| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Fri, 2 Jul 2010 21:20:19 +0200
From: Sebastian Andrzej Siewior <sebastian@...akpoint.cc>
To: netdev@...r.kernel.org
Cc: tglx@...utronix.de,
Sebastian Andrzej Siewior <bigeasy@...utronix.de>
Subject: [PATCH 6/8] net: implement emergency pools
From: Sebastian Andrzej Siewior <bigeasy@...utronix.de>
This patch implements emergency pools which are bound to a specific
network device. They can be activated via the socket interface and used
for a specific socket.
The pools are built on top of rx-recycling. The socket interface allows
to set the number of skbs in the pool and to active the pool.
The size of the skb which are accepted / added to the pool can not be
changed. It is set by the network driver and get altered on MTU change.
This requires to drop the current pool and re-allocate it. If the driver
does not set the skb size, the emergency pools can not be used.
Once the emergency pools are activated all rx-skbs allocation by the
network driver are taken from the pool. tx-skbs are allocated from the
emergency pool only for the relevant socket, i.e. that one which
activated the emergency mode.
Since the socket _and_ the driver can add/remove skbs to/from the pool
the list operations are using now skb_queue_head() and skb_dequeue().
There is patch later in the series which tries to bring the old unlock
behavior back if the emergency pools are not used by the user.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@...utronix.de>
---
arch/alpha/include/asm/socket.h | 4 +
arch/arm/include/asm/socket.h | 3 +
arch/avr32/include/asm/socket.h | 3 +
arch/cris/include/asm/socket.h | 5 +-
arch/frv/include/asm/socket.h | 4 +-
arch/h8300/include/asm/socket.h | 3 +
arch/ia64/include/asm/socket.h | 3 +
arch/m32r/include/asm/socket.h | 3 +
arch/m68k/include/asm/socket.h | 3 +
arch/mips/include/asm/socket.h | 3 +
arch/mn10300/include/asm/socket.h | 3 +
arch/parisc/include/asm/socket.h | 3 +
arch/powerpc/include/asm/socket.h | 3 +
arch/s390/include/asm/socket.h | 3 +
arch/sparc/include/asm/socket.h | 3 +
arch/xtensa/include/asm/socket.h | 3 +
include/asm-generic/socket.h | 4 +
include/linux/netdevice.h | 52 +++++++------
include/linux/skbuff.h | 1 +
include/net/sock.h | 2 +
net/core/skbuff.c | 8 ++
net/core/sock.c | 142 +++++++++++++++++++++++++++++++++++++
22 files changed, 234 insertions(+), 27 deletions(-)
diff --git a/arch/alpha/include/asm/socket.h b/arch/alpha/include/asm/socket.h
index 06edfef..ea49db3 100644
--- a/arch/alpha/include/asm/socket.h
+++ b/arch/alpha/include/asm/socket.h
@@ -69,6 +69,10 @@
#define SO_RXQ_OVFL 40
+#define SO_EPOOL_QLEN 41
+#define SO_EPOOL_SIZE 42
+#define SO_EPOOL_MODE 43
+
/* O_NONBLOCK clashes with the bits used for socket types. Therefore we
* have to define SOCK_NONBLOCK to a different value here.
*/
diff --git a/arch/arm/include/asm/socket.h b/arch/arm/include/asm/socket.h
index 90ffd04..b827010 100644
--- a/arch/arm/include/asm/socket.h
+++ b/arch/arm/include/asm/socket.h
@@ -62,4 +62,7 @@
#define SO_RXQ_OVFL 40
+#define SO_EPOOL_QLEN 41
+#define SO_EPOOL_SIZE 42
+#define SO_EPOOL_MODE 43
#endif /* _ASM_SOCKET_H */
diff --git a/arch/avr32/include/asm/socket.h b/arch/avr32/include/asm/socket.h
index c8d1fae..64a7d45 100644
--- a/arch/avr32/include/asm/socket.h
+++ b/arch/avr32/include/asm/socket.h
@@ -62,4 +62,7 @@
#define SO_RXQ_OVFL 40
+#define SO_EPOOL_QLEN 41
+#define SO_EPOOL_SIZE 42
+#define SO_EPOOL_MODE 43
#endif /* __ASM_AVR32_SOCKET_H */
diff --git a/arch/cris/include/asm/socket.h b/arch/cris/include/asm/socket.h
index 1a4a619..9b8e7ed 100644
--- a/arch/cris/include/asm/socket.h
+++ b/arch/cris/include/asm/socket.h
@@ -64,6 +64,7 @@
#define SO_RXQ_OVFL 40
+#define SO_EPOOL_QLEN 41
+#define SO_EPOOL_SIZE 42
+#define SO_EPOOL_MODE 43
#endif /* _ASM_SOCKET_H */
-
-
diff --git a/arch/frv/include/asm/socket.h b/arch/frv/include/asm/socket.h
index a6b2688..15a262f 100644
--- a/arch/frv/include/asm/socket.h
+++ b/arch/frv/include/asm/socket.h
@@ -62,5 +62,7 @@
#define SO_RXQ_OVFL 40
+#define SO_EPOOL_QLEN 41
+#define SO_EPOOL_SIZE 42
+#define SO_EPOOL_MODE 43
#endif /* _ASM_SOCKET_H */
-
diff --git a/arch/h8300/include/asm/socket.h b/arch/h8300/include/asm/socket.h
index 04c0f45..d46d64e 100644
--- a/arch/h8300/include/asm/socket.h
+++ b/arch/h8300/include/asm/socket.h
@@ -62,4 +62,7 @@
#define SO_RXQ_OVFL 40
+#define SO_EPOOL_QLEN 41
+#define SO_EPOOL_SIZE 42
+#define SO_EPOOL_MODE 43
#endif /* _ASM_SOCKET_H */
diff --git a/arch/ia64/include/asm/socket.h b/arch/ia64/include/asm/socket.h
index 51427ea..04983aa 100644
--- a/arch/ia64/include/asm/socket.h
+++ b/arch/ia64/include/asm/socket.h
@@ -71,4 +71,7 @@
#define SO_RXQ_OVFL 40
+#define SO_EPOOL_QLEN 41
+#define SO_EPOOL_SIZE 42
+#define SO_EPOOL_MODE 43
#endif /* _ASM_IA64_SOCKET_H */
diff --git a/arch/m32r/include/asm/socket.h b/arch/m32r/include/asm/socket.h
index 469787c..a0e5431 100644
--- a/arch/m32r/include/asm/socket.h
+++ b/arch/m32r/include/asm/socket.h
@@ -62,4 +62,7 @@
#define SO_RXQ_OVFL 40
+#define SO_EPOOL_QLEN 41
+#define SO_EPOOL_SIZE 42
+#define SO_EPOOL_MODE 43
#endif /* _ASM_M32R_SOCKET_H */
diff --git a/arch/m68k/include/asm/socket.h b/arch/m68k/include/asm/socket.h
index 9bf49c8..7018ceb 100644
--- a/arch/m68k/include/asm/socket.h
+++ b/arch/m68k/include/asm/socket.h
@@ -62,4 +62,7 @@
#define SO_RXQ_OVFL 40
+#define SO_EPOOL_QLEN 41
+#define SO_EPOOL_SIZE 42
+#define SO_EPOOL_MODE 43
#endif /* _ASM_SOCKET_H */
diff --git a/arch/mips/include/asm/socket.h b/arch/mips/include/asm/socket.h
index 9de5190..9f9d93a 100644
--- a/arch/mips/include/asm/socket.h
+++ b/arch/mips/include/asm/socket.h
@@ -82,6 +82,9 @@ To add: #define SO_REUSEPORT 0x0200 /* Allow local address and port reuse. */
#define SO_RXQ_OVFL 40
+#define SO_EPOOL_QLEN 41
+#define SO_EPOOL_SIZE 42
+#define SO_EPOOL_MODE 43
#ifdef __KERNEL__
/** sock_type - Socket types
diff --git a/arch/mn10300/include/asm/socket.h b/arch/mn10300/include/asm/socket.h
index 4e60c42..70476eb 100644
--- a/arch/mn10300/include/asm/socket.h
+++ b/arch/mn10300/include/asm/socket.h
@@ -62,4 +62,7 @@
#define SO_RXQ_OVFL 40
+#define SO_EPOOL_QLEN 41
+#define SO_EPOOL_SIZE 42
+#define SO_EPOOL_MODE 43
#endif /* _ASM_SOCKET_H */
diff --git a/arch/parisc/include/asm/socket.h b/arch/parisc/include/asm/socket.h
index 225b7d6..a4706d0 100644
--- a/arch/parisc/include/asm/socket.h
+++ b/arch/parisc/include/asm/socket.h
@@ -61,6 +61,9 @@
#define SO_RXQ_OVFL 0x4021
+#define SO_EPOOL_QLEN 0x4022
+#define SO_EPOOL_SIZE 0x4023
+#define SO_EPOOL_MODE 0x4024
/* O_NONBLOCK clashes with the bits used for socket types. Therefore we
* have to define SOCK_NONBLOCK to a different value here.
*/
diff --git a/arch/powerpc/include/asm/socket.h b/arch/powerpc/include/asm/socket.h
index 866f760..dce10f9 100644
--- a/arch/powerpc/include/asm/socket.h
+++ b/arch/powerpc/include/asm/socket.h
@@ -69,4 +69,7 @@
#define SO_RXQ_OVFL 40
+#define SO_EPOOL_QLEN 41
+#define SO_EPOOL_SIZE 42
+#define SO_EPOOL_MODE 43
#endif /* _ASM_POWERPC_SOCKET_H */
diff --git a/arch/s390/include/asm/socket.h b/arch/s390/include/asm/socket.h
index fdff1e9..73d0117 100644
--- a/arch/s390/include/asm/socket.h
+++ b/arch/s390/include/asm/socket.h
@@ -70,4 +70,7 @@
#define SO_RXQ_OVFL 40
+#define SO_EPOOL_QLEN 41
+#define SO_EPOOL_SIZE 42
+#define SO_EPOOL_MODE 43
#endif /* _ASM_SOCKET_H */
diff --git a/arch/sparc/include/asm/socket.h b/arch/sparc/include/asm/socket.h
index 9d3fefc..39eea91 100644
--- a/arch/sparc/include/asm/socket.h
+++ b/arch/sparc/include/asm/socket.h
@@ -58,6 +58,9 @@
#define SO_RXQ_OVFL 0x0024
+#define SO_EPOOL_QLEN 0x0025
+#define SO_EPOOL_SIZE 0x0026
+#define SO_EPOOL_MODE 0x0027
/* Security levels - as per NRL IPv6 - don't actually do anything */
#define SO_SECURITY_AUTHENTICATION 0x5001
#define SO_SECURITY_ENCRYPTION_TRANSPORT 0x5002
diff --git a/arch/xtensa/include/asm/socket.h b/arch/xtensa/include/asm/socket.h
index cbdf2ff..161a2e5 100644
--- a/arch/xtensa/include/asm/socket.h
+++ b/arch/xtensa/include/asm/socket.h
@@ -73,4 +73,7 @@
#define SO_RXQ_OVFL 40
+#define SO_EPOOL_QLEN 41
+#define SO_EPOOL_SIZE 42
+#define SO_EPOOL_MODE 43
#endif /* _XTENSA_SOCKET_H */
diff --git a/include/asm-generic/socket.h b/include/asm-generic/socket.h
index 9a6115e..fa9ccbb 100644
--- a/include/asm-generic/socket.h
+++ b/include/asm-generic/socket.h
@@ -64,4 +64,8 @@
#define SO_DOMAIN 39
#define SO_RXQ_OVFL 40
+
+#define SO_EPOOL_QLEN 41
+#define SO_EPOOL_SIZE 42
+#define SO_EPOOL_MODE 43
#endif /* __ASM_GENERIC_SOCKET_H */
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index 4fa400b..fa7e951 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -1095,6 +1095,28 @@ struct net_device {
};
#define to_net_dev(d) container_of(d, struct net_device, dev)
+/**
+ * dev_put - release reference to device
+ * @dev: network device
+ *
+ * Release reference to device to allow it to be freed.
+ */
+static inline void dev_put(struct net_device *dev)
+{
+ atomic_dec(&dev->refcnt);
+}
+
+/**
+ * dev_hold - get reference to device
+ * @dev: network device
+ *
+ * Hold reference to device to keep it from being freed.
+ */
+static inline void dev_hold(struct net_device *dev)
+{
+ atomic_inc(&dev->refcnt);
+}
+
static inline void net_recycle_init(struct net_device *dev, u32 qlen, u32 size)
{
dev->rx_rec_skbs_max = qlen;
@@ -1118,9 +1140,13 @@ static inline void net_recycle_cleanup(struct net_device *dev)
static inline void net_recycle_add(struct net_device *dev, struct sk_buff *skb)
{
+ if (skb->emerg_dev) {
+ dev_put(skb->emerg_dev);
+ skb->emerg_dev = NULL;
+ }
if (skb_queue_len(&dev->rx_recycle) < dev->rx_rec_skbs_max &&
skb_recycle_check(skb, dev->rx_rec_skb_size))
- __skb_queue_head(&dev->rx_recycle, skb);
+ skb_queue_head(&dev->rx_recycle, skb);
else
dev_kfree_skb_any(skb);
}
@@ -1129,7 +1155,7 @@ static inline struct sk_buff *net_recycle_get(struct net_device *dev)
{
struct sk_buff *skb;
- skb = __skb_dequeue(&dev->rx_recycle);
+ skb = skb_dequeue(&dev->rx_recycle);
if (skb)
return skb;
return netdev_alloc_skb(dev, dev->rx_rec_skb_size);
@@ -1783,28 +1809,6 @@ extern int netdev_budget;
/* Called by rtnetlink.c:rtnl_unlock() */
extern void netdev_run_todo(void);
-/**
- * dev_put - release reference to device
- * @dev: network device
- *
- * Release reference to device to allow it to be freed.
- */
-static inline void dev_put(struct net_device *dev)
-{
- atomic_dec(&dev->refcnt);
-}
-
-/**
- * dev_hold - get reference to device
- * @dev: network device
- *
- * Hold reference to device to keep it from being freed.
- */
-static inline void dev_hold(struct net_device *dev)
-{
- atomic_inc(&dev->refcnt);
-}
-
/* Carrier loss detection, dial on demand. The functions netif_carrier_on
* and _off may be called from IRQ context, but it is caller
* who is responsible for serialization of these calls.
diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h
index ac74ee0..caee62c 100644
--- a/include/linux/skbuff.h
+++ b/include/linux/skbuff.h
@@ -319,6 +319,7 @@ struct sk_buff {
struct sock *sk;
struct net_device *dev;
+ struct net_device *emerg_dev;
/*
* This is the control buffer. It is free to use for every
diff --git a/include/net/sock.h b/include/net/sock.h
index 4f26f2f..3f3518a 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -314,6 +314,8 @@ struct sock {
#endif
__u32 sk_mark;
u32 sk_classid;
+ u32 emerg_en;
+ /* XXX 4 bytes hole on 64 bit */
void (*sk_state_change)(struct sock *sk);
void (*sk_data_ready)(struct sock *sk, int bytes);
void (*sk_write_space)(struct sock *sk);
diff --git a/net/core/skbuff.c b/net/core/skbuff.c
index 34432b4..f02737d 100644
--- a/net/core/skbuff.c
+++ b/net/core/skbuff.c
@@ -425,6 +425,13 @@ static void skb_release_all(struct sk_buff *skb)
void __kfree_skb(struct sk_buff *skb)
{
+ struct net_device *ndev = skb->emerg_dev;
+
+ if (ndev) {
+ net_recycle_add(ndev, skb);
+ return;
+ }
+
skb_release_all(skb);
kfree_skbmem(skb);
}
@@ -563,6 +570,7 @@ static struct sk_buff *__skb_clone(struct sk_buff *n, struct sk_buff *skb)
{
#define C(x) n->x = skb->x
+ n->emerg_dev = NULL;
n->next = n->prev = NULL;
n->sk = NULL;
__copy_skb_header(n, skb);
diff --git a/net/core/sock.c b/net/core/sock.c
index fef2434..33aa1a5 100644
--- a/net/core/sock.c
+++ b/net/core/sock.c
@@ -472,6 +472,71 @@ static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool)
sock_reset_flag(sk, bit);
}
+static int sock_epool_set_qlen(struct sock *sk, int val)
+{
+ struct net *net = sock_net(sk);
+ struct net_device *dev;
+
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+
+ if (!sk->sk_bound_dev_if)
+ return -ENODEV;
+ dev = dev_get_by_index(net, sk->sk_bound_dev_if);
+ if (!dev)
+ return -ENODEV;
+
+ net_recycle_qlen(dev, val);
+ dev_put(dev);
+ return 0;
+}
+
+static int sock_epool_set_mode(struct sock *sk, int val)
+{
+ int ret;
+ struct net *net = sock_net(sk);
+ struct net_device *dev;
+
+ if (!val) {
+ sk->emerg_en = 0;
+ return 0;
+ }
+ if (sk->emerg_en && val)
+ return -EBUSY;
+ if (!capable(CAP_NET_ADMIN))
+ return -EPERM;
+ if (!sk->sk_bound_dev_if)
+ return -ENODEV;
+ dev = dev_get_by_index(net, sk->sk_bound_dev_if);
+ if (!dev)
+ return -ENODEV;
+ ret = -ENODEV;
+ if (!dev->rx_rec_skb_size)
+ goto out;
+
+ do {
+ struct sk_buff *skb;
+
+ if (skb_queue_len(&dev->rx_recycle) >= dev->rx_rec_skbs_max) {
+ ret = 0;
+ break;
+ }
+
+ skb = __netdev_alloc_skb(dev, dev->rx_rec_skb_size, GFP_KERNEL);
+ if (!skb) {
+ ret = -ENOMEM;
+ break;
+ }
+ net_recycle_add(dev, skb);
+ } while (1);
+
+ if (!ret)
+ sk->emerg_en = 1;
+out:
+ dev_put(dev);
+ return ret;
+}
+
/*
* This is meant for all protocols to use and covers goings on
* at the socket level. Everything here is generic.
@@ -740,6 +805,15 @@ set_rcvbuf:
else
sock_reset_flag(sk, SOCK_RXQ_OVFL);
break;
+ case SO_EPOOL_QLEN:
+ ret = sock_epool_set_qlen(sk, val);
+ break;
+ case SO_EPOOL_SIZE:
+ ret = -EINVAL;
+ break;
+ case SO_EPOOL_MODE:
+ ret = sock_epool_set_mode(sk, valbool);
+ break;
default:
ret = -ENOPROTOOPT;
break;
@@ -961,6 +1035,35 @@ int sock_getsockopt(struct socket *sock, int level, int optname,
v.val = !!sock_flag(sk, SOCK_RXQ_OVFL);
break;
+ case SO_EPOOL_QLEN:
+ {
+ struct net *net = sock_net(sk);
+ struct net_device *dev;
+
+ if (!sk->sk_bound_dev_if)
+ return -ENODEV;
+ dev = dev_get_by_index(net, sk->sk_bound_dev_if);
+ if (!dev)
+ return -ENODEV;
+ v.val = dev->rx_rec_skbs_max;
+ break;
+ }
+ case SO_EPOOL_SIZE:
+ {
+ struct net *net = sock_net(sk);
+ struct net_device *dev;
+
+ if (!sk->sk_bound_dev_if)
+ return -ENODEV;
+ dev = dev_get_by_index(net, sk->sk_bound_dev_if);
+ if (!dev)
+ return -ENODEV;
+ v.val = dev->rx_rec_skb_size;
+ break;
+ }
+ case SO_EPOOL_MODE:
+ v.val = sk->emerg_en;
+ break;
default:
return -ENOPROTOOPT;
}
@@ -1459,6 +1562,37 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo)
return timeo;
}
+static struct sk_buff *alloc_emerg_skb(struct sock *sk, unsigned int skb_len)
+{
+ struct net *net = sock_net(sk);
+ struct net_device *dev;
+ int err;
+ struct sk_buff *skb;
+
+ err = -ENODEV;
+ if (!sk->sk_bound_dev_if)
+ return ERR_PTR(err);
+ dev = dev_get_by_index(net, sk->sk_bound_dev_if);
+ if (!dev)
+ return ERR_PTR(err);
+ err = -EINVAL;
+ if (dev->rx_rec_skb_size < skb_len) {
+ dev_put(dev);
+ return ERR_PTR(err);
+ }
+ skb = skb_dequeue(&dev->rx_recycle);
+ if (!skb) {
+ dev_put(dev);
+ err = -ENOBUFS;
+ return ERR_PTR(err);
+ }
+ /*
+ * dev will be put once the skb is back from
+ * its journey.
+ */
+ skb->emerg_dev = dev;
+ return skb;
+}
/*
* Generic send/receive buffer handlers
@@ -1488,6 +1622,14 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len,
goto failure;
if (atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) {
+ if (sk->emerg_en) {
+ skb = alloc_emerg_skb(sk, header_len + data_len);
+ if (IS_ERR(skb)) {
+ err = PTR_ERR(skb);
+ goto failure;
+ }
+ break;
+ }
skb = alloc_skb(header_len, gfp_mask);
if (skb) {
int npages;
--
1.6.6.1
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Powered by blists - more mailing lists