* [net-next-2.6 PATCH v5 1/5 RFC] TCPCT part 1a: add request_values parameter for sending SYNACK
From: William Allen Simpson @ 2009-11-09 16:12 UTC (permalink / raw)
To: Linux Kernel Network Developers
In-Reply-To: <4AF83E2D.1050401@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 1000 bytes --]
Add optional function parameters associated with sending SYNACK.
These parameters are not needed after sending SYNACK, and are not
used for retransmission. Avoids extending struct tcp_request_sock,
and avoids allocating kernel memory.
Also affects DCCP as it uses common struct request_sock_ops,
but this parameter is currently reserved for future use.
Signed-off-by: William.Allen.Simpson@gmail.com
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
---
include/net/request_sock.h | 8 +++++++-
include/net/tcp.h | 1 +
net/dccp/ipv4.c | 5 +++--
net/dccp/ipv6.c | 5 +++--
net/dccp/minisocks.c | 2 +-
net/ipv4/inet_connection_sock.c | 2 +-
net/ipv4/tcp_ipv4.c | 17 ++++++++++-------
net/ipv4/tcp_minisocks.c | 2 +-
net/ipv4/tcp_output.c | 1 +
net/ipv6/tcp_ipv6.c | 28 +++++++++++++---------------
10 files changed, 41 insertions(+), 30 deletions(-)
[-- Attachment #2: TCPCT+1a5.patch --]
[-- Type: text/plain, Size: 8638 bytes --]
diff --git a/include/net/request_sock.h b/include/net/request_sock.h
index c719084..c9b50eb 100644
--- a/include/net/request_sock.h
+++ b/include/net/request_sock.h
@@ -27,13 +27,19 @@ 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_sock *req,
+ struct request_values *rvp);
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 bf20f88..25bf3ba 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -443,6 +443,7 @@ extern int tcp_connect(struct sock *sk);
extern struct sk_buff * tcp_make_synack(struct sock *sk,
struct dst_entry *dst,
+ struct request_values *rvp,
struct request_sock *req);
extern int tcp_disconnect(struct sock *sk, int flags);
diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c
index 2423a08..efbcfdc 100644
--- a/net/dccp/ipv4.c
+++ b/net/dccp/ipv4.c
@@ -477,7 +477,8 @@ static struct dst_entry* dccp_v4_route_skb(struct net *net, struct sock *sk,
return &rt->u.dst;
}
-static int dccp_v4_send_response(struct sock *sk, struct request_sock *req)
+static int dccp_v4_send_response(struct sock *sk, struct request_sock *req,
+ struct request_values *rv_unused)
{
int err = -1;
struct sk_buff *skb;
@@ -626,7 +627,7 @@ int dccp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
dreq->dreq_iss = dccp_v4_init_sequence(skb);
dreq->dreq_service = service;
- if (dccp_v4_send_response(sk, req))
+ if (dccp_v4_send_response(sk, req, NULL))
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 50ea91a..6574215 100644
--- a/net/dccp/ipv6.c
+++ b/net/dccp/ipv6.c
@@ -241,7 +241,8 @@ out:
}
-static int dccp_v6_send_response(struct sock *sk, struct request_sock *req)
+static int dccp_v6_send_response(struct sock *sk, struct request_sock *req,
+ struct request_values *rv_unused)
{
struct inet6_request_sock *ireq6 = inet6_rsk(req);
struct ipv6_pinfo *np = inet6_sk(sk);
@@ -468,7 +469,7 @@ static int dccp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
dreq->dreq_iss = dccp_v6_init_sequence(skb);
dreq->dreq_service = service;
- if (dccp_v6_send_response(sk, req))
+ if (dccp_v6_send_response(sk, req, NULL))
goto drop_and_free;
inet6_csk_reqsk_queue_hash_add(sk, req, DCCP_TIMEOUT_INIT);
diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
index 5ca49ce..af226a0 100644
--- a/net/dccp/minisocks.c
+++ b/net/dccp/minisocks.c
@@ -184,7 +184,7 @@ struct sock *dccp_check_req(struct sock *sk, struct sk_buff *skb,
* counter (backoff, monitored by dccp_response_timer).
*/
req->retrans++;
- req->rsk_ops->rtx_syn_ack(sk, req);
+ req->rsk_ops->rtx_syn_ack(sk, req, NULL);
}
/* Network Duplicate, discard packet */
return NULL;
diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c
index 26fb50e..ad098d6 100644
--- a/net/ipv4/inet_connection_sock.c
+++ b/net/ipv4/inet_connection_sock.c
@@ -531,7 +531,7 @@ void inet_csk_reqsk_queue_prune(struct sock *parent,
&expire, &resend);
if (!expire &&
(!resend ||
- !req->rsk_ops->rtx_syn_ack(parent, req) ||
+ !req->rsk_ops->rtx_syn_ack(parent, req, NULL) ||
inet_rsk(req)->acked)) {
unsigned long timeo;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 657ae33..f83ac91 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -743,7 +743,8 @@ static void tcp_v4_reqsk_send_ack(struct sock *sk, struct sk_buff *skb,
* socket.
*/
static int __tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
- struct dst_entry *dst)
+ struct dst_entry *dst,
+ struct request_values *rvp)
{
const struct inet_request_sock *ireq = inet_rsk(req);
int err = -1;
@@ -753,7 +754,7 @@ static int __tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
if (!dst && (dst = inet_csk_route_req(sk, req)) == NULL)
return -1;
- skb = tcp_make_synack(sk, dst, req);
+ skb = tcp_make_synack(sk, dst, rvp, req);
if (skb) {
struct tcphdr *th = tcp_hdr(skb);
@@ -774,9 +775,10 @@ static int __tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
return err;
}
-static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req)
+static int tcp_v4_send_synack(struct sock *sk, struct request_sock *req,
+ struct request_values *rvp)
{
- return __tcp_v4_send_synack(sk, req, NULL);
+ return __tcp_v4_send_synack(sk, req, NULL, rvp);
}
/*
@@ -1211,13 +1213,13 @@ static struct timewait_sock_ops tcp_timewait_sock_ops = {
int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
- struct inet_request_sock *ireq;
struct tcp_options_received tmp_opt;
struct request_sock *req;
+ struct inet_request_sock *ireq;
+ struct dst_entry *dst = NULL;
__be32 saddr = ip_hdr(skb)->saddr;
__be32 daddr = ip_hdr(skb)->daddr;
__u32 isn = TCP_SKB_CB(skb)->when;
- struct dst_entry *dst = NULL;
#ifdef CONFIG_SYN_COOKIES
int want_cookie = 0;
#else
@@ -1337,7 +1339,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
}
tcp_rsk(req)->snt_isn = isn;
- if (__tcp_v4_send_synack(sk, req, dst) || want_cookie)
+ if (__tcp_v4_send_synack(sk, req, dst, NULL)
+ || want_cookie)
goto drop_and_free;
inet_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index a9d34e2..fb68bab 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -537,7 +537,7 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
* Enforce "SYN-ACK" according to figure 8, figure 6
* of RFC793, fixed by RFC1122.
*/
- req->rsk_ops->rtx_syn_ack(sk, req);
+ req->rsk_ops->rtx_syn_ack(sk, req, NULL);
return NULL;
}
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 616c686..784e6ee 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -2224,6 +2224,7 @@ int tcp_send_synack(struct sock *sk)
/* Prepare a SYN-ACK. */
struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
+ struct request_values *rvp,
struct request_sock *req)
{
struct inet_request_sock *ireq = inet_rsk(req);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 696a22f..6951827 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -461,7 +461,8 @@ out:
}
-static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req)
+static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req,
+ struct request_values *rvp)
{
struct inet6_request_sock *treq = inet6_rsk(req);
struct ipv6_pinfo *np = inet6_sk(sk);
@@ -499,7 +500,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req)
if ((err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0)
goto done;
- skb = tcp_make_synack(sk, dst, req);
+ skb = tcp_make_synack(sk, dst, rvp, req);
if (skb) {
struct tcphdr *th = tcp_hdr(skb);
@@ -1161,13 +1162,13 @@ 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_options_received tmp_opt;
+ struct request_sock *req;
struct inet6_request_sock *treq;
struct ipv6_pinfo *np = inet6_sk(sk);
- struct tcp_options_received tmp_opt;
struct tcp_sock *tp = tcp_sk(sk);
- struct request_sock *req = NULL;
- __u32 isn = TCP_SKB_CB(skb)->when;
struct dst_entry *dst = __sk_dst_get(sk);
+ __u32 isn = TCP_SKB_CB(skb)->when;
#ifdef CONFIG_SYN_COOKIES
int want_cookie = 0;
#else
@@ -1239,23 +1240,20 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
isn = tcp_v6_init_sequence(skb);
}
-
tcp_rsk(req)->snt_isn = isn;
security_inet_conn_request(sk, skb, req);
- if (tcp_v6_send_synack(sk, req))
- goto drop;
+ if (tcp_v6_send_synack(sk, req, NULL)
+ || want_cookie)
+ goto drop_and_free;
- if (!want_cookie) {
- inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
- return 0;
- }
+ inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT);
+ return 0;
+drop_and_free:
+ reqsk_free(req);
drop:
- if (req)
- reqsk_free(req);
-
return 0; /* don't send reset */
}
--
1.6.3.3
^ permalink raw reply related
* [net-next 1/4] bnx2x: GSO implies CSUM offload
From: Eilon Greenstein @ 2009-11-09 16:09 UTC (permalink / raw)
To: David Miller; +Cc: netdev
Making sure that whenever the FW/HW is configured for GSO, it is also configured
to CSUM offload
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
---
drivers/net/bnx2x_main.c | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/bnx2x_main.c b/drivers/net/bnx2x_main.c
index 61974b7..856ca38 100644
--- a/drivers/net/bnx2x_main.c
+++ b/drivers/net/bnx2x_main.c
@@ -11121,10 +11121,10 @@ static inline u32 bnx2x_xmit_type(struct bnx2x *bp, struct sk_buff *skb)
}
if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV4)
- rc |= XMIT_GSO_V4;
+ rc |= (XMIT_GSO_V4 | XMIT_CSUM_V4 | XMIT_CSUM_TCP);
else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)
- rc |= XMIT_GSO_V6;
+ rc |= (XMIT_GSO_V6 | XMIT_CSUM_TCP | XMIT_CSUM_V6);
return rc;
}
--
1.5.4.3
^ permalink raw reply related
* [net-next 2/4] bnx2x: Remove misleading error print
From: Eilon Greenstein @ 2009-11-09 16:09 UTC (permalink / raw)
To: David Miller; +Cc: netdev
Failing to allocate MSI-X vectors is not an error and should not be printed as
such
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
---
drivers/net/bnx2x_main.c | 5 -----
1 files changed, 0 insertions(+), 5 deletions(-)
diff --git a/drivers/net/bnx2x_main.c b/drivers/net/bnx2x_main.c
index 856ca38..a8ebd46 100644
--- a/drivers/net/bnx2x_main.c
+++ b/drivers/net/bnx2x_main.c
@@ -7478,11 +7478,6 @@ static int bnx2x_set_int_mode(struct bnx2x *bp)
rc = bnx2x_enable_msix(bp);
if (rc) {
/* failed to enable MSI-X */
- if (bp->multi_mode)
- BNX2X_ERR("Multi requested but failed to "
- "enable MSI-X (rx %d tx %d), "
- "set number of queues to 1\n",
- bp->num_rx_queues, bp->num_tx_queues);
bp->num_rx_queues = 1;
bp->num_tx_queues = 1;
}
--
1.5.4.3
^ permalink raw reply related
* [net-next 3/4] bnx2x: Change coalescing granularity to 4us
From: Eilon Greenstein @ 2009-11-09 16:09 UTC (permalink / raw)
To: David Miller; +Cc: netdev
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
---
drivers/net/bnx2x.h | 2 +-
drivers/net/bnx2x_main.c | 13 +++++++------
2 files changed, 8 insertions(+), 7 deletions(-)
diff --git a/drivers/net/bnx2x.h b/drivers/net/bnx2x.h
index c3b32f7..928942b 100644
--- a/drivers/net/bnx2x.h
+++ b/drivers/net/bnx2x.h
@@ -1191,7 +1191,7 @@ static inline u32 reg_poll(struct bnx2x *bp, u32 reg, u32 expected, int ms,
#define MAX_SP_DESC_CNT (SP_DESC_CNT - 1)
-#define BNX2X_BTR 3
+#define BNX2X_BTR 1
#define MAX_SPQ_PENDING 8
diff --git a/drivers/net/bnx2x_main.c b/drivers/net/bnx2x_main.c
index a8ebd46..ab552d3 100644
--- a/drivers/net/bnx2x_main.c
+++ b/drivers/net/bnx2x_main.c
@@ -4920,21 +4920,21 @@ static void bnx2x_update_coalesce(struct bnx2x *bp)
REG_WR8(bp, BAR_CSTRORM_INTMEM +
CSTORM_SB_HC_TIMEOUT_U_OFFSET(port, sb_id,
U_SB_ETH_RX_CQ_INDEX),
- bp->rx_ticks/12);
+ bp->rx_ticks/(4 * BNX2X_BTR));
REG_WR16(bp, BAR_CSTRORM_INTMEM +
CSTORM_SB_HC_DISABLE_U_OFFSET(port, sb_id,
U_SB_ETH_RX_CQ_INDEX),
- (bp->rx_ticks/12) ? 0 : 1);
+ (bp->rx_ticks/(4 * BNX2X_BTR)) ? 0 : 1);
/* HC_INDEX_C_ETH_TX_CQ_CONS */
REG_WR8(bp, BAR_CSTRORM_INTMEM +
CSTORM_SB_HC_TIMEOUT_C_OFFSET(port, sb_id,
C_SB_ETH_TX_CQ_INDEX),
- bp->tx_ticks/12);
+ bp->tx_ticks/(4 * BNX2X_BTR));
REG_WR16(bp, BAR_CSTRORM_INTMEM +
CSTORM_SB_HC_DISABLE_C_OFFSET(port, sb_id,
C_SB_ETH_TX_CQ_INDEX),
- (bp->tx_ticks/12) ? 0 : 1);
+ (bp->tx_ticks/(4 * BNX2X_BTR)) ? 0 : 1);
}
}
@@ -9008,8 +9008,9 @@ static int __devinit bnx2x_init_bp(struct bnx2x *bp)
bp->rx_csum = 1;
- bp->tx_ticks = 50;
- bp->rx_ticks = 25;
+ /* make sure that the numbers are in the right granularity */
+ bp->tx_ticks = (50 / (4 * BNX2X_BTR)) * (4 * BNX2X_BTR);
+ bp->rx_ticks = (25 / (4 * BNX2X_BTR)) * (4 * BNX2X_BTR);
timer_interval = (CHIP_REV_IS_SLOW(bp) ? 5*HZ : HZ);
bp->current_interval = (poll ? poll : timer_interval);
--
1.5.4.3
^ permalink raw reply related
* [net-next 4/4] bnx2x: version 1.52.1-4
From: Eilon Greenstein @ 2009-11-09 16:09 UTC (permalink / raw)
To: David Miller; +Cc: netdev
Signed-off-by: Eilon Greenstein <eilong@broadcom.com>
---
drivers/net/bnx2x_main.c | 4 ++--
1 files changed, 2 insertions(+), 2 deletions(-)
diff --git a/drivers/net/bnx2x_main.c b/drivers/net/bnx2x_main.c
index ab552d3..06ffa7d 100644
--- a/drivers/net/bnx2x_main.c
+++ b/drivers/net/bnx2x_main.c
@@ -56,8 +56,8 @@
#include "bnx2x_init_ops.h"
#include "bnx2x_dump.h"
-#define DRV_MODULE_VERSION "1.52.1-3"
-#define DRV_MODULE_RELDATE "2009/11/05"
+#define DRV_MODULE_VERSION "1.52.1-4"
+#define DRV_MODULE_RELDATE "2009/11/09"
#define BNX2X_BC_VER 0x040200
#include <linux/firmware.h>
--
1.5.4.3
^ permalink raw reply related
* [net-next-2.6 PATCH v5 2/5 RFC] TCPCT part1b: TCP_MSS_DEFAULT, TCP_MSS_DESIRED
From: William Allen Simpson @ 2009-11-09 16:24 UTC (permalink / raw)
To: Linux Kernel Network Developers
In-Reply-To: <4AF83E2D.1050401@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 556 bytes --]
Define two symbols needed in both kernel and user space.
Remove old (somewhat incorrect) variant that wasn't used in many cases.
Default applies to both RMSS and SMSS.
Replace numeric constants with defined symbols.
Signed-off-by: William.Allen.Simpson@gmail.com
---
include/linux/tcp.h | 6 ++++++
include/net/tcp.h | 3 ---
net/ipv4/tcp_input.c | 4 ++--
net/ipv4/tcp_ipv4.c | 6 +++---
net/ipv4/tcp_minisocks.c | 2 +-
net/ipv6/tcp_ipv6.c | 2 +-
6 files changed, 13 insertions(+), 10 deletions(-)
[-- Attachment #2: TCPCT+1b5.patch --]
[-- Type: text/plain, Size: 4017 bytes --]
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index eeecb85..32d7d77 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -81,6 +81,12 @@ enum {
TCP_DATA_OFFSET = __cpu_to_be32(0xF0000000)
};
+/*
+ * TCP general constants
+ */
+#define TCP_MSS_DEFAULT 536U /* IPv4 (RFC1122, RFC2581) */
+#define TCP_MSS_DESIRED 1220U /* IPv6 (tunneled), EDNS0 (RFC3226) */
+
/* TCP socket options */
#define TCP_NODELAY 1 /* Turn off Nagle's algorithm. */
#define TCP_MAXSEG 2 /* Limit MSS */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 25bf3ba..a413e9f 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -62,9 +62,6 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
/* Minimal accepted MSS. It is (60+60+8) - (20+20). */
#define TCP_MIN_MSS 88U
-/* Minimal RCV_MSS. */
-#define TCP_MIN_RCVMSS 536U
-
/* The least MTU to use for probing */
#define TCP_BASE_MSS 512
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index be0c5bf..cc306ac 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -140,7 +140,7 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
* "len" is invariant segment length, including TCP header.
*/
len += skb->data - skb_transport_header(skb);
- if (len >= TCP_MIN_RCVMSS + sizeof(struct tcphdr) ||
+ if (len >= TCP_MSS_DEFAULT + sizeof(struct tcphdr) ||
/* If PSH is not set, packet should be
* full sized, provided peer TCP is not badly broken.
* This observation (if it is correct 8)) allows
@@ -411,7 +411,7 @@ void tcp_initialize_rcv_mss(struct sock *sk)
unsigned int hint = min_t(unsigned int, tp->advmss, tp->mss_cache);
hint = min(hint, tp->rcv_wnd / 2);
- hint = min(hint, TCP_MIN_RCVMSS);
+ hint = min(hint, TCP_MSS_DEFAULT);
hint = max(hint, TCP_MIN_MSS);
inet_csk(sk)->icsk_ack.rcv_mss = hint;
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index f83ac91..0718fde 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -217,7 +217,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len)
if (inet->opt)
inet_csk(sk)->icsk_ext_hdr_len = inet->opt->optlen;
- tp->rx_opt.mss_clamp = 536;
+ tp->rx_opt.mss_clamp = TCP_MSS_DEFAULT;
/* Socket identity is still unknown (sport may be zero).
* However we set state to SYN-SENT and not releasing socket
@@ -1270,7 +1270,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
goto drop_and_free;
tcp_clear_options(&tmp_opt);
- tmp_opt.mss_clamp = 536;
+ tmp_opt.mss_clamp = TCP_MSS_DEFAULT;
tmp_opt.user_mss = tcp_sk(sk)->rx_opt.user_mss;
tcp_parse_options(skb, &tmp_opt, 0, dst);
@@ -1818,7 +1818,7 @@ static int tcp_v4_init_sock(struct sock *sk)
*/
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tp->snd_cwnd_clamp = ~0;
- tp->mss_cache = 536;
+ tp->mss_cache = TCP_MSS_DEFAULT;
tp->reordering = sysctl_tcp_reordering;
icsk->icsk_ca_ops = &tcp_init_congestion_ops;
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index fb68bab..7a42990 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -476,7 +476,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
if (newtp->af_specific->md5_lookup(sk, newsk))
newtp->tcp_header_len += TCPOLEN_MD5SIG_ALIGNED;
#endif
- if (skb->len >= TCP_MIN_RCVMSS+newtp->tcp_header_len)
+ if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len)
newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;
newtp->rx_opt.mss_clamp = req->mss;
TCP_ECN_openreq_child(newtp, req);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index 6951827..b528f75 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1849,7 +1849,7 @@ static int tcp_v6_init_sock(struct sock *sk)
*/
tp->snd_ssthresh = TCP_INFINITE_SSTHRESH;
tp->snd_cwnd_clamp = ~0;
- tp->mss_cache = 536;
+ tp->mss_cache = TCP_MSS_DEFAULT;
tp->reordering = sysctl_tcp_reordering;
--
1.6.3.3
^ permalink raw reply related
* [net-next-2.6 PATCH v5 3/5 RFC] TCPCT part1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS, functions
From: William Allen Simpson @ 2009-11-09 16:33 UTC (permalink / raw)
To: Linux Kernel Network Developers
In-Reply-To: <4AF83E2D.1050401@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 1358 bytes --]
Define sysctl (tcp_cookie_size) to turn on and off the cookie option
default globally, instead of a compiled configuration option.
Define per socket option (TCP_COOKIE_TRANSACTIONS) for setting constant
data values, retrieving variable cookie values, and other facilities.
Redefine two TCP header functions to accept TCP header pointer.
When subtracting, return signed int to allow error checking.
Move inline tcp_clear_options() unchanged from net/tcp.h to linux/tcp.h,
near its corresponding struct tcp_options_received (prior to changes).
This is a straightforward re-implementation of an earlier (year-old)
patch that no longer applies cleanly, with permission of the original
author (Adam Langley). The patch was previously reviewed:
http://thread.gmane.org/gmane.linux.network/102586
These functions will also be used in subsequent patches that implement
additional features.
Requires:
TCPCT part 1b: TCP_MSS_DEFAULT, TCP_MSS_DESIRED
Signed-off-by: William.Allen.Simpson@gmail.com
---
Documentation/networking/ip-sysctl.txt | 8 ++++++
include/linux/tcp.h | 44 +++++++++++++++++++++++++++++++-
include/net/tcp.h | 6 +---
net/ipv4/sysctl_net_ipv4.c | 8 ++++++
net/ipv4/tcp_output.c | 8 ++++++
5 files changed, 68 insertions(+), 6 deletions(-)
[-- Attachment #2: TCPCT+1c5.patch --]
[-- Type: text/plain, Size: 5589 bytes --]
diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt
index a0e134d..d47c000 100644
--- a/Documentation/networking/ip-sysctl.txt
+++ b/Documentation/networking/ip-sysctl.txt
@@ -164,6 +164,14 @@ tcp_congestion_control - STRING
additional choices may be available based on kernel configuration.
Default is set as part of kernel configuration.
+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.
+ Default: 0 (off).
+
tcp_dsack - BOOLEAN
Allows TCP to send "duplicate" SACKs.
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 32d7d77..57921c1 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -102,7 +102,9 @@ 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 */
+/* for TCP_INFO socket option */
#define TCPI_OPT_TIMESTAMPS 1
#define TCPI_OPT_SACK 2
#define TCPI_OPT_WSCALE 4
@@ -174,6 +176,30 @@ struct tcp_md5sig {
__u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN]; /* key (binary) */
};
+/* for TCP_COOKIE_TRANSACTIONS (TCPCT) socket option */
+#define TCP_COOKIE_MAX 16 /* 128-bits */
+#define TCP_COOKIE_MIN 8 /* 64-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];
+};
+
#ifdef __KERNEL__
#include <linux/skbuff.h>
@@ -197,6 +223,17 @@ static inline unsigned int tcp_optlen(const struct sk_buff *skb)
return (tcp_hdr(skb)->doff - 5) * 4;
}
+static inline unsigned int tcp_header_len_th(const struct tcphdr *th)
+{
+ return th->doff * 4;
+}
+
+/* When doff is bad, this could be negative. */
+static inline int tcp_option_len_th(const struct tcphdr *th)
+{
+ return (int)(th->doff * 4) - sizeof(*th);
+}
+
/* This defines a selective acknowledgement block. */
struct tcp_sack_block_wire {
__be32 start_seq;
@@ -227,6 +264,11 @@ struct tcp_options_received {
u16 mss_clamp; /* Maximal mss, negotiated at connection setup */
};
+static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
+{
+ rx_opt->tstamp_ok = rx_opt->sack_ok = rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
+}
+
/* This is the max number of SACKS that we'll generate and process. It's safe
* to increse this, although since:
* size = TCPOLEN_SACK_BASE_ALIGNED (4) + n * TCPOLEN_SACK_PERBLOCK (8)
@@ -435,6 +477,6 @@ static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk)
return (struct tcp_timewait_sock *)sk;
}
-#endif
+#endif /* __KERNEL__ */
#endif /* _LINUX_TCP_H */
diff --git a/include/net/tcp.h b/include/net/tcp.h
index a413e9f..f15924b 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -234,6 +234,7 @@ extern int sysctl_tcp_base_mss;
extern int sysctl_tcp_workaround_signed_windows;
extern int sysctl_tcp_slow_start_after_idle;
extern int sysctl_tcp_max_ssthresh;
+extern int sysctl_tcp_cookie_size;
extern atomic_t tcp_memory_allocated;
extern struct percpu_counter tcp_sockets_allocated;
@@ -340,11 +341,6 @@ static inline void tcp_dec_quickack_mode(struct sock *sk,
extern void tcp_enter_quickack_mode(struct sock *sk);
-static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
-{
- rx_opt->tstamp_ok = rx_opt->sack_ok = rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
-}
-
#define TCP_ECN_OK 1
#define TCP_ECN_QUEUE_CWR 2
#define TCP_ECN_DEMAND_CWR 4
diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c
index 2dcf04d..3422c54 100644
--- a/net/ipv4/sysctl_net_ipv4.c
+++ b/net/ipv4/sysctl_net_ipv4.c
@@ -714,6 +714,14 @@ static struct ctl_table ipv4_table[] = {
},
{
.ctl_name = CTL_UNNUMBERED,
+ .procname = "tcp_cookie_size",
+ .data = &sysctl_tcp_cookie_size,
+ .maxlen = sizeof(int),
+ .mode = 0644,
+ .proc_handler = proc_dointvec
+ },
+ {
+ .ctl_name = CTL_UNNUMBERED,
.procname = "udp_mem",
.data = &sysctl_udp_mem,
.maxlen = sizeof(sysctl_udp_mem),
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index 784e6ee..492ccdd 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -59,6 +59,14 @@ int sysctl_tcp_base_mss __read_mostly = 512;
/* By default, RFC2861 behavior. */
int sysctl_tcp_slow_start_after_idle __read_mostly = 1;
+#ifdef CONFIG_SYSCTL
+/* By default, let the user enable it. */
+int sysctl_tcp_cookie_size __read_mostly = 0;
+#else
+int sysctl_tcp_cookie_size __read_mostly = TCP_COOKIE_MAX;
+#endif
+
+
/* Account for new data that has been sent to the network. */
static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb)
{
--
1.6.3.3
^ permalink raw reply related
* Re: [PATCH 42/75] myri10ge: declare MODULE_FIRMWARE
From: Andrew Gallatin @ 2009-11-09 16:33 UTC (permalink / raw)
To: Ben Hutchings; +Cc: David Miller, Brice Goglin, netdev
In-Reply-To: <1257630884.15927.442.camel@localhost>
Ben Hutchings wrote:
> Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
Acked-by Andrew Gallatin <gallatin@myri.com>
Thanks,
Drew
^ permalink raw reply
* Re: [net-next-2.6 PATCH v5 2/5 RFC] TCPCT part1b: TCP_MSS_DEFAULT, TCP_MSS_DESIRED
From: Eric Dumazet @ 2009-11-09 16:39 UTC (permalink / raw)
To: William Allen Simpson; +Cc: Linux Kernel Network Developers
In-Reply-To: <4AF84248.1070103@gmail.com>
William Allen Simpson a écrit :
> Define two symbols needed in both kernel and user space.
>
> Remove old (somewhat incorrect) variant that wasn't used in many cases.
> Default applies to both RMSS and SMSS.
>
> Replace numeric constants with defined symbols.
>
> Signed-off-by: William.Allen.Simpson@gmail.com
> ---
> include/linux/tcp.h | 6 ++++++
> include/net/tcp.h | 3 ---
> net/ipv4/tcp_input.c | 4 ++--
> net/ipv4/tcp_ipv4.c | 6 +++---
> net/ipv4/tcp_minisocks.c | 2 +-
> net/ipv6/tcp_ipv6.c | 2 +-
> 6 files changed, 13 insertions(+), 10 deletions(-)
>
Acked-by: Eric Dumazet <eric.dumazet@gmail.com>
^ permalink raw reply
* [net-next-2.6 PATCH v5 4/5 RFC] TCPCT part1d: generate Responder Cookie
From: William Allen Simpson @ 2009-11-09 16:50 UTC (permalink / raw)
To: Linux Kernel Network Developers; +Cc: Eric Dumazet, Paul E. McKenney
In-Reply-To: <4AF83E2D.1050401@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 807 bytes --]
Define (missing) hash message size for SHA1.
Define hashing size constants specific to TCP cookies, and add new function.
Maintain global secret values for tcp_cookie_generator().
This is a significantly revised implementation of earlier (15-year-old)
Photuris [RFC-2522] code for the KA9Q cooperative multitasking platform.
Linux RCU technique appears to be well-suited to this application, though
neither of the circular queue items are freed.
These functions will also be used in subsequent patches that implement
additional features.
Signed-off-by: William.Allen.Simpson@gmail.com
---
include/linux/cryptohash.h | 1 +
include/net/tcp.h | 8 +++
net/ipv4/tcp.c | 146 ++++++++++++++++++++++++++++++++++++++++++++
3 files changed, 155 insertions(+), 0 deletions(-)
[-- Attachment #2: TCPCT+1d5.patch --]
[-- Type: text/plain, Size: 6995 bytes --]
diff --git a/include/linux/cryptohash.h b/include/linux/cryptohash.h
index c118b2a..ec78a4b 100644
--- a/include/linux/cryptohash.h
+++ b/include/linux/cryptohash.h
@@ -2,6 +2,7 @@
#define __CRYPTOHASH_H
#define SHA_DIGEST_WORDS 5
+#define SHA_MESSAGE_BYTES (512 /*bits*/ / 8)
#define SHA_WORKSPACE_WORDS 80
void sha_init(__u32 *buf);
diff --git a/include/net/tcp.h b/include/net/tcp.h
index f15924b..702fd0a 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -1474,6 +1474,14 @@ 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);
+
extern void tcp_v4_init(void);
extern void tcp_init(void);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index e0cfa63..3ae01bf 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -264,6 +264,7 @@
#include <linux/cache.h>
#include <linux/err.h>
#include <linux/crypto.h>
+#include <linux/time.h>
#include <net/icmp.h>
#include <net/tcp.h>
@@ -2842,6 +2843,141 @@ 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 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 */
+ spin_unlock_bh(&tcp_secret_locker);
+ memcpy(bakery,
+ &tcp_secret_generating->secrets[0],
+ sizeof(tcp_secret_generating->secrets));
+ } else {
+ u32 secrets[COOKIE_WORKSPACE_WORDS];
+
+ /* still needs refreshing */
+ get_random_bytes(secrets, sizeof(secrets));
+
+ /* 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);
+ secrets[COOKIE_DIGEST_WORDS+0] ^=
+ (u32)tv.tv_nsec;
+
+ tcp_secret_secondary->expires = jiffy
+ + TCP_SECRET_1MSL
+ + (0x0f & tcp_cookie_work(secrets, 0));
+ } else {
+ tcp_secret_secondary->expires = jiffy
+ + TCP_SECRET_LIFE
+ + (0xff & tcp_cookie_work(secrets, 1));
+ tcp_secret_primary->expires = jiffy
+ + TCP_SECRET_2MSL
+ + (0x1f & tcp_cookie_work(secrets, 2));
+ }
+ memcpy(&tcp_secret_secondary->secrets[0],
+ &secrets[0],
+ sizeof(secrets));
+
+ rcu_assign_pointer(tcp_secret_generating,
+ tcp_secret_secondary);
+ rcu_assign_pointer(tcp_secret_retiring,
+ tcp_secret_primary);
+ spin_unlock_bh(&tcp_secret_locker);
+ /* Neither call_rcu() or synchronize_rcu() are needed.
+ * Retiring data is not freed. It is replaced after
+ * further (locked) pointer updates, and a quiet time
+ * (minimum 1MSL, maximum LIFE - 2MSL).
+ */
+ memcpy(bakery,
+ &secrets[0],
+ sizeof(secrets));
+ }
+ } else {
+ rcu_read_lock_bh();
+ memcpy(bakery,
+ &rcu_dereference(tcp_secret_generating)->secrets[0],
+ sizeof(tcp_secret_generating->secrets));
+ rcu_read_unlock_bh();
+ }
+ return 0;
+}
+EXPORT_SYMBOL(tcp_cookie_generator);
+
void tcp_done(struct sock *sk)
{
if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV)
@@ -2876,6 +3012,7 @@ void __init tcp_init(void)
struct sk_buff *skb = NULL;
unsigned long nr_pages, limit;
int order, i, max_share;
+ unsigned long jiffy = jiffies;
BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb));
@@ -2969,6 +3106,15 @@ void __init tcp_init(void)
tcp_hashinfo.ehash_mask + 1, tcp_hashinfo.bhash_size);
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;
}
EXPORT_SYMBOL(tcp_close);
--
1.6.3.3
^ permalink raw reply related
* Re: [RFC] netlink: add socket destruction notification
From: Johannes Berg @ 2009-11-09 16:51 UTC (permalink / raw)
To: Patrick McHardy; +Cc: netdev, Jouni Malinen, Thomas Graf
In-Reply-To: <4AF816D3.7000304@trash.net>
[-- Attachment #1: Type: text/plain, Size: 722 bytes --]
On Mon, 2009-11-09 at 14:19 +0100, Patrick McHardy wrote:
> > Ok, cool, thanks. Do you want me to send the change removing the
> > multicast check, or would you want to do that since you audited all the
> > netlink callers?
>
> Please go ahead.
Will do.
> > Also, it's called URELEASE for unicast -- should we rename it to just
> > RELEASE?
>
> I think URELEASE is still fine since won't necessarily get called
> for sockets that are used for pure multicast reception when using
> setsockopt to bind to groups.
Oh? So on which sockets can I rely on it being used? After sending at
least one unicast message into the kernel? This seems to depend on pid
being assigned -- when is that?
johannes
[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 801 bytes --]
^ permalink raw reply
* Re: [RFC] netlink: add socket destruction notification
From: Patrick McHardy @ 2009-11-09 16:57 UTC (permalink / raw)
To: Johannes Berg; +Cc: netdev, Jouni Malinen, Thomas Graf
In-Reply-To: <1257785502.29454.178.camel@johannes.local>
Johannes Berg wrote:
> On Mon, 2009-11-09 at 14:19 +0100, Patrick McHardy wrote:
>
>>> Ok, cool, thanks. Do you want me to send the change removing the
>>> multicast check, or would you want to do that since you audited all the
>>> netlink callers?
>> Please go ahead.
>
> Will do.
>
>>> Also, it's called URELEASE for unicast -- should we rename it to just
>>> RELEASE?
>> I think URELEASE is still fine since won't necessarily get called
>> for sockets that are used for pure multicast reception when using
>> setsockopt to bind to groups.
>
> Oh? So on which sockets can I rely on it being used? After sending at
> least one unicast message into the kernel? This seems to depend on pid
> being assigned -- when is that?
All unicast sockets that have either manually or automatically
bound. Automatic binding happens when sending the first message
or when calling connect().
Before that, your code can't know of the sockets existance, so
I guess this should be fine.
^ permalink raw reply
* [net-next-2.6 PATCH v5 5/5 RFC] TCPCT part1e: initial SYN exchange with SYNACK data
From: William Allen Simpson @ 2009-11-09 17:05 UTC (permalink / raw)
To: Linux Kernel Network Developers
Cc: Eric Dumazet, Ilpo Järvinen, Joe Perches
In-Reply-To: <4AF83E2D.1050401@gmail.com>
[-- Attachment #1: Type: text/plain, Size: 2346 bytes --]
This is a significantly revised implementation of an earlier (year-old)
patch that no longer applies cleanly, with permission of the original
author (Adam Langley). That patch was previously reviewed:
http://thread.gmane.org/gmane.linux.network/102586
The principle difference is using a TCP option to carry the cookie nonce,
instead of a user configured offset in the data. This is more flexible and
less subject to user configuration error. Such a cookie option has been
suggested for many years, and is also useful without SYN data, allowing
several related concepts to use the same extension option.
"Re: SYN floods (was: does history repeat itself?)", September 9, 1996.
http://www.merit.net/mail.archives/nanog/1996-09/msg00235.html
"Re: what a new TCP header might look like", May 12, 1998.
ftp://ftp.isi.edu/end2end/end2end-interest-1998.mail
Data structures are carefully composed to require minimal additions.
For example, the struct tcp_options_received cookie_plus variable fits
between existing 16-bit and 8-bit variables, requiring no additional
space (taking alignment into consideration). There are no additions to
tcp_request_sock, and only 1 pointer in tcp_sock.
Allocations have been rearranged to avoid requiring GFP_ATOMIC, with
only one unavoidable exception in tcp_create_openreq_child(), where the
tcp_sock itself is created GFP_ATOMIC.
These functions will also be used in subsequent patches that implement
additional features.
Requires:
TCPCT part 1a: add request_values parameter for sending SYNACK
TCPCT part 1b: TCP_MSS_DEFAULT, TCP_MSS_DESIRED
TCPCT part 1c: sysctl_tcp_cookie_size, socket option TCP_COOKIE_TRANSACTIONS, functions
TCPCT part 1d: generate Responder Cookie
Signed-off-by: William.Allen.Simpson@gmail.com
---
include/linux/tcp.h | 29 ++++-
include/net/tcp.h | 72 +++++++++++++
net/ipv4/syncookies.c | 5 +-
net/ipv4/tcp.c | 127 ++++++++++++++++++++++-
net/ipv4/tcp_input.c | 86 +++++++++++++--
net/ipv4/tcp_ipv4.c | 69 ++++++++++++-
net/ipv4/tcp_minisocks.c | 59 ++++++++---
net/ipv4/tcp_output.c | 255 +++++++++++++++++++++++++++++++++++++++++-----
net/ipv6/syncookies.c | 5 +-
net/ipv6/tcp_ipv6.c | 65 +++++++++++-
10 files changed, 701 insertions(+), 71 deletions(-)
[-- Attachment #2: TCPCT+1e5.patch --]
[-- Type: text/plain, Size: 41725 bytes --]
diff --git a/include/linux/tcp.h b/include/linux/tcp.h
index 57921c1..80ebb52 100644
--- a/include/linux/tcp.h
+++ b/include/linux/tcp.h
@@ -258,31 +258,38 @@ 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 */
-/* SACKs data */
+ 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 user_mss; /* mss requested by user in ioctl */
u16 mss_clamp; /* Maximal mss, negotiated at connection setup */
};
static inline void tcp_clear_options(struct tcp_options_received *rx_opt)
{
- rx_opt->tstamp_ok = rx_opt->sack_ok = rx_opt->wscale_ok = rx_opt->snd_wscale = 0;
+ 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
- * to increse this, although since:
+ * to increase this, although since:
* size = TCPOLEN_SACK_BASE_ALIGNED (4) + n * TCPOLEN_SACK_PERBLOCK (8)
* only four options will fit in a standard TCP header */
#define TCP_NUM_SACKS 4
+struct tcp_cookie_values;
+struct tcp_request_sock_ops;
+
struct tcp_request_sock {
struct inet_request_sock req;
#ifdef CONFIG_TCP_MD5SIG
/* Only used by TCP MD5 Signature so far. */
const struct tcp_request_sock_ops *af_specific;
#endif
- u32 rcv_isn;
- u32 snt_isn;
+ u32 rcv_isn;
+ u32 snt_isn;
};
static inline struct tcp_request_sock *tcp_rsk(const struct request_sock *req)
@@ -452,6 +459,12 @@ struct tcp_sock {
/* TCP MD5 Signature Option information */
struct tcp_md5sig_info *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;
};
static inline struct tcp_sock *tcp_sk(const struct sock *sk)
@@ -470,6 +483,10 @@ struct tcp_timewait_sock {
u16 tw_md5_keylen;
u8 tw_md5_key[TCP_MD5SIG_MAXKEYLEN];
#endif
+ /* Few sockets in timewait have cookies; in that case, then this
+ * object holds a reference to it (tw_cookie_values->kref)
+ */
+ struct tcp_cookie_values *tw_cookie_values;
};
static inline struct tcp_timewait_sock *tcp_twsk(const struct sock *sk)
diff --git a/include/net/tcp.h b/include/net/tcp.h
index 702fd0a..d992c35 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -30,6 +30,7 @@
#include <linux/dmaengine.h>
#include <linux/crypto.h>
#include <linux/cryptohash.h>
+#include <linux/kref.h>
#include <net/inet_connection_sock.h>
#include <net/inet_timewait_sock.h>
@@ -164,6 +165,7 @@ 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) */
/*
* TCP option lengths
@@ -174,6 +176,10 @@ extern void tcp_time_wait(struct sock *sk, int state, int timeo);
#define TCPOLEN_SACK_PERM 2
#define TCPOLEN_TIMESTAMP 10
#define TCPOLEN_MD5SIG 18
+#define TCPOLEN_COOKIE_BASE 2 /* Cookie-less header extension */
+#define TCPOLEN_COOKIE_PAIR 3 /* Cookie pair header extension */
+#define TCPOLEN_COOKIE_MAX (TCPOLEN_COOKIE_BASE+TCP_COOKIE_MAX)
+#define TCPOLEN_COOKIE_MIN (TCPOLEN_COOKIE_BASE+TCP_COOKIE_MIN)
/* But this is what stacks really send out. */
#define TCPOLEN_TSTAMP_ALIGNED 12
@@ -401,6 +407,7 @@ extern int tcp_recvmsg(struct kiocb *iocb, struct sock *sk,
extern void tcp_parse_options(struct sk_buff *skb,
struct tcp_options_received *opt_rx,
+ u8 **cryptic,
int estab,
struct dst_entry *dst);
@@ -1482,6 +1489,71 @@ struct tcp_request_sock_ops {
extern int tcp_cookie_generator(u32 *bakery);
+/**
+ * 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;
+ 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;
+}
+
+/* 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.
+ */
+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/net/ipv4/syncookies.c b/net/ipv4/syncookies.c
index 3146cc4..3503762 100644
--- a/net/ipv4/syncookies.c
+++ b/net/ipv4/syncookies.c
@@ -253,6 +253,8 @@ EXPORT_SYMBOL(cookie_check_timestamp);
struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
struct ip_options *opt)
{
+ struct tcp_options_received tcp_opt;
+ u8 *cryptic_value;
struct inet_request_sock *ireq;
struct tcp_request_sock *treq;
struct tcp_sock *tp = tcp_sk(sk);
@@ -263,7 +265,6 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb,
int mss;
struct rtable *rt;
__u8 rcv_wscale;
- struct tcp_options_received tcp_opt;
if (!sysctl_tcp_syncookies || !th->ack)
goto out;
@@ -341,7 +342,7 @@ 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, 0, &rt->u.dst);
+ tcp_parse_options(skb, &tcp_opt, &cryptic_value, 0, &rt->u.dst);
if (tcp_opt.saw_tstamp)
cookie_check_timestamp(&tcp_opt);
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 3ae01bf..b650e67 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -2079,8 +2079,8 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
int val;
int err = 0;
- /* This is a string value all the others are int's */
- if (optname == TCP_CONGESTION) {
+ /* These are data/string values, all the others are ints */
+ if (TCP_CONGESTION == optname) {
char name[TCP_CA_NAME_MAX];
if (optlen < 1)
@@ -2096,6 +2096,88 @@ static int do_tcp_setsockopt(struct sock *sk, int level,
err = tcp_set_congestion_control(sk, name);
release_sock(sk);
return err;
+ } else if (TCP_COOKIE_TRANSACTIONS == optname) {
+ 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 (sizeof(ctd.tcpct_value) < ctd.tcpct_used
+ || TCP_MSS_DESIRED < ctd.tcpct_s_data_desired)
+ return -EINVAL;
+
+ if (ctd.tcpct_cookie_desired == 0) {
+ /* default to global value */
+ } else if ((0x1 & ctd.tcpct_cookie_desired)
+ || TCP_COOKIE_MAX < ctd.tcpct_cookie_desired
+ || TCP_COOKIE_MIN > ctd.tcpct_cookie_desired) {
+ 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;
+ }
+ 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);
+ kref_init(&cvp->kref);
+ tp->cookie_values = cvp;
+ } 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 */
+ }
+ }
+ release_sock(sk);
+ return err;
}
if (optlen < sizeof(int))
@@ -2421,6 +2503,47 @@ static int do_tcp_getsockopt(struct sock *sk, int level,
if (copy_to_user(optval, icsk->icsk_ca_ops->name, len))
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;
+
+ /* Cookie(s) saved, return as nonce */
+ if (sizeof(ctd.tcpct_value) < cvp->cookie_pair_size) {
+ /* impossible? */
+ return -EINVAL;
+ }
+ 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;
+ }
default:
return -ENOPROTOOPT;
}
diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
index cc306ac..8fb50f0 100644
--- a/net/ipv4/tcp_input.c
+++ b/net/ipv4/tcp_input.c
@@ -3698,11 +3698,11 @@ old_ack:
* the fast version below fails.
*/
void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
- int estab, struct dst_entry *dst)
+ u8 **cryptic, int estab, struct dst_entry *dst)
{
unsigned char *ptr;
struct tcphdr *th = tcp_hdr(skb);
- int length = (th->doff * 4) - sizeof(struct tcphdr);
+ int length = tcp_option_len_th(th);
ptr = (unsigned char *)(th + 1);
opt_rx->saw_tstamp = 0;
@@ -3785,6 +3785,19 @@ void tcp_parse_options(struct sk_buff *skb, struct tcp_options_received *opt_rx,
*/
break;
#endif
+ case TCPOPT_COOKIE:
+ /* This option carries 3 different lengths.
+ */
+ if (TCPOLEN_COOKIE_MAX >= opsize
+ && TCPOLEN_COOKIE_MIN <= opsize) {
+ opt_rx->cookie_plus = opsize;
+ *cryptic = ptr;
+ } else if (TCPOLEN_COOKIE_PAIR == opsize) {
+ /* not yet implemented */
+ } else if (TCPOLEN_COOKIE_BASE == opsize) {
+ /* not yet implemented */
+ }
+ break;
}
ptr += opsize-2;
@@ -3813,17 +3826,21 @@ static int tcp_parse_aligned_timestamp(struct tcp_sock *tp, struct tcphdr *th)
* If it is wrong it falls back on tcp_parse_options().
*/
static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th,
- struct tcp_sock *tp)
+ struct tcp_sock *tp, u8 **cryptic)
{
- if (th->doff == sizeof(struct tcphdr) >> 2) {
+ /* In the spirit of fast parsing, compare doff directly to shifted
+ * constant values. Because equality is used, short doff can be
+ * ignored here, and checked later.
+ */
+ if (th->doff == (sizeof(*th) >> 2)) {
tp->rx_opt.saw_tstamp = 0;
return 0;
} else if (tp->rx_opt.tstamp_ok &&
- th->doff == (sizeof(struct tcphdr)>>2)+(TCPOLEN_TSTAMP_ALIGNED>>2)) {
+ th->doff == ((sizeof(*th)+TCPOLEN_TSTAMP_ALIGNED)>>2)) {
if (tcp_parse_aligned_timestamp(tp, th))
return 1;
}
- tcp_parse_options(skb, &tp->rx_opt, 1, NULL);
+ tcp_parse_options(skb, &tp->rx_opt, cryptic, 1, NULL);
return 1;
}
@@ -3833,7 +3850,7 @@ static int tcp_fast_parse_options(struct sk_buff *skb, struct tcphdr *th,
*/
u8 *tcp_parse_md5sig_option(struct tcphdr *th)
{
- int length = (th->doff << 2) - sizeof (*th);
+ int length = tcp_option_len_th(th);
u8 *ptr = (u8*)(th + 1);
/* If the TCP option is too short, we can short cut */
@@ -5077,10 +5094,11 @@ out:
static int tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
struct tcphdr *th, int syn_inerr)
{
+ u8 *cv;
struct tcp_sock *tp = tcp_sk(sk);
/* RFC1323: H1. Apply PAWS check first. */
- if (tcp_fast_parse_options(skb, th, tp) && tp->rx_opt.saw_tstamp &&
+ if (tcp_fast_parse_options(skb, th, tp, &cv) && tp->rx_opt.saw_tstamp &&
tcp_paws_discard(sk, skb)) {
if (!th->rst) {
NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_PAWSESTABREJECTED);
@@ -5368,12 +5386,15 @@ discard:
static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
struct tcphdr *th, unsigned len)
{
- struct tcp_sock *tp = tcp_sk(sk);
+ u8 *cryptic_value;
struct inet_connection_sock *icsk = inet_csk(sk);
- int saved_clamp = tp->rx_opt.mss_clamp;
+ struct tcp_sock *tp = tcp_sk(sk);
struct dst_entry *dst = __sk_dst_get(sk);
+ struct tcp_cookie_values *cvp = tp->cookie_values;
+ int saved_clamp = tp->rx_opt.mss_clamp;
+ int queued = 0;
- tcp_parse_options(skb, &tp->rx_opt, 0, dst);
+ tcp_parse_options(skb, &tp->rx_opt, &cryptic_value, 0, dst);
if (th->ack) {
/* rfc793:
@@ -5470,6 +5491,44 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
* Change state from SYN-SENT only after copied_seq
* 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],
+ cryptic_value, cookie_size);
+ cvp->cookie_pair_size = cookie_pair_size;
+ }
+
+ if (tcp_header_len_th(th) < skb->len) {
+ /* Queue incoming transaction data. */
+ __skb_pull(skb, tcp_header_len_th(th));
+ __skb_queue_tail(&sk->sk_receive_queue, skb);
+ skb_set_owner_r(skb, sk);
+ sk->sk_data_ready(sk, 0);
+ cvp->s_data_in = 1; /* true */
+ queued = 1; /* should be amount? */
+ tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
+ tp->rcv_wup = TCP_SKB_CB(skb)->end_seq;
+ tp->copied_seq = TCP_SKB_CB(skb)->seq + 1;
+ }
+ }
+
smp_mb();
tcp_set_state(sk, TCP_ESTABLISHED);
@@ -5521,11 +5580,14 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb,
TCP_DELACK_MAX, TCP_RTO_MAX);
discard:
- __kfree_skb(skb);
+ if (queued == 0)
+ __kfree_skb(skb);
return 0;
} else {
tcp_send_ack(sk);
}
+ if (queued > 0)
+ return 0; /* amount queued? */
return -1;
}
diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index 0718fde..5992d0b 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -1213,9 +1213,12 @@ static struct timewait_sock_ops tcp_timewait_sock_ops = {
int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
{
+ struct tcp_extend_values tmp_ext;
struct tcp_options_received tmp_opt;
+ u8 *cryptic_value;
struct request_sock *req;
struct inet_request_sock *ireq;
+ struct tcp_sock *tp = tcp_sk(sk);
struct dst_entry *dst = NULL;
__be32 saddr = ip_hdr(skb)->saddr;
__be32 daddr = ip_hdr(skb)->daddr;
@@ -1271,15 +1274,50 @@ 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 = tcp_sk(sk)->rx_opt.user_mss;
+ tmp_opt.user_mss = tp->rx_opt.user_mss;
+ tcp_parse_options(skb, &tmp_opt, &cryptic_value, 0, dst);
+
+ 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++ ^= daddr;
+ *mess++ ^= saddr;
+
+ /* plus variable length Initiator Cookie */
+ c = (u8 *)mess;
+ while (l-- > 0) {
+ *c++ ^= *cryptic_value++;
+ }
- tcp_parse_options(skb, &tmp_opt, 0, dst);
+#ifdef CONFIG_SYN_COOKIES
+ want_cookie = 0; /* not our kind of cookie */
+#endif
+ 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;
if (want_cookie && !tmp_opt.saw_tstamp)
tcp_clear_options(&tmp_opt);
tmp_opt.tstamp_ok = tmp_opt.saw_tstamp;
-
tcp_openreq_init(req, &tmp_opt, skb);
if (security_inet_conn_request(sk, skb, req))
@@ -1339,7 +1377,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb)
}
tcp_rsk(req)->snt_isn = isn;
- if (__tcp_v4_send_synack(sk, req, dst, NULL)
+ if (__tcp_v4_send_synack(sk, req, dst,
+ (struct request_values *)&tmp_ext)
|| want_cookie)
goto drop_and_free;
@@ -1834,6 +1873,19 @@ static int tcp_v4_init_sock(struct sock *sk)
tp->af_specific = &tcp_sock_ipv4_specific;
#endif
+ /* TCP Cookie Transactions */
+ if (sysctl_tcp_cookie_size > 0) {
+ /* Default, cookies without s_data. */
+ 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, extend_timestamp,
+ * s_data_constant, s_data_in, s_data_out
+ */
sk->sk_sndbuf = sysctl_tcp_wmem[1];
sk->sk_rcvbuf = sysctl_tcp_rmem[1];
@@ -1887,6 +1939,15 @@ void tcp_v4_destroy_sock(struct sock *sk)
sk->sk_sndmsg_page = NULL;
}
+ /*
+ * If cookie or s_data exists, remove it.
+ */
+ if (tp->cookie_values != NULL) {
+ kref_put(&tp->cookie_values->kref,
+ tcp_cookie_values_release);
+ tp->cookie_values = NULL;
+ }
+
percpu_counter_dec(&tcp_sockets_allocated);
}
diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
index 7a42990..db46797 100644
--- a/net/ipv4/tcp_minisocks.c
+++ b/net/ipv4/tcp_minisocks.c
@@ -96,13 +96,14 @@ enum tcp_tw_status
tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
const struct tcphdr *th)
{
- struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
struct tcp_options_received tmp_opt;
+ u8 *cryptic_value;
+ struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
int paws_reject = 0;
if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
tmp_opt.tstamp_ok = 1;
- tcp_parse_options(skb, &tmp_opt, 1, NULL);
+ tcp_parse_options(skb, &tmp_opt, &cryptic_value, 1, NULL);
if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = tcptw->tw_ts_recent;
@@ -389,14 +390,42 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req,
const struct inet_request_sock *ireq = inet_rsk(req);
struct tcp_request_sock *treq = tcp_rsk(req);
struct inet_connection_sock *newicsk = inet_csk(newsk);
- struct tcp_sock *newtp;
+ 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 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 = tcp_sk(newsk);
newtp->pred_flags = 0;
- newtp->rcv_wup = newtp->copied_seq = newtp->rcv_nxt = treq->rcv_isn + 1;
- newtp->snd_sml = newtp->snd_una = newtp->snd_nxt = treq->snt_isn + 1;
- newtp->snd_up = treq->snt_isn + 1;
+
+ newtp->rcv_wup = newtp->copied_seq =
+ 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);
tcp_prequeue_init(newtp);
@@ -429,8 +458,8 @@ 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 = treq->snt_isn + 1;
- newtp->pushed_seq = newtp->write_seq;
+ newtp->write_seq = newtp->pushed_seq =
+ treq->snt_isn + 1 + tcp_s_data_size(oldtp);
newtp->rx_opt.saw_tstamp = 0;
@@ -495,15 +524,16 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
struct request_sock *req,
struct request_sock **prev)
{
+ struct tcp_options_received tmp_opt;
+ u8 *cryptic_value;
+ 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);
int paws_reject = 0;
- struct tcp_options_received tmp_opt;
- struct sock *child;
- if ((th->doff > (sizeof(struct tcphdr)>>2)) && (req->ts_recent)) {
+ if ((th->doff > (sizeof(*th) >> 2)) && (req->ts_recent)) {
tmp_opt.tstamp_ok = 1;
- tcp_parse_options(skb, &tmp_opt, 1, NULL);
+ tcp_parse_options(skb, &tmp_opt, &cryptic_value, 1, NULL);
if (tmp_opt.saw_tstamp) {
tmp_opt.ts_recent = req->ts_recent;
@@ -596,7 +626,8 @@ struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb,
* Invalid ACK: reset will be sent by listening socket
*/
if ((flg & TCP_FLAG_ACK) &&
- (TCP_SKB_CB(skb)->ack_seq != tcp_rsk(req)->snt_isn + 1))
+ (TCP_SKB_CB(skb)->ack_seq != tcp_rsk(req)->snt_isn + 1 +
+ tcp_s_data_size(tcp_sk(sk))))
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 492ccdd..08dc649 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -370,15 +370,45 @@ static inline int 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)
struct tcp_out_options {
u8 options; /* bit field of OPTION_* */
u8 ws; /* window scale, 0 to disable */
+ u8 hash_size; /* bytes in hash */
u8 num_sack_blocks; /* number of SACK blocks to include */
u16 mss; /* 0 to disable */
__u32 tsval, tsecr; /* need to include OPTION_TS */
+ __u8 *hash_location; /* temporary pointer, overloaded */
};
+/* The sysctl int routines are generic, so check consistency here.
+ */
+static u8 tcp_cookie_size_check(u8 desired)
+{
+ if (desired > 0) {
+ /* previously specified */
+ return desired;
+ }
+ if (sysctl_tcp_cookie_size <= 0) {
+ /* no default specified */
+ return 0;
+ }
+ if (sysctl_tcp_cookie_size < TCP_COOKIE_MIN) {
+ /* value too small, increase to minimum */
+ return TCP_COOKIE_MIN;
+ }
+ if (sysctl_tcp_cookie_size > TCP_COOKIE_MAX) {
+ /* value too large, decrease to maximum */
+ return TCP_COOKIE_MAX;
+ }
+ if (0x1 & sysctl_tcp_cookie_size) {
+ /* 8-bit multiple, illegal, fix it */
+ return (u8)(sysctl_tcp_cookie_size + 0x1);
+ }
+ return (u8)sysctl_tcp_cookie_size;
+}
+
/* Write previously computed TCP options to the packet.
*
* Beware: Something in the Internet is very sensitive to the ordering of
@@ -393,17 +423,34 @@ struct tcp_out_options {
* (but it may well be that other scenarios fail similarly).
*/
static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
- const struct tcp_out_options *opts,
- __u8 **md5_hash) {
- if (unlikely(OPTION_MD5 & opts->options)) {
- *ptr++ = htonl((TCPOPT_NOP << 24) |
- (TCPOPT_NOP << 16) |
- (TCPOPT_MD5SIG << 8) |
- TCPOLEN_MD5SIG);
- *md5_hash = (__u8 *)ptr;
+ struct tcp_out_options *opts)
+{
+ u8 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;
+ /* overload cookie hash location */
+ opts->hash_location = (__u8 *)ptr;
ptr += 4;
- } else {
- *md5_hash = NULL;
}
if (unlikely(opts->mss)) {
@@ -412,12 +459,13 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
opts->mss);
}
- if (likely(OPTION_TS & opts->options)) {
- if (unlikely(OPTION_SACK_ADVERTISE & opts->options)) {
+ if (likely(OPTION_TS & options)) {
+ if (unlikely(OPTION_SACK_ADVERTISE & options)) {
*ptr++ = htonl((TCPOPT_SACK_PERM << 24) |
(TCPOLEN_SACK_PERM << 16) |
(TCPOPT_TIMESTAMP << 8) |
TCPOLEN_TIMESTAMP);
+ options &= ~OPTION_SACK_ADVERTISE;
} else {
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
@@ -428,15 +476,52 @@ static void tcp_options_write(__be32 *ptr, struct tcp_sock *tp,
*ptr++ = htonl(opts->tsecr);
}
- if (unlikely(OPTION_SACK_ADVERTISE & opts->options &&
- !(OPTION_TS & opts->options))) {
+ /* 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;
+
+ if (unlikely(0x1 & cookie_size)) {
+ /* 8-bit multiple, illegal, ignore */
+ cookie_size = 0;
+ } else if (likely(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 >> 2);
+ }
+ }
+
+ if (unlikely(OPTION_SACK_ADVERTISE & options)) {
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_NOP << 16) |
(TCPOPT_SACK_PERM << 8) |
TCPOLEN_SACK_PERM);
}
- if (unlikely(OPTION_WSCALE & opts->options)) {
+ if (unlikely(OPTION_WSCALE & options)) {
*ptr++ = htonl((TCPOPT_NOP << 24) |
(TCPOPT_WINDOW << 16) |
(TCPOLEN_WINDOW << 8) |
@@ -471,8 +556,12 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
struct tcp_out_options *opts,
struct tcp_md5sig_key **md5) {
struct tcp_sock *tp = tcp_sk(sk);
- unsigned size = 0;
+ struct tcp_cookie_values *cvp = tp->cookie_values;
struct dst_entry *dst = __sk_dst_get(sk);
+ unsigned size = 0;
+ u8 cookie_size = (!tp->rx_opt.cookie_out_never && cvp != NULL)
+ ? tcp_cookie_size_check(cvp->cookie_desired)
+ : 0;
#ifdef CONFIG_TCP_MD5SIG
*md5 = tp->af_specific->md5_lookup(sk, sk);
@@ -517,6 +606,53 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb,
size += TCPOLEN_SACKPERM_ALIGNED;
}
+ /* 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;
+ int remaining = MAX_TCP_OPTION_SPACE - 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;
+ }
+
+ size += need;
+ }
+ }
return size;
}
@@ -525,9 +661,14 @@ static unsigned tcp_synack_options(struct sock *sk,
struct request_sock *req,
unsigned mss, struct sk_buff *skb,
struct tcp_out_options *opts,
- struct tcp_md5sig_key **md5) {
- unsigned size = 0;
+ struct tcp_md5sig_key **md5,
+ struct tcp_extend_values *xvp)
+{
struct inet_request_sock *ireq = inet_rsk(req);
+ unsigned size = 0;
+ u8 cookie_plus = (xvp != NULL && !xvp->cookie_out_never)
+ ? xvp->cookie_plus
+ : 0;
char doing_ts;
#ifdef CONFIG_TCP_MD5SIG
@@ -566,6 +707,28 @@ static unsigned tcp_synack_options(struct sock *sk,
size += TCPOLEN_SACKPERM_ALIGNED;
}
+ /* Similar rationale to tcp_syn_options() applies here, too.
+ * If the <SYN> options fit, the same options should fit now!
+ */
+ if (*md5 == NULL
+ && doing_ts
+ && cookie_plus > TCPOLEN_COOKIE_BASE) {
+ int need = cookie_plus; /* has TCPOLEN_COOKIE_BASE */
+ int remaining = MAX_TCP_OPTION_SPACE - size;
+
+ 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;
+ size += need;
+ } else {
+ /* There's no error return, so flag it. */
+ xvp->cookie_out_never = 1; /* true */
+ }
+ }
return size;
}
@@ -632,7 +795,6 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
struct tcp_out_options opts;
unsigned tcp_options_size, tcp_header_size;
struct tcp_md5sig_key *md5;
- __u8 *md5_hash_location;
struct tcphdr *th;
int err;
@@ -703,7 +865,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
}
}
- tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location);
+ tcp_options_write((__be32 *)(th + 1), tp, &opts);
if (likely((tcb->flags & TCPCB_FLAG_SYN) == 0))
TCP_ECN_send(sk, skb, tcp_header_size);
@@ -711,7 +873,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it,
/* Calculate the MD5 hash, as we have all we need now */
if (md5) {
sk->sk_route_caps &= ~NETIF_F_GSO_MASK;
- tp->af_specific->calc_md5_hash(md5_hash_location,
+ tp->af_specific->calc_md5_hash(opts.hash_location,
md5, sk, NULL, skb);
}
#endif
@@ -2235,14 +2397,14 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
struct request_values *rvp,
struct request_sock *req)
{
+ 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);
struct tcphdr *th;
- int tcp_header_size;
- struct tcp_out_options opts;
struct sk_buff *skb;
struct tcp_md5sig_key *md5;
- __u8 *md5_hash_location;
+ int tcp_header_size;
int mss;
skb = sock_wmalloc(sk, MAX_TCP_HEADER + 15, 1, GFP_ATOMIC);
@@ -2280,7 +2442,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
#endif
TCP_SKB_CB(skb)->when = tcp_time_stamp;
tcp_header_size = tcp_synack_options(sk, req, mss,
- skb, &opts, &md5) +
+ skb, &opts, &md5, xvp) +
sizeof(struct tcphdr);
skb_push(skb, tcp_header_size);
@@ -2298,19 +2460,58 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst,
*/
tcp_init_nondata_skb(skb, tcp_rsk(req)->snt_isn,
TCPCB_FLAG_SYN | TCPCB_FLAG_ACK);
+
+ if (OPTION_COOKIE_EXTENSION & opts.options) {
+ const struct tcp_cookie_values *cvp = tp->cookie_values;
+
+ if (cvp != NULL
+ && cvp->s_data_constant
+ && cvp->s_data_desired > 0) {
+ u8 *buf = skb_put(skb, cvp->s_data_desired);
+
+ /* copy data directly from the listening socket. */
+ memcpy(buf, cvp->s_data_payload, cvp->s_data_desired);
+ TCP_SKB_CB(skb)->end_seq += cvp->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-- ^= ((th->dest << 16) | th->source);
+ *tail-- ^= (u32)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);
th->ack_seq = htonl(tcp_rsk(req)->rcv_isn + 1);
/* RFC1323: The window in SYN & SYN/ACK segments is never scaled. */
th->window = htons(min(req->rcv_wnd, 65535U));
- tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location);
+ tcp_options_write((__be32 *)(th + 1), tp, &opts);
th->doff = (tcp_header_size >> 2);
TCP_INC_STATS(sock_net(sk), TCP_MIB_OUTSEGS);
#ifdef CONFIG_TCP_MD5SIG
/* Okay, we have all we need - do the md5 hash if needed */
if (md5) {
- tcp_rsk(req)->af_specific->calc_md5_hash(md5_hash_location,
+ tcp_rsk(req)->af_specific->calc_md5_hash(opts.hash_location,
md5, NULL, req, skb);
}
#endif
diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c
index 612fc53..a60b934 100644
--- a/net/ipv6/syncookies.c
+++ b/net/ipv6/syncookies.c
@@ -159,6 +159,8 @@ static inline int cookie_check(struct sk_buff *skb, __u32 cookie)
struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
{
+ struct tcp_options_received tcp_opt;
+ u8 *cryptic_value;
struct inet_request_sock *ireq;
struct inet6_request_sock *ireq6;
struct tcp_request_sock *treq;
@@ -171,7 +173,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb)
int mss;
struct dst_entry *dst;
__u8 rcv_wscale;
- struct tcp_options_received tcp_opt;
if (!sysctl_tcp_syncookies || !th->ack)
goto out;
@@ -254,7 +255,7 @@ 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, 0, dst);
+ tcp_parse_options(skb, &tcp_opt, &cryptic_value, 0, dst);
if (tcp_opt.saw_tstamp)
cookie_check_timestamp(&tcp_opt);
diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
index b528f75..14b6a32 100644
--- a/net/ipv6/tcp_ipv6.c
+++ b/net/ipv6/tcp_ipv6.c
@@ -1162,7 +1162,9 @@ 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;
+ u8 *cryptic_value;
struct request_sock *req;
struct inet6_request_sock *treq;
struct ipv6_pinfo *np = inet6_sk(sk);
@@ -1206,8 +1208,53 @@ 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, &cryptic_value, 0, dst);
+
+ 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 = &ipv6_hdr(skb)->daddr.s6_addr32[0];
+ *mess++ ^= *d++;
+ *mess++ ^= *d++;
+ *mess++ ^= *d++;
+ *mess++ ^= *d++;
+ d = &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++ ^= *cryptic_value++;
+ }
- tcp_parse_options(skb, &tmp_opt, 0, dst);
+#ifdef CONFIG_SYN_COOKIES
+ want_cookie = 0; /* not our kind of cookie */
+#endif
+ 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;
if (want_cookie && !tmp_opt.saw_tstamp)
tcp_clear_options(&tmp_opt);
@@ -1244,7 +1291,8 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb)
security_inet_conn_request(sk, skb, req);
- if (tcp_v6_send_synack(sk, req, NULL)
+ if (tcp_v6_send_synack(sk, req,
+ (struct request_values *)&tmp_ext)
|| want_cookie)
goto drop_and_free;
@@ -1865,6 +1913,19 @@ static int tcp_v6_init_sock(struct sock *sk)
tp->af_specific = &tcp_sock_ipv6_specific;
#endif
+ /* TCP Cookie Transactions */
+ if (sysctl_tcp_cookie_size > 0) {
+ /* Default, cookies without s_data. */
+ 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, extend_timestamp,
+ * s_data_constant, s_data_in, s_data_out
+ */
sk->sk_sndbuf = sysctl_tcp_wmem[1];
sk->sk_rcvbuf = sysctl_tcp_rmem[1];
--
1.6.3.3
^ permalink raw reply related
* [PATCHv9 0/3] vhost: a kernel-level virtio server
From: Michael S. Tsirkin @ 2009-11-09 17:21 UTC (permalink / raw)
To: netdev, virtualization, kvm, linux-kernel, mingo, linux-mm, akpm
Ok, I think I've addressed all comments so far here, and it still seems
to work :). Please take a look. I basically ended up accepting all
Rusty's suggestions, except I did not get rid of avail_idx field in vq:
I don't (yet?) understand what's wrong with it, if any, and it seems
required for correct implementation of notify on empty. I tried
adding comment where it's changed to clarify the intent.
Rusty, thanks very much for the review. I didn't split the logging code
out as you indicated that it's not necessary at this point.
---
This implements vhost: a kernel-level backend for virtio,
The main motivation for this work is to reduce virtualization
overhead for virtio by removing system calls on data path,
without guest changes. For virtio-net, this removes up to
4 system calls per packet: vm exit for kick, reentry for kick,
iothread wakeup for packet, interrupt injection for packet.
This driver is pretty minimal, but it's fully functional (including
migration support interfaces), and already shows performance (especially
latency) improvement over userspace.
Some more detailed description attached to the patch itself.
The patches apply to both 2.6.32-rc6 and kvm.git. I'd like them to go
into linux-next if possible. Please comment.
Changelog from v8:
- typo in error message
- more checks for vq size (must be power of 2)
From Rusty's review:
- don't hardcode iov size
- rename no_notify disable_notify
- rearrange loop
- convert irq trigger language to signal eventfd
- make vhost_enable_notify return status
- -1 -> -1U
- get rid of kzalloc
- better comment on vail_idx
- convert vq index to vq usage
- rename ACK->SET
- merge vring addresses into a single struct
- some comments and cosmetic changes
Changelog from v7:
- Add note on RCU usage, mirroring this in vhost/vhost.h
- Fix locking typo noted by Eric Dumazet
- Fix warnings on 32 bit
Changelog from v6:
- review comments by Daniel Walker addressed
- checkpatch cleanup
- fix build on 32 bit
- maintainers entry corrected
Changelog from v5:
- tun support
- backends with virtio net header support (enables GSO, checksum etc)
- 32 bit compat fixed
- support indirect buffers, tx exit mitigation,
tx interrupt mitigation
- support write logging (allows migration without virtio ring code in userspace)
Changelog from v4:
- disable rx notification when have rx buffers
- addressed all comments from Rusty's review
- copy bugfixes from lguest commits:
ebf9a5a99c1a464afe0b4dfa64416fc8b273bc5c
e606490c440900e50ccf73a54f6fc6150ff40815
Changelog from v3:
- checkpatch fixes
Changelog from v2:
- Comments on RCU usage
- Compat ioctl support
- Make variable static
- Copied more idiomatic english from Rusty
Changes from v1:
- Move use_mm/unuse_mm from fs/aio.c to mm instead of copying.
- Reorder code to avoid need for forward declarations
- Kill a couple of debugging printks
Michael S. Tsirkin (3):
tun: export underlying socket
mm: export use_mm/unuse_mm to modules
vhost_net: a kernel-level virtio server
MAINTAINERS | 9 +
arch/x86/kvm/Kconfig | 1 +
drivers/Makefile | 1 +
drivers/net/tun.c | 101 ++++-
drivers/vhost/Kconfig | 11 +
drivers/vhost/Makefile | 2 +
drivers/vhost/net.c | 648 +++++++++++++++++++++++++++++
drivers/vhost/vhost.c | 965 ++++++++++++++++++++++++++++++++++++++++++++
drivers/vhost/vhost.h | 159 ++++++++
include/linux/Kbuild | 1 +
include/linux/if_tun.h | 14 +
include/linux/miscdevice.h | 1 +
include/linux/vhost.h | 130 ++++++
mm/mmu_context.c | 3 +
14 files changed, 2027 insertions(+), 19 deletions(-)
create mode 100644 drivers/vhost/Kconfig
create mode 100644 drivers/vhost/Makefile
create mode 100644 drivers/vhost/net.c
create mode 100644 drivers/vhost/vhost.c
create mode 100644 drivers/vhost/vhost.h
create mode 100644 include/linux/vhost.h
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply
* [PATCHv9 1/3] tun: export underlying socket
From: Michael S. Tsirkin @ 2009-11-09 17:22 UTC (permalink / raw)
To: netdev, virtualization, kvm, linux-kernel, mingo, linux-mm, akpm
In-Reply-To: <cover.1257786516.git.mst@redhat.com>
Tun device looks similar to a packet socket
in that both pass complete frames from/to userspace.
This patch fills in enough fields in the socket underlying tun driver
to support sendmsg/recvmsg operations, and message flags
MSG_TRUNC and MSG_DONTWAIT, and exports access to this socket
to modules. Regular read/write behaviour is unchanged.
This way, code using raw sockets to inject packets
into a physical device, can support injecting
packets into host network stack almost without modification.
First user of this interface will be vhost virtualization
accelerator.
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Herbert Xu <herbert@gondor.apana.org.au>
Acked-by: David S. Miller <davem@davemloft.net>
---
drivers/net/tun.c | 101 +++++++++++++++++++++++++++++++++++++++---------
include/linux/if_tun.h | 14 +++++++
2 files changed, 96 insertions(+), 19 deletions(-)
diff --git a/drivers/net/tun.c b/drivers/net/tun.c
index 4fdfa2a..18f8876 100644
--- a/drivers/net/tun.c
+++ b/drivers/net/tun.c
@@ -144,6 +144,7 @@ static int tun_attach(struct tun_struct *tun, struct file *file)
err = 0;
tfile->tun = tun;
tun->tfile = tfile;
+ tun->socket.file = file;
dev_hold(tun->dev);
sock_hold(tun->socket.sk);
atomic_inc(&tfile->count);
@@ -158,6 +159,7 @@ static void __tun_detach(struct tun_struct *tun)
/* Detach from net device */
netif_tx_lock_bh(tun->dev);
tun->tfile = NULL;
+ tun->socket.file = NULL;
netif_tx_unlock_bh(tun->dev);
/* Drop read queue */
@@ -387,7 +389,8 @@ static netdev_tx_t tun_net_xmit(struct sk_buff *skb, struct net_device *dev)
/* Notify and wake up reader process */
if (tun->flags & TUN_FASYNC)
kill_fasync(&tun->fasync, SIGIO, POLL_IN);
- wake_up_interruptible(&tun->socket.wait);
+ wake_up_interruptible_poll(&tun->socket.wait, POLLIN |
+ POLLRDNORM | POLLRDBAND);
return NETDEV_TX_OK;
drop:
@@ -743,7 +746,7 @@ static __inline__ ssize_t tun_put_user(struct tun_struct *tun,
len = min_t(int, skb->len, len);
skb_copy_datagram_const_iovec(skb, 0, iv, total, len);
- total += len;
+ total += skb->len;
tun->dev->stats.tx_packets++;
tun->dev->stats.tx_bytes += len;
@@ -751,34 +754,23 @@ static __inline__ ssize_t tun_put_user(struct tun_struct *tun,
return total;
}
-static ssize_t tun_chr_aio_read(struct kiocb *iocb, const struct iovec *iv,
- unsigned long count, loff_t pos)
+static ssize_t tun_do_read(struct tun_struct *tun,
+ struct kiocb *iocb, const struct iovec *iv,
+ ssize_t len, int noblock)
{
- struct file *file = iocb->ki_filp;
- struct tun_file *tfile = file->private_data;
- struct tun_struct *tun = __tun_get(tfile);
DECLARE_WAITQUEUE(wait, current);
struct sk_buff *skb;
- ssize_t len, ret = 0;
-
- if (!tun)
- return -EBADFD;
+ ssize_t ret = 0;
DBG(KERN_INFO "%s: tun_chr_read\n", tun->dev->name);
- len = iov_length(iv, count);
- if (len < 0) {
- ret = -EINVAL;
- goto out;
- }
-
add_wait_queue(&tun->socket.wait, &wait);
while (len) {
current->state = TASK_INTERRUPTIBLE;
/* Read frames from the queue */
if (!(skb=skb_dequeue(&tun->socket.sk->sk_receive_queue))) {
- if (file->f_flags & O_NONBLOCK) {
+ if (noblock) {
ret = -EAGAIN;
break;
}
@@ -805,6 +797,27 @@ static ssize_t tun_chr_aio_read(struct kiocb *iocb, const struct iovec *iv,
current->state = TASK_RUNNING;
remove_wait_queue(&tun->socket.wait, &wait);
+ return ret;
+}
+
+static ssize_t tun_chr_aio_read(struct kiocb *iocb, const struct iovec *iv,
+ unsigned long count, loff_t pos)
+{
+ struct file *file = iocb->ki_filp;
+ struct tun_file *tfile = file->private_data;
+ struct tun_struct *tun = __tun_get(tfile);
+ ssize_t len, ret;
+
+ if (!tun)
+ return -EBADFD;
+ len = iov_length(iv, count);
+ if (len < 0) {
+ ret = -EINVAL;
+ goto out;
+ }
+
+ ret = tun_do_read(tun, iocb, iv, len, file->f_flags & O_NONBLOCK);
+ ret = min_t(ssize_t, ret, len);
out:
tun_put(tun);
return ret;
@@ -847,7 +860,8 @@ static void tun_sock_write_space(struct sock *sk)
return;
if (sk->sk_sleep && waitqueue_active(sk->sk_sleep))
- wake_up_interruptible_sync(sk->sk_sleep);
+ wake_up_interruptible_sync_poll(sk->sk_sleep, POLLOUT |
+ POLLWRNORM | POLLWRBAND);
tun = container_of(sk, struct tun_sock, sk)->tun;
kill_fasync(&tun->fasync, SIGIO, POLL_OUT);
@@ -858,6 +872,37 @@ static void tun_sock_destruct(struct sock *sk)
free_netdev(container_of(sk, struct tun_sock, sk)->tun->dev);
}
+static int tun_sendmsg(struct kiocb *iocb, struct socket *sock,
+ struct msghdr *m, size_t total_len)
+{
+ struct tun_struct *tun = container_of(sock, struct tun_struct, socket);
+ return tun_get_user(tun, m->msg_iov, total_len,
+ m->msg_flags & MSG_DONTWAIT);
+}
+
+static int tun_recvmsg(struct kiocb *iocb, struct socket *sock,
+ struct msghdr *m, size_t total_len,
+ int flags)
+{
+ struct tun_struct *tun = container_of(sock, struct tun_struct, socket);
+ int ret;
+ if (flags & ~(MSG_DONTWAIT|MSG_TRUNC))
+ return -EINVAL;
+ ret = tun_do_read(tun, iocb, m->msg_iov, total_len,
+ flags & MSG_DONTWAIT);
+ if (ret > total_len) {
+ m->msg_flags |= MSG_TRUNC;
+ ret = flags & MSG_TRUNC ? ret : total_len;
+ }
+ return ret;
+}
+
+/* Ops structure to mimic raw sockets with tun */
+static const struct proto_ops tun_socket_ops = {
+ .sendmsg = tun_sendmsg,
+ .recvmsg = tun_recvmsg,
+};
+
static struct proto tun_proto = {
.name = "tun",
.owner = THIS_MODULE,
@@ -986,6 +1031,7 @@ static int tun_set_iff(struct net *net, struct file *file, struct ifreq *ifr)
goto err_free_dev;
init_waitqueue_head(&tun->socket.wait);
+ tun->socket.ops = &tun_socket_ops;
sock_init_data(&tun->socket, sk);
sk->sk_write_space = tun_sock_write_space;
sk->sk_sndbuf = INT_MAX;
@@ -1489,6 +1535,23 @@ static void tun_cleanup(void)
rtnl_link_unregister(&tun_link_ops);
}
+/* Get an underlying socket object from tun file. Returns error unless file is
+ * attached to a device. The returned object works like a packet socket, it
+ * can be used for sock_sendmsg/sock_recvmsg. The caller is responsible for
+ * holding a reference to the file for as long as the socket is in use. */
+struct socket *tun_get_socket(struct file *file)
+{
+ struct tun_struct *tun;
+ if (file->f_op != &tun_fops)
+ return ERR_PTR(-EINVAL);
+ tun = tun_get(file);
+ if (!tun)
+ return ERR_PTR(-EBADFD);
+ tun_put(tun);
+ return &tun->socket;
+}
+EXPORT_SYMBOL_GPL(tun_get_socket);
+
module_init(tun_init);
module_exit(tun_cleanup);
MODULE_DESCRIPTION(DRV_DESCRIPTION);
diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h
index 3f5fd52..404abe0 100644
--- a/include/linux/if_tun.h
+++ b/include/linux/if_tun.h
@@ -86,4 +86,18 @@ struct tun_filter {
__u8 addr[0][ETH_ALEN];
};
+#ifdef __KERNEL__
+#if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE)
+struct socket *tun_get_socket(struct file *);
+#else
+#include <linux/err.h>
+#include <linux/errno.h>
+struct file;
+struct socket;
+static inline struct socket *tun_get_socket(struct file *f)
+{
+ return ERR_PTR(-EINVAL);
+}
+#endif /* CONFIG_TUN */
+#endif /* __KERNEL__ */
#endif /* __IF_TUN_H */
--
1.6.5.2.143.g8cc62
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCHv9 2/3] mm: export use_mm/unuse_mm to modules
From: Michael S. Tsirkin @ 2009-11-09 17:22 UTC (permalink / raw)
To: netdev, virtualization, kvm, linux-kernel, mingo, linux-mm, akpm
In-Reply-To: <cover.1257786516.git.mst@redhat.com>
vhost net module wants to do copy to/from user from a kernel thread,
which needs use_mm. Export it to modules.
Acked-by: Andrea Arcangeli <aarcange@redhat.com>
Acked-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
mm/mmu_context.c | 3 +++
1 files changed, 3 insertions(+), 0 deletions(-)
diff --git a/mm/mmu_context.c b/mm/mmu_context.c
index ded9081..0777654 100644
--- a/mm/mmu_context.c
+++ b/mm/mmu_context.c
@@ -5,6 +5,7 @@
#include <linux/mm.h>
#include <linux/mmu_context.h>
+#include <linux/module.h>
#include <linux/sched.h>
#include <asm/mmu_context.h>
@@ -37,6 +38,7 @@ void use_mm(struct mm_struct *mm)
if (active_mm != mm)
mmdrop(active_mm);
}
+EXPORT_SYMBOL_GPL(use_mm);
/*
* unuse_mm
@@ -56,3 +58,4 @@ void unuse_mm(struct mm_struct *mm)
enter_lazy_tlb(mm, tsk);
task_unlock(tsk);
}
+EXPORT_SYMBOL_GPL(unuse_mm);
--
1.6.5.2.143.g8cc62
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* [PATCHv9 3/3] vhost_net: a kernel-level virtio server
From: Michael S. Tsirkin @ 2009-11-09 17:22 UTC (permalink / raw)
To: netdev, virtualization, kvm, linux-kernel, mingo, linux-mm, akpm
In-Reply-To: <cover.1257786516.git.mst@redhat.com>
What it is: vhost net is a character device that can be used to reduce
the number of system calls involved in virtio networking.
Existing virtio net code is used in the guest without modification.
There's similarity with vringfd, with some differences and reduced scope
- uses eventfd for signalling
- structures can be moved around in memory at any time (good for
migration, bug work-arounds in userspace)
- write logging is supported (good for migration)
- support memory table and not just an offset (needed for kvm)
common virtio related code has been put in a separate file vhost.c and
can be made into a separate module if/when more backends appear. I used
Rusty's lguest.c as the source for developing this part : this supplied
me with witty comments I wouldn't be able to write myself.
What it is not: vhost net is not a bus, and not a generic new system
call. No assumptions are made on how guest performs hypercalls.
Userspace hypervisors are supported as well as kvm.
How it works: Basically, we connect virtio frontend (configured by
userspace) to a backend. The backend could be a network device, or a tap
device. Backend is also configured by userspace, including vlan/mac
etc.
Status: This works for me, and I haven't see any crashes.
Compared to userspace, people reported improved latency (as I save up to
4 system calls per packet), as well as better bandwidth and CPU
utilization.
Features that I plan to look at in the future:
- mergeable buffers
- zero copy
- scalability tuning: figure out the best threading model to use
Note on RCU usage (this is also documented in vhost.h, near
private_pointer which is the value protected by this variant of RCU):
what is happening is that the rcu_dereference() is being used in a
workqueue item. The role of rcu_read_lock() is taken on by the start of
execution of the workqueue item, of rcu_read_unlock() by the end of
execution of the workqueue item, and of synchronize_rcu() by
flush_workqueue()/flush_work(). In the future we might need to apply
some gcc attribute or sparse annotation to the function passed to
INIT_WORK(). Paul's ack below is for this RCU usage.
Acked-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
---
MAINTAINERS | 9 +
arch/x86/kvm/Kconfig | 1 +
drivers/Makefile | 1 +
drivers/vhost/Kconfig | 11 +
drivers/vhost/Makefile | 2 +
drivers/vhost/net.c | 648 +++++++++++++++++++++++++++++
drivers/vhost/vhost.c | 965 ++++++++++++++++++++++++++++++++++++++++++++
drivers/vhost/vhost.h | 159 ++++++++
include/linux/Kbuild | 1 +
include/linux/miscdevice.h | 1 +
include/linux/vhost.h | 130 ++++++
11 files changed, 1928 insertions(+), 0 deletions(-)
create mode 100644 drivers/vhost/Kconfig
create mode 100644 drivers/vhost/Makefile
create mode 100644 drivers/vhost/net.c
create mode 100644 drivers/vhost/vhost.c
create mode 100644 drivers/vhost/vhost.h
create mode 100644 include/linux/vhost.h
diff --git a/MAINTAINERS b/MAINTAINERS
index a1a2ace..7d4bfa2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -5636,6 +5636,15 @@ S: Maintained
F: Documentation/filesystems/vfat.txt
F: fs/fat/
+VIRTIO HOST (VHOST)
+M: "Michael S. Tsirkin" <mst@redhat.com>
+L: kvm@vger.kernel.org
+L: virtualization@lists.osdl.org
+L: netdev@vger.kernel.org
+S: Maintained
+F: drivers/vhost/
+F: include/linux/vhost.h
+
VIA RHINE NETWORK DRIVER
M: Roger Luethi <rl@hellgate.ch>
S: Maintained
diff --git a/arch/x86/kvm/Kconfig b/arch/x86/kvm/Kconfig
index b84e571..94f44d9 100644
--- a/arch/x86/kvm/Kconfig
+++ b/arch/x86/kvm/Kconfig
@@ -64,6 +64,7 @@ config KVM_AMD
# OK, it's a little counter-intuitive to do this, but it puts it neatly under
# the virtualization menu.
+source drivers/vhost/Kconfig
source drivers/lguest/Kconfig
source drivers/virtio/Kconfig
diff --git a/drivers/Makefile b/drivers/Makefile
index 6ee53c7..81e3659 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -106,6 +106,7 @@ obj-$(CONFIG_HID) += hid/
obj-$(CONFIG_PPC_PS3) += ps3/
obj-$(CONFIG_OF) += of/
obj-$(CONFIG_SSB) += ssb/
+obj-$(CONFIG_VHOST_NET) += vhost/
obj-$(CONFIG_VIRTIO) += virtio/
obj-$(CONFIG_VLYNQ) += vlynq/
obj-$(CONFIG_STAGING) += staging/
diff --git a/drivers/vhost/Kconfig b/drivers/vhost/Kconfig
new file mode 100644
index 0000000..9f409f4
--- /dev/null
+++ b/drivers/vhost/Kconfig
@@ -0,0 +1,11 @@
+config VHOST_NET
+ tristate "Host kernel accelerator for virtio net (EXPERIMENTAL)"
+ depends on NET && EVENTFD && EXPERIMENTAL
+ ---help---
+ This kernel module can be loaded in host kernel to accelerate
+ guest networking with virtio_net. Not to be confused with virtio_net
+ module itself which needs to be loaded in guest kernel.
+
+ To compile this driver as a module, choose M here: the module will
+ be called vhost_net.
+
diff --git a/drivers/vhost/Makefile b/drivers/vhost/Makefile
new file mode 100644
index 0000000..72dd020
--- /dev/null
+++ b/drivers/vhost/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_VHOST_NET) += vhost_net.o
+vhost_net-y := vhost.o net.o
diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c
new file mode 100644
index 0000000..22d5fef
--- /dev/null
+++ b/drivers/vhost/net.c
@@ -0,0 +1,648 @@
+/* Copyright (C) 2009 Red Hat, Inc.
+ * Author: Michael S. Tsirkin <mst@redhat.com>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * virtio-net server in host kernel.
+ */
+
+#include <linux/compat.h>
+#include <linux/eventfd.h>
+#include <linux/vhost.h>
+#include <linux/virtio_net.h>
+#include <linux/mmu_context.h>
+#include <linux/miscdevice.h>
+#include <linux/module.h>
+#include <linux/mutex.h>
+#include <linux/workqueue.h>
+#include <linux/rcupdate.h>
+#include <linux/file.h>
+
+#include <linux/net.h>
+#include <linux/if_packet.h>
+#include <linux/if_arp.h>
+#include <linux/if_tun.h>
+
+#include <net/sock.h>
+
+#include "vhost.h"
+
+/* Max number of bytes transferred before requeueing the job.
+ * Using this limit prevents one virtqueue from starving others. */
+#define VHOST_NET_WEIGHT 0x80000
+
+enum {
+ VHOST_NET_VQ_RX = 0,
+ VHOST_NET_VQ_TX = 1,
+ VHOST_NET_VQ_MAX = 2,
+};
+
+enum vhost_net_poll_state {
+ VHOST_NET_POLL_DISABLED = 0,
+ VHOST_NET_POLL_STARTED = 1,
+ VHOST_NET_POLL_STOPPED = 2,
+};
+
+struct vhost_net {
+ struct vhost_dev dev;
+ struct vhost_virtqueue vqs[VHOST_NET_VQ_MAX];
+ struct vhost_poll poll[VHOST_NET_VQ_MAX];
+ /* Tells us whether we are polling a socket for TX.
+ * We only do this when socket buffer fills up.
+ * Protected by tx vq lock. */
+ enum vhost_net_poll_state tx_poll_state;
+};
+
+/* Pop first len bytes from iovec. Return number of segments used. */
+static int move_iovec_hdr(struct iovec *from, struct iovec *to,
+ size_t len, int iov_count)
+{
+ int seg = 0;
+ size_t size;
+ while (len && seg < iov_count) {
+ size = min(from->iov_len, len);
+ to->iov_base = from->iov_base;
+ to->iov_len = size;
+ from->iov_len -= size;
+ from->iov_base += size;
+ len -= size;
+ ++from;
+ ++to;
+ ++seg;
+ }
+ return seg;
+}
+
+/* Caller must have TX VQ lock */
+static void tx_poll_stop(struct vhost_net *net)
+{
+ if (likely(net->tx_poll_state != VHOST_NET_POLL_STARTED))
+ return;
+ vhost_poll_stop(net->poll + VHOST_NET_VQ_TX);
+ net->tx_poll_state = VHOST_NET_POLL_STOPPED;
+}
+
+/* Caller must have TX VQ lock */
+static void tx_poll_start(struct vhost_net *net, struct socket *sock)
+{
+ if (unlikely(net->tx_poll_state != VHOST_NET_POLL_STOPPED))
+ return;
+ vhost_poll_start(net->poll + VHOST_NET_VQ_TX, sock->file);
+ net->tx_poll_state = VHOST_NET_POLL_STARTED;
+}
+
+/* Expects to be always run from workqueue - which acts as
+ * read-size critical section for our kind of RCU. */
+static void handle_tx(struct vhost_net *net)
+{
+ struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_TX];
+ unsigned head, out, in, s;
+ struct msghdr msg = {
+ .msg_name = NULL,
+ .msg_namelen = 0,
+ .msg_control = NULL,
+ .msg_controllen = 0,
+ .msg_iov = vq->iov,
+ .msg_flags = MSG_DONTWAIT,
+ };
+ size_t len, total_len = 0;
+ int err, wmem;
+ size_t hdr_size;
+ struct socket *sock = rcu_dereference(vq->private_data);
+ if (!sock)
+ return;
+
+ wmem = atomic_read(&sock->sk->sk_wmem_alloc);
+ if (wmem >= sock->sk->sk_sndbuf)
+ return;
+
+ use_mm(net->dev.mm);
+ mutex_lock(&vq->mutex);
+ vhost_disable_notify(vq);
+
+ if (wmem < sock->sk->sk_sndbuf * 2)
+ tx_poll_stop(net);
+ hdr_size = vq->hdr_size;
+
+ for (;;) {
+ head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
+ ARRAY_SIZE(vq->iov),
+ &out, &in,
+ NULL, NULL);
+ /* Nothing new? Wait for eventfd to tell us they refilled. */
+ if (head == vq->num) {
+ wmem = atomic_read(&sock->sk->sk_wmem_alloc);
+ if (wmem >= sock->sk->sk_sndbuf * 3 / 4) {
+ tx_poll_start(net, sock);
+ set_bit(SOCK_ASYNC_NOSPACE, &sock->flags);
+ break;
+ }
+ if (unlikely(vhost_enable_notify(vq))) {
+ vhost_disable_notify(vq);
+ continue;
+ }
+ break;
+ }
+ if (in) {
+ vq_err(vq, "Unexpected descriptor format for TX: "
+ "out %d, int %d\n", out, in);
+ break;
+ }
+ /* Skip header. TODO: support TSO. */
+ s = move_iovec_hdr(vq->iov, vq->hdr, hdr_size, out);
+ msg.msg_iovlen = out;
+ len = iov_length(vq->iov, out);
+ /* Sanity check */
+ if (!len) {
+ vq_err(vq, "Unexpected header len for TX: "
+ "%zd expected %zd\n",
+ iov_length(vq->hdr, s), hdr_size);
+ break;
+ }
+ /* TODO: Check specific error and bomb out unless ENOBUFS? */
+ err = sock->ops->sendmsg(NULL, sock, &msg, len);
+ if (unlikely(err < 0)) {
+ vhost_discard_vq_desc(vq);
+ tx_poll_start(net, sock);
+ break;
+ }
+ if (err != len)
+ pr_err("Truncated TX packet: "
+ " len %d != %zd\n", err, len);
+ vhost_add_used_and_signal(&net->dev, vq, head, 0);
+ total_len += len;
+ if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
+ vhost_poll_queue(&vq->poll);
+ break;
+ }
+ }
+
+ mutex_unlock(&vq->mutex);
+ unuse_mm(net->dev.mm);
+}
+
+/* Expects to be always run from workqueue - which acts as
+ * read-size critical section for our kind of RCU. */
+static void handle_rx(struct vhost_net *net)
+{
+ struct vhost_virtqueue *vq = &net->dev.vqs[VHOST_NET_VQ_RX];
+ unsigned head, out, in, log, s;
+ struct vhost_log *vq_log;
+ struct msghdr msg = {
+ .msg_name = NULL,
+ .msg_namelen = 0,
+ .msg_control = NULL, /* FIXME: get and handle RX aux data. */
+ .msg_controllen = 0,
+ .msg_iov = vq->iov,
+ .msg_flags = MSG_DONTWAIT,
+ };
+
+ struct virtio_net_hdr hdr = {
+ .flags = 0,
+ .gso_type = VIRTIO_NET_HDR_GSO_NONE
+ };
+
+ size_t len, total_len = 0;
+ int err;
+ size_t hdr_size;
+ struct socket *sock = rcu_dereference(vq->private_data);
+ if (!sock || skb_queue_empty(&sock->sk->sk_receive_queue))
+ return;
+
+ use_mm(net->dev.mm);
+ mutex_lock(&vq->mutex);
+ vhost_disable_notify(vq);
+ hdr_size = vq->hdr_size;
+
+ vq_log = unlikely(vhost_has_feature(&net->dev, VHOST_F_LOG_ALL)) ?
+ vq->log : NULL;
+
+ for (;;) {
+ head = vhost_get_vq_desc(&net->dev, vq, vq->iov,
+ ARRAY_SIZE(vq->iov),
+ &out, &in,
+ vq_log, &log);
+ /* OK, now we need to know about added descriptors. */
+ if (head == vq->num) {
+ if (unlikely(vhost_enable_notify(vq))) {
+ /* They have slipped one in as we were
+ * doing that: check again. */
+ vhost_disable_notify(vq);
+ continue;
+ }
+ /* Nothing new? Wait for eventfd to tell us
+ * they refilled. */
+ break;
+ }
+ /* We don't need to be notified again. */
+ if (out) {
+ vq_err(vq, "Unexpected descriptor format for RX: "
+ "out %d, int %d\n",
+ out, in);
+ break;
+ }
+ /* Skip header. TODO: support TSO/mergeable rx buffers. */
+ s = move_iovec_hdr(vq->iov, vq->hdr, hdr_size, in);
+ msg.msg_iovlen = in;
+ len = iov_length(vq->iov, in);
+ /* Sanity check */
+ if (!len) {
+ vq_err(vq, "Unexpected header len for RX: "
+ "%zd expected %zd\n",
+ iov_length(vq->hdr, s), hdr_size);
+ break;
+ }
+ err = sock->ops->recvmsg(NULL, sock, &msg,
+ len, MSG_DONTWAIT | MSG_TRUNC);
+ /* TODO: Check specific error and bomb out unless EAGAIN? */
+ if (err < 0) {
+ vhost_discard_vq_desc(vq);
+ break;
+ }
+ /* TODO: Should check and handle checksum. */
+ if (err > len) {
+ pr_err("Discarded truncated rx packet: "
+ " len %d > %zd\n", err, len);
+ vhost_discard_vq_desc(vq);
+ continue;
+ }
+ len = err;
+ err = memcpy_toiovec(vq->hdr, (unsigned char *)&hdr, hdr_size);
+ if (err) {
+ vq_err(vq, "Unable to write vnet_hdr at addr %p: %d\n",
+ vq->iov->iov_base, err);
+ break;
+ }
+ len += hdr_size;
+ vhost_add_used_and_signal(&net->dev, vq, head, len);
+ if (unlikely(vq_log))
+ vhost_log_write(vq, vq_log, log, len);
+ total_len += len;
+ if (unlikely(total_len >= VHOST_NET_WEIGHT)) {
+ vhost_poll_queue(&vq->poll);
+ break;
+ }
+ }
+
+ mutex_unlock(&vq->mutex);
+ unuse_mm(net->dev.mm);
+}
+
+static void handle_tx_kick(struct work_struct *work)
+{
+ struct vhost_virtqueue *vq;
+ struct vhost_net *net;
+ vq = container_of(work, struct vhost_virtqueue, poll.work);
+ net = container_of(vq->dev, struct vhost_net, dev);
+ handle_tx(net);
+}
+
+static void handle_rx_kick(struct work_struct *work)
+{
+ struct vhost_virtqueue *vq;
+ struct vhost_net *net;
+ vq = container_of(work, struct vhost_virtqueue, poll.work);
+ net = container_of(vq->dev, struct vhost_net, dev);
+ handle_rx(net);
+}
+
+static void handle_tx_net(struct work_struct *work)
+{
+ struct vhost_net *net;
+ net = container_of(work, struct vhost_net, poll[VHOST_NET_VQ_TX].work);
+ handle_tx(net);
+}
+
+static void handle_rx_net(struct work_struct *work)
+{
+ struct vhost_net *net;
+ net = container_of(work, struct vhost_net, poll[VHOST_NET_VQ_RX].work);
+ handle_rx(net);
+}
+
+static int vhost_net_open(struct inode *inode, struct file *f)
+{
+ struct vhost_net *n = kmalloc(sizeof *n, GFP_KERNEL);
+ int r;
+ if (!n)
+ return -ENOMEM;
+ f->private_data = n;
+ n->vqs[VHOST_NET_VQ_TX].handle_kick = handle_tx_kick;
+ n->vqs[VHOST_NET_VQ_RX].handle_kick = handle_rx_kick;
+ r = vhost_dev_init(&n->dev, n->vqs, VHOST_NET_VQ_MAX);
+ if (r < 0) {
+ kfree(n);
+ return r;
+ }
+
+ vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, POLLOUT);
+ vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, POLLIN);
+ n->tx_poll_state = VHOST_NET_POLL_DISABLED;
+ return 0;
+}
+
+static void vhost_net_disable_vq(struct vhost_net *n,
+ struct vhost_virtqueue *vq)
+{
+ if (!vq->private_data)
+ return;
+ if (vq == n->vqs + VHOST_NET_VQ_TX) {
+ tx_poll_stop(n);
+ n->tx_poll_state = VHOST_NET_POLL_DISABLED;
+ } else
+ vhost_poll_stop(n->poll + VHOST_NET_VQ_RX);
+}
+
+static void vhost_net_enable_vq(struct vhost_net *n,
+ struct vhost_virtqueue *vq)
+{
+ struct socket *sock = vq->private_data;
+ if (!sock)
+ return;
+ if (vq == n->vqs + VHOST_NET_VQ_TX) {
+ n->tx_poll_state = VHOST_NET_POLL_STOPPED;
+ tx_poll_start(n, sock);
+ } else
+ vhost_poll_start(n->poll + VHOST_NET_VQ_RX, sock->file);
+}
+
+static struct socket *vhost_net_stop_vq(struct vhost_net *n,
+ struct vhost_virtqueue *vq)
+{
+ struct socket *sock;
+
+ mutex_lock(&vq->mutex);
+ sock = vq->private_data;
+ vhost_net_disable_vq(n, vq);
+ rcu_assign_pointer(vq->private_data, NULL);
+ mutex_unlock(&vq->mutex);
+ return sock;
+}
+
+static void vhost_net_stop(struct vhost_net *n, struct socket **tx_sock,
+ struct socket **rx_sock)
+{
+ *tx_sock = vhost_net_stop_vq(n, n->vqs + VHOST_NET_VQ_TX);
+ *rx_sock = vhost_net_stop_vq(n, n->vqs + VHOST_NET_VQ_RX);
+}
+
+static void vhost_net_flush_vq(struct vhost_net *n, int index)
+{
+ vhost_poll_flush(n->poll + index);
+ vhost_poll_flush(&n->dev.vqs[index].poll);
+}
+
+static void vhost_net_flush(struct vhost_net *n)
+{
+ vhost_net_flush_vq(n, VHOST_NET_VQ_TX);
+ vhost_net_flush_vq(n, VHOST_NET_VQ_RX);
+}
+
+static int vhost_net_release(struct inode *inode, struct file *f)
+{
+ struct vhost_net *n = f->private_data;
+ struct socket *tx_sock;
+ struct socket *rx_sock;
+
+ vhost_net_stop(n, &tx_sock, &rx_sock);
+ vhost_net_flush(n);
+ vhost_dev_cleanup(&n->dev);
+ if (tx_sock)
+ fput(tx_sock->file);
+ if (rx_sock)
+ fput(rx_sock->file);
+ /* We do an extra flush before freeing memory,
+ * since jobs can re-queue themselves. */
+ vhost_net_flush(n);
+ kfree(n);
+ return 0;
+}
+
+static struct socket *get_raw_socket(int fd)
+{
+ struct {
+ struct sockaddr_ll sa;
+ char buf[MAX_ADDR_LEN];
+ } uaddr;
+ int uaddr_len = sizeof uaddr, r;
+ struct socket *sock = sockfd_lookup(fd, &r);
+ if (!sock)
+ return ERR_PTR(-ENOTSOCK);
+
+ /* Parameter checking */
+ if (sock->sk->sk_type != SOCK_RAW) {
+ r = -ESOCKTNOSUPPORT;
+ goto err;
+ }
+
+ r = sock->ops->getname(sock, (struct sockaddr *)&uaddr.sa,
+ &uaddr_len, 0);
+ if (r)
+ goto err;
+
+ if (uaddr.sa.sll_family != AF_PACKET) {
+ r = -EPFNOSUPPORT;
+ goto err;
+ }
+ return sock;
+err:
+ fput(sock->file);
+ return ERR_PTR(r);
+}
+
+static struct socket *get_tun_socket(int fd)
+{
+ struct file *file = fget(fd);
+ struct socket *sock;
+ if (!file)
+ return ERR_PTR(-EBADF);
+ sock = tun_get_socket(file);
+ if (IS_ERR(sock))
+ fput(file);
+ return sock;
+}
+
+static struct socket *get_socket(int fd)
+{
+ struct socket *sock;
+ if (fd == -1)
+ return NULL;
+ sock = get_raw_socket(fd);
+ if (!IS_ERR(sock))
+ return sock;
+ sock = get_tun_socket(fd);
+ if (!IS_ERR(sock))
+ return sock;
+ return ERR_PTR(-ENOTSOCK);
+}
+
+static long vhost_net_set_backend(struct vhost_net *n, unsigned index, int fd)
+{
+ struct socket *sock, *oldsock;
+ struct vhost_virtqueue *vq;
+ int r;
+
+ mutex_lock(&n->dev.mutex);
+ r = vhost_dev_check_owner(&n->dev);
+ if (r)
+ goto err;
+
+ if (index >= VHOST_NET_VQ_MAX) {
+ r = -ENOBUFS;
+ goto err;
+ }
+ vq = n->vqs + index;
+ mutex_lock(&vq->mutex);
+ sock = get_socket(fd);
+ if (IS_ERR(sock)) {
+ r = PTR_ERR(sock);
+ goto err;
+ }
+
+ /* start polling new socket */
+ oldsock = vq->private_data;
+ if (sock == oldsock)
+ goto done;
+
+ vhost_net_disable_vq(n, vq);
+ rcu_assign_pointer(vq->private_data, sock);
+ vhost_net_enable_vq(n, vq);
+ mutex_unlock(&vq->mutex);
+done:
+ mutex_unlock(&n->dev.mutex);
+ if (oldsock) {
+ vhost_net_flush_vq(n, index);
+ fput(oldsock->file);
+ }
+ return r;
+err:
+ mutex_unlock(&n->dev.mutex);
+ return r;
+}
+
+static long vhost_net_reset_owner(struct vhost_net *n)
+{
+ struct socket *tx_sock = NULL;
+ struct socket *rx_sock = NULL;
+ long err;
+ mutex_lock(&n->dev.mutex);
+ err = vhost_dev_check_owner(&n->dev);
+ if (err)
+ goto done;
+ vhost_net_stop(n, &tx_sock, &rx_sock);
+ vhost_net_flush(n);
+ err = vhost_dev_reset_owner(&n->dev);
+done:
+ mutex_unlock(&n->dev.mutex);
+ if (tx_sock)
+ fput(tx_sock->file);
+ if (rx_sock)
+ fput(rx_sock->file);
+ return err;
+}
+
+static void vhost_net_set_features(struct vhost_net *n, u64 features)
+{
+ size_t hdr_size = features & (1 << VHOST_NET_F_VIRTIO_NET_HDR) ?
+ sizeof(struct virtio_net_hdr) : 0;
+ int i;
+ mutex_lock(&n->dev.mutex);
+ n->dev.acked_features = features;
+ smp_wmb();
+ for (i = 0; i < VHOST_NET_VQ_MAX; ++i) {
+ mutex_lock(&n->vqs[i].mutex);
+ n->vqs[i].hdr_size = hdr_size;
+ mutex_unlock(&n->vqs[i].mutex);
+ }
+ mutex_unlock(&n->dev.mutex);
+ vhost_net_flush(n);
+}
+
+static long vhost_net_ioctl(struct file *f, unsigned int ioctl,
+ unsigned long arg)
+{
+ struct vhost_net *n = f->private_data;
+ void __user *argp = (void __user *)arg;
+ u32 __user *featurep = argp;
+ struct vhost_vring_file backend;
+ u64 features;
+ int r;
+ switch (ioctl) {
+ case VHOST_NET_SET_BACKEND:
+ r = copy_from_user(&backend, argp, sizeof backend);
+ if (r < 0)
+ return r;
+ return vhost_net_set_backend(n, backend.index, backend.fd);
+ case VHOST_GET_FEATURES:
+ features = VHOST_FEATURES;
+ return put_user(features, featurep);
+ case VHOST_SET_FEATURES:
+ r = get_user(features, featurep);
+ /* No features for now */
+ if (r < 0)
+ return r;
+ if (features & ~VHOST_FEATURES)
+ return -EOPNOTSUPP;
+ vhost_net_set_features(n, features);
+ return 0;
+ case VHOST_RESET_OWNER:
+ return vhost_net_reset_owner(n);
+ default:
+ r = vhost_dev_ioctl(&n->dev, ioctl, arg);
+ vhost_net_flush(n);
+ return r;
+ }
+}
+
+#ifdef CONFIG_COMPAT
+static long vhost_net_compat_ioctl(struct file *f, unsigned int ioctl,
+ unsigned long arg)
+{
+ return vhost_net_ioctl(f, ioctl, (unsigned long)compat_ptr(arg));
+}
+#endif
+
+const static struct file_operations vhost_net_fops = {
+ .owner = THIS_MODULE,
+ .release = vhost_net_release,
+ .unlocked_ioctl = vhost_net_ioctl,
+#ifdef CONFIG_COMPAT
+ .compat_ioctl = vhost_net_compat_ioctl,
+#endif
+ .open = vhost_net_open,
+};
+
+static struct miscdevice vhost_net_misc = {
+ VHOST_NET_MINOR,
+ "vhost-net",
+ &vhost_net_fops,
+};
+
+int vhost_net_init(void)
+{
+ int r = vhost_init();
+ if (r)
+ goto err_init;
+ r = misc_register(&vhost_net_misc);
+ if (r)
+ goto err_reg;
+ return 0;
+err_reg:
+ vhost_cleanup();
+err_init:
+ return r;
+
+}
+module_init(vhost_net_init);
+
+void vhost_net_exit(void)
+{
+ misc_deregister(&vhost_net_misc);
+ vhost_cleanup();
+}
+module_exit(vhost_net_exit);
+
+MODULE_VERSION("0.0.1");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Michael S. Tsirkin");
+MODULE_DESCRIPTION("Host kernel accelerator for virtio net");
diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c
new file mode 100644
index 0000000..97233d5
--- /dev/null
+++ b/drivers/vhost/vhost.c
@@ -0,0 +1,965 @@
+/* Copyright (C) 2009 Red Hat, Inc.
+ * Copyright (C) 2006 Rusty Russell IBM Corporation
+ *
+ * Author: Michael S. Tsirkin <mst@redhat.com>
+ *
+ * Inspiration, some code, and most witty comments come from
+ * Documentation/lguest/lguest.c, by Rusty Russell
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.
+ *
+ * Generic code for virtio server in host kernel.
+ */
+
+#include <linux/eventfd.h>
+#include <linux/vhost.h>
+#include <linux/virtio_net.h>
+#include <linux/mm.h>
+#include <linux/miscdevice.h>
+#include <linux/mutex.h>
+#include <linux/workqueue.h>
+#include <linux/rcupdate.h>
+#include <linux/poll.h>
+#include <linux/file.h>
+#include <linux/highmem.h>
+
+#include <linux/net.h>
+#include <linux/if_packet.h>
+#include <linux/if_arp.h>
+
+#include <net/sock.h>
+
+#include "vhost.h"
+
+enum {
+ VHOST_MEMORY_MAX_NREGIONS = 64,
+ VHOST_MEMORY_F_LOG = 0x1,
+};
+
+static struct workqueue_struct *vhost_workqueue;
+
+static void vhost_poll_func(struct file *file, wait_queue_head_t *wqh,
+ poll_table *pt)
+{
+ struct vhost_poll *poll;
+ poll = container_of(pt, struct vhost_poll, table);
+
+ poll->wqh = wqh;
+ add_wait_queue(wqh, &poll->wait);
+}
+
+static int vhost_poll_wakeup(wait_queue_t *wait, unsigned mode, int sync,
+ void *key)
+{
+ struct vhost_poll *poll;
+ poll = container_of(wait, struct vhost_poll, wait);
+ if (!((unsigned long)key & poll->mask))
+ return 0;
+
+ queue_work(vhost_workqueue, &poll->work);
+ return 0;
+}
+
+/* Init poll structure */
+void vhost_poll_init(struct vhost_poll *poll, work_func_t func,
+ unsigned long mask)
+{
+ INIT_WORK(&poll->work, func);
+ init_waitqueue_func_entry(&poll->wait, vhost_poll_wakeup);
+ init_poll_funcptr(&poll->table, vhost_poll_func);
+ poll->mask = mask;
+}
+
+/* Start polling a file. We add ourselves to file's wait queue. The caller must
+ * keep a reference to a file until after vhost_poll_stop is called. */
+void vhost_poll_start(struct vhost_poll *poll, struct file *file)
+{
+ unsigned long mask;
+ mask = file->f_op->poll(file, &poll->table);
+ if (mask)
+ vhost_poll_wakeup(&poll->wait, 0, 0, (void *)mask);
+}
+
+/* Stop polling a file. After this function returns, it becomes safe to drop the
+ * file reference. You must also flush afterwards. */
+void vhost_poll_stop(struct vhost_poll *poll)
+{
+ remove_wait_queue(poll->wqh, &poll->wait);
+}
+
+/* Flush any work that has been scheduled. When calling this, don't hold any
+ * locks that are also used by the callback. */
+void vhost_poll_flush(struct vhost_poll *poll)
+{
+ flush_work(&poll->work);
+}
+
+void vhost_poll_queue(struct vhost_poll *poll)
+{
+ queue_work(vhost_workqueue, &poll->work);
+}
+
+static void vhost_vq_reset(struct vhost_dev *dev,
+ struct vhost_virtqueue *vq)
+{
+ vq->num = 1;
+ vq->desc = NULL;
+ vq->avail = NULL;
+ vq->used = NULL;
+ vq->last_avail_idx = 0;
+ vq->avail_idx = 0;
+ vq->last_used_idx = 0;
+ vq->used_flags = 0;
+ vq->used_flags = 0;
+ vq->log_used = false;
+ vq->log_addr = -1ull;
+ vq->hdr_size = 0;
+ vq->private_data = NULL;
+ vq->log_base = NULL;
+ vq->error_ctx = NULL;
+ vq->error = NULL;
+ vq->kick = NULL;
+ vq->call_ctx = NULL;
+ vq->call = NULL;
+}
+
+long vhost_dev_init(struct vhost_dev *dev,
+ struct vhost_virtqueue *vqs, int nvqs)
+{
+ int i;
+ dev->vqs = vqs;
+ dev->nvqs = nvqs;
+ mutex_init(&dev->mutex);
+ dev->log_ctx = NULL;
+ dev->log_file = NULL;
+ dev->memory = NULL;
+ dev->mm = NULL;
+
+ for (i = 0; i < dev->nvqs; ++i) {
+ dev->vqs[i].dev = dev;
+ mutex_init(&dev->vqs[i].mutex);
+ vhost_vq_reset(dev, dev->vqs + i);
+ if (dev->vqs[i].handle_kick)
+ vhost_poll_init(&dev->vqs[i].poll,
+ dev->vqs[i].handle_kick,
+ POLLIN);
+ }
+ return 0;
+}
+
+/* Caller should have device mutex */
+long vhost_dev_check_owner(struct vhost_dev *dev)
+{
+ /* Are you the owner? If not, I don't think you mean to do that */
+ return dev->mm == current->mm ? 0 : -EPERM;
+}
+
+/* Caller should have device mutex */
+static long vhost_dev_set_owner(struct vhost_dev *dev)
+{
+ /* Is there an owner already? */
+ if (dev->mm)
+ return -EBUSY;
+ /* No owner, become one */
+ dev->mm = get_task_mm(current);
+ return 0;
+}
+
+/* Caller should have device mutex */
+long vhost_dev_reset_owner(struct vhost_dev *dev)
+{
+ struct vhost_memory *memory;
+
+ /* Restore memory to default 1:1 mapping. */
+ memory = kmalloc(offsetof(struct vhost_memory, regions) +
+ 2 * sizeof *memory->regions, GFP_KERNEL);
+ if (!memory)
+ return -ENOMEM;
+
+ vhost_dev_cleanup(dev);
+
+ memory->nregions = 2;
+ memory->regions[0].guest_phys_addr = 1;
+ memory->regions[0].userspace_addr = 1;
+ memory->regions[0].memory_size = ~0ULL;
+ memory->regions[1].guest_phys_addr = 0;
+ memory->regions[1].userspace_addr = 0;
+ memory->regions[1].memory_size = 1;
+ dev->memory = memory;
+ return 0;
+}
+
+/* Caller should have device mutex */
+void vhost_dev_cleanup(struct vhost_dev *dev)
+{
+ int i;
+ for (i = 0; i < dev->nvqs; ++i) {
+ if (dev->vqs[i].kick && dev->vqs[i].handle_kick) {
+ vhost_poll_stop(&dev->vqs[i].poll);
+ vhost_poll_flush(&dev->vqs[i].poll);
+ }
+ if (dev->vqs[i].error_ctx)
+ eventfd_ctx_put(dev->vqs[i].error_ctx);
+ if (dev->vqs[i].error)
+ fput(dev->vqs[i].error);
+ if (dev->vqs[i].kick)
+ fput(dev->vqs[i].kick);
+ if (dev->vqs[i].call_ctx)
+ eventfd_ctx_put(dev->vqs[i].call_ctx);
+ if (dev->vqs[i].call)
+ fput(dev->vqs[i].call);
+ vhost_vq_reset(dev, dev->vqs + i);
+ }
+ if (dev->log_ctx)
+ eventfd_ctx_put(dev->log_ctx);
+ dev->log_ctx = NULL;
+ if (dev->log_file)
+ fput(dev->log_file);
+ dev->log_file = NULL;
+ /* No one will access memory at this point */
+ kfree(dev->memory);
+ dev->memory = NULL;
+ if (dev->mm)
+ mmput(dev->mm);
+ dev->mm = NULL;
+}
+
+static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
+{
+ struct vhost_memory mem, *newmem, *oldmem;
+ unsigned long size = offsetof(struct vhost_memory, regions);
+ long r;
+ r = copy_from_user(&mem, m, size);
+ if (r)
+ return r;
+ if (mem.padding)
+ return -EOPNOTSUPP;
+ if (mem.nregions > VHOST_MEMORY_MAX_NREGIONS)
+ return -E2BIG;
+ newmem = kmalloc(size + mem.nregions * sizeof *m->regions, GFP_KERNEL);
+ if (!newmem)
+ return -ENOMEM;
+
+ memcpy(newmem, &mem, size);
+ r = copy_from_user(newmem->regions, m->regions,
+ mem.nregions * sizeof *m->regions);
+ if (r) {
+ kfree(newmem);
+ return r;
+ }
+ oldmem = d->memory;
+ rcu_assign_pointer(d->memory, newmem);
+ synchronize_rcu();
+ kfree(oldmem);
+ return 0;
+}
+
+static int init_used(struct vhost_virtqueue *vq,
+ struct vring_used __user *used)
+{
+ int r = put_user(vq->used_flags, &used->flags);
+ if (r)
+ return r;
+ return get_user(vq->last_used_idx, &used->idx);
+}
+
+static long vhost_set_vring(struct vhost_dev *d, int ioctl, void __user *argp)
+{
+ struct file *eventfp, *filep = NULL,
+ *pollstart = NULL, *pollstop = NULL;
+ struct eventfd_ctx *ctx = NULL;
+ u32 __user *idxp = argp;
+ struct vhost_virtqueue *vq;
+ struct vhost_vring_state s;
+ struct vhost_vring_file f;
+ struct vhost_vring_addr a;
+ u32 idx;
+ long r;
+
+ r = get_user(idx, idxp);
+ if (r < 0)
+ return r;
+ if (idx > d->nvqs)
+ return -ENOBUFS;
+
+ vq = d->vqs + idx;
+
+ mutex_lock(&vq->mutex);
+
+ switch (ioctl) {
+ case VHOST_SET_VRING_NUM:
+ r = copy_from_user(&s, argp, sizeof s);
+ if (r < 0)
+ break;
+ if (!s.num || s.num > 0xffff || (s.num & (s.num - 1))) {
+ r = -EINVAL;
+ break;
+ }
+ vq->num = s.num;
+ break;
+ case VHOST_SET_VRING_BASE:
+ r = copy_from_user(&s, argp, sizeof s);
+ if (r < 0)
+ break;
+ if (s.num > 0xffff) {
+ r = -EINVAL;
+ break;
+ }
+ vq->last_avail_idx = s.num;
+ /* Forget the cached index value. */
+ vq->avail_idx = vq->last_avail_idx;
+ break;
+ case VHOST_GET_VRING_BASE:
+ s.index = idx;
+ s.num = vq->last_avail_idx;
+ r = copy_to_user(argp, &s, sizeof s);
+ break;
+ case VHOST_SET_VRING_ADDR:
+ r = copy_from_user(&a, argp, sizeof a);
+ if (r < 0)
+ break;
+ if (a.flags & ~(0x1 << VHOST_VRING_F_LOG)) {
+ r = -EOPNOTSUPP;
+ break;
+ }
+ if ((u64)(unsigned long)a.desc_user_addr != a.desc_user_addr ||
+ (u64)(unsigned long)a.used_user_addr != a.used_user_addr ||
+ (u64)(unsigned long)a.avail_user_addr != a.avail_user_addr) {
+ r = -EFAULT;
+ break;
+ }
+ if ((a.avail_user_addr & (sizeof *vq->avail->ring - 1)) ||
+ (a.used_user_addr & (sizeof *vq->used->ring - 1)) ||
+ (a.log_guest_addr & (sizeof *vq->used->ring - 1))) {
+ r = -EINVAL;
+ break;
+ }
+ r = init_used(vq, (struct vring_used __user *)a.used_user_addr);
+ if (r)
+ break;
+ vq->log_used = !!(a.flags & (0x1 << VHOST_VRING_F_LOG));
+ vq->desc = (void __user *)(unsigned long)a.desc_user_addr;
+ vq->avail = (void __user *)(unsigned long)a.avail_user_addr;
+ vq->log_addr = a.log_guest_addr;
+ vq->used = (void __user *)(unsigned long)a.used_user_addr;
+ break;
+ case VHOST_SET_VRING_KICK:
+ r = copy_from_user(&f, argp, sizeof f);
+ if (r < 0)
+ break;
+ eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd);
+ if (IS_ERR(eventfp))
+ return PTR_ERR(eventfp);
+ if (eventfp != vq->kick) {
+ pollstop = filep = vq->kick;
+ pollstart = vq->kick = eventfp;
+ } else
+ filep = eventfp;
+ break;
+ case VHOST_SET_VRING_CALL:
+ r = copy_from_user(&f, argp, sizeof f);
+ if (r < 0)
+ break;
+ eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd);
+ if (IS_ERR(eventfp))
+ return PTR_ERR(eventfp);
+ if (eventfp != vq->call) {
+ filep = vq->call;
+ ctx = vq->call_ctx;
+ vq->call = eventfp;
+ vq->call_ctx = eventfp ?
+ eventfd_ctx_fileget(eventfp) : NULL;
+ } else
+ filep = eventfp;
+ break;
+ case VHOST_SET_VRING_ERR:
+ r = copy_from_user(&f, argp, sizeof f);
+ if (r < 0)
+ break;
+ eventfp = f.fd == -1 ? NULL : eventfd_fget(f.fd);
+ if (IS_ERR(eventfp))
+ return PTR_ERR(eventfp);
+ if (eventfp != vq->error) {
+ filep = vq->error;
+ vq->error = eventfp;
+ ctx = vq->error_ctx;
+ vq->error_ctx = eventfp ?
+ eventfd_ctx_fileget(eventfp) : NULL;
+ } else
+ filep = eventfp;
+ break;
+ default:
+ r = -ENOIOCTLCMD;
+ }
+
+ if (pollstop && vq->handle_kick)
+ vhost_poll_stop(&vq->poll);
+
+ if (ctx)
+ eventfd_ctx_put(ctx);
+ if (filep)
+ fput(filep);
+
+ if (pollstart && vq->handle_kick)
+ vhost_poll_start(&vq->poll, vq->kick);
+
+ mutex_unlock(&vq->mutex);
+
+ if (pollstop && vq->handle_kick)
+ vhost_poll_flush(&vq->poll);
+ return r;
+}
+
+long vhost_dev_ioctl(struct vhost_dev *d, unsigned int ioctl, unsigned long arg)
+{
+ void __user *argp = (void __user *)arg;
+ struct file *eventfp, *filep = NULL;
+ struct eventfd_ctx *ctx = NULL;
+ u64 p;
+ long r;
+ int i, fd;
+
+ mutex_lock(&d->mutex);
+ /* If you are not the owner, you can become one */
+ if (ioctl == VHOST_SET_OWNER) {
+ r = vhost_dev_set_owner(d);
+ goto done;
+ }
+
+ /* You must be the owner to do anything else */
+ r = vhost_dev_check_owner(d);
+ if (r)
+ goto done;
+
+ switch (ioctl) {
+ case VHOST_SET_MEM_TABLE:
+ r = vhost_set_memory(d, argp);
+ break;
+ case VHOST_SET_LOG_BASE:
+ r = copy_from_user(&p, argp, sizeof p);
+ if (r < 0)
+ break;
+ if ((u64)(unsigned long)p != p) {
+ r = -EFAULT;
+ break;
+ }
+ for (i = 0; i < d->nvqs; ++i) {
+ mutex_lock(&d->vqs[i].mutex);
+ d->vqs[i].log_base = (void __user *)(unsigned long)p;
+ mutex_unlock(&d->vqs[i].mutex);
+ }
+ break;
+ case VHOST_SET_LOG_FD:
+ r = get_user(fd, (int __user *)argp);
+ if (r < 0)
+ break;
+ eventfp = fd == -1 ? NULL : eventfd_fget(fd);
+ if (IS_ERR(eventfp)) {
+ r = PTR_ERR(eventfp);
+ break;
+ }
+ if (eventfp != d->log_file) {
+ filep = d->log_file;
+ ctx = d->log_ctx;
+ d->log_ctx = eventfp ?
+ eventfd_ctx_fileget(eventfp) : NULL;
+ } else
+ filep = eventfp;
+ for (i = 0; i < d->nvqs; ++i) {
+ mutex_lock(&d->vqs[i].mutex);
+ d->vqs[i].log_ctx = d->log_ctx;
+ mutex_unlock(&d->vqs[i].mutex);
+ }
+ if (ctx)
+ eventfd_ctx_put(ctx);
+ if (filep)
+ fput(filep);
+ break;
+ default:
+ r = vhost_set_vring(d, ioctl, argp);
+ break;
+ }
+done:
+ mutex_unlock(&d->mutex);
+ return r;
+}
+
+static const struct vhost_memory_region *find_region(struct vhost_memory *mem,
+ __u64 addr, __u32 len)
+{
+ struct vhost_memory_region *reg;
+ int i;
+ /* linear search is not brilliant, but we really have on the order of 6
+ * regions in practice */
+ for (i = 0; i < mem->nregions; ++i) {
+ reg = mem->regions + i;
+ if (reg->guest_phys_addr <= addr &&
+ reg->guest_phys_addr + reg->memory_size - 1 >= addr)
+ return reg;
+ }
+ return NULL;
+}
+
+/* TODO: This is really inefficient. We need something like get_user()
+ * (instruction directly accesses the data, with an exception table entry
+ * returning -EFAULT). See Documentation/x86/exception-tables.txt.
+ */
+static int set_bit_to_user(int nr, void __user *addr)
+{
+ unsigned long log = (unsigned long)addr;
+ struct page *page;
+ void *base;
+ int bit = nr + (log % PAGE_SIZE) * 8;
+ int r;
+ r = get_user_pages_fast(log, 1, 1, &page);
+ if (r)
+ return r;
+ base = kmap_atomic(page, KM_USER0);
+ set_bit(bit, base);
+ kunmap_atomic(base, KM_USER0);
+ set_page_dirty_lock(page);
+ put_page(page);
+ return 0;
+}
+
+static int log_write(void __user *log_base,
+ u64 write_address, u64 write_length)
+{
+ int r;
+ if (!write_length)
+ return 0;
+ write_address /= VHOST_PAGE_SIZE;
+ for (;;) {
+ u64 base = (u64)(unsigned long)log_base;
+ u64 log = base + write_address / 8;
+ int bit = write_address % 8;
+ if ((u64)(unsigned long)log != log)
+ return -EFAULT;
+ r = set_bit_to_user(bit, (void __user *)(unsigned long)log);
+ if (r < 0)
+ return r;
+ if (write_length <= VHOST_PAGE_SIZE)
+ break;
+ write_length -= VHOST_PAGE_SIZE;
+ write_address += VHOST_PAGE_SIZE;
+ }
+ return r;
+}
+
+int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
+ unsigned int log_num, u64 len)
+{
+ int i, r;
+
+ /* Make sure data written is seen before log. */
+ wmb();
+ for (i = 0; i < log_num; ++i) {
+ u64 l = min(log[i].len, len);
+ r = log_write(vq->log_base, log[i].addr, l);
+ if (r < 0)
+ return r;
+ len -= l;
+ if (!len)
+ return 0;
+ }
+ if (vq->log_ctx)
+ eventfd_signal(vq->log_ctx, 1);
+ /* Length written exceeds what we have stored. This is a bug. */
+ BUG();
+ return 0;
+}
+
+int translate_desc(struct vhost_dev *dev, u64 addr, u32 len,
+ struct iovec iov[], int iov_size)
+{
+ const struct vhost_memory_region *reg;
+ struct vhost_memory *mem;
+ struct iovec *_iov;
+ u64 s = 0;
+ int ret = 0;
+
+ rcu_read_lock();
+
+ mem = rcu_dereference(dev->memory);
+ while ((u64)len > s) {
+ u64 size;
+ if (ret >= iov_size) {
+ ret = -ENOBUFS;
+ break;
+ }
+ reg = find_region(mem, addr, len);
+ if (!reg) {
+ ret = -EFAULT;
+ break;
+ }
+ _iov = iov + ret;
+ size = reg->memory_size - addr + reg->guest_phys_addr;
+ _iov->iov_len = min((u64)len, size);
+ _iov->iov_base = (void *)(unsigned long)
+ (reg->userspace_addr + addr - reg->guest_phys_addr);
+ s += size;
+ addr += size;
+ ++ret;
+ }
+
+ rcu_read_unlock();
+ return ret;
+}
+
+/* Each buffer in the virtqueues is actually a chain of descriptors. This
+ * function returns the next descriptor in the chain,
+ * or -1U if we're at the end. */
+static unsigned next_desc(struct vring_desc *desc)
+{
+ unsigned int next;
+
+ /* If this descriptor says it doesn't chain, we're done. */
+ if (!(desc->flags & VRING_DESC_F_NEXT))
+ return -1U;
+
+ /* Check they're not leading us off end of descriptors. */
+ next = desc->next;
+ /* Make sure compiler knows to grab that: we don't want it changing! */
+ /* We will use the result as an index in an array, so most
+ * architectures only need a compiler barrier here. */
+ read_barrier_depends();
+
+ return next;
+}
+
+static unsigned get_indirect(struct vhost_dev *dev, struct vhost_virtqueue *vq,
+ struct iovec iov[], unsigned int iov_size,
+ unsigned int *out_num, unsigned int *in_num,
+ struct vhost_log *log, unsigned int *log_num,
+ struct vring_desc *indirect)
+{
+ struct vring_desc desc;
+ unsigned int i = 0, count, found = 0;
+ int ret;
+
+ /* Sanity check */
+ if (indirect->len % sizeof desc) {
+ vq_err(vq, "Invalid length in indirect descriptor: "
+ "len 0x%llx not multiple of 0x%zx\n",
+ (unsigned long long)indirect->len,
+ sizeof desc);
+ return -EINVAL;
+ }
+
+ ret = translate_desc(dev, indirect->addr, indirect->len, vq->indirect,
+ ARRAY_SIZE(vq->indirect));
+ if (ret < 0) {
+ vq_err(vq, "Translation failure %d in indirect.\n", ret);
+ return ret;
+ }
+
+ /* We will use the result as an address to read from, so most
+ * architectures only need a compiler barrier here. */
+ read_barrier_depends();
+
+ count = indirect->len / sizeof desc;
+ /* Buffers are chained via a 16 bit next field, so
+ * we can have at most 2^16 of these. */
+ if (count > USHORT_MAX + 1) {
+ vq_err(vq, "Indirect buffer length too big: %d\n",
+ indirect->len);
+ return -E2BIG;
+ }
+
+ do {
+ unsigned iov_count = *in_num + *out_num;
+ if (++found > count) {
+ vq_err(vq, "Loop detected: last one at %u "
+ "indirect size %u\n",
+ i, count);
+ return -EINVAL;
+ }
+ if (memcpy_fromiovec((unsigned char *)&desc, vq->indirect,
+ sizeof desc)) {
+ vq_err(vq, "Failed indirect descriptor: idx %d, %zx\n",
+ i, (size_t)indirect->addr + i * sizeof desc);
+ return -EINVAL;
+ }
+ if (desc.flags & VRING_DESC_F_INDIRECT) {
+ vq_err(vq, "Nested indirect descriptor: idx %d, %zx\n",
+ i, (size_t)indirect->addr + i * sizeof desc);
+ return -EINVAL;
+ }
+
+ ret = translate_desc(dev, desc.addr, desc.len, iov + iov_count,
+ iov_size - iov_count);
+ if (ret < 0) {
+ vq_err(vq, "Translation failure %d indirect idx %d\n",
+ ret, i);
+ return ret;
+ }
+ /* If this is an input descriptor, increment that count. */
+ if (desc.flags & VRING_DESC_F_WRITE) {
+ *in_num += ret;
+ if (unlikely(log)) {
+ log[*log_num].addr = desc.addr;
+ log[*log_num].len = desc.len;
+ ++*log_num;
+ }
+ } else {
+ /* If it's an output descriptor, they're all supposed
+ * to come before any input descriptors. */
+ if (*in_num) {
+ vq_err(vq, "Indirect descriptor "
+ "has out after in: idx %d\n", i);
+ return -EINVAL;
+ }
+ *out_num += ret;
+ }
+ } while ((i = next_desc(&desc)) != -1);
+ return 0;
+}
+
+/* This looks in the virtqueue and for the first available buffer, and converts
+ * it to an iovec for convenient access. Since descriptors consist of some
+ * number of output then some number of input descriptors, it's actually two
+ * iovecs, but we pack them into one and note how many of each there were.
+ *
+ * This function returns the descriptor number found, or vq->num (which
+ * is never a valid descriptor number) if none was found. */
+unsigned vhost_get_vq_desc(struct vhost_dev *dev, struct vhost_virtqueue *vq,
+ struct iovec iov[], unsigned int iov_size,
+ unsigned int *out_num, unsigned int *in_num,
+ struct vhost_log *log, unsigned int *log_num)
+{
+ struct vring_desc desc;
+ unsigned int i, head, found = 0;
+ u16 last_avail_idx;
+ int ret;
+
+ /* Check it isn't doing very strange things with descriptor numbers. */
+ last_avail_idx = vq->last_avail_idx;
+ if (get_user(vq->avail_idx, &vq->avail->idx)) {
+ vq_err(vq, "Failed to access avail idx at %p\n",
+ &vq->avail->idx);
+ return vq->num;
+ }
+
+ if ((u16)(vq->avail_idx - last_avail_idx) > vq->num) {
+ vq_err(vq, "Guest moved used index from %u to %u",
+ last_avail_idx, vq->avail_idx);
+ return vq->num;
+ }
+
+ /* If there's nothing new since last we looked, return invalid. */
+ if (vq->avail_idx == last_avail_idx)
+ return vq->num;
+
+ /* Only get avail ring entries after they have been exposed by guest. */
+ rmb();
+
+ /* Grab the next descriptor number they're advertising, and increment
+ * the index we've seen. */
+ if (get_user(head, &vq->avail->ring[last_avail_idx % vq->num])) {
+ vq_err(vq, "Failed to read head: idx %d address %p\n",
+ last_avail_idx,
+ &vq->avail->ring[last_avail_idx % vq->num]);
+ return vq->num;
+ }
+
+ /* If their number is silly, that's an error. */
+ if (head >= vq->num) {
+ vq_err(vq, "Guest says index %u > %u is available",
+ head, vq->num);
+ return vq->num;
+ }
+
+ /* When we start there are none of either input nor output. */
+ *out_num = *in_num = 0;
+ if (unlikely(log))
+ *log_num = 0;
+
+ i = head;
+ do {
+ unsigned iov_count = *in_num + *out_num;
+ if (i >= vq->num) {
+ vq_err(vq, "Desc index is %u > %u, head = %u",
+ i, vq->num, head);
+ return vq->num;
+ }
+ if (++found > vq->num) {
+ vq_err(vq, "Loop detected: last one at %u "
+ "vq size %u head %u\n",
+ i, vq->num, head);
+ return vq->num;
+ }
+ ret = copy_from_user(&desc, vq->desc + i, sizeof desc);
+ if (ret) {
+ vq_err(vq, "Failed to get descriptor: idx %d addr %p\n",
+ i, vq->desc + i);
+ return vq->num;
+ }
+ if (desc.flags & VRING_DESC_F_INDIRECT) {
+ ret = get_indirect(dev, vq, iov, iov_size,
+ out_num, in_num,
+ log, log_num, &desc);
+ if (ret < 0) {
+ vq_err(vq, "Failure detected "
+ "in indirect descriptor at idx %d\n", i);
+ return vq->num;
+ }
+ continue;
+ }
+
+ ret = translate_desc(dev, desc.addr, desc.len, iov + iov_count,
+ iov_size - iov_count);
+ if (ret < 0) {
+ vq_err(vq, "Translation failure %d descriptor idx %d\n",
+ ret, i);
+ return vq->num;
+ }
+ if (desc.flags & VRING_DESC_F_WRITE) {
+ /* If this is an input descriptor,
+ * increment that count. */
+ *in_num += ret;
+ if (unlikely(log)) {
+ log[*log_num].addr = desc.addr;
+ log[*log_num].len = desc.len;
+ ++*log_num;
+ }
+ } else {
+ /* If it's an output descriptor, they're all supposed
+ * to come before any input descriptors. */
+ if (*in_num) {
+ vq_err(vq, "Descriptor has out after in: "
+ "idx %d\n", i);
+ return vq->num;
+ }
+ *out_num += ret;
+ }
+ } while ((i = next_desc(&desc)) != -1);
+
+ /* On success, increment avail index. */
+ vq->last_avail_idx++;
+ return head;
+}
+
+/* Reverse the effect of vhost_get_vq_desc. Useful for error handling. */
+void vhost_discard_vq_desc(struct vhost_virtqueue *vq)
+{
+ vq->last_avail_idx--;
+}
+
+/* After we've used one of their buffers, we tell them about it. We'll then
+ * want to notify the guest, using eventfd. */
+int vhost_add_used(struct vhost_virtqueue *vq, unsigned int head, int len)
+{
+ struct vring_used_elem *used;
+
+ /* The virtqueue contains a ring of used buffers. Get a pointer to the
+ * next entry in that used ring. */
+ used = &vq->used->ring[vq->last_used_idx % vq->num];
+ if (put_user(head, &used->id)) {
+ vq_err(vq, "Failed to write used id");
+ return -EFAULT;
+ }
+ if (put_user(len, &used->len)) {
+ vq_err(vq, "Failed to write used len");
+ return -EFAULT;
+ }
+ /* Make sure buffer is written before we update index. */
+ wmb();
+ if (put_user(vq->last_used_idx + 1, &vq->used->idx)) {
+ vq_err(vq, "Failed to increment used idx");
+ return -EFAULT;
+ }
+ if (unlikely(vq->log_used)) {
+ /* Make sure data is seen before log. */
+ wmb();
+ log_write(vq->log_base, vq->log_addr + sizeof *vq->used->ring *
+ (vq->last_used_idx % vq->num),
+ sizeof *vq->used->ring);
+ log_write(vq->log_base, vq->log_addr, sizeof *vq->used->ring);
+ if (vq->log_ctx)
+ eventfd_signal(vq->log_ctx, 1);
+ }
+ vq->last_used_idx++;
+ return 0;
+}
+
+/* This actually signals the guest, using eventfd. */
+void vhost_signal(struct vhost_dev *dev, struct vhost_virtqueue *vq)
+{
+ __u16 flags = 0;
+ if (get_user(flags, &vq->avail->flags)) {
+ vq_err(vq, "Failed to get flags");
+ return;
+ }
+
+ /* If they don't want an interrupt, don't signal, unless empty. */
+ if ((flags & VRING_AVAIL_F_NO_INTERRUPT) &&
+ (vq->avail_idx != vq->last_avail_idx ||
+ !vhost_has_feature(dev, VIRTIO_F_NOTIFY_ON_EMPTY)))
+ return;
+
+ /* Signal the Guest tell them we used something up. */
+ if (vq->call_ctx)
+ eventfd_signal(vq->call_ctx, 1);
+}
+
+/* And here's the combo meal deal. Supersize me! */
+void vhost_add_used_and_signal(struct vhost_dev *dev,
+ struct vhost_virtqueue *vq,
+ unsigned int head, int len)
+{
+ vhost_add_used(vq, head, len);
+ vhost_signal(dev, vq);
+}
+
+/* OK, now we need to know about added descriptors. */
+bool vhost_enable_notify(struct vhost_virtqueue *vq)
+{
+ u16 avail_idx;
+ int r;
+ if (!(vq->used_flags & VRING_USED_F_NO_NOTIFY))
+ return false;
+ vq->used_flags &= ~VRING_USED_F_NO_NOTIFY;
+ r = put_user(vq->used_flags, &vq->used->flags);
+ if (r) {
+ vq_err(vq, "Failed to enable notification at %p: %d\n",
+ &vq->used->flags, r);
+ return false;
+ }
+ /* They could have slipped one in as we were doing that: make
+ * sure it's written, then check again. */
+ mb();
+ r = get_user(avail_idx, &vq->avail->idx);
+ if (r) {
+ vq_err(vq, "Failed to check avail idx at %p: %d\n",
+ &vq->avail->idx, r);
+ return false;
+ }
+
+ return avail_idx != vq->last_avail_idx;
+}
+
+/* We don't need to be notified again. */
+void vhost_disable_notify(struct vhost_virtqueue *vq)
+{
+ int r;
+ if (vq->used_flags & VRING_USED_F_NO_NOTIFY)
+ return;
+ vq->used_flags |= VRING_USED_F_NO_NOTIFY;
+ r = put_user(vq->used_flags, &vq->used->flags);
+ if (r)
+ vq_err(vq, "Failed to enable notification at %p: %d\n",
+ &vq->used->flags, r);
+}
+
+int vhost_init(void)
+{
+ vhost_workqueue = create_singlethread_workqueue("vhost");
+ if (!vhost_workqueue)
+ return -ENOMEM;
+ return 0;
+}
+
+void vhost_cleanup(void)
+{
+ destroy_workqueue(vhost_workqueue);
+}
diff --git a/drivers/vhost/vhost.h b/drivers/vhost/vhost.h
new file mode 100644
index 0000000..d1f0453
--- /dev/null
+++ b/drivers/vhost/vhost.h
@@ -0,0 +1,159 @@
+#ifndef _VHOST_H
+#define _VHOST_H
+
+#include <linux/eventfd.h>
+#include <linux/vhost.h>
+#include <linux/mm.h>
+#include <linux/mutex.h>
+#include <linux/workqueue.h>
+#include <linux/poll.h>
+#include <linux/file.h>
+#include <linux/skbuff.h>
+#include <linux/uio.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ring.h>
+
+struct vhost_device;
+
+enum {
+ /* Enough place for all fragments, head, and virtio net header. */
+ VHOST_NET_MAX_SG = MAX_SKB_FRAGS + 2,
+};
+
+/* Poll a file (eventfd or socket) */
+/* Note: there's nothing vhost specific about this structure. */
+struct vhost_poll {
+ poll_table table;
+ wait_queue_head_t *wqh;
+ wait_queue_t wait;
+ /* struct which will handle all actual work. */
+ struct work_struct work;
+ unsigned long mask;
+};
+
+void vhost_poll_init(struct vhost_poll *poll, work_func_t func,
+ unsigned long mask);
+void vhost_poll_start(struct vhost_poll *poll, struct file *file);
+void vhost_poll_stop(struct vhost_poll *poll);
+void vhost_poll_flush(struct vhost_poll *poll);
+void vhost_poll_queue(struct vhost_poll *poll);
+
+struct vhost_log {
+ u64 addr;
+ u64 len;
+};
+
+/* The virtqueue structure describes a queue attached to a device. */
+struct vhost_virtqueue {
+ struct vhost_dev *dev;
+
+ /* The actual ring of buffers. */
+ struct mutex mutex;
+ unsigned int num;
+ struct vring_desc __user *desc;
+ struct vring_avail __user *avail;
+ struct vring_used __user *used;
+ struct file *kick;
+ struct file *call;
+ struct file *error;
+ struct eventfd_ctx *call_ctx;
+ struct eventfd_ctx *error_ctx;
+ struct eventfd_ctx *log_ctx;
+
+ struct vhost_poll poll;
+
+ /* The routine to call when the Guest pings us, or timeout. */
+ work_func_t handle_kick;
+
+ /* Last available index we saw. */
+ u16 last_avail_idx;
+
+ /* Caches available index value from user. */
+ u16 avail_idx;
+
+ /* Last index we used. */
+ u16 last_used_idx;
+
+ /* Used flags */
+ u16 used_flags;
+
+ /* Log writes to used structure. */
+ bool log_used;
+ u64 log_addr;
+
+ struct iovec indirect[VHOST_NET_MAX_SG];
+ struct iovec iov[VHOST_NET_MAX_SG];
+ struct iovec hdr[VHOST_NET_MAX_SG];
+ size_t hdr_size;
+ /* We use a kind of RCU to access private pointer.
+ * All readers access it from workqueue, which makes it possible to
+ * flush the workqueue instead of synchronize_rcu. Therefore readers do
+ * not need to call rcu_read_lock/rcu_read_unlock: the beginning of
+ * work item execution acts instead of rcu_read_lock() and the end of
+ * work item execution acts instead of rcu_read_lock().
+ * Writers use virtqueue mutex. */
+ void *private_data;
+ /* Log write descriptors */
+ void __user *log_base;
+ struct vhost_log log[VHOST_NET_MAX_SG];
+};
+
+struct vhost_dev {
+ /* Readers use RCU to access memory table pointer
+ * log base pointer and features.
+ * Writers use mutex below.*/
+ struct vhost_memory *memory;
+ struct mm_struct *mm;
+ struct mutex mutex;
+ unsigned acked_features;
+ struct vhost_virtqueue *vqs;
+ int nvqs;
+ struct file *log_file;
+ struct eventfd_ctx *log_ctx;
+};
+
+long vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue *vqs, int nvqs);
+long vhost_dev_check_owner(struct vhost_dev *);
+long vhost_dev_reset_owner(struct vhost_dev *);
+void vhost_dev_cleanup(struct vhost_dev *);
+long vhost_dev_ioctl(struct vhost_dev *, unsigned int ioctl, unsigned long arg);
+
+unsigned vhost_get_vq_desc(struct vhost_dev *, struct vhost_virtqueue *,
+ struct iovec iov[], unsigned int iov_count,
+ unsigned int *out_num, unsigned int *in_num,
+ struct vhost_log *log, unsigned int *log_num);
+void vhost_discard_vq_desc(struct vhost_virtqueue *);
+
+int vhost_add_used(struct vhost_virtqueue *, unsigned int head, int len);
+void vhost_signal(struct vhost_dev *, struct vhost_virtqueue *);
+void vhost_add_used_and_signal(struct vhost_dev *, struct vhost_virtqueue *,
+ unsigned int head, int len);
+void vhost_disable_notify(struct vhost_virtqueue *);
+bool vhost_enable_notify(struct vhost_virtqueue *);
+
+int vhost_log_write(struct vhost_virtqueue *vq, struct vhost_log *log,
+ unsigned int log_num, u64 len);
+
+int vhost_init(void);
+void vhost_cleanup(void);
+
+#define vq_err(vq, fmt, ...) do { \
+ pr_debug(pr_fmt(fmt), ##__VA_ARGS__); \
+ if ((vq)->error_ctx) \
+ eventfd_signal((vq)->error_ctx, 1);\
+ } while (0)
+
+enum {
+ VHOST_FEATURES = (1 << VIRTIO_F_NOTIFY_ON_EMPTY) |
+ (1 << VIRTIO_RING_F_INDIRECT_DESC) |
+ (1 << VHOST_F_LOG_ALL) |
+ (1 << VHOST_NET_F_VIRTIO_NET_HDR),
+};
+
+static inline int vhost_has_feature(struct vhost_dev *dev, int bit)
+{
+ unsigned acked_features = rcu_dereference(dev->acked_features);
+ return acked_features & (1 << bit);
+}
+
+#endif
diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index 1feed71..e210194 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -361,6 +361,7 @@ unifdef-y += uio.h
unifdef-y += unistd.h
unifdef-y += usbdevice_fs.h
unifdef-y += utsname.h
+unifdef-y += vhost.h
unifdef-y += videodev2.h
unifdef-y += videodev.h
unifdef-y += virtio_config.h
diff --git a/include/linux/miscdevice.h b/include/linux/miscdevice.h
index adaf3c1..8b5f7cc 100644
--- a/include/linux/miscdevice.h
+++ b/include/linux/miscdevice.h
@@ -30,6 +30,7 @@
#define HPET_MINOR 228
#define FUSE_MINOR 229
#define KVM_MINOR 232
+#define VHOST_NET_MINOR 233
#define MISC_DYNAMIC_MINOR 255
struct device;
diff --git a/include/linux/vhost.h b/include/linux/vhost.h
new file mode 100644
index 0000000..e847f1e
--- /dev/null
+++ b/include/linux/vhost.h
@@ -0,0 +1,130 @@
+#ifndef _LINUX_VHOST_H
+#define _LINUX_VHOST_H
+/* Userspace interface for in-kernel virtio accelerators. */
+
+/* vhost is used to reduce the number of system calls involved in virtio.
+ *
+ * Existing virtio net code is used in the guest without modification.
+ *
+ * This header includes interface used by userspace hypervisor for
+ * device configuration.
+ */
+
+#include <linux/types.h>
+#include <linux/compiler.h>
+#include <linux/ioctl.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ring.h>
+
+struct vhost_vring_state {
+ unsigned int index;
+ unsigned int num;
+};
+
+struct vhost_vring_file {
+ unsigned int index;
+ int fd; /* Pass -1 to unbind from file. */
+
+};
+
+struct vhost_vring_addr {
+ unsigned int index;
+ /* Option flags. */
+ unsigned int flags;
+ /* Flag values: */
+ /* Whether log address is valid. If set enables logging. */
+#define VHOST_VRING_F_LOG 0
+
+ /* Start of array of descriptors (virtually contiguous) */
+ __u64 desc_user_addr;
+ /* Used structure address. Must be 32 bit aligned */
+ __u64 used_user_addr;
+ /* Available structure address. Must be 16 bit aligned */
+ __u64 avail_user_addr;
+ /* Logging support. */
+ /* Log writes to used structure, at offset calculated from specified
+ * address. Address must be 32 bit aligned. */
+ __u64 log_guest_addr;
+};
+
+struct vhost_memory_region {
+ __u64 guest_phys_addr;
+ __u64 memory_size; /* bytes */
+ __u64 userspace_addr;
+ __u64 flags_padding; /* No flags are currently specified. */
+};
+
+/* All region addresses and sizes must be 4K aligned. */
+#define VHOST_PAGE_SIZE 0x1000
+
+struct vhost_memory {
+ __u32 nregions;
+ __u32 padding;
+ struct vhost_memory_region regions[0];
+};
+
+/* ioctls */
+
+#define VHOST_VIRTIO 0xAF
+
+/* Features bitmask for forward compatibility. Transport bits are used for
+ * vhost specific features. */
+#define VHOST_GET_FEATURES _IOR(VHOST_VIRTIO, 0x00, __u64)
+#define VHOST_SET_FEATURES _IOW(VHOST_VIRTIO, 0x00, __u64)
+
+/* Set current process as the (exclusive) owner of this file descriptor. This
+ * must be called before any other vhost command. Further calls to
+ * VHOST_OWNER_SET fail until VHOST_OWNER_RESET is called. */
+#define VHOST_SET_OWNER _IO(VHOST_VIRTIO, 0x01)
+/* Give up ownership, and reset the device to default values.
+ * Allows subsequent call to VHOST_OWNER_SET to succeed. */
+#define VHOST_RESET_OWNER _IO(VHOST_VIRTIO, 0x02)
+
+/* Set up/modify memory layout */
+#define VHOST_SET_MEM_TABLE _IOW(VHOST_VIRTIO, 0x03, struct vhost_memory)
+
+/* Write logging setup. */
+/* Memory writes can optionally be logged by setting bit at an offset
+ * (calculated from the physical address) from specified log base.
+ * The bit is set using an atomic 32 bit operation. */
+/* Set base address for logging. */
+#define VHOST_SET_LOG_BASE _IOW(VHOST_VIRTIO, 0x04, __u64)
+/* Specify an eventfd file descriptor to signal on log write. */
+#define VHOST_SET_LOG_FD _IOW(VHOST_VIRTIO, 0x07, int)
+
+/* Ring setup. */
+/* Set number of descriptors in ring. This parameter can not
+ * be modified while ring is running (bound to a device). */
+#define VHOST_SET_VRING_NUM _IOW(VHOST_VIRTIO, 0x10, struct vhost_vring_state)
+/* Set addresses for the ring. */
+#define VHOST_SET_VRING_ADDR _IOW(VHOST_VIRTIO, 0x11, struct vhost_vring_addr)
+/* Base value where queue looks for available descriptors */
+#define VHOST_SET_VRING_BASE _IOW(VHOST_VIRTIO, 0x12, struct vhost_vring_state)
+/* Get accessor: reads index, writes value in num */
+#define VHOST_GET_VRING_BASE _IOWR(VHOST_VIRTIO, 0x12, struct vhost_vring_state)
+
+/* The following ioctls use eventfd file descriptors to signal and poll
+ * for events. */
+
+/* Set eventfd to poll for added buffers */
+#define VHOST_SET_VRING_KICK _IOW(VHOST_VIRTIO, 0x20, struct vhost_vring_file)
+/* Set eventfd to signal when buffers have beed used */
+#define VHOST_SET_VRING_CALL _IOW(VHOST_VIRTIO, 0x21, struct vhost_vring_file)
+/* Set eventfd to signal an error */
+#define VHOST_SET_VRING_ERR _IOW(VHOST_VIRTIO, 0x22, struct vhost_vring_file)
+
+/* VHOST_NET specific defines */
+
+/* Attach virtio net ring to a raw socket, or tap device.
+ * The socket must be already bound to an ethernet device, this device will be
+ * used for transmit. Pass fd -1 to unbind from the socket and the transmit
+ * device. This can be used to stop the ring (e.g. for migration). */
+#define VHOST_NET_SET_BACKEND _IOW(VHOST_VIRTIO, 0x30, struct vhost_vring_file)
+
+/* Feature bits */
+/* Log all write descriptors. Can be changed while device is active. */
+#define VHOST_F_LOG_ALL 26
+/* vhost-net should add virtio_net_hdr for RX, and strip for TX packets. */
+#define VHOST_NET_F_VIRTIO_NET_HDR 27
+
+#endif
--
1.6.5.2.143.g8cc62
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply related
* Re: RFC: ethtool support for n-tuple filter programming
From: Caitlin Bestler @ 2009-11-09 17:23 UTC (permalink / raw)
To: Rick Jones; +Cc: Bill Fink, Peter P Waskiewicz Jr, netdev@vger.kernel.org
In-Reply-To: <4AF6029F.6020403@hp.com>
On Sat, Nov 7, 2009 at 3:28 PM, Rick Jones <rick.jones2@hp.com> wrote:
>
> At the risk of typing words into someone's keyboard, I interpreted it as
> suggesting using the filtering language of netfilter or something similar,
> not necessarily netfilter itself?
>
Correct, a netfilter-friendly interface to the driver could be invoked by
lower-overhead entities that netfilter and the driver would not care.
However the real goal would be to still use netfilter, which would become
a low-overhead entity if it could delegate 90% of the rules it enforced to
smart hardware.
The fundamental suggestion is to start with a filter specification that is
clearly too rich for any Ethernet device, and let the Ethernet devices
decide how quickly they want to catch up. As opposed to standardizing
how smart a smart Ethernet device is and potentially leaving some hardware
capabilities made inaccessible.
I'll point out that once you assume an Ethernet Device is capable of doing
TCP/UDP checksum offload and LSO/LRO then clearly you have recognized
that it is an L4 aware device. Designing its filtering rules as though it were
an L2-only device does not allow it to take advantage of the L4 parsing that
many/most Ethernet NICs already do.
^ permalink raw reply
* Re: RFC: ethtool support for n-tuple filter programming
From: Patrick McHardy @ 2009-11-09 17:36 UTC (permalink / raw)
To: Caitlin Bestler
Cc: Rick Jones, Bill Fink, Peter P Waskiewicz Jr,
netdev@vger.kernel.org
In-Reply-To: <469958e00911090923s7688bb78i18c7102195be6f9b@mail.gmail.com>
Caitlin Bestler wrote:
> On Sat, Nov 7, 2009 at 3:28 PM, Rick Jones <rick.jones2@hp.com> wrote:
>> At the risk of typing words into someone's keyboard, I interpreted it as
>> suggesting using the filtering language of netfilter or something similar,
>> not necessarily netfilter itself?
>>
>
> Correct, a netfilter-friendly interface to the driver could be invoked by
> lower-overhead entities that netfilter and the driver would not care.
>
> However the real goal would be to still use netfilter, which would become
> a low-overhead entity if it could delegate 90% of the rules it enforced to
> smart hardware.
That's not possible in a compatible fashion with ip_tables because of
counters, logging, rules affecting traffic from multiple interfaces,
targets not supported in hardware (which I presume will simply be
"DROP") etc.
Counters are actually the worst feature standing in the way of this,
but even without them, you could usually only offload the first n
dropping rules that don't use any features not supported in hardware
and only affect the specific interface. Any "ACCEPT" rule is most
likely followed by further drop rules, so packets actually need to
hit those rules in software to exit table processing.
It gets even worse if you consider ingress TC actions directing the
packets to different interfaces or mangling them.
> The fundamental suggestion is to start with a filter specification that is
> clearly too rich for any Ethernet device, and let the Ethernet devices
> decide how quickly they want to catch up. As opposed to standardizing
> how smart a smart Ethernet device is and potentially leaving some hardware
> capabilities made inaccessible.
>
> I'll point out that once you assume an Ethernet Device is capable of doing
> TCP/UDP checksum offload and LSO/LRO then clearly you have recognized
> that it is an L4 aware device. Designing its filtering rules as though it were
> an L2-only device does not allow it to take advantage of the L4 parsing that
> many/most Ethernet NICs already do.
^ permalink raw reply
* [PATCH] ipv6: Allow inet6_dump_addr() to handle more than 64 addresses
From: Eric Dumazet @ 2009-11-09 17:40 UTC (permalink / raw)
To: David S. Miller; +Cc: Linux Netdev List
Apparently, inet6_dump_addr() is not able to handle more than
64 ipv6 addresses per device. We must break from inner loops
in case skb is full, or else cursor is put at the end of list.
Signed-off-by: Eric Dumazet <eric.dumazet@gmail.com>
---
net/ipv6/addrconf.c | 6 ++++++
1 files changed, 6 insertions(+)
diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
index 024bba3..1b072fe 100644
--- a/net/ipv6/addrconf.c
+++ b/net/ipv6/addrconf.c
@@ -3519,6 +3519,8 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
cb->nlh->nlmsg_seq,
RTM_NEWADDR,
NLM_F_MULTI);
+ if (err <= 0)
+ break;
}
break;
case MULTICAST_ADDR:
@@ -3532,6 +3534,8 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
cb->nlh->nlmsg_seq,
RTM_GETMULTICAST,
NLM_F_MULTI);
+ if (err <= 0)
+ break;
}
break;
case ANYCAST_ADDR:
@@ -3545,6 +3549,8 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
cb->nlh->nlmsg_seq,
RTM_GETANYCAST,
NLM_F_MULTI);
+ if (err <= 0)
+ break;
}
break;
default:
^ permalink raw reply related
* Re: [RFC] netlink: add socket destruction notification
From: Johannes Berg @ 2009-11-09 17:46 UTC (permalink / raw)
To: Patrick McHardy; +Cc: netdev, Jouni Malinen, Thomas Graf
In-Reply-To: <4AF849F6.4050308@trash.net>
[-- Attachment #1: Type: text/plain, Size: 687 bytes --]
On Mon, 2009-11-09 at 17:57 +0100, Patrick McHardy wrote:
> > Oh? So on which sockets can I rely on it being used? After sending at
> > least one unicast message into the kernel? This seems to depend on pid
> > being assigned -- when is that?
>
> All unicast sockets that have either manually or automatically
> bound. Automatic binding happens when sending the first message
> or when calling connect().
>
> Before that, your code can't know of the sockets existance, so
> I guess this should be fine.
Ah, yes, of course... that's part of the boilerplate code to use generic
netlink so I always forget about what exactly is going on there :)
Thanks!
johannes
[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 801 bytes --]
^ permalink raw reply
* pull request: wireless-next-2.6 2009-11-09
From: John W. Linville @ 2009-11-09 18:30 UTC (permalink / raw)
To: davme-fT/PcQaiUtIeIZ0/mPfg9Q
Cc: linux-wireless-u79uwXL29TY76Z2rM5mHXA,
netdev-u79uwXL29TY76Z2rM5mHXA
Dave,
Another big batch of patches intended for 2.6.33... Among the usual
suspects are big updates for ath9k, iwlwifi, wl1271, mwl8k, and (especially)
rt2x00. Also included are some patches to move some old pre-802.11
drivers over to staging, and a number of mac80211 updates.
Please let me know if there are problems!
Thanks,
John
---
Individual patches are available here:
http://www.kernel.org/pub/linux/kernel/people/linville/wireless-next-2.6/
---
The following changes since commit 29906f6a427d2004a515ebbcdc7b28bae8f6c19c:
Patrick McHardy (1):
vlan: cleanup multiple unregistrations
are available in the git repository at:
git://git.kernel.org/pub/scm/linux/kernel/git/linville/wireless-next-2.6.git master
Andrey Yurovsky (1):
libertas: remove internal buffers from GSPI driver
Bartlomiej Zolnierkiewicz (41):
rt2800usb: make Kconfig help entry more helpful
rt2800pci: make Kconfig help entry more helpful
rt2800usb: fix rt2800usb_rfcsr_read()
rt2800pci: fix crypto in TX frame
rt2800pci: fix comment about register access
rt2800pci: fix comment about IV/EIV fields
rt2x00: fix rt2x00usb_register_read() comment
rt2800usb: use rt2x00usb_register_multiwrite() to set key entries
rt2800usb: fix comments in rt2800usb.h
rt2x00: remove needless ifdefs from rt2x00leds.h
rt2800usb: add rt2800_register_[read,write]() wrappers
rt2800pci: add rt2800_register_[read,write]() wrappers
rt2800usb: add rt2800_register_multi[read,write]() wrappers
rt2800pci: add rt2800_register_multi[read,write]() wrappers
rt2800usb: add rt2800_regbusy_read() wrapper
rt2800pci: add rt2800_regbusy_read() wrapper
rt2800usb: add rt2800_bbp_[read,write]() wrappers
rt2800pci: add rt2800_bbp_[read,write]() wrappers
rt2800usb: add rt2800_rfcsr_[read,write]() wrappers
rt2800pci: add rt2800_rfcsr_[read,write]() wrappers
rt2800usb: add rt2800_rf_[read,write]() wrappers
rt2800pci: add rt2800_rf_[read,write]() wrappers
rt2800usb: add rt2800_mcu_request() wrapper
rt2800pci: add rt2800_mcu_request() wrapper
rt2x00: add driver private field to struct rt2x00_dev
rt2800usb: convert to use struct rt2800_ops methods
rt2800pci: convert to use struct rt2800_ops methods
rt2x00: fix rt2x00usb_register_multiwrite() arguments
rt2x00: fix rt2x00usb_regbusy_read() arguments
rt2x00: fix rt2x00pci_register_multi[read,write]() arguments
rt2800: add rt2800lib.h
rt2800usb: add RXINFO_DESC_SIZE definition
rt2800: fix duplication in header files
rt2800: fix comments in rt2800.h
rt2x00: add support for different chipset interfaces
rt2800: prepare for rt2800lib addition
rt2800: add rt2800lib (part one)
rt2800: add rt2800lib (part two)
rt2x00: move REGISTER_BUSY_* definitions to rt2x00.h
rt2800: add rt2800lib (part three)
rt2800: add rt2800lib (part four)
Ben M Cahill (5):
iwlwifi: remove unneeded locks from apm_stop() and stop_master()
iwlwifi: remove power-wasting calls to apm_ops.init()
iwlagn: invoke L0S workaround for 6000/1000 series
iwlagn: Clarify FH_TX interrupt
iwlagn: update write pointers for all tx queues after wakeup
Christian Lamparter (1):
p54: disable channels with incomplete calibration data sets
Greg Kroah-Hartman (4):
Staging: strip: add TODO file
Staging: arlan: add TODO file
Staging: wavelan: add TODO file
Staging: netwave: add TODO file
Gábor Stefanik (1):
b43: LP-PHY: Begin implementing calibration & software RFKILL support
Johannes Berg (19):
cfg80211/mac80211: use debugfs_remove_recursive
mac80211_hwsim: don't register CCK rates on 5ghz
mac80211: remove outdated comment
mac80211: split hardware scan by band
mac80211: fix radiotap header generation
mac80211: remove RX_FLAG_RADIOTAP
mac80211: introduce ieee80211_beacon_get_tim()
mac80211: deprecate qual value
mac80211: unconditionally set IEEE80211_TX_CTL_SEND_AFTER_DTIM
mac80211: also drop qos-nullfunc frames silently
mac80211: remove sent_ps_buffered
mac80211: remove bogus code
mac80211: make CALL_TXH a statement
mac80211: fix scan abort sanity checks
cfg80211: validate scan channels
cfg80211: remove dead variable
mac80211: make ieee80211_find_sta per virtual interface
mac80211: fix internal scan request
mac80211: async station powersave handling
John W. Linville (7):
strip: move driver to staging
arlan: move driver to staging
wavelan: move driver to staging
netwave: move driver to staging
wireless: remove WLAN_80211 and WLAN_PRE80211 from Kconfig
wl1271: depend on INET
mwl8k: use integral index instead of pointer for driver_data
Jouni Malinen (3):
cfg80211: Fix WEXT compat siwauth wpa and group cipher
mac80211_hwsim: Check idle state on TX
mac80211_hwsim: Send ACK frames on the hwsim0 interface
Juuso Oikarinen (6):
wl1271: Remove excess null-data template settings
wl1271: Increase TX power value
wl1271: Check result code of commands
wl1271: Add retry implementation for PSM entries
wl1271: Correct endianness-handling of command status
wl1271: Generalize command response reading
Kalle Valo (3):
mac80211: refactor dynamic power save check
mac80211: fix dynamic power save for devices with nullfunc support in hw
wl1251: enable power save
Keng-Yu Lin (1):
ath5k: add LED support for Acer Aspire One AO751h/AO531h
Larry Finger (4):
b43legacy: Fix DMA TX bounce buffer copying
b43: Remove deprecated 'qual' from returned RX status
b43legacy: Remove deprecated 'qual' from returned RX status
rtl8187: Remove deprecated 'qual' from returned RX status
Lennert Buytenhek (28):
mwl8k: fix GET_STAT firmware command packet layout
mwl8k: coding style cleanups
mwl8k: minor transmit quiescing rework
mwl8k: fix multicast address filter programming
mwl8k: use the mac80211-provided workqueue instead of creating our own
mwl8k: implement FIF_ALLMULTI
mwl8k: enforce FIF_BCN_PRBRESP_PROMISC when no STA interfaces are active
mwl8k: clear hardware MAC address if no STA interface configured
mwl8k: use cond_resched() when loading firmware blocks
mwl8k: clarify WME transmit queue 0/1 swizzling
mwl8k: report rate and other information for received frames
mwl8k: add support for enabling hardware sniffer mode
mwl8k: shorten receive/transmit state variable names
mwl8k: pci BAR mapping changes
mwl8k: change pci id table driver data to a structure pointer
mwl8k: spell out the names of firmware images in the pci driver data
mwl8k: handle loading AP firmware images
mwl8k: use pci_unmap_addr{,set}() to keep track of unmap addresses on rx
mwl8k: allow for different receive descriptor formats
mwl8k: set ->interface_modes from the driver data
mwl8k: rename mwl8k_cmd_get_hw_spec() to mwl8k_cmd_get_hw_spec_sta()
mwl8k: add the commands used for AP firmware initialisation
mwl8k: implement AP firmware antenna configuration
mwl8k: add AP firmware handling to ->configure_filter()
mwl8k: add AP firmware handling to ->start()
mwl8k: add AP firmware (mbss) handling to mwl8k_set_mac_addr()
mwl8k: implement AP firmware EDCA parameter configuration
mwl8k: add support for the 88w8366
Luciano Coelho (1):
wl1271: fix init loop timeout
Luis R. Rodriguez (21):
ath9k_hw: move mac name and rf name helpers to hw code
ath9k_hw: distinguish single-chip solutions on initial probe print
ath9k_hw: add AR9271 single chip name mapping
ath9k_hw: correct AR_PHY_SPECTRAL_SCAN register offset
ath9k_hw: remove bogus register write on ath9k_hw_9271_pa_cal()
ath9k_hw: modify the rf control register for ar9271 revision 1.0
ath9k_hw: update register initialization/reset values for ar9271
ath9k_hw: change the way we initialize the pll for ar9271
ath9k_hw: start documenting 802.11n RF anlong front ends
ath9k_hw: bail out early on ath9k_hw_init_rf()
ath9k_hw: simplify rf attach and rename to ath9k_hw_rf_alloc_ext_banks()
ath9k_hw: simplify ath9k_hw_rf_alloc_ext_banks()
ath9k_hw: rename ath9k_hw_rf_free() to ath9k_hw_rf_free_ext_banks()
ath9k_hw: make both analog channel change routines return int
ath9k_hw: use a callback for frequency change
ath9k_hw: order phy.c code and integrate spur mitigation
ath9k_hw: make spur mitigation a callback
ath9k_hw: remove unused modesIndex param from ath9k_hw_write_regs()
ath9k_hw: Fix and complete force bias for AR5416
ath9k_hw: make ath9k_phy_modify_rx_buffer() static
wl1271: use __dev_alloc_skb() on RX
Randy Dunlap (1):
wireless: airo_cs needs WEXT_SPY
Reinette Chatre (7):
iwlwifi: provide firmware version
iwlwifi: unmap memory before use
iwlwifi: move iwl_[un]init_drv to iwlagn
iwlwifi: split adding broadcast station from others
iwl3945: store station rate scale information in mac80211 station structure
iwlagn: move rate scale initialization to init function
iwlwifi: print warning when sending host command fails
Sujith (1):
mac80211: Fix IBSS merge
Wey-Yi Guy (3):
iwlwifi: coex API data structure
iwlwifi: add SM PS support for 6x50 series
iwlwifi: add wimax/wifi coexist support for 6x50 series
Zhu Yi (1):
mac80211: make align adjustment code support paged SKB
drivers/net/wireless/Kconfig | 140 +--
drivers/net/wireless/Makefile | 10 -
drivers/net/wireless/ath/Kconfig | 1 -
drivers/net/wireless/ath/ar9170/Kconfig | 2 +-
drivers/net/wireless/ath/ath5k/Kconfig | 2 +-
drivers/net/wireless/ath/ath5k/led.c | 2 +
drivers/net/wireless/ath/ath9k/Kconfig | 2 +-
drivers/net/wireless/ath/ath9k/ahb.c | 10 +-
drivers/net/wireless/ath/ath9k/calib.c | 2 +-
drivers/net/wireless/ath/ath9k/eeprom_4k.c | 4 +
drivers/net/wireless/ath/ath9k/hw.c | 669 ++-----
drivers/net/wireless/ath/ath9k/hw.h | 22 +-
drivers/net/wireless/ath/ath9k/initvals.h | 29 +-
drivers/net/wireless/ath/ath9k/main.c | 58 -
drivers/net/wireless/ath/ath9k/pci.c | 10 +-
drivers/net/wireless/ath/ath9k/phy.c | 1100 +++++++++---
drivers/net/wireless/ath/ath9k/phy.h | 40 +-
drivers/net/wireless/ath/ath9k/recv.c | 3 +-
drivers/net/wireless/ath/ath9k/reg.h | 3 +
drivers/net/wireless/ath/ath9k/xmit.c | 3 +-
drivers/net/wireless/b43/Kconfig | 2 +-
drivers/net/wireless/b43/b43.h | 2 -
drivers/net/wireless/b43/main.c | 2 +-
drivers/net/wireless/b43/phy_lp.c | 783 +++++++--
drivers/net/wireless/b43/phy_lp.h | 11 +-
drivers/net/wireless/b43/xmit.c | 1 -
drivers/net/wireless/b43legacy/Kconfig | 2 +-
drivers/net/wireless/b43legacy/b43legacy.h | 2 -
drivers/net/wireless/b43legacy/dma.c | 17 +-
drivers/net/wireless/b43legacy/main.c | 2 +-
drivers/net/wireless/b43legacy/xmit.c | 1 -
drivers/net/wireless/hostap/Kconfig | 1 -
drivers/net/wireless/ipw2x00/Kconfig | 6 +-
drivers/net/wireless/iwlwifi/Kconfig | 2 +-
drivers/net/wireless/iwlwifi/iwl-1000.c | 4 +-
drivers/net/wireless/iwlwifi/iwl-3945-rs.c | 102 +-
drivers/net/wireless/iwlwifi/iwl-3945.h | 35 +-
drivers/net/wireless/iwlwifi/iwl-5000.c | 12 +-
drivers/net/wireless/iwlwifi/iwl-6000.c | 25 +-
drivers/net/wireless/iwlwifi/iwl-agn-rs.c | 13 +-
drivers/net/wireless/iwlwifi/iwl-agn.c | 143 ++-
drivers/net/wireless/iwlwifi/iwl-calib.c | 1 +
drivers/net/wireless/iwlwifi/iwl-commands.h | 161 ++-
drivers/net/wireless/iwlwifi/iwl-core.c | 236 ++--
drivers/net/wireless/iwlwifi/iwl-core.h | 7 +-
drivers/net/wireless/iwlwifi/iwl-dev.h | 1 +
drivers/net/wireless/iwlwifi/iwl-eeprom.c | 11 +
drivers/net/wireless/iwlwifi/iwl-hcmd.c | 2 +
drivers/net/wireless/iwlwifi/iwl-scan.c | 1 +
drivers/net/wireless/iwlwifi/iwl-sta.c | 69 +-
drivers/net/wireless/iwlwifi/iwl-sta.h | 1 +
drivers/net/wireless/iwlwifi/iwl-tx.c | 13 +-
drivers/net/wireless/iwlwifi/iwl3945-base.c | 15 +-
drivers/net/wireless/iwmc3200wifi/Kconfig | 2 +-
drivers/net/wireless/libertas/Kconfig | 2 +-
drivers/net/wireless/libertas/if_spi.c | 136 +--
drivers/net/wireless/mac80211_hwsim.c | 67 +-
drivers/net/wireless/mwl8k.c | 1258 +++++++++----
drivers/net/wireless/orinoco/Kconfig | 2 +-
drivers/net/wireless/p54/Kconfig | 2 +-
drivers/net/wireless/p54/eeprom.c | 31 +-
drivers/net/wireless/rt2x00/Kconfig | 18 +-
drivers/net/wireless/rt2x00/Makefile | 1 +
drivers/net/wireless/rt2x00/rt2800.h | 1816 +++++++++++++++++++
drivers/net/wireless/rt2x00/rt2800lib.c | 1817 +++++++++++++++++++
drivers/net/wireless/rt2x00/rt2800lib.h | 134 ++
drivers/net/wireless/rt2x00/rt2800pci.c | 1908 ++------------------
drivers/net/wireless/rt2x00/rt2800pci.h | 1780 ------------------
drivers/net/wireless/rt2x00/rt2800usb.c | 1828 +------------------
drivers/net/wireless/rt2x00/rt2800usb.h | 1818 +-------------------
drivers/net/wireless/rt2x00/rt2x00.h | 43 +
drivers/net/wireless/rt2x00/rt2x00leds.h | 4 -
drivers/net/wireless/rt2x00/rt2x00pci.h | 24 +-
drivers/net/wireless/rt2x00/rt2x00usb.c | 2 +-
drivers/net/wireless/rt2x00/rt2x00usb.h | 17 +-
drivers/net/wireless/rtl818x/rtl8187.h | 1 -
drivers/net/wireless/rtl818x/rtl8187_dev.c | 13 +-
drivers/net/wireless/wl12xx/Kconfig | 3 +-
drivers/net/wireless/wl12xx/wl1251_main.c | 3 +-
drivers/net/wireless/wl12xx/wl1271.h | 3 +
drivers/net/wireless/wl12xx/wl1271_acx.c | 2 +-
drivers/net/wireless/wl12xx/wl1271_boot.c | 5 +-
drivers/net/wireless/wl12xx/wl1271_cmd.c | 99 +-
drivers/net/wireless/wl12xx/wl1271_cmd.h | 3 +-
drivers/net/wireless/wl12xx/wl1271_conf.h | 8 +
drivers/net/wireless/wl12xx/wl1271_event.c | 53 +
drivers/net/wireless/wl12xx/wl1271_event.h | 7 +
drivers/net/wireless/wl12xx/wl1271_init.c | 7 +-
drivers/net/wireless/wl12xx/wl1271_main.c | 19 +-
drivers/net/wireless/wl12xx/wl1271_rx.c | 2 +-
drivers/net/wireless/zd1211rw/Kconfig | 2 +-
drivers/staging/Kconfig | 8 +
drivers/staging/Makefile | 5 +
drivers/staging/arlan/Kconfig | 15 +
drivers/staging/arlan/Makefile | 3 +
drivers/staging/arlan/TODO | 7 +
.../{net/wireless => staging/arlan}/arlan-main.c | 0
.../{net/wireless => staging/arlan}/arlan-proc.c | 0
drivers/{net/wireless => staging/arlan}/arlan.h | 0
drivers/staging/netwave/Kconfig | 11 +
drivers/staging/netwave/Makefile | 1 +
drivers/staging/netwave/TODO | 7 +
.../{net/wireless => staging/netwave}/netwave_cs.c | 0
drivers/staging/strip/Kconfig | 22 +
drivers/staging/strip/Makefile | 1 +
drivers/staging/strip/TODO | 7 +
drivers/{net/wireless => staging/strip}/strip.c | 0
drivers/staging/wavelan/Kconfig | 38 +
drivers/staging/wavelan/Makefile | 2 +
drivers/staging/wavelan/TODO | 7 +
drivers/{net/wireless => staging/wavelan}/i82586.h | 0
drivers/{net/wireless => staging/wavelan}/i82593.h | 0
.../{net/wireless => staging/wavelan}/wavelan.c | 0
.../{net/wireless => staging/wavelan}/wavelan.h | 0
.../{net/wireless => staging/wavelan}/wavelan.p.h | 0
.../{net/wireless => staging/wavelan}/wavelan_cs.c | 0
.../{net/wireless => staging/wavelan}/wavelan_cs.h | 0
.../wireless => staging/wavelan}/wavelan_cs.p.h | 0
include/linux/ieee80211.h | 12 +-
include/net/ieee80211_radiotap.h | 2 +-
include/net/mac80211.h | 116 +-
net/mac80211/cfg.c | 7 -
net/mac80211/debugfs.c | 73 +-
net/mac80211/debugfs.h | 2 -
net/mac80211/debugfs_key.c | 44 +-
net/mac80211/debugfs_netdev.c | 174 +--
net/mac80211/debugfs_sta.c | 38 +-
net/mac80211/ibss.c | 4 +
net/mac80211/ieee80211_i.h | 123 +--
net/mac80211/iface.c | 8 +-
net/mac80211/key.h | 12 -
net/mac80211/main.c | 11 +-
net/mac80211/rate.c | 7 +-
net/mac80211/rx.c | 173 +--
net/mac80211/scan.c | 119 +-
net/mac80211/sta_info.c | 136 ++-
net/mac80211/sta_info.h | 47 +-
net/mac80211/tx.c | 99 +-
net/mac80211/util.c | 8 +-
net/wireless/core.c | 3 +-
net/wireless/core.h | 11 -
net/wireless/debugfs.c | 15 +-
net/wireless/debugfs.h | 3 -
net/wireless/mlme.c | 2 -
net/wireless/nl80211.c | 34 +-
net/wireless/scan.c | 6 +
net/wireless/wext-compat.c | 6 +-
147 files changed, 8305 insertions(+), 9862 deletions(-)
create mode 100644 drivers/net/wireless/rt2x00/rt2800.h
create mode 100644 drivers/net/wireless/rt2x00/rt2800lib.c
create mode 100644 drivers/net/wireless/rt2x00/rt2800lib.h
create mode 100644 drivers/staging/arlan/Kconfig
create mode 100644 drivers/staging/arlan/Makefile
create mode 100644 drivers/staging/arlan/TODO
rename drivers/{net/wireless => staging/arlan}/arlan-main.c (100%)
rename drivers/{net/wireless => staging/arlan}/arlan-proc.c (100%)
rename drivers/{net/wireless => staging/arlan}/arlan.h (100%)
create mode 100644 drivers/staging/netwave/Kconfig
create mode 100644 drivers/staging/netwave/Makefile
create mode 100644 drivers/staging/netwave/TODO
rename drivers/{net/wireless => staging/netwave}/netwave_cs.c (100%)
create mode 100644 drivers/staging/strip/Kconfig
create mode 100644 drivers/staging/strip/Makefile
create mode 100644 drivers/staging/strip/TODO
rename drivers/{net/wireless => staging/strip}/strip.c (100%)
create mode 100644 drivers/staging/wavelan/Kconfig
create mode 100644 drivers/staging/wavelan/Makefile
create mode 100644 drivers/staging/wavelan/TODO
rename drivers/{net/wireless => staging/wavelan}/i82586.h (100%)
rename drivers/{net/wireless => staging/wavelan}/i82593.h (100%)
rename drivers/{net/wireless => staging/wavelan}/wavelan.c (100%)
rename drivers/{net/wireless => staging/wavelan}/wavelan.h (100%)
rename drivers/{net/wireless => staging/wavelan}/wavelan.p.h (100%)
rename drivers/{net/wireless => staging/wavelan}/wavelan_cs.c (100%)
rename drivers/{net/wireless => staging/wavelan}/wavelan_cs.h (100%)
rename drivers/{net/wireless => staging/wavelan}/wavelan_cs.p.h (100%)
Omnibus patch available here:
http://www.kernel.org/pub/linux/kernel/people/linville/wireless-next-2.6-2009-11-09.patch.bz2
--
John W. Linville Someday the world will need a hero, and you
linville-2XuSBdqkA4R54TAoqtyWWQ@public.gmane.org might be all we have. Be ready.
--
To unsubscribe from this list: send the line "unsubscribe linux-wireless" in
the body of a message to majordomo-u79uwXL29TY76Z2rM5mHXA@public.gmane.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
^ permalink raw reply
* Re: [PATCH] xfrm: SAD entries do not expire correctly after suspend-resume
From: Yury Polyanskiy @ 2009-11-09 18:31 UTC (permalink / raw)
To: Herbert Xu; +Cc: netdev, davem, peterz, yoshfuji, tglx, mingo
In-Reply-To: <20091109153910.GA8039@gondor.apana.org.au>
[-- Attachment #1: Type: text/plain, Size: 1924 bytes --]
On Mon, 9 Nov 2009 10:39:10 -0500
Herbert Xu <herbert@gondor.apana.org.au> wrote:
> However, I have some reservations as to whether this is the ideal
> situation. Unless I'm mistaken, this patch may cause IPsec SAs
> to expire if the system clock was out of sync prior to IPsec startup
> and is subsequently resynced by ntpdate or similar.
>
> For example, it's quite common for clocks to be out-of-sync by
> 10 hours in Australia due to time zone issues with BIOS clocks.
> So potentially ntpdate could move the clock forward by 10 hours
> or more on bootup thus causing IPsec SAs to expire prematurely
> with this patch.
>
> This shouldn't really be a problem in itself except that there
> are some dodgy IPsec gateways out there that refuse to reestablish
> IPsec SAs if the interval between two successive connections is
> too small. This could render the SA inoperable for hours.
But why would it be inoperable for hours?
I think that the following will happen:
* racoon will recreate SAD entry in the larval state, wait 30s and drop
it (since dodgy-gw filtered out all keyexchange packets)
* The next time there is a connect() with a match in the SPD, racoon
will again try to recreate the SAD entry. If there dodgy-gw still
filters out, the larval SAD entry dies after 30s.
So the inoperability will only last as long as dodgy-gw filters
keyexchanges.
In any case, running ntpdate before racoon fixes the problem.
>
> So the upshot of all this is that we definitely want the effect
> of this patch for suspend/resume, but it would be great if we can
> avoid it for settimeofday(2).
I think the natural solution is to have CLOCK_BOOTBASED hrtimers. I.e.
something in the spirit of monotonic_to_bootbased() and getboottime().
I understand that doing +=total_sleep_time is against the core idea of
hires timers, but perhaps there is a nicer way.
Best,
Y
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 198 bytes --]
^ permalink raw reply
* sit: Clean up DF code by copying from IPIP
From: Herbert Xu @ 2009-11-09 18:42 UTC (permalink / raw)
To: David S. Miller, netdev
In-Reply-To: <20091106203741.GA19736@gondor.apana.org.au>
Hi Dave:
This can go into net-next since it doesn't really alter the
behaviour in any significant way.
sit: Clean up DF code by copying from IPIP
This patch rearranges the SIT DF bit handling using the new IPIP
DF code. The only externally visible effect should be the case where
PMTU is enabled and the MTU is exactly 1280 bytes. In this case
the previous code would send packets out with DF off while the new
code would set the DF bit. This is inline with RFC 4213.
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c
index dbd19a7..97739ee 100644
--- a/net/ipv6/sit.c
+++ b/net/ipv6/sit.c
@@ -559,6 +559,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
struct iphdr *tiph = &tunnel->parms.iph;
struct ipv6hdr *iph6 = ipv6_hdr(skb);
u8 tos = tunnel->parms.iph.tos;
+ __be16 df = tiph->frag_off;
struct rtable *rt; /* Route to the other host */
struct net_device *tdev; /* Device to other host */
struct iphdr *iph; /* Our new IP header */
@@ -648,25 +649,28 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
goto tx_error;
}
- if (tiph->frag_off)
+ if (df) {
mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr);
- else
- mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
- if (mtu < 68) {
- stats->collisions++;
- ip_rt_put(rt);
- goto tx_error;
- }
- if (mtu < IPV6_MIN_MTU)
- mtu = IPV6_MIN_MTU;
- if (tunnel->parms.iph.daddr && skb_dst(skb))
- skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
+ if (mtu < 68) {
+ stats->collisions++;
+ ip_rt_put(rt);
+ goto tx_error;
+ }
- if (skb->len > mtu) {
- icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev);
- ip_rt_put(rt);
- goto tx_error;
+ if (mtu < IPV6_MIN_MTU) {
+ mtu = IPV6_MIN_MTU;
+ df = 0;
+ }
+
+ if (tunnel->parms.iph.daddr && skb_dst(skb))
+ skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu);
+
+ if (skb->len > mtu) {
+ icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev);
+ ip_rt_put(rt);
+ goto tx_error;
+ }
}
if (tunnel->err_count > 0) {
@@ -714,11 +718,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb,
iph = ip_hdr(skb);
iph->version = 4;
iph->ihl = sizeof(struct iphdr)>>2;
- if (mtu > IPV6_MIN_MTU)
- iph->frag_off = tiph->frag_off;
- else
- iph->frag_off = 0;
-
+ iph->frag_off = df;
iph->protocol = IPPROTO_IPV6;
iph->tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6));
iph->daddr = rt->rt_dst;
Thanks,
--
Visit Openswan at http://www.openswan.org/
Email: Herbert Xu ~{PmV>HI~} <herbert@gondor.apana.org.au>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt
^ permalink raw reply related
* Re: [RFC,PATCH] mutex: mutex_is_owner() helper
From: Peter Zijlstra @ 2009-11-09 18:56 UTC (permalink / raw)
To: Eric Dumazet
Cc: Ingo Molnar, Linus Torvalds, David S. Miller, Linux Netdev List,
linux kernel, Thomas Gleixner
In-Reply-To: <4AF1B7A7.6030902@gmail.com>
On Wed, 2009-11-04 at 18:19 +0100, Eric Dumazet wrote:
>
> BTW, I was thinking of a mutex_yield() implementation, but could not
> cook it without hard thinking, maybe you already have some nice
> implementation ?
Why? Yield sets off alarm bells, since 99.9%, and possibly more, of its
uses are wrong.
> int mutex_yield(struct mutex *lock)
> {
> int ret = 0;
>
> if (mutex_needbreak(lock) || should_resched()) {
> mutex_unlock(lock);
> __cond_resched();
> mutex_lock(lock);
> ret = 1;
> }
> return ret;
> }
That reads like it should be called cond_resched_mutex(), except that
the should_resched() thing seems daft (but maybe it makes sense for
silly preemption modes like voluntary).
iirc we actually have something similar in -rt in order to implement the
lock-break for the rt-mutex based spinlocks, we set ->needbreak when a
higher priority task contends -- a policy for regular mutexes might be
'interesting' though.
As to your 'debug' helper that started this thread, doesn't
lockdep_assert_held() work for you?
^ 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