CVE-2024-26937

In the Linux kernel, the following vulnerability has been resolved:

drm/i915/gt: Reset queuepriorityhint on parking

Originally, with strict in order execution, we could complete execution only when the queue was empty. Preempt-to-busy allows replacement of an active request that may complete before the preemption is processed by HW. If that happens, the request is retired from the queue, but the queuepriorityhint remains set, preventing direct submission until after the next CS interrupt is processed.

This preempt-to-busy race can be triggered by the heartbeat, which will also act as the power-management barrier and upon completion allow us to idle the HW. We may process the completion of the heartbeat, and begin parking the engine before the CS event that restores the queuepriorityhint, causing us to fail the assertion that it is MIN.

<3>[ 166.210729] __enginepark:283 GEMBUGON(engine->schedengine->queuepriorityhint != (-((int)(~0U >> 1)) - 1)) <0>[ 166.210781] Dumping ftrace buffer: <0>[ 166.210795] --------------------------------- ... <0>[ 167.302811] drmfdin-1097 2..s1. 165741070us : traceports: 0000:00:02.0 rcs0: promote { ccid:20 1217:2 prio 0 } <0>[ 167.302861] drmfdin-1097 2d.s2. 165741072us : execlistssubmissiontasklet: 0000:00:02.0 rcs0: preempting last=1217:2, prio=0, hint=2147483646 <0>[ 167.302928] drmfdin-1097 2d.s2. 165741072us : __i915requestunsubmit: 0000:00:02.0 rcs0: fence 1217:2, current 0 <0>[ 167.302992] drm_fdin-1097 2d.s2. 165741073us : __i915requestsubmit: 0000:00:02.0 rcs0: fence 3:4660, current 4659 <0>[ 167.303044] drmfdin-1097 2d.s1. 165741076us : execlistssubmissiontasklet: 0000:00:02.0 rcs0: context:3 schedule-in, ccid:40 <0>[ 167.303095] drmfdin-1097 2d.s1. 165741077us : traceports: 0000:00:02.0 rcs0: submit { ccid:40 3:4660* prio 2147483646 } <0>[ 167.303159] kworker/-89 11..... 165741139us : i915request_retire.part.0: 0000:00:02.0 rcs0: fence c90:2, current 2 <0>[ 167.303208] kworker/-89 11..... 165741148us : __intelcontextdounpin: 0000:00:02.0 rcs0: context:c90 unpin <0>[ 167.303272] kworker/-89 11..... 165741159us : i915request_retire.part.0: 0000:00:02.0 rcs0: fence 1217:2, current 2 <0>[ 167.303321] kworker/-89 11..... 165741166us : __intelcontextdounpin: 0000:00:02.0 rcs0: context:1217 unpin <0>[ 167.303384] kworker/-89 11..... 165741170us : i915request_retire.part.0: 0000:00:02.0 rcs0: fence 3:4660, current 4660 <0>[ 167.303434] kworker/-89 11d..1. 165741172us : __intelcontextretire: 0000:00:02.0 rcs0: context:1216 retire runtime: { total:56028ns, avg:56028ns } <0>[ 167.303484] kworker/-89 11..... 165741198us : __enginepark: 0000:00:02.0 rcs0: parked <0>[ 167.303534] <idle>-0 5d.H3. 165741207us : execlistsirq_handler: 0000:00:02.0 rcs0: semaphore yield: 00000040 <0>[ 167.303583] kworker/-89 11..... 165741397us : __intelcontextretire: 0000:00:02.0 rcs0: context:1217 retire runtime: { total:325575ns, avg:0ns } <0>[ 167.303756] kworker/-89 11..... 165741777us : __intelcontextretire: 0000:00:02.0 rcs0: context:c90 retire runtime: { total:0ns, avg:0ns } <0>[ 167.303806] kworker/-89 11..... 165742017us : __engine_park: __enginepark:283 GEMBUGON(engine->schedengine->queuepriorityhint != (-((int)(~0U >> 1)) - 1)) <0>[ 167.303811] --------------------------------- <4>[ 167.304722] ------------[ cut here ]------------ <2>[ 167.304725] kernel BUG at drivers/gpu/drm/i915/gt/intelenginepm.c:283! <4>[ 167.304731] invalid opcode: 0000 [#1] PREEMPT SMP NOPTI <4>[ 167.304734] CPU: 11 PID: 89 Comm: kworker/11:1 Tainted: G W 6.8.0-rc2-CIDRM14193-gc655e0fd2804+ #1 <4>[ 167.304736] Hardware name: Intel Corporation Rocket Lake Client Platform/RocketLake S UDIMM 6L RVP, BIOS RKLSFWI1.R00.3173.A03.2204210138 04/21/2022 <4>[ 167.304738] Workqueue: i915-unordered retireworkhandler [i915] <4>[ 16 ---truncated---