- 23 Sep, 2017 6 commits
-
-
David S. Miller authored
Josef Bacik says: ==================== net: fix reuseaddr regression I introduced a regression when reworking the fastreuse port stuff that allows bind conflicts to occur once a reuseaddr successfully opens on an existing tb. The root cause is I reversed an if statement which caused us to set the tb as if there were no owners on the socket if there were, which obviously is not correct. Dave could you please queue these changes up for -stable, I've run them through the net tests and added another test to check for this problem specifically. ==================== Signed-off-by:David S. Miller <davem@davemloft.net>
-
Josef Bacik authored
When doing my reuseport rework I screwed up and changed a if (hlist_empty(&tb->owners)) to if (!hlist_empty(&tb->owners)) This is obviously bad as all of the reuseport/reuse logic was reversed, which caused weird problems like allowing an ipv4 bind conflict if we opened an ipv4 only socket on a port followed by an ipv6 only socket on the same port. Fixes: b9470c27 ("inet: kill smallest_size and smallest_port") Reported-by:
Cole Robinson <crobinso@redhat.com> Signed-off-by:
Josef Bacik <jbacik@fb.com> Signed-off-by:
-
Josef Bacik authored
In ipv6_rcv_saddr_equal() we need to use inet6_rcv_saddr(sk) for the ipv6 compare with the fast socket information to make sure we're doing the proper comparisons. Fixes: 637bc8bb ("inet: reset tb->fastreuseport when adding a reuseport sk") Reported-and-tested-by:
-
Josef Bacik authored
We need to set the tb->fast_sk_family properly so we can use the proper comparison function for all subsequent reuseport bind requests. Fixes: 637bc8bb ("inet: reset tb->fastreuseport when adding a reuseport sk") Reported-and-tested-by:
-
Willem de Bruijn authored
Zerocopy skbs frags are copied when the skb is looped to a local sock. Commit 1080e512 ("net: orphan frags on receive") introduced calls to skb_orphan_frags to deliver_skb and __netif_receive_skb for this. With msg_zerocopy, these skbs can also exist in the tx path and thus loop from dev_queue_xmit_nit. This already calls deliver_skb in its loop. But it does not orphan before a separate pt_prev->func(). Add the missing skb_orphan_frags_rx. Changes v1->v2: handle skb_orphan_frags_rx failure Fixes: 1f8b977a ("sock: enable MSG_ZEROCOPY") Signed-off-by:
Willem de Bruijn <willemb@google.com> Reviewed-by:
Eric Dumazet <edumazet@google.com> Signed-off-by:
-
Stefan Schmidt authored
Patches for ieee802154 will go through my new trees towards netdev from now on. The 6LoWPAN subsystem will stay as is (shared between ieee802154 and bluetooth) and go through the bluetooth tree as usual. Signed-off-by:
Stefan Schmidt <stefan@osg.samsung.com> Signed-off-by:
-
- 22 Sep, 2017 2 commits
-
-
Eric Dumazet authored
In linux-4.13, Wei worked hard to convert dst to a traditional refcounted model, removing GC. We now want to make sure a dst refcount can not transition from 0 back to 1. The problem here is that input path attached a not refcounted dst to an skb. Then later, because packet is forwarded and hits skb_dst_force() before exiting RCU section, we might try to take a refcount on one dst that is about to be freed, if another cpu saw 1 -> 0 transition in dst_release() and queued the dst for freeing after one RCU grace period. Lets unify skb_dst_force() and skb_dst_force_safe(), since we should always perform the complete check against dst refcount, and not assume it is not zero. Bugzilla : https://bugzilla.kernel.org/show_bug.cgi?id=197005 [ 989.919496] skb_dst_force+0x32/0x34 [ 989.919498] __dev_queue_xmit+0x1ad/0x482 [ 989.919501] ? eth_header+0x28/0xc6 [ 989.919502] dev_queue_xmit+0xb/0xd [ 989.919504] neigh_connected_output+0x9b/0xb4 [ 989.919507] ip_finish_output2+0x234/0x294 [ 989.919509] ? ipt_do_table+0x369/0x388 [ 989.919510] ip_finish_output+0x12c/0x13f [ 989.919512] ip_output+0x53/0x87 [ 989.919513] ip_forward_finish+0x53/0x5a [ 989.919515] ip_forward+0x2cb/0x3e6 [ 989.919516] ? pskb_trim_rcsum.part.9+0x4b/0x4b [ 989.919518] ip_rcv_finish+0x2e2/0x321 [ 989.919519] ip_rcv+0x26f/0x2eb [ 989.919522] ? vlan_do_receive+0x4f/0x289 [ 989.919523] __netif_receive_skb_core+0x467/0x50b [ 989.919526] ? tcp_gro_receive+0x239/0x239 [ 989.919529] ? inet_gro_receive+0x226/0x238 [ 989.919530] __netif_receive_skb+0x4d/0x5f [ 989.919532] netif_receive_skb_internal+0x5c/0xaf [ 989.919533] napi_gro_receive+0x45/0x81 [ 989.919536] ixgbe_poll+0xc8a/0xf09 [ 989.919539] ? kmem_cache_free_bulk+0x1b6/0x1f7 [ 989.919540] net_rx_action+0xf4/0x266 [ 989.919543] __do_softirq+0xa8/0x19d [ 989.919545] irq_exit+0x5d/0x6b [ 989.919546] do_IRQ+0x9c/0xb5 [ 989.919548] common_interrupt+0x93/0x93 [ 989.919548] </IRQ> Similarly dst_clone() can use dst_hold() helper to have additional debugging, as a follow up to commit 44ebe791 ("net: add debug atomic_inc_not_zero() in dst_hold()") In net-next we will convert dst atomic_t to refcount_t for peace of mind. Fixes: a4c2fd7f ("net: remove DST_NOCACHE flag") Signed-off-by:
Paweł Staszewski <pstaszewski@itcare.pl> Bisected-by:
Wei Wang <weiwan@google.com> Acked-by:
Martin KaFai Lau <kafai@fb.com> Signed-off-by:
-
Geert Uytterhoeven authored
Given NR_IRQS is 2048 on sparc64, and even 32784 on alpha, 3 digits is not enough to represent interrupt numbers on all architectures. Hence PHY interrupt numbers may be truncated during printing. Increase the buffer size from 4 to 8 bytes to fix this. Fixes: 5e369aef ("net: stmmac: Delete dead code for MDIO registration") Signed-off-by:
Geert Uytterhoeven <geert+renesas@glider.be> Reviewed-by:
Andrew Lunn <andrew@lunn.ch> Signed-off-by:
-
- 21 Sep, 2017 23 commits
-
-
David S. Miller authored
Ursula Braun says: ==================== net/smc: bug fixes 2017-09-20 here is a collection of small smc-patches built for net fixing smc problems in different areas. ==================== Signed-off-by: -
Ursula Braun authored
Usually socket closing is delayed if there is still data available in the send buffer to be transmitted. If a process is killed, the delay should be avoided. Signed-off-by:
Ursula Braun <ubraun@linux.vnet.ibm.com> Signed-off-by:
-
Ursula Braun authored
The number of outstanding work requests is limited. If all work requests are in use, tx processing is postponed to another scheduling of the tx worker. Switch to a delayed worker to have a gap for tx completion queue events before the next retry. Signed-off-by:
-
Ursula Braun authored
An out-of-sync condition can just be detected by the client. If the server receives a CLC DECLINE message indicating an out-of-sync condition for the link groups, the server must clean up the out-of-sync link group. There is no need for an extra third parameter in smc_clc_send_decline(). Signed-off-by:
-
Ursula Braun authored
Client link group creation always follows the server linkgroup creation. If peer creates a new server link group, client has to create a new client link group. If peer reuses a server link group for a new connection, client has to reuse its client link group as well. This patch introduces a longer delay for client link group removal to make sure this link group still exists, once the peer decides to reuse a server link group. This avoids out-of-sync conditions for link groups. If already scheduled, modify the delay. Signed-off-by:
-
Ursula Braun authored
The solicited flag is meaningful for the receive completion queue. Ask for next work completion of any type on the send queue. Signed-off-by:
-
Ursula Braun authored
smc_pnet_fill_entry() uses dev_get_by_name() adding a refcount to ndev. The following smc_pnet_enter() has to reduce the refcount if the entry to be added exists already in the pnet table. Signed-off-by:
-
Ursula Braun authored
smc_netinfo_by_tcpsk() looks up the routing cache. Such a lookup requires protection by an RCU read lock. Signed-off-by:
-
Hans Wippel authored
The SMC receive function currently lacks a timeout check under the condition that no data were received and no data are available. This patch adds such a check. Signed-off-by:
Hans Wippel <hwippel@linux.vnet.ibm.com> Signed-off-by:
-
Hans Wippel authored
In the infiniband part, SMC currently uses get_netdev which calls dev_hold on the returned net device. However, the SMC code never calls dev_put on that net device resulting in a wrong reference count. This patch adds a dev_put after the usage of the net device to fix the issue. Signed-off-by:
-
Thomas Meyer authored
Make sure (of/i2c/platform)_device_id tables are NULL terminated. Found by coccinelle spatch "misc/of_table.cocci" Signed-off-by:
Thomas Meyer <thomas@m3y3r.de> Signed-off-by:
-
David S. Miller authored
Nisar Sayed says: ==================== lan78xx: This series of patches are for lan78xx driver. This series of patches are for lan78xx driver. These patches fixes potential issues associated with lan78xx driver. v5 - Updated changes as per comments v4 - Updated changes to handle return values as per comments - Updated EEPROM write handling as per comments v3 - Updated chagnes as per comments v2 - Added patch version information - Added fixes tag - Updated patch description - Updated chagnes as per comments v1 - Splitted patches as per comments - Dropped "fixed_phy device support" and "Fix for system suspend" changes ==================== Signed-off-by: -
Nisar Sayed authored
Use default value of auto duplex and auto speed values loaded from EEPROM/OTP after reset. The LAN78xx allows platform configurations to be loaded from EEPROM/OTP. Ex: When external phy is connected, the MAC can be configured to have correct auto speed, auto duplex, auto polarity configured from the EEPROM/OTP. Fixes: 55d7de9d ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver") Signed-off-by:
Nisar Sayed <Nisar.Sayed@microchip.com> Signed-off-by:
-
Nisar Sayed authored
Allow EEPROM write for less than MAX_EEPROM_SIZE Fixes: 55d7de9d ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver") Signed-off-by:
-
Nisar Sayed authored
Fix for eeprom read/write when device auto suspend Fixes: 55d7de9d ("Microchip's LAN7800 family USB 2/3 to 10/100/1000 Ethernet device driver") Signed-off-by:
-
David S. Miller authored
Florian Fainelli says: ==================== net: Bring back transceiver type for PHYLIB With the introduction of the xLINKSETTINGS ethtool APIs, the transceiver type was deprecated, but in that process we lost some useful information that PHYLIB was consistently reporting about internal vs. external PHYs. This brings back transceiver as a read-only field that is only consumed in the legacy path where ETHTOOL_GET is called but the underlying drivers implement the new style klink_settings API. ==================== Signed-off-by: -
Florian Fainelli authored
With commit 2d55173e ("phy: add generic function to support ksetting support"), we lost the ability to report the transceiver type like we used to. Now that we have added back the transceiver type to ethtool_link_settings, we can report it back like we used to and have no loss of information. Fixes: 3f1ac7a7 ("net: ethtool: add new ETHTOOL_xLINKSETTINGS API") Fixes: 2d55173e ("phy: add generic function to support ksetting support") Signed-off-by:
Florian Fainelli <f.fainelli@gmail.com> Signed-off-by:
-
Florian Fainelli authored
Commit 3f1ac7a7 ("net: ethtool: add new ETHTOOL_xLINKSETTINGS API") deprecated the ethtool_cmd::transceiver field, which was fine in premise, except that the PHY library was actually using it to report the type of transceiver: internal or external. Use the first word of the reserved field to put this __u8 transceiver field back in. It is made read-only, and we don't expect the ETHTOOL_xLINKSETTINGS API to be doing anything with this anyway, so this is mostly for the legacy path where we do: ethtool_get_settings() -> dev->ethtool_ops->get_link_ksettings() -> convert_link_ksettings_to_legacy_settings() to have no information loss compared to the legacy get_settings API. Fixes: 3f1ac7a7 ("net: ethtool: add new ETHTOOL_xLINKSETTINGS API") Signed-off-by:
-
Timur Tabi authored
The EMAC has the option of sending only a single pause frame when flow control is enabled and the RX queue is full. Although sending only one pause frame has little value, this would allow admins to enable automatic flow control without having to worry about the EMAC flooding nearby switches with pause frames if the kernel hangs. The option is enabled by using the single-pause-mode private flag. Signed-off-by:
Timur Tabi <timur@codeaurora.org> Signed-off-by:
-
Alex Ng authored
If MTU is changed the host would reject the send buffer change. This problem is result of recent change to allow changing send buffer size. Every time we change the MTU, we store the previous net_device section count before destroying the buffer, but we don’t store the previous section size. When we reinitialize the buffer, its size is calculated by multiplying the previous count and previous size. Since we continuously increase the MTU, the host returns us a decreasing count value while the section size is reinitialized to 1728 bytes every time. This eventually leads to a condition where the calculated buf_size is so small that the host rejects it. Fixes: 8b532797 ("netvsc: allow controlling send/recv buffer size") Signed-off-by:
Alex Ng <alexng@microsoft.com> Signed-off-by:
Stephen Hemminger <sthemmin@microsoft.com> Signed-off-by:
-
Cong Wang authored
Fixes: c15ab236 ("net/sched: Change cls_flower to use IDR") Cc: Chris Mi <chrism@mellanox.com> Cc: Jiri Pirko <jiri@mellanox.com> Signed-off-by:
Cong Wang <xiyou.wangcong@gmail.com> Acked-by:
Jiri Pirko <jiri@mellanox.com> Signed-off-by:
-
Konstantin Khlebnikov authored
If real-time or fair-share curves are enabled in hfsc_change_class() class isn't inserted into rb-trees yet. Thus init_ed() and init_vf() must be called in place of update_ed() and update_vf(). Remove isn't required because for now curves cannot be disabled. Signed-off-by:
Konstantin Khlebnikov <khlebnikov@yandex-team.ru> Signed-off-by:
-
Konstantin Khlebnikov authored
SKB stored in qdisc->gso_skb also counted into backlog. Some qdiscs don't reset backlog to zero in ->reset(), for example sfq just dequeue and free all queued skb. Signed-off-by:
-
- 20 Sep, 2017 9 commits
-
-
David S. Miller authored
Yunsheng Lin says: ==================== TM related bugfixes for the HNS3 Ethernet Driver This patch set contains a few bugfixes related to hclge_tm module. ==================== Signed-off-by: -
Yunsheng Lin authored
Current mapping between pri and tc is one to one, so user can't map multi priorities to the same tc. This patch changes the mapping to many to one. Fixes: 84844054 ("net: hns3: Add support of TX Scheduler & Shaper to HNS3 driver") Signed-off-by:
Yunsheng Lin <linyunsheng@huawei.com> Signed-off-by:
-
Yunsheng Lin authored
rss_size is 1, 2, 4, 8, 16, 32, 64, 128, but acutal tc queue size can be any u16 less than 128. If tc queue size is 5, we set the rss_size to 8, indirection table will be used to limit the size of actual queue size. It may cause dropping of receiving packet in hardware if rss_size is not set correctly. For now, each TC has the same rss size. Fixes: 46a3df9f ("net: hns3: Add HNS3 Acceleration Engine & Compatibility Layer Support") Signed-off-by:
-
Yunsheng Lin authored
This patch fixes a typo error for feild, which should be field. Fixes: 84844054 ("net: hns3: Add support of TX Scheduler & Shaper to HNS3 driver") Signed-off-by:
-
Yunsheng Lin authored
When hdev doesn't support DCB, rx private buffer is not allocated, otherwise there is not enough buffer for rx shared buffer, causing buffer allocation process to fail. This patch fixes by checking the dcb capability in hclge_rx_buffer_calc. Fixes: 46a3df9f ("net: hns3: Add HNS3 Acceleration Engine & Compatibility Layer Support") Signed-off-by:
-
Yunsheng Lin authored
rx_priv_buf_alloc is used to tell hardware how much buffer is used for rx direction, right now only the private buffer is assigned. For ae_dev that doesn't support DCB, private rx buffer is assigned to zero, only shared rx buffer is used. So not setting the shared rx buffer cause dropping of packet in SSU. Fixes: 46a3df9f ("net: hns3: Add HNS3 Acceleration Engine & Compatibility Layer Support") Signed-off-by:
-
Yunsheng Lin authored
When rx private buffer is disabled, there may be some case that the rx private buffer is not set to zero, which may cause buffer allocation process to fail. This patch fixes this problem by setting priv->enable to 0 and priv->buf_size to zero when rx private buffer is disabled. Fixes: 46a3df9f ("net: hns3: Add HNS3 Acceleration Engine & Compatibility Layer Support") Signed-off-by:
-
Yunsheng Lin authored
When ae_dev doesn't support DCB, DEFAULT_DV must be set to a lower value, otherwise the buffer allocation process will fail. This patch fix it by setting it to 30K bytes. Fixes: 46a3df9f ("net: hns3: Add HNS3 Acceleration Engine & Compatibility Layer Support") Signed-off-by:
-
Yunsheng Lin authored
When ae_dev doesn't support DCB, rx_priv_wl_config, common_thrd_config and tm_qs_bp_cfg can't be called, otherwise cmd return fail, which causes the hclge module initialization process to fail. This patch fix it by adding a DCB capability flag to check if the ae_dev support DCB. Fixes: 46a3df9f ("net: hns3: Add HNS3 Acceleration Engine & Compatibility Layer Support") Signed-off-by:
-
