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 4D1F1C4167B for ; Tue, 7 Nov 2023 05:26:14 +0000 (UTC) Received: from gabe.freedesktop.org (localhost [127.0.0.1]) by gabe.freedesktop.org (Postfix) with ESMTP id 022FE10E4B4; Tue, 7 Nov 2023 05:26:14 +0000 (UTC) Received: from mgamail.intel.com (mgamail.intel.com [192.55.52.136]) by gabe.freedesktop.org (Postfix) with ESMTPS id 9B06710E4B5 for ; Tue, 7 Nov 2023 05:25:57 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=intel.com; i=@intel.com; q=dns/txt; s=Intel; t=1699334757; x=1730870757; h=from:to:cc:subject:date:message-id:in-reply-to: references:mime-version:content-transfer-encoding; bh=SjflOPRtcHq9R4lYTrNNUzBOFg7PJ7/Dt+Pn8Y3d0Cg=; b=V1ldK4Eh9fPwAQ95jiCAF19RyIi6p6zXHmV0ZuPakT4hJ5PEDLudQf7+ HHgv1moCSdtcyJFy/Vt0H1ZGb3mhF/LPCzDSrfJrth5uR6RUyYT2TOiIo i1t9/oljsFSIkneDPwiwCHWU9/6yeaeADf4KkJ7ZipSAtFx7dp+Ez7hMn 2F/3Lv2VA2D/rveX3/Oi0LFIaQwlPWaKVkXHnnjselJXCpscvIuLDEyxc J5UMoaHF6fKD6uYPzb2V2Pme98TeQzxVG86cWbKl48aHbqsk0r+PIykEK QC+irMA8yTqT6/x096CdZH//tFtXsbL+5KJD3Fh/p083m+JAxCqZYCGr9 Q==; X-IronPort-AV: E=McAfee;i="6600,9927,10886"; a="368769527" X-IronPort-AV: E=Sophos;i="6.03,282,1694761200"; d="scan'208";a="368769527" Received: from orsmga008.jf.intel.com ([10.7.209.65]) by fmsmga106.fm.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 06 Nov 2023 21:25:57 -0800 X-ExtLoop1: 1 X-IronPort-AV: E=McAfee;i="6600,9927,10886"; a="791689860" X-IronPort-AV: E=Sophos;i="6.03,282,1694761200"; d="scan'208";a="791689860" Received: from lstrano-desk.jf.intel.com ([10.54.39.91]) by orsmga008-auth.jf.intel.com with ESMTP/TLS/ECDHE-RSA-AES256-GCM-SHA384; 06 Nov 2023 21:25:55 -0800 From: Matthew Brost To: Date: Mon, 6 Nov 2023 21:25:51 -0800 Message-Id: <20231107052603.124361-16-matthew.brost@intel.com> X-Mailer: git-send-email 2.34.1 In-Reply-To: <20231107052603.124361-1-matthew.brost@intel.com> References: <20231107052603.124361-1-matthew.brost@intel.com> MIME-Version: 1.0 Content-Transfer-Encoding: 8bit Subject: [Intel-xe] [PATCH v2 15/27] drm/xe: Add xe_vm_pgtable_update_op to xe_vma_ops 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" Will help with the converstion to 1 job per VM bind IOCTL. Allocation only implemented in this patch. Signed-off-by: Matthew Brost --- drivers/gpu/drm/xe/xe_pt_types.h | 12 ++++++ drivers/gpu/drm/xe/xe_vm.c | 64 ++++++++++++++++++++++++++++++-- drivers/gpu/drm/xe/xe_vm_types.h | 8 ++++ 3 files changed, 80 insertions(+), 4 deletions(-) diff --git a/drivers/gpu/drm/xe/xe_pt_types.h b/drivers/gpu/drm/xe/xe_pt_types.h index 82cbf1ef8e57..33b2df72aad7 100644 --- a/drivers/gpu/drm/xe/xe_pt_types.h +++ b/drivers/gpu/drm/xe/xe_pt_types.h @@ -73,4 +73,16 @@ struct xe_vm_pgtable_update { u32 flags; }; +/** struct xe_vm_pgtable_update_op - Page table update operation */ +struct xe_vm_pgtable_update_op { + /** @entries: entries to update for this operation */ + struct xe_vm_pgtable_update entries[XE_VM_MAX_LEVEL * 2 + 1]; + /** @num_entries: number of entries for this update operation */ + u32 num_entries; + /** @bind: is a bind */ + bool bind; + /** @rebind: is a rebind */ + bool rebind; +}; + #endif diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c index f708c08633a7..7ae12e4441b0 100644 --- a/drivers/gpu/drm/xe/xe_vm.c +++ b/drivers/gpu/drm/xe/xe_vm.c @@ -1356,6 +1356,42 @@ static void xe_vma_ops_init(struct xe_vma_ops *vops, struct xe_vm *vm, vops->num_syncs = num_syncs; } +static int xe_vma_ops_alloc(struct xe_vma_ops *vops) +{ + int i; + + for (i = 0; i < XE_MAX_TILES_PER_DEVICE; ++i) { + if (!vops->pt_update_ops[i].num_ops) + continue; + + vops->pt_update_ops[i].ops = + kmalloc_array(vops->pt_update_ops[i].num_ops, + sizeof(*vops->pt_update_ops[i].ops), + GFP_KERNEL); + if (!vops->pt_update_ops[i].ops) + return -ENOMEM; + } + + return 0; +} + +static void xe_vma_ops_fini(struct xe_vma_ops *vops) +{ + int i; + + for (i = 0; i < XE_MAX_TILES_PER_DEVICE; ++i) + kfree(vops->pt_update_ops[i].ops); +} + +static void xe_vma_ops_incr_pt_update_ops(struct xe_vma_ops *vops, u8 tile_mask) +{ + int i; + + for (i = 0; i < XE_MAX_TILES_PER_DEVICE; ++i) + if (BIT(i) & tile_mask) + ++vops->pt_update_ops[i].num_ops; +} + struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags) { struct xe_vm *vm; @@ -1380,6 +1416,11 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags) xe_vma_ops_init(&vm->dummy_ops.vops, vm, NULL, NULL, 0); INIT_LIST_HEAD(&vm->dummy_ops.op.link); list_add(&vm->dummy_ops.op.link, &vm->dummy_ops.vops.list); + for (i = 0; i < XE_MAX_TILES_PER_DEVICE; ++i) + vm->dummy_ops.vops.pt_update_ops[i].num_ops = 1; + err = xe_vma_ops_alloc(&vm->dummy_ops.vops); + if (err) + goto err_free; INIT_LIST_HEAD(&vm->rebind_list); @@ -1517,12 +1558,14 @@ struct xe_vm *xe_vm_create(struct xe_device *xe, u32 flags) dma_resv_unlock(&vm->resv); drm_gpuvm_destroy(&vm->gpuvm); err_put: + if (!(flags & XE_VM_FLAG_MIGRATION)) + xe_device_mem_access_put(xe); dma_resv_fini(&vm->resv); for_each_tile(tile, xe, id) xe_range_fence_tree_fini(&vm->rftree[id]); +err_free: + xe_vma_ops_fini(&vm->dummy_ops.vops); kfree(vm); - if (!(flags & XE_VM_FLAG_MIGRATION)) - xe_device_mem_access_put(xe); return ERR_PTR(err); } @@ -1676,6 +1719,7 @@ static void vm_destroy_work_func(struct work_struct *w) trace_xe_vm_free(vm); dma_fence_put(vm->rebind_fence); dma_resv_fini(&vm->resv); + xe_vma_ops_fini(&vm->dummy_ops.vops); kfree(vm); } @@ -2360,7 +2404,6 @@ static int xe_vma_op_commit(struct xe_vm *vm, struct xe_vma_op *op) return err; } - static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct xe_exec_queue *q, struct drm_gpuva_ops *ops, struct xe_sync_entry *syncs, u32 num_syncs, @@ -2400,6 +2443,9 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct xe_exec_queue *q, return PTR_ERR(vma); op->map.vma = vma; + if (op->map.immediate || !xe_vm_in_fault_mode(vm)) + xe_vma_ops_incr_pt_update_ops(vops, + op->tile_mask); break; } case DRM_GPUVA_OP_REMAP: @@ -2440,6 +2486,8 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct xe_exec_queue *q, xe_vma_end(vma) - xe_vma_start(old); op->remap.start = xe_vma_end(vma); + } else { + xe_vma_ops_incr_pt_update_ops(vops, op->tile_mask); } } @@ -2473,13 +2521,16 @@ static int vm_bind_ioctl_ops_parse(struct xe_vm *vm, struct xe_exec_queue *q, op->remap.range -= xe_vma_end(old) - xe_vma_start(vma); + } else { + xe_vma_ops_incr_pt_update_ops(vops, op->tile_mask); } } + xe_vma_ops_incr_pt_update_ops(vops, op->tile_mask); break; } case DRM_GPUVA_OP_UNMAP: case DRM_GPUVA_OP_PREFETCH: - /* Nothing to do */ + xe_vma_ops_incr_pt_update_ops(vops, op->tile_mask); break; default: drm_warn(&vm->xe->drm, "NOT POSSIBLE"); @@ -3186,11 +3237,16 @@ int xe_vm_bind_ioctl(struct drm_device *dev, void *data, struct drm_file *file) goto unwind_ops; } + err = xe_vma_ops_alloc(&vops); + if (err) + goto unwind_ops; + err = vm_bind_ioctl_ops_execute(vm, &vops); unwind_ops: if (err && err != -ENODATA) vm_bind_ioctl_ops_unwind(vm, ops, args->num_binds); + xe_vma_ops_fini(&vops); for (i = args->num_binds - 1; i >= 0; --i) if (ops[i]) drm_gpuva_ops_free(&vm->gpuvm, ops[i]); diff --git a/drivers/gpu/drm/xe/xe_vm_types.h b/drivers/gpu/drm/xe/xe_vm_types.h index df85975b43fb..aa72330f824f 100644 --- a/drivers/gpu/drm/xe/xe_vm_types.h +++ b/drivers/gpu/drm/xe/xe_vm_types.h @@ -21,6 +21,7 @@ struct xe_bo; struct xe_device; struct xe_sync_entry; struct xe_vm; +struct xe_vm_pgtable_update_op; #define TEST_VM_ASYNC_OPS_ERROR #define FORCE_ASYNC_OP_ERROR BIT(31) @@ -227,6 +228,13 @@ struct xe_vma_ops { struct xe_sync_entry *syncs; /** @num_syncs: number of syncs */ u32 num_syncs; + /** @pt_update_ops: page table update operations */ + struct { + /** @ops: operations */ + struct xe_vm_pgtable_update_op *ops; + /** @num_ops: number of operations */ + u32 num_ops; + } pt_update_ops[XE_MAX_TILES_PER_DEVICE]; }; #define xe_vm_assert_held(vm) dma_resv_assert_held(&(vm)->resv) -- 2.34.1