larger than
* one byte, a feature-specific extension of the code will be required.
@@ -23,53 +25,560 @@
#define DCCP_FEAT_SP_NOAGREE (-123)
-int dccp_feat_change(struct dccp_minisock *dmsk, u8 type, u8 feature,
- u8 *val, u8 len, gfp_t gfp)
+static const struct {
+ u8 feat_num; /* DCCPF_xxx */
+ enum dccp_feat_type rxtx; /* RX or TX */
+ enum dccp_feat_type reconciliation; /* SP or NN */
+ u8 default_value; /* as in 6.4 */
+/*
+ * Lookup table for location and type of features (from RFC 4340/4342)
+ * +--------------------------+----+-----+----+----+---------+-----------+
+ * | Feature | Location | Reconc. | Initial | Section |
+ * | | RX | TX | SP | NN | Value | Reference |
+ * +--------------------------+----+-----+----+----+---------+-----------+
+ * | DCCPF_CCID | | X | X | | 2 | 10 |
+ * | DCCPF_SHORT_SEQNOS | | X | X | | 0 | 7.6.1 |
+ * | DCCPF_SEQUENCE_WINDOW | | X | | X | 100 | 7.5.2 |
+ * | DCCPF_ECN_INCAPABLE | X | | X | | 0 | 12.1 |
+ * | DCCPF_ACK_RATIO | | X | | X | 2 | 11.3 |
+ * | DCCPF_SEND_ACK_VECTOR | X | | X | | 0 | 11.5 |
+ * | DCCPF_SEND_NDP_COUNT | | X | X | | 0 | 7.7.2 |
+ * | DCCPF_MIN_CSUM_COVER | X | | X | | 0 | 9.2.1 |
+ * | DCCPF_DATA_CHECKSUM | X | | X | | 0 | 9.3.1 |
+ * | DCCPF_SEND_LEV_RATE | X | | X | | 0 | 4342/8.4 |
+ * +--------------------------+----+-----+----+----+---------+-----------+
+ */
+} dccp_feat_table[] = {
+ { DCCPF_CCID, FEAT_AT_TX, FEAT_SP, 2 },
+ { DCCPF_SHORT_SEQNOS, FEAT_AT_TX, FEAT_SP, 0 },
+ { DCCPF_SEQUENCE_WINDOW, FEAT_AT_TX, FEAT_NN, 100 },
+ { DCCPF_ECN_INCAPABLE, FEAT_AT_RX, FEAT_SP, 0 },
+ { DCCPF_ACK_RATIO, FEAT_AT_TX, FEAT_NN, 2 },
+ { DCCPF_SEND_ACK_VECTOR, FEAT_AT_RX, FEAT_SP, 0 },
+ { DCCPF_SEND_NDP_COUNT, FEAT_AT_TX, FEAT_SP, 0 },
+ { DCCPF_MIN_CSUM_COVER, FEAT_AT_RX, FEAT_SP, 0 },
+ { DCCPF_DATA_CHECKSUM, FEAT_AT_RX, FEAT_SP, 0 },
+ { DCCPF_SEND_LEV_RATE, FEAT_AT_RX, FEAT_SP, 0 },
+};
+#define DCCP_FEAT_SUPPORTED_MAX ARRAY_SIZE(dccp_feat_table)
+
+/**
+ * dccp_feat_index - Hash function to map feature number into array position
+ * Returns consecutive array index or -1 if the feature is not understood.
+ */
+static int dccp_feat_index(u8 feat_num)
{
- struct dccp_opt_pend *opt;
+ /* The first 9 entries are occupied by the types from RFC 4340, 6.4 */
+ if (feat_num > DCCPF_RESERVED && feat_num <= DCCPF_DATA_CHECKSUM)
+ return feat_num - 1;
- dccp_feat_debug(type, feature, *val);
+ /*
+ * Other features: add cases for new feature types here after adding
+ * them to the above table.
+ */
+ switch (feat_num) {
+ case DCCPF_SEND_LEV_RATE:
+ return DCCP_FEAT_SUPPORTED_MAX - 1;
+ }
+ return -1;
+}
- if (len > 3) {
- DCCP_WARN("invalid length %d\n", len);
- return -EINVAL;
+static u8 dccp_feat_type(u8 feat_num)
+{
+ int idx = dccp_feat_index(feat_num);
+
+ if (idx < 0)
+ return FEAT_UNKNOWN;
+ return dccp_feat_table[idx].reconciliation;
+}
+
+static int dccp_feat_default_value(u8 feat_num)
+{
+ int idx = dccp_feat_index(feat_num);
+ /*
+ * There are no default values for unknown features, so encountering a
+ * negative index here indicates a serious problem somewhere else.
+ */
+ DCCP_BUG_ON(idx < 0);
+
+ return idx < 0 ? 0 : dccp_feat_table[idx].default_value;
+}
+
+/* copy constructor, fval must not already contain allocated memory */
+static int dccp_feat_clone_sp_val(dccp_feat_val *fval, u8 const *val, u8 len)
+{
+ fval->sp.len = len;
+ if (fval->sp.len > 0) {
+ fval->sp.vec = kmemdup(val, len, gfp_any());
+ if (fval->sp.vec == NULL) {
+ fval->sp.len = 0;
+ return -ENOBUFS;
+ }
}
- /* XXX add further sanity checks */
+ return 0;
+}
- /* check if that feature is already being negotiated */
- list_for_each_entry(opt, &dmsk->dccpms_pending, dccpop_node) {
- /* ok we found a negotiation for this option already */
- if (opt->dccpop_feat == feature && opt->dccpop_type == type) {
- dccp_pr_debug("Replacing old\n");
- /* replace */
- BUG_ON(opt->dccpop_val == NULL);
- kfree(opt->dccpop_val);
- opt->dccpop_val = val;
- opt->dccpop_len = len;
- opt->dccpop_conf = 0;
- return 0;
+static void dccp_feat_val_destructor(u8 feat_num, dccp_feat_val *val)
+{
+ if (unlikely(val == NULL))
+ return;
+ if (dccp_feat_type(feat_num) == FEAT_SP)
+ kfree(val->sp.vec);
+ memset(val, 0, sizeof(*val));
+}
+
+static struct dccp_feat_entry *
+ dccp_feat_clone_entry(struct dccp_feat_entry const *original)
+{
+ struct dccp_feat_entry *new;
+ u8 type = dccp_feat_type(original->feat_num);
+
+ if (type == FEAT_UNKNOWN)
+ return NULL;
+
+ new = kmemdup(original, sizeof(struct dccp_feat_entry), gfp_any());
+ if (new == NULL)
+ return NULL;
+
+ if (type == FEAT_SP && dccp_feat_clone_sp_val(&new->val,
+ original->val.sp.vec,
+ original->val.sp.len)) {
+ kfree(new);
+ return NULL;
+ }
+ return new;
+}
+
+static void dccp_feat_entry_destructor(struct dccp_feat_entry *entry)
+{
+ if (entry != NULL) {
+ dccp_feat_val_destructor(entry->feat_num, &entry->val);
+ kfree(entry);
+ }
+}
+
+/*
+ * List management functions
+ *
+ * Feature negotiation lists rely on and maintain the following invariants:
+ * - each feat_num in the list is known, i.e. we know its type and default value
+ * - each feat_num/is_local combination is unique (old entries are overwritten)
+ * - SP values are always freshly allocated
+ * - list is sorted in increasing order of feature number (faster lookup)
+ */
+static struct dccp_feat_entry *dccp_feat_list_lookup(struct list_head *fn_list,
+ u8 feat_num, bool is_local)
+{
+ struct dccp_feat_entry *entry;
+
+ list_for_each_entry(entry, fn_list, node) {
+ if (entry->feat_num == feat_num && entry->is_local == is_local)
+ return entry;
+ else if (entry->feat_num > feat_num)
+ break;
+ }
+ return NULL;
+}
+
+/**
+ * dccp_feat_entry_new - Central list update routine (called by all others)
+ * @head: list to add to
+ * @feat: feature number
+ * @local: whether the local (1) or remote feature with number @feat is meant
+ * This is the only constructor and serves to ensure the above invariants.
+ */
+static struct dccp_feat_entry *
+ dccp_feat_entry_new(struct list_head *head, u8 feat, bool local)
+{
+ struct dccp_feat_entry *entry;
+
+ list_for_each_entry(entry, head, node)
+ if (entry->feat_num == feat && entry->is_local == local) {
+ dccp_feat_val_destructor(entry->feat_num, &entry->val);
+ return entry;
+ } else if (entry->feat_num > feat) {
+ head = &entry->node;
+ break;
}
+
+ entry = kmalloc(sizeof(*entry), gfp_any());
+ if (entry != NULL) {
+ entry->feat_num = feat;
+ entry->is_local = local;
+ list_add_tail(&entry->node, head);
}
+ return entry;
+}
- /* negotiation for a new feature */
- opt = kmalloc(sizeof(*opt), gfp);
- if (opt == NULL)
+/**
+ * dccp_feat_push_change - Add/overwrite a Change option in the list
+ * @fn_list: feature-negotiation list to update
+ * @feat: one of %dccp_feature_numbers
+ * @local: whether local (1) or remote (0) @feat_num is meant
+ * @needs_mandatory: whether to use Mandatory feature negotiation options
+ * @fval: pointer to NN/SP value to be inserted (will be copied)
+ */
+static int dccp_feat_push_change(struct list_head *fn_list, u8 feat, u8 local,
+ u8 mandatory, dccp_feat_val *fval)
+{
+ struct dccp_feat_entry *new = dccp_feat_entry_new(fn_list, feat, local);
+
+ if (new == NULL)
return -ENOMEM;
- opt->dccpop_type = type;
- opt->dccpop_feat = feature;
- opt->dccpop_len = len;
- opt->dccpop_val = val;
- opt->dccpop_conf = 0;
- opt->dccpop_sc = NULL;
+ new->feat_num = feat;
+ new->is_local = local;
+ new->state = FEAT_INITIALISING;
+ new->needs_confirm = 0;
+ new->empty_confirm = 0;
+ new->val = *fval;
+ new->needs_mandatory = mandatory;
+
+ return 0;
+}
+
+static inline void dccp_feat_list_pop(struct dccp_feat_entry *entry)
+{
+ list_del(&entry->node);
+ dccp_feat_entry_destructor(entry);
+}
+
+void dccp_feat_list_purge(struct list_head *fn_list)
+{
+ struct dccp_feat_entry *entry, *next;
+
+ list_for_each_entry_safe(entry, next, fn_list, node)
+ dccp_feat_entry_destructor(entry);
+ INIT_LIST_HEAD(fn_list);
+}
+EXPORT_SYMBOL_GPL(dccp_feat_list_purge);
+
+/* generate @to as full clone of @from - @to must not contain any nodes */
+int dccp_feat_clone_list(struct list_head const *from, struct list_head *to)
+{
+ struct dccp_feat_entry *entry, *new;
+
+ INIT_LIST_HEAD(to);
+ list_for_each_entry(entry, from, node) {
+ new = dccp_feat_clone_entry(entry);
+ if (new == NULL)
+ goto cloning_failed;
+ list_add_tail(&new->node, to);
+ }
+ return 0;
+
+cloning_failed:
+ dccp_feat_list_purge(to);
+ return -ENOMEM;
+}
+
+static u8 dccp_feat_is_valid_nn_val(u8 feat_num, u64 val)
+{
+ switch (feat_num) {
+ case DCCPF_ACK_RATIO:
+ return val <= DCCPF_ACK_RATIO_MAX;
+ case DCCPF_SEQUENCE_WINDOW:
+ return val >= DCCPF_SEQ_WMIN && val <= DCCPF_SEQ_WMAX;
+ }
+ return 0; /* feature unknown - so we can't tell */
+}
+
+/* check that SP values are within the ranges defined in RFC 4340 */
+static u8 dccp_feat_is_valid_sp_val(u8 feat_num, u8 val)
+{
+ switch (feat_num) {
+ case DCCPF_CCID:
+ return val == DCCPC_CCID2 || val == DCCPC_CCID3;
+ /* Type-check Boolean feature values: */
+ case DCCPF_SHORT_SEQNOS:
+ case DCCPF_ECN_INCAPABLE:
+ case DCCPF_SEND_ACK_VECTOR:
+ case DCCPF_SEND_NDP_COUNT:
+ case DCCPF_DATA_CHECKSUM:
+ case DCCPF_SEND_LEV_RATE:
+ return val < 2;
+ case DCCPF_MIN_CSUM_COVER:
+ return val < 16;
+ }
+ return 0; /* feature unknown */
+}
+
+static u8 dccp_feat_sp_list_ok(u8 feat_num, u8 const *sp_list, u8 sp_len)
+{
+ if (sp_list == NULL || sp_len < 1)
+ return 0;
+ while (sp_len--)
+ if (!dccp_feat_is_valid_sp_val(feat_num, *sp_list++))
+ return 0;
+ return 1;
+}
+
+/**
+ * __feat_register_nn - Register new NN value on socket
+ * @fn: feature-negotiation list to register with
+ * @feat: an NN feature from %dccp_feature_numbers
+ * @mandatory: use Mandatory option if 1
+ * @nn_val: value to register (restricted to 4 bytes)
+ * Note that NN features are local by definition (RFC 4340, 6.3.2).
+ */
+static int __feat_register_nn(struct list_head *fn, u8 feat,
+ u8 mandatory, u64 nn_val)
+{
+ dccp_feat_val fval = { .nn = nn_val };
+
+ if (dccp_feat_type(feat) != FEAT_NN ||
+ !dccp_feat_is_valid_nn_val(feat, nn_val))
+ return -EINVAL;
+
+ /* Don't bother with default values, they will be activated anyway. */
+ if (nn_val - (u64)dccp_feat_default_value(feat) == 0)
+ return 0;
+
+ return dccp_feat_push_change(fn, feat, 1, mandatory, &fval);
+}
+
+/**
+ * __feat_register_sp - Register new SP value/list on socket
+ * @fn: feature-negotiation list to register with
+ * @feat: an SP feature from %dccp_feature_numbers
+ * @is_local: whether the local (1) or the remote (0) @feat is meant
+ * @mandatory: use Mandatory option if 1
+ * @sp_val: SP value followed by optional preference list
+ * @sp_len: length of @sp_val in bytes
+ */
+static int __feat_register_sp(struct list_head *fn, u8 feat, u8 is_local,
+ u8 mandatory, u8 const *sp_val, u8 sp_len)
+{
+ dccp_feat_val fval;
+
+ if (dccp_feat_type(feat) != FEAT_SP ||
+ !dccp_feat_sp_list_ok(feat, sp_val, sp_len))
+ return -EINVAL;
+
+ /* Avoid negotiating alien CCIDs by only advertising supported ones */
+ if (feat == DCCPF_CCID && !ccid_support_check(sp_val, sp_len))
+ return -EOPNOTSUPP;
- BUG_ON(opt->dccpop_val == NULL);
+ if (dccp_feat_clone_sp_val(&fval, sp_val, sp_len))
+ return -ENOMEM;
- list_add_tail(&opt->dccpop_node, &dmsk->dccpms_pending);
+ return dccp_feat_push_change(fn, feat, is_local, mandatory, &fval);
+}
+
+/**
+ * dccp_feat_register_sp - Register requests to change SP feature values
+ * @sk: client or listening socket
+ * @feat: one of %dccp_feature_numbers
+ * @is_local: whether the local (1) or remote (0) @feat is meant
+ * @list: array of preferred values, in descending order of preference
+ * @len: length of @list in bytes
+ */
+int dccp_feat_register_sp(struct sock *sk, u8 feat, u8 is_local,
+ u8 const *list, u8 len)
+{ /* any changes must be registered before establishing the connection */
+ if (sk->sk_state != DCCP_CLOSED)
+ return -EISCONN;
+ if (dccp_feat_type(feat) != FEAT_SP)
+ return -EINVAL;
+ return __feat_register_sp(&dccp_sk(sk)->dccps_featneg, feat, is_local,
+ 0, list, len);
+}
+
+/* Analogous to dccp_feat_register_sp(), but for non-negotiable values */
+int dccp_feat_register_nn(struct sock *sk, u8 feat, u64 val)
+{
+ /* any changes must be registered before establishing the connection */
+ if (sk->sk_state != DCCP_CLOSED)
+ return -EISCONN;
+ if (dccp_feat_type(feat) != FEAT_NN)
+ return -EINVAL;
+ return __feat_register_nn(&dccp_sk(sk)->dccps_featneg, feat, 0, val);
+}
+
+/*
+ * Tracking features whose value depend on the choice of CCID
+ *
+ * This is designed with an extension in mind so that a list walk could be done
+ * before activating any features. However, the existing framework was found to
+ * work satisfactorily up until now, the automatic verification is left open.
+ * When adding new CCIDs, add a corresponding dependency table here.
+ */
+static const struct ccid_dependency *dccp_feat_ccid_deps(u8 ccid, bool is_local)
+{
+ static const struct ccid_dependency ccid2_dependencies[2][2] = {
+ /*
+ * CCID2 mandates Ack Vectors (RFC 4341, 4.): as CCID is a TX
+ * feature and Send Ack Vector is an RX feature, `is_local'
+ * needs to be reversed.
+ */
+ { /* Dependencies of the receiver-side (remote) CCID2 */
+ {
+ .dependent_feat = DCCPF_SEND_ACK_VECTOR,
+ .is_local = true,
+ .is_mandatory = true,
+ .val = 1
+ },
+ { 0, 0, 0, 0 }
+ },
+ { /* Dependencies of the sender-side (local) CCID2 */
+ {
+ .dependent_feat = DCCPF_SEND_ACK_VECTOR,
+ .is_local = false,
+ .is_mandatory = true,
+ .val = 1
+ },
+ { 0, 0, 0, 0 }
+ }
+ };
+ static const struct ccid_dependency ccid3_dependencies[2][5] = {
+ { /*
+ * Dependencies of the receiver-side CCID3
+ */
+ { /* locally disable Ack Vectors */
+ .dependent_feat = DCCPF_SEND_ACK_VECTOR,
+ .is_local = true,
+ .is_mandatory = false,
+ .val = 0
+ },
+ { /* see below why Send Loss Event Rate is on */
+ .dependent_feat = DCCPF_SEND_LEV_RATE,
+ .is_local = true,
+ .is_mandatory = true,
+ .val = 1
+ },
+ { /* NDP Count is needed as per RFC 4342, 6.1.1 */
+ .dependent_feat = DCCPF_SEND_NDP_COUNT,
+ .is_local = false,
+ .is_mandatory = true,
+ .val = 1
+ },
+ { 0, 0, 0, 0 },
+ },
+ { /*
+ * CCID3 at the TX side: we request that the HC-receiver
+ * will not send Ack Vectors (they will be ignored, so
+ * Mandatory is not set); we enable Send Loss Event Rate
+ * (Mandatory since the implementation does not support
+ * the Loss Intervals option of RFC 4342, 8.6).
+ * The last two options are for peer's information only.
+ */
+ {
+ .dependent_feat = DCCPF_SEND_ACK_VECTOR,
+ .is_local = false,
+ .is_mandatory = false,
+ .val = 0
+ },
+ {
+ .dependent_feat = DCCPF_SEND_LEV_RATE,
+ .is_local = false,
+ .is_mandatory = true,
+ .val = 1
+ },
+ { /* this CCID does not support Ack Ratio */
+ .dependent_feat = DCCPF_ACK_RATIO,
+ .is_local = true,
+ .is_mandatory = false,
+ .val = 0
+ },
+ { /* tell receiver we are sending NDP counts */
+ .dependent_feat = DCCPF_SEND_NDP_COUNT,
+ .is_local = true,
+ .is_mandatory = false,
+ .val = 1
+ },
+ { 0, 0, 0, 0 }
+ }
+ };
+ switch (ccid) {
+ case DCCPC_CCID2:
+ return ccid2_dependencies[is_local];
+ case DCCPC_CCID3:
+ return ccid3_dependencies[is_local];
+ default:
+ return NULL;
+ }
+}
+
+/**
+ * dccp_feat_propagate_ccid - Resolve dependencies of features on choice of CCID
+ * @fn: feature-negotiation list to update
+ * @id: CCID number to track
+ * @is_local: whether TX CCID (1) or RX CCID (0) is meant
+ * This function needs to be called after registering all other features.
+ */
+static int dccp_feat_propagate_ccid(struct list_head *fn, u8 id, bool is_local)
+{
+ const struct ccid_dependency *table = dccp_feat_ccid_deps(id, is_local);
+ int i, rc = (table == NULL);
+
+ for (i = 0; rc == 0 && table[i].dependent_feat != DCCPF_RESERVED; i++)
+ if (dccp_feat_type(table[i].dependent_feat) == FEAT_SP)
+ rc = __feat_register_sp(fn, table[i].dependent_feat,
+ table[i].is_local,
+ table[i].is_mandatory,
+ &table[i].val, 1);
+ else
+ rc = __feat_register_nn(fn, table[i].dependent_feat,
+ table[i].is_mandatory,
+ table[i].val);
+ return rc;
+}
+
+/**
+ * dccp_feat_finalise_settings - Finalise settings before starting negotiation
+ * @dp: client or listening socket (settings will be inherited)
+ * This is called after all registrations (socket initialisation, sysctls, and
+ * sockopt calls), and before sending the first packet containing Change options
+ * (ie. client-Request or server-Response), to ensure internal consistency.
+ */
+int dccp_feat_finalise_settings(struct dccp_sock *dp)
+{
+ struct list_head *fn = &dp->dccps_featneg;
+ struct dccp_feat_entry *entry;
+ int i = 2, ccids[2] = { -1, -1 };
+
+ /*
+ * Propagating CCIDs:
+ * 1) not useful to propagate CCID settings if this host advertises more
+ * than one CCID: the choice of CCID may still change - if this is
+ * the client, or if this is the server and the client sends
+ * singleton CCID values.
+ * 2) since is that propagate_ccid changes the list, we defer changing
+ * the sorted list until after the traversal.
+ */
+ list_for_each_entry(entry, fn, node)
+ if (entry->feat_num == DCCPF_CCID && entry->val.sp.len == 1)
+ ccids[entry->is_local] = entry->val.sp.vec[0];
+ while (i--)
+ if (ccids[i] > 0 && dccp_feat_propagate_ccid(fn, ccids[i], i))
+ return -1;
return 0;
}
-EXPORT_SYMBOL_GPL(dccp_feat_change);
+/**
+ * dccp_feat_server_ccid_dependencies - Resolve CCID-dependent features
+ * It is the server which resolves the dependencies once the CCID has been
+ * fully negotiated. If no CCID has been negotiated, it uses the default CCID.
+ */
+int dccp_feat_server_ccid_dependencies(struct dccp_request_sock *dreq)
+{
+ struct list_head *fn = &dreq->dreq_featneg;
+ struct dccp_feat_entry *entry;
+ u8 is_local, ccid;
+
+ for (is_local = 0; is_local <= 1; is_local++) {
+ entry = dccp_feat_list_lookup(fn, DCCPF_CCID, is_local);
+
+ if (entry != NULL && !entry->empty_confirm)
+ ccid = entry->val.sp.vec[0];
+ else
+ ccid = dccp_feat_default_value(DCCPF_CCID);
+
+ if (dccp_feat_propagate_ccid(fn, ccid, is_local))
+ return -1;
+ }
+ return 0;
+}
static int dccp_feat_update_ccid(struct sock *sk, u8 type, u8 new_ccid_nr)
{
@@ -377,6 +886,9 @@ int dccp_feat_change_recv(struct sock *sk, u8 type, u8 feature, u8 *val, u8 len)
{
int rc;
+ /* Ignore Change requests other than during connection setup */
+ if (sk->sk_state != DCCP_LISTEN && sk->sk_state != DCCP_REQUESTING)
+ return 0;
dccp_feat_debug(type, feature, *val);
/* figure out if it's SP or NN feature */
@@ -426,6 +938,9 @@ int dccp_feat_confirm_recv(struct sock *sk, u8 type, u8 feature,
int found = 0;
int all_confirmed = 1;
+ /* Ignore Confirm options other than during connection setup */
+ if (sk->sk_state != DCCP_LISTEN && sk->sk_state != DCCP_REQUESTING)
+ return 0;
dccp_feat_debug(type, feature, *val);
/* locate our change request */
@@ -460,17 +975,6 @@ int dccp_feat_confirm_recv(struct sock *sk, u8 type, u8 feature,
all_confirmed = 0;
}
- /* fix re-transmit timer */
- /* XXX gotta make sure that no option negotiation occurs during
- * connection shutdown. Consider that the CLOSEREQ is sent and timer is
- * on. if all options are confirmed it might kill timer which should
- * remain alive until close is received.
- */
- if (all_confirmed) {
- dccp_pr_debug("clear feat negotiation timer %p\n", sk);
- inet_csk_clear_xmit_timer(sk, ICSK_TIME_RETRANS);
- }
-
if (!found)
dccp_pr_debug("%s(%d, ...) never requested\n",
dccp_feat_typename(type), feature);
@@ -564,42 +1068,30 @@ out_clean:
EXPORT_SYMBOL_GPL(dccp_feat_clone);
-static int __dccp_feat_init(struct dccp_minisock *dmsk, u8 type, u8 feat,
- u8 *val, u8 len)
-{
- int rc = -ENOMEM;
- u8 *copy = kmemdup(val, len, GFP_KERNEL);
-
- if (copy != NULL) {
- rc = dccp_feat_change(dmsk, type, feat, copy, len, GFP_KERNEL);
- if (rc)
- kfree(copy);
- }
- return rc;
-}
-
-int dccp_feat_init(struct dccp_minisock *dmsk)
+int dccp_feat_init(struct sock *sk)
{
+ struct dccp_sock *dp = dccp_sk(sk);
+ struct dccp_minisock *dmsk = dccp_msk(sk);
int rc;
- INIT_LIST_HEAD(&dmsk->dccpms_pending);
- INIT_LIST_HEAD(&dmsk->dccpms_conf);
+ INIT_LIST_HEAD(&dmsk->dccpms_pending); /* XXX no longer used */
+ INIT_LIST_HEAD(&dmsk->dccpms_conf); /* XXX no longer used */
/* CCID L */
- rc = __dccp_feat_init(dmsk, DCCPO_CHANGE_L, DCCPF_CCID,
- &dmsk->dccpms_tx_ccid, 1);
+ rc = __feat_register_sp(&dp->dccps_featneg, DCCPF_CCID, 1, 0,
+ &dmsk->dccpms_tx_ccid, 1);
if (rc)
goto out;
/* CCID R */
- rc = __dccp_feat_init(dmsk, DCCPO_CHANGE_R, DCCPF_CCID,
- &dmsk->dccpms_rx_ccid, 1);
+ rc = __feat_register_sp(&dp->dccps_featneg, DCCPF_CCID, 0, 0,
+ &dmsk->dccpms_rx_ccid, 1);
if (rc)
goto out;
/* Ack ratio */
- rc = __dccp_feat_init(dmsk, DCCPO_CHANGE_L, DCCPF_ACK_RATIO,
- &dmsk->dccpms_ack_ratio, 1);
+ rc = __feat_register_nn(&dp->dccps_featneg, DCCPF_ACK_RATIO, 0,
+ dp->dccps_l_ack_ratio);
out:
return rc;
}
@@ -639,6 +1131,8 @@ const char *dccp_feat_name(const u8 feat)
if (feat > DCCPF_DATA_CHECKSUM && feat < DCCPF_MIN_CCID_SPECIFIC)
return feature_names[DCCPF_RESERVED];
+ if (feat == DCCPF_SEND_LEV_RATE)
+ return "Send Loss Event Rate";
if (feat >= DCCPF_MIN_CCID_SPECIFIC)
return "CCID-specific";
diff --git a/net/dccp/feat.h b/net/dccp/feat.h
index e272222c7ace..7efb2025f6bf 100644
--- a/net/dccp/feat.h
+++ b/net/dccp/feat.h
@@ -14,6 +14,92 @@
#include <linux/types.h>
#include "dccp.h"
+/*
+ * Known limit values
+ */
+/* Ack Ratio takes 2-byte integer values (11.3) */
+#define DCCPF_ACK_RATIO_MAX 0xFFFF
+/* Wmin=32 and Wmax=2^46-1 from 7.5.2 */
+#define DCCPF_SEQ_WMIN 32
+#define DCCPF_SEQ_WMAX 0x3FFFFFFFFFFFull
+/* Maximum number of SP values that fit in a single (Confirm) option */
+#define DCCP_FEAT_MAX_SP_VALS (DCCP_SINGLE_OPT_MAXLEN - 2)
+
+enum dccp_feat_type {
+ FEAT_AT_RX = 1, /* located at RX side of half-connection */
+ FEAT_AT_TX = 2, /* located at TX side of half-connection */
+ FEAT_SP = 4, /* server-priority reconciliation (6.3.1) */
+ FEAT_NN = 8, /* non-negotiable reconciliation (6.3.2) */
+ FEAT_UNKNOWN = 0xFF /* not understood or invalid feature */
+};
+
+enum dccp_feat_state {
+ FEAT_DEFAULT = 0, /* using default values from 6.4 */
+ FEAT_INITIALISING, /* feature is being initialised */
+ FEAT_CHANGING, /* Change sent but not confirmed yet */
+ FEAT_UNSTABLE, /* local modification in state CHANGING */
+ FEAT_STABLE /* both ends (think they) agree */
+};
+
+/**
+ * dccp_feat_val - Container for SP or NN feature values
+ * @nn: single NN value
+ * @sp.vec: single SP value plus optional preference list
+ * @sp.len: length of @sp.vec in bytes
+ */
+typedef union {
+ u64 nn;
+ struct {
+ u8 *vec;
+ u8 len;
+ } sp;
+} dccp_feat_val;
+
+/**
+ * struct feat_entry - Data structure to perform feature negotiation
+ * @val: feature's current value (SP features may have preference list)
+ * @state: feature's current state
+ * @feat_num: one of %dccp_feature_numbers
+ * @needs_mandatory: whether Mandatory options should be sent
+ * @needs_confirm: whether to send a Confirm instead of a Change
+ * @empty_confirm: whether to send an empty Confirm (depends on @needs_confirm)
+ * @is_local: feature location (1) or feature-remote (0)
+ * @node: list pointers, entries arranged in FIFO order
+ */
+struct dccp_feat_entry {
+ dccp_feat_val val;
+ enum dccp_feat_state state:8;
+ u8 feat_num;
+
+ bool needs_mandatory,
+ needs_confirm,
+ empty_confirm,
+ is_local;
+
+ struct list_head node;
+};
+
+static inline u8 dccp_feat_genopt(struct dccp_feat_entry *entry)
+{
+ if (entry->needs_confirm)
+ return entry->is_local ? DCCPO_CONFIRM_L : DCCPO_CONFIRM_R;
+ return entry->is_local ? DCCPO_CHANGE_L : DCCPO_CHANGE_R;
+}
+
+/**
+ * struct ccid_dependency - Track changes resulting from choosing a CCID
+ * @dependent_feat: one of %dccp_feature_numbers
+ * @is_local: local (1) or remote (0) @dependent_feat
+ * @is_mandatory: whether presence of @dependent_feat is mission-critical or not
+ * @val: corresponding default value for @dependent_feat (u8 is sufficient here)
+ */
+struct ccid_dependency {
+ u8 dependent_feat;
+ bool is_local:1,
+ is_mandatory:1;
+ u8 val;
+};
+
#ifdef CONFIG_IP_DCCP_DEBUG
extern const char *dccp_feat_typename(const u8 type);
extern const char *dccp_feat_name(const u8 feat);
@@ -27,14 +113,34 @@ static inline void dccp_feat_debug(const u8 type, const u8 feat, const u8 val)
#define dccp_feat_debug(type, feat, val)
#endif /* CONFIG_IP_DCCP_DEBUG */
-extern int dccp_feat_change(struct dccp_minisock *dmsk, u8 type, u8 feature,
- u8 *val, u8 len, gfp_t gfp);
+extern int dccp_feat_register_sp(struct sock *sk, u8 feat, u8 is_local,
+ u8 const *list, u8 len);
+extern int dccp_feat_register_nn(struct sock *sk, u8 feat, u64 val);
extern int dccp_feat_change_recv(struct sock *sk, u8 type, u8 feature,
u8 *val, u8 len);
extern int dccp_feat_confirm_recv(struct sock *sk, u8 type, u8 feature,
u8 *val, u8 len);
extern void dccp_feat_clean(struct dccp_minisock *dmsk);
extern int dccp_feat_clone(struct sock *oldsk, struct sock *newsk);
-extern int dccp_feat_init(struct dccp_minisock *dmsk);
+extern int dccp_feat_clone_list(struct list_head const *, struct list_head *);
+extern int dccp_feat_init(struct sock *sk);
+
+/*
+ * Encoding variable-length options and their maximum length.
+ *
+ * This affects NN options (SP options are all u8) and other variable-length
+ * options (see table 3 in RFC 4340). The limit is currently given the Sequence
+ * Window NN value (sec. 7.5.2) and the NDP count (sec. 7.7) option, all other
+ * options consume less than 6 bytes (timestamps are 4 bytes).
+ * When updating this constant (e.g. due to new internet drafts / RFCs), make
+ * sure that you also update all code which refers to it.
+ */
+#define DCCP_OPTVAL_MAXLEN 6
+
+extern void dccp_encode_value_var(const u64 value, u8 *to, const u8 len);
+extern u64 dccp_decode_value_var(const u8 *bf, const u8 len);
+extern int dccp_insert_option_mandatory(struct sk_buff *skb);
+extern int dccp_insert_fn_opt(struct sk_buff *skb, u8 type, u8 feat,
+ u8 *val, u8 len, bool repeat_first);
#endif /* _DCCP_FEAT_H */
diff --git a/net/dccp/input.c b/net/dccp/input.c
index 779d0ed9ae94..3070015edc75 100644
--- a/net/dccp/input.c
+++ b/net/dccp/input.c
@@ -590,8 +590,6 @@ int dccp_rcv_state_process(struct sock *sk, struct sk_buff *skb,
if (inet_csk(sk)->icsk_af_ops->conn_request(sk,
skb) < 0)
return 1;
-
- /* FIXME: do congestion control initialization */
goto discard;
}
if (dh->dccph_type == DCCP_PKT_RESET)
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 01e3e0206254..d1dd95289b89 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -545,6 +545,7 @@ out:
static void dccp_v4_reqsk_destructor(struct request_sock *req)
{
+ dccp_feat_list_purge(&dccp_rsk(req)->dreq_featneg);
kfree(inet_rsk(req)->opt);
}
@@ -595,7 +596,8 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
if (req == NULL)
goto drop;
- dccp_reqsk_init(req, skb);
+ if (dccp_reqsk_init(req, dccp_sk(sk), skb))
+ goto drop_and_free;
dreq = dccp_rsk(req);
if (dccp_parse_options(sk, dreq, skb))
@@ -936,6 +938,7 @@ static struct proto dccp_v4_prot = {
.orphan_count = &dccp_orphan_count,
.max_header = MAX_DCCP_HEADER,
.obj_size = sizeof(struct dccp_sock),
+ .slab_flags = SLAB_DESTROY_BY_RCU,
.rsk_prot = &dccp_request_sock_ops,
.twsk_prot = &dccp_timewait_sock_ops,
.h.hashinfo = &dccp_hashinfo,
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index d4ce1224e008..b963f35c65f6 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -168,7 +168,7 @@ static void dccp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
goto out;
}
- err = xfrm_lookup(&dst, &fl, sk, 0);
+ err = xfrm_lookup(net, &dst, &fl, sk, 0);
if (err < 0) {
sk->sk_err_soft = -err;
goto out;
@@ -279,7 +279,7 @@ static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
if (final_p)
ipv6_addr_copy(&fl.fl6_dst, final_p);
- err = xfrm_lookup(&dst, &fl, sk, 0);
+ err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0);
if (err < 0)
goto done;
@@ -304,6 +304,7 @@ done:
static void dccp_v6_reqsk_destructor(struct request_sock *req)
{
+ dccp_feat_list_purge(&dccp_rsk(req)->dreq_featneg);
if (inet6_rsk(req)->pktopts != NULL)
kfree_skb(inet6_rsk(req)->pktopts);
}
@@ -342,7 +343,7 @@ static void dccp_v6_ctl_send_reset(struct sock *sk, struct sk_buff *rxskb)
/* sk = NULL, but it is safe for now. RST socket required. */
if (!ip6_dst_lookup(ctl_sk, &skb->dst, &fl)) {
- if (xfrm_lookup(&skb->dst, &fl, NULL, 0) >= 0) {
+ if (xfrm_lookup(net, &skb->dst, &fl, NULL, 0) >= 0) {
ip6_xmit(ctl_sk, skb, &fl, NULL, 0);
DCCP_INC_STATS_BH(DCCP_MIB_OUTSEGS);
DCCP_INC_STATS_BH(DCCP_MIB_OUTRSTS);
@@ -426,7 +427,8 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
if (req == NULL)
goto drop;
- dccp_reqsk_init(req, skb);
+ if (dccp_reqsk_init(req, dccp_sk(sk), skb))
+ goto drop_and_free;
dreq = dccp_rsk(req);
if (dccp_parse_options(sk, dreq, skb))
@@ -567,7 +569,7 @@ static struct sock *dccp_v6_request_recv_sock(struct sock *sk,
if (final_p)
ipv6_addr_copy(&fl.fl6_dst, final_p);
- if ((xfrm_lookup(&dst, &fl, sk, 0)) < 0)
+ if ((xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0)
goto out;
}
@@ -1002,7 +1004,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr,
if (final_p)
ipv6_addr_copy(&fl.fl6_dst, final_p);
- err = __xfrm_lookup(&dst, &fl, sk, XFRM_LOOKUP_WAIT);
+ err = __xfrm_lookup(sock_net(sk), &dst, &fl, sk, XFRM_LOOKUP_WAIT);
if (err < 0) {
if (err == -EREMOTE)
err = ip6_dst_blackhole(sk, &dst, &fl);
@@ -1138,6 +1140,7 @@ static struct proto dccp_v6_prot = {
.orphan_count = &dccp_orphan_count,
.max_header = MAX_DCCP_HEADER,
.obj_size = sizeof(struct dccp6_sock),
+ .slab_flags = SLAB_DESTROY_BY_RCU,
.rsk_prot = &dccp6_request_sock_ops,
.twsk_prot = &dccp6_timewait_sock_ops,
.h.hashinfo = &dccp_hashinfo,
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index e6bf99e3e41a..ed61bc58e41e 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -47,7 +47,6 @@ void dccp_minisock_init(struct dccp_minisock *dmsk)
dmsk->dccpms_sequence_window = sysctl_dccp_feat_sequence_window;
dmsk->dccpms_rx_ccid = sysctl_dccp_feat_rx_ccid;
dmsk->dccpms_tx_ccid = sysctl_dccp_feat_tx_ccid;
- dmsk->dccpms_ack_ratio = sysctl_dccp_feat_ack_ratio;
dmsk->dccpms_send_ack_vector = sysctl_dccp_feat_send_ack_vector;
dmsk->dccpms_send_ndp_count = sysctl_dccp_feat_send_ndp_count;
}
@@ -125,6 +124,7 @@ struct sock *dccp_create_openreq_child(struct sock *sk,
newdp->dccps_timestamp_time = dreq->dreq_timestamp_time;
newicsk->icsk_rto = DCCP_TIMEOUT_INIT;
+ INIT_LIST_HEAD(&newdp->dccps_featneg);
if (dccp_feat_clone(sk, newsk))
goto out_free;
@@ -304,7 +304,8 @@ void dccp_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
EXPORT_SYMBOL_GPL(dccp_reqsk_send_ack);
-void dccp_reqsk_init(struct request_sock *req, struct sk_buff *skb)
+int dccp_reqsk_init(struct request_sock *req,
+ struct dccp_sock const *dp, struct sk_buff const *skb)
{
struct dccp_request_sock *dreq = dccp_rsk(req);
@@ -313,6 +314,9 @@ void dccp_reqsk_init(struct request_sock *req, struct sk_buff *skb)
inet_rsk(req)->acked = 0;
req->rcv_wnd = sysctl_dccp_feat_sequence_window;
dreq->dreq_timestamp_echo = 0;
+
+ /* inherit feature negotiation options from listening socket */
+ return dccp_feat_clone_list(&dp->dccps_featneg, &dreq->dreq_featneg);
}
EXPORT_SYMBOL_GPL(dccp_reqsk_init);
diff --git a/net/dccp/options.c b/net/dccp/options.c
index 0809b63cb055..20d5c72d1fdb 100644
--- a/net/dccp/options.c
+++ b/net/dccp/options.c
@@ -26,20 +26,23 @@
int sysctl_dccp_feat_sequence_window = DCCPF_INITIAL_SEQUENCE_WINDOW;
int sysctl_dccp_feat_rx_ccid = DCCPF_INITIAL_CCID;
int sysctl_dccp_feat_tx_ccid = DCCPF_INITIAL_CCID;
-int sysctl_dccp_feat_ack_ratio = DCCPF_INITIAL_ACK_RATIO;
int sysctl_dccp_feat_send_ack_vector = DCCPF_INITIAL_SEND_ACK_VECTOR;
int sysctl_dccp_feat_send_ndp_count = DCCPF_INITIAL_SEND_NDP_COUNT;
-static u32 dccp_decode_value_var(const unsigned char *bf, const u8 len)
+u64 dccp_decode_value_var(const u8 *bf, const u8 len)
{
- u32 value = 0;
+ u64 value = 0;
+ if (len >= DCCP_OPTVAL_MAXLEN)
+ value += ((u64)*bf++) << 40;
+ if (len > 4)
+ value += ((u64)*bf++) << 32;
if (len > 3)
- value += *bf++ << 24;
+ value += ((u64)*bf++) << 24;
if (len > 2)
- value += *bf++ << 16;
+ value += ((u64)*bf++) << 16;
if (len > 1)
- value += *bf++ << 8;
+ value += ((u64)*bf++) << 8;
if (len > 0)
value += *bf;
@@ -64,7 +67,7 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq,
(dh->dccph_doff * 4);
struct dccp_options_received *opt_recv = &dp->dccps_options_received;
unsigned char opt, len;
- unsigned char *value;
+ unsigned char *uninitialized_var(value);
u32 elapsed_time;
__be32 opt_val;
int rc;
@@ -299,9 +302,12 @@ out_invalid_option:
EXPORT_SYMBOL_GPL(dccp_parse_options);
-static void dccp_encode_value_var(const u32 value, unsigned char *to,
- const unsigned int len)
+void dccp_encode_value_var(const u64 value, u8 *to, const u8 len)
{
+ if (len >= DCCP_OPTVAL_MAXLEN)
+ *to++ = (value & 0xFF0000000000ull) >> 40;
+ if (len > 4)
+ *to++ = (value & 0xFF00000000ull) >> 32;
if (len > 3)
*to++ = (value & 0xFF000000) >> 24;
if (len > 2)
@@ -461,23 +467,61 @@ static int dccp_insert_option_timestamp_echo(struct dccp_sock *dp,
return 0;
}
-static int dccp_insert_feat_opt(struct sk_buff *skb, u8 type, u8 feat,
- u8 *val, u8 len)
+/**
+ * dccp_insert_option_mandatory - Mandatory option (5.8.2)
+ * Note that since we are using skb_push, this function needs to be called
+ * _after_ inserting the option it is supposed to influence (stack order).
+ */
+int dccp_insert_option_mandatory(struct sk_buff *skb)
{
- u8 *to;
+ if (DCCP_SKB_CB(skb)->dccpd_opt_len >= DCCP_MAX_OPT_LEN)
+ return -1;
- if (DCCP_SKB_CB(skb)->dccpd_opt_len + len + 3 > DCCP_MAX_OPT_LEN) {
- DCCP_WARN("packet too small for feature %d option!\n", feat);
+ DCCP_SKB_CB(skb)->dccpd_opt_len++;
+ *skb_push(skb, 1) = DCCPO_MANDATORY;
+ return 0;
+}
+
+/**
+ * dccp_insert_fn_opt - Insert single Feature-Negotiation option into @skb
+ * @type: %DCCPO_CHANGE_L, %DCCPO_CHANGE_R, %DCCPO_CONFIRM_L, %DCCPO_CONFIRM_R
+ * @feat: one out of %dccp_feature_numbers
+ * @val: NN value or SP array (preferred element first) to copy
+ * @len: true length of @val in bytes (excluding first element repetition)
+ * @repeat_first: whether to copy the first element of @val twice
+ * The last argument is used to construct Confirm options, where the preferred
+ * value and the preference list appear separately (RFC 4340, 6.3.1). Preference
+ * lists are kept such that the preferred entry is always first, so we only need
+ * to copy twice, and avoid the overhead of cloning into a bigger array.
+ */
+int dccp_insert_fn_opt(struct sk_buff *skb, u8 type, u8 feat,
+ u8 *val, u8 len, bool repeat_first)
+{
+ u8 tot_len, *to;
+
+ /* take the `Feature' field and possible repetition into account */
+ if (len > (DCCP_SINGLE_OPT_MAXLEN - 2)) {
+ DCCP_WARN("length %u for feature %u too large\n", len, feat);
return -1;
}
- DCCP_SKB_CB(skb)->dccpd_opt_len += len + 3;
+ if (unlikely(val == NULL || len == 0))
+ len = repeat_first = 0;
+ tot_len = 3 + repeat_first + len;
+
+ if (DCCP_SKB_CB(skb)->dccpd_opt_len + tot_len > DCCP_MAX_OPT_LEN) {
+ DCCP_WARN("packet too small for feature %d option!\n", feat);
+ return -1;
+ }
+ DCCP_SKB_CB(skb)->dccpd_opt_len += tot_len;
- to = skb_push(skb, len + 3);
+ to = skb_push(skb, tot_len);
*to++ = type;
- *to++ = len + 3;
+ *to++ = tot_len;
*to++ = feat;
+ if (repeat_first)
+ *to++ = *val;
if (len)
memcpy(to, val, len);
@@ -487,69 +531,6 @@ static int dccp_insert_feat_opt(struct sk_buff *skb, u8 type, u8 feat,
return 0;
}
-static int dccp_insert_options_feat(struct sock *sk, struct sk_buff *skb)
-{
- struct dccp_sock *dp = dccp_sk(sk);
- struct dccp_minisock *dmsk = dccp_msk(sk);
- struct dccp_opt_pend *opt, *next;
- int change = 0;
-
- /* confirm any options [NN opts] */
- list_for_each_entry_safe(opt, next, &dmsk->dccpms_conf, dccpop_node) {
- dccp_insert_feat_opt(skb, opt->dccpop_type,
- opt->dccpop_feat, opt->dccpop_val,
- opt->dccpop_len);
- /* fear empty confirms */
- if (opt->dccpop_val)
- kfree(opt->dccpop_val);
- kfree(opt);
- }
- INIT_LIST_HEAD(&dmsk->dccpms_conf);
-
- /* see which features we need to send */
- list_for_each_entry(opt, &dmsk->dccpms_pending, dccpop_node) {
- /* see if we need to send any confirm */
- if (opt->dccpop_sc) {
- dccp_insert_feat_opt(skb, opt->dccpop_type + 1,
- opt->dccpop_feat,
- opt->dccpop_sc->dccpoc_val,
- opt->dccpop_sc->dccpoc_len);
-
- BUG_ON(!opt->dccpop_sc->dccpoc_val);
- kfree(opt->dccpop_sc->dccpoc_val);
- kfree(opt->dccpop_sc);
- opt->dccpop_sc = NULL;
- }
-
- /* any option not confirmed, re-send it */
- if (!opt->dccpop_conf) {
- dccp_insert_feat_opt(skb, opt->dccpop_type,
- opt->dccpop_feat, opt->dccpop_val,
- opt->dccpop_len);
- change++;
- }
- }
-
- /* Retransmit timer.
- * If this is the master listening sock, we don't set a timer on it. It
- * should be fine because if the dude doesn't receive our RESPONSE
- * [which will contain the CHANGE] he will send another REQUEST which
- * will "retrnasmit" the change.
- */
- if (change && dp->dccps_role != DCCP_ROLE_LISTEN) {
- dccp_pr_debug("reset feat negotiation timer %p\n", sk);
-
- /* XXX don't reset the timer on re-transmissions. I.e. reset it
- * only when sending new stuff i guess. Currently the timer
- * never backs off because on re-transmission it just resets it!
- */
- inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS,
- inet_csk(sk)->icsk_rto, DCCP_RTO_MAX);
- }
-
- return 0;
-}
-
/* The length of all options needs to be a multiple of 4 (5.8) */
static void dccp_insert_option_padding(struct sk_buff *skb)
{
@@ -586,13 +567,6 @@ int dccp_insert_options(struct sock *sk, struct sk_buff *skb)
dp->dccps_hc_rx_insert_options = 0;
}
- /* Feature negotiation */
- /* Data packets can't do feat negotiation */
- if (DCCP_SKB_CB(skb)->dccpd_type != DCCP_PKT_DATA &&
- DCCP_SKB_CB(skb)->dccpd_type != DCCP_PKT_DATAACK &&
- dccp_insert_options_feat(sk, skb))
- return -1;
-
/*
* Obtain RTT sample from Request/Response exchange.
* This is currently used in CCID 3 initialisation.
diff --git a/net/dccp/output.c b/net/dccp/output.c
index 809d803d5006..fea30cdc0bee 100644
--- a/net/dccp/output.c
+++ b/net/dccp/output.c
@@ -339,10 +339,12 @@ struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst,
DCCP_SKB_CB(skb)->dccpd_type = DCCP_PKT_RESPONSE;
DCCP_SKB_CB(skb)->dccpd_seq = dreq->dreq_iss;
- if (dccp_insert_options_rsk(dreq, skb)) {
- kfree_skb(skb);
- return NULL;
- }
+ /* Resolve feature dependencies resulting from choice of CCID */
+ if (dccp_feat_server_ccid_dependencies(dreq))
+ goto response_failed;
+
+ if (dccp_insert_options_rsk(dreq, skb))
+ goto response_failed;
/* Build and checksum header */
dh = dccp_zeroed_hdr(skb, dccp_header_size);
@@ -363,6 +365,9 @@ struct sk_buff *dccp_make_response(struct sock *sk, struct dst_entry *dst,
inet_rsk(req)->acked = 1;
DCCP_INC_STATS(DCCP_MIB_OUTSEGS);
return skb;
+response_failed:
+ kfree_skb(skb);
+ return NULL;
}
EXPORT_SYMBOL_GPL(dccp_make_response);
@@ -469,6 +474,10 @@ int dccp_connect(struct sock *sk)
struct sk_buff *skb;
struct inet_connection_sock *icsk = inet_csk(sk);
+ /* do not connect if feature negotiation setup fails */
+ if (dccp_feat_finalise_settings(dccp_sk(sk)))
+ return -EPROTO;
+
dccp_connect_init(sk);
skb = alloc_skb(sk->sk_prot->max_header, sk->sk_allocation);
diff --git a/net/dccp/probe.c b/net/dccp/probe.c
index 49ba8d5ec4b5..37731da41481 100644
--- a/net/dccp/probe.c
+++ b/net/dccp/probe.c
@@ -74,14 +74,11 @@ static void printl(const char *fmt, ...)
static int jdccp_sendmsg(struct kiocb *iocb, struct sock *sk,
struct msghdr *msg, size_t size)
{
- const struct dccp_minisock *dmsk = dccp_msk(sk);
const struct inet_sock *inet = inet_sk(sk);
- const struct ccid3_hc_tx_sock *hctx;
+ struct ccid3_hc_tx_sock *hctx = NULL;
- if (dmsk->dccpms_tx_ccid == DCCPC_CCID3)
+ if (ccid_get_current_tx_ccid(dccp_sk(sk)) == DCCPC_CCID3)
hctx = ccid3_hc_tx_sk(sk);
- else
- hctx = NULL;
if (port == 0 || ntohs(inet->dport) == port ||
ntohs(inet->sport) == port) {
diff --git a/net/dccp/proto.c b/net/dccp/proto.c
index d0bd34819761..db225f93cd5a 100644
--- a/net/dccp/proto.c
+++ b/net/dccp/proto.c
@@ -40,16 +40,10 @@ DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics) __read_mostly;
EXPORT_SYMBOL_GPL(dccp_statistics);
-atomic_t dccp_orphan_count = ATOMIC_INIT(0);
-
+struct percpu_counter dccp_orphan_count;
EXPORT_SYMBOL_GPL(dccp_orphan_count);
-struct inet_hashinfo __cacheline_aligned dccp_hashinfo = {
- .lhash_lock = RW_LOCK_UNLOCKED,
- .lhash_users = ATOMIC_INIT(0),
- .lhash_wait = __WAIT_QUEUE_HEAD_INITIALIZER(dccp_hashinfo.lhash_wait),
-};
-
+struct inet_hashinfo dccp_hashinfo;
EXPORT_SYMBOL_GPL(dccp_hashinfo);
/* the maximum queue length for tx in packets. 0 is no limit */
@@ -193,6 +187,7 @@ int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized)
dccp_init_xmit_timers(sk);
+ INIT_LIST_HEAD(&dp->dccps_featneg);
/*
* FIXME: We're hardcoding the CCID, and doing this at this point makes
* the listening (master) sock get CCID control blocks, which is not
@@ -201,7 +196,7 @@ int dccp_init_sock(struct sock *sk, const __u8 ctl_sock_initialized)
* setsockopt(CCIDs-I-want/accept). -acme
*/
if (likely(ctl_sock_initialized)) {
- int rc = dccp_feat_init(dmsk);
+ int rc = dccp_feat_init(sk);
if (rc)
return rc;
@@ -267,7 +262,7 @@ void dccp_destroy_sock(struct sock *sk)
dp->dccps_hc_rx_ccid = dp->dccps_hc_tx_ccid = NULL;
/* clean up feature negotiation state */
- dccp_feat_clean(dmsk);
+ dccp_feat_list_purge(&dp->dccps_featneg);
}
EXPORT_SYMBOL_GPL(dccp_destroy_sock);
@@ -277,6 +272,9 @@ static inline int dccp_listen_start(struct sock *sk, int backlog)
struct dccp_sock *dp = dccp_sk(sk);
dp->dccps_role = DCCP_ROLE_LISTEN;
+ /* do not start to listen if feature negotiation setup fails */
+ if (dccp_feat_finalise_settings(dp))
+ return -EPROTO;
return inet_csk_listen_start(sk, backlog);
}
@@ -466,42 +464,70 @@ static int dccp_setsockopt_service(struct sock *sk, const __be32 service,
return 0;
}
-/* byte 1 is feature. the rest is the preference list */
-static int dccp_setsockopt_change(struct sock *sk, int type,
- struct dccp_so_feat __user *optval)
+static int dccp_setsockopt_cscov(struct sock *sk, int cscov, bool rx)
{
- struct dccp_so_feat opt;
- u8 *val;
- int rc;
+ u8 *list, len;
+ int i, rc;
- if (copy_from_user(&opt, optval, sizeof(opt)))
- return -EFAULT;
+ if (cscov < 0 || cscov > 15)
+ return -EINVAL;
/*
- * rfc4340: 6.1. Change Options
+ * Populate a list of permissible values, in the range cscov...15. This
+ * is necessary since feature negotiation of single values only works if
+ * both sides incidentally choose the same value. Since the list starts
+ * lowest-value first, negotiation will pick the smallest shared value.
*/
- if (opt.dccpsf_len < 1)
+ if (cscov == 0)
+ return 0;
+ len = 16 - cscov;
+
+ list = kmalloc(len, GFP_KERNEL);
+ if (list == NULL)
+ return -ENOBUFS;
+
+ for (i = 0; i < len; i++)
+ list[i] = cscov++;
+
+ rc = dccp_feat_register_sp(sk, DCCPF_MIN_CSUM_COVER, rx, list, len);
+
+ if (rc == 0) {
+ if (rx)
+ dccp_sk(sk)->dccps_pcrlen = cscov;
+ else
+ dccp_sk(sk)->dccps_pcslen = cscov;
+ }
+ kfree(list);
+ return rc;
+}
+
+static int dccp_setsockopt_ccid(struct sock *sk, int type,
+ char __user *optval, int optlen)
+{
+ u8 *val;
+ int rc = 0;
+
+ if (optlen < 1 || optlen > DCCP_FEAT_MAX_SP_VALS)
return -EINVAL;
- val = kmalloc(opt.dccpsf_len, GFP_KERNEL);
- if (!val)
+ val = kmalloc(optlen, GFP_KERNEL);
+ if (val == NULL)
return -ENOMEM;
- if (copy_from_user(val, opt.dccpsf_val, opt.dccpsf_len)) {
- rc = -EFAULT;
- goto out_free_val;
+ if (copy_from_user(val, optval, optlen)) {
+ kfree(val);
+ return -EFAULT;
}
- rc = dccp_feat_change(dccp_msk(sk), type, opt.dccpsf_feat,
- val, opt.dccpsf_len, GFP_KERNEL);
- if (rc)
- goto out_free_val;
+ lock_sock(sk);
+ if (type == DCCP_SOCKOPT_TX_CCID || type == DCCP_SOCKOPT_CCID)
+ rc = dccp_feat_register_sp(sk, DCCPF_CCID, 1, val, optlen);
-out:
- return rc;
+ if (!rc && (type == DCCP_SOCKOPT_RX_CCID || type == DCCP_SOCKOPT_CCID))
+ rc = dccp_feat_register_sp(sk, DCCPF_CCID, 0, val, optlen);
+ release_sock(sk);
-out_free_val:
kfree(val);
- goto out;
+ return rc;
}
static int do_dccp_setsockopt(struct sock *sk, int level, int optname,
@@ -510,7 +536,21 @@ static int do_dccp_setsockopt(struct sock *sk, int level, int optname,
struct dccp_sock *dp = dccp_sk(sk);
int val, err = 0;
- if (optlen < sizeof(int))
+ switch (optname) {
+ case DCCP_SOCKOPT_PACKET_SIZE:
+ DCCP_WARN("sockopt(PACKET_SIZE) is deprecated: fix your app\n");
+ return 0;
+ case DCCP_SOCKOPT_CHANGE_L:
+ case DCCP_SOCKOPT_CHANGE_R:
+ DCCP_WARN("sockopt(CHANGE_L/R) is deprecated: fix your app\n");
+ return 0;
+ case DCCP_SOCKOPT_CCID:
+ case DCCP_SOCKOPT_RX_CCID:
+ case DCCP_SOCKOPT_TX_CCID:
+ return dccp_setsockopt_ccid(sk, optname, optval, optlen);
+ }
+
+ if (optlen < (int)sizeof(int))
return -EINVAL;
if (get_user(val, (int __user *)optval))
@@ -521,53 +561,24 @@ static int do_dccp_setsockopt(struct sock *sk, int level, int optname,
lock_sock(sk);
switch (optname) {
- case DCCP_SOCKOPT_PACKET_SIZE:
- DCCP_WARN("sockopt(PACKET_SIZE) is deprecated: fix your app\n");
- err = 0;
- break;
- case DCCP_SOCKOPT_CHANGE_L:
- if (optlen != sizeof(struct dccp_so_feat))
- err = -EINVAL;
- else
- err = dccp_setsockopt_change(sk, DCCPO_CHANGE_L,
- (struct dccp_so_feat __user *)
- optval);
- break;
- case DCCP_SOCKOPT_CHANGE_R:
- if (optlen != sizeof(struct dccp_so_feat))
- err = -EINVAL;
- else
- err = dccp_setsockopt_change(sk, DCCPO_CHANGE_R,
- (struct dccp_so_feat __user *)
- optval);
- break;
case DCCP_SOCKOPT_SERVER_TIMEWAIT:
if (dp->dccps_role != DCCP_ROLE_SERVER)
err = -EOPNOTSUPP;
else
dp->dccps_server_timewait = (val != 0);
break;
- case DCCP_SOCKOPT_SEND_CSCOV: /* sender side, RFC 4340, sec. 9.2 */
- if (val < 0 || val > 15)
- err = -EINVAL;
- else
- dp->dccps_pcslen = val;
+ case DCCP_SOCKOPT_SEND_CSCOV:
+ err = dccp_setsockopt_cscov(sk, val, false);
break;
- case DCCP_SOCKOPT_RECV_CSCOV: /* receiver side, RFC 4340 sec. 9.2.1 */
- if (val < 0 || val > 15)
- err = -EINVAL;
- else {
- dp->dccps_pcrlen = val;
- /* FIXME: add feature negotiation,
- * ChangeL(MinimumChecksumCoverage, val) */
- }
+ case DCCP_SOCKOPT_RECV_CSCOV:
+ err = dccp_setsockopt_cscov(sk, val, true);
break;
default:
err = -ENOPROTOOPT;
break;
}
-
release_sock(sk);
+
return err;
}
@@ -648,6 +659,18 @@ static int do_dccp_getsockopt(struct sock *sk, int level, int optname,
case DCCP_SOCKOPT_GET_CUR_MPS:
val = dp->dccps_mss_cache;
break;
+ case DCCP_SOCKOPT_AVAILABLE_CCIDS:
+ return ccid_getsockopt_builtin_ccids(sk, len, optval, optlen);
+ case DCCP_SOCKOPT_TX_CCID:
+ val = ccid_get_current_tx_ccid(dp);
+ if (val < 0)
+ return -ENOPROTOOPT;
+ break;
+ case DCCP_SOCKOPT_RX_CCID:
+ val = ccid_get_current_rx_ccid(dp);
+ if (val < 0)
+ return -ENOPROTOOPT;
+ break;
case DCCP_SOCKOPT_SERVER_TIMEWAIT:
val = dp->dccps_server_timewait;
break;
@@ -976,7 +999,7 @@ adjudge_to_death:
state = sk->sk_state;
sock_hold(sk);
sock_orphan(sk);
- atomic_inc(sk->sk_prot->orphan_count);
+ percpu_counter_inc(sk->sk_prot->orphan_count);
/*
* It is the last release_sock in its life. It will remove backlog.
@@ -1040,17 +1063,21 @@ static int __init dccp_init(void)
{
unsigned long goal;
int ehash_order, bhash_order, i;
- int rc = -ENOBUFS;
+ int rc;
BUILD_BUG_ON(sizeof(struct dccp_skb_cb) >
FIELD_SIZEOF(struct sk_buff, cb));
-
+ rc = percpu_counter_init(&dccp_orphan_count, 0);
+ if (rc)
+ goto out;
+ rc = -ENOBUFS;
+ inet_hashinfo_init(&dccp_hashinfo);
dccp_hashinfo.bind_bucket_cachep =
kmem_cache_create("dccp_bind_bucket",
sizeof(struct inet_bind_bucket), 0,
SLAB_HWCACHE_ALIGN, NULL);
if (!dccp_hashinfo.bind_bucket_cachep)
- goto out;
+ goto out_free_percpu;
/*
* Size and allocate the main established and bind bucket
@@ -1084,8 +1111,8 @@ static int __init dccp_init(void)
}
for (i = 0; i < dccp_hashinfo.ehash_size; i++) {
- INIT_HLIST_HEAD(&dccp_hashinfo.ehash[i].chain);
- INIT_HLIST_HEAD(&dccp_hashinfo.ehash[i].twchain);
+ INIT_HLIST_NULLS_HEAD(&dccp_hashinfo.ehash[i].chain, i);
+ INIT_HLIST_NULLS_HEAD(&dccp_hashinfo.ehash[i].twchain, i);
}
if (inet_ehash_locks_alloc(&dccp_hashinfo))
@@ -1143,6 +1170,8 @@ out_free_dccp_ehash:
out_free_bind_bucket_cachep:
kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep);
dccp_hashinfo.bind_bucket_cachep = NULL;
+out_free_percpu:
+ percpu_counter_destroy(&dccp_orphan_count);
goto out;
}
diff --git a/net/dccp/sysctl.c b/net/dccp/sysctl.c
index 21295993fdb8..f6e54f433e29 100644
--- a/net/dccp/sysctl.c
+++ b/net/dccp/sysctl.c
@@ -41,13 +41,6 @@ static struct ctl_table dccp_default_table[] = {
.proc_handler = proc_dointvec,
},
{
- .procname = "ack_ratio",
- .data = &sysctl_dccp_feat_ack_ratio,
- .maxlen = sizeof(sysctl_dccp_feat_ack_ratio),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
.procname = "send_ackvec",
.data = &sysctl_dccp_feat_send_ack_vector,
.maxlen = sizeof(sysctl_dccp_feat_send_ack_vector),
diff --git a/net/dccp/timer.c b/net/dccp/timer.c
index 54b3c7e9e016..162d1e683c39 100644
--- a/net/dccp/timer.c
+++ b/net/dccp/timer.c
@@ -87,17 +87,6 @@ static void dccp_retransmit_timer(struct sock *sk)
{
struct inet_connection_sock *icsk = inet_csk(sk);
- /* retransmit timer is used for feature negotiation throughout
- * connection. In this case, no packet is re-transmitted, but rather an
- * ack is generated and pending changes are placed into its options.
- */
- if (sk->sk_send_head == NULL) {
- dccp_pr_debug("feat negotiation retransmit timeout %p\n", sk);
- if (sk->sk_state == DCCP_OPEN)
- dccp_send_ack(sk);
- goto backoff;
- }
-
/*
* More than than 4MSL (8 minutes) has passed, a RESET(aborted) was
* sent, no need to retransmit, this sock is dead.
@@ -126,7 +115,6 @@ static void dccp_retransmit_timer(struct sock *sk)
return;
}
-backoff:
icsk->icsk_backoff++;
icsk->icsk_rto = min(icsk->icsk_rto << 1, DCCP_RTO_MAX);
generated by cgit v1.2.3 (git 2.39.1) at 2024-12-23 20:18:11 +0100