From: Tomasz Lis Date: Sat, 2 Aug 2025 03:10:40 +0000 (+0200) Subject: drm/xe: Block reset while recovering from VF migration X-Git-Tag: v6.18-rc1~134^2~18^2~115 X-Git-Url: http://git.ipfire.org/gitweb.cgi?a=commitdiff_plain;h=a0840b1ce95e37a1a870a3e794ed25c69080cecf;p=thirdparty%2Flinux.git drm/xe: Block reset while recovering from VF migration Resetting GuC during recovery could interfere with the recovery process. Such reset might be also triggered without justification, due to migration taking time, rather than due to the workload not progressing. Doing GuC reset during the recovery would cause exit of RESFIX state, and therefore continuation of GuC work while fixups are still being applied. To avoid that, reset needs to be blocked during the recovery. This patch blocks the reset during recovery. Reset request in that time range will be stalled, and unblocked only after GuC goes out of RESFIX state. In case a reset procedure already started while the recovery is triggered, there isn't much we can do - we cannot wait for it to finish as it involves waiting for hardware, and we can't be sure at which exact point of the reset procedure the GPU got switched. Therefore, the rare cases where migration happens while reset is in progress, are still dangerous. Resets are not a part of the standard flow, and cause unfinished workloads - that will happen during the reset interrupted by migration as well, so it doesn't diverge that much from what normally happens during such resets. v2: Introduce a new atomic for reset blocking, as we cannot reuse `stopped` atomic (that could lead to losing a workload). v3: Switched atomic functs to ones which include proper barriers Signed-off-by: Tomasz Lis Cc: Michal Wajdeczko Cc: Michal Winiarski Reviewed-by: Michal Winiarski Link: https://lore.kernel.org/r/20250802031045.1127138-4-tomasz.lis@intel.com Signed-off-by: Michał Winiarski --- diff --git a/drivers/gpu/drm/xe/xe_gt.c b/drivers/gpu/drm/xe/xe_gt.c index 5a79c6e3208b4..390394bbaadcb 100644 --- a/drivers/gpu/drm/xe/xe_gt.c +++ b/drivers/gpu/drm/xe/xe_gt.c @@ -41,6 +41,7 @@ #include "xe_gt_topology.h" #include "xe_guc_exec_queue_types.h" #include "xe_guc_pc.h" +#include "xe_guc_submit.h" #include "xe_hw_fence.h" #include "xe_hw_engine_class_sysfs.h" #include "xe_irq.h" @@ -802,6 +803,11 @@ static int do_gt_restart(struct xe_gt *gt) return 0; } +static int gt_wait_reset_unblock(struct xe_gt *gt) +{ + return xe_guc_wait_reset_unblock(>->uc.guc); +} + static int gt_reset(struct xe_gt *gt) { unsigned int fw_ref; @@ -816,6 +822,10 @@ static int gt_reset(struct xe_gt *gt) xe_gt_info(gt, "reset started\n"); + err = gt_wait_reset_unblock(gt); + if (!err) + xe_gt_warn(gt, "reset block failed to get lifted"); + xe_pm_runtime_get(gt_to_xe(gt)); if (xe_fault_inject_gt_reset()) { diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c index ebc137be4de20..3274048e6a389 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.c +++ b/drivers/gpu/drm/xe/xe_guc_submit.c @@ -1783,6 +1783,43 @@ static void guc_exec_queue_stop(struct xe_guc *guc, struct xe_exec_queue *q) } } +/** + * xe_guc_submit_reset_block - Disallow reset calls on given GuC. + * @guc: the &xe_guc struct instance + */ +int xe_guc_submit_reset_block(struct xe_guc *guc) +{ + return atomic_fetch_or(1, &guc->submission_state.reset_blocked); +} + +/** + * xe_guc_submit_reset_unblock - Allow back reset calls on given GuC. + * @guc: the &xe_guc struct instance + */ +void xe_guc_submit_reset_unblock(struct xe_guc *guc) +{ + atomic_set_release(&guc->submission_state.reset_blocked, 0); + wake_up_all(&guc->ct.wq); +} + +static int guc_submit_reset_is_blocked(struct xe_guc *guc) +{ + return atomic_read_acquire(&guc->submission_state.reset_blocked); +} + +/* Maximum time of blocking reset */ +#define RESET_BLOCK_PERIOD_MAX (HZ * 5) + +/** + * xe_guc_wait_reset_unblock - Wait until reset blocking flag is lifted, or timeout. + * @guc: the &xe_guc struct instance + */ +int xe_guc_wait_reset_unblock(struct xe_guc *guc) +{ + return wait_event_timeout(guc->ct.wq, + !guc_submit_reset_is_blocked(guc), RESET_BLOCK_PERIOD_MAX); +} + int xe_guc_submit_reset_prepare(struct xe_guc *guc) { int ret; diff --git a/drivers/gpu/drm/xe/xe_guc_submit.h b/drivers/gpu/drm/xe/xe_guc_submit.h index ff44500f3da2f..4dd278f5f61b4 100644 --- a/drivers/gpu/drm/xe/xe_guc_submit.h +++ b/drivers/gpu/drm/xe/xe_guc_submit.h @@ -20,6 +20,9 @@ void xe_guc_submit_stop(struct xe_guc *guc); int xe_guc_submit_start(struct xe_guc *guc); void xe_guc_submit_pause(struct xe_guc *guc); void xe_guc_submit_unpause(struct xe_guc *guc); +int xe_guc_submit_reset_block(struct xe_guc *guc); +void xe_guc_submit_reset_unblock(struct xe_guc *guc); +int xe_guc_wait_reset_unblock(struct xe_guc *guc); void xe_guc_submit_wedge(struct xe_guc *guc); int xe_guc_read_stopped(struct xe_guc *guc); diff --git a/drivers/gpu/drm/xe/xe_guc_types.h b/drivers/gpu/drm/xe/xe_guc_types.h index 1fde7614fcc52..c7b9642b41ba7 100644 --- a/drivers/gpu/drm/xe/xe_guc_types.h +++ b/drivers/gpu/drm/xe/xe_guc_types.h @@ -85,6 +85,12 @@ struct xe_guc { struct xarray exec_queue_lookup; /** @submission_state.stopped: submissions are stopped */ atomic_t stopped; + /** + * @submission_state.reset_blocked: reset attempts are blocked; + * blocking reset in order to delay it may be required if running + * an operation which is sensitive to resets. + */ + atomic_t reset_blocked; /** @submission_state.lock: protects submission state */ struct mutex lock; /** @submission_state.enabled: submission is enabled */ diff --git a/drivers/gpu/drm/xe/xe_sriov_vf.c b/drivers/gpu/drm/xe/xe_sriov_vf.c index c66b17da1ce7a..71d28b30de432 100644 --- a/drivers/gpu/drm/xe/xe_sriov_vf.c +++ b/drivers/gpu/drm/xe/xe_sriov_vf.c @@ -163,9 +163,15 @@ static void vf_post_migration_shutdown(struct xe_device *xe) { struct xe_gt *gt; unsigned int id; + int ret = 0; - for_each_gt(gt, xe, id) + for_each_gt(gt, xe, id) { xe_guc_submit_pause(>->uc.guc); + ret |= xe_guc_submit_reset_block(>->uc.guc); + } + + if (ret) + drm_info(&xe->drm, "migration recovery encountered ongoing reset\n"); } /** @@ -187,8 +193,10 @@ static void vf_post_migration_kickstart(struct xe_device *xe) */ xe_irq_resume(xe); - for_each_gt(gt, xe, id) + for_each_gt(gt, xe, id) { + xe_guc_submit_reset_unblock(>->uc.guc); xe_guc_submit_unpause(>->uc.guc); + } } static bool gt_vf_post_migration_needed(struct xe_gt *gt)