From fb7861d14c8d7edac65b2fcb6e8031cb138457b2 Mon Sep 17 00:00:00 2001 From: Taehee Yoo Date: Tue, 16 Jun 2020 15:52:05 +0000 Subject: net: core: reduce recursion limit value In the current code, ->ndo_start_xmit() can be executed recursively only 10 times because of stack memory. But, in the case of the vxlan, 10 recursion limit value results in a stack overflow. In the current code, the nested interface is limited by 8 depth. There is no critical reason that the recursion limitation value should be 10. So, it would be good to be the same value with the limitation value of nesting interface depth. Test commands: ip link add vxlan10 type vxlan vni 10 dstport 4789 srcport 4789 4789 ip link set vxlan10 up ip a a 192.168.10.1/24 dev vxlan10 ip n a 192.168.10.2 dev vxlan10 lladdr fc:22:33:44:55:66 nud permanent for i in {9..0} do let A=$i+1 ip link add vxlan$i type vxlan vni $i dstport 4789 srcport 4789 4789 ip link set vxlan$i up ip a a 192.168.$i.1/24 dev vxlan$i ip n a 192.168.$i.2 dev vxlan$i lladdr fc:22:33:44:55:66 nud permanent bridge fdb add fc:22:33:44:55:66 dev vxlan$A dst 192.168.$i.2 self done hping3 192.168.10.2 -2 -d 60000 Splat looks like: [ 103.814237][ T1127] ============================================================================= [ 103.871955][ T1127] BUG kmalloc-2k (Tainted: G B ): Padding overwritten. 0x00000000897a2e4f-0x000 [ 103.873187][ T1127] ----------------------------------------------------------------------------- [ 103.873187][ T1127] [ 103.874252][ T1127] INFO: Slab 0x000000005cccc724 objects=5 used=5 fp=0x0000000000000000 flags=0x10000000001020 [ 103.881323][ T1127] CPU: 3 PID: 1127 Comm: hping3 Tainted: G B 5.7.0+ #575 [ 103.882131][ T1127] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 103.883006][ T1127] Call Trace: [ 103.883324][ T1127] dump_stack+0x96/0xdb [ 103.883716][ T1127] slab_err+0xad/0xd0 [ 103.884106][ T1127] ? _raw_spin_unlock+0x1f/0x30 [ 103.884620][ T1127] ? get_partial_node.isra.78+0x140/0x360 [ 103.885214][ T1127] slab_pad_check.part.53+0xf7/0x160 [ 103.885769][ T1127] ? pskb_expand_head+0x110/0xe10 [ 103.886316][ T1127] check_slab+0x97/0xb0 [ 103.886763][ T1127] alloc_debug_processing+0x84/0x1a0 [ 103.887308][ T1127] ___slab_alloc+0x5a5/0x630 [ 103.887765][ T1127] ? pskb_expand_head+0x110/0xe10 [ 103.888265][ T1127] ? lock_downgrade+0x730/0x730 [ 103.888762][ T1127] ? pskb_expand_head+0x110/0xe10 [ 103.889244][ T1127] ? __slab_alloc+0x3e/0x80 [ 103.889675][ T1127] __slab_alloc+0x3e/0x80 [ 103.890108][ T1127] __kmalloc_node_track_caller+0xc7/0x420 [ ... ] Fixes: 11a766ce915f ("net: Increase xmit RECURSION_LIMIT to 10.") Signed-off-by: Taehee Yoo Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/linux') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 6fc613ed8eae..39e28e11863c 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -3157,7 +3157,7 @@ static inline int dev_recursion_level(void) return this_cpu_read(softnet_data.xmit.recursion); } -#define XMIT_RECURSION_LIMIT 10 +#define XMIT_RECURSION_LIMIT 8 static inline bool dev_xmit_recursion(void) { return unlikely(__this_cpu_read(softnet_data.xmit.recursion) > -- cgit v1.2.3 From 97dd1abd026ae4e6a82fa68645928404ad483409 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Tue, 23 Jun 2020 16:51:29 +0300 Subject: net: qed: fix left elements count calculation qed_chain_get_element_left{,_u32} returned 0 when the difference between producer and consumer page count was equal to the total page count. Fix this by conditional expanding of producer value (vs unconditional). This allowed to eliminate normalizaton against total page count, which was the cause of this bug. Misc: replace open-coded constants with common defines. Fixes: a91eb52abb50 ("qed: Revisit chain implementation") Signed-off-by: Alexander Lobakin Signed-off-by: Igor Russkikh Signed-off-by: Michal Kalderon Signed-off-by: David S. Miller --- include/linux/qed/qed_chain.h | 26 ++++++++++++++++---------- 1 file changed, 16 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/include/linux/qed/qed_chain.h b/include/linux/qed/qed_chain.h index 733fad7dfbed..6d15040c642c 100644 --- a/include/linux/qed/qed_chain.h +++ b/include/linux/qed/qed_chain.h @@ -207,28 +207,34 @@ static inline u32 qed_chain_get_cons_idx_u32(struct qed_chain *p_chain) static inline u16 qed_chain_get_elem_left(struct qed_chain *p_chain) { + u16 elem_per_page = p_chain->elem_per_page; + u32 prod = p_chain->u.chain16.prod_idx; + u32 cons = p_chain->u.chain16.cons_idx; u16 used; - used = (u16) (((u32)0x10000 + - (u32)p_chain->u.chain16.prod_idx) - - (u32)p_chain->u.chain16.cons_idx); + if (prod < cons) + prod += (u32)U16_MAX + 1; + + used = (u16)(prod - cons); if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR) - used -= p_chain->u.chain16.prod_idx / p_chain->elem_per_page - - p_chain->u.chain16.cons_idx / p_chain->elem_per_page; + used -= prod / elem_per_page - cons / elem_per_page; return (u16)(p_chain->capacity - used); } static inline u32 qed_chain_get_elem_left_u32(struct qed_chain *p_chain) { + u16 elem_per_page = p_chain->elem_per_page; + u64 prod = p_chain->u.chain32.prod_idx; + u64 cons = p_chain->u.chain32.cons_idx; u32 used; - used = (u32) (((u64)0x100000000ULL + - (u64)p_chain->u.chain32.prod_idx) - - (u64)p_chain->u.chain32.cons_idx); + if (prod < cons) + prod += (u64)U32_MAX + 1; + + used = (u32)(prod - cons); if (p_chain->mode == QED_CHAIN_MODE_NEXT_PTR) - used -= p_chain->u.chain32.prod_idx / p_chain->elem_per_page - - p_chain->u.chain32.cons_idx / p_chain->elem_per_page; + used -= (u32)(prod / elem_per_page - cons / elem_per_page); return p_chain->capacity - used; } -- cgit v1.2.3 From 3dd4ef1bdbac959bb20faec93937720ddd9917c6 Mon Sep 17 00:00:00 2001 From: Jisheng Zhang Date: Wed, 24 Jun 2020 15:58:24 +0800 Subject: net: phy: make phy_disable_interrupts() non-static We face an issue with rtl8211f, a pin is shared between INTB and PMEB, and the PHY Register Accessible Interrupt is enabled by default, so the INTB/PMEB pin is always active in polling mode case. As Heiner pointed out "I was thinking about calling phy_disable_interrupts() in phy_init_hw(), to have a defined init state as we don't know in which state the PHY is if the PHY driver is loaded. We shouldn't assume that it's the chip power-on defaults, BIOS or boot loader could have changed this. Or in case of dual-boot systems the other OS could leave the PHY in whatever state." Make phy_disable_interrupts() non-static so that it could be used in phy_init_hw() to have a defined init state. Suggested-by: Heiner Kallweit Signed-off-by: Jisheng Zhang Signed-off-by: David S. Miller --- include/linux/phy.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux') diff --git a/include/linux/phy.h b/include/linux/phy.h index 8c05d0fb5c00..b693b609b2f5 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1416,6 +1416,7 @@ int phy_ethtool_ksettings_set(struct phy_device *phydev, int phy_mii_ioctl(struct phy_device *phydev, struct ifreq *ifr, int cmd); int phy_do_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd); int phy_do_ioctl_running(struct net_device *dev, struct ifreq *ifr, int cmd); +int phy_disable_interrupts(struct phy_device *phydev); void phy_request_interrupt(struct phy_device *phydev); void phy_free_interrupt(struct phy_device *phydev); void phy_print_status(struct phy_device *phydev); -- cgit v1.2.3 From 1cbf90985f7448f1b0dd630e17ee1070f7d58665 Mon Sep 17 00:00:00 2001 From: David Wilder Date: Mon, 22 Jun 2020 10:10:11 -0700 Subject: netfilter: iptables: Split ipt_unregister_table() into pre_exit and exit helpers. The pre_exit will un-register the underlying hook and .exit will do the table freeing. The netns core does an unconditional synchronize_rcu after the pre_exit hooks insuring no packets are in flight that have picked up the pointer before completing the un-register. Fixes: b9e69e127397 ("netfilter: xtables: don't hook tables by default") Signed-off-by: David Wilder Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv4/ip_tables.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv4/ip_tables.h b/include/linux/netfilter_ipv4/ip_tables.h index b394bd4f68a3..c4676d6feeff 100644 --- a/include/linux/netfilter_ipv4/ip_tables.h +++ b/include/linux/netfilter_ipv4/ip_tables.h @@ -25,6 +25,12 @@ int ipt_register_table(struct net *net, const struct xt_table *table, const struct ipt_replace *repl, const struct nf_hook_ops *ops, struct xt_table **res); + +void ipt_unregister_table_pre_exit(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops); + +void ipt_unregister_table_exit(struct net *net, struct xt_table *table); + void ipt_unregister_table(struct net *net, struct xt_table *table, const struct nf_hook_ops *ops); -- cgit v1.2.3 From 57ea5f18882a3d7cf6135fa8c949a37c89395837 Mon Sep 17 00:00:00 2001 From: David Wilder Date: Mon, 22 Jun 2020 10:10:13 -0700 Subject: netfilter: ip6tables: Split ip6t_unregister_table() into pre_exit and exit helpers. The pre_exit will un-register the underlying hook and .exit will do the table freeing. The netns core does an unconditional synchronize_rcu after the pre_exit hooks insuring no packets are in flight that have picked up the pointer before completing the un-register. Fixes: b9e69e127397 ("netfilter: xtables: don't hook tables by default") Signed-off-by: David Wilder Signed-off-by: Pablo Neira Ayuso --- include/linux/netfilter_ipv6/ip6_tables.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'include/linux') diff --git a/include/linux/netfilter_ipv6/ip6_tables.h b/include/linux/netfilter_ipv6/ip6_tables.h index 8225f7821a29..1547d5f9ae06 100644 --- a/include/linux/netfilter_ipv6/ip6_tables.h +++ b/include/linux/netfilter_ipv6/ip6_tables.h @@ -29,6 +29,9 @@ int ip6t_register_table(struct net *net, const struct xt_table *table, const struct nf_hook_ops *ops, struct xt_table **res); void ip6t_unregister_table(struct net *net, struct xt_table *table, const struct nf_hook_ops *ops); +void ip6t_unregister_table_pre_exit(struct net *net, struct xt_table *table, + const struct nf_hook_ops *ops); +void ip6t_unregister_table_exit(struct net *net, struct xt_table *table); extern unsigned int ip6t_do_table(struct sk_buff *skb, const struct nf_hook_state *state, struct xt_table *table); -- cgit v1.2.3