From 499ab5ccbd42839f40d5572e7a4799c412986a11 Mon Sep 17 00:00:00 2001 From: akepner Date: Wed, 13 Mar 2013 14:54:58 +0000 Subject: [PATCH] ixgbe: in shutdown, do netif_running() under rtnl_lock During shutdown it's possible for __dev_close() (which holds rtnl_lock) to clear the __LINK_STATE_START bit, and for ixgbe to then read that bit (without holding rtnl_lock), and then not fail to free irqs, etc. The result is a crash like this: ------------[ cut here ]------------ kernel BUG at drivers/pci/msi.c:313! invalid opcode: 0000 [#1] SMP last sysfs file: /sys/devices/system/cpu/cpu3/cache/index2/shared_cpu_map CPU 1 Pid: 5910, comm: reboot Tainted: P ---------------- 2.6.32 #1 empty RIP: 0010:[] [] free_msi_irqs+0x11b/0x130 RSP: 0018:ffff880185c9bc88 EFLAGS: 00010282 RAX: ffff880219f58bc0 RBX: ffff88021ac53b00 RCX: 0000000000000000 RDX: 0000000000000001 RSI: 0000000000000246 RDI: 000000000000004a RBP: ffff880185c9bcc8 R08: 0000000000000002 R09: 0000000000000106 R10: 0000000000000000 R11: 0000000000000006 R12: ffff88021e524778 R13: 0000000000000001 R14: ffff88021e524000 R15: 0000000000000000 FS: 00007f90821b7700(0000) GS:ffff880028220000(0000) knlGS:0000000000000000 CS: 0010 DS: 0000 ES: 0000 CR0: 000000008005003b CR2: 00007f90818bd010 CR3: 0000000132c64000 CR4: 00000000000006e0 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400 Process reboot (pid: 5910, threadinfo ffff880185c9a000, task ffff88021bf04a80) Stack: ffff880185c9bc98 000000018130529d ffff880185c9bcc8 ffff88021e524000 <0> 0000000000000004 ffff88021948c700 0000000000000000 ffff880185c9bda7 <0> ffff880185c9bce8 ffffffff81305cbd ffff880185c9bce8 ffff88021948c700 Call Trace: [] pci_disable_msix+0x3d/0x50 [] ixgbe_reset_interrupt_capability+0x65/0x90 [ixgbe] [] ixgbe_clear_interrupt_scheme+0xb6/0xd0 [ixgbe] [] __ixgbe_shutdown+0x5b/0x200 [ixgbe] [] ixgbe_shutdown+0x1a/0x60 [ixgbe] [] pci_device_shutdown+0x2c/0x50 [] device_shutdown+0x4b/0x160 [] kernel_restart_prepare+0x2c/0x40 ehci timer_action, mod_timer io_watchdog [] kernel_restart+0x16/0x60 [] sys_reboot+0x1ad/0x200 [] ? __d_free+0x3f/0x60 [] ? d_free+0x58/0x60 [] ? mntput_no_expire+0x30/0x100 [] ? __fput+0x191/0x200 [] ? do_page_fault+0x3e/0xa0 [] system_call_fastpath+0x16/0x1b Code: 4c 89 ef e8 98 8c e3 ff 4d 39 f4 48 8b 43 10 75 cf 48 83 c4 18 5b 41 5c 41 5d 41 5e 41 5f c9 c3 49 8b 7d 20 e8 07 5a d3 ff eb c9 <0f> 0b 0f 1f 00 eb fb 66 66 66 66 66 2e 0f 1f 84 00 00 00 00 00 ehci timer_action, mod_timer io_watchdog RIP [] free_msi_irqs+0x11b/0x130 RSP ---[ end trace 27de882a0fe75593 ]--- (This was seen on a pretty old kernel/driver, but looks like the same bug is still possible.) Signed-off-by: Tested-by: Phil Schmitt Signed-off-by: Jeff Kirsher --- drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 6bd1dd13682c..48f3fd501ac8 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -5123,14 +5123,14 @@ static int __ixgbe_shutdown(struct pci_dev *pdev, bool *enable_wake) netif_device_detach(netdev); + rtnl_lock(); if (netif_running(netdev)) { - rtnl_lock(); ixgbe_down(adapter); ixgbe_free_irq(adapter); ixgbe_free_all_tx_resources(adapter); ixgbe_free_all_rx_resources(adapter); - rtnl_unlock(); } + rtnl_unlock(); ixgbe_clear_interrupt_scheme(adapter); -- 2.20.1