From d00c362f1b0ff54161e0a42b4554ac621a9ef92d Mon Sep 17 00:00:00 2001 From: Jarek Poplawski Date: Sat, 16 Jan 2010 01:04:04 -0800 Subject: ax25: netrom: rose: Fix timer oopses Wrong ax25_cb refcounting in ax25_send_frame() and by its callers can cause timer oopses (first reported with 2.6.29.6 kernel). Fixes: http://bugzilla.kernel.org/show_bug.cgi?id=14905 Reported-by: Bernard Pidoux Tested-by: Bernard Pidoux Signed-off-by: Jarek Poplawski Signed-off-by: David S. Miller --- include/net/netrom.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/net/netrom.h b/include/net/netrom.h index 15696b1fd30f..ab170a60e7d3 100644 --- a/include/net/netrom.h +++ b/include/net/netrom.h @@ -132,6 +132,8 @@ static __inline__ void nr_node_put(struct nr_node *nr_node) static __inline__ void nr_neigh_put(struct nr_neigh *nr_neigh) { if (atomic_dec_and_test(&nr_neigh->refcount)) { + if (nr_neigh->ax25) + ax25_cb_put(nr_neigh->ax25); kfree(nr_neigh->digipeat); kfree(nr_neigh); } -- cgit v1.2.3 From 4f9c85a1b03bfa5c0a0d8488a3a7766f3c9fb756 Mon Sep 17 00:00:00 2001 From: Anton Vorontsov Date: Mon, 18 Jan 2010 05:37:16 +0000 Subject: phylib: Move workqueue initialization to a proper place commit 541cd3ee00a4fe975b22fac6a3bc846bacef37f7 ("phylib: Fix deadlock on resume") caused TI DaVinci EMAC ethernet driver to oops upon resume: PM: resume of devices complete after 237.098 msecs Restarting tasks ... done. kernel BUG at kernel/workqueue.c:354! Unable to handle kernel NULL pointer dereference at virtual address 00000000 [...] Backtrace: [] (__bug+0x0/0x2c) from [] (queue_delayed_work_on+0x74/0xf8) [] (queue_delayed_work_on+0x0/0xf8) from [] (queue_delayed_work+0x2c/0x30) The oops pops up because TI DaVinci EMAC driver detaches PHY on suspend and attaches it back on resume. Attaching makes phylib call phy_start_machine() that initializes a workqueue. On the other hand, PHY's resume routine will call phy_start_machine() again, and that will cause the oops since we just destroyed the already scheduled workqueue. This patch fixes the issue by moving workqueue initialization to phy_device_create(). p.s. We don't see this oops with ucc_geth and gianfar drivers because they perform a fine-grained suspend, i.e. they just stop the PHYs without detaching. Reported-by: Sekhar Nori Signed-off-by: Anton Vorontsov Tested-by: Sekhar Nori Signed-off-by: David S. Miller --- drivers/net/phy/phy.c | 4 +--- drivers/net/phy/phy_device.c | 1 + include/linux/phy.h | 1 + 3 files changed, 3 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index b0e9f9c51721..0295097d6c44 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -410,7 +410,6 @@ EXPORT_SYMBOL(phy_start_aneg); static void phy_change(struct work_struct *work); -static void phy_state_machine(struct work_struct *work); /** * phy_start_machine - start PHY state machine tracking @@ -430,7 +429,6 @@ void phy_start_machine(struct phy_device *phydev, { phydev->adjust_state = handler; - INIT_DELAYED_WORK(&phydev->state_queue, phy_state_machine); schedule_delayed_work(&phydev->state_queue, HZ); } @@ -761,7 +759,7 @@ EXPORT_SYMBOL(phy_start); * phy_state_machine - Handle the state machine * @work: work_struct that describes the work to be done */ -static void phy_state_machine(struct work_struct *work) +void phy_state_machine(struct work_struct *work) { struct delayed_work *dwork = to_delayed_work(work); struct phy_device *phydev = diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 8212b2b93422..adbc0fded130 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -177,6 +177,7 @@ struct phy_device* phy_device_create(struct mii_bus *bus, int addr, int phy_id) dev->state = PHY_DOWN; mutex_init(&dev->lock); + INIT_DELAYED_WORK(&dev->state_queue, phy_state_machine); return dev; } diff --git a/include/linux/phy.h b/include/linux/phy.h index 7968defd2fa7..6a7eb402165d 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -485,6 +485,7 @@ void phy_driver_unregister(struct phy_driver *drv); int phy_driver_register(struct phy_driver *new_driver); void phy_prepare_link(struct phy_device *phydev, void (*adjust_link)(struct net_device *)); +void phy_state_machine(struct work_struct *work); void phy_start_machine(struct phy_device *phydev, void (*handler)(struct net_device *)); void phy_stop_machine(struct phy_device *phydev); -- cgit v1.2.3 From e071041be037eca208b62b84469a06bdfc692bea Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Sat, 23 Jan 2010 13:37:10 +0000 Subject: netns xfrm: fix "ip xfrm state|policy count" misreport "ip xfrm state|policy count" report SA/SP count from init_net, not from netns of caller process. Signed-off-by: Alexey Dobriyan Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/net/xfrm.h | 4 ++-- net/xfrm/xfrm_policy.c | 16 ++++++++-------- net/xfrm/xfrm_state.c | 6 +++--- net/xfrm/xfrm_user.c | 14 ++++++++------ 4 files changed, 21 insertions(+), 19 deletions(-) (limited to 'include') diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 6d85861ab990..60c27706e7b9 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1367,8 +1367,8 @@ struct xfrmk_spdinfo { extern struct xfrm_state *xfrm_find_acq_byseq(struct net *net, u32 seq); extern int xfrm_state_delete(struct xfrm_state *x); extern int xfrm_state_flush(struct net *net, u8 proto, struct xfrm_audit *audit_info); -extern void xfrm_sad_getinfo(struct xfrmk_sadinfo *si); -extern void xfrm_spd_getinfo(struct xfrmk_spdinfo *si); +extern void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si); +extern void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si); extern int xfrm_replay_check(struct xfrm_state *x, struct sk_buff *skb, __be32 seq); extern void xfrm_replay_advance(struct xfrm_state *x, __be32 seq); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 4725a549ad4d..d2c8cb57ee4c 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -469,16 +469,16 @@ static inline int xfrm_byidx_should_resize(struct net *net, int total) return 0; } -void xfrm_spd_getinfo(struct xfrmk_spdinfo *si) +void xfrm_spd_getinfo(struct net *net, struct xfrmk_spdinfo *si) { read_lock_bh(&xfrm_policy_lock); - si->incnt = init_net.xfrm.policy_count[XFRM_POLICY_IN]; - si->outcnt = init_net.xfrm.policy_count[XFRM_POLICY_OUT]; - si->fwdcnt = init_net.xfrm.policy_count[XFRM_POLICY_FWD]; - si->inscnt = init_net.xfrm.policy_count[XFRM_POLICY_IN+XFRM_POLICY_MAX]; - si->outscnt = init_net.xfrm.policy_count[XFRM_POLICY_OUT+XFRM_POLICY_MAX]; - si->fwdscnt = init_net.xfrm.policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX]; - si->spdhcnt = init_net.xfrm.policy_idx_hmask; + si->incnt = net->xfrm.policy_count[XFRM_POLICY_IN]; + si->outcnt = net->xfrm.policy_count[XFRM_POLICY_OUT]; + si->fwdcnt = net->xfrm.policy_count[XFRM_POLICY_FWD]; + si->inscnt = net->xfrm.policy_count[XFRM_POLICY_IN+XFRM_POLICY_MAX]; + si->outscnt = net->xfrm.policy_count[XFRM_POLICY_OUT+XFRM_POLICY_MAX]; + si->fwdscnt = net->xfrm.policy_count[XFRM_POLICY_FWD+XFRM_POLICY_MAX]; + si->spdhcnt = net->xfrm.policy_idx_hmask; si->spdhmcnt = xfrm_policy_hashmax; read_unlock_bh(&xfrm_policy_lock); } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index d847f1a52b44..b36cc344474b 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -641,11 +641,11 @@ out: } EXPORT_SYMBOL(xfrm_state_flush); -void xfrm_sad_getinfo(struct xfrmk_sadinfo *si) +void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si) { spin_lock_bh(&xfrm_state_lock); - si->sadcnt = init_net.xfrm.state_num; - si->sadhcnt = init_net.xfrm.state_hmask; + si->sadcnt = net->xfrm.state_num; + si->sadhcnt = net->xfrm.state_hmask; si->sadhmcnt = xfrm_state_hashmax; spin_unlock_bh(&xfrm_state_lock); } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 1ada6186933c..d5a712976004 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -781,7 +781,8 @@ static inline size_t xfrm_spdinfo_msgsize(void) + nla_total_size(sizeof(struct xfrmu_spdhinfo)); } -static int build_spdinfo(struct sk_buff *skb, u32 pid, u32 seq, u32 flags) +static int build_spdinfo(struct sk_buff *skb, struct net *net, + u32 pid, u32 seq, u32 flags) { struct xfrmk_spdinfo si; struct xfrmu_spdinfo spc; @@ -795,7 +796,7 @@ static int build_spdinfo(struct sk_buff *skb, u32 pid, u32 seq, u32 flags) f = nlmsg_data(nlh); *f = flags; - xfrm_spd_getinfo(&si); + xfrm_spd_getinfo(net, &si); spc.incnt = si.incnt; spc.outcnt = si.outcnt; spc.fwdcnt = si.fwdcnt; @@ -828,7 +829,7 @@ static int xfrm_get_spdinfo(struct sk_buff *skb, struct nlmsghdr *nlh, if (r_skb == NULL) return -ENOMEM; - if (build_spdinfo(r_skb, spid, seq, *flags) < 0) + if (build_spdinfo(r_skb, net, spid, seq, *flags) < 0) BUG(); return nlmsg_unicast(net->xfrm.nlsk, r_skb, spid); @@ -841,7 +842,8 @@ static inline size_t xfrm_sadinfo_msgsize(void) + nla_total_size(4); /* XFRMA_SAD_CNT */ } -static int build_sadinfo(struct sk_buff *skb, u32 pid, u32 seq, u32 flags) +static int build_sadinfo(struct sk_buff *skb, struct net *net, + u32 pid, u32 seq, u32 flags) { struct xfrmk_sadinfo si; struct xfrmu_sadhinfo sh; @@ -854,7 +856,7 @@ static int build_sadinfo(struct sk_buff *skb, u32 pid, u32 seq, u32 flags) f = nlmsg_data(nlh); *f = flags; - xfrm_sad_getinfo(&si); + xfrm_sad_getinfo(net, &si); sh.sadhmcnt = si.sadhmcnt; sh.sadhcnt = si.sadhcnt; @@ -882,7 +884,7 @@ static int xfrm_get_sadinfo(struct sk_buff *skb, struct nlmsghdr *nlh, if (r_skb == NULL) return -ENOMEM; - if (build_sadinfo(r_skb, spid, seq, *flags) < 0) + if (build_sadinfo(r_skb, net, spid, seq, *flags) < 0) BUG(); return nlmsg_unicast(net->xfrm.nlsk, r_skb, spid); -- cgit v1.2.3 From d7c7544c3d5f59033d1bf3236bc7b289f5f26b75 Mon Sep 17 00:00:00 2001 From: Alexey Dobriyan Date: Sun, 24 Jan 2010 22:47:53 -0800 Subject: netns xfrm: deal with dst entries in netns GC is non-existent in netns, so after you hit GC threshold, no new dst entries will be created until someone triggers cleanup in init_net. Make xfrm4_dst_ops and xfrm6_dst_ops per-netns. This is not done in a generic way, because it woule waste (AF_MAX - 2) * sizeof(struct dst_ops) bytes per-netns. Reorder GC threshold initialization so it'd be done before registering XFRM policies. Signed-off-by: Alexey Dobriyan Signed-off-by: David S. Miller --- include/net/netns/xfrm.h | 6 +++++ net/ipv4/xfrm4_policy.c | 14 +++++++----- net/ipv6/xfrm6_policy.c | 25 +++++++++++--------- net/xfrm/xfrm_policy.c | 59 +++++++++++++++++++++++++++++++++++++++++++++--- 4 files changed, 84 insertions(+), 20 deletions(-) (limited to 'include') diff --git a/include/net/netns/xfrm.h b/include/net/netns/xfrm.h index 56f8e5585df7..74f119a2829a 100644 --- a/include/net/netns/xfrm.h +++ b/include/net/netns/xfrm.h @@ -5,6 +5,7 @@ #include #include #include +#include struct ctl_table_header; @@ -42,6 +43,11 @@ struct netns_xfrm { unsigned int policy_count[XFRM_POLICY_MAX * 2]; struct work_struct policy_hash_work; + struct dst_ops xfrm4_dst_ops; +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + struct dst_ops xfrm6_dst_ops; +#endif + struct sock *nlsk; struct sock *nlsk_stash; diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 8c08a28d8f83..67107d63c1cd 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -15,7 +15,6 @@ #include #include -static struct dst_ops xfrm4_dst_ops; static struct xfrm_policy_afinfo xfrm4_policy_afinfo; static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, @@ -190,8 +189,10 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) static inline int xfrm4_garbage_collect(struct dst_ops *ops) { - xfrm4_policy_afinfo.garbage_collect(&init_net); - return (atomic_read(&xfrm4_dst_ops.entries) > xfrm4_dst_ops.gc_thresh*2); + struct net *net = container_of(ops, struct net, xfrm.xfrm4_dst_ops); + + xfrm4_policy_afinfo.garbage_collect(net); + return (atomic_read(&ops->entries) > ops->gc_thresh * 2); } static void xfrm4_update_pmtu(struct dst_entry *dst, u32 mtu) @@ -268,7 +269,7 @@ static struct xfrm_policy_afinfo xfrm4_policy_afinfo = { static struct ctl_table xfrm4_policy_table[] = { { .procname = "xfrm4_gc_thresh", - .data = &xfrm4_dst_ops.gc_thresh, + .data = &init_net.xfrm.xfrm4_dst_ops.gc_thresh, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, @@ -295,8 +296,6 @@ static void __exit xfrm4_policy_fini(void) void __init xfrm4_init(int rt_max_size) { - xfrm4_state_init(); - xfrm4_policy_init(); /* * Select a default value for the gc_thresh based on the main route * table hash size. It seems to me the worst case scenario is when @@ -308,6 +307,9 @@ void __init xfrm4_init(int rt_max_size) * and start cleaning when were 1/2 full */ xfrm4_dst_ops.gc_thresh = rt_max_size/2; + + xfrm4_state_init(); + xfrm4_policy_init(); #ifdef CONFIG_SYSCTL sysctl_hdr = register_net_sysctl_table(&init_net, net_ipv4_ctl_path, xfrm4_policy_table); diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 7254e3f899a7..dbdc696f5fc5 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -24,7 +24,6 @@ #include #endif -static struct dst_ops xfrm6_dst_ops; static struct xfrm_policy_afinfo xfrm6_policy_afinfo; static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, @@ -224,8 +223,10 @@ _decode_session6(struct sk_buff *skb, struct flowi *fl, int reverse) static inline int xfrm6_garbage_collect(struct dst_ops *ops) { - xfrm6_policy_afinfo.garbage_collect(&init_net); - return (atomic_read(&xfrm6_dst_ops.entries) > xfrm6_dst_ops.gc_thresh*2); + struct net *net = container_of(ops, struct net, xfrm.xfrm6_dst_ops); + + xfrm6_policy_afinfo.garbage_collect(net); + return (atomic_read(&ops->entries) > ops->gc_thresh * 2); } static void xfrm6_update_pmtu(struct dst_entry *dst, u32 mtu) @@ -310,7 +311,7 @@ static void xfrm6_policy_fini(void) static struct ctl_table xfrm6_policy_table[] = { { .procname = "xfrm6_gc_thresh", - .data = &xfrm6_dst_ops.gc_thresh, + .data = &init_net.xfrm.xfrm6_dst_ops.gc_thresh, .maxlen = sizeof(int), .mode = 0644, .proc_handler = proc_dointvec, @@ -326,13 +327,6 @@ int __init xfrm6_init(void) int ret; unsigned int gc_thresh; - ret = xfrm6_policy_init(); - if (ret) - goto out; - - ret = xfrm6_state_init(); - if (ret) - goto out_policy; /* * We need a good default value for the xfrm6 gc threshold. * In ipv4 we set it to the route hash table size * 8, which @@ -346,6 +340,15 @@ int __init xfrm6_init(void) */ gc_thresh = FIB6_TABLE_HASHSZ * 8; xfrm6_dst_ops.gc_thresh = (gc_thresh < 1024) ? 1024 : gc_thresh; + + ret = xfrm6_policy_init(); + if (ret) + goto out; + + ret = xfrm6_state_init(); + if (ret) + goto out_policy; + #ifdef CONFIG_SYSCTL sysctl_hdr = register_net_sysctl_table(&init_net, net_ipv6_ctl_path, xfrm6_policy_table); diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index d2c8cb57ee4c..0ecb16a9a883 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1309,15 +1309,28 @@ static inline int xfrm_get_tos(struct flowi *fl, int family) return tos; } -static inline struct xfrm_dst *xfrm_alloc_dst(int family) +static inline struct xfrm_dst *xfrm_alloc_dst(struct net *net, int family) { struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); + struct dst_ops *dst_ops; struct xfrm_dst *xdst; if (!afinfo) return ERR_PTR(-EINVAL); - xdst = dst_alloc(afinfo->dst_ops) ?: ERR_PTR(-ENOBUFS); + switch (family) { + case AF_INET: + dst_ops = &net->xfrm.xfrm4_dst_ops; + break; +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + case AF_INET6: + dst_ops = &net->xfrm.xfrm6_dst_ops; + break; +#endif + default: + BUG(); + } + xdst = dst_alloc(dst_ops) ?: ERR_PTR(-ENOBUFS); xfrm_policy_put_afinfo(afinfo); @@ -1366,6 +1379,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, struct flowi *fl, struct dst_entry *dst) { + struct net *net = xp_net(policy); unsigned long now = jiffies; struct net_device *dev; struct dst_entry *dst_prev = NULL; @@ -1389,7 +1403,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, dst_hold(dst); for (; i < nx; i++) { - struct xfrm_dst *xdst = xfrm_alloc_dst(family); + struct xfrm_dst *xdst = xfrm_alloc_dst(net, family); struct dst_entry *dst1 = &xdst->u.dst; err = PTR_ERR(xdst); @@ -2279,6 +2293,7 @@ EXPORT_SYMBOL(xfrm_bundle_ok); int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) { + struct net *net; int err = 0; if (unlikely(afinfo == NULL)) return -EINVAL; @@ -2302,6 +2317,27 @@ int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo) xfrm_policy_afinfo[afinfo->family] = afinfo; } write_unlock_bh(&xfrm_policy_afinfo_lock); + + rtnl_lock(); + for_each_net(net) { + struct dst_ops *xfrm_dst_ops; + + switch (afinfo->family) { + case AF_INET: + xfrm_dst_ops = &net->xfrm.xfrm4_dst_ops; + break; +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + case AF_INET6: + xfrm_dst_ops = &net->xfrm.xfrm6_dst_ops; + break; +#endif + default: + BUG(); + } + *xfrm_dst_ops = *afinfo->dst_ops; + } + rtnl_unlock(); + return err; } EXPORT_SYMBOL(xfrm_policy_register_afinfo); @@ -2332,6 +2368,22 @@ int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo) } EXPORT_SYMBOL(xfrm_policy_unregister_afinfo); +static void __net_init xfrm_dst_ops_init(struct net *net) +{ + struct xfrm_policy_afinfo *afinfo; + + read_lock_bh(&xfrm_policy_afinfo_lock); + afinfo = xfrm_policy_afinfo[AF_INET]; + if (afinfo) + net->xfrm.xfrm4_dst_ops = *afinfo->dst_ops; +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) + afinfo = xfrm_policy_afinfo[AF_INET6]; + if (afinfo) + net->xfrm.xfrm6_dst_ops = *afinfo->dst_ops; +#endif + read_unlock_bh(&xfrm_policy_afinfo_lock); +} + static struct xfrm_policy_afinfo *xfrm_policy_get_afinfo(unsigned short family) { struct xfrm_policy_afinfo *afinfo; @@ -2494,6 +2546,7 @@ static int __net_init xfrm_net_init(struct net *net) rv = xfrm_policy_init(net); if (rv < 0) goto out_policy; + xfrm_dst_ops_init(net); rv = xfrm_sysctl_init(net); if (rv < 0) goto out_sysctl; -- cgit v1.2.3