* [PATCH] tcp: Remove TCPCT
From: Christoph Paasch @ 2013-03-17 18:23 UTC (permalink / raw)
To: David Miller; +Cc: netdev, Eric Dumazet
TCPCT uses option-number 253, reserved for experimental use and should
not be used in production environments.
Further, TCPCT does not fully implement RFC 6013.
As a nice side-effect, removing TCPCT increases TCP's performance for
very short flows:
Doing an apache-benchmark with -c 100 -n 100000, sending HTTP-requests
for files of 1KB size.
before this patch:
average (among 7 runs) of 20845.5 Requests/Second
after:
average (among 7 runs) of 21403.6 Requests/Second
Signed-off-by: Christoph Paasch <christoph.paasch@uclouvain.be>
---
Documentation/networking/ip-sysctl.txt | 8 -
drivers/infiniband/hw/cxgb4/cm.c | 2 +-
include/linux/tcp.h | 10 --
include/net/request_sock.h | 8 +-
include/net/tcp.h | 89 +----------
include/uapi/linux/tcp.h | 26 ----
net/dccp/ipv4.c | 5 +-
net/dccp/ipv6.c | 5 +-
net/ipv4/inet_connection_sock.c | 2 +-
net/ipv4/syncookies.c | 3 +-
net/ipv4/sysctl_net_ipv4.c | 7 -
net/ipv4/tcp.c | 267 ---------------------------------
net/ipv4/tcp_input.c | 69 +--------
net/ipv4/tcp_ipv4.c | 60 +-------
net/ipv4/tcp_minisocks.c | 40 +----
net/ipv4/tcp_output.c | 219 +--------------------------
net/ipv6/syncookies.c | 3 +-
net/ipv6/tcp_ipv6.c | 56 +------
18 files changed, 38 insertions(+), 841 deletions(-)
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index 18a24c4..17953e2 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -175,14 +175,6 @@ tcp_congestion_control - STRING
is inherited.
[see setsockopt(listenfd, SOL_TCP, TCP_CONGESTION, "name" ...) ]
-tcp_cookie_size - INTEGER
- Default size of TCP Cookie Transactions (TCPCT) option, that may be
- overridden on a per socket basis by the TCPCT socket option.
- Values greater than the maximum (16) are interpreted as the maximum.
- Values greater than zero and less than the minimum (8) are interpreted
- as the minimum. Odd values are interpreted as the next even value.
- Default: 0 (off).
-
tcp_dsack - BOOLEAN
Allows TCP to send "duplicate" SACKs.
diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
index 8dcc84f..54fd31f 100644
--- a/drivers/infiniband/hw/cxgb4/cm.c
+++ b/drivers/infiniband/hw/cxgb4/cm.c
@@ -2915,7 +2915,7 @@ static void build_cpl_pass_accept_req(struct sk_buff *skb, int stid , u8 tos)
*/
memset(&tmp_opt, 0, sizeof(tmp_opt));
tcp_clear_options(&tmp_opt);
- tcp_parse_options(skb, &tmp_opt, NULL, 0, NULL);
+ tcp_parse_options(skb, &tmp_opt, 0, NULL);
req = (struct cpl_pass_accept_req *)__skb_push(skb, sizeof(*req));
memset(req, 0, sizeof(*req));
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 763c108..ed6a745 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -90,9 +90,6 @@ struct tcp_options_received {
sack_ok : 4, /* SACK seen on SYN packet */
snd_wscale : 4, /* Window scaling received from sender */
rcv_wscale : 4; /* Window scaling to send to receiver */
- u8 cookie_plus:6, /* bytes in authenticator/cookie option */
- cookie_out_never:1,
- cookie_in_always:1;
u8 num_sacks; /* Number of SACK blocks */
u16 user_mss; /* mss requested by user in ioctl */
u16 mss_clamp; /* Maximal mss, negotiated at connection setup */
@@ -102,7 +99,6 @@ static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
{
rx_opt->tstamp_ok = rx_opt->sack_ok = 0;
rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
- rx_opt->cookie_plus = 0;
}
/* This is the max number of SACKS that we'll generate and process. It's safe
@@ -320,12 +316,6 @@ struct tcp_sock {
struct tcp_md5sig_info __rcu *md5sig_info;
#endif
- /* When the cookie options are generated and exchanged, then this
- * object holds a reference to them (cookie_values->kref). Also
- * contains related tcp_cookie_transactions fields.
- */
- struct tcp_cookie_values *cookie_values;
-
/* TCP fastopen related information */
struct tcp_fastopen_request *fastopen_req;
/* fastopen_rsk points to request_sock that resulted in this big
diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index a51dbd1..9069e65 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -27,19 +27,13 @@ struct sk_buff;
struct dst_entry;
struct proto;
-/* empty to "strongly type" an otherwise void parameter.
- */
-struct request_values {
-};
-
struct request_sock_ops {
int family;
int obj_size;
struct kmem_cache *slab;
char *slab_name;
int (*rtx_syn_ack)(struct sock *sk,
- struct request_sock *req,
- struct request_values *rvp);
+ struct request_sock *req);
void (*send_ack)(struct sock *sk, struct sk_buff *skb,
struct request_sock *req);
void (*send_reset)(struct sock *sk,
diff --git a/include/net/tcp.h b/include/net/tcp.h
index ab9f947..7f2f171 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -179,7 +179,6 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
#define TCPOPT_SACK 5 /* SACK Block */
#define TCPOPT_TIMESTAMP 8 /* Better RTT estimations/PAWS */
#define TCPOPT_MD5SIG 19 /* MD5 Signature (RFC2385) */
-#define TCPOPT_COOKIE 253 /* Cookie extension (experimental) */
#define TCPOPT_EXP 254 /* Experimental */
/* Magic number to be after the option value for sharing TCP
* experimental options. See draft-ietf-tcpm-experimental-options-00.txt
@@ -454,7 +453,7 @@ extern void tcp_syn_ack_timeout(struct sock *sk, struct request_sock *req);
extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg,
size_t len, int nonblock, int flags, int *addr_len);
extern void tcp_parse_options(const struct sk_buff *skb,
- struct tcp_options_received *opt_rx, const u8 **hvpp,
+ struct tcp_options_received *opt_rx,
int estab, struct tcp_fastopen_cookie *foc);
extern const u8 *tcp_parse_md5sig_option(const struct tcphdr *th);
@@ -476,7 +475,6 @@ extern int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr,
extern int tcp_connect(struct sock *sk);
extern struct sk_buff * tcp_make_synack(struct sock *sk, struct dst_entry *dst,
struct request_sock *req,
- struct request_values *rvp,
struct tcp_fastopen_cookie *foc);
extern int tcp_disconnect(struct sock *sk, int flags);
@@ -1589,91 +1587,6 @@ struct tcp_request_sock_ops {
#endif
};
-/* Using SHA1 for now, define some constants.
- */
-#define COOKIE_DIGEST_WORDS (SHA_DIGEST_WORDS)
-#define COOKIE_MESSAGE_WORDS (SHA_MESSAGE_BYTES / 4)
-#define COOKIE_WORKSPACE_WORDS (COOKIE_DIGEST_WORDS + COOKIE_MESSAGE_WORDS)
-
-extern int tcp_cookie_generator(u32 *bakery);
-
-/**
- * struct tcp_cookie_values - each socket needs extra space for the
- * cookies, together with (optional) space for any SYN data.
- *
- * A tcp_sock contains a pointer to the current value, and this is
- * cloned to the tcp_timewait_sock.
- *
- * @cookie_pair: variable data from the option exchange.
- *
- * @cookie_desired: user specified tcpct_cookie_desired. Zero
- * indicates default (sysctl_tcp_cookie_size).
- * After cookie sent, remembers size of cookie.
- * Range 0, TCP_COOKIE_MIN to TCP_COOKIE_MAX.
- *
- * @s_data_desired: user specified tcpct_s_data_desired. When the
- * constant payload is specified (@s_data_constant),
- * holds its length instead.
- * Range 0 to TCP_MSS_DESIRED.
- *
- * @s_data_payload: constant data that is to be included in the
- * payload of SYN or SYNACK segments when the
- * cookie option is present.
- */
-struct tcp_cookie_values {
- struct kref kref;
- u8 cookie_pair[TCP_COOKIE_PAIR_SIZE];
- u8 cookie_pair_size;
- u8 cookie_desired;
- u16 s_data_desired:11,
- s_data_constant:1,
- s_data_in:1,
- s_data_out:1,
- s_data_unused:2;
- u8 s_data_payload[0];
-};
-
-static inline void tcp_cookie_values_release(struct kref *kref)
-{
- kfree(container_of(kref, struct tcp_cookie_values, kref));
-}
-
-/* The length of constant payload data. Note that s_data_desired is
- * overloaded, depending on s_data_constant: either the length of constant
- * data (returned here) or the limit on variable data.
- */
-static inline int tcp_s_data_size(const struct tcp_sock *tp)
-{
- return (tp->cookie_values != NULL && tp->cookie_values->s_data_constant)
- ? tp->cookie_values->s_data_desired
- : 0;
-}
-
-/**
- * struct tcp_extend_values - tcp_ipv?.c to tcp_output.c workspace.
- *
- * As tcp_request_sock has already been extended in other places, the
- * only remaining method is to pass stack values along as function
- * parameters. These parameters are not needed after sending SYNACK.
- *
- * @cookie_bakery: cryptographic secret and message workspace.
- *
- * @cookie_plus: bytes in authenticator/cookie option, copied from
- * struct tcp_options_received (above).
- */
-struct tcp_extend_values {
- struct request_values rv;
- u32 cookie_bakery[COOKIE_WORKSPACE_WORDS];
- u8 cookie_plus:6,
- cookie_out_never:1,
- cookie_in_always:1;
-};
-
-static inline struct tcp_extend_values *tcp_xv(struct request_values *rvp)
-{
- return (struct tcp_extend_values *)rvp;
-}
-
extern void tcp_v4_init(void);
extern void tcp_init(void);
diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h
index 6b1ead0..8d776eb 100644
--- a/include/uapi/linux/tcp.h
+++ b/include/uapi/linux/tcp.h
@@ -102,7 +102,6 @@ enum {
#define TCP_QUICKACK 12 /* Block/reenable quick acks */
#define TCP_CONGESTION 13 /* Congestion control algorithm */
#define TCP_MD5SIG 14 /* TCP MD5 Signature (RFC2385) */
-#define TCP_COOKIE_TRANSACTIONS 15 /* TCP Cookie Transactions */
#define TCP_THIN_LINEAR_TIMEOUTS 16 /* Use linear timeouts for thin streams*/
#define TCP_THIN_DUPACK 17 /* Fast retrans. after 1 dupack */
#define TCP_USER_TIMEOUT 18 /* How long for loss retry before timeout */
@@ -199,29 +198,4 @@ struct tcp_md5sig {
__u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN]; /* key (binary) */
};
-/* for TCP_COOKIE_TRANSACTIONS (TCPCT) socket option */
-#define TCP_COOKIE_MIN 8 /* 64-bits */
-#define TCP_COOKIE_MAX 16 /* 128-bits */
-#define TCP_COOKIE_PAIR_SIZE (2*TCP_COOKIE_MAX)
-
-/* Flags for both getsockopt and setsockopt */
-#define TCP_COOKIE_IN_ALWAYS (1 << 0) /* Discard SYN without cookie */
-#define TCP_COOKIE_OUT_NEVER (1 << 1) /* Prohibit outgoing cookies,
- * supercedes everything. */
-
-/* Flags for getsockopt */
-#define TCP_S_DATA_IN (1 << 2) /* Was data received? */
-#define TCP_S_DATA_OUT (1 << 3) /* Was data sent? */
-
-/* TCP_COOKIE_TRANSACTIONS data */
-struct tcp_cookie_transactions {
- __u16 tcpct_flags; /* see above */
- __u8 __tcpct_pad1; /* zero */
- __u8 tcpct_cookie_desired; /* bytes */
- __u16 tcpct_s_data_desired; /* bytes of variable data */
- __u16 tcpct_used; /* bytes in value */
- __u8 tcpct_value[TCP_MSS_DEFAULT];
-};
-
-
#endif /* _UAPI_LINUX_TCP_H */
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 4f9f5eb..ebc54fe 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -500,8 +500,7 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
return &rt->dst;
}
-static int dccp_v4_send_response(struct sock *sk, struct request_sock *req,
- struct request_values *rv_unused)
+static int dccp_v4_send_response(struct sock *sk, struct request_sock *req)
{
int err = -1;
struct sk_buff *skb;
@@ -658,7 +657,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
dreq->dreq_gss = dreq->dreq_iss;
dreq->dreq_service = service;
- if (dccp_v4_send_response(sk, req, NULL))
+ if (dccp_v4_send_response(sk, req))
goto drop_and_free;
inet_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c
index 6e05981..9c61f9c 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -213,8 +213,7 @@ out:
}
-static int dccp_v6_send_response(struct sock *sk, struct request_sock *req,
- struct request_values *rv_unused)
+static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
{
struct inet6_request_sock *ireq6 = inet6_rsk(req);
struct ipv6_pinfo *np = inet6_sk(sk);
@@ -428,7 +427,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
dreq->dreq_gss = dreq->dreq_iss;
dreq->dreq_service = service;
- if (dccp_v6_send_response(sk, req, NULL))
+ if (dccp_v6_send_response(sk, req))
goto drop_and_free;
inet6_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 786d97a..6acb541 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -559,7 +559,7 @@ static inline void syn_ack_recalc(struct request_sock *req, const int thresh,
int inet_rtx_syn_ack(struct sock *parent, struct request_sock *req)
{
- int err = req->rsk_ops->rtx_syn_ack(parent, req, NULL);
+ int err = req->rsk_ops->rtx_syn_ack(parent, req);
if (!err)
req->num_retrans++;
diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index ef54377..7f4a5cb 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -267,7 +267,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
struct ip_options *opt)
{
struct tcp_options_received tcp_opt;
- const u8 *hash_location;
struct inet_request_sock *ireq;
struct tcp_request_sock *treq;
struct tcp_sock *tp = tcp_sk(sk);
@@ -294,7 +293,7 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
/* check for timestamp cookie support */
memset(&tcp_opt, 0, sizeof(tcp_opt));
- tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL);
+ tcp_parse_options(skb, &tcp_opt, 0, NULL);
if (!cookie_check_timestamp(&tcp_opt, sock_net(sk), &ecn_ok))
goto out;
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index cca4550..cb45062 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -733,13 +733,6 @@ static struct ctl_table ipv4_table[] = {
.proc_handler = proc_dointvec,
},
{
- .procname = "tcp_cookie_size",
- .data = &sysctl_tcp_cookie_size,
- .maxlen = sizeof(int),
- .mode = 0644,
- .proc_handler = proc_dointvec
- },
- {
.procname = "tcp_thin_linear_timeouts",
.data = &sysctl_tcp_thin_linear_timeouts,
.maxlen = sizeof(int),
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 8d14573..17a6810 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -409,15 +409,6 @@ void tcp_init_sock(struct sock *sk)
icsk->icsk_sync_mss = tcp_sync_mss;
- /* TCP Cookie Transactions */
- if (sysctl_tcp_cookie_size > 0) {
- /* Default, cookies without s_data_payload. */
- tp->cookie_values =
- kzalloc(sizeof(*tp->cookie_values),
- sk->sk_allocation);
- if (tp->cookie_values != NULL)
- kref_init(&tp->cookie_values->kref);
- }
/* Presumed zeroed, in order of appearance:
* cookie_in_always, cookie_out_never,
* s_data_constant, s_data_in, s_data_out
@@ -2397,92 +2388,6 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
release_sock(sk);
return err;
}
- case TCP_COOKIE_TRANSACTIONS: {
- struct tcp_cookie_transactions ctd;
- struct tcp_cookie_values *cvp = NULL;
-
- if (sizeof(ctd) > optlen)
- return -EINVAL;
- if (copy_from_user(&ctd, optval, sizeof(ctd)))
- return -EFAULT;
-
- if (ctd.tcpct_used > sizeof(ctd.tcpct_value) ||
- ctd.tcpct_s_data_desired > TCP_MSS_DESIRED)
- return -EINVAL;
-
- if (ctd.tcpct_cookie_desired == 0) {
- /* default to global value */
- } else if ((0x1 & ctd.tcpct_cookie_desired) ||
- ctd.tcpct_cookie_desired > TCP_COOKIE_MAX ||
- ctd.tcpct_cookie_desired < TCP_COOKIE_MIN) {
- return -EINVAL;
- }
-
- if (TCP_COOKIE_OUT_NEVER & ctd.tcpct_flags) {
- /* Supercedes all other values */
- lock_sock(sk);
- if (tp->cookie_values != NULL) {
- kref_put(&tp->cookie_values->kref,
- tcp_cookie_values_release);
- tp->cookie_values = NULL;
- }
- tp->rx_opt.cookie_in_always = 0; /* false */
- tp->rx_opt.cookie_out_never = 1; /* true */
- release_sock(sk);
- return err;
- }
-
- /* Allocate ancillary memory before locking.
- */
- if (ctd.tcpct_used > 0 ||
- (tp->cookie_values == NULL &&
- (sysctl_tcp_cookie_size > 0 ||
- ctd.tcpct_cookie_desired > 0 ||
- ctd.tcpct_s_data_desired > 0))) {
- cvp = kzalloc(sizeof(*cvp) + ctd.tcpct_used,
- GFP_KERNEL);
- if (cvp == NULL)
- return -ENOMEM;
-
- kref_init(&cvp->kref);
- }
- lock_sock(sk);
- tp->rx_opt.cookie_in_always =
- (TCP_COOKIE_IN_ALWAYS & ctd.tcpct_flags);
- tp->rx_opt.cookie_out_never = 0; /* false */
-
- if (tp->cookie_values != NULL) {
- if (cvp != NULL) {
- /* Changed values are recorded by a changed
- * pointer, ensuring the cookie will differ,
- * without separately hashing each value later.
- */
- kref_put(&tp->cookie_values->kref,
- tcp_cookie_values_release);
- } else {
- cvp = tp->cookie_values;
- }
- }
-
- if (cvp != NULL) {
- cvp->cookie_desired = ctd.tcpct_cookie_desired;
-
- if (ctd.tcpct_used > 0) {
- memcpy(cvp->s_data_payload, ctd.tcpct_value,
- ctd.tcpct_used);
- cvp->s_data_desired = ctd.tcpct_used;
- cvp->s_data_constant = 1; /* true */
- } else {
- /* No constant payload data. */
- cvp->s_data_desired = ctd.tcpct_s_data_desired;
- cvp->s_data_constant = 0; /* false */
- }
-
- tp->cookie_values = cvp;
- }
- release_sock(sk);
- return err;
- }
default:
/* fallthru */
break;
@@ -2902,41 +2807,6 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
return -EFAULT;
return 0;
- case TCP_COOKIE_TRANSACTIONS: {
- struct tcp_cookie_transactions ctd;
- struct tcp_cookie_values *cvp = tp->cookie_values;
-
- if (get_user(len, optlen))
- return -EFAULT;
- if (len < sizeof(ctd))
- return -EINVAL;
-
- memset(&ctd, 0, sizeof(ctd));
- ctd.tcpct_flags = (tp->rx_opt.cookie_in_always ?
- TCP_COOKIE_IN_ALWAYS : 0)
- | (tp->rx_opt.cookie_out_never ?
- TCP_COOKIE_OUT_NEVER : 0);
-
- if (cvp != NULL) {
- ctd.tcpct_flags |= (cvp->s_data_in ?
- TCP_S_DATA_IN : 0)
- | (cvp->s_data_out ?
- TCP_S_DATA_OUT : 0);
-
- ctd.tcpct_cookie_desired = cvp->cookie_desired;
- ctd.tcpct_s_data_desired = cvp->s_data_desired;
-
- memcpy(&ctd.tcpct_value[0], &cvp->cookie_pair[0],
- cvp->cookie_pair_size);
- ctd.tcpct_used = cvp->cookie_pair_size;
- }
-
- if (put_user(sizeof(ctd), optlen))
- return -EFAULT;
- if (copy_to_user(optval, &ctd, sizeof(ctd)))
- return -EFAULT;
- return 0;
- }
case TCP_THIN_LINEAR_TIMEOUTS:
val = tp->thin_lto;
break;
@@ -3409,134 +3279,6 @@ EXPORT_SYMBOL(tcp_md5_hash_key);
#endif
-/* Each Responder maintains up to two secret values concurrently for
- * efficient secret rollover. Each secret value has 4 states:
- *
- * Generating. (tcp_secret_generating != tcp_secret_primary)
- * Generates new Responder-Cookies, but not yet used for primary
- * verification. This is a short-term state, typically lasting only
- * one round trip time (RTT).
- *
- * Primary. (tcp_secret_generating == tcp_secret_primary)
- * Used both for generation and primary verification.
- *
- * Retiring. (tcp_secret_retiring != tcp_secret_secondary)
- * Used for verification, until the first failure that can be
- * verified by the newer Generating secret. At that time, this
- * cookie's state is changed to Secondary, and the Generating
- * cookie's state is changed to Primary. This is a short-term state,
- * typically lasting only one round trip time (RTT).
- *
- * Secondary. (tcp_secret_retiring == tcp_secret_secondary)
- * Used for secondary verification, after primary verification
- * failures. This state lasts no more than twice the Maximum Segment
- * Lifetime (2MSL). Then, the secret is discarded.
- */
-struct tcp_cookie_secret {
- /* The secret is divided into two parts. The digest part is the
- * equivalent of previously hashing a secret and saving the state,
- * and serves as an initialization vector (IV). The message part
- * serves as the trailing secret.
- */
- u32 secrets[COOKIE_WORKSPACE_WORDS];
- unsigned long expires;
-};
-
-#define TCP_SECRET_1MSL (HZ * TCP_PAWS_MSL)
-#define TCP_SECRET_2MSL (HZ * TCP_PAWS_MSL * 2)
-#define TCP_SECRET_LIFE (HZ * 600)
-
-static struct tcp_cookie_secret tcp_secret_one;
-static struct tcp_cookie_secret tcp_secret_two;
-
-/* Essentially a circular list, without dynamic allocation. */
-static struct tcp_cookie_secret *tcp_secret_generating;
-static struct tcp_cookie_secret *tcp_secret_primary;
-static struct tcp_cookie_secret *tcp_secret_retiring;
-static struct tcp_cookie_secret *tcp_secret_secondary;
-
-static DEFINE_SPINLOCK(tcp_secret_locker);
-
-/* Select a pseudo-random word in the cookie workspace.
- */
-static inline u32 tcp_cookie_work(const u32 *ws, const int n)
-{
- return ws[COOKIE_DIGEST_WORDS + ((COOKIE_MESSAGE_WORDS-1) & ws[n])];
-}
-
-/* Fill bakery[COOKIE_WORKSPACE_WORDS] with generator, updating as needed.
- * Called in softirq context.
- * Returns: 0 for success.
- */
-int tcp_cookie_generator(u32 *bakery)
-{
- unsigned long jiffy = jiffies;
-
- if (unlikely(time_after_eq(jiffy, tcp_secret_generating->expires))) {
- spin_lock_bh(&tcp_secret_locker);
- if (!time_after_eq(jiffy, tcp_secret_generating->expires)) {
- /* refreshed by another */
- memcpy(bakery,
- &tcp_secret_generating->secrets[0],
- COOKIE_WORKSPACE_WORDS);
- } else {
- /* still needs refreshing */
- get_random_bytes(bakery, COOKIE_WORKSPACE_WORDS);
-
- /* The first time, paranoia assumes that the
- * randomization function isn't as strong. But,
- * this secret initialization is delayed until
- * the last possible moment (packet arrival).
- * Although that time is observable, it is
- * unpredictably variable. Mash in the most
- * volatile clock bits available, and expire the
- * secret extra quickly.
- */
- if (unlikely(tcp_secret_primary->expires ==
- tcp_secret_secondary->expires)) {
- struct timespec tv;
-
- getnstimeofday(&tv);
- bakery[COOKIE_DIGEST_WORDS+0] ^=
- (u32)tv.tv_nsec;
-
- tcp_secret_secondary->expires = jiffy
- + TCP_SECRET_1MSL
- + (0x0f & tcp_cookie_work(bakery, 0));
- } else {
- tcp_secret_secondary->expires = jiffy
- + TCP_SECRET_LIFE
- + (0xff & tcp_cookie_work(bakery, 1));
- tcp_secret_primary->expires = jiffy
- + TCP_SECRET_2MSL
- + (0x1f & tcp_cookie_work(bakery, 2));
- }
- memcpy(&tcp_secret_secondary->secrets[0],
- bakery, COOKIE_WORKSPACE_WORDS);
-
- rcu_assign_pointer(tcp_secret_generating,
- tcp_secret_secondary);
- rcu_assign_pointer(tcp_secret_retiring,
- tcp_secret_primary);
- /*
- * Neither call_rcu() nor synchronize_rcu() needed.
- * Retiring data is not freed. It is replaced after
- * further (locked) pointer updates, and a quiet time
- * (minimum 1MSL, maximum LIFE - 2MSL).
- */
- }
- spin_unlock_bh(&tcp_secret_locker);
- } else {
- rcu_read_lock_bh();
- memcpy(bakery,
- &rcu_dereference(tcp_secret_generating)->secrets[0],
- COOKIE_WORKSPACE_WORDS);
- rcu_read_unlock_bh();
- }
- return 0;
-}
-EXPORT_SYMBOL(tcp_cookie_generator);
-
void tcp_done(struct sock *sk)
{
struct request_sock *req = tcp_sk(sk)->fastopen_rsk;
@@ -3591,7 +3333,6 @@ void __init tcp_init(void)
unsigned long limit;
int max_rshare, max_wshare, cnt;
unsigned int i;
- unsigned long jiffy = jiffies;
BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
@@ -3667,13 +3408,5 @@ void __init tcp_init(void)
tcp_register_congestion_control(&tcp_reno);
- memset(&tcp_secret_one.secrets[0], 0, sizeof(tcp_secret_one.secrets));
- memset(&tcp_secret_two.secrets[0], 0, sizeof(tcp_secret_two.secrets));
- tcp_secret_one.expires = jiffy; /* past due */
- tcp_secret_two.expires = jiffy; /* past due */
- tcp_secret_generating = &tcp_secret_one;
- tcp_secret_primary = &tcp_secret_one;
- tcp_secret_retiring = &tcp_secret_two;
- tcp_secret_secondary = &tcp_secret_two;
tcp_tasklet_init();
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index 836d74d..19f0149 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3760,8 +3760,8 @@ old_ack:
* But, this can also be called on packets in the established flow when
* the fast version below fails.
*/
-void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *opt_rx,
- const u8 **hvpp, int estab,
+void tcp_parse_options(const struct sk_buff *skb,
+ struct tcp_options_received *opt_rx, int estab,
struct tcp_fastopen_cookie *foc)
{
const unsigned char *ptr;
@@ -3845,31 +3845,6 @@ void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *o
*/
break;
#endif
- case TCPOPT_COOKIE:
- /* This option is variable length.
- */
- switch (opsize) {
- case TCPOLEN_COOKIE_BASE:
- /* not yet implemented */
- break;
- case TCPOLEN_COOKIE_PAIR:
- /* not yet implemented */
- break;
- case TCPOLEN_COOKIE_MIN+0:
- case TCPOLEN_COOKIE_MIN+2:
- case TCPOLEN_COOKIE_MIN+4:
- case TCPOLEN_COOKIE_MIN+6:
- case TCPOLEN_COOKIE_MAX:
- /* 16-bit multiple */
- opt_rx->cookie_plus = opsize;
- *hvpp = ptr;
- break;
- default:
- /* ignore option */
- break;
- }
- break;
-
case TCPOPT_EXP:
/* Fast Open option shares code 254 using a
* 16 bits magic number. It's valid only in
@@ -3915,8 +3890,7 @@ static bool tcp_parse_aligned_timestamp(struct tcp_sock *tp, const struct tcphdr
* If it is wrong it falls back on tcp_parse_options().
*/
static bool tcp_fast_parse_options(const struct sk_buff *skb,
- const struct tcphdr *th,
- struct tcp_sock *tp, const u8 **hvpp)
+ const struct tcphdr *th, struct tcp_sock *tp)
{
/* In the spirit of fast parsing, compare doff directly to constant
* values. Because equality is used, short doff can be ignored here.
@@ -3930,7 +3904,7 @@ static bool tcp_fast_parse_options(const struct sk_buff *skb,
return true;
}
- tcp_parse_options(skb, &tp->rx_opt, hvpp, 1, NULL);
+ tcp_parse_options(skb, &tp->rx_opt, 1, NULL);
if (tp->rx_opt.saw_tstamp)
tp->rx_opt.rcv_tsecr -= tp->tsoffset;
@@ -5311,12 +5285,10 @@ out:
static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
const struct tcphdr *th, int syn_inerr)
{
- const u8 *hash_location;
struct tcp_sock *tp = tcp_sk(sk);
/* RFC1323: H1. Apply PAWS check first. */
- if (tcp_fast_parse_options(skb, th, tp, &hash_location) &&
- tp->rx_opt.saw_tstamp &&
+ if (tcp_fast_parse_options(skb, th, tp) && tp->rx_opt.saw_tstamp &&
tcp_paws_discard(sk, skb)) {
if (!th->rst) {
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
@@ -5670,12 +5642,11 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
if (mss == tp->rx_opt.user_mss) {
struct tcp_options_received opt;
- const u8 *hash_location;
/* Get original SYNACK MSS value if user MSS sets mss_clamp */
tcp_clear_options(&opt);
opt.user_mss = opt.mss_clamp = 0;
- tcp_parse_options(synack, &opt, &hash_location, 0, NULL);
+ tcp_parse_options(synack, &opt, 0, NULL);
mss = opt.mss_clamp;
}
@@ -5706,14 +5677,12 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack,
static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
const struct tcphdr *th, unsigned int len)
{
- const u8 *hash_location;
struct inet_connection_sock *icsk = inet_csk(sk);
struct tcp_sock *tp = tcp_sk(sk);
- struct tcp_cookie_values *cvp = tp->cookie_values;
struct tcp_fastopen_cookie foc = { .len = -1 };
int saved_clamp = tp->rx_opt.mss_clamp;
- tcp_parse_options(skb, &tp->rx_opt, &hash_location, 0, &foc);
+ tcp_parse_options(skb, &tp->rx_opt, 0, &foc);
if (tp->rx_opt.saw_tstamp)
tp->rx_opt.rcv_tsecr -= tp->tsoffset;
@@ -5810,30 +5779,6 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
* is initialized. */
tp->copied_seq = tp->rcv_nxt;
- if (cvp != NULL &&
- cvp->cookie_pair_size > 0 &&
- tp->rx_opt.cookie_plus > 0) {
- int cookie_size = tp->rx_opt.cookie_plus
- - TCPOLEN_COOKIE_BASE;
- int cookie_pair_size = cookie_size
- + cvp->cookie_desired;
-
- /* A cookie extension option was sent and returned.
- * Note that each incoming SYNACK replaces the
- * Responder cookie. The initial exchange is most
- * fragile, as protection against spoofing relies
- * entirely upon the sequence and timestamp (above).
- * This replacement strategy allows the correct pair to
- * pass through, while any others will be filtered via
- * Responder verification later.
- */
- if (sizeof(cvp->cookie_pair) >= cookie_pair_size) {
- memcpy(&cvp->cookie_pair[cvp->cookie_desired],
- hash_location, cookie_size);
- cvp->cookie_pair_size = cookie_pair_size;
- }
- }
-
smp_mb();
tcp_finish_connect(sk, skb);
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index b7ab868..b27c758 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -838,7 +838,6 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
*/
static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
struct request_sock *req,
- struct request_values *rvp,
u16 queue_mapping,
bool nocache)
{
@@ -851,7 +850,7 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
if (!dst && (dst = inet_csk_route_req(sk, &fl4, req)) == NULL)
return -1;
- skb = tcp_make_synack(sk, dst, req, rvp, NULL);
+ skb = tcp_make_synack(sk, dst, req, NULL);
if (skb) {
__tcp_v4_send_check(skb, ireq->loc_addr, ireq->rmt_addr);
@@ -868,10 +867,9 @@ static int tcp_v4_send_synack(struct sock *sk, struct dst_entry *dst,
return err;
}
-static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req,
- struct request_values *rvp)
+static int tcp_v4_rtx_synack(struct sock *sk, struct request_sock *req)
{
- int res = tcp_v4_send_synack(sk, NULL, req, rvp, 0, false);
+ int res = tcp_v4_send_synack(sk, NULL, req, 0, false);
if (!res)
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
@@ -1371,8 +1369,7 @@ static bool tcp_fastopen_check(struct sock *sk, struct sk_buff *skb,
static int tcp_v4_conn_req_fastopen(struct sock *sk,
struct sk_buff *skb,
struct sk_buff *skb_synack,
- struct request_sock *req,
- struct request_values *rvp)
+ struct request_sock *req)
{
struct tcp_sock *tp = tcp_sk(sk);
struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue;
@@ -1467,9 +1464,7 @@ static int tcp_v4_conn_req_fastopen(struct sock *sk,
int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
- struct tcp_extend_values tmp_ext;
struct tcp_options_received tmp_opt;
- const u8 *hash_location;
struct request_sock *req;
struct inet_request_sock *ireq;
struct tcp_sock *tp = tcp_sk(sk);
@@ -1519,42 +1514,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
tcp_clear_options(&tmp_opt);
tmp_opt.mss_clamp = TCP_MSS_DEFAULT;
tmp_opt.user_mss = tp->rx_opt.user_mss;
- tcp_parse_options(skb, &tmp_opt, &hash_location, 0,
- want_cookie ? NULL : &foc);
-
- if (tmp_opt.cookie_plus > 0 &&
- tmp_opt.saw_tstamp &&
- !tp->rx_opt.cookie_out_never &&
- (sysctl_tcp_cookie_size > 0 ||
- (tp->cookie_values != NULL &&
- tp->cookie_values->cookie_desired > 0))) {
- u8 *c;
- u32 *mess = &tmp_ext.cookie_bakery[COOKIE_DIGEST_WORDS];
- int l = tmp_opt.cookie_plus - TCPOLEN_COOKIE_BASE;
-
- if (tcp_cookie_generator(&tmp_ext.cookie_bakery[0]) != 0)
- goto drop_and_release;
-
- /* Secret recipe starts with IP addresses */
- *mess++ ^= (__force u32)daddr;
- *mess++ ^= (__force u32)saddr;
-
- /* plus variable length Initiator Cookie */
- c = (u8 *)mess;
- while (l-- > 0)
- *c++ ^= *hash_location++;
-
- want_cookie = false; /* not our kind of cookie */
- tmp_ext.cookie_out_never = 0; /* false */
- tmp_ext.cookie_plus = tmp_opt.cookie_plus;
- } else if (!tp->rx_opt.cookie_in_always) {
- /* redundant indications, but ensure initialization. */
- tmp_ext.cookie_out_never = 1; /* true */
- tmp_ext.cookie_plus = 0;
- } else {
- goto drop_and_release;
- }
- tmp_ext.cookie_in_always = tp->rx_opt.cookie_in_always;
+ tcp_parse_options(skb, &tmp_opt, 0, want_cookie ? NULL : &foc);
if (want_cookie && !tmp_opt.saw_tstamp)
tcp_clear_options(&tmp_opt);
@@ -1636,7 +1596,6 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
* of tcp_v4_send_synack()->tcp_select_initial_window().
*/
skb_synack = tcp_make_synack(sk, dst, req,
- (struct request_values *)&tmp_ext,
fastopen_cookie_present(&valid_foc) ? &valid_foc : NULL);
if (skb_synack) {
@@ -1660,8 +1619,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
if (fastopen_cookie_present(&foc) && foc.len != 0)
NET_INC_STATS_BH(sock_net(sk),
LINUX_MIB_TCPFASTOPENPASSIVEFAIL);
- } else if (tcp_v4_conn_req_fastopen(sk, skb, skb_synack, req,
- (struct request_values *)&tmp_ext))
+ } else if (tcp_v4_conn_req_fastopen(sk, skb, skb_synack, req))
goto drop_and_free;
return 0;
@@ -2241,12 +2199,6 @@ void tcp_v4_destroy_sock(struct sock *sk)
if (inet_csk(sk)->icsk_bind_hash)
inet_put_port(sk);
- /* TCP Cookie Transactions */
- if (tp->cookie_values != NULL) {
- kref_put(&tp->cookie_values->kref,
- tcp_cookie_values_release);
- tp->cookie_values = NULL;
- }
BUG_ON(tp->fastopen_rsk != NULL);
/* If socket is aborted during connect operation */
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 4bdb09f..8f0234f 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -93,13 +93,12 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
const struct tcphdr *th)
{
struct tcp_options_received tmp_opt;
- const u8 *hash_location;
struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
bool paws_reject = false;
tmp_opt.saw_tstamp = 0;
if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
- tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL);
+ tcp_parse_options(skb, &tmp_opt, 0, NULL);
if (tmp_opt.saw_tstamp) {
tmp_opt.rcv_tsecr -= tcptw->tw_ts_offset;
@@ -388,32 +387,6 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
struct tcp_request_sock *treq = tcp_rsk(req);
struct inet_connection_sock *newicsk = inet_csk(newsk);
struct tcp_sock *newtp = tcp_sk(newsk);
- struct tcp_sock *oldtp = tcp_sk(sk);
- struct tcp_cookie_values *oldcvp = oldtp->cookie_values;
-
- /* TCP Cookie Transactions require space for the cookie pair,
- * as it differs for each connection. There is no need to
- * copy any s_data_payload stored at the original socket.
- * Failure will prevent resuming the connection.
- *
- * Presumed copied, in order of appearance:
- * cookie_in_always, cookie_out_never
- */
- if (oldcvp != NULL) {
- struct tcp_cookie_values *newcvp =
- kzalloc(sizeof(*newtp->cookie_values),
- GFP_ATOMIC);
-
- if (newcvp != NULL) {
- kref_init(&newcvp->kref);
- newcvp->cookie_desired =
- oldcvp->cookie_desired;
- newtp->cookie_values = newcvp;
- } else {
- /* Not Yet Implemented */
- newtp->cookie_values = NULL;
- }
- }
/* Now setup tcp_sock */
newtp->pred_flags = 0;
@@ -422,8 +395,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
newtp->rcv_nxt = treq->rcv_isn + 1;
newtp->snd_sml = newtp->snd_una =
- newtp->snd_nxt = newtp->snd_up =
- treq->snt_isn + 1 + tcp_s_data_size(oldtp);
+ newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1;
tcp_prequeue_init(newtp);
INIT_LIST_HEAD(&newtp->tsq_node);
@@ -460,8 +432,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
tcp_set_ca_state(newsk, TCP_CA_Open);
tcp_init_xmit_timers(newsk);
skb_queue_head_init(&newtp->out_of_order_queue);
- newtp->write_seq = newtp->pushed_seq =
- treq->snt_isn + 1 + tcp_s_data_size(oldtp);
+ newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1;
newtp->rx_opt.saw_tstamp = 0;
@@ -538,7 +509,6 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
bool fastopen)
{
struct tcp_options_received tmp_opt;
- const u8 *hash_location;
struct sock *child;
const struct tcphdr *th = tcp_hdr(skb);
__be32 flg = tcp_flag_word(th) & (TCP_FLAG_RST|TCP_FLAG_SYN|TCP_FLAG_ACK);
@@ -548,7 +518,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
tmp_opt.saw_tstamp = 0;
if (th->doff > (sizeof(struct tcphdr)>>2)) {
- tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL);
+ tcp_parse_options(skb, &tmp_opt, 0, NULL);
if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = req->ts_recent;
@@ -648,7 +618,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
*/
if ((flg & TCP_FLAG_ACK) && !fastopen &&
(TCP_SKB_CB(skb)->ack_seq !=
- tcp_rsk(req)->snt_isn + 1 + tcp_s_data_size(tcp_sk(sk))))
+ tcp_rsk(req)->snt_isn + 1))
return sk;
/* Also, it would be not so bad idea to check rcv_tsecr, which
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 8e7742f..ac5871e 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -65,9 +65,6 @@ int sysctl_tcp_base_mss __read_mostly = TCP_BASE_MSS;
/* By default, RFC2861 behavior. */
int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
-int sysctl_tcp_cookie_size __read_mostly = 0; /* TCP_COOKIE_MAX */
-EXPORT_SYMBOL_GPL(sysctl_tcp_cookie_size);
-
static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle,
int push_one, gfp_t gfp);
@@ -386,7 +383,6 @@ static inline bool tcp_urg_mode(const struct tcp_sock *tp)
#define OPTION_TS (1 << 1)
#define OPTION_MD5 (1 << 2)
#define OPTION_WSCALE (1 << 3)
-#define OPTION_COOKIE_EXTENSION (1 << 4)
#define OPTION_FAST_OPEN_COOKIE (1 << 8)
struct tcp_out_options {
@@ -400,36 +396,6 @@ struct tcp_out_options {
struct tcp_fastopen_cookie *fastopen_cookie; /* Fast open cookie */
};
-/* The sysctl int routines are generic, so check consistency here.
- */
-static u8 tcp_cookie_size_check(u8 desired)
-{
- int cookie_size;
-
- if (desired > 0)
- /* previously specified */
- return desired;
-
- cookie_size = ACCESS_ONCE(sysctl_tcp_cookie_size);
- if (cookie_size <= 0)
- /* no default specified */
- return 0;
-
- if (cookie_size <= TCP_COOKIE_MIN)
- /* value too small, specify minimum */
- return TCP_COOKIE_MIN;
-
- if (cookie_size >= TCP_COOKIE_MAX)
- /* value too large, specify maximum */
- return TCP_COOKIE_MAX;
-
- if (cookie_size & 1)
- /* 8-bit multiple, illegal, fix it */
- cookie_size++;
-
- return (u8)cookie_size;
-}
-
/* Write previously computed TCP options to the packet.
*
* Beware: Something in the Internet is very sensitive to the ordering of
@@ -448,27 +414,9 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
{
u16 options = opts->options; /* mungable copy */
- /* Having both authentication and cookies for security is redundant,
- * and there's certainly not enough room. Instead, the cookie-less
- * extension variant is proposed.
- *
- * Consider the pessimal case with authentication. The options
- * could look like:
- * COOKIE|MD5(20) + MSS(4) + SACK|TS(12) + WSCALE(4) == 40
- */
if (unlikely(OPTION_MD5 & options)) {
- if (unlikely(OPTION_COOKIE_EXTENSION & options)) {
- *ptr++ = htonl((TCPOPT_COOKIE << 24) |
- (TCPOLEN_COOKIE_BASE << 16) |
- (TCPOPT_MD5SIG << 8) |
- TCPOLEN_MD5SIG);
- } else {
- *ptr++ = htonl((TCPOPT_NOP << 24) |
- (TCPOPT_NOP << 16) |
- (TCPOPT_MD5SIG << 8) |
- TCPOLEN_MD5SIG);
- }
- options &= ~OPTION_COOKIE_EXTENSION;
+ *ptr++ = htonl((TCPOPT_NOP << 24) | (TCPOPT_NOP << 16) |
+ (TCPOPT_MD5SIG << 8) | TCPOLEN_MD5SIG);
/* overload cookie hash location */
opts->hash_location = (__u8 *)ptr;
ptr += 4;
@@ -497,44 +445,6 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
*ptr++ = htonl(opts->tsecr);
}
- /* Specification requires after timestamp, so do it now.
- *
- * Consider the pessimal case without authentication. The options
- * could look like:
- * MSS(4) + SACK|TS(12) + COOKIE(20) + WSCALE(4) == 40
- */
- if (unlikely(OPTION_COOKIE_EXTENSION & options)) {
- __u8 *cookie_copy = opts->hash_location;
- u8 cookie_size = opts->hash_size;
-
- /* 8-bit multiple handled in tcp_cookie_size_check() above,
- * and elsewhere.
- */
- if (0x2 & cookie_size) {
- __u8 *p = (__u8 *)ptr;
-
- /* 16-bit multiple */
- *p++ = TCPOPT_COOKIE;
- *p++ = TCPOLEN_COOKIE_BASE + cookie_size;
- *p++ = *cookie_copy++;
- *p++ = *cookie_copy++;
- ptr++;
- cookie_size -= 2;
- } else {
- /* 32-bit multiple */
- *ptr++ = htonl(((TCPOPT_NOP << 24) |
- (TCPOPT_NOP << 16) |
- (TCPOPT_COOKIE << 8) |
- TCPOLEN_COOKIE_BASE) +
- cookie_size);
- }
-
- if (cookie_size > 0) {
- memcpy(ptr, cookie_copy, cookie_size);
- ptr += (cookie_size / 4);
- }
- }
-
if (unlikely(OPTION_SACK_ADVERTISE & options)) {
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
@@ -593,11 +503,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
struct tcp_md5sig_key **md5)
{
struct tcp_sock *tp = tcp_sk(sk);
- struct tcp_cookie_values *cvp = tp->cookie_values;
unsigned int remaining = MAX_TCP_OPTION_SPACE;
- u8 cookie_size = (!tp->rx_opt.cookie_out_never && cvp != NULL) ?
- tcp_cookie_size_check(cvp->cookie_desired) :
- 0;
struct tcp_fastopen_request *fastopen = tp->fastopen_req;
#ifdef CONFIG_TCP_MD5SIG
@@ -649,52 +555,7 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb,
tp->syn_fastopen = 1;
}
}
- /* Note that timestamps are required by the specification.
- *
- * Odd numbers of bytes are prohibited by the specification, ensuring
- * that the cookie is 16-bit aligned, and the resulting cookie pair is
- * 32-bit aligned.
- */
- if (*md5 == NULL &&
- (OPTION_TS & opts->options) &&
- cookie_size > 0) {
- int need = TCPOLEN_COOKIE_BASE + cookie_size;
-
- if (0x2 & need) {
- /* 32-bit multiple */
- need += 2; /* NOPs */
-
- if (need > remaining) {
- /* try shrinking cookie to fit */
- cookie_size -= 2;
- need -= 4;
- }
- }
- while (need > remaining && TCP_COOKIE_MIN <= cookie_size) {
- cookie_size -= 4;
- need -= 4;
- }
- if (TCP_COOKIE_MIN <= cookie_size) {
- opts->options |= OPTION_COOKIE_EXTENSION;
- opts->hash_location = (__u8 *)&cvp->cookie_pair[0];
- opts->hash_size = cookie_size;
-
- /* Remember for future incarnations. */
- cvp->cookie_desired = cookie_size;
-
- if (cvp->cookie_desired != cvp->cookie_pair_size) {
- /* Currently use random bytes as a nonce,
- * assuming these are completely unpredictable
- * by hostile users of the same system.
- */
- get_random_bytes(&cvp->cookie_pair[0],
- cookie_size);
- cvp->cookie_pair_size = cookie_size;
- }
- remaining -= need;
- }
- }
return MAX_TCP_OPTION_SPACE - remaining;
}
@@ -704,14 +565,10 @@ static unsigned int tcp_synack_options(struct sock *sk,
unsigned int mss, struct sk_buff *skb,
struct tcp_out_options *opts,
struct tcp_md5sig_key **md5,
- struct tcp_extend_values *xvp,
struct tcp_fastopen_cookie *foc)
{
struct inet_request_sock *ireq = inet_rsk(req);
unsigned int remaining = MAX_TCP_OPTION_SPACE;
- u8 cookie_plus = (xvp != NULL && !xvp->cookie_out_never) ?
- xvp->cookie_plus :
- 0;
#ifdef CONFIG_TCP_MD5SIG
*md5 = tcp_rsk(req)->af_specific->md5_lookup(sk, req);
@@ -759,28 +616,7 @@ static unsigned int tcp_synack_options(struct sock *sk,
remaining -= need;
}
}
- /* Similar rationale to tcp_syn_options() applies here, too.
- * If the <SYN> options fit, the same options should fit now!
- */
- if (*md5 == NULL &&
- ireq->tstamp_ok &&
- cookie_plus > TCPOLEN_COOKIE_BASE) {
- int need = cookie_plus; /* has TCPOLEN_COOKIE_BASE */
-
- if (0x2 & need) {
- /* 32-bit multiple */
- need += 2; /* NOPs */
- }
- if (need <= remaining) {
- opts->options |= OPTION_COOKIE_EXTENSION;
- opts->hash_size = cookie_plus - TCPOLEN_COOKIE_BASE;
- remaining -= need;
- } else {
- /* There's no error return, so flag it. */
- xvp->cookie_out_never = 1; /* true */
- opts->hash_size = 0;
- }
- }
+
return MAX_TCP_OPTION_SPACE - remaining;
}
@@ -2802,32 +2638,24 @@ int tcp_send_synack(struct sock *sk)
* sk: listener socket
* dst: dst entry attached to the SYNACK
* req: request_sock pointer
- * rvp: request_values pointer
*
* Allocate one skb and build a SYNACK packet.
* @dst is consumed : Caller should not use it again.
*/
struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
struct request_sock *req,
- struct request_values *rvp,
struct tcp_fastopen_cookie *foc)
{
struct tcp_out_options opts;
- struct tcp_extend_values *xvp = tcp_xv(rvp);
struct inet_request_sock *ireq = inet_rsk(req);
struct tcp_sock *tp = tcp_sk(sk);
- const struct tcp_cookie_values *cvp = tp->cookie_values;
struct tcphdr *th;
struct sk_buff *skb;
struct tcp_md5sig_key *md5;
int tcp_header_size;
int mss;
- int s_data_desired = 0;
- if (cvp != NULL && cvp->s_data_constant && cvp->s_data_desired)
- s_data_desired = cvp->s_data_desired;
- skb = alloc_skb(MAX_TCP_HEADER + 15 + s_data_desired,
- sk_gfp_atomic(sk, GFP_ATOMIC));
+ skb = alloc_skb(MAX_TCP_HEADER + 15, sk_gfp_atomic(sk, GFP_ATOMIC));
if (unlikely(!skb)) {
dst_release(dst);
return NULL;
@@ -2869,9 +2697,8 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
else
#endif
TCP_SKB_CB(skb)->when = tcp_time_stamp;
- tcp_header_size = tcp_synack_options(sk, req, mss,
- skb, &opts, &md5, xvp, foc)
- + sizeof(*th);
+ tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, &md5,
+ foc) + sizeof(*th);
skb_push(skb, tcp_header_size);
skb_reset_transport_header(skb);
@@ -2889,40 +2716,6 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
tcp_init_nondata_skb(skb, tcp_rsk(req)->snt_isn,
TCPHDR_SYN | TCPHDR_ACK);
- if (OPTION_COOKIE_EXTENSION & opts.options) {
- if (s_data_desired) {
- u8 *buf = skb_put(skb, s_data_desired);
-
- /* copy data directly from the listening socket. */
- memcpy(buf, cvp->s_data_payload, s_data_desired);
- TCP_SKB_CB(skb)->end_seq += s_data_desired;
- }
-
- if (opts.hash_size > 0) {
- __u32 workspace[SHA_WORKSPACE_WORDS];
- u32 *mess = &xvp->cookie_bakery[COOKIE_DIGEST_WORDS];
- u32 *tail = &mess[COOKIE_MESSAGE_WORDS-1];
-
- /* Secret recipe depends on the Timestamp, (future)
- * Sequence and Acknowledgment Numbers, Initiator
- * Cookie, and others handled by IP variant caller.
- */
- *tail-- ^= opts.tsval;
- *tail-- ^= tcp_rsk(req)->rcv_isn + 1;
- *tail-- ^= TCP_SKB_CB(skb)->seq + 1;
-
- /* recommended */
- *tail-- ^= (((__force u32)th->dest << 16) | (__force u32)th->source);
- *tail-- ^= (u32)(unsigned long)cvp; /* per sockopt */
-
- sha_transform((__u32 *)&xvp->cookie_bakery[0],
- (char *)mess,
- &workspace[0]);
- opts.hash_location =
- (__u8 *)&xvp->cookie_bakery[0];
- }
- }
-
th->seq = htonl(TCP_SKB_CB(skb)->seq);
/* XXX data is queued and acked as is. No buffer/window check */
th->ack_seq = htonl(tcp_rsk(req)->rcv_nxt);
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 8a0848b..d5dda20 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -149,7 +149,6 @@ static inline int cookie_check(const struct sk_buff *skb, __u32 cookie)
struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
{
struct tcp_options_received tcp_opt;
- const u8 *hash_location;
struct inet_request_sock *ireq;
struct inet6_request_sock *ireq6;
struct tcp_request_sock *treq;
@@ -177,7 +176,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
/* check for timestamp cookie support */
memset(&tcp_opt, 0, sizeof(tcp_opt));
- tcp_parse_options(skb, &tcp_opt, &hash_location, 0, NULL);
+ tcp_parse_options(skb, &tcp_opt, 0, NULL);
if (!cookie_check_timestamp(&tcp_opt, sock_net(sk), &ecn_ok))
goto out;
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 9b64600..0a97add 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -454,7 +454,6 @@ out:
static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
struct flowi6 *fl6,
struct request_sock *req,
- struct request_values *rvp,
u16 queue_mapping)
{
struct inet6_request_sock *treq = inet6_rsk(req);
@@ -466,7 +465,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct dst_entry *dst,
if (!dst && (dst = inet6_csk_route_req(sk, fl6, req)) == NULL)
goto done;
- skb = tcp_make_synack(sk, dst, req, rvp, NULL);
+ skb = tcp_make_synack(sk, dst, req, NULL);
if (skb) {
__tcp_v6_send_check(skb, &treq->loc_addr, &treq->rmt_addr);
@@ -481,13 +480,12 @@ done:
return err;
}
-static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req,
- struct request_values *rvp)
+static int tcp_v6_rtx_synack(struct sock *sk, struct request_sock *req)
{
struct flowi6 fl6;
int res;
- res = tcp_v6_send_synack(sk, NULL, &fl6, req, rvp, 0);
+ res = tcp_v6_send_synack(sk, NULL, &fl6, req, 0);
if (!res)
TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_RETRANSSEGS);
return res;
@@ -940,9 +938,7 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb)
*/
static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
{
- struct tcp_extend_values tmp_ext;
struct tcp_options_received tmp_opt;
- const u8 *hash_location;
struct request_sock *req;
struct inet6_request_sock *treq;
struct ipv6_pinfo *np = inet6_sk(sk);
@@ -980,50 +976,7 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
tcp_clear_options(&tmp_opt);
tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr);
tmp_opt.user_mss = tp->rx_opt.user_mss;
- tcp_parse_options(skb, &tmp_opt, &hash_location, 0, NULL);
-
- if (tmp_opt.cookie_plus > 0 &&
- tmp_opt.saw_tstamp &&
- !tp->rx_opt.cookie_out_never &&
- (sysctl_tcp_cookie_size > 0 ||
- (tp->cookie_values != NULL &&
- tp->cookie_values->cookie_desired > 0))) {
- u8 *c;
- u32 *d;
- u32 *mess = &tmp_ext.cookie_bakery[COOKIE_DIGEST_WORDS];
- int l = tmp_opt.cookie_plus - TCPOLEN_COOKIE_BASE;
-
- if (tcp_cookie_generator(&tmp_ext.cookie_bakery[0]) != 0)
- goto drop_and_free;
-
- /* Secret recipe starts with IP addresses */
- d = (__force u32 *)&ipv6_hdr(skb)->daddr.s6_addr32[0];
- *mess++ ^= *d++;
- *mess++ ^= *d++;
- *mess++ ^= *d++;
- *mess++ ^= *d++;
- d = (__force u32 *)&ipv6_hdr(skb)->saddr.s6_addr32[0];
- *mess++ ^= *d++;
- *mess++ ^= *d++;
- *mess++ ^= *d++;
- *mess++ ^= *d++;
-
- /* plus variable length Initiator Cookie */
- c = (u8 *)mess;
- while (l-- > 0)
- *c++ ^= *hash_location++;
-
- want_cookie = false; /* not our kind of cookie */
- tmp_ext.cookie_out_never = 0; /* false */
- tmp_ext.cookie_plus = tmp_opt.cookie_plus;
- } else if (!tp->rx_opt.cookie_in_always) {
- /* redundant indications, but ensure initialization. */
- tmp_ext.cookie_out_never = 1; /* true */
- tmp_ext.cookie_plus = 0;
- } else {
- goto drop_and_free;
- }
- tmp_ext.cookie_in_always = tp->rx_opt.cookie_in_always;
+ tcp_parse_options(skb, &tmp_opt, 0, NULL);
if (want_cookie && !tmp_opt.saw_tstamp)
tcp_clear_options(&tmp_opt);
@@ -1101,7 +1054,6 @@ have_isn:
goto drop_and_release;
if (tcp_v6_send_synack(sk, dst, &fl6, req,
- (struct request_values *)&tmp_ext,
skb_get_queue_mapping(skb)) ||
want_cookie)
goto drop_and_free;
--
1.8.1.227.g44fe835
^ permalink raw reply related
* Re: [PATCH] bnx2x: fix occasional statistics off-by-4GB error
From: David Miller @ 2013-03-17 18:24 UTC (permalink / raw)
To: dmitry; +Cc: zenczykowski, maze, netdev, yuvalmin
In-Reply-To: <504C9EFCA2D0054393414C9CB605C37F20BE6A2B@SJEXCHMB06.corp.ad.broadcom.com>
From: "Dmitry Kravkov" <dmitry@broadcom.com>
Date: Sun, 17 Mar 2013 13:10:37 +0000
> Probably this commit resolved the issue:
>
> commit bef05406ac0ea6f468e1e25e9934f3011ea9259b
> Author: Dmitry Kravkov <dmitry@broadcom.com>
> Date: Tue Sep 11 04:34:08 2012 +0000
>
> bnx2x: Avoid sending multiple statistics queries
>
> Can you try it pls?
These are completely seperate bugs.
The macro in question does not handle rollover of the lower 32-bits of
the statistic properly at all, and therefore Maciej's patch should be
applied and queud up for -stable.
Please give it your ACK unless you can find a bug in his change.
^ permalink raw reply
* Re: [Patch net-next] net: fix some typos in netif features
From: David Miller @ 2013-03-17 18:26 UTC (permalink / raw)
To: amwang; +Cc: netdev, pshelar
In-Reply-To: <1363445275-3917-1-git-send-email-amwang@redhat.com>
From: Cong Wang <amwang@redhat.com>
Date: Sat, 16 Mar 2013 22:47:55 +0800
> From: Cong Wang <amwang@redhat.com>
>
> Cc: Pravin B Shelar <pshelar@nicira.com>
> Cc: "David S. Miller" <davem@davemloft.net>
> Signed-off-by: Cong Wang <amwang@redhat.com>
Applied.
^ permalink raw reply
* Re: [PATCH] sfc: make local functions static
From: David Miller @ 2013-03-17 18:26 UTC (permalink / raw)
To: stephen; +Cc: bhutchings, netdev
In-Reply-To: <20130316095751.33087a2b@nehalam.linuxnetplumber.net>
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Sat, 16 Mar 2013 09:57:51 -0700
> Trivial sparse detected functions that should be static.
>
> Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Applied, thanks Stephen.
^ permalink raw reply
* Re: [PATCH] drivers: net: irda: use resource_size() in au1k_ir.c
From: David Miller @ 2013-03-17 18:28 UTC (permalink / raw)
To: silviupopescu1990; +Cc: netdev, samuel, linux-kernel
In-Reply-To: <1363503826-24166-1-git-send-email-silviupopescu1990@gmail.com>
From: Silviu-Mihai Popescu <silviupopescu1990@gmail.com>
Date: Sun, 17 Mar 2013 09:03:46 +0200
> This uses the resource_size() function instead of explicit computation.
>
> Signed-off-by: Silviu-Mihai Popescu <silviupopescu1990@gmail.com>
Applied.
^ permalink raw reply
* Re: [PATCH net] vhost/net: fix heads usage of ubuf_info
From: David Miller @ 2013-03-17 18:29 UTC (permalink / raw)
To: mst; +Cc: kvm, netdev, linux-kernel, nab, virtualization, stable, basil.gor
In-Reply-To: <20130317124609.GA25967@redhat.com>
From: "Michael S. Tsirkin" <mst@redhat.com>
Date: Sun, 17 Mar 2013 14:46:09 +0200
> ubuf info allocator uses guest controlled head as an index,
> so a malicious guest could put the same head entry in the ring twice,
> and we will get two callbacks on the same value.
> To fix use upend_idx which is guaranteed to be unique.
>
> Reported-by: Rusty Russell <rusty@rustcorp.com.au>
> Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Applied and queued up for -stable, thanks.
And thankfully you got the stable URL wrong, please do not CC:
networking patches to stable, just make sure I apply them and in
your post-commit text explicitly ask me to queue it up to my
-stable queue.
Thanks.
^ permalink raw reply
* Re: [PATCH net-next] qdisc: propagate errors from qdisc_create_dflt
From: David Miller @ 2013-03-17 18:32 UTC (permalink / raw)
To: stephen; +Cc: netdev
In-Reply-To: <20130317093622.088bfb3f@nehalam.linuxnetplumber.net>
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Sun, 17 Mar 2013 09:36:22 -0700
> This patch improves the error handling of default queuing discipline.
>
> The function qdisc_create_dflt masks the error code from the underlying
> qdisc init function. Use IS_ERR() to propagate it back out to the callers.
>
> Change the error handling of several qdisc's to report error rather than
> silently substituting a noop qdisc. Change the log level of failure to
> setup queue discipline from info to notice, since it is a real error.
>
> In current kernel, the only likely error from pfifo_fast is out of memory,
> but the API shouldn't be hiding errors.
>
> Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
If you're going to do this, you must change all the call sites so that
they don't leave error pointers in the various datastructures.
So code that does:
foo->member = qdisc_create_dflt();
must now go:
var = qdisc_create_dflt();
if (IS_ERR(var))
goto out_err;
foo->member = var;
^ permalink raw reply
* Re: [PATCH] tcp: Remove TCPCT
From: David Miller @ 2013-03-17 18:35 UTC (permalink / raw)
To: christoph.paasch; +Cc: netdev, eric.dumazet
In-Reply-To: <1363544614-14411-1-git-send-email-christoph.paasch@uclouvain.be>
From: Christoph Paasch <christoph.paasch@uclouvain.be>
Date: Sun, 17 Mar 2013 19:23:34 +0100
> TCPCT uses option-number 253, reserved for experimental use and should
> not be used in production environments.
> Further, TCPCT does not fully implement RFC 6013.
>
> As a nice side-effect, removing TCPCT increases TCP's performance for
> very short flows:
>
> Doing an apache-benchmark with -c 100 -n 100000, sending HTTP-requests
> for files of 1KB size.
>
> before this patch:
> average (among 7 runs) of 20845.5 Requests/Second
> after:
> average (among 7 runs) of 21403.6 Requests/Second
>
> Signed-off-by: Christoph Paasch <christoph.paasch@uclouvain.be>
Applied, thanks Christoph.
^ permalink raw reply
* Re: [PATCH net] vhost/net: fix heads usage of ubuf_info
From: Michael S. Tsirkin @ 2013-03-17 18:50 UTC (permalink / raw)
To: David Miller
Cc: kvm, netdev, linux-kernel, nab, virtualization, stable, basil.gor
In-Reply-To: <20130317.142955.1114572401286297685.davem@davemloft.net>
On Sun, Mar 17, 2013 at 02:29:55PM -0400, David Miller wrote:
> From: "Michael S. Tsirkin" <mst@redhat.com>
> Date: Sun, 17 Mar 2013 14:46:09 +0200
>
> > ubuf info allocator uses guest controlled head as an index,
> > so a malicious guest could put the same head entry in the ring twice,
> > and we will get two callbacks on the same value.
> > To fix use upend_idx which is guaranteed to be unique.
> >
> > Reported-by: Rusty Russell <rusty@rustcorp.com.au>
> > Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
>
> Applied and queued up for -stable, thanks.
OK I'll drop it from my tree then.
^ permalink raw reply
* Re: BUG: IPv4: Attempt to release TCP socket in state 1
From: Eric Dumazet @ 2013-03-17 19:00 UTC (permalink / raw)
To: dormando; +Cc: Cong Wang, linux-kernel, netdev
In-Reply-To: <1363539169.29475.78.camel@edumazet-glaptop>
On Sun, 2013-03-17 at 09:52 -0700, Eric Dumazet wrote:
>
> We perform a sock_hold() somewhere while the socket is already dead.
Oh well, thats not exactly that.
When processing ICMP messages we perform a full inet[6] lookup and can
find a LISTEN socket.
Please try the following fix :
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index b7ab868..3d250c6 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -407,7 +407,8 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info)
if (code > NR_ICMP_UNREACH)
goto out;
- if (code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */
+ if (sk->sk_state != TCP_LISTEN &&
+ code == ICMP_FRAG_NEEDED) { /* PMTU discovery (RFC1191) */
tp->mtu_info = info;
if (!sock_owned_by_user(sk)) {
tcp_v4_mtu_reduced(sk);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 9b64600..c12b3ff 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -388,7 +388,7 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
dst->ops->redirect(dst, sk, skb);
}
- if (type == ICMPV6_PKT_TOOBIG) {
+ if (type == ICMPV6_PKT_TOOBIG && sk->sk_state != TCP_LISTEN) {
tp->mtu_info = ntohl(info);
if (!sock_owned_by_user(sk))
tcp_v6_mtu_reduced(sk);
^ permalink raw reply related
* Re: [PATCH] bnx2x: fix occasional statistics off-by-4GB error
From: Eilon Greenstein @ 2013-03-17 19:37 UTC (permalink / raw)
To: David Miller; +Cc: dmitry, zenczykowski, maze, netdev, yuvalmin
In-Reply-To: <20130317.142425.1713640249735424829.davem@davemloft.net>
On Sun, 2013-03-17 at 14:24 -0400, David Miller wrote:
> From: "Dmitry Kravkov" <dmitry@broadcom.com>
> Date: Sun, 17 Mar 2013 13:10:37 +0000
>
> > Probably this commit resolved the issue:
> >
> > commit bef05406ac0ea6f468e1e25e9934f3011ea9259b
> > Author: Dmitry Kravkov <dmitry@broadcom.com>
> > Date: Tue Sep 11 04:34:08 2012 +0000
> >
> > bnx2x: Avoid sending multiple statistics queries
> >
> > Can you try it pls?
>
> These are completely seperate bugs.
>
> The macro in question does not handle rollover of the lower 32-bits of
> the statistic properly at all, and therefore Maciej's patch should be
> applied and queud up for -stable.
>
> Please give it your ACK unless you can find a bug in his change.
Both the high value and the low value are read from the chip - so this
patch will increment the higher 32 bits twice (well, more than once).
Not taking the HW/FW high counter at all is also not acceptable since
the reading frequency is not high enough without those.
So the original patch is nacked, but we are trying to figure out what is
causing the statistics to misbehave and it might be related to sending
statistics query twice.
Thanks,
Eilon
^ permalink raw reply
* Re: [PATCH] bnx2x: fix occasional statistics off-by-4GB error
From: Eric Dumazet @ 2013-03-17 20:25 UTC (permalink / raw)
To: eilong; +Cc: David Miller, dmitry, zenczykowski, maze, netdev, yuvalmin
In-Reply-To: <1363549074.4752.3.camel@lb-tlvb-eilong.il.broadcom.com>
On Sun, 2013-03-17 at 21:37 +0200, Eilon Greenstein wrote:
> On Sun, 2013-03-17 at 14:24 -0400, David Miller wrote:
> > From: "Dmitry Kravkov" <dmitry@broadcom.com>
> > Date: Sun, 17 Mar 2013 13:10:37 +0000
> >
> > > Probably this commit resolved the issue:
> > >
> > > commit bef05406ac0ea6f468e1e25e9934f3011ea9259b
> > > Author: Dmitry Kravkov <dmitry@broadcom.com>
> > > Date: Tue Sep 11 04:34:08 2012 +0000
> > >
> > > bnx2x: Avoid sending multiple statistics queries
> > >
> > > Can you try it pls?
> >
> > These are completely seperate bugs.
> >
> > The macro in question does not handle rollover of the lower 32-bits of
> > the statistic properly at all, and therefore Maciej's patch should be
> > applied and queud up for -stable.
> >
> > Please give it your ACK unless you can find a bug in his change.
>
> Both the high value and the low value are read from the chip - so this
> patch will increment the higher 32 bits twice (well, more than once).
> Not taking the HW/FW high counter at all is also not acceptable since
> the reading frequency is not high enough without those.
>
> So the original patch is nacked, but we are trying to figure out what is
> causing the statistics to misbehave and it might be related to sending
> statistics query twice.
This looks like the typical problem of updating a 64bit value in non
atomic way.
Its guaranteed to happen on 32bit hosts.
We had to introduce include/linux/u64_stats_sync.h to help to solve this
without adding extra cost on 64bit arches.
In bnx2x case, we perform 32bit operations even on 64bit host, so we
probably need to add a seqcount_t, so that a stat consumer can detect it
read a stale value.
^ permalink raw reply
* Re: [PATCH] bnx2x: fix occasional statistics off-by-4GB error
From: Eilon Greenstein @ 2013-03-17 20:53 UTC (permalink / raw)
To: Eric Dumazet; +Cc: David Miller, dmitry, zenczykowski, maze, netdev, yuvalmin
In-Reply-To: <1363551952.29475.93.camel@edumazet-glaptop>
On Sun, 2013-03-17 at 13:25 -0700, Eric Dumazet wrote:
> On Sun, 2013-03-17 at 21:37 +0200, Eilon Greenstein wrote:
> > On Sun, 2013-03-17 at 14:24 -0400, David Miller wrote:
> > > From: "Dmitry Kravkov" <dmitry@broadcom.com>
> > > Date: Sun, 17 Mar 2013 13:10:37 +0000
> > >
> > > > Probably this commit resolved the issue:
> > > >
> > > > commit bef05406ac0ea6f468e1e25e9934f3011ea9259b
> > > > Author: Dmitry Kravkov <dmitry@broadcom.com>
> > > > Date: Tue Sep 11 04:34:08 2012 +0000
> > > >
> > > > bnx2x: Avoid sending multiple statistics queries
> > > >
> > > > Can you try it pls?
> > >
> > > These are completely seperate bugs.
> > >
> > > The macro in question does not handle rollover of the lower 32-bits of
> > > the statistic properly at all, and therefore Maciej's patch should be
> > > applied and queud up for -stable.
> > >
> > > Please give it your ACK unless you can find a bug in his change.
> >
> > Both the high value and the low value are read from the chip - so this
> > patch will increment the higher 32 bits twice (well, more than once).
> > Not taking the HW/FW high counter at all is also not acceptable since
> > the reading frequency is not high enough without those.
> >
> > So the original patch is nacked, but we are trying to figure out what is
> > causing the statistics to misbehave and it might be related to sending
> > statistics query twice.
>
> This looks like the typical problem of updating a 64bit value in non
> atomic way.
>
> Its guaranteed to happen on 32bit hosts.
> We had to introduce include/linux/u64_stats_sync.h to help to solve this
> without adding extra cost on 64bit arches.
>
> In bnx2x case, we perform 32bit operations even on 64bit host, so we
> probably need to add a seqcount_t, so that a stat consumer can detect it
> read a stale value.
This is not such a trivial issue - the HW/FW is guaranteeing the atomic
read and this is why we can always use 32b variables.
^ permalink raw reply
* Re: [PATCHv3 vringh] caif_virtio: Introduce caif over virtio
From: Ohad Ben-Cohen @ 2013-03-17 22:52 UTC (permalink / raw)
To: Erwan Yvin
Cc: David S. Miller, Rusty Russel, Sjur Braendeland, Linus Walleij,
virtualization, netdev, Rusty Russell
In-Reply-To: <1363340537-16011-1-git-send-email-erwan.yvin@stericsson.com>
Hi Erwan,
On Fri, Mar 15, 2013 at 11:42 AM, Erwan Yvin <erwan.yvin@stericsson.com> wrote:
> diff --git a/drivers/net/caif/caif_virtio.c b/drivers/net/caif/caif_virtio.c
> new file mode 100644
> index 0000000..6a745dd
> --- /dev/null
> +++ b/drivers/net/caif/caif_virtio.c
> @@ -0,0 +1,786 @@
> +/*
> + * Copyright (C) ST-Ericsson AB 2013
> + * Authors: Vicram Arv / vikram.arv@stericsson.com,
> + * Dmitry Tarnyagin / dmitry.tarnyagin@stericsson.com
> + * Sjur Brendeland / sjur.brandeland@stericsson.com
> + * License terms: GNU General Public License (GPL) version 2
> + */
> +#include <linux/module.h>
> +#include <linux/if_arp.h>
> +#include <linux/virtio.h>
> +#include <linux/vringh.h>
> +#include <linux/debugfs.h>
> +#include <linux/spinlock.h>
> +#include <linux/genalloc.h>
> +#include <linux/interrupt.h>
> +#include <linux/netdevice.h>
> +#include <linux/rtnetlink.h>
> +#include <linux/remoteproc.h>
The driver looks nicely decoupled from remoteproc - do you still need
remoteproc.h ?
Thanks,
Ohad.
^ permalink raw reply
* Re: [PATCH] bnx2x: fix occasional statistics off-by-4GB error
From: Eric Dumazet @ 2013-03-17 23:17 UTC (permalink / raw)
To: eilong; +Cc: David Miller, dmitry, zenczykowski, maze, netdev, yuvalmin
In-Reply-To: <1363553608.4752.5.camel@lb-tlvb-eilong.il.broadcom.com>
On Sun, 2013-03-17 at 22:53 +0200, Eilon Greenstein wrote:
> This is not such a trivial issue - the HW/FW is guaranteeing the atomic
> read and this is why we can always use 32b variables.
>
I am glad you qualify the following code as 'trivial'
/* difference = minuend - subtrahend */
#define DIFF_64(d_hi, m_hi, s_hi, d_lo, m_lo, s_lo) \
do { \
if (m_lo < s_lo) { \
/* underflow */ \
d_hi = m_hi - s_hi; \
if (d_hi > 0) { \
/* we can 'loan' 1 */ \
d_hi--; \
d_lo = m_lo + (UINT_MAX - s_lo) + 1; \
} else { \
/* m_hi <= s_hi */ \
d_hi = 0; \
d_lo = 0; \
} \
} else { \
/* m_lo >= s_lo */ \
if (m_hi < s_hi) { \
d_hi = 0; \
d_lo = 0; \
} else { \
/* m_hi >= s_hi */ \
d_hi = m_hi - s_hi; \
d_lo = m_lo - s_lo; \
} \
} \
} while (0)
All the macros and _hi/_ho fields found in
drivers/net/ethernet/broadcom/bnx2x/bnx2x_stats.h
are really badly designed.
It hurts so much the common sense its not even funny.
All you really needed is to have normal host structures containing u64
fields, and you only needed one single helper to convert from hw u32:u32
to host u64.
Because gcc handles u64 operations very well, even on 32bit hosts, and
it knows about the carry flag.
^ permalink raw reply
* Re: [PATCHi v2] net: sh_eth: Add support of device tree probe
From: Nobuhiro Iwamatsu @ 2013-03-18 0:53 UTC (permalink / raw)
To: Mark Rutland
Cc: netdev@vger.kernel.org, devicetree-discuss@lists.ozlabs.org,
magnus.damm@gmail.com, kda@linux-powerpc.org,
horms+renesas@verge.net.au
In-Reply-To: <20130215163251.GA2597@e106331-lin.cambridge.arm.com>
Hi,
On Sat, Feb 16, 2013 at 1:32 AM, Mark Rutland <mark.rutland@arm.com> wrote:
> Hello,
>
> I have a couple of comments on the binding and the way it's parsed.
Thank you for your comment.
>
> On Thu, Feb 14, 2013 at 12:51:31AM +0000, Nobuhiro Iwamatsu wrote:
>> This adds support of device tree probe for Renesas sh-ether driver.
>>
>> Signed-off-by: Nobuhiro Iwamatsu <nobuhiro.iwamatsu.yj@renesas.com>
>>
>> ---
>> V2: - Removed ether_setup().
>> - Fixed typo from "sh-etn" to "sh-eth".
>> - Removed "needs-init" and sh-eth,endian from definition of DT.
>> - Changed "sh-eth,edmac-endian" instead of "sh-eth,edmac-big-endain"
>> in definition of DT.
>>
>> Documentation/devicetree/bindings/net/sh_ether.txt | 41 +++++
>> drivers/net/ethernet/renesas/sh_eth.c | 156 +++++++++++++++++---
>> 2 files changed, 173 insertions(+), 24 deletions(-)
>> create mode 100644 Documentation/devicetree/bindings/net/sh_ether.txt
>>
>> diff --git a/Documentation/devicetree/bindings/net/sh_ether.txt b/Documentation/devicetree/bindings/net/sh_ether.txt
>> new file mode 100644
>> index 0000000..7415e54
>> --- /dev/null
>> +++ b/Documentation/devicetree/bindings/net/sh_ether.txt
>> @@ -0,0 +1,41 @@
>> +* Renesas Electronics SuperH EMAC
>> +
>> +This file provides information, what the device node
>> +for the sh_eth interface contains.
>> +
>> +Required properties:
>> +- compatible: "renesas,sh-eth";
>> +- interrupt-parent: The phandle for the interrupt controller that
>> + services interrupts for this device.
>
> Is this really a required property?
>
> As it's a standard property with a well-defined meaning, is it necessary to
> document?
Yes, this is necessary.
CPU handled by this device has multiple interrupt controllers. It uses
the interrupt vector ID.
The interrupt controller may have the same vector id. This is
necessary in order to distinguish
between them.
>
>> +- reg: Offset and length of the register set for the
>> + device.
>
> The example below shows 2 reg values, yet this implies only one is necessary.
OK, I will add more infomation for first registger and 2nd register.
>
>> +- interrupts: Interrupt mapping for the sh_eth interrupt
>> + sources (vector id).
>
> How many interrupts are expected, what are they, and in what order should they be in?
This should contain sh-eth LAN interrupt line.
One value is set up. I will add these.
>
>> +- phy-mode: String, operation mode of the PHY interface.
>
> What are the valid values for this?
A string that of_get_phy_mode() can understand.
I will add more infomation.
>
> If they're defined in another document, it'd be good to reference it.
>
>> +- sh-eth,register-type: String, register type of sh_eth.
>> + Please select "gigabit", "fast-sh4" or
>> + "fast-sh3-sh2".
>
> Why are these not handled as separate versions using the compatible string to
> differentiate them?
As you pointed, this line was removed and moved to using compatible string.
>
> [...]
>
>> +- sh-eth,phy-id: PHY id.
>> +
>> +Optional properties:
>> +- local-mac-address: 6 bytes, mac address
>> +- sh-eth,no-ether-link: Set link control by software. When device does
>> + not support ether-link, set.
>> +- sh-eth,ether-link-active-low: Set link check method.
>> + When detection of link is treated as active-low,
>> + set.
>> +- sh-eth,edmac-big-endian: Set big endian for sh_eth dmac.
>> + It work as little endian when this is not set.
>> +- sh-etn,needs-init: Initialization flag.
>> + When initialize device in probing device, set.
>> +
>> +Example (armadillo800eva):
>> + sh-eth@e9a00000 {
>> + compatible = "renesas,sh-eth";
>> + interrupt-parent = <&intca>;
>> + reg = <0xe9a00000 0x800>, <0xe9a01800 0x800>;
>> + interrupts = <0x500>;
>> + phy-mode = "mii";
>> + sh-eth,register-type = "gigabit";
>> + sh-eth,phy-id = <0>;
>> + };
>> diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c
>> index 3d70586..15e50b87 100644
>> --- a/drivers/net/ethernet/renesas/sh_eth.c
>> +++ b/drivers/net/ethernet/renesas/sh_eth.c
>> @@ -1,7 +1,7 @@
>> /*
>> * SuperH Ethernet device driver
>> *
>> - * Copyright (C) 2006-2012 Nobuhiro Iwamatsu
>> + * Copyright (C) 2006-2013 Nobuhiro Iwamatsu
>> * Copyright (C) 2008-2012 Renesas Solutions Corp.
>> *
>> * This program is free software; you can redistribute it and/or modify it
>> @@ -31,6 +31,12 @@
>> #include <linux/platform_device.h>
>> #include <linux/mdio-bitbang.h>
>> #include <linux/netdevice.h>
>> +#include <linux/of.h>
>> +#include <linux/of_device.h>
>> +#include <linux/of_platform.h>
>> +#include <linux/of_address.h>
>> +#include <linux/of_irq.h>
>> +#include <linux/of_net.h>
>> #include <linux/phy.h>
>> #include <linux/cache.h>
>> #include <linux/io.h>
>> @@ -2347,26 +2353,109 @@ static const struct net_device_ops sh_eth_netdev_ops = {
>> .ndo_change_mtu = eth_change_mtu,
>> };
>>
>> +#ifdef CONFIG_OF
>> +
>> +static int
>> +sh_eth_of_get_register_type(struct device_node *np)
>> +{
>> + const char *of_str;
>> + int ret = of_property_read_string(np, "sh-eth,register-type", &of_str);
>> + if (ret)
>> + return ret;
>> +
>> + if (of_str && !strcmp(of_str, "gigabit"))
>> + return SH_ETH_REG_GIGABIT;
>> +
>
> This line space between the if and the else should disappear.
OK, I will fix.
>
>> + else if (of_str && !strcmp(of_str, "fast-sh4"))
>> + return SH_ETH_REG_FAST_SH4;
>> + else if (of_str && !strcmp(of_str, "fast-sh3-sh2"))
>> + return SH_ETH_REG_FAST_SH3_SH2;
>> + else
>> + return -EINVAL;
>
> I think this block is better handled using a compatible string.
I see, I will fix and update document.
>
>> +}
>> +
>> +static struct sh_eth_plat_data *
>> +sh_eth_parse_dt(struct device *dev, struct net_device *ndev)
>> +{
>> + int ret;
>> + struct device_node *np = dev->of_node;
>> + struct sh_eth_plat_data *pdata;
>> +
>> + pdata = devm_kzalloc(dev, sizeof(struct sh_eth_plat_data),
>> + GFP_KERNEL);
>> + if (!pdata) {
>> + dev_err(dev, "%s: failed to allocate config data\n", __func__);
>> + return NULL;
>> + }
>> +
>> + pdata->phy_interface = of_get_phy_mode(np);
>> +
>> + of_property_read_u32(np, "sh-eth,phy-id", &pdata->phy);
>
> No sanity checking required?
>
> Is there a maximum possible PHY id?
>
OK, I will add sanity checking.
>> +
>> + if (of_find_property(np, "sh-eth,edmac-big-endian", NULL))
>> + pdata->edmac_endian = EDMAC_BIG_ENDIAN;
>> + else
>> + pdata->edmac_endian = EDMAC_LITTLE_ENDIAN;
>
> You can use of_property_read_bool here.
>
OK, I will fix.
>> +
>> + if (of_find_property(np, "sh-eth,no-ether-link", NULL))
>> + pdata->no_ether_link = 1;
>> + else
>> + pdata->no_ether_link = 0;
>
> This can be:
>
> pdata->no_ether_link = of_property_read_bool(np, "sh-eth,no-ether-link");
OK, I will fix.
>
>> +
>> + if (of_find_property(np, "sh-eth,ether-link-active-low", NULL))
>> + pdata->ether_link_active_low = 1;
>> + else
>> + pdata->ether_link_active_low = 0;
>
> A similar thing can be done here.
and this too.
>
>> +
>> + ret = sh_eth_of_get_register_type(np);
>> + if (ret < 0)
>> + goto error;
>> + pdata->register_type = ret;
>
> This could be done using the compatible string and some auxdata.
OK, I will fix.
>
> [...]
>
> Thanks,
> Mark.
> _______________________________________________
Best regards,
Nobuhiro
--
Nobuhiro Iwamatsu
^ permalink raw reply
* Re: [PATCH][v3.2.y] xen-netfront: delay gARP until backend switches to Connected
From: Ben Hutchings @ 2013-03-18 2:19 UTC (permalink / raw)
To: Joseph Salisbury
Cc: jeremy, xen-devel, konrad.wilk, netdev, stable, virtualization
In-Reply-To: <514360DD.8050406@canonical.com>
[-- Attachment #1.1: Type: text/plain, Size: 679 bytes --]
On Fri, 2013-03-15 at 13:56 -0400, Joseph Salisbury wrote:
> Hello,
>
> Please consider including upstream commit
> 08e34eb14fe4cfd934b5c169a7682a969457c4ea in the next v3.2.y release.
> It was included upstream as of v3.3-rc1. It has been tested and
> confirmed to resolve http://bugs.launchpad.net/bugs/1154608 .
>
> commit 08e34eb14fe4cfd934b5c169a7682a969457c4ea
> Author: Laszlo Ersek <lersek@redhat.com>
> Date: Sun Dec 11 01:48:59 2011 +0000
>
> xen-netfront: delay gARP until backend switches to Connected
Added to the queue, thanks.
Ben.
--
Ben Hutchings
Never attribute to conspiracy what can adequately be explained by stupidity.
[-- Attachment #1.2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 828 bytes --]
[-- Attachment #2: Type: text/plain, Size: 183 bytes --]
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
^ permalink raw reply
* [PATCH nf-next] netfilter: nfnetlink_queue: zero copy support
From: Eric Dumazet @ 2013-03-18 3:15 UTC (permalink / raw)
To: Pablo Neira Ayuso; +Cc: netdev, Netfilter Developer Mailing List
From: Eric Dumazet <edumazet@google.com>
nfqnl_build_packet_message() actually copy the packet
inside the netlink message, while it can instead use
zero copy.
Make sure the skb 'copy' is the last component of the
cooked netlink message, as we cant add anything after it.
Patch cooked in Copenhagen at Netfilter Workshop ;)
Still to be addressed in separate patches :
-GRO/GSO packets are segmented in nf_queue()
and checksummed in nfqnl_build_packet_message().
Proper support for GSO/GRO packets (no segmentation,
and no checksumming) needs application cooperation, if we
want no regressions.
Signed-off-by: Eric Dumazet <edumazet@google.com>
---
net/netfilter/nfnetlink_queue_core.c | 94 +++++++++++++++++++------
1 file changed, 72 insertions(+), 22 deletions(-)
diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c
index 858fd52..388fb8ba3 100644
--- a/net/netfilter/nfnetlink_queue_core.c
+++ b/net/netfilter/nfnetlink_queue_core.c
@@ -217,14 +217,59 @@ nfqnl_flush(struct nfqnl_instance *queue, nfqnl_cmpfn cmpfn, unsigned long data)
spin_unlock_bh(&queue->lock);
}
+static void
+nfqnl_zcopy(struct sk_buff *to, const struct sk_buff *from, int len, int hlen)
+{
+ int i, j = 0;
+ int plen = 0; /* length of skb->head fragment */
+ struct page *page;
+ unsigned int offset;
+
+ /* dont bother with small payloads */
+ if (len <= skb_tailroom(to)) {
+ skb_copy_bits(from, 0, skb_put(to, len), len);
+ return;
+ }
+
+ if (hlen) {
+ skb_copy_bits(from, 0, skb_put(to, hlen), hlen);
+ len -= hlen;
+ } else {
+ plen = min_t(int, skb_headlen(from), len);
+ if (plen) {
+ page = virt_to_head_page(from->head);
+ offset = from->data - (unsigned char *)page_address(page);
+ __skb_fill_page_desc(to, 0, page, offset, plen);
+ get_page(page);
+ j = 1;
+ len -= plen;
+ }
+ }
+
+ to->truesize += len + plen;
+ to->len += len + plen;
+ to->data_len += len + plen;
+
+ for (i = 0; i < skb_shinfo(from)->nr_frags; i++) {
+ if (!len)
+ break;
+ skb_shinfo(to)->frags[j] = skb_shinfo(from)->frags[i];
+ skb_shinfo(to)->frags[j].size = min_t(int, skb_shinfo(to)->frags[j].size, len);
+ len -= skb_shinfo(to)->frags[j].size;
+ skb_frag_ref(to, j);
+ j++;
+ }
+ skb_shinfo(to)->nr_frags = j;
+}
+
static struct sk_buff *
nfqnl_build_packet_message(struct nfqnl_instance *queue,
struct nf_queue_entry *entry,
__be32 **packet_id_ptr)
{
- sk_buff_data_t old_tail;
size_t size;
size_t data_len = 0, cap_len = 0;
+ int hlen = 0;
struct sk_buff *skb;
struct nlattr *nla;
struct nfqnl_msg_packet_hdr *pmsg;
@@ -246,8 +291,10 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue,
#endif
+ nla_total_size(sizeof(u_int32_t)) /* mark */
+ nla_total_size(sizeof(struct nfqnl_msg_packet_hw))
- + nla_total_size(sizeof(struct nfqnl_msg_packet_timestamp)
- + nla_total_size(sizeof(u_int32_t))); /* cap_len */
+ + nla_total_size(sizeof(u_int32_t)); /* cap_len */
+
+ if (entskb->tstamp.tv64)
+ size += nla_total_size(sizeof(struct nfqnl_msg_packet_timestamp));
outdev = entry->outdev;
@@ -265,7 +312,16 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue,
if (data_len == 0 || data_len > entskb->len)
data_len = entskb->len;
- size += nla_total_size(data_len);
+
+ if (!entskb->head_frag ||
+ skb_headlen(entskb) < L1_CACHE_BYTES ||
+ skb_shinfo(entskb)->nr_frags >= MAX_SKB_FRAGS)
+ hlen = skb_headlen(entskb);
+
+ if (skb_has_frag_list(entskb))
+ hlen = entskb->len;
+ hlen = min_t(int, data_len, hlen);
+ size += sizeof(struct nlattr) + hlen;
cap_len = entskb->len;
break;
}
@@ -277,7 +333,6 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue,
if (!skb)
return NULL;
- old_tail = skb->tail;
nlh = nlmsg_put(skb, 0, 0,
NFNL_SUBSYS_QUEUE << 8 | NFQNL_MSG_PACKET,
sizeof(struct nfgenmsg), 0);
@@ -382,31 +437,26 @@ nfqnl_build_packet_message(struct nfqnl_instance *queue,
goto nla_put_failure;
}
+ if (ct && nfqnl_ct_put(skb, ct, ctinfo) < 0)
+ goto nla_put_failure;
+
+ if (cap_len > 0 && nla_put_be32(skb, NFQA_CAP_LEN, htonl(cap_len)))
+ goto nla_put_failure;
+
if (data_len) {
struct nlattr *nla;
- int sz = nla_attr_size(data_len);
- if (skb_tailroom(skb) < nla_total_size(data_len)) {
- printk(KERN_WARNING "nf_queue: no tailroom!\n");
- kfree_skb(skb);
- return NULL;
- }
+ if (skb_tailroom(skb) < sizeof(*nla) + hlen)
+ goto nla_put_failure;
- nla = (struct nlattr *)skb_put(skb, nla_total_size(data_len));
+ nla = (struct nlattr *)skb_put(skb, sizeof(*nla));
nla->nla_type = NFQA_PAYLOAD;
- nla->nla_len = sz;
+ nla->nla_len = nla_attr_size(data_len);
- if (skb_copy_bits(entskb, 0, nla_data(nla), data_len))
- BUG();
+ nfqnl_zcopy(skb, entskb, data_len, hlen);
}
- if (ct && nfqnl_ct_put(skb, ct, ctinfo) < 0)
- goto nla_put_failure;
-
- if (cap_len > 0 && nla_put_be32(skb, NFQA_CAP_LEN, htonl(cap_len)))
- goto nla_put_failure;
-
- nlh->nlmsg_len = skb->tail - old_tail;
+ nlh->nlmsg_len = skb->len;
return skb;
nla_put_failure:
^ permalink raw reply related
* Re: [PATCHv3 vringh] caif_virtio: Introduce caif over virtio
From: Rusty Russell @ 2013-03-18 3:46 UTC (permalink / raw)
To: Erwan Yvin, David S. Miller, Rusty Russel
Cc: Linus Walleij, netdev, Erwan Yvin, virtualization,
Sjur Braendeland
In-Reply-To: <1363340537-16011-1-git-send-email-erwan.yvin@stericsson.com>
Erwan Yvin <erwan.yvin@stericsson.com> writes:
> From: Erwan Yvin <erwan.yvin@stericsson.com>
>
> Add the CAIF Virtio shared memory driver for talking
> to a modem.
I've added a minor build fix:
caif_virtio: fix compilation
ERROR: "gen_pool_add_virt" [drivers/net/caif/caif_virtio.ko] undefined!
ERROR: "gen_pool_create" [drivers/net/caif/caif_virtio.ko] undefined!
ERROR: "gen_pool_destroy" [drivers/net/caif/caif_virtio.ko] undefined!
ERROR: "gen_pool_free" [drivers/net/caif/caif_virtio.ko] undefined!
ERROR: "gen_pool_alloc" [drivers/net/caif/caif_virtio.ko] undefined!
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
diff --git a/drivers/net/caif/Kconfig b/drivers/net/caif/Kconfig
index 676cfff..893f915 100644
--- a/drivers/net/caif/Kconfig
+++ b/drivers/net/caif/Kconfig
@@ -53,6 +53,7 @@ config CAIF_VIRTIO
depends on CAIF
select VHOST_RING
select VIRTIO
+ select GENERIC_ALLOCATOR
default n
---help---
The caif driver for CAIF over Virtio.
^ permalink raw reply related
* Re: [PATCH] bnx2x: fix occasional statistics off-by-4GB error
From: Maciej Żenczykowski @ 2013-03-18 6:18 UTC (permalink / raw)
To: eilong
Cc: Eric Dumazet, David Miller, Dmitry Kravkov, Linux NetDev,
Mintz Yuval
In-Reply-To: <1363553608.4752.5.camel@lb-tlvb-eilong.il.broadcom.com>
This has nothing to do with atomicity or races or anything.
Look at the ADD_64 macro (which implements a += b) and compare it to
this one (which implents a = b + c).
It simply doesn't know how to correctly add in any situation in which
"qstats_old->t..._lo != 0".
By this point all the stats are already in software and both firmware
and hardware is not relevant.
Normally qstats_old starts off at 0 and the bug isn't visible (since
with a value of 0, there can't be overflow and carry propagation is
not needed).
The reason qstats_old was introduced was to allow for a partial nic
reset [or whatever the proper term is] which resets fw/hw provided
stats to not reset sw exported stats.
During the reset old stats are copied into qstats_old, and in the
future stats are returned as "qstats_old + current stats from fw/hw"
except this addition is buggy and only works if qstats_old happens to
have lower 32-bits zero (ie. basically only before first partial nic
reset).
Imagine:
(a) driver initializes, nic gets brought up, qstats_old = 0, stats
from device = 0
(b) 2GB of xfer happens
(c) qstats_old still = 0, stats from device = 2GB
(d) addition happens qstats = qstats_old + stats_from_dev = 0 + 2GB =
2GB --- we report 2GB xfer
(e) something partially resets nic (say mtu change), qstats_old = 2GB,
stats from device = 0
(f) 2GB-1 of xfer happens
(g) qstats_old = 2GB, stats from device = 2GB-1
(h) addition happens qstats = qstats_old + stats_from_dev = 2GB +
2GB-1 = 4GB-1 --- we report 4GB-1 xfer
(i) 1 byte of xfer happens
(j) qstats_old = 2GB, stats from device = 2GB
(k) addition happens qstats = qstats_old + stats_from_dev = 2GB + 2GB
= 0 --- we report 0 xfer
(l) 2GB of xfer happens
(m) qstats_old = 2GB, stats from device = 4GB
(n) addition happens qstats = qstats_old + stats_from_dev = 2GB + 4GB
= 6GB --- we report 6GB xfer
And yes the macro in question when asked to do 2GB+2GB will return 0.
(btw. at least on the driver I tested there's still some weirdness
with mtu change not-resetting per-queue stats but resetting
coalesced-from-all-queues stats)
Now, to be fair, I don't yet have confirmation that my patch fixes the
problem our SREs saw in deployment, but I expect to have that soon.
(and even if it doesn't fix the problem, this code is still buggy and
should be fixed)
Maciej
On Sun, Mar 17, 2013 at 1:53 PM, Eilon Greenstein <eilong@broadcom.com> wrote:
> On Sun, 2013-03-17 at 13:25 -0700, Eric Dumazet wrote:
>> On Sun, 2013-03-17 at 21:37 +0200, Eilon Greenstein wrote:
>> > On Sun, 2013-03-17 at 14:24 -0400, David Miller wrote:
>> > > From: "Dmitry Kravkov" <dmitry@broadcom.com>
>> > > Date: Sun, 17 Mar 2013 13:10:37 +0000
>> > >
>> > > > Probably this commit resolved the issue:
>> > > >
>> > > > commit bef05406ac0ea6f468e1e25e9934f3011ea9259b
>> > > > Author: Dmitry Kravkov <dmitry@broadcom.com>
>> > > > Date: Tue Sep 11 04:34:08 2012 +0000
>> > > >
>> > > > bnx2x: Avoid sending multiple statistics queries
>> > > >
>> > > > Can you try it pls?
>> > >
>> > > These are completely seperate bugs.
>> > >
>> > > The macro in question does not handle rollover of the lower 32-bits of
>> > > the statistic properly at all, and therefore Maciej's patch should be
>> > > applied and queud up for -stable.
>> > >
>> > > Please give it your ACK unless you can find a bug in his change.
>> >
>> > Both the high value and the low value are read from the chip - so this
>> > patch will increment the higher 32 bits twice (well, more than once).
>> > Not taking the HW/FW high counter at all is also not acceptable since
>> > the reading frequency is not high enough without those.
>> >
>> > So the original patch is nacked, but we are trying to figure out what is
>> > causing the statistics to misbehave and it might be related to sending
>> > statistics query twice.
>>
>> This looks like the typical problem of updating a 64bit value in non
>> atomic way.
>>
>> Its guaranteed to happen on 32bit hosts.
>> We had to introduce include/linux/u64_stats_sync.h to help to solve this
>> without adding extra cost on 64bit arches.
>>
>> In bnx2x case, we perform 32bit operations even on 64bit host, so we
>> probably need to add a seqcount_t, so that a stat consumer can detect it
>> read a stale value.
>
> This is not such a trivial issue - the HW/FW is guaranteeing the atomic
> read and this is why we can always use 32b variables.
>
>
^ permalink raw reply
* Re: [RFC 0/3] arm: mxs: sanitize enet_out clock handling
From: Shawn Guo @ 2013-03-18 6:40 UTC (permalink / raw)
To: Trent Piepho; +Cc: Wolfram Sang, linux-arm-kernel, netdev, Shawn Guo
In-Reply-To: <CA+7tXiinVCjs7NAdGd+0KyUL+kfwWUi_XAPYdMHiugT3W2Xz4w@mail.gmail.com>
On Fri, Mar 15, 2013 at 02:27:35PM -0700, Trent Piepho wrote:
> But as you say most boards need enet_out (AFAICT, all but the Denx
> board). So wouldn't it make more sense to add enet_out to the dtsi
> file and then just override it in the one board that doesn't need it,
> instead of overriding in every board except that one?
Yes, sounds reasonable. Since I'm not sure Wolfram is still interested
in the work, I will pick it up from here.
Shawn
^ permalink raw reply
* [PATCH net-next 0/2] be2net: patch set
From: Somnath Kotur @ 2013-03-18 7:03 UTC (permalink / raw)
To: netdev; +Cc: davem, Somnath Kotur
Pls apply.
Somnath Kotur (2):
be2net: enable interrupts in be_probe() (RoCE and other ULPs need
them)
be2net: Use new F/W mailbox cmd to manipulate interrupts.
drivers/net/ethernet/emulex/benet/be_cmds.c | 25 +++++++++++++++++
drivers/net/ethernet/emulex/benet/be_cmds.h | 8 +++++
drivers/net/ethernet/emulex/benet/be_main.c | 38 ++++++++++++++++----------
3 files changed, 56 insertions(+), 15 deletions(-)
^ permalink raw reply
* [PATCH net-next 1/2] be2net: enable interrupts in be_probe() (RoCE and other ULPs need them)
From: Somnath Kotur @ 2013-03-18 7:04 UTC (permalink / raw)
To: netdev; +Cc: davem, Somnath Kotur, Sathya Perla
As the NIC PCI function may be used by other protocols, the chip interrupts
must be enabled in be_probe() itself rather than be_open().
Signed-off-by: Sathya Perla <sathya.perla@emulex.com>
Signed-off-by: Somnath Kotur <somnath.kotur@emulex.com>
---
drivers/net/ethernet/emulex/benet/be_main.c | 21 ++++++++++-----------
1 files changed, 10 insertions(+), 11 deletions(-)
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index b8e5019..dae7172 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -157,6 +157,10 @@ static void be_intr_set(struct be_adapter *adapter, bool enable)
{
u32 reg, enabled;
+ /* On lancer interrupts can't be controlled via this register */
+ if (lancer_chip(adapter))
+ return;
+
if (adapter->eeh_error)
return;
@@ -2435,9 +2439,6 @@ static int be_close(struct net_device *netdev)
be_roce_dev_close(adapter);
- if (!lancer_chip(adapter))
- be_intr_set(adapter, false);
-
for_all_evt_queues(adapter, eqo, i)
napi_disable(&eqo->napi);
@@ -2525,9 +2526,6 @@ static int be_open(struct net_device *netdev)
be_irq_register(adapter);
- if (!lancer_chip(adapter))
- be_intr_set(adapter, true);
-
for_all_rx_queues(adapter, rxo, i)
be_cq_notify(adapter, rxo->cq.id, true, 0);
@@ -3853,6 +3851,7 @@ static void be_remove(struct pci_dev *pdev)
return;
be_roce_dev_remove(adapter);
+ be_intr_set(adapter, false);
cancel_delayed_work_sync(&adapter->func_recovery_work);
@@ -4142,11 +4141,11 @@ static int be_probe(struct pci_dev *pdev, const struct pci_device_id *pdev_id)
goto ctrl_clean;
}
- /* The INTR bit may be set in the card when probed by a kdump kernel
- * after a crash.
- */
- if (!lancer_chip(adapter))
- be_intr_set(adapter, false);
+ /* Wait for interrupts to quiesce after an FLR */
+ msleep(100);
+
+ /* Allow interrupts for other ULPs running on NIC function */
+ be_intr_set(adapter, true);
status = be_stats_init(adapter);
if (status)
--
1.5.6.1
^ permalink raw reply related
* [PATCH net-next 2/2] be2net: Use new F/W mailbox cmd to manipulate interrupts.
From: Somnath Kotur @ 2013-03-18 7:04 UTC (permalink / raw)
To: netdev; +Cc: davem, Somnath Kotur
This is needed as the earlier method of manipulating this register via PCI
Config space is disallowed by certain Hypervisors.
Signed-off-by: Somnath Kotur <somnath.kotur@emulex.com>
---
drivers/net/ethernet/emulex/benet/be_cmds.c | 25 +++++++++++++++++++++++++
drivers/net/ethernet/emulex/benet/be_cmds.h | 8 ++++++++
drivers/net/ethernet/emulex/benet/be_main.c | 25 +++++++++++++++++--------
3 files changed, 50 insertions(+), 8 deletions(-)
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.c b/drivers/net/ethernet/emulex/benet/be_cmds.c
index 6ed4639..9916364 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.c
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.c
@@ -3202,6 +3202,31 @@ err:
return status;
}
+int be_cmd_intr_set(struct be_adapter *adapter, bool intr_enable)
+{
+ struct be_mcc_wrb *wrb;
+ struct be_cmd_req_intr_set *req;
+ int status;
+
+ if (mutex_lock_interruptible(&adapter->mbox_lock))
+ return -1;
+
+ wrb = wrb_from_mbox(adapter);
+
+ req = embedded_payload(wrb);
+
+ be_wrb_cmd_hdr_prepare(&req->hdr, CMD_SUBSYSTEM_COMMON,
+ OPCODE_COMMON_SET_INTERRUPT_ENABLE, sizeof(*req),
+ wrb, NULL);
+
+ req->intr_enabled = intr_enable;
+
+ status = be_mbox_notify_wait(adapter);
+
+ mutex_unlock(&adapter->mbox_lock);
+ return status;
+}
+
int be_roce_mcc_cmd(void *netdev_handle, void *wrb_payload,
int wrb_payload_size, u16 *cmd_status, u16 *ext_status)
{
diff --git a/drivers/net/ethernet/emulex/benet/be_cmds.h b/drivers/net/ethernet/emulex/benet/be_cmds.h
index 6ef4575..f2af855 100644
--- a/drivers/net/ethernet/emulex/benet/be_cmds.h
+++ b/drivers/net/ethernet/emulex/benet/be_cmds.h
@@ -188,6 +188,7 @@ struct be_mcc_mailbox {
#define OPCODE_COMMON_GET_BEACON_STATE 70
#define OPCODE_COMMON_READ_TRANSRECV_DATA 73
#define OPCODE_COMMON_GET_PORT_NAME 77
+#define OPCODE_COMMON_SET_INTERRUPT_ENABLE 89
#define OPCODE_COMMON_GET_PHY_DETAILS 102
#define OPCODE_COMMON_SET_DRIVER_FUNCTION_CAP 103
#define OPCODE_COMMON_GET_CNTL_ADDITIONAL_ATTRIBUTES 121
@@ -1791,6 +1792,12 @@ struct be_cmd_enable_disable_vf {
u8 rsvd[3];
};
+struct be_cmd_req_intr_set {
+ struct be_cmd_req_hdr hdr;
+ u8 intr_enabled;
+ u8 rsvd[3];
+};
+
static inline bool check_privilege(struct be_adapter *adapter, u32 flags)
{
return flags & adapter->cmd_privileges ? true : false;
@@ -1938,3 +1945,4 @@ extern int be_cmd_set_profile_config(struct be_adapter *adapter, u32 bps,
extern int be_cmd_get_if_id(struct be_adapter *adapter,
struct be_vf_cfg *vf_cfg, int vf_num);
extern int be_cmd_enable_vf(struct be_adapter *adapter, u8 domain);
+extern int be_cmd_intr_set(struct be_adapter *adapter, bool intr_enable);
diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c
index dae7172..c71b180 100644
--- a/drivers/net/ethernet/emulex/benet/be_main.c
+++ b/drivers/net/ethernet/emulex/benet/be_main.c
@@ -153,17 +153,10 @@ static int be_queue_alloc(struct be_adapter *adapter, struct be_queue_info *q,
return 0;
}
-static void be_intr_set(struct be_adapter *adapter, bool enable)
+static void be_reg_intr_set(struct be_adapter *adapter, bool enable)
{
u32 reg, enabled;
- /* On lancer interrupts can't be controlled via this register */
- if (lancer_chip(adapter))
- return;
-
- if (adapter->eeh_error)
- return;
-
pci_read_config_dword(adapter->pdev, PCICFG_MEMBAR_CTRL_INT_CTRL_OFFSET,
®);
enabled = reg & MEMBAR_CTRL_INT_CTRL_HOSTINTR_MASK;
@@ -179,6 +172,22 @@ static void be_intr_set(struct be_adapter *adapter, bool enable)
PCICFG_MEMBAR_CTRL_INT_CTRL_OFFSET, reg);
}
+static void be_intr_set(struct be_adapter *adapter, bool enable)
+{
+ int status = 0;
+
+ /* On lancer interrupts can't be controlled via this register */
+ if (lancer_chip(adapter))
+ return;
+
+ if (adapter->eeh_error)
+ return;
+
+ status = be_cmd_intr_set(adapter, enable);
+ if (status)
+ be_reg_intr_set(adapter, enable);
+}
+
static void be_rxq_notify(struct be_adapter *adapter, u16 qid, u16 posted)
{
u32 val = 0;
--
1.5.6.1
^ permalink raw reply related
* Re: [PATCH] bnx2x: fix occasional statistics off-by-4GB error
From: Eilon Greenstein @ 2013-03-18 7:27 UTC (permalink / raw)
To: Eric Dumazet; +Cc: David Miller, dmitry, zenczykowski, maze, netdev, yuvalmin
In-Reply-To: <1363562251.29475.109.camel@edumazet-glaptop>
On Sun, 2013-03-17 at 16:17 -0700, Eric Dumazet wrote:
> On Sun, 2013-03-17 at 22:53 +0200, Eilon Greenstein wrote:
>
> > This is not such a trivial issue - the HW/FW is guaranteeing the atomic
> > read and this is why we can always use 32b variables.
> >
>
> I am glad you qualify the following code as 'trivial'
>
Eric - I did not mean that the solution is trivial, I meant that the
problem is trivial. Like the trivial statement that the code should not
contain any bugs :)
> All you really needed is to have normal host structures containing u64
> fields, and you only needed one single helper to convert from hw u32:u32
> to host u64.
>
> Because gcc handles u64 operations very well, even on 32bit hosts, and
> it knows about the carry flag.
I was not clear when I said size-extension: most of the HW counters are
46bits and we are trying to keep 64bits counters in the SW, so simply
copying the data from the HW is not enough.
^ permalink raw reply
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox