- 20 Aug, 2015 2 commits
-
-
Nikolay Aleksandrov authored
While running net-next I hit this: [ 634.073119] =============================== [ 634.073150] [ INFO: suspicious RCU usage. ] [ 634.073182] 4.2.0-rc6+ #45 Not tainted [ 634.073213] ------------------------------- [ 634.073244] include/net/vrf.h:38 suspicious rcu_dereference_check() usage! [ 634.073274] other info that might help us debug this: [ 634.073307] rcu_scheduler_active = 1, debug_locks = 1 [ 634.073338] 2 locks held by swapper/0/0: [ 634.073369] #0: (((&n->timer))){+.-...}, at: [<ffffffff8112bc35>] call_timer_fn+0x5/0x480 [ 634.073412] #1: (slock-AF_INET){+.-...}, at: [<ffffffff8174f0f5>] icmp_send+0x155/0x5f0 [ 634.073450] stack backtrace: [ 634.073483] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 4.2.0-rc6+ #45 [ 634.073514] Hardware name: innotek GmbH VirtualBox/VirtualBox, BIOS VirtualBox 12/01/2006 [ 634.073545] 0000000000000000 0593ba8242d9ace4 ffff88002fc03b48 ffffffff81803f1b [ 634.073612] 0000000000000000 ffffffff81e12500 ffff88002fc03b78 ffffffff811003c5 [ 634.073642] 0000000000000000 ffff88002ec4e600 ffffffff81f00f80 ffff88002fc03cf0 [ 634.073669] Call Trace: [ 634.073694] <IRQ> [<ffffffff81803f1b>] dump_stack+0x4c/0x65 [ 634.073728] [<ffffffff811003c5>] lockdep_rcu_suspicious+0xc5/0x100 [ 634.073763] [<ffffffff8174eb56>] icmp_route_lookup+0x176/0x5c0 [ 634.073793] [<ffffffff8174f2fb>] ? icmp_send+0x35b/0x5f0 [ 634.073818] [<ffffffff8174f274>] ? icmp_send+0x2d4/0x5f0 [ 634.073844] [<ffffffff8174f3ce>] icmp_send+0x42e/0x5f0 [ 634.073873] [<ffffffff8170b662>] ipv4_link_failure+0x22/0xa0 [ 634.073899] [<ffffffff8174bdda>] arp_error_report+0x3a/0x80 [ 634.073926] [<ffffffff816d6100>] ? neigh_lookup+0x2c0/0x2c0 [ 634.073952] [<ffffffff816d396e>] neigh_invalidate+0x8e/0x110 [ 634.073984] [<ffffffff816d62ae>] neigh_timer_handler+0x1ae/0x290 [ 634.074013] [<ffffffff816d6100>] ? neigh_lookup+0x2c0/0x2c0 [ 634.074013] [<ffffffff8112bce3>] call_timer_fn+0xb3/0x480 [ 634.074013] [<ffffffff8112bc35>] ? call_timer_fn+0x5/0x480 [ 634.074013] [<ffffffff816d6100>] ? neigh_lookup+0x2c0/0x2c0 [ 634.074013] [<ffffffff8112c2bc>] run_timer_softirq+0x20c/0x430 [ 634.074013] [<ffffffff810af50e>] __do_softirq+0xde/0x630 [ 634.074013] [<ffffffff810afc97>] irq_exit+0x117/0x120 [ 634.074013] [<ffffffff81810976>] smp_apic_timer_interrupt+0x46/0x60 [ 634.074013] [<ffffffff8180e950>] apic_timer_interrupt+0x70/0x80 [ 634.074013] <EOI> [<ffffffff8106b9d6>] ? native_safe_halt+0x6/0x10 [ 634.074013] [<ffffffff81101d8d>] ? trace_hardirqs_on+0xd/0x10 [ 634.074013] [<ffffffff81027d43>] default_idle+0x23/0x200 [ 634.074013] [<ffffffff8102852f>] arch_cpu_idle+0xf/0x20 [ 634.074013] [<ffffffff810f89ba>] default_idle_call+0x2a/0x40 [ 634.074013] [<ffffffff810f8dcc>] cpu_startup_entry+0x39c/0x4c0 [ 634.074013] [<ffffffff817f9cad>] rest_init+0x13d/0x150 [ 634.074013] [<ffffffff81f69038>] start_kernel+0x4a8/0x4c9 [ 634.074013] [<ffffffff81f68120>] ? early_idt_handler_array+0x120/0x120 [ 634.074013] [<ffffffff81f68339>] x86_64_start_reservations+0x2a/0x2c [ 634.074013] [<ffffffff81f68485>] x86_64_start_kernel+0x14a/0x16d It would seem vrf_master_ifindex_rcu() can be called without RCU held in other contexts as well so introduce a new helper which acquires rcu and returns the ifindex. Also add curly braces around both the "if" and "else" parts as per the style guide. Signed-off-by:Nikolay Aleksandrov <nikolay@cumulusnetworks.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Ying Xue authored
When CONFIG_LWTUNNEL config is not enabled, the lwtstate_free() is not declared in lwtunnel.h at all. However, even in this case, the function is still referenced in fib_semantics.c so that there appears the following sparse warnings: net/ipv4/fib_semantics.c:553:17: error: undefined identifier 'lwtstate_free' CC net/ipv4/fib_semantics.o net/ipv4/fib_semantics.c: In function ‘fib_encap_match’: net/ipv4/fib_semantics.c:553:3: error: implicit declaration of function ‘lwtstate_free’ [-Werror=implicit-function-declaration] cc1: some warnings being treated as errors make[1]: *** [net/ipv4/fib_semantics.o] Error 1 make: *** [net/ipv4/fib_semantics.o] Error 2 To eliminate the error, we define an empty function for lwtstate_free() in lwtunnel.h when CONFIG_LWTUNNEL is disabled. Fixes: df383e62 ("lwtunnel: fix memory leak") Cc: Jiri Benc <jbenc@redhat.com> Reported-by:
kbuild test robot <fengguang.wu@intel.com> Signed-off-by:
Ying Xue <ying.xue@windriver.com> Acked-by:
Jiri Benc <jbenc@redhat.com> Signed-off-by:
-
- 19 Aug, 2015 10 commits
-
-
git://git.kernel.org/pub/scm/linux/kernel/git/jkirsher/next-queueDavid S. Miller authored
Jeff Kirsher says: ==================== Intel Wired LAN Driver Updates 2015-08-18 This series contains updates to igb, e100, e1000e and ixgbe. Shota Suzuki provides a fix for a possible overflow in igb_set_interrupt_capability() which leads to an oops. When changing the number of queues by "ethtool -L", set IGB_FLAG_QUEUE_PAIRS in the same manner as when initializing the igb driver. Vasily Averin provides a fix for a missing rtnl_unlock() for when we error out due to not being able to allocate memory for our queues. Stefan Assman provides a couple of fixes for igb/igbvf. First changes the igb driver in probe to simply call igb_enable_sriov() instead of igb_sriov_reinit() since we are starting from scratch. Then in igbvf, fix the driver where it does not clear the buffer_info->dma in all cases after calling dma_unmap_single(), which was found by changing the MTU twice. Richard Cochran implements the periodic output function using the programmable clock outputs available in i210 when possible, falling back to the target time for longer periods. Todd adds support for the Marvell PHY 1512 which is required for i354 devices. Then updates igb to make sure SR-IOV init uses the correct number of queues, since recent changes could result in the PF holding onto all of the queues. Alex Williamson provides a fix in the case where a guest OS does not support hot-unplug, so disable SR-IOV prior to unregister_netdev() to avoid the problem. Jia-Ju Bai provides several patches, first knocks some collecting dust off an old e100 driver to add a check to avoid a null pointer dereference. Then cleans up a possible resource leak by releasing the skb buffer allocated when the e100_xmit_prepare() runs into an issue in the DMA mapping. In igb, add a missing rtnl_unlock() for when we error out due to igb_sriov_reinit() in the igb_init_interrupt_scheme(). Provides a e1000e fix, based on suggestions from Alex Duyck to move head/tail register writing to e1000_configure_tx/rx() to avoid a possible null pointer dereference (similar to igb driver). Lastly, fix a possible memory leak in igb_probe(), where the memory shadow_vfta allocated by kcalloc in igb_sw_init() is not freed. Mark simplifies port-specific macros for ixgbe by eliminating explicit comparisons with 0 and enclose formal parameters in parens to eliminate the risk of an operator precedence issue. ==================== Signed-off-by: -
David S. Miller authored
Nikolay Aleksandrov says: ==================== vrf: a few simplifications and cleanups These patches remove some unnecessary checks (patches 3, 4), unnecessary num_slaves member and refcnt manipulations which are already done by the upper functions. ==================== Acked-by:
David Ahern <dsa@cumulusnetworks.com> Signed-off-by:
-
Nikolay Aleksandrov authored
We can drop the check because if vrf_ptr is present then we must have the vrf device as a master and since we're running with rtnl it can't go away. Signed-off-by:
-
Nikolay Aleksandrov authored
dstats and rth are always present because we fail the device registration if they can't be allocated in vrf_init() (ndo_init) so drop the unnecessary checks. Signed-off-by:
-
Nikolay Aleksandrov authored
slave_queue has a num_slaves member which is unused, drop it. Signed-off-by:
-
Nikolay Aleksandrov authored
netdev_master_upper_dev_link/unlink already do a dev_hold/put on the devices being linked, so no need to take another reference. Signed-off-by:
-
Andrew Schwartzmeyer authored
Passes static analysis by Smatch. Signed-off-by:
Andrew Schwartzmeyer <andschwa@microsoft.com> Signed-off-by:
-
Jiri Benc authored
Currently, two routes going through the same tunnel interface are considered the same even when they are routed to a different host after encapsulation. This causes all routes added after the first one to have incorrect encapsulation parameters. This is nicely visible by doing: # ip r a 192.168.1.2/32 dev vxlan0 tunnel dst 10.0.0.2 # ip r a 192.168.1.3/32 dev vxlan0 tunnel dst 10.0.0.3 # ip r [...] 192.168.1.2/32 tunnel id 0 src 0.0.0.0 dst 10.0.0.2 [...] 192.168.1.3/32 tunnel id 0 src 0.0.0.0 dst 10.0.0.2 [...] Implement the missing comparison function. Fixes: 3093fbe7 ("route: Per route IP tunnel metadata via lightweight tunnel") Signed-off-by:
-
Jiri Benc authored
The built lwtunnel_state struct has to be freed after comparison. Fixes: 571e7226 ("ipv4: support for fib route lwtunnel encap attributes") Signed-off-by:
Roopa Prabhu <roopa@cumulusnetworks.com> Signed-off-by:
-
Dan Carpenter authored
You can't use kstrtoul() with an int or it causes memory corruption. Also j should be unsigned or we have underflow bugs. I considered changing "j" to unsigned long but everything fits in a u32. Fixes: 8e3d04fd ('cxgb4: Add MPS tracing support') Signed-off-by:
Dan Carpenter <dan.carpenter@oracle.com> Signed-off-by:
-
- 18 Aug, 2015 28 commits
-
-
David S. Miller authored
drivers/net/built-in.o: In function `.vnic_wq_devcmd2_alloc': (.text+0x49fe40): multiple definition of `.vnic_wq_devcmd2_alloc' drivers/scsi/built-in.o:(.text+0xb4318): first defined here drivers/net/built-in.o:(.opd+0x2af00): multiple definition of `vnic_wq_devcmd2_alloc' drivers/scsi/built-in.o:(.opd+0xad70): first defined here drivers/net/built-in.o: In function `.vnic_wq_init_start': (.text+0x49f9c0): multiple definition of `.vnic_wq_init_start' drivers/scsi/built-in.o:(.text+0xb3b58): first defined here drivers/net/built-in.o:(.opd+0x2ae88): multiple definition of `vnic_wq_init_start' drivers/scsi/built-in.o:(.opd+0xace0): first defined here Rename these to 'enic_*' to avoid the conflict with the functiosn of the same name in the snic scsi driver. Reported-by:
Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by:
-
Rajesh Borundia authored
Latest FW submission added some vxlan offload capabilities to our device. This patch adds the ability to connect to the vxlan NDOs and configure the UDP port associated with it in the HW. The device would now be capable of performing RSS according to the inner headers of the vxlan packets. Signed-off-by:
Rajesh Borundia <Rajesh.Borundia@qlogic.com> Signed-off-by:
Yuval Mintz <Yuval.Mintz@qlogic.com> Signed-off-by:
-
David S. Miller authored
Andrew Lunn says: ==================== D in DSA patches The D in DSA is distributed, meaning multiple switches can be connected together. Currently no mainline system does this, and so the code is broken. This patchset contains two fixes, and a small helper. With three of more switches, the current device tree binding is not sufficient to express the routing between the switches. The first patch extends the binding, in a backwards compatible way, to allow a link between a switch to describe all the switches accessible over the link, not just the direct neighbor. The third patch fixes the port configuration on newer devices for links connecting switches. ==================== Signed-off-by: -
Andrew Lunn authored
Older devices only support a single DSA frame format, where as newer devices have two. Take this into account when configuring a DSA port. The port needs to be in plain old DSA mode, since this is a DSA link, where as the newer format can be used for the CPU port. Signed-off-by:
Andrew Lunn <andrew@lunn.ch> Signed-off-by:
-
Andrew Lunn authored
Add an inline helper for determining is a port is a DSA port. Signed-off-by:
-
Andrew Lunn authored
With more than two switches in a hierarchy, it becomes necessary to describe multi-hop routes between switches. The current binding does not allow this, although the older platform_data did. Extend the link property to be a list rather than a single phandle to a remote switch. It is then possible to express that a port should be used to reach more than one switch and the switch maybe more than one hop away. Signed-off-by:
-
Jacob Keller authored
Signed-off-by:
Jacob Keller <jacob.e.keller@intel.com> Tested-by:
Phil Schmitt <phillip.j.schmitt@intel.com> Signed-off-by:
Jeff Kirsher <jeffrey.t.kirsher@intel.com>
-
Mark Rustad authored
Simplify port-specific macros by eliminating explicit comparison with 0. More importantly, enclose formal parameter in parens to eliminate the risk of an operator precedence surprise. Signed-off-by:
Mark Rustad <mark.d.rustad@intel.com> Tested-by:
-
Todd Fujinaka authored
Recent changes to igb_probe_vfs() could lead to the PF holding onto all of the queues. Reorder igb_probe_vfs() to be before gb_init_queue_configuration() and add some more error checking. Signed-off-by:
Todd Fujinaka <todd.fujinaka@intel.com> Tested-by:
Aaron Brown <aaron.f.brown@intel.com> Signed-off-by:
-
Stefan Assmann authored
The driver doesn't clear buffer_info->dma after calling dma_unmap_single() in all cases. This has been discovered by changing the mtu twice, which caused the following backtrace. [ 68.569280] WARNING: CPU: 2 PID: 1860 at drivers/iommu/intel-iommu.c:3517 intel_unmap+0x20c/0x220() [ 68.579392] Driver unmaps unmatched page at PFN fffc2a40 [ 68.585322] Modules linked in: igbvf ipt_MASQUERADE nf_nat_masquerade_ipv4 iptable_nat nf_nat_ipv4 nf_nat kvm_intel kvm igb megs [ 68.599163] CPU: 2 PID: 1860 Comm: ifconfig Not tainted 4.2.0-rc4+ #147 [ 68.606543] Hardware name: IBM -[546025Z]-/00Y7630, BIOS -[VVE134TUS-1.51]- 10/17/2013 [ 68.615473] 0000000000000dbd ffff88046441bb08 ffffffff81a5ad0b ffffffff81e2f9ea [ 68.623775] ffff88046441bb58 ffff88046441bb48 ffffffff81056b55 ffff88047fc583c0 [ 68.632075] 0000000000000000 ffff880469a8e600 00000000fffc2a40 ffff880465b32098 [ 68.640375] Call Trace: [ 68.643109] [<ffffffff81a5ad0b>] dump_stack+0x48/0x5d [ 68.648844] [<ffffffff81056b55>] warn_slowpath_common+0x95/0xe0 [ 68.655549] [<ffffffff81056c56>] warn_slowpath_fmt+0x46/0x70 [ 68.661960] [<ffffffff8158a614>] ? find_iova+0x54/0x90 [ 68.667791] [<ffffffff815988dc>] intel_unmap+0x20c/0x220 [ 68.673815] [<ffffffff8159891e>] intel_unmap_page+0xe/0x10 [ 68.680038] [<ffffffffa0067536>] igbvf_clean_rx_ring+0x96/0x370 [igbvf] [ 68.687516] [<ffffffffa0067915>] igbvf_down+0x105/0x110 [igbvf] [ 68.694219] [<ffffffffa0067beb>] igbvf_change_mtu+0x16b/0x180 [igbvf] [...] Signed-off-by:
Stefan Assmann <sassmann@kpanic.de> Acked-by:
Jesse Brandeburg <jesse.brandeburg@intel.com> Tested-by:
-
Jia-Ju Bai authored
In error handling code of igb_probe, the memory adapter->shadow_vfta allocated by kcalloc in igb_sw_init is not freed. So when register_netdev or igb_init_i2c is failed, a memory leak will occur. This patch adds kfree to fix it. Signed-off-by:
Jia-Ju Bai <baijiaju1990@163.com> Tested-by:
-
Jia-Ju Bai authored
When e1000e_setup_rx_resources is failed in e1000_open, e1000e_free_tx_resources in "err_setup_rx" segment is executed. "writel(0, tx_ring->head)" statement in e1000_clean_tx_ring in e1000e_free_tx_resources will cause a null poonter dereference(crash), because "tx_ring->head" is only assigned in e1000_configure_tx in e1000_configure, but it is after e1000e_setup_rx_resources. This patch moves head/tail register writing to e1000_configure_tx/rx, which can fix this problem. It is inspired by igb_configure_tx_ring in the igb driver. Specially, thank Alexander Duyck for his valuable suggestion. Signed-off-by:
-
Jia-Ju Bai authored
When igb_init_interrupt_scheme in igb_sriov_reinit is failed, the lock acquired by rtnl_lock() is not released, which causes a deadlock. This patch adds rtnl_unlock() in error handling to fix it. Signed-off-by:
-
Jia-Ju Bai authored
When pci_dma_mapping_error in e100_xmit_prepare is failed, the skb buffer allocated by netdev_alloc_skb_ip_align in e100_rx_alloc_skb is not released, which causes a possible resource leak. This patch adds error handling code to fix it. Signed-off-by:
-
Jia-Ju Bai authored
The driver lacks the check of nic->cbs_pool after pci_pool_create in e100_probe. When this function is failed, a null pointer dereference occurs when pci_pool_alloc uses nic->cbs_pool in e100_alloc_cbs. This patch adds a check and related error handling code to fix it. Signed-off-by:
-
Alex Williamson authored
When the .remove() callback for a PF is called, SR-IOV support for the device is disabled, which requires unbinding and removing the VFs. The VFs may be in-use either by the host kernel or userspace, such as assigned to a VM through vfio-pci. In this latter case, the VFs may be removed either by shutting down the VM or hot-unplugging the devices from the VM. Unfortunately in the case of a Windows 2012 R2 guest, hot-unplug is broken due to the ordering of the PF driver teardown. Disabling SR-IOV prior to unregister_netdev() avoids this issue. Signed-off-by:
Alex Williamson <alex.williamson@redhat.com> Acked-by:
Mitch Williams <mitch.a.williams@intel.com> Tested-by:
-
Todd Fujinaka authored
This patch adds support for Marvell PHY 1512 (required for I354). Submitted by: Maciej Szwed <maciej.szwed@intel.com> Signed-off-by:
-
Richard Cochran authored
In addition to interrupt driven target time output events, the i210 also has two programmable clock outputs. These clocks support periods between 16 nanoseconds and 140 milliseconds. This patch implements the periodic output function using the clock outputs when possible, falling back to the target time for longer periods. Signed-off-by:
Richard Cochran <richardcochran@gmail.com> Tested-by:
-
Stefan Assmann authored
During driver probing the following code path is triggered. igb_probe ->igb_sw_init ->igb_probe_vfs ->igb_pci_enable_sriov ->igb_sriov_reinit Doing the SR-IOV re-init is not necessary during probing since we're starting from scratch. Here we can call igb_enable_sriov() right away. Running igb_sriov_reinit() during igb_probe() also seems to cause occasional packet loss on some onboard 82576 NICs. Reproduced on Dell and HP servers with onboard 82576 NICs. Example: Intel Corporation 82576 Gigabit Network Connection [8086:10c9] (rev 01) Subsystem: Dell Device [1028:0481] Signed-off-by: -
Vasily Averin authored
Signed-off-by:
Vasily Averin <vvs@virtuozzo.com> Tested-by:
-
Shota Suzuki authored
When initializing igb driver (e.g. 82576, I350), IGB_FLAG_QUEUE_PAIRS is set if adapter->rss_queues exceeds half of max_rss_queues in igb_init_queue_configuration(). On the other hand, IGB_FLAG_QUEUE_PAIRS is not set even if the number of queues exceeds half of max_combined in igb_set_channels() when changing the number of queues by "ethtool -L". In this case, if numvecs is larger than MAX_MSIX_ENTRIES (10), the size of adapter->msix_entries[], an overflow can occur in igb_set_interrupt_capability(), which in turn leads to an oops. Fix this problem as follows: - When changing the number of queues by "ethtool -L", set IGB_FLAG_QUEUE_PAIRS in the same way as initializing igb driver. - When increasing the size of q_vector, reallocate it appropriately. (With IGB_FLAG_QUEUE_PAIRS set, the size of q_vector gets larger.) Another possible way to fix this problem is to cap the queues at its initial number, which is the number of the initial online cpus. But this is not the optimal way because we cannot increase queues when another cpu becomes online. Note that before commit cd14ef54 ("igb: Change to use statically allocated array for MSIx entries"), this problem did not cause oops but just made the number of queues become 1 because of entering msi_only mode in igb_set_interrupt_capability(). Fixes: 907b7835 ("igb: Add ethtool support to configure number of channels") CC: stable <stable@vger.kernel.org> Signed-off-by:
Shota Suzuki <suzuki_shota_t3@lab.ntt.co.jp> Tested-by:
-
David S. Miller authored
Phil Sutter says: ==================== net: Convert drivers to IFF_NO_QUEUE and cleanup afterwards This series converts in-tree users away from the old and deprecated 'tx_queue_len = 0' idiom, adds a warning to notify out-of-tree driver maintainers that there is need for action on their behalf and finally drops any workarounds in scheduling algorithm implementations. ==================== Signed-off-by: -
Phil Sutter authored
Those were all workarounds for the formerly double meaning of tx_queue_len, which broke scheduling algorithms if untreated. Now that all in-tree drivers have been converted away from setting tx_queue_len = 0, it should be safe to drop these workarounds for categorically broken setups. Signed-off-by:
Phil Sutter <phil@nwl.cc> Cc: Jamal Hadi Salim <jhs@mojatatu.com> Signed-off-by:
-
Phil Sutter authored
Due to the introduction of IFF_NO_QUEUE, there is a better way for drivers to indicate that no qdisc should be attached by default. Though, the old convention can't be dropped since ignoring that setting would break drivers still using it. Instead, add a warning so out-of-tree driver maintainers get a chance to adjust their code before we finally get rid of any special handling of tx_queue_len == 0. Signed-off-by:
-
Phil Sutter authored
Signed-off-by:
-
Phil Sutter authored
Signed-off-by:
-
Phil Sutter authored
Signed-off-by:
-
Phil Sutter authored
Signed-off-by:
-
