- Linux-stable-mirror - lists.linaro.org

[PATCH v8 3/5] drm/nouveau: Fix deadlock with fb_helper with async RPM requests

by Lyude Paul

Currently, nouveau uses the generic drm_fb_helper_output_poll_changed() function provided by DRM as it's output_poll_changed callback. Unfortunately however, this function doesn't grab runtime PM references early enough and even if it did-we can't block waiting for the device to resume in output_poll_changed() since it's very likely that we'll need to grab the fb_helper lock at some point during the runtime resume process. This currently results in deadlocking like so: [ 246.669625] INFO: task kworker/4:0:37 blocked for more than 120 seconds. [ 246.673398] Not tainted 4.18.0-rc5Lyude-Test+ #2 [ 246.675271] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 246.676527] kworker/4:0 D 0 37 2 0x80000000 [ 246.677580] Workqueue: events output_poll_execute [drm_kms_helper] [ 246.678704] Call Trace: [ 246.679753] __schedule+0x322/0xaf0 [ 246.680916] schedule+0x33/0x90 [ 246.681924] schedule_preempt_disabled+0x15/0x20 [ 246.683023] __mutex_lock+0x569/0x9a0 [ 246.684035] ? kobject_uevent_env+0x117/0x7b0 [ 246.685132] ? drm_fb_helper_hotplug_event.part.28+0x20/0xb0 [drm_kms_helper] [ 246.686179] mutex_lock_nested+0x1b/0x20 [ 246.687278] ? mutex_lock_nested+0x1b/0x20 [ 246.688307] drm_fb_helper_hotplug_event.part.28+0x20/0xb0 [drm_kms_helper] [ 246.689420] drm_fb_helper_output_poll_changed+0x23/0x30 [drm_kms_helper] [ 246.690462] drm_kms_helper_hotplug_event+0x2a/0x30 [drm_kms_helper] [ 246.691570] output_poll_execute+0x198/0x1c0 [drm_kms_helper] [ 246.692611] process_one_work+0x231/0x620 [ 246.693725] worker_thread+0x214/0x3a0 [ 246.694756] kthread+0x12b/0x150 [ 246.695856] ? wq_pool_ids_show+0x140/0x140 [ 246.696888] ? kthread_create_worker_on_cpu+0x70/0x70 [ 246.697998] ret_from_fork+0x3a/0x50 [ 246.699034] INFO: task kworker/0:1:60 blocked for more than 120 seconds. [ 246.700153] Not tainted 4.18.0-rc5Lyude-Test+ #2 [ 246.701182] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 246.702278] kworker/0:1 D 0 60 2 0x80000000 [ 246.703293] Workqueue: pm pm_runtime_work [ 246.704393] Call Trace: [ 246.705403] __schedule+0x322/0xaf0 [ 246.706439] ? wait_for_completion+0x104/0x190 [ 246.707393] schedule+0x33/0x90 [ 246.708375] schedule_timeout+0x3a5/0x590 [ 246.709289] ? mark_held_locks+0x58/0x80 [ 246.710208] ? _raw_spin_unlock_irq+0x2c/0x40 [ 246.711222] ? wait_for_completion+0x104/0x190 [ 246.712134] ? trace_hardirqs_on_caller+0xf4/0x190 [ 246.713094] ? wait_for_completion+0x104/0x190 [ 246.713964] wait_for_completion+0x12c/0x190 [ 246.714895] ? wake_up_q+0x80/0x80 [ 246.715727] ? get_work_pool+0x90/0x90 [ 246.716649] flush_work+0x1c9/0x280 [ 246.717483] ? flush_workqueue_prep_pwqs+0x1b0/0x1b0 [ 246.718442] __cancel_work_timer+0x146/0x1d0 [ 246.719247] cancel_delayed_work_sync+0x13/0x20 [ 246.720043] drm_kms_helper_poll_disable+0x1f/0x30 [drm_kms_helper] [ 246.721123] nouveau_pmops_runtime_suspend+0x3d/0xb0 [nouveau] [ 246.721897] pci_pm_runtime_suspend+0x6b/0x190 [ 246.722825] ? pci_has_legacy_pm_support+0x70/0x70 [ 246.723737] __rpm_callback+0x7a/0x1d0 [ 246.724721] ? pci_has_legacy_pm_support+0x70/0x70 [ 246.725607] rpm_callback+0x24/0x80 [ 246.726553] ? pci_has_legacy_pm_support+0x70/0x70 [ 246.727376] rpm_suspend+0x142/0x6b0 [ 246.728185] pm_runtime_work+0x97/0xc0 [ 246.728938] process_one_work+0x231/0x620 [ 246.729796] worker_thread+0x44/0x3a0 [ 246.730614] kthread+0x12b/0x150 [ 246.731395] ? wq_pool_ids_show+0x140/0x140 [ 246.732202] ? kthread_create_worker_on_cpu+0x70/0x70 [ 246.732878] ret_from_fork+0x3a/0x50 [ 246.733768] INFO: task kworker/4:2:422 blocked for more than 120 seconds. [ 246.734587] Not tainted 4.18.0-rc5Lyude-Test+ #2 [ 246.735393] "echo 0 > /proc/sys/kernel/hung_task_timeout_secs" disables this message. [ 246.736113] kworker/4:2 D 0 422 2 0x80000080 [ 246.736789] Workqueue: events_long drm_dp_mst_link_probe_work [drm_kms_helper] [ 246.737665] Call Trace: [ 246.738490] __schedule+0x322/0xaf0 [ 246.739250] schedule+0x33/0x90 [ 246.739908] rpm_resume+0x19c/0x850 [ 246.740750] ? finish_wait+0x90/0x90 [ 246.741541] __pm_runtime_resume+0x4e/0x90 [ 246.742370] nv50_disp_atomic_commit+0x31/0x210 [nouveau] [ 246.743124] drm_atomic_commit+0x4a/0x50 [drm] [ 246.743775] restore_fbdev_mode_atomic+0x1c8/0x240 [drm_kms_helper] [ 246.744603] restore_fbdev_mode+0x31/0x140 [drm_kms_helper] [ 246.745373] drm_fb_helper_restore_fbdev_mode_unlocked+0x54/0xb0 [drm_kms_helper] [ 246.746220] drm_fb_helper_set_par+0x2d/0x50 [drm_kms_helper] [ 246.746884] drm_fb_helper_hotplug_event.part.28+0x96/0xb0 [drm_kms_helper] [ 246.747675] drm_fb_helper_output_poll_changed+0x23/0x30 [drm_kms_helper] [ 246.748544] drm_kms_helper_hotplug_event+0x2a/0x30 [drm_kms_helper] [ 246.749439] nv50_mstm_hotplug+0x15/0x20 [nouveau] [ 246.750111] drm_dp_send_link_address+0x177/0x1c0 [drm_kms_helper] [ 246.750764] drm_dp_check_and_send_link_address+0xa8/0xd0 [drm_kms_helper] [ 246.751602] drm_dp_mst_link_probe_work+0x51/0x90 [drm_kms_helper] [ 246.752314] process_one_work+0x231/0x620 [ 246.752979] worker_thread+0x44/0x3a0 [ 246.753838] kthread+0x12b/0x150 [ 246.754619] ? wq_pool_ids_show+0x140/0x140 [ 246.755386] ? kthread_create_worker_on_cpu+0x70/0x70 [ 246.756162] ret_from_fork+0x3a/0x50 [ 246.756847] Showing all locks held in the system: [ 246.758261] 3 locks held by kworker/4:0/37: [ 246.759016] #0: 00000000f8df4d2d ((wq_completion)"events"){+.+.}, at: process_one_work+0x1b3/0x620 [ 246.759856] #1: 00000000e6065461 ((work_completion)(&(&dev->mode_config.output_poll_work)->work)){+.+.}, at: process_one_work+0x1b3/0x620 [ 246.760670] #2: 00000000cb66735f (&helper->lock){+.+.}, at: drm_fb_helper_hotplug_event.part.28+0x20/0xb0 [drm_kms_helper] [ 246.761516] 2 locks held by kworker/0:1/60: [ 246.762274] #0: 00000000fff6be0f ((wq_completion)"pm"){+.+.}, at: process_one_work+0x1b3/0x620 [ 246.762982] #1: 000000005ab44fb4 ((work_completion)(&dev->power.work)){+.+.}, at: process_one_work+0x1b3/0x620 [ 246.763890] 1 lock held by khungtaskd/64: [ 246.764664] #0: 000000008cb8b5c3 (rcu_read_lock){....}, at: debug_show_all_locks+0x23/0x185 [ 246.765588] 5 locks held by kworker/4:2/422: [ 246.766440] #0: 00000000232f0959 ((wq_completion)"events_long"){+.+.}, at: process_one_work+0x1b3/0x620 [ 246.767390] #1: 00000000bb59b134 ((work_completion)(&mgr->work)){+.+.}, at: process_one_work+0x1b3/0x620 [ 246.768154] #2: 00000000cb66735f (&helper->lock){+.+.}, at: drm_fb_helper_restore_fbdev_mode_unlocked+0x4c/0xb0 [drm_kms_helper] [ 246.768966] #3: 000000004c8f0b6b (crtc_ww_class_acquire){+.+.}, at: restore_fbdev_mode_atomic+0x4b/0x240 [drm_kms_helper] [ 246.769921] #4: 000000004c34a296 (crtc_ww_class_mutex){+.+.}, at: drm_modeset_backoff+0x8a/0x1b0 [drm] [ 246.770839] 1 lock held by dmesg/1038: [ 246.771739] 2 locks held by zsh/1172: [ 246.772650] #0: 00000000836d0438 (&tty->ldisc_sem){++++}, at: ldsem_down_read+0x37/0x40 [ 246.773680] #1: 000000001f4f4d48 (&ldata->atomic_read_lock){+.+.}, at: n_tty_read+0xc1/0x870 [ 246.775522] ============================================= After trying dozens of different solutions, I found one very simple one that should also have the benefit of preventing us from having to fight locking for the rest of our lives. So, we work around these deadlocks by deferring all fbcon hotplug events that happen after the runtime suspend process starts until after the device is resumed again. Changes since v7: - Fixup commit message - Daniel Vetter Changes since v6: - Remove unused nouveau_fbcon_hotplugged_in_suspend() - Ilia Changes since v5: - Come up with the (hopefully final) solution for solving this dumb problem, one that is a lot less likely to cause issues with locking in the future. This should work around all deadlock conditions with fbcon brought up thus far. Changes since v4: - Add nouveau_fbcon_hotplugged_in_suspend() to workaround deadlock condition that Lukas described - Just move all of this out of drm_fb_helper. It seems that other DRM drivers have already figured out other workarounds for this. If other drivers do end up needing this in the future, we can just move this back into drm_fb_helper again. Changes since v3: - Actually check if fb_helper is NULL in both new helpers - Actually check drm_fbdev_emulation in both new helpers - Don't fire off a fb_helper hotplug unconditionally; only do it if the following conditions are true (as otherwise, calling this in the wrong spot will cause Bad Things to happen): - fb_helper hotplug handling was actually inhibited previously - fb_helper actually has a delayed hotplug pending - fb_helper is actually bound - fb_helper is actually initialized - Add __must_check to drm_fb_helper_suspend_hotplug(). There's no situation where a driver would actually want to use this without checking the return value, so enforce that - Rewrite and clarify the documentation for both helpers. - Make sure to return true in the drm_fb_helper_suspend_hotplug() stub that's provided in drm_fb_helper.h when CONFIG_DRM_FBDEV_EMULATION isn't enabled - Actually grab the toplevel fb_helper lock in drm_fb_helper_resume_hotplug(), since it's possible other activity (such as a hotplug) could be going on at the same time the driver calls drm_fb_helper_resume_hotplug(). We need this to check whether or not drm_fb_helper_hotplug_event() needs to be called anyway Signed-off-by: Lyude Paul <lyude(a)redhat.com> Reviewed-by: Karol Herbst <kherbst(a)redhat.com> Acked-by: Daniel Vetter <daniel(a)ffwll.ch> Cc: stable(a)vger.kernel.org Cc: Lukas Wunner <lukas(a)wunner.de> --- drivers/gpu/drm/nouveau/dispnv50/disp.c | 2 +- drivers/gpu/drm/nouveau/nouveau_display.c | 2 +- drivers/gpu/drm/nouveau/nouveau_fbcon.c | 57 +++++++++++++++++++++++ drivers/gpu/drm/nouveau/nouveau_fbcon.h | 5 ++ 4 files changed, 64 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/nouveau/dispnv50/disp.c b/drivers/gpu/drm/nouveau/dispnv50/disp.c index 8b522a9b12f6..a0772389ed90 100644 --- a/drivers/gpu/drm/nouveau/dispnv50/disp.c +++ b/drivers/gpu/drm/nouveau/dispnv50/disp.c @@ -2049,7 +2049,7 @@ nv50_disp_atomic_state_alloc(struct drm_device *dev) static const struct drm_mode_config_funcs nv50_disp_func = { .fb_create = nouveau_user_framebuffer_create, - .output_poll_changed = drm_fb_helper_output_poll_changed, + .output_poll_changed = nouveau_fbcon_output_poll_changed, .atomic_check = nv50_disp_atomic_check, .atomic_commit = nv50_disp_atomic_commit, .atomic_state_alloc = nv50_disp_atomic_state_alloc, diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index 1d36ab5d4796..4b873e668b26 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -293,7 +293,7 @@ nouveau_user_framebuffer_create(struct drm_device *dev, static const struct drm_mode_config_funcs nouveau_mode_config_funcs = { .fb_create = nouveau_user_framebuffer_create, - .output_poll_changed = drm_fb_helper_output_poll_changed, + .output_poll_changed = nouveau_fbcon_output_poll_changed, }; diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.c b/drivers/gpu/drm/nouveau/nouveau_fbcon.c index 85c1f10bc2b6..8cf966690963 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.c +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.c @@ -466,6 +466,7 @@ nouveau_fbcon_set_suspend_work(struct work_struct *work) console_unlock(); if (state == FBINFO_STATE_RUNNING) { + nouveau_fbcon_hotplug_resume(drm->fbcon); pm_runtime_mark_last_busy(drm->dev->dev); pm_runtime_put_sync(drm->dev->dev); } @@ -487,6 +488,61 @@ nouveau_fbcon_set_suspend(struct drm_device *dev, int state) schedule_work(&drm->fbcon_work); } +void +nouveau_fbcon_output_poll_changed(struct drm_device *dev) +{ + struct nouveau_drm *drm = nouveau_drm(dev); + struct nouveau_fbdev *fbcon = drm->fbcon; + int ret; + + if (!fbcon) + return; + + mutex_lock(&fbcon->hotplug_lock); + + ret = pm_runtime_get(dev->dev); + if (ret == 1 || ret == -EACCES) { + drm_fb_helper_hotplug_event(&fbcon->helper); + + pm_runtime_mark_last_busy(dev->dev); + pm_runtime_put_autosuspend(dev->dev); + } else if (ret == 0) { + /* If the GPU was already in the process of suspending before + * this event happened, then we can't block here as we'll + * deadlock the runtime pmops since they wait for us to + * finish. So, just defer this event for when we runtime + * resume again. It will be handled by fbcon_work. + */ + NV_DEBUG(drm, "fbcon HPD event deferred until runtime resume\n"); + fbcon->hotplug_waiting = true; + pm_runtime_put_noidle(drm->dev->dev); + } else { + DRM_WARN("fbcon HPD event lost due to RPM failure: %d\n", + ret); + } + + mutex_unlock(&fbcon->hotplug_lock); +} + +void +nouveau_fbcon_hotplug_resume(struct nouveau_fbdev *fbcon) +{ + struct nouveau_drm *drm; + + if (!fbcon) + return; + drm = nouveau_drm(fbcon->helper.dev); + + mutex_lock(&fbcon->hotplug_lock); + if (fbcon->hotplug_waiting) { + fbcon->hotplug_waiting = false; + + NV_DEBUG(drm, "Handling deferred fbcon HPD events\n"); + drm_fb_helper_hotplug_event(&fbcon->helper); + } + mutex_unlock(&fbcon->hotplug_lock); +} + int nouveau_fbcon_init(struct drm_device *dev) { @@ -505,6 +561,7 @@ nouveau_fbcon_init(struct drm_device *dev) drm->fbcon = fbcon; INIT_WORK(&drm->fbcon_work, nouveau_fbcon_set_suspend_work); + mutex_init(&fbcon->hotplug_lock); drm_fb_helper_prepare(dev, &fbcon->helper, &nouveau_fbcon_helper_funcs); diff --git a/drivers/gpu/drm/nouveau/nouveau_fbcon.h b/drivers/gpu/drm/nouveau/nouveau_fbcon.h index a6f192ea3fa6..db9d52047ef8 100644 --- a/drivers/gpu/drm/nouveau/nouveau_fbcon.h +++ b/drivers/gpu/drm/nouveau/nouveau_fbcon.h @@ -41,6 +41,9 @@ struct nouveau_fbdev { struct nvif_object gdi; struct nvif_object blit; struct nvif_object twod; + + struct mutex hotplug_lock; + bool hotplug_waiting; }; void nouveau_fbcon_restore(void); @@ -68,6 +71,8 @@ void nouveau_fbcon_set_suspend(struct drm_device *dev, int state); void nouveau_fbcon_accel_save_disable(struct drm_device *dev); void nouveau_fbcon_accel_restore(struct drm_device *dev); +void nouveau_fbcon_output_poll_changed(struct drm_device *dev); +void nouveau_fbcon_hotplug_resume(struct nouveau_fbdev *fbcon); extern int nouveau_nofbaccel; #endif /* __NV50_FBCON_H__ */ -- 2.17.1

7 years, 2 months

1
0
0 0

[PATCH v8 2/5] drm/nouveau: Remove duplicate poll_enable() in pmops_runtime_suspend()

by Lyude Paul

Since actual hotplug notifications don't get disabled until nouveau_display_fini() is called, all this will do is cause any hotplugs that happen between this drm_kms_helper_poll_disable() call and the actual hotplug disablement to potentially be dropped if ACPI isn't around to help us. Signed-off-by: Lyude Paul <lyude(a)redhat.com> Acked-by: Karol Herbst <kherbst(a)redhat.com> Acked-by: Daniel Vetter <daniel(a)ffwll.ch> Cc: stable(a)vger.kernel.org Cc: Lukas Wunner <lukas(a)wunner.de> --- drivers/gpu/drm/nouveau/nouveau_drm.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_drm.c b/drivers/gpu/drm/nouveau/nouveau_drm.c index c7ec86d6c3c9..5fdc1fbe2ee5 100644 --- a/drivers/gpu/drm/nouveau/nouveau_drm.c +++ b/drivers/gpu/drm/nouveau/nouveau_drm.c @@ -835,7 +835,6 @@ nouveau_pmops_runtime_suspend(struct device *dev) return -EBUSY; } - drm_kms_helper_poll_disable(drm_dev); nouveau_switcheroo_optimus_dsm(); ret = nouveau_do_suspend(drm_dev, true); pci_save_state(pdev); -- 2.17.1

7 years, 2 months

1
0
0 0

[PATCH v8 1/5] drm/nouveau: Fix bogus drm_kms_helper_poll_enable() placement

by Lyude Paul

Turns out this part is my fault for not noticing when reviewing 9a2eba337cace ("drm/nouveau: Fix drm poll_helper handling"). Currently we call drm_kms_helper_poll_enable() from nouveau_display_hpd_work(). This makes basically no sense however, because that means we're calling drm_kms_helper_poll_enable() every time we schedule the hotplug detection work. This is also against the advice mentioned in drm_kms_helper_poll_enable()'s documentation: Note that calls to enable and disable polling must be strictly ordered, which is automatically the case when they're only call from suspend/resume callbacks. Of course, hotplugs can't really be ordered. They could even happen immediately after we called drm_kms_helper_poll_disable() in nouveau_display_fini(), which can lead to all sorts of issues. Additionally; enabling polling /after/ we call drm_helper_hpd_irq_event() could also mean that we'd miss a hotplug event anyway, since drm_helper_hpd_irq_event() wouldn't bother trying to probe connectors so long as polling is disabled. So; simply move this back into nouveau_display_init() again. The race condition that both of these patches attempted to work around has already been fixed properly in d61a5c106351 ("drm/nouveau: Fix deadlock on runtime suspend") Fixes: 9a2eba337cace ("drm/nouveau: Fix drm poll_helper handling") Signed-off-by: Lyude Paul <lyude(a)redhat.com> Acked-by: Karol Herbst <kherbst(a)redhat.com> Acked-by: Daniel Vetter <daniel(a)ffwll.ch> Cc: Lukas Wunner <lukas(a)wunner.de> Cc: Peter Ujfalusi <peter.ujfalusi(a)ti.com> Cc: stable(a)vger.kernel.org --- drivers/gpu/drm/nouveau/nouveau_display.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/nouveau/nouveau_display.c b/drivers/gpu/drm/nouveau/nouveau_display.c index ec7861457b84..1d36ab5d4796 100644 --- a/drivers/gpu/drm/nouveau/nouveau_display.c +++ b/drivers/gpu/drm/nouveau/nouveau_display.c @@ -355,8 +355,6 @@ nouveau_display_hpd_work(struct work_struct *work) pm_runtime_get_sync(drm->dev->dev); drm_helper_hpd_irq_event(drm->dev); - /* enable polling for external displays */ - drm_kms_helper_poll_enable(drm->dev); pm_runtime_mark_last_busy(drm->dev->dev); pm_runtime_put_sync(drm->dev->dev); @@ -411,6 +409,11 @@ nouveau_display_init(struct drm_device *dev) if (ret) return ret; + /* enable connector detection and polling for connectors without HPD + * support + */ + drm_kms_helper_poll_enable(dev); + /* enable hotplug interrupts */ drm_connector_list_iter_begin(dev, &conn_iter); nouveau_for_each_non_mst_connector_iter(connector, &conn_iter) { -- 2.17.1

7 years, 2 months

1
0
0 0

[PATCH v4.{9, 14, 17, 18}] x86/l1tf: Fix build error seen if CONFIG_KVM_INTEL is disabled

by Guenter Roeck

commit 1eb46908b35dfbac0ec1848d4b1e39667e0187e9 upstream allmodconfig+CONFIG_INTEL_KVM=n results in the following build error. ERROR: "l1tf_vmx_mitigation" [arch/x86/kvm/kvm.ko] undefined! Fixes: 5b76a3cff011 ("KVM: VMX: Tell the nested hypervisor to skip L1D flush on vmentry") Reported-by: Meelis Roos <mroos(a)linux.ee> Cc: Meelis Roos <mroos(a)linux.ee> Cc: Paolo Bonzini <pbonzini(a)redhat.com> Cc: Thomas Gleixner <tglx(a)linutronix.de> Signed-off-by: Guenter Roeck <linux(a)roeck-us.net> Signed-off-by: Linus Torvalds <torvalds(a)linux-foundation.org> Signed-off-by: Guenter Roeck <linux(a)roeck-us.net> --- arch/x86/kernel/cpu/bugs.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index 5229eaf73828..ac67a76550bd 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -647,10 +647,9 @@ void x86_spec_ctrl_setup_ap(void) enum l1tf_mitigations l1tf_mitigation __ro_after_init = L1TF_MITIGATION_FLUSH; #if IS_ENABLED(CONFIG_KVM_INTEL) EXPORT_SYMBOL_GPL(l1tf_mitigation); - +#endif enum vmx_l1d_flush_state l1tf_vmx_mitigation = VMENTER_L1D_FLUSH_AUTO; EXPORT_SYMBOL_GPL(l1tf_vmx_mitigation); -#endif static void __init l1tf_select_mitigation(void) { -- 2.7.4

7 years, 2 months

2
2
0 0

Re: Fix for 84676c1f (b5b6e8c8) missing in 4.14.y

by Ming Lei

On Fri, Aug 10, 2018 at 02:09:01AM +0000, Felipe Franciosi wrote: > Hi Ming (and all), > > Your series "scsi: virtio_scsi: fix IO hang caused by irq vector automatic affinity" which forces virtio-scsi to use blk-mq fixes an issue introduced by 84676c1f. We noticed that this bug also exists in 4.14.y (as ef86f3a72adb), but your series was not backported to that stable branch. > > Are there any plans to do that? At least CoreOS is using 4.14 and showing issues on AHV (which provides an mq virtio-scsi controller). > Hi Felipe, Looks the following 4 patches should have been marked as stable, sorry for missing that. b5b6e8c8d3b4 scsi: virtio_scsi: fix IO hang caused by automatic irq vector affinity 2f31115e940c scsi: core: introduce force_blk_mq adbe552349f2 scsi: megaraid_sas: fix selection of reply queue 8b834bff1b73 scsi: hpsa: fix selection of reply queue Usually this backporting is done by our stable guys, so I will CC stable and leave them handle it, but I am happy to provide any help for addressing conflicts or sort of thing. Thanks, Ming

7 years, 2 months

3
7
0 0

Re: [PATCH 4.14 000/104] 4.14.63-stable review

by Jinpu Wang

> From: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org> > Date: 2018年8月15日周三上午8:15 > Subject: Re: [PATCH 4.14 000/104] 4.14.63-stable review > To: <linux-kernel(a)vger.kernel.org> > Cc: <torvalds(a)linux-foundation.org>, <akpm(a)linux-foundation.org>, > <linux(a)roeck-us.net>, <shuah(a)kernel.org>, <patches(a)kernelci.org>, > <ben.hutchings(a)codethink.co.uk>, <lkft-triage(a)lists.linaro.org>, > <stable(a)vger.kernel.org> > > > On Tue, Aug 14, 2018 at 07:16:14PM +0200, Greg Kroah-Hartman wrote: > > This is the start of the stable review cycle for the 4.14.63 release. > > There are 104 patches in this series, all will be posted as a response > > to this one. If anyone has any issues with these being applied, please > > let me know. > > > > Responses should be made by Thu Aug 16 17:14:49 UTC 2018. > > Anything received after that time might be too late. > > > > The whole patch series can be found in one patch at: > > https://www.kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.14.63-rc… > > -rc2 is now out: > https://www.kernel.org/pub/linux/kernel/v4.x/stable-review/patch-4.14.63-rc… Merged to our tree, tested on my test machines with basic functional tests, all looks fine. Thanks, -- Jack Wang Linux Kernel Developer ProfitBricks GmbH Greifswalder Str. 207 D - 10405 Berlin Tel: +49 30 577 008 042 Fax: +49 30 577 008 299 Email: jinpu.wang(a)profitbricks.com URL: https://www.profitbricks.de Sitz der Gesellschaft: Berlin Registergericht: Amtsgericht Charlottenburg, HRB 125506 B Geschäftsführer: Achim Weiss, Matthias Steinberg, Christoph Steffens

7 years, 2 months

2
1
0 0

Applied "spi: fix IDR collision on systems with both fixed and dynamic SPI bus numbers" to the spi tree

by Mark Brown

The patch spi: fix IDR collision on systems with both fixed and dynamic SPI bus numbers has been applied to the spi tree at https://git.kernel.org/pub/scm/linux/kernel/git/broonie/spi.git All being well this means that it will be integrated into the linux-next tree (usually sometime in the next 24 hours) and sent to Linus during the next merge window (or sooner if it is a bug fix), however if problems are discovered then the patch may be dropped or reverted. You may get further e-mails resulting from automated or manual testing and review of the tree, please engage with people reporting problems and send followup patches addressing any issues that are reported if needed. If any updates are required or you are submitting further changes they should be sent as incremental updates against current git, existing patches will not be replaced. Please add any relevant lists and maintainers to the CCs when replying to this mail. Thanks, Mark >From 1a4327fbf4554d5b78d75b19a13d40d6de220159 Mon Sep 17 00:00:00 2001 From: Kirill Kapranov <kirill.kapranov(a)compulab.co.il> Date: Mon, 13 Aug 2018 19:48:10 +0300 Subject: [PATCH] spi: fix IDR collision on systems with both fixed and dynamic SPI bus numbers On systems where some controllers get a dynamic ID assigned and some have a fixed number (e.g. from ACPI tables), the current implementation might run into an IDR collision: in case of a fixed bus number is gotten by a driver (but not marked busy in IDR tree) and a driver with dynamic bus number gets the same ID and predictably fails. Fix this by means of checking-in fixed IDsin IDR as far as dynamic ones at the moment of the controller registration. Fixes: 9b61e302210e (spi: Pick spi bus number from Linux idr or spi alias) Signed-off-by: Kirill Kapranov <kirill.kapranov(a)compulab.co.il> Signed-off-by: Mark Brown <broonie(a)kernel.org> Cc: stable(a)vger.kernel.org --- drivers/spi/spi.c | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/drivers/spi/spi.c b/drivers/spi/spi.c index ec395a6baf9c..a00d006d4c3a 100644 --- a/drivers/spi/spi.c +++ b/drivers/spi/spi.c @@ -2170,6 +2170,15 @@ int spi_register_controller(struct spi_controller *ctlr) if (WARN(id < 0, "couldn't get idr")) return id; ctlr->bus_num = id; + } else { + /* devices with a fixed bus num must check-in with the num */ + mutex_lock(&board_lock); + id = idr_alloc(&spi_master_idr, ctlr, ctlr->bus_num, + ctlr->bus_num + 1, GFP_KERNEL); + mutex_unlock(&board_lock); + if (WARN(id < 0, "couldn't get idr")) + return id == -ENOSPC ? -EBUSY : id; + ctlr->bus_num = id; } INIT_LIST_HEAD(&ctlr->queue); spin_lock_init(&ctlr->queue_lock); -- 2.18.0

7 years, 2 months

1
0
0 0

[PATCH v4.9 1/2] x86/cpu/amd: Limit cpu_core_id fixup to families older than F17h

by Guenter Roeck

From: Suravee Suthikulpanit <suravee.suthikulpanit(a)amd.com> commit b89b41d0b8414690ec0030c134b8bde209e6d06c upstream Current cpu_core_id fixup causes downcored F17h configurations to be incorrect: NODE: 0 processor 0 core id : 0 processor 1 core id : 1 processor 2 core id : 2 processor 3 core id : 4 processor 4 core id : 5 processor 5 core id : 0 NODE: 1 processor 6 core id : 2 processor 7 core id : 3 processor 8 core id : 4 processor 9 core id : 0 processor 10 core id : 1 processor 11 core id : 2 Code that relies on the cpu_core_id, like match_smt(), for example, which builds the thread siblings masks used by the scheduler, is mislead. So, limit the fixup to pre-F17h machines. The new value for cpu_core_id for F17h and later will represent the CPUID_Fn8000001E_EBX[CoreId], which is guaranteed to be unique for each core within a socket. This way we have: NODE: 0 processor 0 core id : 0 processor 1 core id : 1 processor 2 core id : 2 processor 3 core id : 4 processor 4 core id : 5 processor 5 core id : 6 NODE: 1 processor 6 core id : 8 processor 7 core id : 9 processor 8 core id : 10 processor 9 core id : 12 processor 10 core id : 13 processor 11 core id : 14 Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit(a)amd.com> [ Heavily massaged. ] Signed-off-by: Borislav Petkov <bp(a)suse.de> Cc: Linus Torvalds <torvalds(a)linux-foundation.org> Cc: Peter Zijlstra <peterz(a)infradead.org> Cc: Thomas Gleixner <tglx(a)linutronix.de> Cc: Yazen Ghannam <Yazen.Ghannam(a)amd.com> Link: http://lkml.kernel.org/r/20170731085159.9455-2-bp@alien8.de Signed-off-by: Ingo Molnar <mingo(a)kernel.org> Signed-off-by: Guenter Roeck <linux(a)roeck-us.net> --- arch/x86/kernel/cpu/amd.c | 24 +++++++++++++++++------- 1 file changed, 17 insertions(+), 7 deletions(-) diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 6de596449488..e864ff6cd8bd 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -305,6 +305,22 @@ static void amd_get_topology_early(struct cpuinfo_x86 *c) } /* + * Fix up cpu_core_id for pre-F17h systems to be in the + * [0 .. cores_per_node - 1] range. Not really needed but + * kept so as not to break existing setups. + */ +static void legacy_fixup_core_id(struct cpuinfo_x86 *c) +{ + u32 cus_per_node; + + if (c->x86 >= 0x17) + return; + + cus_per_node = c->x86_max_cores / nodes_per_socket; + c->cpu_core_id %= cus_per_node; +} + +/* * Fixup core topology information for * (1) AMD multi-node processors * Assumption: Number of cores in each internal node is the same. @@ -359,15 +375,9 @@ static void amd_get_topology(struct cpuinfo_x86 *c) } else return; - /* fixup multi-node processor information */ if (nodes_per_socket > 1) { - u32 cus_per_node; - set_cpu_cap(c, X86_FEATURE_AMD_DCM); - cus_per_node = c->x86_max_cores / nodes_per_socket; - - /* core id has to be in the [0 .. cores_per_node - 1] range */ - c->cpu_core_id %= cus_per_node; + legacy_fixup_core_id(c); } } #endif -- 2.7.4

7 years, 2 months

2
2
0 0

[PATCH v4.14, v4.17] x86/CPU/AMD: Have smp_num_siblings and cpu_llc_id always be present

by Guenter Roeck

From: Borislav Petkov <bpetkov(a)suse.de> commit f8b64d08dde2714c62751d18ba77f4aeceb161d3 upstream Move smp_num_siblings and cpu_llc_id to cpu/common.c so that they're always present as symbols and not only in the CONFIG_SMP case. Then, other code using them doesn't need ugly ifdeffery anymore. Get rid of some ifdeffery. Signed-off-by: Borislav Petkov <bpetkov(a)suse.de> Signed-off-by: Suravee Suthikulpanit <suravee.suthikulpanit(a)amd.com> Signed-off-by: Borislav Petkov <bp(a)suse.de> Signed-off-by: Thomas Gleixner <tglx(a)linutronix.de> Link: http://lkml.kernel.org/r/1524864877-111962-2-git-send-email-suravee.suthiku… Signed-off-by: Guenter Roeck <linux(a)roeck-us.net> --- Needed for x86_64:allnoconfig. arch/x86/include/asm/smp.h | 1 - arch/x86/kernel/cpu/amd.c | 10 +--------- arch/x86/kernel/cpu/common.c | 7 +++++++ arch/x86/kernel/smpboot.c | 7 ------- 4 files changed, 8 insertions(+), 17 deletions(-) diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h index 461f53d27708..fe2ee61880a8 100644 --- a/arch/x86/include/asm/smp.h +++ b/arch/x86/include/asm/smp.h @@ -170,7 +170,6 @@ static inline int wbinvd_on_all_cpus(void) wbinvd(); return 0; } -#define smp_num_siblings 1 #endif /* CONFIG_SMP */ extern unsigned disabled_cpus; diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index bb013735510a..dda741bd5789 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -298,7 +298,6 @@ static int nearby_node(int apicid) } #endif -#ifdef CONFIG_SMP /* * Fix up cpu_core_id for pre-F17h systems to be in the * [0 .. cores_per_node - 1] range. Not really needed but @@ -382,7 +381,6 @@ static void amd_get_topology(struct cpuinfo_x86 *c) legacy_fixup_core_id(c); } } -#endif /* * On a AMD dual core setup the lower bits of the APIC id distinguish the cores. @@ -390,7 +388,6 @@ static void amd_get_topology(struct cpuinfo_x86 *c) */ static void amd_detect_cmp(struct cpuinfo_x86 *c) { -#ifdef CONFIG_SMP unsigned bits; int cpu = smp_processor_id(); @@ -402,16 +399,11 @@ static void amd_detect_cmp(struct cpuinfo_x86 *c) /* use socket ID also for last level cache */ per_cpu(cpu_llc_id, cpu) = c->phys_proc_id; amd_get_topology(c); -#endif } u16 amd_get_nb_id(int cpu) { - u16 id = 0; -#ifdef CONFIG_SMP - id = per_cpu(cpu_llc_id, cpu); -#endif - return id; + return per_cpu(cpu_llc_id, cpu); } EXPORT_SYMBOL_GPL(amd_get_nb_id); diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index c925498224d0..dd02ee4fa8cd 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -66,6 +66,13 @@ cpumask_var_t cpu_callin_mask; /* representing cpus for which sibling maps can be computed */ cpumask_var_t cpu_sibling_setup_mask; +/* Number of siblings per CPU package */ +int smp_num_siblings = 1; +EXPORT_SYMBOL(smp_num_siblings); + +/* Last level cache ID of each logical CPU */ +DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id) = BAD_APICID; + /* correctly size the local cpu masks */ void __init setup_cpu_local_masks(void) { diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c index 6fd12e0a07c9..5ebb0dbcf4f7 100644 --- a/arch/x86/kernel/smpboot.c +++ b/arch/x86/kernel/smpboot.c @@ -80,13 +80,6 @@ #include <asm/spec-ctrl.h> #include <asm/hw_irq.h> -/* Number of siblings per CPU package */ -int smp_num_siblings = 1; -EXPORT_SYMBOL(smp_num_siblings); - -/* Last level cache ID of each logical CPU */ -DEFINE_PER_CPU_READ_MOSTLY(u16, cpu_llc_id) = BAD_APICID; - /* representing HT siblings of each logical CPU */ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_sibling_map); EXPORT_PER_CPU_SYMBOL(cpu_sibling_map); -- 2.7.4

7 years, 2 months

2
1
0 0

[PATCH V2] EDAC, amd64: Add Family 17h Model 10h support.

by Michael Jin

Add support for ECC error decoding on family 17h models 10h-2fh. Link: https://lkml.kernel.org/r/20180810193623.24629-1-mikhail.jin@gmail.com Cc: stable(a)vger.kernel.org Signed-off-by: Michael Jin <mikhail.jin(a)gmail.com> --- drivers/edac/amd64_edac.c | 15 +++++++++++++++ drivers/edac/amd64_edac.h | 3 +++ 2 files changed, 18 insertions(+) diff --git a/drivers/edac/amd64_edac.c b/drivers/edac/amd64_edac.c index 18aeabb1d5ee..2d7b6d37d6ec 100644 --- a/drivers/edac/amd64_edac.c +++ b/drivers/edac/amd64_edac.c @@ -2200,6 +2200,15 @@ static struct amd64_family_type family_types[] = { .dbam_to_cs = f17_base_addr_to_cs_size, } }, + [F17_M10H_CPUS] = { + .ctl_name = "F17h_M10h", + .f0_id = PCI_DEVICE_ID_AMD_17H_M10H_DF_F0, + .f6_id = PCI_DEVICE_ID_AMD_17H_M10H_DF_F6, + .ops = { + .early_channel_count = f17_early_channel_count, + .dbam_to_cs = f17_base_addr_to_cs_size, + } + }, }; /* @@ -3188,6 +3197,12 @@ static struct amd64_family_type *per_family_init(struct amd64_pvt *pvt) break; case 0x17: + /* Check if CPU model is in range 10h-2fh */ + if (pvt->model >= 0x10 && pvt->model <= 0x2f) { + fam_type = &family_types[F17_M10H_CPUS]; + pvt->ops = &family_types[F17_M10H_CPUS].ops; + break; + } fam_type = &family_types[F17_CPUS]; pvt->ops = &family_types[F17_CPUS].ops; break; diff --git a/drivers/edac/amd64_edac.h b/drivers/edac/amd64_edac.h index 1d4b74e9a037..4242f8e39c18 100644 --- a/drivers/edac/amd64_edac.h +++ b/drivers/edac/amd64_edac.h @@ -115,6 +115,8 @@ #define PCI_DEVICE_ID_AMD_16H_M30H_NB_F2 0x1582 #define PCI_DEVICE_ID_AMD_17H_DF_F0 0x1460 #define PCI_DEVICE_ID_AMD_17H_DF_F6 0x1466 +#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F0 0x15e8 +#define PCI_DEVICE_ID_AMD_17H_M10H_DF_F6 0x15ee /* * Function 1 - Address Map @@ -281,6 +283,7 @@ enum amd_families { F16_CPUS, F16_M30H_CPUS, F17_CPUS, + F17_M10H_CPUS, NUM_FAMILIES, }; -- 2.14.3 (Apple Git-98)

7 years, 2 months

1
0
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror