nouveau: pci: quiesce GPU on shutdown

Kexec reboot does not reset PCI devices.
Invoking the full DRM/TTM teardown from ->shutdown can trigger WARNs when
userspace still holds DRM file descriptors.

Quiesce the GPU through the suspend path and then power down the PCI
function so the next kernel can re-initialize the device from a consistent
state.

WARNING: drivers/gpu/drm/drm_mode_config.c:578 at drm_mode_config_cleanup+0x2e7/0x300, CPU#2: kexec/1300
Call Trace:
 <TASK>
 ? srso_return_thunk+0x5/0x5f
 ? enable_work+0x3a/0x100
 nouveau_display_destroy+0x39/0x70 [nouveau c19e0da7fd83583a023f855c510d9a3903808734]
 nouveau_drm_device_fini+0x7b/0x1f0 [nouveau c19e0da7fd83583a023f855c510d9a3903808734]
 nouveau_drm_shutdown+0x52/0xc0 [nouveau c19e0da7fd83583a023f855c510d9a3903808734]
 pci_device_shutdown+0x35/0x60
 device_shutdown+0x11c/0x1b0
 kernel_kexec+0x13a/0x160
 __do_sys_reboot+0x209/0x240
 do_syscall_64+0x81/0x610
 ? srso_return_thunk+0x5/0x5f
 ? __rtnl_unlock+0x37/0x70
 ? srso_return_thunk+0x5/0x5f
 ? netdev_run_todo+0x63/0x570
 ? netif_change_flags+0x54/0x70
 ? srso_return_thunk+0x5/0x5f
 ? devinet_ioctl+0x1e5/0x790
 ? srso_return_thunk+0x5/0x5f
 ? inet_ioctl+0x1e9/0x200
 ? srso_return_thunk+0x5/0x5f
 ? srso_return_thunk+0x5/0x5f
 ? sock_do_ioctl+0x7d/0x130
 ? srso_return_thunk+0x5/0x5f
 ? __x64_sys_ioctl+0x97/0xe0
 ? srso_return_thunk+0x5/0x5f
 ? srso_return_thunk+0x5/0x5f
 ? do_syscall_64+0x23b/0x610
 ? srso_return_thunk+0x5/0x5f
 ? put_user_ifreq+0x7a/0x90
 ? srso_return_thunk+0x5/0x5f
 ? sock_do_ioctl+0x107/0x130
 ? srso_return_thunk+0x5/0x5f
 ? __x64_sys_ioctl+0x97/0xe0
 ? srso_return_thunk+0x5/0x5f
 ? do_syscall_64+0x81/0x610
 ? srso_return_thunk+0x5/0x5f
 ? exc_page_fault+0x7e/0x1a0
 entry_SYSCALL_64_after_hwframe+0x76/0x7e

nouveau 0000:26:00.0: [drm] drm_WARN_ON(!list_empty(&fb->filp_head))
WARNING: drivers/gpu/drm/drm_framebuffer.c:833 at drm_framebuffer_free+0x73/0xa0, CPU#2: kexec/1300
Call Trace:
 <TASK>
 drm_mode_config_cleanup+0x248/0x300
 ? __pfx___drm_printfn_dbg+0x10/0x10
 ? drm_mode_config_cleanup+0x1dc/0x300
 nouveau_display_destroy+0x39/0x70 [nouveau c19e0da7fd83583a023f855c510d9a3903808734]
 nouveau_drm_device_fini+0x7b/0x1f0 [nouveau c19e0da7fd83583a023f855c510d9a3903808734]
 nouveau_drm_shutdown+0x52/0xc0 [nouveau c19e0da7fd83583a023f855c510d9a3903808734]
 pci_device_shutdown+0x35/0x60
 device_shutdown+0x11c/0x1b0
 kernel_kexec+0x13a/0x160
 __do_sys_reboot+0x209/0x240
 do_syscall_64+0x81/0x610
 ? srso_return_thunk+0x5/0x5f
 ? __rtnl_unlock+0x37/0x70
 ? srso_return_thunk+0x5/0x5f
 ? netdev_run_todo+0x63/0x570
 ? netif_change_flags+0x54/0x70
 ? srso_return_thunk+0x5/0x5f
 ? devinet_ioctl+0x1e5/0x790
 ? srso_return_thunk+0x5/0x5f
 ? inet_ioctl+0x1e9/0x200
 ? srso_return_thunk+0x5/0x5f
 ? srso_return_thunk+0x5/0x5f
 ? sock_do_ioctl+0x7d/0x130
 ? srso_return_thunk+0x5/0x5f
 ? __x64_sys_ioctl+0x97/0xe0
 ? srso_return_thunk+0x5/0x5f
 ? srso_return_thunk+0x5/0x5f
 ? do_syscall_64+0x23b/0x610
 ? srso_return_thunk+0x5/0x5f
 ? put_user_ifreq+0x7a/0x90
 ? srso_return_thunk+0x5/0x5f
 ? sock_do_ioctl+0x107/0x130
 ? srso_return_thunk+0x5/0x5f
 ? __x64_sys_ioctl+0x97/0xe0
 ? srso_return_thunk+0x5/0x5f
 ? do_syscall_64+0x81/0x610
 ? srso_return_thunk+0x5/0x5f
 ? exc_page_fault+0x7e/0x1a0
 entry_SYSCALL_64_after_hwframe+0x76/0x7e

WARNING: include/drm/ttm/ttm_resource.h:406 at nouveau_ttm_fini+0x257/0x270 [nouveau], CPU#2: kexec/1300
Call Trace:
 <TASK>
 nouveau_drm_device_fini+0x93/0x1f0 [nouveau c19e0da7fd83583a023f855c510d9a3903808734]
 nouveau_drm_shutdown+0x52/0xc0 [nouveau c19e0da7fd83583a023f855c510d9a3903808734]
 pci_device_shutdown+0x35/0x60
 device_shutdown+0x11c/0x1b0
 kernel_kexec+0x13a/0x160
 __do_sys_reboot+0x209/0x240
 do_syscall_64+0x81/0x610
 ? srso_return_thunk+0x5/0x5f
 ? __rtnl_unlock+0x37/0x70
 ? srso_return_thunk+0x5/0x5f
 ? netdev_run_todo+0x63/0x570
 ? netif_change_flags+0x54/0x70
 ? srso_return_thunk+0x5/0x5f
 ? devinet_ioctl+0x1e5/0x790
 ? srso_return_thunk+0x5/0x5f
 ? inet_ioctl+0x1e9/0x200
 ? srso_return_thunk+0x5/0x5f
 ? srso_return_thunk+0x5/0x5f
 ? sock_do_ioctl+0x7d/0x130
 ? srso_return_thunk+0x5/0x5f
 ? __x64_sys_ioctl+0x97/0xe0
 ? srso_return_thunk+0x5/0x5f
 ? srso_return_thunk+0x5/0x5f
 ? do_syscall_64+0x23b/0x610
 ? srso_return_thunk+0x5/0x5f
 ? put_user_ifreq+0x7a/0x90
 ? srso_return_thunk+0x5/0x5f
 ? sock_do_ioctl+0x107/0x130
 ? srso_return_thunk+0x5/0x5f
 ? __x64_sys_ioctl+0x97/0xe0
 ? srso_return_thunk+0x5/0x5f
 ? do_syscall_64+0x81/0x610
 ? srso_return_thunk+0x5/0x5f
 ? exc_page_fault+0x7e/0x1a0
 entry_SYSCALL_64_after_hwframe+0x76/0x7e

Signed-off-by: Li Chen <me@linux.beauty>
Reviewed-by: Dave Airlie <airlied@redhat.com>
Signed-off-by: Dave Airlie <airlied@redhat.com>
Link: https://patch.msgid.link/20260121113646.111561-1-me@linux.beauty

diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c
index 1527b801f013aacf82af96382c4be9320a595d50..f2e04a048ac2c30cc449b1c0b2e9ed6da7bd243d 100644 (file)
--- a/drivers/gpu/drm/nouveau/nouveau_drm.c
+++ b/drivers/gpu/drm/nouveau/nouveau_drm.c
@@ -1079,6 +1079,37 @@ nouveau_pmops_resume(struct device *dev)
        return ret;
 }
 
+static void
+nouveau_drm_shutdown(struct pci_dev *pdev)
+{
+       struct nouveau_drm *drm = pci_get_drvdata(pdev);
+       int ret;
+
+       if (!drm)
+               return;
+
+       if (drm->dev->switch_power_state == DRM_SWITCH_POWER_OFF ||
+           drm->dev->switch_power_state == DRM_SWITCH_POWER_DYNAMIC_OFF)
+               return;
+
+       ret = nouveau_do_suspend(drm, false);
+       if (ret)
+               NV_ERROR(drm, "shutdown suspend failed with: %d\n", ret);
+
+       pci_save_state(pdev);
+       pci_disable_device(pdev);
+       pci_set_power_state(pdev, PCI_D3hot);
+       /*
+        *  This is just to give the pci power transition time to settle
+        *  before an immediate kexec jump. it’s mirroring the existing
+        *  nouveau_pmops_suspend() behavior, which already does
+        *  udelay(200) right after pci_set_power_state(..., pci_d3hot). In
+        *  ->shutdown() we’re allowed to sleep, so I used usleep_range()
+        *  instead of a busy-wait udelay().
+        */
+       usleep_range(200, 400);
+}
+
 static int
 nouveau_pmops_freeze(struct device *dev)
 {
@@ -1408,6 +1439,7 @@ nouveau_drm_pci_driver = {
        .id_table = nouveau_drm_pci_table,
        .probe = nouveau_drm_probe,
        .remove = nouveau_drm_remove,
+       .shutdown = nouveau_drm_shutdown,
        .driver.pm = &nouveau_pm_ops,
 };