From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from gabe.freedesktop.org (gabe.freedesktop.org [131.252.210.177]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.lore.kernel.org (Postfix) with ESMTPS id 39E18CF9C72 for ; Tue, 24 Sep 2024 20:26:01 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id F23EE10E741; Tue, 24 Sep 2024 20:26:00 +0000 (UTC) Authentication-Results: gabe.freedesktop.org; dkim=pass (2048-bit key; unprotected) header.d=intel.com header.i=@intel.com header.b="VYCsCNlM"; dkim-atps=neutral Received: from mgamail.intel.com (mgamail.intel.com [192.198.163.7]) by gabe.freedesktop.org (Postfix) with ESMTPS id 0BEEA10E27B for ; Tue, 24 Sep 2024 20:25:57 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1727209557; x=1758745557; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=0O/513QAlC1Q4RhTKy39MNuDR/N7rcQpoYRDkEziemw=; b=VYCsCNlMpISY3bIOR3CgRnsKEj4L8IHxfh4256VB0DVQICCACoUBpL6m NN0KcYR5/pJlyoi2HITnk1I+D1S2dqrMazZOGoCZxUyt92JobGcsmdUJA FWmNYMQCpruRqvujFWepH7FaOq2CXdzsITZn0u3Ck53ZDYgGqKZzsL9NI kzlsHXOkoRhK2TrsgESVnPlkLmeQaRe4D09Klh34wrRGBkVRBhqxLlvSH 1WAz5bLu0HtHLQXhEsejLjWy9L7V/FOX8rwpzFuPIa7kBvmgpmZssZnmu Zq3o+BAiF4ntqxbkehTInUBajPIzQ53U/MsZhUVcYG7ZRgsDyigYZGtPR w==; X-CSE-ConnectionGUID: MzLz3eqxS0+R8oKcei0Yug== X-CSE-MsgGUID: 1EqdcaCoSlqDwuU6iLqJMg== X-IronPort-AV: E=McAfee;i="6700,10204,11205"; a="51647409" X-IronPort-AV: E=Sophos;i="6.10,255,1719903600"; d="scan'208";a="51647409" Received: from orviesa003.jf.intel.com ([10.64.159.143]) by fmvoesa101.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 24 Sep 2024 13:25:57 -0700 X-CSE-ConnectionGUID: ZrosjuPZStK2Uu4I/r2Aag== X-CSE-MsgGUID: uk8jCMUETdWtio/Q8SOVFg== X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="6.10,255,1719903600"; d="scan'208";a="76335584" Received: from gkczarna.igk.intel.com ([10.102.139.130]) by orviesa003.jf.intel.com with ESMTP; 24 Sep 2024 13:25:55 -0700 From: Tomasz Lis To: intel-xe@lists.freedesktop.org Cc: =?UTF-8?q?Micha=C5=82=20Winiarski?= , =?UTF-8?q?Micha=C5=82=20Wajdeczko?= Subject: [PATCH v2 1/4] drm/xe/vf: React to MIGRATED interrupt Date: Tue, 24 Sep 2024 22:25:50 +0200 Message-Id: <20240924202553.1541574-2-tomasz.lis@intel.com> X-Mailer: git-send-email 2.25.1 In-Reply-To: <20240924202553.1541574-1-tomasz.lis@intel.com> References: <20240924202553.1541574-1-tomasz.lis@intel.com> MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit X-BeenThere: intel-xe@lists.freedesktop.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: Intel Xe graphics driver List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: intel-xe-bounces@lists.freedesktop.org Sender: "Intel-xe" To properly support VF Save/Restore procedure, fixups need to be applied after PF driver finishes its part of VF Restore. Those fixups are applied by the VF driver within a VM. A VF driver gets informed that it was migrated by receiving an interrupt from each GuC. That should be the trigger for fixups. The VF can safely do post-migration fixups on resources associated to each GuC only after that GuC issued the MIGRATED interrupt. This change introduces a worker to be used for post-migration fixups, and a mechanism to schedule said worker when all GuCs sent the irq. v2: renamed and moved functions, updated logged messages, removed unused includes, used anon struct (mwajdeczko) Signed-off-by: Tomasz Lis --- drivers/gpu/drm/xe/Makefile | 1 + drivers/gpu/drm/xe/xe_device_types.h | 2 + drivers/gpu/drm/xe/xe_gt_sriov_vf.c | 11 +++++ drivers/gpu/drm/xe/xe_gt_sriov_vf.h | 2 + drivers/gpu/drm/xe/xe_guc.c | 11 +++++ drivers/gpu/drm/xe/xe_memirq.c | 3 ++ drivers/gpu/drm/xe/xe_sriov.c | 4 ++ drivers/gpu/drm/xe/xe_sriov_types.h | 10 ++++ drivers/gpu/drm/xe/xe_sriov_vf.c | 73 ++++++++++++++++++++++++++++ drivers/gpu/drm/xe/xe_sriov_vf.h | 14 ++++++ 10 files changed, 131 insertions(+) create mode 100644 drivers/gpu/drm/xe/xe_sriov_vf.c create mode 100644 drivers/gpu/drm/xe/xe_sriov_vf.h diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile index 8f1c5c329f79..1f07983bb865 100644 --- a/drivers/gpu/drm/xe/Makefile +++ b/drivers/gpu/drm/xe/Makefile @@ -123,6 +123,7 @@ xe-y += \ xe_gt_sriov_vf.o \ xe_guc_relay.o \ xe_memirq.o \ + xe_sriov_vf.o \ xe_sriov.o xe-$(CONFIG_PCI_IOV) += \ diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h index 484fb34dde98..07ff7554fc3e 100644 --- a/drivers/gpu/drm/xe/xe_device_types.h +++ b/drivers/gpu/drm/xe/xe_device_types.h @@ -374,6 +374,8 @@ struct xe_device { /** @sriov.pf: PF specific data */ struct xe_device_pf pf; + /** @sriov.vf: VF specific data */ + struct xe_device_vf vf; /** @sriov.wq: workqueue used by the virtualization workers */ struct workqueue_struct *wq; diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c index d3baba50f085..489ace57c2a1 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.c +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.c @@ -27,6 +27,7 @@ #include "xe_guc_relay.h" #include "xe_mmio.h" #include "xe_sriov.h" +#include "xe_sriov_vf.h" #include "xe_uc_fw.h" #include "xe_wopcm.h" @@ -692,6 +693,16 @@ int xe_gt_sriov_vf_connect(struct xe_gt *gt) return err; } +void xe_gt_sriov_vf_migrated_event_handler(struct xe_gt *gt) +{ + struct xe_device *xe = gt_to_xe(gt); + + set_bit(gt->info.id, &xe->sriov.vf.migration.gt_flags); + smp_mb__after_atomic(); + xe_gt_sriov_info(gt, "VF migration recovery ready\n"); + xe_sriov_vf_start_migration_recovery(xe); +} + static bool vf_is_negotiated(struct xe_gt *gt, u16 major, u16 minor) { xe_gt_assert(gt, IS_SRIOV_VF(gt_to_xe(gt))); diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_vf.h b/drivers/gpu/drm/xe/xe_gt_sriov_vf.h index e541ce57bec2..544e913b8465 100644 --- a/drivers/gpu/drm/xe/xe_gt_sriov_vf.h +++ b/drivers/gpu/drm/xe/xe_gt_sriov_vf.h @@ -18,6 +18,8 @@ int xe_gt_sriov_vf_connect(struct xe_gt *gt); int xe_gt_sriov_vf_query_runtime(struct xe_gt *gt); int xe_gt_sriov_vf_prepare_ggtt(struct xe_gt *gt); +void xe_gt_sriov_vf_migrated_event_handler(struct xe_gt *gt); + u32 xe_gt_sriov_vf_gmdid(struct xe_gt *gt); u16 xe_gt_sriov_vf_guc_ids(struct xe_gt *gt); u64 xe_gt_sriov_vf_lmem(struct xe_gt *gt); diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c index b6cd5e941f19..05aa93070e5a 100644 --- a/drivers/gpu/drm/xe/xe_guc.c +++ b/drivers/gpu/drm/xe/xe_guc.c @@ -1092,10 +1092,21 @@ int xe_guc_self_cfg64(struct xe_guc *guc, u16 key, u64 val) return guc_self_cfg(guc, key, 2, val); } +static void xe_guc_sw_0_irq_handler(struct xe_guc *guc) +{ + struct xe_gt *gt = guc_to_gt(guc); + + if (IS_SRIOV_VF(gt_to_xe(gt))) + xe_gt_sriov_vf_migrated_event_handler(gt); +} + void xe_guc_irq_handler(struct xe_guc *guc, const u16 iir) { if (iir & GUC_INTR_GUC2HOST) xe_guc_ct_irq_handler(&guc->ct); + + if (iir & GUC_INTR_SW_INT_0) + xe_guc_sw_0_irq_handler(guc); } void xe_guc_sanitize(struct xe_guc *guc) diff --git a/drivers/gpu/drm/xe/xe_memirq.c b/drivers/gpu/drm/xe/xe_memirq.c index 3f8d4ca64302..2d2f40378942 100644 --- a/drivers/gpu/drm/xe/xe_memirq.c +++ b/drivers/gpu/drm/xe/xe_memirq.c @@ -435,6 +435,9 @@ static void memirq_dispatch_guc(struct xe_memirq *memirq, struct iosys_map *stat if (memirq_received(memirq, status, ilog2(GUC_INTR_GUC2HOST), name)) xe_guc_irq_handler(guc, GUC_INTR_GUC2HOST); + + if (memirq_received(memirq, status, ilog2(GUC_INTR_SW_INT_0), name)) + xe_guc_irq_handler(guc, GUC_INTR_SW_INT_0); } /** diff --git a/drivers/gpu/drm/xe/xe_sriov.c b/drivers/gpu/drm/xe/xe_sriov.c index 69a066ef20c0..2f4c3ae24f6e 100644 --- a/drivers/gpu/drm/xe/xe_sriov.c +++ b/drivers/gpu/drm/xe/xe_sriov.c @@ -12,6 +12,7 @@ #include "xe_mmio.h" #include "xe_sriov.h" #include "xe_sriov_pf.h" +#include "xe_sriov_vf.h" /** * xe_sriov_mode_to_string - Convert enum value to string. @@ -112,6 +113,9 @@ int xe_sriov_init(struct xe_device *xe) return err; } + if (IS_SRIOV_VF(xe)) + xe_sriov_vf_init_early(xe); + xe_assert(xe, !xe->sriov.wq); xe->sriov.wq = alloc_workqueue("xe-sriov-wq", 0, 0); if (!xe->sriov.wq) diff --git a/drivers/gpu/drm/xe/xe_sriov_types.h b/drivers/gpu/drm/xe/xe_sriov_types.h index c7b7ad4af5c8..8c518e68d33a 100644 --- a/drivers/gpu/drm/xe/xe_sriov_types.h +++ b/drivers/gpu/drm/xe/xe_sriov_types.h @@ -56,4 +56,14 @@ struct xe_device_pf { struct mutex master_lock; }; +struct xe_device_vf { + /** @migration: VF Migration state data */ + struct { + /** @migration.worker: VF migration recovery worker */ + struct work_struct worker; + /** @migration.gt_flags: Per-GT request flags for VF migration recovery */ + unsigned long gt_flags; + } migration; +}; + #endif diff --git a/drivers/gpu/drm/xe/xe_sriov_vf.c b/drivers/gpu/drm/xe/xe_sriov_vf.c new file mode 100644 index 000000000000..0e332bb215fd --- /dev/null +++ b/drivers/gpu/drm/xe/xe_sriov_vf.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: MIT +/* + * Copyright © 2023-2024 Intel Corporation + */ + +#include + +#include "xe_assert.h" +#include "xe_device.h" +#include "xe_sriov.h" +#include "xe_sriov_vf.h" +#include "xe_sriov_printk.h" + +static void migration_worker_func(struct work_struct *w); + +/** + * xe_sriov_vf_init_early - Initialize SR-IOV VF specific data. + * @xe: the &xe_device to initialize + */ +void xe_sriov_vf_init_early(struct xe_device *xe) +{ + INIT_WORK(&xe->sriov.vf.migration.worker, migration_worker_func); +} + +static void vf_post_migration_recovery(struct xe_device *xe) +{ + drm_dbg(&xe->drm, "migration recovery in progress\n"); + /* FIXME: add the recovery steps */ + drm_notice(&xe->drm, "migration recovery ended\n"); +} + +static void migration_worker_func(struct work_struct *w) +{ + struct xe_device *xe = container_of(w, struct xe_device, + sriov.vf.migration.worker); + + vf_post_migration_recovery(xe); +} + +static bool vf_ready_to_recovery_on_all_tiles(struct xe_device *xe) +{ + struct xe_gt *gt; + unsigned int id; + + for_each_gt(gt, xe, id) { + if (!test_bit(id, &xe->sriov.vf.migration.gt_flags)) + return false; + } + return true; +} + +/** + * xe_sriov_vf_start_migration_recovery - Start VF migration recovery. + * @xe: the &xe_device to start recovery on + * + * This function shall be called only by VF. + */ +void xe_sriov_vf_start_migration_recovery(struct xe_device *xe) +{ + bool started; + + xe_assert(xe, IS_SRIOV_VF(xe)); + + if (!vf_ready_to_recovery_on_all_tiles(xe)) + return; + + WRITE_ONCE(xe->sriov.vf.migration.gt_flags, 0); + smp_mb(); + + started = queue_work(xe->sriov.wq, &xe->sriov.vf.migration.worker); + drm_info(&xe->drm, "VF migration recovery %s\n", started ? + "scheduled" : "already in progress"); +} diff --git a/drivers/gpu/drm/xe/xe_sriov_vf.h b/drivers/gpu/drm/xe/xe_sriov_vf.h new file mode 100644 index 000000000000..7b8622cff2b7 --- /dev/null +++ b/drivers/gpu/drm/xe/xe_sriov_vf.h @@ -0,0 +1,14 @@ +/* SPDX-License-Identifier: MIT */ +/* + * Copyright © 2023-2024 Intel Corporation + */ + +#ifndef _XE_SRIOV_VF_H_ +#define _XE_SRIOV_VF_H_ + +struct xe_device; + +void xe_sriov_vf_init_early(struct xe_device *xe); +void xe_sriov_vf_start_migration_recovery(struct xe_device *xe); + +#endif -- 2.25.1