From: Anatoli Antonovitch <anatoli.antonovitch@xxxxxxx> It is to avoid any potential issues when S3 resume but at the same time we want to hot-unplug. To fix the race between pciehp and AER reported in https://bugzilla.kernel.org/show_bug.cgi?id=215590 INFO: task irq/26-aerdrv:95 blocked for more than 120 seconds. Tainted: G W 6.2.0-rc3-custom-norework-jan11+ #29 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:irq/26-aerdrv state:D stack:0 pid:95 ppid:2 flags:0x00004000 Call Trace: <TASK> __schedule+0x3df/0xec0 ? rcu_read_lock_held_common+0x12/0x60 schedule+0x6b/0x100 rwsem_down_write_slowpath+0x3b2/0x9c0 down_write_nested+0x16b/0x220 pciehp_reset_slot+0x63/0x160 pci_reset_hotplug_slot+0x44/0x80 pci_slot_reset+0x10d/0x1a0 pci_bus_error_reset+0xb2/0xe0 aer_root_reset+0x144/0x1a0 pcie_do_recovery+0x15a/0x280 ? __pfx_aer_root_reset+0x20/0x20 aer_process_err_devices+0xfa/0x115 aer_isr.cold+0x52/0xa1 ? __kmem_cache_free+0x36a/0x3c0 ? irq_thread+0xb0/0x1e0 ? irq_thread+0xb0/0x1e0 irq_thread_fn+0x28/0x80 irq_thread+0x106/0x1e0 ? __pfx_irq_thread_fn+0x20/0x20 ? __pfx_irq_thread_dtor+0x20/0x20 ? __pfx_irq_thread+0x20/0x20 kthread+0x10a/0x140 ? __pfx_kthread+0x20/0x20 ret_from_fork+0x35/0x60 </TASK> INFO: task irq/26-pciehp:96 blocked for more than 120 seconds. Tainted: G W 6.2.0-rc3-custom-norework-jan11+ #29 "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. task:irq/26-pciehp state:D stack:0 pid:96 ppid:2 flags:0x00004000 Call Trace: <TASK> __schedule+0x3df/0xec0 ? rcu_read_lock_sched_held+0x25/0x80 schedule+0x6b/0x100 schedule_preempt_disabled+0x18/0x40 __mutex_lock+0x685/0xf60 ? rcu_read_lock_sched_held+0x25/0x80 ? rcu_read_lock_held_common+0x12/0x60 ? pci_dev_set_disconnected+0x1b/0x80 mutex_lock_nested+0x1b/0x40 ? mutex_lock_nested+0x1b/0x40 pci_dev_set_disconnected+0x1b/0x80 ? __pfx_pci_dev_set_disconnected+0x20/0x20 pci_walk_bus+0x48/0xa0 pciehp_unconfigure_device+0x129/0x140 pciehp_disable_slot+0x6e/0x120 pciehp_handle_presence_or_link_change+0xf1/0x320 pciehp_ist+0x1a0/0x1c0 ? irq_thread+0xb0/0x1e0 irq_thread_fn+0x28/0x80 irq_thread+0x106/0x1e0 ? __pfx_irq_thread_fn+0x20/0x20 ? __pfx_irq_thread_dtor+0x20/0x20 ? __pfx_irq_thread+0x20/0x20 kthread+0x10a/0x140 ? __pfx_kthread+0x20/0x20 ret_from_fork+0x35/0x60 </TASK> Signed-off-by: Anatoli Antonovitch <anatoli.antonovitch@xxxxxxx> --- drivers/pci/hotplug/pciehp_hpc.c | 13 +++++++++++-- 1 file changed, 11 insertions(+), 2 deletions(-) diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c index 10e9670eea0b..b1084e67f798 100644 --- a/drivers/pci/hotplug/pciehp_hpc.c +++ b/drivers/pci/hotplug/pciehp_hpc.c @@ -27,6 +27,8 @@ #include "../pci.h" #include "pciehp.h" +static DECLARE_RWSEM(hotplug_slot_rwsem); + static const struct dmi_system_id inband_presence_disabled_dmi_table[] = { /* * Match all Dell systems, as some Dell systems have inband @@ -911,7 +913,10 @@ int pciehp_reset_slot(struct hotplug_slot *hotplug_slot, bool probe) if (probe) return 0; - down_write_nested(&ctrl->reset_lock, ctrl->depth); + if (ctrl->depth > 0) + down_write_nested(&ctrl->reset_lock, ctrl->depth); + else + down_write(&hotplug_slot_rwsem); if (!ATTN_BUTTN(ctrl)) { ctrl_mask |= PCI_EXP_SLTCTL_PDCE; @@ -931,7 +936,11 @@ int pciehp_reset_slot(struct hotplug_slot *hotplug_slot, bool probe) ctrl_dbg(ctrl, "%s: SLOTCTRL %x write cmd %x\n", __func__, pci_pcie_cap(ctrl->pcie->port) + PCI_EXP_SLTCTL, ctrl_mask); - up_write(&ctrl->reset_lock); + if (ctrl->depth > 0) + up_write(&ctrl->reset_lock); + else + up_write(&hotplug_slot_rwsem); + return rc; } -- 2.25.1
