September 2024 - Linux-stable-mirror

[PATCH v2] drm/xe: fix UAF around queue destruction

by Matthew Auld

We currently do stuff like queuing the final destruction step on a random system wq, which will outlive the driver instance. With bad timing we can teardown the driver with one or more work workqueue still being alive leading to various UAF splats. Add a fini step to ensure user queues are properly torn down. At this point GuC should already be nuked so queue itself should no longer be referenced from hw pov. v2 (Matt B) - Looks much safer to use a waitqueue and then just wait for the xa_array to become empty before triggering the drain. Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/2317 Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Signed-off-by: Matthew Auld <matthew.auld(a)intel.com> Cc: Matthew Brost <matthew.brost(a)intel.com> Cc: <stable(a)vger.kernel.org> # v6.8+ --- drivers/gpu/drm/xe/xe_device.c | 6 +++++- drivers/gpu/drm/xe/xe_device_types.h | 3 +++ drivers/gpu/drm/xe/xe_guc_submit.c | 26 +++++++++++++++++++++++++- drivers/gpu/drm/xe/xe_guc_types.h | 2 ++ 4 files changed, 35 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index cb5a9fd820cf..90b3478ed7cd 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -297,6 +297,9 @@ static void xe_device_destroy(struct drm_device *dev, void *dummy) if (xe->unordered_wq) destroy_workqueue(xe->unordered_wq); + if (xe->destroy_wq) + destroy_workqueue(xe->destroy_wq); + ttm_device_fini(&xe->ttm); } @@ -360,8 +363,9 @@ struct xe_device *xe_device_create(struct pci_dev *pdev, xe->preempt_fence_wq = alloc_ordered_workqueue("xe-preempt-fence-wq", 0); xe->ordered_wq = alloc_ordered_workqueue("xe-ordered-wq", 0); xe->unordered_wq = alloc_workqueue("xe-unordered-wq", 0, 0); + xe->destroy_wq = alloc_workqueue("xe-destroy-wq", 0, 0); if (!xe->ordered_wq || !xe->unordered_wq || - !xe->preempt_fence_wq) { + !xe->preempt_fence_wq || !xe->destroy_wq) { /* * Cleanup done in xe_device_destroy via * drmm_add_action_or_reset register above diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index 5ad96d283a71..515385b916cc 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -422,6 +422,9 @@ struct xe_device { /** @unordered_wq: used to serialize unordered work, mostly display */ struct workqueue_struct *unordered_wq; + /** @destroy_wq: used to serialize user destroy work, like queue */ + struct workqueue_struct *destroy_wq; + /** @tiles: device tiles */ struct xe_tile tiles[XE_MAX_TILES_PER_DEVICE]; diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index fbbe6a487bbb..ae2f85cc2d08 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -276,10 +276,26 @@ static struct workqueue_struct *get_submit_wq(struct xe_guc *guc) } #endif +static void xe_guc_submit_fini(struct xe_guc *guc) +{ + struct xe_device *xe = guc_to_xe(guc); + struct xe_gt *gt = guc_to_gt(guc); + int ret; + + ret = wait_event_timeout( + guc->submission_state.fini_wq, + xa_empty(&guc->submission_state.exec_queue_lookup), HZ * 5); + + drain_workqueue(xe->destroy_wq); + + xe_gt_assert(gt, ret); +} + static void guc_submit_fini(struct drm_device *drm, void *arg) { struct xe_guc *guc = arg; + xe_guc_submit_fini(guc); xa_destroy(&guc->submission_state.exec_queue_lookup); free_submit_wq(guc); } @@ -345,6 +361,8 @@ int xe_guc_submit_init(struct xe_guc *guc, unsigned int num_ids) xa_init(&guc->submission_state.exec_queue_lookup); + init_waitqueue_head(&guc->submission_state.fini_wq); + primelockdep(guc); return drmm_add_action_or_reset(&xe->drm, guc_submit_fini, guc); @@ -361,6 +379,9 @@ static void __release_guc_id(struct xe_guc *guc, struct xe_exec_queue *q, u32 xa xe_guc_id_mgr_release_locked(&guc->submission_state.idm, q->guc->id, q->width); + + if (xa_empty(&guc->submission_state.exec_queue_lookup)) + wake_up(&guc->submission_state.fini_wq); } static int alloc_guc_id(struct xe_guc *guc, struct xe_exec_queue *q) @@ -1268,13 +1289,16 @@ static void __guc_exec_queue_fini_async(struct work_struct *w) static void guc_exec_queue_fini_async(struct xe_exec_queue *q) { + struct xe_guc *guc = exec_queue_to_guc(q); + struct xe_device *xe = guc_to_xe(guc); + INIT_WORK(&q->guc->fini_async, __guc_exec_queue_fini_async); /* We must block on kernel engines so slabs are empty on driver unload */ if (q->flags & EXEC_QUEUE_FLAG_PERMANENT || exec_queue_wedged(q)) __guc_exec_queue_fini_async(&q->guc->fini_async); else - queue_work(system_wq, &q->guc->fini_async); + queue_work(xe->destroy_wq, &q->guc->fini_async); } static void __guc_exec_queue_fini(struct xe_guc *guc, struct xe_exec_queue *q) diff --git a/drivers/gpu/drm/xe/xe_guc_types.h b/drivers/gpu/drm/xe/xe_guc_types.h index 546ac6350a31..69046f698271 100644 --- a/drivers/gpu/drm/xe/xe_guc_types.h +++ b/drivers/gpu/drm/xe/xe_guc_types.h @@ -81,6 +81,8 @@ struct xe_guc { #endif /** @submission_state.enabled: submission is enabled */ bool enabled; + /** @submission_state.fini_wq: submit fini wait queue */ + wait_queue_head_t fini_wq; } submission_state; /** @hwconfig: Hardware config state */ struct { -- 2.46.1

11 months, 3 weeks

2
1
0 0

[PATCH 1/2] drm/xe/vm: move xa_alloc to prevent UAF

by Matthew Auld

Evil user can guess the next id of the vm before the ioctl completes and then call vm destroy ioctl to trigger UAF since create ioctl is still referencing the same vm. Move the xa_alloc all the way to the end to prevent this. Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Signed-off-by: Matthew Auld <matthew.auld(a)intel.com> Cc: Matthew Brost <matthew.brost(a)intel.com> Cc: <stable(a)vger.kernel.org> # v6.8+ --- drivers/gpu/drm/xe/xe_vm.c | 22 ++++++++++------------ 1 file changed, 10 insertions(+), 12 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index a3d7cb7cfd22..f7182ef3d8e6 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -1765,12 +1765,6 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data, if (IS_ERR(vm)) return PTR_ERR(vm); - mutex_lock(&xef->vm.lock); - err = xa_alloc(&xef->vm.xa, &id, vm, xa_limit_32b, GFP_KERNEL); - mutex_unlock(&xef->vm.lock); - if (err) - goto err_close_and_put; - if (xe->info.has_asid) { down_write(&xe->usm.lock); err = xa_alloc_cyclic(&xe->usm.asid_to_vm, &asid, vm, @@ -1778,12 +1772,11 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data, &xe->usm.next_asid, GFP_KERNEL); up_write(&xe->usm.lock); if (err < 0) - goto err_free_id; + goto err_close_and_put; vm->usm.asid = asid; } - args->vm_id = id; vm->xef = xe_file_get(xef); /* Record BO memory for VM pagetable created against client */ @@ -1796,12 +1789,17 @@ int xe_vm_create_ioctl(struct drm_device *dev, void *data, args->reserved[0] = xe_bo_main_addr(vm->pt_root[0]->bo, XE_PAGE_SIZE); #endif - return 0; - -err_free_id: + /* user id alloc must always be last in ioctl to prevent UAF */ mutex_lock(&xef->vm.lock); - xa_erase(&xef->vm.xa, id); + err = xa_alloc(&xef->vm.xa, &id, vm, xa_limit_32b, GFP_KERNEL); mutex_unlock(&xef->vm.lock); + if (err) + goto err_close_and_put; + + args->vm_id = id; + + return 0; + err_close_and_put: xe_vm_close_and_put(vm); -- 2.46.1

11 months, 3 weeks

2
1
0 0

RESEND. syzbot: KASAN: slab-out-of-bounds Read in xlog_pack_data

by Andrey Kalachev

Hi, I found that the syzbot bug 'KASAN: slab-out-of-bounds Read in xlog_pack_data' [1] has been fixed in master branch since v6.4-rc6-11-gf1e1765aad7d [2]. But, it still exist in LTS kernels: 5.4, 5.10, 5.15 [3], 6.1 [4] Common c-reproducer code can be found here [5]. I've made backport f1e1765aad7d ("xfs: journal geometry is not properly bounds checked") Patch for v5.15 & v6.1 is same with original upstream code. Patches for v5.4 and v5.10 has some cosmetic variations: `xfs_has_crc(mp)` call replaced by `xfs_sb_version_hascrc(&mp->m_sb)` at most. I would be grateful for any assistance. Regards, AK [1] https://syzkaller.appspot.com/bug?extid=b7854dc75e15ffc8c2ae [2] https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git/commit/?id… [3] https://syzkaller.appspot.com/bug?extid=66f256de193ab682584f [4] https://syzkaller.appspot.com/bug?extid=904ffc7f25c759741787 [5] https://syzkaller.appspot.com/text?tag=ReproC&x=152f7343280000 Reported-by: syzbot+66f256de193ab682584f(a)syzkaller.appspotmail.com Reported-by: syzbot+904ffc7f25c759741787(a)syzkaller.appspotmail.com

11 months, 3 weeks

1
3
0 0

Re: [PATCH] x86/CPU/AMD: Only apply Zenbleed fix for Zen2 during late microcode load

by John Allen

On Mon, Sep 23, 2024 at 03:41:12PM +0000, John Allen wrote: > A problem was introduced with f69759b ("x86/CPU/AMD: Move Zenbleed check to > the Zen2 init function") where a bit in the DE_CFG MSR is getting set after > a microcode late load. > > The problem is that the microcode late load path calls into > amd_check_microcode and subsequently zen2_zenbleed_check. Since the patch > removes the cpu_has_amd_erratum check from zen2_zenbleed_check, this will > cause all non-Zen2 cpus to go through the function and set the bit in the > DE_CFG MSR. > > Call into the zenbleed fix path on Zen2 cpus only. > > Fixes: f69759be251d ("x86/CPU/AMD: Move Zenbleed check to the Zen2 init function") Should probably go into stable as well. Cc: <stable(a)vger.kernel.org> > Signed-off-by: John Allen <john.allen(a)amd.com> > --- > arch/x86/kernel/cpu/amd.c | 3 ++- > 1 file changed, 2 insertions(+), 1 deletion(-) > > diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c > index 015971adadfc..368344e1394b 100644 > --- a/arch/x86/kernel/cpu/amd.c > +++ b/arch/x86/kernel/cpu/amd.c > @@ -1202,5 +1202,6 @@ void amd_check_microcode(void) > if (boot_cpu_data.x86_vendor != X86_VENDOR_AMD) > return; > > - on_each_cpu(zenbleed_check_cpu, NULL, 1); > + if (boot_cpu_has(X86_FEATURE_ZEN2)) > + on_each_cpu(zenbleed_check_cpu, NULL, 1); > } > -- > 2.34.1 >

11 months, 3 weeks

1
0
0 0

[PATCH] i2c/synquacer: Deal with optional PCLK correctly

by Ard Biesheuvel

From: Ard Biesheuvel <ardb(a)kernel.org> ACPI boot does not provide clocks and regulators, but instead, provides the PCLK rate directly, and enables the clock in firmware. So deal gracefully with this. Fixes: 55750148e559 ("i2c: synquacer: Fix an error handling path in synquacer_i2c_probe()") Cc: <stable(a)vger.kernel.org> Cc: Andi Shyti <andi.shyti(a)kernel.org> Cc: Christophe JAILLET <christophe.jaillet(a)wanadoo.fr> Signed-off-by: Ard Biesheuvel <ardb(a)kernel.org> --- https://lore.kernel.org/all/CAMj1kXFH+zB_YuUS+vaEpguhuVGLYbQw55VNDCxnBfSPe6… drivers/i2c/busses/i2c-synquacer.c | 5 +++-- 1 file changed, 3 insertions(+), 2 deletions(-) diff --git a/drivers/i2c/busses/i2c-synquacer.c b/drivers/i2c/busses/i2c-synquacer.c index 4eccbcd0fbfc..bbb9062669e4 100644 --- a/drivers/i2c/busses/i2c-synquacer.c +++ b/drivers/i2c/busses/i2c-synquacer.c @@ -550,12 +550,13 @@ static int synquacer_i2c_probe(struct platform_device *pdev) device_property_read_u32(&pdev->dev, "socionext,pclk-rate", &i2c->pclkrate); - pclk = devm_clk_get_enabled(&pdev->dev, "pclk"); + pclk = devm_clk_get_optional_enabled(&pdev->dev, "pclk"); if (IS_ERR(pclk)) return dev_err_probe(&pdev->dev, PTR_ERR(pclk), "failed to get and enable clock\n"); - i2c->pclkrate = clk_get_rate(pclk); + if (pclk) + i2c->pclkrate = clk_get_rate(pclk); if (i2c->pclkrate < SYNQUACER_I2C_MIN_CLK_RATE || i2c->pclkrate > SYNQUACER_I2C_MAX_CLK_RATE) -- 2.46.0.662.g92d0881bb0-goog

11 months, 3 weeks

5
5
0 0

[PATCH] drm: Consistently use struct drm_mode_rect for FB_DAMAGE_CLIPS

by Thomas Zimmermann

FB_DAMAGE_CLIPS is a plane property for damage handling. Its UAPI should only use UAPI types. Hence replace struct drm_rect with struct drm_mode_rect in drm_atomic_plane_set_property(). Both types are identical in practice, so there's no change in behavior. Reported-by: Ville Syrjälä <ville.syrjala(a)linux.intel.com> Closes: https://lore.kernel.org/dri-devel/Zu1Ke1TuThbtz15E@intel.com/ Signed-off-by: Thomas Zimmermann <tzimmermann(a)suse.de> Fixes: d3b21767821e ("drm: Add a new plane property to send damage during plane update") Cc: Lukasz Spintzyk <lukasz.spintzyk(a)displaylink.com> Cc: Deepak Rawat <drawat(a)vmware.com> Cc: Daniel Vetter <daniel.vetter(a)ffwll.ch> Cc: Thomas Hellstrom <thellstrom(a)vmware.com> Cc: David Airlie <airlied(a)gmail.com> Cc: Simona Vetter <simona(a)ffwll.ch> Cc: Maarten Lankhorst <maarten.lankhorst(a)linux.intel.com> Cc: Maxime Ripard <mripard(a)kernel.org> Cc: Thomas Zimmermann <tzimmermann(a)suse.de> Cc: dri-devel(a)lists.freedesktop.org Cc: <stable(a)vger.kernel.org> # v5.0+ --- drivers/gpu/drm/drm_atomic_uapi.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c index 7936c2023955..370dc676e3aa 100644 --- a/drivers/gpu/drm/drm_atomic_uapi.c +++ b/drivers/gpu/drm/drm_atomic_uapi.c @@ -543,7 +543,7 @@ static int drm_atomic_plane_set_property(struct drm_plane *plane, &state->fb_damage_clips, val, -1, - sizeof(struct drm_rect), + sizeof(struct drm_mode_rect), &replaced); return ret; } else if (property == plane->scaling_filter_property) { -- 2.46.0

11 months, 3 weeks

2
1
0 0

[PATCH v3] pinctrl: stm32: check devm_kasprintf() returned value

by Ma Ke

devm_kasprintf() can return a NULL pointer on failure but this returned value is not checked. Fix this lack and check the returned value. Found by code review. Cc: stable(a)vger.kernel.org Fixes: 32c170ff15b0 ("pinctrl: stm32: set default gpio line names using pin names") Signed-off-by: Ma Ke <make24(a)iscas.ac.cn> --- Changes in v3: - modified the code style according to suggestions. Changes in v2: - modified the patch according to suggestions, added braces; - modified the typo. --- drivers/pinctrl/stm32/pinctrl-stm32.c | 9 +++++++-- 1 file changed, 7 insertions(+), 2 deletions(-) diff --git a/drivers/pinctrl/stm32/pinctrl-stm32.c b/drivers/pinctrl/stm32/pinctrl-stm32.c index a8673739871d..5b7fa77c1184 100644 --- a/drivers/pinctrl/stm32/pinctrl-stm32.c +++ b/drivers/pinctrl/stm32/pinctrl-stm32.c @@ -1374,10 +1374,15 @@ static int stm32_gpiolib_register_bank(struct stm32_pinctrl *pctl, struct fwnode for (i = 0; i < npins; i++) { stm32_pin = stm32_pctrl_get_desc_pin_from_gpio(pctl, bank, i); - if (stm32_pin && stm32_pin->pin.name) + if (stm32_pin && stm32_pin->pin.name) { names[i] = devm_kasprintf(dev, GFP_KERNEL, "%s", stm32_pin->pin.name); - else + if (!names[i]) { + err = -ENOMEM; + goto err_clk; + } + } else { names[i] = NULL; + } } bank->gpio_chip.names = (const char * const *)names; -- 2.25.1

11 months, 3 weeks

2
1
0 0

[PATCH] pinctrl: check devm_kasprintf() returned value

by Ma Ke

devm_kasprintf() can return a NULL pointer on failure but this returned value is not checked. Fix this lack and check the returned value. Found by code review. Cc: stable(a)vger.kernel.org Fixes: a0f160ffcb83 ("pinctrl: add pinctrl/GPIO driver for Apple SoCs") Signed-off-by: Ma Ke <make24(a)iscas.ac.cn> --- drivers/pinctrl/pinctrl-apple-gpio.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/pinctrl/pinctrl-apple-gpio.c b/drivers/pinctrl/pinctrl-apple-gpio.c index 3751c7de37aa..f861e63f4115 100644 --- a/drivers/pinctrl/pinctrl-apple-gpio.c +++ b/drivers/pinctrl/pinctrl-apple-gpio.c @@ -474,6 +474,9 @@ static int apple_gpio_pinctrl_probe(struct platform_device *pdev) for (i = 0; i < npins; i++) { pins[i].number = i; pins[i].name = devm_kasprintf(&pdev->dev, GFP_KERNEL, "PIN%u", i); + if (!pins[i].name) + return -ENOMEM; + pins[i].drv_data = pctl; pin_names[i] = pins[i].name; pin_nums[i] = i; -- 2.25.1

11 months, 3 weeks

2
1
0 0

[PATCH] drm/xe: fix UAF around queue destruction

by Matthew Auld

We currently do stuff like queuing the final destruction step on a random system wq, which will outlive the driver instance. With bad timing we can teardown the driver with one or more work workqueue still being alive leading to various UAF splats. Add a fini step to ensure user queues are properly torn down. At this point GuC should already be nuked so queue itself should no longer be referenced from hw pov. Closes: https://gitlab.freedesktop.org/drm/xe/kernel/-/issues/2317 Fixes: dd08ebf6c352 ("drm/xe: Introduce a new DRM driver for Intel GPUs") Signed-off-by: Matthew Auld <matthew.auld(a)intel.com> Cc: Matthew Brost <matthew.brost(a)intel.com> Cc: <stable(a)vger.kernel.org> # v6.8+ --- drivers/gpu/drm/xe/xe_device.c | 6 +++++- drivers/gpu/drm/xe/xe_device_types.h | 3 +++ drivers/gpu/drm/xe/xe_guc_submit.c | 32 +++++++++++++++++++++++++++- 3 files changed, 39 insertions(+), 2 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c index cb5a9fd820cf..90b3478ed7cd 100644 --- a/drivers/gpu/drm/xe/xe_device.c +++ b/drivers/gpu/drm/xe/xe_device.c @@ -297,6 +297,9 @@ static void xe_device_destroy(struct drm_device *dev, void *dummy) if (xe->unordered_wq) destroy_workqueue(xe->unordered_wq); + if (xe->destroy_wq) + destroy_workqueue(xe->destroy_wq); + ttm_device_fini(&xe->ttm); } @@ -360,8 +363,9 @@ struct xe_device *xe_device_create(struct pci_dev *pdev, xe->preempt_fence_wq = alloc_ordered_workqueue("xe-preempt-fence-wq", 0); xe->ordered_wq = alloc_ordered_workqueue("xe-ordered-wq", 0); xe->unordered_wq = alloc_workqueue("xe-unordered-wq", 0, 0); + xe->destroy_wq = alloc_workqueue("xe-destroy-wq", 0, 0); if (!xe->ordered_wq || !xe->unordered_wq || - !xe->preempt_fence_wq) { + !xe->preempt_fence_wq || !xe->destroy_wq) { /* * Cleanup done in xe_device_destroy via * drmm_add_action_or_reset register above diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index 5ad96d283a71..515385b916cc 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -422,6 +422,9 @@ struct xe_device { /** @unordered_wq: used to serialize unordered work, mostly display */ struct workqueue_struct *unordered_wq; + /** @destroy_wq: used to serialize user destroy work, like queue */ + struct workqueue_struct *destroy_wq; + /** @tiles: device tiles */ struct xe_tile tiles[XE_MAX_TILES_PER_DEVICE]; diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index fbbe6a487bbb..66441efa0bcd 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -276,10 +276,37 @@ static struct workqueue_struct *get_submit_wq(struct xe_guc *guc) } #endif +static void guc_exec_queue_fini_async(struct xe_exec_queue *q); + +static void xe_guc_submit_fini(struct xe_guc *guc) +{ + struct xe_device *xe = guc_to_xe(guc); + struct xe_exec_queue *q; + unsigned long index; + + mutex_lock(&guc->submission_state.lock); + xa_for_each(&guc->submission_state.exec_queue_lookup, index, q) { + struct xe_gpu_scheduler *sched = &q->guc->sched; + + xe_assert(xe, !kref_read(&q->refcount)); + + xe_sched_submission_stop(sched); + + if (exec_queue_registered(q) && !exec_queue_wedged(q)) + guc_exec_queue_fini_async(q); + } + mutex_unlock(&guc->submission_state.lock); + + drain_workqueue(xe->destroy_wq); + + xe_assert(xe, xa_empty(&guc->submission_state.exec_queue_lookup)); +} + static void guc_submit_fini(struct drm_device *drm, void *arg) { struct xe_guc *guc = arg; + xe_guc_submit_fini(guc); xa_destroy(&guc->submission_state.exec_queue_lookup); free_submit_wq(guc); } @@ -1268,13 +1295,16 @@ static void __guc_exec_queue_fini_async(struct work_struct *w) static void guc_exec_queue_fini_async(struct xe_exec_queue *q) { + struct xe_guc *guc = exec_queue_to_guc(q); + struct xe_device *xe = guc_to_xe(guc); + INIT_WORK(&q->guc->fini_async, __guc_exec_queue_fini_async); /* We must block on kernel engines so slabs are empty on driver unload */ if (q->flags & EXEC_QUEUE_FLAG_PERMANENT || exec_queue_wedged(q)) __guc_exec_queue_fini_async(&q->guc->fini_async); else - queue_work(system_wq, &q->guc->fini_async); + queue_work(xe->destroy_wq, &q->guc->fini_async); } static void __guc_exec_queue_fini(struct xe_guc *guc, struct xe_exec_queue *q) -- 2.46.0

11 months, 3 weeks

2
2
0 0

Fix for kernel crash when changing amd-pstate modes

by Mario Limonciello

Hi, This commit from mainline fixes a crash found in kernel 6.11 if users change modes with amd-pstate. commit 49243adc715e ("cpufreq/amd-pstate: Add the missing cpufreq_cpu_put()") Please backport to 6.11.y. Earlier kernels should not be affected. Thanks!

11 months, 3 weeks

2
1
0 0

2025

2024

2023

2022

2021

2020

2019

2018

2017

Linux-stable-mirror September 2024