pull request for net: batman-adv 2023-08-16
Subsystems (4)
Simon Wunderlich
maintainercover pull request for net: batman-adv 2023-08-16
Hi David, hi Jakub,
here are a few bugfixes for batman-adv which we would like to have integrated into net.
Please pull or let me know of any problem!
Thank you,
Simon
The following changes since commit 06c2afb862f9da8dc5efa4b6076a0e48c3fbaaa5:
Linux 6.5-rc1 (2023-07-09 13:53:13 -0700)
are available in the Git repository at:
git://git.open-mesh.org/linux-merge.git tags/batadv-net-pullrequest-20230816
for you to fetch changes up to 421d467dc2d483175bad4fb76a31b9e5a3d744cf:
batman-adv: Fix batadv_v_ogm_aggr_send memory leak (2023-08-09 17:33:03 +0200)
----------------------------------------------------------------
Here are some batman-adv bugfixes:
- Fix issues with adjusted MTUs (2 patches), by Sven Eckelmann
- Fix header access for memory reallocation case, by Remi Pommarel
- Fix two memory leaks (2 patches), by Remi Pommarel
----------------------------------------------------------------
Remi Pommarel (3):
batman-adv: Do not get eth header before batadv_check_management_packet
batman-adv: Fix TT global entry leak when client roamed back
batman-adv: Fix batadv_v_ogm_aggr_send memory leak
Sven Eckelmann (2):
batman-adv: Trigger events for auto adjusted MTU
batman-adv: Don't increase MTU when set by user
net/batman-adv/bat_v_elp.c | 3 ++- net/batman-adv/bat_v_ogm.c | 7 +++++-- net/batman-adv/hard-interface.c | 14 +++++++++++++- net/batman-adv/soft-interface.c | 3 +++ net/batman-adv/translation-table.c | 1 - net/batman-adv/types.h | 6 ++++++ 6 files changed, 29 insertions(+), 5 deletions(-)
Simon Wunderlich
maintainerPATCH 1/5 batman-adv: Trigger events for auto adjusted MTU
From: Sven Eckelmann <[email protected]>
If an interface changes the MTU, it is expected that an NETDEV_PRECHANGEMTU and NETDEV_CHANGEMTU notification events is triggered. This worked fine for .ndo_change_mtu based changes because core networking code took care of it. But for auto-adjustments after hard-interfaces changes, these events were simply missing.
Due to this problem, non-batman-adv components weren't aware of MTU changes and thus couldn't perform their own tasks correctly.
--- net/batman-adv/hard-interface.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-)
net/batman-adv/hard-interface.c +1 -1
@@ -630,7 +630,7 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface)*/ void batadv_update_min_mtu (struct net_device *soft_iface) { - soft_iface->mtu =batadv_hardif_min_mtu (soft_iface); +dev_set_mtu (soft_iface,batadv_hardif_min_mtu (soft_iface));/* Check if the local translate table should be cleaned up to match a * new (and smaller) MTU.
Signature · 1 line
2.39.2
Re: [PATCH 1/5] batman-adv: Trigger events for auto adjusted MTU
This series was applied to netdev/net.git (main) by Simon Wunderlich <[email protected]>:
Hello:
This series was applied to netdev/net.git (main)
by Simon Wunderlich <[email protected]>:
Quoted 9 lines · On Wed, 16 Aug 2023 18:33:14 +0200 you wrote:
From: Sven Eckelmann <[email protected]>
If an interface changes the MTU, it is expected that an
NETDEV_PRECHANGEMTUandNETDEV_CHANGEMTUnotification events is triggered. This worked fine for .ndo_change_mtu based changes because core networking code took care of it. But for auto-adjustments after hard-interfaces changes, these events were simply missing.[...]
Here is the summary with links:
- [1/5] batman-adv: Trigger events for auto adjusted MTU
https://git.kernel.org/netdev/net/c/c6a953cce8d0 - [2/5] batman-adv: Don't increase MTU when set by user https://git.kernel.org/netdev/net/c/d8e42a2b0add - [3/5] batman-adv: Do not get eth header before batadv_check_management_packet https://git.kernel.org/netdev/net/c/eac27a41ab64 - [4/5] batman-adv: Fix TT global entry leak when client roamed back https://git.kernel.org/netdev/net/c/d25ddb7e788d - [5/5] batman-adv: Fix batadv_v_ogm_aggr_send memory leak https://git.kernel.org/netdev/net/c/421d467dc2d4
You are awesome, thank you!
Signature · 2 lines
Deet-doot-dot, I am a bot. https://korg.docs.kernel.org/patchwork/pwbot.html
Simon Wunderlich
maintainerPATCH 2/5 batman-adv: Don't increase MTU when set by user
In reply to Simon WunderlichFrom: Sven Eckelmann <[email protected]>
If the user set an MTU value, it usually means that there are special requirements for the MTU. But if an interface gots activated, the MTU was always recalculated and then the user set value was overwritten.
The only reason why this user set value has to be overwritten, is when the MTU has to be decreased because batman-adv is not able to transfer packets with the user specified size.
--- net/batman-adv/hard-interface.c | 14 +++++++++++++- net/batman-adv/soft-interface.c | 3 +++ net/batman-adv/types.h | 6 ++++++ 3 files changed, 22 insertions(+), 1 deletion(-)
net/batman-adv/hard-interface.c +13 -1
@@ -630,7 +630,19 @@ int batadv_hardif_min_mtu(struct net_device *soft_iface)*/ void batadv_update_min_mtu (struct net_device *soft_iface) { -dev_set_mtu (soft_iface,batadv_hardif_min_mtu (soft_iface)); +struct batadv_priv *bat_priv =netdev_priv (soft_iface); +int limit_mtu; +int mtu; + + mtu =batadv_hardif_min_mtu (soft_iface); + +if (bat_priv->mtu_set_by_user) + limit_mtu = bat_priv->mtu_set_by_user; +else + limit_mtu =ETH_DATA_LEN ; + + mtu =min (mtu, limit_mtu); +dev_set_mtu (soft_iface, mtu);/* Check if the local translate table should be cleaned up to match a * new (and smaller) MTU.
net/batman-adv/soft-interface.c +3 -0
@@ -153,11 +153,14 @@ static int batadv_interface_set_mac_addr(struct net_device *dev, void *p)static int batadv_interface_change_mtu (struct net_device *dev,int new_mtu) { +struct batadv_priv *bat_priv =netdev_priv (dev); +/* check ranges */ if (new_mtu <68 || new_mtu >batadv_hardif_min_mtu (dev))return -EINVAL ; dev->mtu = new_mtu; + bat_priv->mtu_set_by_user = new_mtu;return 0 ; }
net/batman-adv/types.h +6 -0
@@ -1546,6 +1546,12 @@ struct batadv_priv {/** @soft_iface: net device which holds this struct as private data */ struct net_device *soft_iface; +/** +* @mtu_set_by_user: MTU was set once by user +* protected by rtnl_lock +*/ +int mtu_set_by_user; +/** * @bat_counters: mesh internal traffic statistic counters (see * batadv_counters)
Signature · 1 line
2.39.2
Simon Wunderlich
maintainerPATCH 3/5 batman-adv: Do not get eth header before batadv_check_management_packet
In reply to Simon WunderlichFrom: Remi Pommarel <[email protected]>
If received skb in batadv_v_elp_packet_recv or batadv_v_ogm_packet_recv is either cloned or non linearized then its data buffer will be reallocated by batadv_check_management_packet when skb_cow or skb_linearize get called. Thus geting ethernet header address inside skb data buffer before batadv_check_management_packet had any chance to reallocate it could lead to the following kernel panic:
Unable to handle kernel paging request at virtual address ffffff8020ab069a
Mem abort info:
ESR = 0x96000007
EC = 0x25: DABT (current EL), IL = 32 bits
SET = 0, FnV = 0
EA = 0, S1PTW = 0
FSC = 0x07: level 3 translation fault
Data abort info:
ISV = 0, ISS = 0x00000007
CM = 0, WnR = 0
swapper pgtable: 4k pages, 39-bit VAs, pgdp=0000000040f45000
[ffffff8020ab069a] pgd=180000007fffa003, p4d=180000007fffa003, pud=180000007fffa003, pmd=180000007fefe003, pte=0068000020ab0706
Internal error: Oops: 96000007 [#1] SMP
Modules linked in: ahci_mvebu libahci_platform libahci dvb_usb_af9035 dvb_usb_dib0700 dib0070 dib7000m dibx000_common ath11k_pci ath10k_pci ath10k_core mwl8k_new nf_nat_sip nf_conntrack_sip xhci_plat_hcd xhci_hcd nf_nat_pptp nf_conntrack_pptp at24 sbsa_gwdt
CPU: 1 PID: 16 Comm: ksoftirqd/1 Not tainted 5.15.42-00066-g3242268d425c-dirty #550
Hardware name: A8k (DT)
pstate: 60000005 (nZCv daif -PAN -UAO -TCO -DIT -SSBS BTYPE=--)
pc : batadv_is_my_mac+0x60/0xc0
lr : batadv_v_ogm_packet_recv+0x98/0x5d0
sp : ffffff8000183820
x29: ffffff8000183820 x28: 0000000000000001 x27: ffffff8014f9af00
x26: 0000000000000000 x25: 0000000000000543 x24: 0000000000000003
x23: ffffff8020ab0580 x22: 0000000000000110 x21: ffffff80168ae880
x20: 0000000000000000 x19: ffffff800b561000 x18: 0000000000000000
x17: 0000000000000000 x16: 0000000000000000 x15: 00dc098924ae0032
x14: 0f0405433e0054b0 x13: ffffffff00000080 x12: 0000004000000001
x11: 0000000000000000 x10: 0000000000000000 x9 : 0000000000000000
x8 : 0000000000000000 x7 : ffffffc076dae000 x6 : ffffff8000183700
x5 : ffffffc00955e698 x4 : ffffff80168ae000 x3 : ffffff80059cf000
x2 : ffffff800b561000 x1 : ffffff8020ab0696 x0 : ffffff80168ae880
Call trace:
batadv_is_my_mac+0x60/0xc0
batadv_v_ogm_packet_recv+0x98/0x5d0
batadv_batman_skb_recv+0x1b8/0x244
__netif_receive_skb_core.isra.0+0x440/0xc74
__netif_receive_skb_one_core+0x14/0x20
netif_receive_skb+0x68/0x140
br_pass_frame_up+0x70/0x80
br_handle_frame_finish+0x108/0x284
br_handle_frame+0x190/0x250
__netif_receive_skb_core.isra.0+0x240/0xc74
__netif_receive_skb_list_core+0x6c/0x90
netif_receive_skb_list_internal+0x1f4/0x310
napi_complete_done+0x64/0x1d0
gro_cell_poll+0x7c/0xa0
__napi_poll+0x34/0x174
net_rx_action+0xf8/0x2a0
_stext+0x12c/0x2ac
run_ksoftirqd+0x4c/0x7c
smpboot_thread_fn+0x120/0x210
kthread+0x140/0x150
ret_from_fork+0x10/0x20
Code: f9403844 eb03009f 54fffee1 f94Thus ethernet header address should only be fetched after batadv_check_management_packet has been called.
--- net/batman-adv/bat_v_elp.c | 3 ++- net/batman-adv/bat_v_ogm.c | 3 ++- 2 files changed, 4 insertions(+), 2 deletions(-)
net/batman-adv/bat_v_elp.c +2 -1
@@ -505,7 +505,7 @@ int batadv_v_elp_packet_recv(struct sk_buff *skb,struct batadv_priv *bat_priv =netdev_priv (if_incoming->soft_iface);struct batadv_elp_packet *elp_packet;struct batadv_hard_iface *primary_if; -struct ethhdr *ethhdr = (struct ethhdr *)skb_mac_header (skb); +struct ethhdr *ethhdr;bool res;int ret =NET_RX_DROP ;
@@ -513,6 +513,7 @@ int batadv_v_elp_packet_recv(struct sk_buff *skb,if (!res) goto free_skb; + ethhdr =eth_hdr (skb);if (batadv_is_my_mac (bat_priv, ethhdr->h_source)) goto free_skb;
net/batman-adv/bat_v_ogm.c +2 -1
@@ -985,7 +985,7 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb, {struct batadv_priv *bat_priv =netdev_priv (if_incoming->soft_iface);struct batadv_ogm2_packet *ogm_packet; -struct ethhdr *ethhdr =eth_hdr (skb); +struct ethhdr *ethhdr;int ogm_offset;u8 *packet_pos;int ret =NET_RX_DROP ;
@@ -999,6 +999,7 @@ int batadv_v_ogm_packet_recv(struct sk_buff *skb,if (!batadv_check_management_packet (skb, if_incoming,BATADV_OGM2_HLEN )) goto free_skb; + ethhdr =eth_hdr (skb);if (batadv_is_my_mac (bat_priv, ethhdr->h_source)) goto free_skb;
Signature · 1 line
2.39.2
Simon Wunderlich
maintainerPATCH 4/5 batman-adv: Fix TT global entry leak when client roamed back
In reply to Simon WunderlichFrom: Remi Pommarel <[email protected]>
When a client roamed back to a node before it got time to destroy the pending local entry (i.e. within the same originator interval) the old global one is directly removed from hash table and left as such.
But because this entry had an extra reference taken at lookup (i.e using batadv_tt_global_hash_find) there is no way its memory will be reclaimed at any time causing the following memory leak:
unreferenced object 0xffff0000073c8000 (size 18560):
comm "softirq", pid 0, jiffies 4294907738 (age 228.644s)
hex dump (first 32 bytes):
06 31 ac 12 c7 7a 05 00 01 00 00 00 00 00 00 00 .1...z..........
2c ad be 08 00 80 ff ff 6c b6 be 08 00 80 ff ff ,.......l.......
backtrace:
[<00000000ee6e0ffa>] kmem_cache_alloc+0x1b4/0x300
[<000000000ff2fdbc>] batadv_tt_global_add+0x700/0xe20
[<00000000443897c7>] _batadv_tt_update_changes+0x21c/0x790
[<000000005dd90463>] batadv_tt_update_changes+0x3c/0x110
[<00000000a2d7fc57>] batadv_tt_tvlv_unicast_handler_v1+0xafc/0xe10
[<0000000011793f2a>] batadv_tvlv_containers_process+0x168/0x2b0
[<00000000b7cbe2ef>] batadv_recv_unicast_tvlv+0xec/0x1f4
[<0000000042aef1d8>] batadv_batman_skb_recv+0x25c/0x3a0
[<00000000bbd8b0a2>] __netif_receive_skb_core.isra.0+0x7a8/0xe90
[<000000004033d428>] __netif_receive_skb_one_core+0x64/0x74
[<000000000f39a009>] __netif_receive_skb+0x48/0xe0
[<00000000f2cd8888>] process_backlog+0x174/0x344
[<00000000507d6564>] __napi_poll+0x58/0x1f4
[<00000000b64ef9eb>] net_rx_action+0x504/0x590
[<00000000056fa5e4>] _stext+0x1b8/0x418
[<00000000878879d6>] run_ksoftirqd+0x74/0xa4
unreferenced object 0xffff00000bae1a80 (size 56):
comm "softirq", pid 0, jiffies 4294910888 (age 216.092s)
hex dump (first 32 bytes):
00 78 b1 0b 00 00 ff ff 0d 50 00 00 00 00 00 00 .x.......P......
00 00 00 00 00 00 00 00 50 c8 3c 07 00 00 ff ff ........P.<.....
backtrace:
[<00000000ee6e0ffa>] kmem_cache_alloc+0x1b4/0x300
[<00000000d9aaa49e>] batadv_tt_global_add+0x53c/0xe20
[<00000000443897c7>] _batadv_tt_update_changes+0x21c/0x790
[<000000005dd90463>] batadv_tt_update_changes+0x3c/0x110
[<00000000a2d7fc57>] batadv_tt_tvlv_unicast_handler_v1+0xafc/0xe10
[<0000000011793f2a>] batadv_tvlv_containers_process+0x168/0x2b0
[<00000000b7cbe2ef>] batadv_recv_unicast_tvlv+0xec/0x1f4
[<0000000042aef1d8>] batadv_batman_skb_recv+0x25c/0x3a0
[<00000000bbd8b0a2>] __netif_receive_skb_core.isra.0+0x7a8/0xe90
[<000000004033d428>] __netif_receive_skb_one_core+0x64/0x74
[<000000000f39a009>] __netif_receive_skb+0x48/0xe0
[<00000000f2cd8888>] process_backlog+0x174/0x344
[<00000000507d6564>] __napi_poll+0x58/0x1f4
[<00000000b64ef9eb>] net_rx_action+0x504/0x590
[<00000000056fa5e4>] _stext+0x1b8/0x418
[<00000000878879d6>] run_ksoftirqd+0x74/0xa4Releasing the extra reference from batadv_tt_global_hash_find even at roam back when batadv_tt_global_free is called fixes this memory leak.
Signed-off-by; Sven Eckelmann <[email protected]>
--- net/batman-adv/translation-table.c | 1 - 1 file changed, 1 deletion(-)
net/batman-adv/translation-table.c +0 -1
@@ -774,7 +774,6 @@ bool batadv_tt_local_add(struct net_device *soft_iface, const u8 *addr,if (roamed_back) {batadv_tt_global_free (bat_priv, tt_global,"Roaming canceled" ); - tt_global =NULL ; }else {/* The global entry has to be marked as ROAMING and * has to be kept for consistency purpose
Signature · 1 line
2.39.2
Simon Wunderlich
maintainerPATCH 5/5 batman-adv: Fix batadv_v_ogm_aggr_send memory leak
In reply to Simon WunderlichFrom: Remi Pommarel <[email protected]>
When batadv_v_ogm_aggr_send is called for an inactive interface, the skb is silently dropped by batadv_v_ogm_send_to_if() but never freed causing the following memory leak:
unreferenced object 0xffff00000c164800 (size 512):
comm "kworker/u8:1", pid 2648, jiffies 4295122303 (age 97.656s)
hex dump (first 32 bytes):
00 80 af 09 00 00 ff ff e1 09 00 00 75 01 60 83 ............u.`.
1f 00 00 00 b8 00 00 00 15 00 05 00 da e3 d3 64 ...............d
backtrace:
[<0000000007ad20f6>] __kmalloc_track_caller+0x1a8/0x310
[<00000000d1029e55>] kmalloc_reserve.constprop.0+0x70/0x13c
[<000000008b9d4183>] __alloc_skb+0xec/0x1fc
[<00000000c7af5051>] __netdev_alloc_skb+0x48/0x23c
[<00000000642ee5f5>] batadv_v_ogm_aggr_send+0x50/0x36c
[<0000000088660bd7>] batadv_v_ogm_aggr_work+0x24/0x40
[<0000000042fc2606>] process_one_work+0x3b0/0x610
[<000000002f2a0b1c>] worker_thread+0xa0/0x690
[<0000000059fae5d4>] kthread+0x1fc/0x210
[<000000000c587d3a>] ret_from_fork+0x10/0x20Free the skb in that case to fix this leak.
--- net/batman-adv/bat_v_ogm.c | 4 +++- 1 file changed, 3 insertions(+), 1 deletion(-)
net/batman-adv/bat_v_ogm.c +3 -1
@@ -123,8 +123,10 @@ static void batadv_v_ogm_send_to_if(struct sk_buff *skb, {struct batadv_priv *bat_priv =netdev_priv (hard_iface->soft_iface); -if (hard_iface->if_status !=BATADV_IF_ACTIVE ) +if (hard_iface->if_status !=BATADV_IF_ACTIVE ) { +kfree_skb (skb);return ; + }batadv_inc_counter (bat_priv,BATADV_CNT_MGMT_TX ); batadv_add_counter(bat_priv, BATADV_CNT_MGMT_TX_BYTES,
Signature · 1 line
2.39.2