From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 47CFCC43217 for ; Sat, 5 Feb 2022 02:34:31 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1379040AbiBECe3 (ORCPT ); Fri, 4 Feb 2022 21:34:29 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45076 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1378991AbiBECeX (ORCPT ); Fri, 4 Feb 2022 21:34:23 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id 62F3420B6C63; Fri, 4 Feb 2022 18:34:23 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com 62F3420B6C63 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028463; bh=IpToOsqqxItEXz6optBBDvTXH5uaCmT+csRrvNEfkko=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=DuXCVfRjs5G0mm9qG2jnnIL0pgjaISOUxTetNFsIrUNvFsnNv9zV0bUIo8uRXqW4p eff+TUWvcMAH1v3HJfYE+np2V9J/66FqYbC16bLjVA9jzGFj4rW1Tn+NLT9hJ/HKds 8NmrdkAOIpicEHmIzf5j+INgHYQsPrYDNzbHt88I= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 01/24] drivers: hv: dxgkrnl: Driver initialization and creation of dxgadapter Date: Fri, 4 Feb 2022 18:33:59 -0800 Message-Id: <98fe53740526526c4df85a3a3d2e13e88c95f229.1644025661.git.iourit@linux.microsoft.com> X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" This is the first commit for adding support for a Hyper-V based vGPU implementation that exposes the DirectX API to Linux userspace. - Handle driver loading, registration for the PCI and VM bus device notifications - Add headers for user mode interfaces, internal driver objects and VM bus communication interface - Handle initialization of VM bus channels and creation of the dxgadapter object - Connect the dxgkrnl module to the drivers/hv/ makefile and Kconfig. - Create a MAINTAINERS entry A PCI device is created for each virtual GPU (vGPU) device, projected by the host. The device vendor is PCI_VENDOR_ID_MICROSOFT and device id is PCI_DEVICE_ID_VIRTUAL_RENDER. dxg_pci_probe_device handles arrival of such devices and it creates dxgadapter objects. The PCI config space of the vGPU device has luid of the corresponding per GPU VM bus channel. This is how the adapters are linked to VM bus channels. A dxgadapter object represents a virtual GPU, projected to the VM by the host. This object can start functioning only when the global VM bus channel and the corresponding per vGPU VM bus channel are initialized in the guest. Notifications about arrival of vGPU PCI device and VM bus channels can happen in any order. Therefore, the initial dxgadapter object state is DXGADAPTER_STATE_WAITING_VMBUS. A list of VM bus channels and a list of dxgadapter objects are created. When dxgkrnl is notified about a VM bus channel arrival, if tries to start all adapters, which are not started yet. VM bus interface version is exchanged by reading/writing the PCI config space of the vGPU device. Signed-off-by: Iouri Tarassov Reported-by: kernel test robot --- MAINTAINERS | 7 + drivers/hv/Kconfig | 2 + drivers/hv/Makefile | 1 + drivers/hv/dxgkrnl/Kconfig | 26 + drivers/hv/dxgkrnl/Makefile | 5 + drivers/hv/dxgkrnl/dxgadapter.c | 172 +++ drivers/hv/dxgkrnl/dxgkrnl.h | 223 ++++ drivers/hv/dxgkrnl/dxgmodule.c | 736 ++++++++++++ drivers/hv/dxgkrnl/dxgprocess.c | 17 + drivers/hv/dxgkrnl/dxgvmbus.c | 578 +++++++++ drivers/hv/dxgkrnl/dxgvmbus.h | 855 ++++++++++++++ drivers/hv/dxgkrnl/hmgr.c | 23 + drivers/hv/dxgkrnl/hmgr.h | 75 ++ drivers/hv/dxgkrnl/ioctl.c | 24 + drivers/hv/dxgkrnl/misc.c | 37 + drivers/hv/dxgkrnl/misc.h | 89 ++ include/linux/hyperv.h | 16 + include/uapi/misc/d3dkmthk.h | 1945 +++++++++++++++++++++++++++++++ 18 files changed, 4831 insertions(+) create mode 100644 drivers/hv/dxgkrnl/Kconfig create mode 100644 drivers/hv/dxgkrnl/Makefile create mode 100644 drivers/hv/dxgkrnl/dxgadapter.c create mode 100644 drivers/hv/dxgkrnl/dxgkrnl.h create mode 100644 drivers/hv/dxgkrnl/dxgmodule.c create mode 100644 drivers/hv/dxgkrnl/dxgprocess.c create mode 100644 drivers/hv/dxgkrnl/dxgvmbus.c create mode 100644 drivers/hv/dxgkrnl/dxgvmbus.h create mode 100644 drivers/hv/dxgkrnl/hmgr.c create mode 100644 drivers/hv/dxgkrnl/hmgr.h create mode 100644 drivers/hv/dxgkrnl/ioctl.c create mode 100644 drivers/hv/dxgkrnl/misc.c create mode 100644 drivers/hv/dxgkrnl/misc.h create mode 100644 include/uapi/misc/d3dkmthk.h diff --git a/MAINTAINERS b/MAINTAINERS index a2bd991db512..5856e09d834c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8841,6 +8841,13 @@ F: Documentation/devicetree/bindings/mtd/ti,am654-hb= mc.yaml F: drivers/mtd/hyperbus/ F: include/linux/mtd/hyperbus.h =20 +Hyper-V vGPU DRIVER +M: Iouri Tarassov +L: linux-hyperv@vger.kernel.org +S: Supported +F: drivers/hv/dxgkrnl/ +F: include/uapi/misc/d3dkmthk.h + HYPERVISOR VIRTUAL CONSOLE DRIVER L: linuxppc-dev@lists.ozlabs.org S: Odd Fixes diff --git a/drivers/hv/Kconfig b/drivers/hv/Kconfig index dd12af20e467..7006f7b66200 100644 --- a/drivers/hv/Kconfig +++ b/drivers/hv/Kconfig @@ -29,4 +29,6 @@ config HYPERV_BALLOON help Select this option to enable Hyper-V Balloon driver. =20 +source "drivers/hv/dxgkrnl/Kconfig" + endmenu diff --git a/drivers/hv/Makefile b/drivers/hv/Makefile index d76df5c8c2a9..aa1cbdb5d0d2 100644 --- a/drivers/hv/Makefile +++ b/drivers/hv/Makefile @@ -2,6 +2,7 @@ obj-$(CONFIG_HYPERV) +=3D hv_vmbus.o obj-$(CONFIG_HYPERV_UTILS) +=3D hv_utils.o obj-$(CONFIG_HYPERV_BALLOON) +=3D hv_balloon.o +obj-$(CONFIG_DXGKRNL) +=3D dxgkrnl/ =20 CFLAGS_hv_trace.o =3D -I$(src) CFLAGS_hv_balloon.o =3D -I$(src) diff --git a/drivers/hv/dxgkrnl/Kconfig b/drivers/hv/dxgkrnl/Kconfig new file mode 100644 index 000000000000..22d0914d8f1e --- /dev/null +++ b/drivers/hv/dxgkrnl/Kconfig @@ -0,0 +1,26 @@ +# +# dxgkrnl configuration +# + +config DXGKRNL + tristate "Microsoft Paravirtualized GPU support" + depends on HYPERV + depends on 64BIT || COMPILE_TEST + help + This driver supports paravirtualized virtual compute devices, exposed + by Microsoft Hyper-V when Linux is running inside of a virtual machine + hosted by Windows. The virtual machines needs to be configured to use + host compute adapters. The driver name is dxgkrnl. + + An example of such virtual machine is a Windows Subsystem for + Linux container. When such container is instantiated, the Windows host + assigns compatible host GPU adapters to the container. The corresponding + virtual GPU devices appear on the PCI bus in the container. These + devices are enumerated and accessed by this driver. + + Communications with the driver are done by using the Microsoft libdxcore + library, which translates the D3DKMT interface + + to the driver IOCTLs. The virtual GPU devices are paravirtualized, + which means that access to the hardware is done in the host. The driver + communicates with the host using Hyper-V VM bus communication channels. diff --git a/drivers/hv/dxgkrnl/Makefile b/drivers/hv/dxgkrnl/Makefile new file mode 100644 index 000000000000..745c66bebe5d --- /dev/null +++ b/drivers/hv/dxgkrnl/Makefile @@ -0,0 +1,5 @@ +# SPDX-License-Identifier: GPL-2.0 +# Makefile for the Linux video drivers. + +obj-$(CONFIG_DXGKRNL) +=3D dxgkrnl.o +dxgkrnl-y :=3D dxgmodule.o hmgr.o misc.o dxgadapter.o ioctl.o dxgvmbus.o = dxgprocess.o diff --git a/drivers/hv/dxgkrnl/dxgadapter.c b/drivers/hv/dxgkrnl/dxgadapte= r.c new file mode 100644 index 000000000000..e0a6fea00bd5 --- /dev/null +++ b/drivers/hv/dxgkrnl/dxgadapter.c @@ -0,0 +1,172 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (c) 2019, Microsoft Corporation. + * + * Author: + * Iouri Tarassov + * + * Dxgkrnl Graphics Driver + * Implementation of dxgadapter and its objects + * + */ + +#include +#include +#include +#include + +#include "dxgkrnl.h" + +#undef pr_fmt +#define pr_fmt(fmt) "dxgk: " fmt + +int dxgadapter_set_vmbus(struct dxgadapter *adapter, struct hv_device *hde= v) +{ + int ret; + + guid_to_luid(&hdev->channel->offermsg.offer.if_instance, + &adapter->luid); + pr_debug("%s: %x:%x %p %pUb\n", + __func__, adapter->luid.b, adapter->luid.a, hdev->channel, + &hdev->channel->offermsg.offer.if_instance); + + ret =3D dxgvmbuschannel_init(&adapter->channel, hdev); + if (ret) + goto cleanup; + + adapter->channel.adapter =3D adapter; + adapter->hv_dev =3D hdev; + + ret =3D dxgvmb_send_open_adapter(adapter); + if (ret < 0) { + pr_err("dxgvmb_send_open_adapter failed: %d\n", ret); + goto cleanup; + } + + ret =3D dxgvmb_send_get_internal_adapter_info(adapter); + if (ret < 0) + pr_err("get_internal_adapter_info failed: %d", ret); + +cleanup: + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +void dxgadapter_start(struct dxgadapter *adapter) +{ + struct dxgvgpuchannel *ch =3D NULL; + struct dxgvgpuchannel *entry; + int ret; + + pr_debug("%s %x-%x", + __func__, adapter->luid.a, adapter->luid.b); + + /* Find the corresponding vGPU vm bus channel */ + list_for_each_entry(entry, &dxgglobal->vgpu_ch_list_head, + vgpu_ch_list_entry) { + if (memcmp(&adapter->luid, + &entry->adapter_luid, + sizeof(struct winluid)) =3D=3D 0) { + ch =3D entry; + break; + } + } + if (ch =3D=3D NULL) { + pr_debug("%s vGPU chanel is not ready", __func__); + return; + } + + /* The global channel is initialized when the first adapter starts */ + if (!dxgglobal->global_channel_initialized) { + ret =3D dxgglobal_init_global_channel(); + if (ret) { + dxgglobal_destroy_global_channel(); + return; + } + dxgglobal->global_channel_initialized =3D true; + } + + /* Initialize vGPU vm bus channel */ + ret =3D dxgadapter_set_vmbus(adapter, ch->hdev); + if (ret) { + pr_err("Failed to start adapter %p", adapter); + adapter->adapter_state =3D DXGADAPTER_STATE_STOPPED; + return; + } + + adapter->adapter_state =3D DXGADAPTER_STATE_ACTIVE; + pr_debug("%s Adapter started %p", __func__, adapter); +} + +void dxgadapter_stop(struct dxgadapter *adapter) +{ + bool adapter_stopped =3D false; + + down_write(&adapter->core_lock); + if (!adapter->stopping_adapter) + adapter->stopping_adapter =3D true; + else + adapter_stopped =3D true; + up_write(&adapter->core_lock); + + if (adapter_stopped) + return; + + if (dxgadapter_acquire_lock_exclusive(adapter) =3D=3D 0) { + dxgvmb_send_close_adapter(adapter); + dxgadapter_release_lock_exclusive(adapter); + } + dxgvmbuschannel_destroy(&adapter->channel); + + adapter->adapter_state =3D DXGADAPTER_STATE_STOPPED; +} + +void dxgadapter_release(struct kref *refcount) +{ + struct dxgadapter *adapter; + + adapter =3D container_of(refcount, struct dxgadapter, adapter_kref); + pr_debug("%s %p\n", __func__, adapter); + vfree(adapter); +} + +bool dxgadapter_is_active(struct dxgadapter *adapter) +{ + return adapter->adapter_state =3D=3D DXGADAPTER_STATE_ACTIVE; +} + +int dxgadapter_acquire_lock_exclusive(struct dxgadapter *adapter) +{ + down_write(&adapter->core_lock); + if (adapter->adapter_state !=3D DXGADAPTER_STATE_ACTIVE) { + dxgadapter_release_lock_exclusive(adapter); + return -ENODEV; + } + return 0; +} + +void dxgadapter_acquire_lock_forced(struct dxgadapter *adapter) +{ + down_write(&adapter->core_lock); +} + +void dxgadapter_release_lock_exclusive(struct dxgadapter *adapter) +{ + up_write(&adapter->core_lock); +} + +int dxgadapter_acquire_lock_shared(struct dxgadapter *adapter) +{ + down_read(&adapter->core_lock); + if (adapter->adapter_state =3D=3D DXGADAPTER_STATE_ACTIVE) + return 0; + dxgadapter_release_lock_shared(adapter); + return -ENODEV; +} + +void dxgadapter_release_lock_shared(struct dxgadapter *adapter) +{ + up_read(&adapter->core_lock); +} diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h new file mode 100644 index 000000000000..15208328cb71 --- /dev/null +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -0,0 +1,223 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Copyright (c) 2019, Microsoft Corporation. + * + * Author: + * Iouri Tarassov + * + * Dxgkrnl Graphics Driver + * Headers for internal objects + * + */ + +#ifndef _DXGKRNL_H +#define _DXGKRNL_H + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include + +struct dxgadapter; + +#include "misc.h" +#include "hmgr.h" +#include + +struct dxgk_device_types { + u32 post_device:1; + u32 post_device_certain:1; + u32 software_device:1; + u32 soft_gpu_device:1; + u32 warp_device:1; + u32 bdd_device:1; + u32 support_miracast:1; + u32 mismatched_lda:1; + u32 indirect_display_device:1; + u32 xbox_one_device:1; + u32 child_id_support_dwm_clone:1; + u32 child_id_support_dwm_clone2:1; + u32 has_internal_panel:1; + u32 rfx_vgpu_device:1; + u32 virtual_render_device:1; + u32 support_preserve_boot_display:1; + u32 is_uefi_frame_buffer:1; + u32 removable_device:1; + u32 virtual_monitor_device:1; +}; + +enum dxgobjectstate { + DXGOBJECTSTATE_CREATED, + DXGOBJECTSTATE_ACTIVE, + DXGOBJECTSTATE_STOPPED, + DXGOBJECTSTATE_DESTROYED, +}; + +struct dxgvmbuschannel { + struct vmbus_channel *channel; + struct hv_device *hdev; + struct dxgadapter *adapter; + spinlock_t packet_list_mutex; + struct list_head packet_list_head; + struct kmem_cache *packet_cache; + atomic64_t packet_request_id; +}; + +int dxgvmbuschannel_init(struct dxgvmbuschannel *ch, struct hv_device *hde= v); +void dxgvmbuschannel_destroy(struct dxgvmbuschannel *ch); +void dxgvmbuschannel_receive(void *ctx); + +/* + * The structure defines an offered vGPU vm bus channel. + */ +struct dxgvgpuchannel { + struct list_head vgpu_ch_list_entry; + struct winluid adapter_luid; + struct hv_device *hdev; +}; + +struct dxgglobal { + struct dxgvmbuschannel channel; + struct delayed_work dwork; + struct hv_device *hdev; + u32 num_adapters; + u32 vmbus_ver; /* Interface version */ + struct resource *mem; + u64 mmiospace_base; + u64 mmiospace_size; + struct miscdevice dxgdevice; + struct mutex device_mutex; + + /* list of created processes */ + struct list_head plisthead; + struct mutex plistmutex; + + /* list of created adapters */ + struct list_head adapter_list_head; + struct rw_semaphore adapter_list_lock; + + /* List of all current threads for lock order tracking. */ + struct mutex thread_info_mutex; + struct list_head thread_info_list_head; + + /* + * List of the vGPU VM bus channels (dxgvgpuchannel) + * Protected by device_mutex + */ + struct list_head vgpu_ch_list_head; + + /* protects acces to the global VM bus channel */ + struct rw_semaphore channel_lock; + + bool dxg_dev_initialized; + bool vmbus_registered; + bool pci_registered; + bool global_channel_initialized; + bool async_msg_enabled; +}; + +extern struct dxgglobal *dxgglobal; + +int dxgglobal_create_adapter(struct pci_dev *dev, guid_t *guid, + struct winluid host_vgpu_luid); +void dxgglobal_acquire_adapter_list_lock(enum dxglockstate state); +void dxgglobal_release_adapter_list_lock(enum dxglockstate state); +int dxgglobal_init_global_channel(void); +void dxgglobal_destroy_global_channel(void); +struct vmbus_channel *dxgglobal_get_vmbus(void); +struct dxgvmbuschannel *dxgglobal_get_dxgvmbuschannel(void); +int dxgglobal_acquire_channel_lock(void); +void dxgglobal_release_channel_lock(void); + +struct dxgprocess { + /* Placeholder */ +}; + +enum dxgadapter_state { + DXGADAPTER_STATE_ACTIVE =3D 0, + DXGADAPTER_STATE_STOPPED =3D 1, + DXGADAPTER_STATE_WAITING_VMBUS =3D 2, +}; + +/* + * This object represents the grapchis adapter. + * Objects, which take reference on the adapter: + * - dxgglobal + * - adapter handle (struct d3dkmthandle) + */ +struct dxgadapter { + struct rw_semaphore core_lock; + struct kref adapter_kref; + /* Entry in the list of adapters in dxgglobal */ + struct list_head adapter_list_entry; + struct pci_dev *pci_dev; + struct hv_device *hv_dev; + struct dxgvmbuschannel channel; + struct d3dkmthandle host_handle; + enum dxgadapter_state adapter_state; + struct winluid host_adapter_luid; + struct winluid host_vgpu_luid; + struct winluid luid; /* VM bus channel luid */ + u16 device_description[80]; + u16 device_instance_id[WIN_MAX_PATH]; + bool stopping_adapter; +}; + +int dxgadapter_set_vmbus(struct dxgadapter *adapter, struct hv_device *hde= v); +bool dxgadapter_is_active(struct dxgadapter *adapter); +void dxgadapter_start(struct dxgadapter *adapter); +void dxgadapter_stop(struct dxgadapter *adapter); +void dxgadapter_release(struct kref *refcount); +int dxgadapter_acquire_lock_shared(struct dxgadapter *adapter); +void dxgadapter_release_lock_shared(struct dxgadapter *adapter); +int dxgadapter_acquire_lock_exclusive(struct dxgadapter *adapter); +void dxgadapter_acquire_lock_forced(struct dxgadapter *adapter); +void dxgadapter_release_lock_exclusive(struct dxgadapter *adapter); + +void init_ioctls(void); +long dxgk_compat_ioctl(struct file *f, unsigned int p1, unsigned long p2); +long dxgk_unlocked_ioctl(struct file *f, unsigned int p1, unsigned long p2= ); + +static inline void guid_to_luid(guid_t *guid, struct winluid *luid) +{ + *luid =3D *(struct winluid *)&guid->b[0]; +} + +/* + * VM bus interface + * + */ + +/* + * The interface version is used to ensure that the host and the guest use= the + * same VM bus protocol. It needs to be incremented every time the VM bus + * interface changes. DXGK_VMBUS_LAST_COMPATIBLE_INTERFACE_VERSION is + * incremented each time the earlier versions of the interface are no long= er + * compatible with the current version. + */ +#define DXGK_VMBUS_INTERFACE_VERSION_OLD 27 +#define DXGK_VMBUS_INTERFACE_VERSION 40 +#define DXGK_VMBUS_LAST_COMPATIBLE_INTERFACE_VERSION 16 + +void dxgvmb_initialize(void); +int dxgvmb_send_set_iospace_region(u64 start, u64 len, + struct vmbus_gpadl *shared_mem_gpadl); +int dxgvmb_send_open_adapter(struct dxgadapter *adapter); +int dxgvmb_send_close_adapter(struct dxgadapter *adapter); +int dxgvmb_send_get_internal_adapter_info(struct dxgadapter *adapter); +int dxgvmb_send_async_msg(struct dxgvmbuschannel *channel, + void *command, + u32 cmd_size); + +int ntstatus2int(struct ntstatus status); + +#endif diff --git a/drivers/hv/dxgkrnl/dxgmodule.c b/drivers/hv/dxgkrnl/dxgmodule.c new file mode 100644 index 000000000000..a9a00dae2088 --- /dev/null +++ b/drivers/hv/dxgkrnl/dxgmodule.c @@ -0,0 +1,736 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (c) 2019, Microsoft Corporation. + * + * Author: + * Iouri Tarassov + * + * Dxgkrnl Graphics Driver + * Interface with Linux kernel, PCI driver and the VM bus driver + * + */ + +#include +#include +#include +#include + +#include "dxgkrnl.h" + +/* + * Pointer to the global device data. By design + * there is a single vGPU device on the VM bus and a single /dev/dxg device + * is created. + */ +struct dxgglobal *dxgglobal; + +#define DXGKRNL_VERSION 0x2111 +#define PCI_VENDOR_ID_MICROSOFT 0x1414 +#define PCI_DEVICE_ID_VIRTUAL_RENDER 0x008E + +#undef pr_fmt +#define pr_fmt(fmt) "dxgk: " fmt + +// +// Interface from dxgglobal +// + +struct vmbus_channel *dxgglobal_get_vmbus(void) +{ + return dxgglobal->channel.channel; +} + +struct dxgvmbuschannel *dxgglobal_get_dxgvmbuschannel(void) +{ + return &dxgglobal->channel; +} + +int dxgglobal_acquire_channel_lock(void) +{ + down_read(&dxgglobal->channel_lock); + if (dxgglobal->channel.channel =3D=3D NULL) { + pr_err("Failed to acquire global channel lock"); + return -ENODEV; + } else { + return 0; + } +} + +void dxgglobal_release_channel_lock(void) +{ + up_read(&dxgglobal->channel_lock); +} + +void dxgglobal_acquire_adapter_list_lock(enum dxglockstate state) +{ + if (state =3D=3D DXGLOCK_EXCL) + down_write(&dxgglobal->adapter_list_lock); + else + down_read(&dxgglobal->adapter_list_lock); +} + +void dxgglobal_release_adapter_list_lock(enum dxglockstate state) +{ + if (state =3D=3D DXGLOCK_EXCL) + up_write(&dxgglobal->adapter_list_lock); + else + up_read(&dxgglobal->adapter_list_lock); +} + +/* + * Returns a pointer to dxgadapter object, which corresponds to the given = PCI + * device, or NULL. + */ +static struct dxgadapter *find_pci_adapter(struct pci_dev *dev) +{ + struct dxgadapter *entry; + struct dxgadapter *adapter =3D NULL; + + dxgglobal_acquire_adapter_list_lock(DXGLOCK_EXCL); + + list_for_each_entry(entry, &dxgglobal->adapter_list_head, + adapter_list_entry) { + if (dev =3D=3D entry->pci_dev) { + adapter =3D entry; + break; + } + } + + dxgglobal_release_adapter_list_lock(DXGLOCK_EXCL); + return adapter; +} + +/* + * Returns a pointer to dxgadapter object, which has the givel LUID + * device, or NULL. + */ +static struct dxgadapter *find_adapter(struct winluid *luid) +{ + struct dxgadapter *entry; + struct dxgadapter *adapter =3D NULL; + + dxgglobal_acquire_adapter_list_lock(DXGLOCK_EXCL); + + list_for_each_entry(entry, &dxgglobal->adapter_list_head, + adapter_list_entry) { + if (memcmp(luid, &entry->luid, sizeof(struct winluid)) =3D=3D 0) { + adapter =3D entry; + break; + } + } + + dxgglobal_release_adapter_list_lock(DXGLOCK_EXCL); + return adapter; +} + +/* + * Creates a new dxgadapter object, which represents a virtual GPU, projec= ted + * by the host. + * The adapter is in the waiting state. It will become active when the glo= bal + * VM bus channel and the adapter VM bus channel are created. + */ +int dxgglobal_create_adapter(struct pci_dev *dev, guid_t *guid, + struct winluid host_vgpu_luid) +{ + struct dxgadapter *adapter; + int ret =3D 0; + + adapter =3D vzalloc(sizeof(struct dxgadapter)); + if (adapter =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + + adapter->adapter_state =3D DXGADAPTER_STATE_WAITING_VMBUS; + adapter->host_vgpu_luid =3D host_vgpu_luid; + kref_init(&adapter->adapter_kref); + init_rwsem(&adapter->core_lock); + + adapter->pci_dev =3D dev; + guid_to_luid(guid, &adapter->luid); + + dxgglobal_acquire_adapter_list_lock(DXGLOCK_EXCL); + + list_add_tail(&adapter->adapter_list_entry, + &dxgglobal->adapter_list_head); + dxgglobal->num_adapters++; + dxgglobal_release_adapter_list_lock(DXGLOCK_EXCL); + + pr_debug("new adapter added %p %x-%x\n", adapter, + adapter->luid.a, adapter->luid.b); +cleanup: + pr_debug("%s end: %d", __func__, ret); + return ret; +} + +/* + * Attempts to start dxgadapter objects, which are not active yet. + */ +static void dxgglobal_start_adapters(void) +{ + struct dxgadapter *adapter; + + if (dxgglobal->hdev =3D=3D NULL) { + pr_debug("Global channel is not ready"); + return; + } + dxgglobal_acquire_adapter_list_lock(DXGLOCK_EXCL); + list_for_each_entry(adapter, &dxgglobal->adapter_list_head, + adapter_list_entry) { + if (adapter->adapter_state =3D=3D DXGADAPTER_STATE_WAITING_VMBUS) + dxgadapter_start(adapter); + } + dxgglobal_release_adapter_list_lock(DXGLOCK_EXCL); +} + +/* + * Stopsthe active dxgadapter objects. + */ +static void dxgglobal_stop_adapters(void) +{ + struct dxgadapter *adapter; + + if (dxgglobal->hdev =3D=3D NULL) { + pr_debug("Global channel is not ready"); + return; + } + dxgglobal_acquire_adapter_list_lock(DXGLOCK_EXCL); + list_for_each_entry(adapter, &dxgglobal->adapter_list_head, + adapter_list_entry) { + if (adapter->adapter_state =3D=3D DXGADAPTER_STATE_ACTIVE) + dxgadapter_stop(adapter); + } + dxgglobal_release_adapter_list_lock(DXGLOCK_EXCL); +} + +/* + * File operations for the /dev/dxg device + */ + +static int dxgk_open(struct inode *n, struct file *f) +{ + return 0; +} + +static int dxgk_release(struct inode *n, struct file *f) +{ + return 0; +} + +static ssize_t dxgk_read(struct file *f, char __user *s, size_t len, + loff_t *o) +{ + pr_debug("file read\n"); + return 0; +} + +static ssize_t dxgk_write(struct file *f, const char __user *s, size_t len, + loff_t *o) +{ + pr_debug("file write\n"); + return len; +} + +const struct file_operations dxgk_fops =3D { + .owner =3D THIS_MODULE, + .open =3D dxgk_open, + .release =3D dxgk_release, + .write =3D dxgk_write, + .read =3D dxgk_read, +}; + +/* + * Interface with the PCI driver + */ + +/* + * Part of the PCI config space of the vGPU device is used for vGPU + * configuration data. Reading/writing of the PCI config space is forwarded + * to the host. + */ + +/* vGPU VM bus channel instance ID */ +#define DXGK_VMBUS_CHANNEL_ID_OFFSET 192 +/* DXGK_VMBUS_INTERFACE_VERSION (u32) */ +#define DXGK_VMBUS_VERSION_OFFSET (DXGK_VMBUS_CHANNEL_ID_OFFSET + \ + sizeof(guid_t)) +/* Luid of the virtual GPU on the host (struct winluid) */ +#define DXGK_VMBUS_VGPU_LUID_OFFSET (DXGK_VMBUS_VERSION_OFFSET + \ + sizeof(u32)) +/* The guest writes its capavilities to this adderss */ +#define DXGK_VMBUS_GUESTCAPS_OFFSET (DXGK_VMBUS_VERSION_OFFSET + \ + sizeof(u32)) + +/* Capabilities of the guest driver, reported to the host */ +struct dxgk_vmbus_guestcaps { + union { + struct { + u32 wsl2 : 1; + u32 reserved : 31; + }; + u32 guest_caps; + }; +}; + +/* + * A helper function to read PCI config space. + */ +static int dxg_pci_read_dwords(struct pci_dev *dev, int offset, int size, + void *val) +{ + int off =3D offset; + int ret; + int i; + + for (i =3D 0; i < size / sizeof(int); i++) { + ret =3D pci_read_config_dword(dev, off, &((int *)val)[i]); + if (ret) { + pr_err("Failed to read PCI config: %d", off); + return ret; + } + off +=3D sizeof(int); + } + return 0; +} + +static int dxg_pci_probe_device(struct pci_dev *dev, + const struct pci_device_id *id) +{ + int ret; + guid_t guid; + u32 vmbus_interface_ver =3D DXGK_VMBUS_INTERFACE_VERSION; + struct winluid vgpu_luid =3D {}; + struct dxgk_vmbus_guestcaps guest_caps =3D {.wsl2 =3D 1}; + + mutex_lock(&dxgglobal->device_mutex); + + if (dxgglobal->vmbus_ver =3D=3D 0) { + /* Report capabilities to the host */ + + ret =3D pci_write_config_dword(dev, DXGK_VMBUS_GUESTCAPS_OFFSET, + guest_caps.guest_caps); + if (ret) + goto cleanup; + + /* Negotiate the VM bus version */ + + ret =3D pci_read_config_dword(dev, DXGK_VMBUS_VERSION_OFFSET, + &vmbus_interface_ver); + if (ret =3D=3D 0 && vmbus_interface_ver !=3D 0) + dxgglobal->vmbus_ver =3D vmbus_interface_ver; + else + dxgglobal->vmbus_ver =3D DXGK_VMBUS_INTERFACE_VERSION_OLD; + + if (dxgglobal->vmbus_ver < DXGK_VMBUS_INTERFACE_VERSION) + goto read_channel_id; + + ret =3D pci_write_config_dword(dev, DXGK_VMBUS_VERSION_OFFSET, + DXGK_VMBUS_INTERFACE_VERSION); + if (ret) + goto cleanup; + + if (dxgglobal->vmbus_ver > DXGK_VMBUS_INTERFACE_VERSION) + dxgglobal->vmbus_ver =3D DXGK_VMBUS_INTERFACE_VERSION; + } + +read_channel_id: + + /* Get the VM bus channel ID for the virtual GPU */ + ret =3D dxg_pci_read_dwords(dev, DXGK_VMBUS_CHANNEL_ID_OFFSET, + sizeof(guid), (int *)&guid); + if (ret) + goto cleanup; + + if (dxgglobal->vmbus_ver >=3D DXGK_VMBUS_INTERFACE_VERSION) { + ret =3D dxg_pci_read_dwords(dev, DXGK_VMBUS_VGPU_LUID_OFFSET, + sizeof(vgpu_luid), &vgpu_luid); + if (ret) + goto cleanup; + } + + /* Create new virtual GPU adapter */ + + pr_debug("Adapter channel: %pUb\n", &guid); + pr_debug("Vmbus interface version: %d\n", + dxgglobal->vmbus_ver); + pr_debug("Host vGPU luid: %x-%x\n", + vgpu_luid.b, vgpu_luid.a); + + ret =3D dxgglobal_create_adapter(dev, &guid, vgpu_luid); + if (ret) + goto cleanup; + + /* Attempt to start the adapter in case VM bus channels are created */ + + dxgglobal_start_adapters(); + +cleanup: + + mutex_unlock(&dxgglobal->device_mutex); + + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +static void dxg_pci_remove_device(struct pci_dev *dev) +{ + struct dxgadapter *adapter; + + mutex_lock(&dxgglobal->device_mutex); + + adapter =3D find_pci_adapter(dev); + if (adapter) { + dxgglobal_acquire_adapter_list_lock(DXGLOCK_EXCL); + list_del(&adapter->adapter_list_entry); + dxgglobal->num_adapters--; + dxgglobal_release_adapter_list_lock(DXGLOCK_EXCL); + + dxgadapter_stop(adapter); + kref_put(&adapter->adapter_kref, dxgadapter_release); + } else { + pr_err("Failed to find dxgadapter"); + } + + mutex_unlock(&dxgglobal->device_mutex); +} + +static struct pci_device_id dxg_pci_id_table =3D { + .vendor =3D PCI_VENDOR_ID_MICROSOFT, + .device =3D PCI_DEVICE_ID_VIRTUAL_RENDER, + .subvendor =3D PCI_ANY_ID, + .subdevice =3D PCI_ANY_ID +}; + +static struct pci_driver dxg_pci_drv =3D { + .name =3D KBUILD_MODNAME, + .id_table =3D &dxg_pci_id_table, + .probe =3D dxg_pci_probe_device, + .remove =3D dxg_pci_remove_device +}; + +/* + * Interface with the VM bus driver + */ + +static int dxgglobal_getiospace(struct dxgglobal *dxgglobal) +{ + /* Get mmio space for the global channel */ + struct hv_device *hdev =3D dxgglobal->hdev; + struct vmbus_channel *channel =3D hdev->channel; + resource_size_t pot_start =3D 0; + resource_size_t pot_end =3D -1; + int ret; + + dxgglobal->mmiospace_size =3D channel->offermsg.offer.mmio_megabytes; + if (dxgglobal->mmiospace_size =3D=3D 0) { + pr_debug("zero mmio space is offered\n"); + return -ENOMEM; + } + dxgglobal->mmiospace_size <<=3D 20; + pr_debug("mmio offered: %llx\n", + dxgglobal->mmiospace_size); + + ret =3D vmbus_allocate_mmio(&dxgglobal->mem, hdev, pot_start, pot_end, + dxgglobal->mmiospace_size, 0x10000, false); + if (ret) { + pr_err("Unable to allocate mmio memory: %d\n", ret); + return ret; + } + dxgglobal->mmiospace_size =3D dxgglobal->mem->end - + dxgglobal->mem->start + 1; + dxgglobal->mmiospace_base =3D dxgglobal->mem->start; + pr_info("mmio allocated %llx %llx %llx %llx\n", + dxgglobal->mmiospace_base, + dxgglobal->mmiospace_size, + dxgglobal->mem->start, dxgglobal->mem->end); + + return 0; +} + +int dxgglobal_init_global_channel(void) +{ + int ret =3D 0; + + ret =3D dxgvmbuschannel_init(&dxgglobal->channel, dxgglobal->hdev); + if (ret) { + pr_err("dxgvmbuschannel_init failed: %d\n", ret); + goto error; + } + + ret =3D dxgglobal_getiospace(dxgglobal); + if (ret) { + pr_err("getiospace failed: %d\n", ret); + goto error; + } + + ret =3D dxgvmb_send_set_iospace_region(dxgglobal->mmiospace_base, + dxgglobal->mmiospace_size, 0); + if (ret < 0) { + pr_err("send_set_iospace_region failed"); + goto error; + } + + hv_set_drvdata(dxgglobal->hdev, dxgglobal); + + dxgglobal->dxgdevice.minor =3D MISC_DYNAMIC_MINOR; + dxgglobal->dxgdevice.name =3D "dxg"; + dxgglobal->dxgdevice.fops =3D &dxgk_fops; + dxgglobal->dxgdevice.mode =3D 0666; + ret =3D misc_register(&dxgglobal->dxgdevice); + if (ret) { + pr_err("misc_register failed: %d", ret); + goto error; + } + dxgglobal->dxg_dev_initialized =3D true; + +error: + return ret; +} + +void dxgglobal_destroy_global_channel(void) +{ + down_write(&dxgglobal->channel_lock); + + dxgglobal->global_channel_initialized =3D false; + + if (dxgglobal->dxg_dev_initialized) { + misc_deregister(&dxgglobal->dxgdevice); + dxgglobal->dxg_dev_initialized =3D false; + } + + if (dxgglobal->mem) { + vmbus_free_mmio(dxgglobal->mmiospace_base, + dxgglobal->mmiospace_size); + dxgglobal->mem =3D NULL; + } + + dxgvmbuschannel_destroy(&dxgglobal->channel); + + if (dxgglobal->hdev) { + hv_set_drvdata(dxgglobal->hdev, NULL); + dxgglobal->hdev =3D NULL; + } + + up_write(&dxgglobal->channel_lock); +} + +static void dxgglobal_stop_adapter_vmbus(struct hv_device *hdev) +{ + struct dxgadapter *adapter =3D NULL; + struct winluid luid; + + guid_to_luid(&hdev->channel->offermsg.offer.if_instance, &luid); + + pr_debug("%s: %x:%x\n", __func__, luid.b, luid.a); + + adapter =3D find_adapter(&luid); + + if (adapter && adapter->adapter_state =3D=3D DXGADAPTER_STATE_ACTIVE) { + down_write(&adapter->core_lock); + dxgvmbuschannel_destroy(&adapter->channel); + adapter->adapter_state =3D DXGADAPTER_STATE_STOPPED; + up_write(&adapter->core_lock); + } +} + +static const struct hv_vmbus_device_id id_table[] =3D { + /* Per GPU Device GUID */ + { HV_GPUP_DXGK_VGPU_GUID }, + /* Global Dxgkgnl channel for the virtual machine */ + { HV_GPUP_DXGK_GLOBAL_GUID }, + { } +}; + +static int dxg_probe_vmbus(struct hv_device *hdev, + const struct hv_vmbus_device_id *dev_id) +{ + int ret =3D 0; + struct winluid luid; + struct dxgvgpuchannel *vgpuch; + + mutex_lock(&dxgglobal->device_mutex); + + if (uuid_le_cmp(hdev->dev_type, id_table[0].guid) =3D=3D 0) { + /* This is a new virtual GPU channel */ + guid_to_luid(&hdev->channel->offermsg.offer.if_instance, &luid); + pr_debug("vGPU channel: %pUb", + &hdev->channel->offermsg.offer.if_instance); + vgpuch =3D vzalloc(sizeof(struct dxgvgpuchannel)); + if (vgpuch =3D=3D NULL) { + ret =3D -ENOMEM; + goto error; + } + vgpuch->adapter_luid =3D luid; + vgpuch->hdev =3D hdev; + list_add_tail(&vgpuch->vgpu_ch_list_entry, + &dxgglobal->vgpu_ch_list_head); + dxgglobal_start_adapters(); + } else if (uuid_le_cmp(hdev->dev_type, id_table[1].guid) =3D=3D 0) { + /* This is the global Dxgkgnl channel */ + pr_debug("Global channel: %pUb", + &hdev->channel->offermsg.offer.if_instance); + if (dxgglobal->hdev) { + /* This device should appear only once */ + pr_err("global channel already present\n"); + ret =3D -EBADE; + goto error; + } + dxgglobal->hdev =3D hdev; + dxgglobal_start_adapters(); + } else { + /* Unknown device type */ + pr_err("probe: unknown device type\n"); + ret =3D -EBADE; + goto error; + } + +error: + + mutex_unlock(&dxgglobal->device_mutex); + + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +static int dxg_remove_vmbus(struct hv_device *hdev) +{ + int ret =3D 0; + struct dxgvgpuchannel *vgpu_channel; + + mutex_lock(&dxgglobal->device_mutex); + + if (uuid_le_cmp(hdev->dev_type, id_table[0].guid) =3D=3D 0) { + pr_debug("Remove virtual GPU channel\n"); + dxgglobal_stop_adapter_vmbus(hdev); + list_for_each_entry(vgpu_channel, + &dxgglobal->vgpu_ch_list_head, + vgpu_ch_list_entry) { + if (vgpu_channel->hdev =3D=3D hdev) { + list_del(&vgpu_channel->vgpu_ch_list_entry); + vfree(vgpu_channel); + break; + } + } + } else if (uuid_le_cmp(hdev->dev_type, id_table[1].guid) =3D=3D 0) { + pr_debug("Remove global channel device\n"); + dxgglobal_destroy_global_channel(); + } else { + /* Unknown device type */ + pr_err("remove: unknown device type\n"); + ret =3D -EBADE; + } + + mutex_unlock(&dxgglobal->device_mutex); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +MODULE_DEVICE_TABLE(vmbus, id_table); + +static struct hv_driver dxg_drv =3D { + .name =3D KBUILD_MODNAME, + .id_table =3D id_table, + .probe =3D dxg_probe_vmbus, + .remove =3D dxg_remove_vmbus, + .driver =3D { + .probe_type =3D PROBE_PREFER_ASYNCHRONOUS, + }, +}; + +/* + * Interface with Linux kernel + */ + +static int dxgglobal_create(void) +{ + int ret =3D 0; + + dxgglobal =3D vzalloc(sizeof(struct dxgglobal)); + if (!dxgglobal) + return -ENOMEM; + + INIT_LIST_HEAD(&dxgglobal->plisthead); + mutex_init(&dxgglobal->plistmutex); + mutex_init(&dxgglobal->device_mutex); + + INIT_LIST_HEAD(&dxgglobal->thread_info_list_head); + mutex_init(&dxgglobal->thread_info_mutex); + + INIT_LIST_HEAD(&dxgglobal->vgpu_ch_list_head); + INIT_LIST_HEAD(&dxgglobal->adapter_list_head); + init_rwsem(&dxgglobal->adapter_list_lock); + + init_rwsem(&dxgglobal->channel_lock); + + pr_debug("dxgglobal_init end\n"); + return ret; +} + +static void dxgglobal_destroy(void) +{ + if (dxgglobal) { + dxgglobal_stop_adapters(); + + if (dxgglobal->vmbus_registered) + vmbus_driver_unregister(&dxg_drv); + + dxgglobal_destroy_global_channel(); + + if (dxgglobal->pci_registered) + pci_unregister_driver(&dxg_pci_drv); + + vfree(dxgglobal); + dxgglobal =3D NULL; + } +} + +/* + * Driver entry points + */ + +static int __init dxg_drv_init(void) +{ + int ret; + + + ret =3D dxgglobal_create(); + if (ret) { + pr_err("dxgglobal_init failed"); + return -ENOMEM; + } + + ret =3D vmbus_driver_register(&dxg_drv); + if (ret) { + pr_err("vmbus_driver_register failed: %d", ret); + return ret; + } + dxgglobal->vmbus_registered =3D true; + + pr_info("%s Version: %x", __func__, DXGKRNL_VERSION); + + ret =3D pci_register_driver(&dxg_pci_drv); + if (ret) { + pr_err("pci_driver_register failed: %d", ret); + return ret; + } + dxgglobal->pci_registered =3D true; + + init_ioctls(); + + return 0; +} + +static void __exit dxg_drv_exit(void) +{ + dxgglobal_destroy(); +} + +module_init(dxg_drv_init); +module_exit(dxg_drv_exit); + +MODULE_LICENSE("GPL"); +MODULE_DESCRIPTION("Microsoft Dxgkrnl virtual GPU Driver"); diff --git a/drivers/hv/dxgkrnl/dxgprocess.c b/drivers/hv/dxgkrnl/dxgproces= s.c new file mode 100644 index 000000000000..81e5b4a137e7 --- /dev/null +++ b/drivers/hv/dxgkrnl/dxgprocess.c @@ -0,0 +1,17 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (c) 2019, Microsoft Corporation. + * + * Author: + * Iouri Tarassov + * + * Dxgkrnl Graphics Driver + * DXGPROCESS implementation + * + */ + +#include "dxgkrnl.h" + +#undef pr_fmt +#define pr_fmt(fmt) "dxgk: " fmt diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c new file mode 100644 index 000000000000..84693c98a4af --- /dev/null +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -0,0 +1,578 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (c) 2019, Microsoft Corporation. + * + * Author: + * Iouri Tarassov + * + * Dxgkrnl Graphics Driver + * VM bus interface implementation + * + */ + +#include +#include +#include +#include +#include +#include +#include +#include +#include "dxgkrnl.h" +#include "dxgvmbus.h" + +#undef pr_fmt +#define pr_fmt(fmt) "dxgk: " fmt + +#define RING_BUFSIZE (256 * 1024) + +/* + * The structure is used to track VM bus packets, waiting for completion. + */ +struct dxgvmbuspacket { + struct list_head packet_list_entry; + u64 request_id; + struct completion wait; + void *buffer; + u32 buffer_length; + int status; +}; + +struct dxgvmb_ext_header { + /* Offset from the start of the message to DXGKVMB_COMMAND_BASE */ + u32 command_offset; + u32 reserved; + struct winluid vgpu_luid; +}; + +#define VMBUSMESSAGEONSTACK 64 + +struct dxgvmbusmsg { +/* Points to the allocated buffer */ + struct dxgvmb_ext_header *hdr; +/* Points to dxgkvmb_command_vm_to_host or dxgkvmb_command_vgpu_to_host */ + void *msg; +/* The vm bus channel, used to pass the message to the host */ + struct dxgvmbuschannel *channel; +/* Message size in bytes including the header and the payload */ + u32 size; +/* Buffer used for small messages */ + char msg_on_stack[VMBUSMESSAGEONSTACK]; +}; + +struct dxgvmbusmsgres { +/* Points to the allocated buffer */ + struct dxgvmb_ext_header *hdr; +/* Points to dxgkvmb_command_vm_to_host or dxgkvmb_command_vgpu_to_host */ + void *msg; +/* The vm bus channel, used to pass the message to the host */ + struct dxgvmbuschannel *channel; +/* Message size in bytes including the header, the payload and the result = */ + u32 size; +/* Result buffer size in bytes */ + u32 res_size; +/* Points to the result within the allocated buffer */ + void *res; +}; + +static int init_message(struct dxgvmbusmsg *msg, struct dxgadapter *adapte= r, + struct dxgprocess *process, u32 size) +{ + bool use_ext_header =3D dxgglobal->vmbus_ver >=3D + DXGK_VMBUS_INTERFACE_VERSION; + + if (use_ext_header) + size +=3D sizeof(struct dxgvmb_ext_header); + msg->size =3D size; + if (size <=3D VMBUSMESSAGEONSTACK) { + msg->hdr =3D (void *)msg->msg_on_stack; + memset(msg->hdr, 0, size); + } else { + msg->hdr =3D vzalloc(size); + if (msg->hdr =3D=3D NULL) + return -ENOMEM; + } + if (use_ext_header) { + msg->msg =3D (char *)&msg->hdr[1]; + msg->hdr->command_offset =3D sizeof(msg->hdr[0]); + if (adapter) + msg->hdr->vgpu_luid =3D adapter->host_vgpu_luid; + } else { + msg->msg =3D (char *)msg->hdr; + } + if (adapter && !dxgglobal->async_msg_enabled) + msg->channel =3D &adapter->channel; + else + msg->channel =3D &dxgglobal->channel; + return 0; +} + +static void free_message(struct dxgvmbusmsg *msg, struct dxgprocess *proce= ss) +{ + if (msg->hdr && (char *)msg->hdr !=3D msg->msg_on_stack) + vfree(msg->hdr); +} + +/* + * Helper functions + */ + +static void command_vm_to_host_init2(struct dxgkvmb_command_vm_to_host *co= mmand, + enum dxgkvmb_commandtype_global t, + struct d3dkmthandle process) +{ + command->command_type =3D t; + command->process =3D process; + command->command_id =3D 0; + command->channel_type =3D DXGKVMB_VM_TO_HOST; +} + +static void command_vgpu_to_host_init1(struct dxgkvmb_command_vgpu_to_host + *command, + enum dxgkvmb_commandtype type) +{ + command->command_type =3D type; + command->process.v =3D 0; + command->command_id =3D 0; + command->channel_type =3D DXGKVMB_VGPU_TO_HOST; +} + +static void command_vgpu_to_host_init2(struct dxgkvmb_command_vgpu_to_host + *command, + enum dxgkvmb_commandtype type, + struct d3dkmthandle process) +{ + command->command_type =3D type; + command->process =3D process; + command->command_id =3D 0; + command->channel_type =3D DXGKVMB_VGPU_TO_HOST; +} + +int ntstatus2int(struct ntstatus status) +{ + if (NT_SUCCESS(status)) + return (int)status.v; + switch (status.v) { + case STATUS_OBJECT_NAME_COLLISION: + return -EEXIST; + case STATUS_NO_MEMORY: + return -ENOMEM; + case STATUS_INVALID_PARAMETER: + return -EINVAL; + case STATUS_OBJECT_NAME_INVALID: + case STATUS_OBJECT_NAME_NOT_FOUND: + return -ENOENT; + case STATUS_TIMEOUT: + return -EAGAIN; + case STATUS_BUFFER_TOO_SMALL: + return -EOVERFLOW; + case STATUS_DEVICE_REMOVED: + return -ENODEV; + case STATUS_ACCESS_DENIED: + return -EACCES; + case STATUS_NOT_SUPPORTED: + return -EPERM; + case STATUS_ILLEGAL_INSTRUCTION: + return -EOPNOTSUPP; + case STATUS_INVALID_HANDLE: + return -EBADF; + case STATUS_GRAPHICS_ALLOCATION_BUSY: + return -EINPROGRESS; + case STATUS_OBJECT_TYPE_MISMATCH: + return -EPROTOTYPE; + case STATUS_NOT_IMPLEMENTED: + return -EPERM; + default: + return -EINVAL; + } +} + +int dxgvmbuschannel_init(struct dxgvmbuschannel *ch, struct hv_device *hde= v) +{ + int ret; + + ch->hdev =3D hdev; + spin_lock_init(&ch->packet_list_mutex); + INIT_LIST_HEAD(&ch->packet_list_head); + atomic64_set(&ch->packet_request_id, 0); + + ch->packet_cache =3D kmem_cache_create("DXGK packet cache", + sizeof(struct dxgvmbuspacket), 0, + 0, NULL); + if (ch->packet_cache =3D=3D NULL) { + pr_err("packet_cache alloc failed"); + ret =3D -ENOMEM; + goto cleanup; + } + + hdev->channel->max_pkt_size =3D DXG_MAX_VM_BUS_PACKET_SIZE; + ret =3D vmbus_open(hdev->channel, RING_BUFSIZE, RING_BUFSIZE, + NULL, 0, dxgvmbuschannel_receive, ch); + if (ret) { + pr_err("vmbus_open failed: %d", ret); + goto cleanup; + } + + ch->channel =3D hdev->channel; + +cleanup: + + return ret; +} + +void dxgvmbuschannel_destroy(struct dxgvmbuschannel *ch) +{ + kmem_cache_destroy(ch->packet_cache); + ch->packet_cache =3D NULL; + + if (ch->channel) { + vmbus_close(ch->channel); + ch->channel =3D NULL; + } +} + +static void command_vm_to_host_init1(struct dxgkvmb_command_vm_to_host *co= mmand, + enum dxgkvmb_commandtype_global type) +{ + command->command_type =3D type; + command->process.v =3D 0; + command->command_id =3D 0; + command->channel_type =3D DXGKVMB_VM_TO_HOST; +} + +static void process_inband_packet(struct dxgvmbuschannel *channel, + struct vmpacket_descriptor *desc) +{ + u32 packet_length =3D hv_pkt_datalen(desc); + struct dxgkvmb_command_host_to_vm *packet; + + if (channel->adapter =3D=3D NULL) { + if (packet_length < sizeof(struct dxgkvmb_command_host_to_vm)) { + pr_err("Invalid global packet"); + } else { + packet =3D hv_pkt_data(desc); + pr_debug("global packet %d", + packet->command_type); + switch (packet->command_type) { + case DXGK_VMBCOMMAND_SIGNALGUESTEVENT: + case DXGK_VMBCOMMAND_SIGNALGUESTEVENTPASSIVE: + break; + case DXGK_VMBCOMMAND_SENDWNFNOTIFICATION: + break; + default: + pr_err("unexpected host message %d", + packet->command_type); + } + } + } else { + pr_err("Unexpected packet for adapter channel"); + } +} + +static void process_completion_packet(struct dxgvmbuschannel *channel, + struct vmpacket_descriptor *desc) +{ + struct dxgvmbuspacket *packet =3D NULL; + struct dxgvmbuspacket *entry; + u32 packet_length =3D hv_pkt_datalen(desc); + unsigned long flags; + + spin_lock_irqsave(&channel->packet_list_mutex, flags); + list_for_each_entry(entry, &channel->packet_list_head, + packet_list_entry) { + if (desc->trans_id =3D=3D entry->request_id) { + packet =3D entry; + list_del(&packet->packet_list_entry); + break; + } + } + spin_unlock_irqrestore(&channel->packet_list_mutex, flags); + if (packet) { + if (packet->buffer_length) { + if (packet_length < packet->buffer_length) { + pr_debug("invalid size %d Expected:%d", + packet_length, + packet->buffer_length); + packet->status =3D -EOVERFLOW; + } else { + memcpy(packet->buffer, hv_pkt_data(desc), + packet->buffer_length); + } + } + complete(&packet->wait); + } else { + pr_err("did not find packet to complete"); + } +} + +/* Receive callback for messages from the host */ +void dxgvmbuschannel_receive(void *ctx) +{ + struct dxgvmbuschannel *channel =3D ctx; + struct vmpacket_descriptor *desc; + u32 packet_length =3D 0; + + pr_debug("%s %p", __func__, channel->adapter); + foreach_vmbus_pkt(desc, channel->channel) { + packet_length =3D hv_pkt_datalen(desc); + pr_debug("next packet (id, size, type): %llu %d %d", + desc->trans_id, packet_length, desc->type); + if (desc->type =3D=3D VM_PKT_COMP) { + process_completion_packet(channel, desc); + } else { + if (desc->type !=3D VM_PKT_DATA_INBAND) + pr_err("unexpected packet type"); + else + process_inband_packet(channel, desc); + } + } +} + +int dxgvmb_send_sync_msg(struct dxgvmbuschannel *channel, + void *command, + u32 cmd_size, + void *result, + u32 result_size) +{ + int ret; + struct dxgvmbuspacket *packet =3D NULL; + struct dxgkvmb_command_vm_to_host *cmd1; + struct dxgkvmb_command_vgpu_to_host *cmd2; + + if (cmd_size > DXG_MAX_VM_BUS_PACKET_SIZE || + result_size > DXG_MAX_VM_BUS_PACKET_SIZE) { + pr_err("%s invalid data size", __func__); + return -EINVAL; + } + + packet =3D kmem_cache_alloc(channel->packet_cache, 0); + if (packet =3D=3D NULL) { + pr_err("kmem_cache_alloc failed"); + return -ENOMEM; + } + + if (channel->adapter =3D=3D NULL) { + cmd1 =3D command; + pr_debug("send_sync_msg global: %d %p %d %d", + cmd1->command_type, command, cmd_size, result_size); + } else { + cmd2 =3D command; + pr_debug("send_sync_msg adapter: %d %p %d %d", + cmd2->command_type, command, cmd_size, result_size); + } + + packet->request_id =3D atomic64_inc_return(&channel->packet_request_id); + init_completion(&packet->wait); + packet->buffer =3D result; + packet->buffer_length =3D result_size; + packet->status =3D 0; + spin_lock_irq(&channel->packet_list_mutex); + list_add_tail(&packet->packet_list_entry, &channel->packet_list_head); + spin_unlock_irq(&channel->packet_list_mutex); + + ret =3D vmbus_sendpacket(channel->channel, command, cmd_size, + packet->request_id, VM_PKT_DATA_INBAND, + VMBUS_DATA_PACKET_FLAG_COMPLETION_REQUESTED); + if (ret) { + pr_err("vmbus_sendpacket failed: %x", ret); + spin_lock_irq(&channel->packet_list_mutex); + list_del(&packet->packet_list_entry); + spin_unlock_irq(&channel->packet_list_mutex); + goto cleanup; + } + + pr_debug("waiting completion: %llu", packet->request_id); + wait_for_completion(&packet->wait); + pr_debug("completion done: %llu %x", + packet->request_id, packet->status); + ret =3D packet->status; + +cleanup: + + kmem_cache_free(channel->packet_cache, packet); + if (ret < 0) + pr_debug("%s failed: %x", __func__, ret); + return ret; +} + +int dxgvmb_send_async_msg(struct dxgvmbuschannel *channel, + void *command, + u32 cmd_size) +{ + int ret; + int try_count =3D 0; + + if (cmd_size > DXG_MAX_VM_BUS_PACKET_SIZE) { + pr_err("%s invalid data size", __func__); + return -EINVAL; + } + + if (channel->adapter) { + pr_err("Async messages should be sent to the global channel"); + return -EINVAL; + } + + do { + ret =3D vmbus_sendpacket(channel->channel, command, cmd_size, + 0, VM_PKT_DATA_INBAND, 0); + /* + * -EAGAIN is returned when the VM bus ring buffer if full. + * Wait 2ms to allow the host to process messages and try again. + */ + if (ret =3D=3D -EAGAIN) { + usleep_range(1000, 2000); + try_count++; + } + } while (ret =3D=3D -EAGAIN && try_count < 5000); + if (ret < 0) + pr_err("vmbus_sendpacket failed: %x", ret); + + return ret; +} + +static int +dxgvmb_send_sync_msg_ntstatus(struct dxgvmbuschannel *channel, + void *command, u32 cmd_size) +{ + struct ntstatus status; + int ret; + + ret =3D dxgvmb_send_sync_msg(channel, command, cmd_size, + &status, sizeof(status)); + if (ret >=3D 0) + ret =3D ntstatus2int(status); + return ret; +} + +/* + * Global messages to the host + */ + +int dxgvmb_send_set_iospace_region(u64 start, u64 len, + struct vmbus_gpadl *shared_mem_gpadl) +{ + int ret; + struct dxgkvmb_command_setiospaceregion *command; + struct dxgvmbusmsg msg; + + ret =3D init_message(&msg, NULL, NULL, sizeof(*command)); + if (ret) + return ret; + command =3D (void *)msg.msg; + + ret =3D dxgglobal_acquire_channel_lock(); + if (ret < 0) + goto cleanup; + + command_vm_to_host_init1(&command->hdr, + DXGK_VMBCOMMAND_SETIOSPACEREGION); + command->start =3D start; + command->length =3D len; + if (command->shared_page_gpadl) + command->shared_page_gpadl =3D shared_mem_gpadl->gpadl_handle; + ret =3D dxgvmb_send_sync_msg_ntstatus(&dxgglobal->channel, msg.hdr, + msg.size); + if (ret < 0) + pr_err("send_set_iospace_region failed %x", ret); + + dxgglobal_release_channel_lock(); +cleanup: + free_message(&msg, NULL); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +/* + * Virtual GPU messages to the host + */ + +int dxgvmb_send_open_adapter(struct dxgadapter *adapter) +{ + int ret; + struct dxgkvmb_command_openadapter *command; + struct dxgkvmb_command_openadapter_return result =3D { }; + struct dxgvmbusmsg msg; + + ret =3D init_message(&msg, adapter, NULL, sizeof(*command)); + if (ret) + return ret; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init1(&command->hdr, DXGK_VMBCOMMAND_OPENADAPTER); + command->vmbus_interface_version =3D dxgglobal->vmbus_ver; + command->vmbus_last_compatible_interface_version =3D + DXGK_VMBUS_LAST_COMPATIBLE_INTERFACE_VERSION; + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, + &result, sizeof(result)); + if (ret < 0) + goto cleanup; + + ret =3D ntstatus2int(result.status); + adapter->host_handle =3D result.host_adapter_handle; + +cleanup: + free_message(&msg, NULL); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +int dxgvmb_send_close_adapter(struct dxgadapter *adapter) +{ + int ret; + struct dxgkvmb_command_closeadapter *command; + struct dxgvmbusmsg msg; + + ret =3D init_message(&msg, adapter, NULL, sizeof(*command)); + if (ret) + return ret; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init1(&command->hdr, DXGK_VMBCOMMAND_CLOSEADAPTER); + command->host_handle =3D adapter->host_handle; + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, + NULL, 0); + free_message(&msg, NULL); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +int dxgvmb_send_get_internal_adapter_info(struct dxgadapter *adapter) +{ + int ret; + struct dxgkvmb_command_getinternaladapterinfo *command; + struct dxgkvmb_command_getinternaladapterinfo_return result =3D { }; + struct dxgvmbusmsg msg; + u32 result_size =3D sizeof(result); + + ret =3D init_message(&msg, adapter, NULL, sizeof(*command)); + if (ret) + return ret; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init1(&command->hdr, + DXGK_VMBCOMMAND_GETINTERNALADAPTERINFO); + if (dxgglobal->vmbus_ver < DXGK_VMBUS_INTERFACE_VERSION) + result_size -=3D sizeof(struct winluid); + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, + &result, result_size); + if (ret >=3D 0) { + adapter->host_adapter_luid =3D result.host_adapter_luid; + adapter->host_vgpu_luid =3D result.host_vgpu_luid; + wcsncpy(adapter->device_description, result.device_description, + sizeof(adapter->device_description) / sizeof(u16)); + wcsncpy(adapter->device_instance_id, result.device_instance_id, + sizeof(adapter->device_instance_id) / sizeof(u16)); + dxgglobal->async_msg_enabled =3D result.async_msg_enabled !=3D 0; + } + free_message(&msg, NULL); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} diff --git a/drivers/hv/dxgkrnl/dxgvmbus.h b/drivers/hv/dxgkrnl/dxgvmbus.h new file mode 100644 index 000000000000..93cce587158b --- /dev/null +++ b/drivers/hv/dxgkrnl/dxgvmbus.h @@ -0,0 +1,855 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Copyright (c) 2019, Microsoft Corporation. + * + * Author: + * Iouri Tarassov + * + * Dxgkrnl Graphics Driver + * VM bus interface with the host definitions + * + */ + +#ifndef _DXGVMBUS_H +#define _DXGVMBUS_H + +struct dxgadapter; + +#define DXG_MAX_VM_BUS_PACKET_SIZE (1024 * 128) +#define DXG_MAX_OBJECT_COUNT 0xFFF + +#define DXGK_DECL_VMBUS_OUTPUTSIZE(Type)\ + ((sizeof(##Type) + 0x7) & ~(u32)0x7) +#define DXGK_DECL_VMBUS_ALIGN_FOR_OUTPUT(Size) (((Size) + 0x7) & ~(u32)0x7) +/* + * Defines a structure, which has the size, multiple of 8 bytes. + */ +#define DXGK_DECL_ALIGNED8_STRUCT(Type, Name, OutputSize) \ + const u32 _Size =3D DXGK_DECL_VMBUS_OUTPUTSIZE(Type); \ + u8 _AlignedStruct[_Size]; \ + ##Type & Name =3D (##Type &)_AlignedStruct; \ + u32 OutputSize =3D _Size + +#define DXGK_BUFFER_VMBUS_ALIGNED(Buffer) (((Buffer) & 7) =3D=3D 0) + +enum dxgkvmb_commandchanneltype { + DXGKVMB_VGPU_TO_HOST, + DXGKVMB_VM_TO_HOST, + DXGKVMB_HOST_TO_VM +}; + +/* + * + * Commands, sent to the host via the guest global VM bus channel + * DXG_GUEST_GLOBAL_VMBUS + * + */ + +#define DXG_VM_PROCESS_NAME_LENGTH 260 + +enum dxgkvmb_commandtype_global { + DXGK_VMBCOMMAND_VM_TO_HOST_FIRST =3D 1000, + DXGK_VMBCOMMAND_CREATEPROCESS =3D DXGK_VMBCOMMAND_VM_TO_HOST_FIRST, + DXGK_VMBCOMMAND_DESTROYPROCESS =3D 1001, + DXGK_VMBCOMMAND_OPENSYNCOBJECT =3D 1002, + DXGK_VMBCOMMAND_DESTROYSYNCOBJECT =3D 1003, + DXGK_VMBCOMMAND_CREATENTSHAREDOBJECT =3D 1004, + DXGK_VMBCOMMAND_DESTROYNTSHAREDOBJECT =3D 1005, + DXGK_VMBCOMMAND_SIGNALFENCE =3D 1006, + DXGK_VMBCOMMAND_NOTIFYPROCESSFREEZE =3D 1007, + DXGK_VMBCOMMAND_NOTIFYPROCESSTHAW =3D 1008, + DXGK_VMBCOMMAND_QUERYETWSESSION =3D 1009, + DXGK_VMBCOMMAND_SETIOSPACEREGION =3D 1010, + DXGK_VMBCOMMAND_COMPLETETRANSACTION =3D 1011, + DXGK_VMBCOMMAND_INVALID_VM_TO_HOST +}; + +/* + * + * Commands, sent to the host via the per adapter VM bus channel + * DXG_GUEST_VGPU_VMBUS + * + */ + +enum dxgkvmb_commandtype { + DXGK_VMBCOMMAND_CREATEDEVICE =3D 0, + DXGK_VMBCOMMAND_DESTROYDEVICE =3D 1, + DXGK_VMBCOMMAND_QUERYADAPTERINFO =3D 2, + DXGK_VMBCOMMAND_DDIQUERYADAPTERINFO =3D 3, + DXGK_VMBCOMMAND_CREATEALLOCATION =3D 4, + DXGK_VMBCOMMAND_DESTROYALLOCATION =3D 5, + DXGK_VMBCOMMAND_CREATECONTEXTVIRTUAL =3D 6, + DXGK_VMBCOMMAND_DESTROYCONTEXT =3D 7, + DXGK_VMBCOMMAND_CREATESYNCOBJECT =3D 8, + DXGK_VMBCOMMAND_CREATEPAGINGQUEUE =3D 9, + DXGK_VMBCOMMAND_DESTROYPAGINGQUEUE =3D 10, + DXGK_VMBCOMMAND_MAKERESIDENT =3D 11, + DXGK_VMBCOMMAND_EVICT =3D 12, + DXGK_VMBCOMMAND_ESCAPE =3D 13, + DXGK_VMBCOMMAND_OPENADAPTER =3D 14, + DXGK_VMBCOMMAND_CLOSEADAPTER =3D 15, + DXGK_VMBCOMMAND_FREEGPUVIRTUALADDRESS =3D 16, + DXGK_VMBCOMMAND_MAPGPUVIRTUALADDRESS =3D 17, + DXGK_VMBCOMMAND_RESERVEGPUVIRTUALADDRESS =3D 18, + DXGK_VMBCOMMAND_UPDATEGPUVIRTUALADDRESS =3D 19, + DXGK_VMBCOMMAND_SUBMITCOMMAND =3D 20, + dxgk_vmbcommand_queryvideomemoryinfo =3D 21, + DXGK_VMBCOMMAND_WAITFORSYNCOBJECTFROMCPU =3D 22, + DXGK_VMBCOMMAND_LOCK2 =3D 23, + DXGK_VMBCOMMAND_UNLOCK2 =3D 24, + DXGK_VMBCOMMAND_WAITFORSYNCOBJECTFROMGPU =3D 25, + DXGK_VMBCOMMAND_SIGNALSYNCOBJECT =3D 26, + DXGK_VMBCOMMAND_SIGNALFENCENTSHAREDBYREF =3D 27, + DXGK_VMBCOMMAND_GETDEVICESTATE =3D 28, + DXGK_VMBCOMMAND_MARKDEVICEASERROR =3D 29, + DXGK_VMBCOMMAND_ADAPTERSTOP =3D 30, + DXGK_VMBCOMMAND_SETQUEUEDLIMIT =3D 31, + DXGK_VMBCOMMAND_OPENRESOURCE =3D 32, + DXGK_VMBCOMMAND_SETCONTEXTSCHEDULINGPRIORITY =3D 33, + DXGK_VMBCOMMAND_PRESENTHISTORYTOKEN =3D 34, + DXGK_VMBCOMMAND_SETREDIRECTEDFLIPFENCEVALUE =3D 35, + DXGK_VMBCOMMAND_GETINTERNALADAPTERINFO =3D 36, + DXGK_VMBCOMMAND_FLUSHHEAPTRANSITIONS =3D 37, + DXGK_VMBCOMMAND_BLT =3D 38, + DXGK_VMBCOMMAND_DDIGETSTANDARDALLOCATIONDRIVERDATA =3D 39, + DXGK_VMBCOMMAND_CDDGDICOMMAND =3D 40, + DXGK_VMBCOMMAND_QUERYALLOCATIONRESIDENCY =3D 41, + DXGK_VMBCOMMAND_FLUSHDEVICE =3D 42, + DXGK_VMBCOMMAND_FLUSHADAPTER =3D 43, + DXGK_VMBCOMMAND_DDIGETNODEMETADATA =3D 44, + DXGK_VMBCOMMAND_SETEXISTINGSYSMEMSTORE =3D 45, + DXGK_VMBCOMMAND_ISSYNCOBJECTSIGNALED =3D 46, + DXGK_VMBCOMMAND_CDDSYNCGPUACCESS =3D 47, + DXGK_VMBCOMMAND_QUERYSTATISTICS =3D 48, + DXGK_VMBCOMMAND_CHANGEVIDEOMEMORYRESERVATION =3D 49, + DXGK_VMBCOMMAND_CREATEHWQUEUE =3D 50, + DXGK_VMBCOMMAND_DESTROYHWQUEUE =3D 51, + DXGK_VMBCOMMAND_SUBMITCOMMANDTOHWQUEUE =3D 52, + DXGK_VMBCOMMAND_GETDRIVERSTOREFILE =3D 53, + DXGK_VMBCOMMAND_READDRIVERSTOREFILE =3D 54, + DXGK_VMBCOMMAND_GETNEXTHARDLINK =3D 55, + DXGK_VMBCOMMAND_UPDATEALLOCATIONPROPERTY =3D 56, + DXGK_VMBCOMMAND_OFFERALLOCATIONS =3D 57, + DXGK_VMBCOMMAND_RECLAIMALLOCATIONS =3D 58, + DXGK_VMBCOMMAND_SETALLOCATIONPRIORITY =3D 59, + DXGK_VMBCOMMAND_GETALLOCATIONPRIORITY =3D 60, + DXGK_VMBCOMMAND_GETCONTEXTSCHEDULINGPRIORITY =3D 61, + DXGK_VMBCOMMAND_QUERYCLOCKCALIBRATION =3D 62, + DXGK_VMBCOMMAND_QUERYRESOURCEINFO =3D 64, + DXGK_VMBCOMMAND_INVALID +}; + +enum dxgkvmb_commandtype_host_to_vm { + DXGK_VMBCOMMAND_SIGNALGUESTEVENT, + DXGK_VMBCOMMAND_PROPAGATEPRESENTHISTORYTOKEN, + DXGK_VMBCOMMAND_SETGUESTDATA, + DXGK_VMBCOMMAND_SIGNALGUESTEVENTPASSIVE, + DXGK_VMBCOMMAND_SENDWNFNOTIFICATION, + DXGK_VMBCOMMAND_INVALID_HOST_TO_VM +}; + +struct dxgkvmb_command_vm_to_host { + u64 command_id; + struct d3dkmthandle process; + enum dxgkvmb_commandchanneltype channel_type; + enum dxgkvmb_commandtype_global command_type; +}; + +struct dxgkvmb_command_vgpu_to_host { + u64 command_id; + struct d3dkmthandle process; + u32 channel_type : 8; + u32 async_msg : 1; + u32 reserved : 23; + enum dxgkvmb_commandtype command_type; +}; + +struct dxgkvmb_command_host_to_vm { + u64 command_id; + struct d3dkmthandle process; + u32 channel_type : 8; + u32 async_msg : 1; + u32 reserved : 23; + enum dxgkvmb_commandtype_host_to_vm command_type; +}; + +struct dxgkvmb_command_signalguestevent { + struct dxgkvmb_command_host_to_vm hdr; + u64 event; + u64 process_id; + bool dereference_event; +}; + +enum set_guestdata_type { + SETGUESTDATA_DATATYPE_DWORD =3D 0, + SETGUESTDATA_DATATYPE_UINT64 =3D 1 +}; + +struct dxgkvmb_command_setguestdata { + struct dxgkvmb_command_host_to_vm hdr; + void *guest_pointer; + union { + u64 data64; + u32 data32; + }; + u32 dereference : 1; + u32 data_type : 4; +}; + +struct dxgkvmb_command_opensyncobject { + struct dxgkvmb_command_vm_to_host hdr; + struct d3dkmthandle device; + struct d3dkmthandle global_sync_object; + u32 engine_affinity; + struct d3dddi_synchronizationobject_flags flags; +}; + +struct dxgkvmb_command_opensyncobject_return { + struct d3dkmthandle sync_object; + struct ntstatus status; + u64 gpu_virtual_address; + u64 guest_cpu_physical_address; +}; + +/* + * The command returns struct d3dkmthandle of a shared object for the + * given pre-process object + */ +struct dxgkvmb_command_createntsharedobject { + struct dxgkvmb_command_vm_to_host hdr; + struct d3dkmthandle object; +}; + +/* The command returns ntstatus */ +struct dxgkvmb_command_destroyntsharedobject { + struct dxgkvmb_command_vm_to_host hdr; + struct d3dkmthandle shared_handle; +}; + +/* Returns ntstatus */ +struct dxgkvmb_command_setiospaceregion { + struct dxgkvmb_command_vm_to_host hdr; + u64 start; + u64 length; + u32 shared_page_gpadl; +}; + +/* Returns ntstatus */ +struct dxgkvmb_command_setexistingsysmemstore { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle device; + struct d3dkmthandle allocation; + u32 gpadl; +}; + +struct dxgkvmb_command_createprocess { + struct dxgkvmb_command_vm_to_host hdr; + void *process; + u64 process_id; + u16 process_name[DXG_VM_PROCESS_NAME_LENGTH + 1]; + u8 csrss_process:1; + u8 dwm_process:1; + u8 wow64_process:1; + u8 linux_process:1; +}; + +struct dxgkvmb_command_createprocess_return { + struct d3dkmthandle hprocess; +}; + +// The command returns ntstatus +struct dxgkvmb_command_destroyprocess { + struct dxgkvmb_command_vm_to_host hdr; +}; + +struct dxgkvmb_command_openadapter { + struct dxgkvmb_command_vgpu_to_host hdr; + u32 vmbus_interface_version; + u32 vmbus_last_compatible_interface_version; + struct winluid guest_adapter_luid; +}; + +struct dxgkvmb_command_openadapter_return { + struct d3dkmthandle host_adapter_handle; + struct ntstatus status; + u32 vmbus_interface_version; + u32 vmbus_last_compatible_interface_version; +}; + +struct dxgkvmb_command_closeadapter { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle host_handle; +}; + +struct dxgkvmb_command_getinternaladapterinfo { + struct dxgkvmb_command_vgpu_to_host hdr; +}; + +struct dxgkvmb_command_getinternaladapterinfo_return { + struct dxgk_device_types device_types; + u32 driver_store_copy_mode; + u32 driver_ddi_version; + u32 secure_virtual_machine : 1; + u32 virtual_machine_reset : 1; + u32 is_vail_supported : 1; + u32 hw_sch_enabled : 1; + u32 hw_sch_capable : 1; + u32 va_backed_vm : 1; + u32 async_msg_enabled : 1; + u32 hw_support_state : 2; + u32 reserved : 23; + struct winluid host_adapter_luid; + u16 device_description[80]; + u16 device_instance_id[WIN_MAX_PATH]; + struct winluid host_vgpu_luid; +}; + +struct dxgkvmb_command_queryadapterinfo { + struct dxgkvmb_command_vgpu_to_host hdr; + enum kmtqueryadapterinfotype query_type; + u32 private_data_size; + u8 private_data[1]; +}; + +struct dxgkvmb_command_queryadapterinfo_return { + struct ntstatus status; + u8 private_data[1]; +}; + +/* Returns ntstatus */ +struct dxgkvmb_command_setallocationpriority { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle device; + struct d3dkmthandle resource; + u32 allocation_count; + /* struct d3dkmthandle allocations[allocation_count or 0]; */ + /* u32 priorities[allocation_count or 1]; */ +}; + +struct dxgkvmb_command_getallocationpriority { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle device; + struct d3dkmthandle resource; + u32 allocation_count; + /* struct d3dkmthandle allocations[allocation_count or 0]; */ +}; + +struct dxgkvmb_command_getallocationpriority_return { + struct ntstatus status; + /* u32 priorities[allocation_count or 1]; */ +}; + +/* Returns ntstatus */ +struct dxgkvmb_command_setcontextschedulingpriority { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle context; + int priority; +}; + +/* Returns ntstatus */ +struct dxgkvmb_command_setcontextschedulingpriority2 { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle context; + int priority; + bool in_process; +}; + +struct dxgkvmb_command_getcontextschedulingpriority { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle context; + bool in_process; +}; + +struct dxgkvmb_command_getcontextschedulingpriority_return { + struct ntstatus status; + int priority; +}; + +struct dxgkvmb_command_createdevice { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmt_createdeviceflags flags; + bool cdd_device; + void *error_code; +}; + +struct dxgkvmb_command_createdevice_return { + struct d3dkmthandle device; +}; + +struct dxgkvmb_command_destroydevice { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle device; +}; + +struct dxgkvmb_command_makeresident { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle device; + struct d3dkmthandle paging_queue; + struct d3dddi_makeresident_flags flags; + u32 alloc_count; + struct d3dkmthandle allocations[1]; +}; + +struct dxgkvmb_command_makeresident_return { + u64 paging_fence_value; + u64 num_bytes_to_trim; + struct ntstatus status; +}; + +struct dxgkvmb_command_evict { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle device; + struct d3dddi_evict_flags flags; + u32 alloc_count; + struct d3dkmthandle allocations[1]; +}; + +struct dxgkvmb_command_evict_return { + u64 num_bytes_to_trim; +}; + +struct dxgkvmb_command_submitcommand { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmt_submitcommand args; + /* HistoryBufferHandles */ + /* PrivateDriverData */ +}; + +struct dxgkvmb_command_submitcommandtohwqueue { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmt_submitcommandtohwqueue args; + /* Written primaries */ + /* PrivateDriverData */ +}; + +/* Returns ntstatus */ +struct dxgkvmb_command_flushheaptransitions { + struct dxgkvmb_command_vgpu_to_host hdr; +}; + +struct dxgkvmb_command_freegpuvirtualaddress { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmt_freegpuvirtualaddress args; +}; + +struct dxgkvmb_command_mapgpuvirtualaddress { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dddi_mapgpuvirtualaddress args; + struct d3dkmthandle device; +}; + +struct dxgkvmb_command_mapgpuvirtualaddress_return { + u64 virtual_address; + u64 paging_fence_value; + struct ntstatus status; +}; + +struct dxgkvmb_command_reservegpuvirtualaddress { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dddi_reservegpuvirtualaddress args; +}; + +struct dxgkvmb_command_reservegpuvirtualaddress_return { + u64 virtual_address; + u64 paging_fence_value; +}; + +struct dxgkvmb_command_updategpuvirtualaddress { + struct dxgkvmb_command_vgpu_to_host hdr; + u64 fence_value; + struct d3dkmthandle device; + struct d3dkmthandle context; + struct d3dkmthandle fence_object; + u32 num_operations; + u32 flags; + struct d3dddi_updategpuvirtualaddress_operation operations[1]; +}; + +struct dxgkvmb_command_queryclockcalibration { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmt_queryclockcalibration args; +}; + +struct dxgkvmb_command_queryclockcalibration_return { + struct ntstatus status; + struct dxgk_gpuclockdata clock_data; +}; + +struct dxgkvmb_command_createallocation_allocinfo { + u32 flags; + u32 priv_drv_data_size; + u32 vidpn_source_id; +}; + +struct dxgkvmb_command_createallocation { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle device; + struct d3dkmthandle resource; + u32 private_runtime_data_size; + u32 priv_drv_data_size; + u32 alloc_count; + struct d3dkmt_createallocationflags flags; + u64 private_runtime_resource_handle; + bool make_resident; +/* dxgkvmb_command_createallocation_allocinfo alloc_info[alloc_count]; */ +/* u8 private_rutime_data[private_runtime_data_size] */ +/* u8 priv_drv_data[] for each alloc_info */ +}; + +struct dxgkvmb_command_openresource { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle device; + bool nt_security_sharing; + struct d3dkmthandle global_share; + u32 allocation_count; + u32 total_priv_drv_data_size; +}; + +struct dxgkvmb_command_openresource_return { + struct d3dkmthandle resource; + struct ntstatus status; +/* struct d3dkmthandle allocation[allocation_count]; */ +}; + +struct dxgkvmb_command_querystatistics { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmt_querystatistics args; +}; + +struct dxgkvmb_command_querystatistics_return { + struct ntstatus status; + u32 reserved; + struct d3dkmt_querystatistics_result result; +}; + +struct dxgkvmb_command_getstandardallocprivdata { + struct dxgkvmb_command_vgpu_to_host hdr; + enum d3dkmdt_standardallocationtype alloc_type; + u32 priv_driver_data_size; + u32 priv_driver_resource_size; + u32 physical_adapter_index; + union { + struct d3dkmdt_sharedprimarysurfacedata primary; + struct d3dkmdt_shadowsurfacedata shadow; + struct d3dkmdt_stagingsurfacedata staging; + struct d3dkmdt_gdisurfacedata gdi_surface; + }; +}; + +struct dxgkvmb_command_getstandardallocprivdata_return { + struct ntstatus status; + u32 priv_driver_data_size; + u32 priv_driver_resource_size; + union { + struct d3dkmdt_sharedprimarysurfacedata primary; + struct d3dkmdt_shadowsurfacedata shadow; + struct d3dkmdt_stagingsurfacedata staging; + struct d3dkmdt_gdisurfacedata gdi_surface; + }; +/* char alloc_priv_data[priv_driver_data_size]; */ +/* char resource_priv_data[priv_driver_resource_size]; */ +}; + +struct dxgkarg_describeallocation { + u64 allocation; + u32 width; + u32 height; + u32 format; + u32 multisample_method; + struct d3dddi_rational refresh_rate; + u32 private_driver_attribute; + u32 flags; + u32 rotation; +}; + +struct dxgkvmb_allocflags { + union { + u32 flags; + struct { + u32 primary:1; + u32 cdd_primary:1; + u32 dod_primary:1; + u32 overlay:1; + u32 reserved6:1; + u32 capture:1; + u32 reserved0:4; + u32 reserved1:1; + u32 existing_sysmem:1; + u32 stereo:1; + u32 direct_flip:1; + u32 hardware_protected:1; + u32 reserved2:1; + u32 reserved3:1; + u32 reserved4:1; + u32 protected:1; + u32 cached:1; + u32 independent_primary:1; + u32 reserved:11; + }; + }; +}; + +struct dxgkvmb_command_allocinfo_return { + struct d3dkmthandle allocation; + u32 priv_drv_data_size; + struct dxgkvmb_allocflags allocation_flags; + u64 allocation_size; + struct dxgkarg_describeallocation driver_info; +}; + +struct dxgkvmb_command_createallocation_return { + struct d3dkmt_createallocationflags flags; + struct d3dkmthandle resource; + struct d3dkmthandle global_share; + u32 vgpu_flags; + struct dxgkvmb_command_allocinfo_return allocation_info[1]; + /* Private driver data for allocations */ +}; + +/* The command returns ntstatus */ +struct dxgkvmb_command_destroyallocation { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle device; + struct d3dkmthandle resource; + u32 alloc_count; + struct d3dddicb_destroyallocation2flags flags; + struct d3dkmthandle allocations[1]; +}; + +struct dxgkvmb_command_createcontextvirtual { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle context; + struct d3dkmthandle device; + u32 node_ordinal; + u32 engine_affinity; + struct d3dddi_createcontextflags flags; + enum d3dkmt_clienthint client_hint; + u32 priv_drv_data_size; + u8 priv_drv_data[1]; +}; + +/* The command returns ntstatus */ +struct dxgkvmb_command_destroycontext { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle context; +}; + +struct dxgkvmb_command_createpagingqueue { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmt_createpagingqueue args; +}; + +struct dxgkvmb_command_createpagingqueue_return { + struct d3dkmthandle paging_queue; + struct d3dkmthandle sync_object; + u64 fence_storage_physical_address; + u64 fence_storage_offset; +}; + +struct dxgkvmb_command_destroypagingqueue { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle paging_queue; +}; + +struct dxgkvmb_command_createsyncobject { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmt_createsynchronizationobject2 args; + u32 client_hint; +}; + +struct dxgkvmb_command_createsyncobject_return { + struct d3dkmthandle sync_object; + struct d3dkmthandle global_sync_object; + u64 fence_gpu_va; + u64 fence_storage_address; + u32 fence_storage_offset; +}; + +/* The command returns ntstatus */ +struct dxgkvmb_command_destroysyncobject { + struct dxgkvmb_command_vm_to_host hdr; + struct d3dkmthandle sync_object; +}; + +/* The command returns ntstatus */ +struct dxgkvmb_command_signalsyncobject { + struct dxgkvmb_command_vgpu_to_host hdr; + u32 object_count; + struct d3dddicb_signalflags flags; + u32 context_count; + u64 fence_value; + union { + /* Pointer to the guest event object */ + u64 cpu_event_handle; + /* Non zero when signal from CPU is done */ + struct d3dkmthandle device; + }; + /* struct d3dkmthandle ObjectHandleArray[object_count] */ + /* struct d3dkmthandle ContextArray[context_count] */ + /* u64 MonitoredFenceValueArray[object_count] */ +}; + +/* The command returns ntstatus */ +struct dxgkvmb_command_waitforsyncobjectfromcpu { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle device; + u32 object_count; + struct d3dddi_waitforsynchronizationobjectfromcpu_flags flags; + u64 guest_event_pointer; + bool dereference_event; + /* struct d3dkmthandle ObjectHandleArray[object_count] */ + /* u64 FenceValueArray [object_count] */ +}; + +/* The command returns ntstatus */ +struct dxgkvmb_command_waitforsyncobjectfromgpu { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle context; + /* Must be 1 when bLegacyFenceObject is TRUE */ + u32 object_count; + bool legacy_fence_object; + u64 fence_values[1]; + /* struct d3dkmthandle ObjectHandles[object_count] */ +}; + +struct dxgkvmb_command_lock2 { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmt_lock2 args; + bool use_legacy_lock; + u32 flags; + u32 priv_drv_data; +}; + +struct dxgkvmb_command_lock2_return { + struct ntstatus status; + void *cpu_visible_buffer_offset; +}; + +struct dxgkvmb_command_unlock2 { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmt_unlock2 args; + bool use_legacy_unlock; +}; + +struct dxgkvmb_command_updateallocationproperty { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dddi_updateallocproperty args; +}; + +struct dxgkvmb_command_updateallocationproperty_return { + u64 paging_fence_value; + struct ntstatus status; +}; + +struct dxgkvmb_command_markdeviceaserror { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmt_markdeviceaserror args; +}; + +/* Returns ntstatus */ +struct dxgkvmb_command_offerallocations { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle device; + u32 allocation_count; + enum d3dkmt_offer_priority priority; + struct d3dkmt_offer_flags flags; + bool resources; + struct d3dkmthandle allocations[1]; +}; + +struct dxgkvmb_command_reclaimallocations { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle device; + struct d3dkmthandle paging_queue; + u32 allocation_count; + bool resources; + bool write_results; + struct d3dkmthandle allocations[1]; +}; + +struct dxgkvmb_command_reclaimallocations_return { + u64 paging_fence_value; + struct ntstatus status; + enum d3dddi_reclaim_result discarded[1]; +}; + +/* Returns ntstatus */ +struct dxgkvmb_command_changevideomemoryreservation { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmt_changevideomemoryreservation args; +}; + +/* Returns the same structure */ +struct dxgkvmb_command_createhwqueue { + struct dxgkvmb_command_vgpu_to_host hdr; + struct ntstatus status; + struct d3dkmthandle hwqueue; + struct d3dkmthandle hwqueue_progress_fence; + void *hwqueue_progress_fence_cpuva; + u64 hwqueue_progress_fence_gpuva; + struct d3dkmthandle context; + struct d3dddi_createhwqueueflags flags; + u32 priv_drv_data_size; + char priv_drv_data[1]; +}; + +/* The command returns ntstatus */ +struct dxgkvmb_command_destroyhwqueue { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle hwqueue; +}; + +struct dxgkvmb_command_queryallocationresidency { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmt_queryallocationresidency args; + /* struct d3dkmthandle allocations[0 or number of allocations] */ +}; + +struct dxgkvmb_command_queryallocationresidency_return { + struct ntstatus status; + /* d3dkmt_allocationresidencystatus[NumAllocations] */ +}; + +/* Returns only private data */ +struct dxgkvmb_command_escape { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle adapter; + struct d3dkmthandle device; + enum d3dkmt_escapetype type; + struct d3dddi_escapeflags flags; + u32 priv_drv_data_size; + struct d3dkmthandle context; + u8 priv_drv_data[1]; +}; + +struct dxgkvmb_command_queryvideomemoryinfo { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle adapter; + enum d3dkmt_memory_segment_group memory_segment_group; + u32 physical_adapter_index; +}; + +struct dxgkvmb_command_queryvideomemoryinfo_return { + u64 budget; + u64 current_usage; + u64 current_reservation; + u64 available_for_reservation; +}; + +struct dxgkvmb_command_getdevicestate { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmt_getdevicestate args; +}; + +struct dxgkvmb_command_getdevicestate_return { + struct d3dkmt_getdevicestate args; + struct ntstatus status; +}; + +int +dxgvmb_send_sync_msg(struct dxgvmbuschannel *channel, + void *command, u32 command_size, void *result, + u32 result_size); + +#endif /* _DXGVMBUS_H */ diff --git a/drivers/hv/dxgkrnl/hmgr.c b/drivers/hv/dxgkrnl/hmgr.c new file mode 100644 index 000000000000..216e0956f8f8 --- /dev/null +++ b/drivers/hv/dxgkrnl/hmgr.c @@ -0,0 +1,23 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (c) 2019, Microsoft Corporation. + * + * Author: + * Iouri Tarassov + * + * Dxgkrnl Graphics Driver + * Handle manager implementation + * + */ + +#include +#include +#include + +#include "misc.h" +#include "dxgkrnl.h" +#include "hmgr.h" + +#undef pr_fmt +#define pr_fmt(fmt) "dxgk: " fmt diff --git a/drivers/hv/dxgkrnl/hmgr.h b/drivers/hv/dxgkrnl/hmgr.h new file mode 100644 index 000000000000..b8b8f3ae5939 --- /dev/null +++ b/drivers/hv/dxgkrnl/hmgr.h @@ -0,0 +1,75 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Copyright (c) 2019, Microsoft Corporation. + * + * Author: + * Iouri Tarassov + * + * Dxgkrnl Graphics Driver + * Handle manager definitions + * + */ + +#ifndef _HMGR_H_ +#define _HMGR_H_ + +#include "misc.h" + +struct hmgrentry; + +/* + * Handle manager table. + * + * Implementation notes: + * A list of free handles is built on top of the array of table entries. + * free_handle_list_head is the index of the first entry in the list. + * m_FreeHandleListTail is the index of an entry in the list, which is + * HMGRTABLE_MIN_FREE_ENTRIES from the head. It means that when a handle= is + * freed, the next time the handle can be re-used is after allocating + * HMGRTABLE_MIN_FREE_ENTRIES number of handles. + * Handles are allocated from the start of the list and free handles are + * inserted after the tail of the list. + * + */ +struct hmgrtable { + struct dxgprocess *process; + struct hmgrentry *entry_table; + u32 free_handle_list_head; + u32 free_handle_list_tail; + u32 table_size; + u32 free_count; + struct rw_semaphore table_lock; +}; + +/* + * Handle entry data types. + */ +#define HMGRENTRY_TYPE_BITS 5 + +enum hmgrentry_type { + HMGRENTRY_TYPE_FREE =3D 0, + HMGRENTRY_TYPE_DXGADAPTER =3D 1, + HMGRENTRY_TYPE_DXGSHAREDRESOURCE =3D 2, + HMGRENTRY_TYPE_DXGDEVICE =3D 3, + HMGRENTRY_TYPE_DXGRESOURCE =3D 4, + HMGRENTRY_TYPE_DXGALLOCATION =3D 5, + HMGRENTRY_TYPE_DXGOVERLAY =3D 6, + HMGRENTRY_TYPE_DXGCONTEXT =3D 7, + HMGRENTRY_TYPE_DXGSYNCOBJECT =3D 8, + HMGRENTRY_TYPE_DXGKEYEDMUTEX =3D 9, + HMGRENTRY_TYPE_DXGPAGINGQUEUE =3D 10, + HMGRENTRY_TYPE_DXGDEVICESYNCOBJECT =3D 11, + HMGRENTRY_TYPE_DXGPROCESS =3D 12, + HMGRENTRY_TYPE_DXGSHAREDVMOBJECT =3D 13, + HMGRENTRY_TYPE_DXGPROTECTEDSESSION =3D 14, + HMGRENTRY_TYPE_DXGHWQUEUE =3D 15, + HMGRENTRY_TYPE_DXGREMOTEBUNDLEOBJECT =3D 16, + HMGRENTRY_TYPE_DXGCOMPOSITIONSURFACEOBJECT =3D 17, + HMGRENTRY_TYPE_DXGCOMPOSITIONSURFACEPROXY =3D 18, + HMGRENTRY_TYPE_DXGTRACKEDWORKLOAD =3D 19, + HMGRENTRY_TYPE_LIMIT =3D ((1 << HMGRENTRY_TYPE_BITS) - 1), + HMGRENTRY_TYPE_MONITOREDFENCE =3D HMGRENTRY_TYPE_LIMIT + 1, +}; + +#endif diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c new file mode 100644 index 000000000000..277e25e5d8c6 --- /dev/null +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -0,0 +1,24 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (c) 2019, Microsoft Corporation. + * + * Author: + * Iouri Tarassov + * + * Dxgkrnl Graphics Driver + * Ioctl implementation + * + */ + +#include +#include +#include +#include +#include + +#include "dxgkrnl.h" +#include "dxgvmbus.h" + +#undef pr_fmt +#define pr_fmt(fmt) "dxgk: " fmt diff --git a/drivers/hv/dxgkrnl/misc.c b/drivers/hv/dxgkrnl/misc.c new file mode 100644 index 000000000000..cb1e0635bebc --- /dev/null +++ b/drivers/hv/dxgkrnl/misc.c @@ -0,0 +1,37 @@ +// SPDX-License-Identifier: GPL-2.0 + +/* + * Copyright (c) 2019, Microsoft Corporation. + * + * Author: + * Iouri Tarassov + * + * Dxgkrnl Graphics Driver + * Helper functions + * + */ + +#include +#include +#include + +#include "dxgkrnl.h" +#include "misc.h" + +#undef pr_fmt +#define pr_fmt(fmt) "dxgk: " fmt + +u16 *wcsncpy(u16 *dest, const u16 *src, size_t n) +{ + int i; + + for (i =3D 0; i < n; i++) { + dest[i] =3D src[i]; + if (src[i] =3D=3D 0) { + i++; + break; + } + } + dest[i - 1] =3D 0; + return dest; +} diff --git a/drivers/hv/dxgkrnl/misc.h b/drivers/hv/dxgkrnl/misc.h new file mode 100644 index 000000000000..1ff0c0e28332 --- /dev/null +++ b/drivers/hv/dxgkrnl/misc.h @@ -0,0 +1,89 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +/* + * Copyright (c) 2019, Microsoft Corporation. + * + * Author: + * Iouri Tarassov + * + * Dxgkrnl Graphics Driver + * Misc definitions + * + */ + +#ifndef _MISC_H_ +#define _MISC_H_ + +/* Max characters in Windows path */ +#define WIN_MAX_PATH 260 + +extern const struct d3dkmthandle zerohandle; + +/* + * Synchronization lock hierarchy. + * + * The higher enum value, the higher is the lock order. + * When a lower lock ois held, the higher lock should not be acquired. + * + * channel_lock + * fd_mutex + * plistmutex + * table_lock + * core_lock + * device_lock + * process->process_mutex + * adapter_list_lock + * device_mutex + */ + +u16 *wcsncpy(u16 *dest, const u16 *src, size_t n); + +enum dxglockstate { + DXGLOCK_SHARED, + DXGLOCK_EXCL +}; + +/* + * Some of the Windows return codes, which needs to be translated to Linux + * IOCTL return codes. Positive values are success codes and need to be + * returned from the driver IOCTLs. libdxcore.so depends on returning + * specific return codes. + */ +#define STATUS_SUCCESS ((int)(0)) +#define STATUS_OBJECT_NAME_INVALID ((int)(0xC0000033L)) +#define STATUS_DEVICE_REMOVED ((int)(0xC00002B6L)) +#define STATUS_INVALID_HANDLE ((int)(0xC0000008L)) +#define STATUS_ILLEGAL_INSTRUCTION ((int)(0xC000001DL)) +#define STATUS_NOT_IMPLEMENTED ((int)(0xC0000002L)) +#define STATUS_PENDING ((int)(0x00000103L)) +#define STATUS_ACCESS_DENIED ((int)(0xC0000022L)) +#define STATUS_BUFFER_TOO_SMALL ((int)(0xC0000023L)) +#define STATUS_OBJECT_TYPE_MISMATCH ((int)(0xC0000024L)) +#define STATUS_GRAPHICS_ALLOCATION_BUSY ((int)(0xC01E0102L)) +#define STATUS_NOT_SUPPORTED ((int)(0xC00000BBL)) +#define STATUS_TIMEOUT ((int)(0x00000102L)) +#define STATUS_INVALID_PARAMETER ((int)(0xC000000DL)) +#define STATUS_NO_MEMORY ((int)(0xC0000017L)) +#define STATUS_OBJECT_NAME_COLLISION ((int)(0xC0000035L)) +#define STATUS_OBJECT_NAME_NOT_FOUND ((int)(0xC0000034L)) + + +#define NT_SUCCESS(status) (status.v >=3D 0) + +#ifndef DEBUG + +#define DXGKRNL_ASSERT(exp) + +#else + +#define DXGKRNL_ASSERT(exp) \ +do { \ + if (!(exp)) { \ + dump_stack(); \ + BUG_ON(true); \ + } \ +} while (0) + +#endif /* DEBUG */ + +#endif /* _MISC_H_ */ diff --git a/include/linux/hyperv.h b/include/linux/hyperv.h index b823311eac79..9d21055b003d 100644 --- a/include/linux/hyperv.h +++ b/include/linux/hyperv.h @@ -1414,6 +1414,22 @@ void vmbus_free_mmio(resource_size_t start, resource= _size_t size); .guid =3D GUID_INIT(0xda0a7802, 0xe377, 0x4aac, 0x8e, 0x77, \ 0x05, 0x58, 0xeb, 0x10, 0x73, 0xf8) =20 +/* + * GPU paravirtualization global DXGK channel + * {DDE9CBC0-5060-4436-9448-EA1254A5D177} + */ +#define HV_GPUP_DXGK_GLOBAL_GUID \ + .guid =3D GUID_INIT(0xdde9cbc0, 0x5060, 0x4436, 0x94, 0x48, \ + 0xea, 0x12, 0x54, 0xa5, 0xd1, 0x77) + +/* + * GPU paravirtualization per virtual GPU DXGK channel + * {6E382D18-3336-4F4B-ACC4-2B7703D4DF4A} + */ +#define HV_GPUP_DXGK_VGPU_GUID \ + .guid =3D GUID_INIT(0x6e382d18, 0x3336, 0x4f4b, 0xac, 0xc4, \ + 0x2b, 0x77, 0x3, 0xd4, 0xdf, 0x4a) + /* * Synthetic FC GUID * {2f9bcc4a-0069-4af3-b76b-6fd0be528cda} diff --git a/include/uapi/misc/d3dkmthk.h b/include/uapi/misc/d3dkmthk.h new file mode 100644 index 000000000000..6e5519d5dbc7 --- /dev/null +++ b/include/uapi/misc/d3dkmthk.h @@ -0,0 +1,1945 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ + +/* + * Copyright (c) 2019, Microsoft Corporation. + * + * Author: + * Iouri Tarassov + * + * Dxgkrnl Graphics Driver + * User mode WDDM interface definitions + * + */ + +#ifndef _D3DKMTHK_H +#define _D3DKMTHK_H + +/* + * This structure matches the definition of D3DKMTHANDLE in Windows. + * The handle is opaque in user mode. It is used by user mode applications= to + * represent kernel mode objects, created by dxgkrnl. + */ +struct d3dkmthandle { + union { + struct { + __u32 instance : 6; + __u32 index : 24; + __u32 unique : 2; + }; + __u32 v; + }; +}; + +/* + * VM bus messages return Windows' NTSTATUS, which is integer and only neg= ative + * value indicates a failure. A positive number is a success and needs to = be + * returned to user mode as the IOCTL return code. Negative status codes a= re + * converted to Linux error codes. + */ +struct ntstatus { + union { + struct { + int code : 16; + int facility : 13; + int customer : 1; + int severity : 2; + }; + int v; + }; +}; + +/* Matches Windows LUID definition */ +struct winluid { + __u32 a; + __u32 b; +}; + +#define D3DDDI_MAX_WRITTEN_PRIMARIES 16 +#define D3DDDI_MAX_MPO_PRESENT_DIRTY_RECTS 0xFFF + +#define D3DKMT_CREATEALLOCATION_MAX 1024 +#define D3DKMT_MAKERESIDENT_ALLOC_MAX (1024 * 10) +#define D3DKMT_ADAPTERS_MAX 64 +#define D3DDDI_MAX_BROADCAST_CONTEXT 64 +#define D3DDDI_MAX_OBJECT_WAITED_ON 32 +#define D3DDDI_MAX_OBJECT_SIGNALED 32 + +struct d3dkmt_adapterinfo { + struct d3dkmthandle adapter_handle; + struct winluid adapter_luid; + __u32 num_sources; + __u32 present_move_regions_preferred; +}; + +struct d3dkmt_enumadapters2 { + __u32 num_adapters; + __u32 reserved; +#ifdef __KERNEL__ + struct d3dkmt_adapterinfo *adapters; +#else + __u64 *adapters; +#endif +}; + +struct d3dkmt_closeadapter { + struct d3dkmthandle adapter_handle; +}; + +struct d3dkmt_openadapterfromluid { + struct winluid adapter_luid; + struct d3dkmthandle adapter_handle; +}; + +struct d3dddi_allocationlist { + struct d3dkmthandle allocation; + union { + struct { + __u32 write_operation :1; + __u32 do_not_retire_instance :1; + __u32 offer_priority :3; + __u32 reserved :27; + }; + __u32 value; + }; +}; + +struct d3dddi_patchlocationlist { + __u32 allocation_index; + union { + struct { + __u32 slot_id:24; + __u32 reserved:8; + }; + __u32 value; + }; + __u32 driver_id; + __u32 allocation_offset; + __u32 patch_offset; + __u32 split_offset; +}; + +struct d3dkmt_createdeviceflags { + __u32 legacy_mode:1; + __u32 request_vSync:1; + __u32 disable_gpu_timeout:1; + __u32 gdi_device:1; + __u32 reserved:28; +}; + +struct d3dkmt_createdevice { + struct d3dkmthandle adapter; + __u32 reserved3; + struct d3dkmt_createdeviceflags flags; + struct d3dkmthandle device; +#ifdef __KERNEL__ + void *command_buffer; +#else + __u64 command_buffer; +#endif + __u32 command_buffer_size; + __u32 reserved; +#ifdef __KERNEL__ + struct d3dddi_allocationlist *allocation_list; +#else + __u64 allocation_list; +#endif + __u32 allocation_list_size; + __u32 reserved1; +#ifdef __KERNEL__ + struct d3dddi_patchlocationlist *patch_location_list; +#else + __u64 patch_location_list; +#endif + __u32 patch_location_list_size; + __u32 reserved2; +}; + +struct d3dkmt_destroydevice { + struct d3dkmthandle device; +}; + +enum d3dkmt_clienthint { + _D3DKMT_CLIENTHNT_UNKNOWN =3D 0, + _D3DKMT_CLIENTHINT_OPENGL =3D 1, + _D3DKMT_CLIENTHINT_CDD =3D 2, + _D3DKMT_CLIENTHINT_DX7 =3D 7, + _D3DKMT_CLIENTHINT_DX8 =3D 8, + _D3DKMT_CLIENTHINT_DX9 =3D 9, + _D3DKMT_CLIENTHINT_DX10 =3D 10, +}; + +struct d3dddi_createcontextflags { + union { + struct { + __u32 null_rendering:1; + __u32 initial_data:1; + __u32 disable_gpu_timeout:1; + __u32 synchronization_only:1; + __u32 hw_queue_supported:1; + __u32 reserved:27; + }; + __u32 value; + }; +}; + +struct d3dkmt_createcontext { + struct d3dkmthandle device; + __u32 node_ordinal; + __u32 engine_affinity; + struct d3dddi_createcontextflags flags; +#ifdef __KERNEL__ + void *priv_drv_data; +#else + __u64 priv_drv_data; +#endif + __u32 priv_drv_data_size; + enum d3dkmt_clienthint client_hint; + struct d3dkmthandle context; +#ifdef __KERNEL__ + void *command_buffer; +#else + __u64 command_buffer; +#endif + __u32 command_buffer_size; +#ifdef __KERNEL__ + struct d3dddi_allocationlist *allocation_list; +#else + __u64 allocation_list; +#endif + __u32 allocation_list_size; +#ifdef __KERNEL__ + struct d3dddi_patchlocationlist *patch_location_list; +#else + __u64 patch_location_list; +#endif + __u32 patch_location_list_size; + __u64 obsolete; +}; + +struct d3dkmt_destroycontext { + struct d3dkmthandle context; +}; + +struct d3dkmt_createcontextvirtual { + struct d3dkmthandle device; + __u32 node_ordinal; + __u32 engine_affinity; + struct d3dddi_createcontextflags flags; +#ifdef __KERNEL__ + void *priv_drv_data; +#else + __u64 priv_drv_data; +#endif + __u32 priv_drv_data_size; + enum d3dkmt_clienthint client_hint; + struct d3dkmthandle context; +}; + +struct d3dddi_createhwcontextflags { + union { + struct { + __u32 reserved:32; + }; + __u32 value; + }; +}; + +struct d3dddi_createhwqueueflags { + union { + struct { + __u32 disable_gpu_timeout:1; + __u32 reserved:31; + }; + __u32 value; + }; +}; + +enum d3dddi_pagingqueue_priority { + _D3DDDI_PAGINGQUEUE_PRIORITY_BELOW_NORMAL =3D -1, + _D3DDDI_PAGINGQUEUE_PRIORITY_NORMAL =3D 0, + _D3DDDI_PAGINGQUEUE_PRIORITY_ABOVE_NORMAL =3D 1, +}; + +struct d3dkmt_createpagingqueue { + struct d3dkmthandle device; + enum d3dddi_pagingqueue_priority priority; + struct d3dkmthandle paging_queue; + struct d3dkmthandle sync_object; +#ifdef __KERNEL__ + void *fence_cpu_virtual_address; +#else + __u64 fence_cpu_virtual_address; +#endif + __u32 physical_adapter_index; +}; + +struct d3dddi_destroypagingqueue { + struct d3dkmthandle paging_queue; +}; + +struct d3dkmt_renderflags { + __u32 resize_command_buffer:1; + __u32 resize_allocation_list:1; + __u32 resize_patch_location_list:1; + __u32 null_rendering:1; + __u32 present_redirected:1; + __u32 render_km:1; + __u32 render_km_readback:1; + __u32 reserved:25; +}; +struct d3dkmt_render { + union { + struct d3dkmthandle device; + struct d3dkmthandle context; + }; + __u32 command_offset; + __u32 command_length; + __u32 allocation_count; + __u32 patch_location_count; +#ifdef __KERNEL__ + void *new_command_buffer; +#else + __u64 new_command_buffer; +#endif + __u32 new_command_buffer_size; +#ifdef __KERNEL__ + struct d3dddi_allocationlist *new_allocation_list; +#else + __u64 new_allocation_list; +#endif + __u32 new_allocation_list_size; +#ifdef __KERNEL__ + struct d3dddi_patchlocationlist *new_patch_pocation_list; +#else + __u64 new_patch_pocation_list; +#endif + __u32 new_patch_pocation_list_size; + struct d3dkmt_renderflags flags; + __u64 present_history_token; + __u32 broadcast_context_count; + struct d3dkmthandle broadcast_context[D3DDDI_MAX_BROADCAST_CONTEXT]; + __u32 queued_buffer_count; + __u64 obsolete; +#ifdef __KERNEL__ + void *priv_drv_data; +#else + __u64 priv_drv_data; +#endif + __u32 priv_drv_data_size; +}; + +enum d3dkmt_standardallocationtype { + _D3DKMT_STANDARDALLOCATIONTYPE_EXISTINGHEAP =3D 1, + _D3DKMT_STANDARDALLOCATIONTYPE_CROSSADAPTER =3D 2, +}; + +struct d3dkmt_standardallocation_existingheap { + __u64 size; +}; + +struct d3dkmt_createstandardallocationflags { + union { + struct { + __u32 reserved:32; + }; + __u32 value; + }; +}; + +struct d3dkmt_createstandardallocation { + enum d3dkmt_standardallocationtype type; + __u32 reserved; + struct d3dkmt_standardallocation_existingheap existing_heap_data; + struct d3dkmt_createstandardallocationflags flags; + __u32 reserved1; +}; + +struct d3dddi_allocationinfo2 { + struct d3dkmthandle allocation; +#ifdef __KERNEL__ + const void *sysmem; +#else + __u64 sysmem; +#endif +#ifdef __KERNEL__ + void *priv_drv_data; +#else + __u64 priv_drv_data; +#endif + __u32 priv_drv_data_size; + __u32 vidpn_source_id; + union { + struct { + __u32 primary:1; + __u32 stereo:1; + __u32 override_priority:1; + __u32 reserved:29; + }; + __u32 value; + } flags; + __u64 gpu_virtual_address; + union { + __u32 priority; + __u64 unused; + }; + __u64 reserved[5]; +}; + +struct d3dkmt_createallocationflags { + union { + struct { + __u32 create_resource:1; + __u32 create_shared:1; + __u32 non_secure:1; + __u32 create_protected:1; + __u32 restrict_shared_access:1; + __u32 existing_sysmem:1; + __u32 nt_security_sharing:1; + __u32 read_only:1; + __u32 create_write_combined:1; + __u32 create_cached:1; + __u32 swap_chain_back_buffer:1; + __u32 cross_adapter:1; + __u32 open_cross_adapter:1; + __u32 partial_shared_creation:1; + __u32 zeroed:1; + __u32 write_watch:1; + __u32 standard_allocation:1; + __u32 existing_section:1; + __u32 reserved:14; + }; + __u32 value; + }; +}; + +struct d3dkmt_createallocation { + struct d3dkmthandle device; + struct d3dkmthandle resource; + struct d3dkmthandle global_share; + __u32 reserved; +#ifdef __KERNEL__ + const void *private_runtime_data; +#else + __u64 private_runtime_data; +#endif + __u32 private_runtime_data_size; + __u32 reserved1; + union { +#ifdef __KERNEL__ + struct d3dkmt_createstandardallocation *standard_allocation; + const void *priv_drv_data; +#else + __u64 standard_allocation; + __u64 priv_drv_data; +#endif + }; + __u32 priv_drv_data_size; + __u32 alloc_count; +#ifdef __KERNEL__ + struct d3dddi_allocationinfo2 *allocation_info; +#else + __u64 allocation_info; +#endif + struct d3dkmt_createallocationflags flags; + __u32 reserved2; + __u64 private_runtime_resource_handle; +}; + +struct d3dddicb_destroyallocation2flags { + union { + struct { + __u32 assume_not_in_use:1; + __u32 synchronous_destroy:1; + __u32 reserved:29; + __u32 system_use_only:1; + }; + __u32 value; + }; +}; + +struct d3dkmt_destroyallocation2 { + struct d3dkmthandle device; + struct d3dkmthandle resource; +#ifdef __KERNEL__ + const struct d3dkmthandle *allocations; +#else + __u64 allocations; +#endif + __u32 alloc_count; + struct d3dddicb_destroyallocation2flags flags; +}; + +struct d3dddi_makeresident_flags { + union { + struct { + __u32 cant_trim_further:1; + __u32 must_succeed:1; + __u32 reserved:30; + }; + __u32 value; + }; +}; + +struct d3dddi_makeresident { + struct d3dkmthandle paging_queue; + __u32 alloc_count; +#ifdef __KERNEL__ + const struct d3dkmthandle *allocation_list; + const __u32 *priority_list; +#else + __u64 allocation_list; + __u64 priority_list; +#endif + struct d3dddi_makeresident_flags flags; + __u64 paging_fence_value; + __u64 num_bytes_to_trim; +}; + +struct d3dddi_evict_flags { + union { + struct { + __u32 evict_only_if_necessary:1; + __u32 not_written_to:1; + __u32 reserved:30; + }; + __u32 value; + }; +}; + +struct d3dkmt_evict { + struct d3dkmthandle device; + __u32 alloc_count; +#ifdef __KERNEL__ + const struct d3dkmthandle *allocations; +#else + __u64 allocations; +#endif + struct d3dddi_evict_flags flags; + __u32 reserved; + __u64 num_bytes_to_trim; +}; + +struct d3dddigpuva_protection_type { + union { + struct { + __u64 write:1; + __u64 execute:1; + __u64 zero:1; + __u64 no_access:1; + __u64 system_use_only:1; + __u64 reserved:59; + }; + __u64 value; + }; +}; + +enum d3dddi_updategpuvirtualaddress_operation_type { + _D3DDDI_UPDATEGPUVIRTUALADDRESS_MAP =3D 0, + _D3DDDI_UPDATEGPUVIRTUALADDRESS_UNMAP =3D 1, + _D3DDDI_UPDATEGPUVIRTUALADDRESS_COPY =3D 2, + _D3DDDI_UPDATEGPUVIRTUALADDRESS_MAP_PROTECT =3D 3, +}; + +struct d3dddi_updategpuvirtualaddress_operation { + enum d3dddi_updategpuvirtualaddress_operation_type operation; + union { + struct { + __u64 base_address; + __u64 size; + struct d3dkmthandle allocation; + __u64 allocation_offset; + __u64 allocation_size; + } map; + struct { + __u64 base_address; + __u64 size; + struct d3dkmthandle allocation; + __u64 allocation_offset; + __u64 allocation_size; + struct d3dddigpuva_protection_type protection; + __u64 driver_protection; + } map_protect; + struct { + __u64 base_address; + __u64 size; + struct d3dddigpuva_protection_type protection; + } unmap; + struct { + __u64 source_address; + __u64 size; + __u64 dest_address; + } copy; + }; +}; + +enum d3dddigpuva_reservation_type { + _D3DDDIGPUVA_RESERVE_NO_ACCESS =3D 0, + _D3DDDIGPUVA_RESERVE_ZERO =3D 1, + _D3DDDIGPUVA_RESERVE_NO_COMMIT =3D 2 +}; + +struct d3dkmt_updategpuvirtualaddress { + struct d3dkmthandle device; + struct d3dkmthandle context; + struct d3dkmthandle fence_object; + __u32 num_operations; +#ifdef __KERNEL__ + struct d3dddi_updategpuvirtualaddress_operation *operations; +#else + __u64 operations; +#endif + __u32 reserved0; + __u32 reserved1; + __u64 reserved2; + __u64 fence_value; + union { + struct { + __u32 do_not_wait:1; + __u32 reserved:31; + }; + __u32 value; + } flags; + __u32 reserved3; +}; + +struct d3dddi_mapgpuvirtualaddress { + struct d3dkmthandle paging_queue; + __u64 base_address; + __u64 minimum_address; + __u64 maximum_address; + struct d3dkmthandle allocation; + __u64 offset_in_pages; + __u64 size_in_pages; + struct d3dddigpuva_protection_type protection; + __u64 driver_protection; + __u32 reserved0; + __u64 reserved1; + __u64 virtual_address; + __u64 paging_fence_value; +}; + +struct d3dddi_reservegpuvirtualaddress { + struct d3dkmthandle adapter; + __u64 base_address; + __u64 minimum_address; + __u64 maximum_address; + __u64 size; + enum d3dddigpuva_reservation_type reservation_type; + __u64 driver_protection; + __u64 virtual_address; + __u64 paging_fence_value; +}; + +struct d3dkmt_freegpuvirtualaddress { + struct d3dkmthandle adapter; + __u32 reserved; + __u64 base_address; + __u64 size; +}; + +enum d3dkmt_memory_segment_group { + _D3DKMT_MEMORY_SEGMENT_GROUP_LOCAL =3D 0, + _D3DKMT_MEMORY_SEGMENT_GROUP_NON_LOCAL =3D 1 +}; + +struct d3dkmt_queryvideomemoryinfo { + __u64 process; + struct d3dkmthandle adapter; + enum d3dkmt_memory_segment_group memory_segment_group; + __u64 budget; + __u64 current_usage; + __u64 current_reservation; + __u64 available_for_reservation; + __u32 physical_adapter_index; +}; + +struct d3dkmt_adaptertype { + union { + struct { + __u32 render_supported:1; + __u32 display_supported:1; + __u32 software_device:1; + __u32 post_device:1; + __u32 hybrid_discrete:1; + __u32 hybrid_integrated:1; + __u32 indirect_display_device:1; + __u32 paravirtualized:1; + __u32 acg_supported:1; + __u32 support_set_timings_from_vidpn:1; + __u32 detachable:1; + __u32 compute_only:1; + __u32 prototype:1; + __u32 reserved:19; + }; + __u32 value; + }; +}; + +enum kmtqueryadapterinfotype { + _KMTQAITYPE_UMDRIVERPRIVATE =3D 0, + _KMTQAITYPE_ADAPTERTYPE =3D 15, + _KMTQAITYPE_ADAPTERTYPE_RENDER =3D 57 +}; + +struct d3dkmt_queryadapterinfo { + struct d3dkmthandle adapter; + enum kmtqueryadapterinfotype type; +#ifdef __KERNEL__ + void *private_data; +#else + __u64 private_data; +#endif + __u32 private_data_size; +}; + +enum d3dkmt_escapetype { + _D3DKMT_ESCAPE_DRIVERPRIVATE =3D 0, + _D3DKMT_ESCAPE_VIDMM =3D 1, + _D3DKMT_ESCAPE_VIDSCH =3D 3, + _D3DKMT_ESCAPE_DEVICE =3D 4, + _D3DKMT_ESCAPE_DRT_TEST =3D 8, +}; + +enum d3dkmt_drt_test_command { + _D3DKMT_DRT_TEST_COMMAND_HANDLETABLE =3D 39, +}; + +struct d3dkmt_drt_escape_head { + __u32 signature; + __u32 buffer_size; + enum d3dkmt_drt_test_command command; +}; + +enum d3dkmt_ht_command { + _D3DKMT_HT_COMMAND_ALLOC, + _D3DKMT_HT_COMMAND_FREE, + _D3DKMT_HT_COMMAND_ASSIGN, + _D3DKMT_HT_COMMAND_GET, + _D3DKMT_HT_COMMAND_DESTROY, +}; + +struct d3dkmt_ht_desc { + struct d3dkmt_drt_escape_head head; + enum d3dkmt_ht_command command; + __u32 index; + struct d3dkmthandle handle; + __u32 object_type; +#ifdef __KERNEL__ + void *object; +#else + __u64 object; +#endif +}; + +struct d3dddi_escapeflags { + union { + struct { + __u32 hardware_access:1; + __u32 device_status_query:1; + __u32 change_frame_latency:1; + __u32 no_adapter_synchronization:1; + __u32 reserved:1; + __u32 virtual_machine_data:1; + __u32 driver_known_escape:1; + __u32 driver_common_escape:1; + __u32 reserved2:24; + }; + __u32 value; + }; +}; + +struct d3dkmt_escape { + struct d3dkmthandle adapter; + struct d3dkmthandle device; + enum d3dkmt_escapetype type; + struct d3dddi_escapeflags flags; +#ifdef __KERNEL__ + void *priv_drv_data; +#else + __u64 priv_drv_data; +#endif + __u32 priv_drv_data_size; + struct d3dkmthandle context; +}; + +enum dxgk_render_pipeline_stage { + _DXGK_RENDER_PIPELINE_STAGE_UNKNOWN =3D 0, + _DXGK_RENDER_PIPELINE_STAGE_INPUT_ASSEMBLER =3D 1, + _DXGK_RENDER_PIPELINE_STAGE_VERTEX_SHADER =3D 2, + _DXGK_RENDER_PIPELINE_STAGE_GEOMETRY_SHADER =3D 3, + _DXGK_RENDER_PIPELINE_STAGE_STREAM_OUTPUT =3D 4, + _DXGK_RENDER_PIPELINE_STAGE_RASTERIZER =3D 5, + _DXGK_RENDER_PIPELINE_STAGE_PIXEL_SHADER =3D 6, + _DXGK_RENDER_PIPELINE_STAGE_OUTPUT_MERGER =3D 7, +}; + +enum dxgk_page_fault_flags { + _DXGK_PAGE_FAULT_WRITE =3D 0x1, + _DXGK_PAGE_FAULT_FENCE_INVALID =3D 0x2, + _DXGK_PAGE_FAULT_ADAPTER_RESET_REQUIRED =3D 0x4, + _DXGK_PAGE_FAULT_ENGINE_RESET_REQUIRED =3D 0x8, + _DXGK_PAGE_FAULT_FATAL_HARDWARE_ERROR =3D 0x10, + _DXGK_PAGE_FAULT_IOMMU =3D 0x20, + _DXGK_PAGE_FAULT_HW_CONTEXT_VALID =3D 0x40, + _DXGK_PAGE_FAULT_PROCESS_HANDLE_VALID =3D 0x80, +}; + +enum dxgk_general_error_code { + _DXGK_GENERAL_ERROR_PAGE_FAULT =3D 0, + _DXGK_GENERAL_ERROR_INVALID_INSTRUCTION =3D 1, +}; + +struct dxgk_fault_error_code { + union { + struct { + __u32 is_device_specific_code:1; + enum dxgk_general_error_code general_error_code:31; + }; + struct { + __u32 is_device_specific_code_reserved_bit:1; + __u32 device_specific_code:31; + }; + }; +}; + +enum d3dkmt_deviceexecution_state { + _D3DKMT_DEVICEEXECUTION_ACTIVE =3D 1, + _D3DKMT_DEVICEEXECUTION_RESET =3D 2, + _D3DKMT_DEVICEEXECUTION_HUNG =3D 3, + _D3DKMT_DEVICEEXECUTION_STOPPED =3D 4, + _D3DKMT_DEVICEEXECUTION_ERROR_OUTOFMEMORY =3D 5, + _D3DKMT_DEVICEEXECUTION_ERROR_DMAFAULT =3D 6, + _D3DKMT_DEVICEEXECUTION_ERROR_DMAPAGEFAULT =3D 7, +}; + +struct d3dkmt_devicereset_state { + union { + struct { + __u32 desktop_switched:1; + __u32 reserved:31; + }; + __u32 value; + }; +}; + +struct d3dkmt_present_stats { + __u32 present_count; + __u32 present_refresh_count; + __u32 sync_refresh_count; + __u32 reserved; + __u64 sync_qpc_time; + __u64 sync_gpu_time; +}; + +struct d3dkmt_devicepresent_state { + __u32 vidpn_source_id; + __u32 reserved; + struct d3dkmt_present_stats present_stats; +}; + +struct d3dkmt_present_stats_dwm { + __u32 present_count; + __u32 present_refresh_count; + __u64 present_qpc_time; + __u32 sync_refresh_count; + __u32 reserved; + __u64 sync_qpc_time; + __u32 custom_present_duration; + __u32 reserved1; +}; + +struct d3dkmt_devicepagefault_state { + __u64 faulted_primitive_api_sequence_number; + enum dxgk_render_pipeline_stage faulted_pipeline_stage; + __u32 faulted_bind_table_entry; + enum dxgk_page_fault_flags page_fault_flags; + struct dxgk_fault_error_code fault_error_code; + __u64 faulted_virtual_address; +}; + +struct d3dkmt_devicepresent_state_dwm { + __u32 vidpn_source_id; + __u32 reserved; + struct d3dkmt_present_stats_dwm present_stats; +}; + +struct d3dkmt_devicepresent_queue_state { + __u32 vidpn_source_id; + bool bQueuedPresentLimitReached; +}; + +enum d3dkmt_devicestate_type { + _D3DKMT_DEVICESTATE_EXECUTION =3D 1, + _D3DKMT_DEVICESTATE_PRESENT =3D 2, + _D3DKMT_DEVICESTATE_RESET =3D 3, + _D3DKMT_DEVICESTATE_PRESENT_DWM =3D 4, + _D3DKMT_DEVICESTATE_PAGE_FAULT =3D 5, + _D3DKMT_DEVICESTATE_PRESENT_QUEUE =3D 6, +}; + +struct d3dkmt_getdevicestate { + struct d3dkmthandle device; + enum d3dkmt_devicestate_type state_type; + union { + enum d3dkmt_deviceexecution_state execution_state; + struct d3dkmt_devicepresent_state present_state; + struct d3dkmt_devicereset_state reset_state; + struct d3dkmt_devicepresent_state_dwm present_state_dwm; + struct d3dkmt_devicepagefault_state page_fault_state; + struct d3dkmt_devicepresent_queue_state present_queue_state; + }; +}; + +enum d3dkmdt_gdisurfacetype { + _D3DKMDT_GDISURFACE_INVALID =3D 0, + _D3DKMDT_GDISURFACE_TEXTURE =3D 1, + _D3DKMDT_GDISURFACE_STAGING_CPUVISIBLE =3D 2, + _D3DKMDT_GDISURFACE_STAGING =3D 3, + _D3DKMDT_GDISURFACE_LOOKUPTABLE =3D 4, + _D3DKMDT_GDISURFACE_EXISTINGSYSMEM =3D 5, + _D3DKMDT_GDISURFACE_TEXTURE_CPUVISIBLE =3D 6, + _D3DKMDT_GDISURFACE_TEXTURE_CROSSADAPTER =3D 7, + _D3DKMDT_GDISURFACE_TEXTURE_CPUVISIBLE_CROSSADAPTER =3D 8, +}; + +struct d3dddi_rational { + __u32 numerator; + __u32 denominator; +}; + +enum d3dddiformat { + _D3DDDIFMT_UNKNOWN =3D 0, +}; + +struct d3dkmdt_gdisurfacedata { + __u32 width; + __u32 height; + __u32 format; + enum d3dkmdt_gdisurfacetype type; + __u32 flags; + __u32 pitch; +}; + +struct d3dkmdt_stagingsurfacedata { + __u32 width; + __u32 height; + __u32 pitch; +}; + +struct d3dkmdt_sharedprimarysurfacedata { + __u32 width; + __u32 height; + enum d3dddiformat format; + struct d3dddi_rational refresh_rate; + __u32 vidpn_source_id; +}; + +struct d3dkmdt_shadowsurfacedata { + __u32 width; + __u32 height; + enum d3dddiformat format; + __u32 pitch; +}; + +enum d3dkmdt_standardallocationtype { + _D3DKMDT_STANDARDALLOCATION_SHAREDPRIMARYSURFACE =3D 1, + _D3DKMDT_STANDARDALLOCATION_SHADOWSURFACE =3D 2, + _D3DKMDT_STANDARDALLOCATION_STAGINGSURFACE =3D 3, + _D3DKMDT_STANDARDALLOCATION_GDISURFACE =3D 4, +}; + +struct d3dddi_synchronizationobject_flags { + union { + struct { + __u32 shared:1; + __u32 nt_security_sharing:1; + __u32 cross_adapter:1; + __u32 top_of_pipeline:1; + __u32 no_signal:1; + __u32 no_wait:1; + __u32 no_signal_max_value_on_tdr:1; + __u32 no_gpu_access:1; + __u32 reserved:23; + }; + __u32 value; + }; +}; + +enum d3dddi_synchronizationobject_type { + _D3DDDI_SYNCHRONIZATION_MUTEX =3D 1, + _D3DDDI_SEMAPHORE =3D 2, + _D3DDDI_FENCE =3D 3, + _D3DDDI_CPU_NOTIFICATION =3D 4, + _D3DDDI_MONITORED_FENCE =3D 5, + _D3DDDI_PERIODIC_MONITORED_FENCE =3D 6, + _D3DDDI_SYNCHRONIZATION_TYPE_LIMIT +}; + +struct d3dddi_synchronizationobjectinfo2 { + enum d3dddi_synchronizationobject_type type; + struct d3dddi_synchronizationobject_flags flags; + union { + struct { + __u32 initial_state; + } synchronization_mutex; + + struct { + __u32 max_count; + __u32 initial_count; + } semaphore; + + struct { + __u64 fence_value; + } fence; + + struct { + __u64 event; + } cpu_notification; + + struct { + __u64 initial_fence_value; +#ifdef __KERNEL__ + void *fence_cpu_virtual_address; +#else + __u64 *fence_cpu_virtual_address; +#endif + __u64 fence_gpu_virtual_address; + __u32 engine_affinity; + } monitored_fence; + + struct { + struct d3dkmthandle adapter; + __u32 vidpn_target_id; + __u64 time; +#ifdef __KERNEL__ + void *fence_cpu_virtual_address; +#else + __u64 fence_cpu_virtual_address; +#endif + __u64 fence_gpu_virtual_address; + __u32 engine_affinity; + } periodic_monitored_fence; + + struct { + __u64 reserved[8]; + } reserved; + }; + struct d3dkmthandle shared_handle; +}; + +struct d3dkmt_createsynchronizationobject2 { + struct d3dkmthandle device; + __u32 reserved; + struct d3dddi_synchronizationobjectinfo2 info; + struct d3dkmthandle sync_object; + __u32 reserved1; +}; + +struct d3dkmt_waitforsynchronizationobject2 { + struct d3dkmthandle context; + __u32 object_count; + struct d3dkmthandle object_array[D3DDDI_MAX_OBJECT_WAITED_ON]; + union { + struct { + __u64 fence_value; + } fence; + __u64 reserved[8]; + }; +}; + +struct d3dddicb_signalflags { + union { + struct { + __u32 signal_at_submission:1; + __u32 enqueue_cpu_event:1; + __u32 allow_fence_rewind:1; + __u32 reserved:28; + __u32 DXGK_SIGNAL_FLAG_INTERNAL0:1; + }; + __u32 value; + }; +}; + +struct d3dkmt_signalsynchronizationobject2 { + struct d3dkmthandle context; + __u32 object_count; + struct d3dkmthandle object_array[D3DDDI_MAX_OBJECT_SIGNALED]; + struct d3dddicb_signalflags flags; + __u32 context_count; + struct d3dkmthandle contexts[D3DDDI_MAX_BROADCAST_CONTEXT]; + union { + struct { + __u64 fence_value; + } fence; + __u64 cpu_event_handle; + __u64 reserved[8]; + }; +}; + +struct d3dddi_waitforsynchronizationobjectfromcpu_flags { + union { + struct { + __u32 wait_any:1; + __u32 reserved:31; + }; + __u32 value; + }; +}; + +struct d3dkmt_waitforsynchronizationobjectfromcpu { + struct d3dkmthandle device; + __u32 object_count; +#ifdef __KERNEL__ + struct d3dkmthandle *objects; + __u64 *fence_values; +#else + __u64 objects; + __u64 fence_values; +#endif + __u64 async_event; + struct d3dddi_waitforsynchronizationobjectfromcpu_flags flags; +}; + +struct d3dkmt_signalsynchronizationobjectfromcpu { + struct d3dkmthandle device; + __u32 object_count; +#ifdef __KERNEL__ + struct d3dkmthandle *objects; + __u64 *fence_values; +#else + __u64 objects; + __u64 fence_values; +#endif + struct d3dddicb_signalflags flags; +}; + +struct d3dkmt_waitforsynchronizationobjectfromgpu { + struct d3dkmthandle context; + __u32 object_count; +#ifdef __KERNEL__ + struct d3dkmthandle *objects; +#else + __u64 objects; +#endif + union { +#ifdef __KERNEL__ + __u64 *monitored_fence_values; +#else + __u64 monitored_fence_values; +#endif + __u64 fence_value; + __u64 reserved[8]; + }; +}; + +struct d3dkmt_signalsynchronizationobjectfromgpu { + struct d3dkmthandle context; + __u32 object_count; +#ifdef __KERNEL__ + struct d3dkmthandle *objects; +#else + __u64 objects; +#endif + union { +#ifdef __KERNEL__ + __u64 *monitored_fence_values; +#else + __u64 monitored_fence_values; +#endif + __u64 reserved[8]; + }; +}; + +struct d3dkmt_signalsynchronizationobjectfromgpu2 { + __u32 object_count; + __u32 reserved1; +#ifdef __KERNEL__ + struct d3dkmthandle *objects; +#else + __u64 objects; +#endif + struct d3dddicb_signalflags flags; + __u32 context_count; +#ifdef __KERNEL__ + struct d3dkmthandle *contexts; +#else + __u64 contexts; +#endif + union { + __u64 fence_value; + __u64 cpu_event_handle; +#ifdef __KERNEL__ + __u64 *monitored_fence_values; +#else + __u64 monitored_fence_values; +#endif + __u64 reserved[8]; + }; +}; + +struct d3dkmt_destroysynchronizationobject { + struct d3dkmthandle sync_object; +}; + +struct d3dkmt_opensynchronizationobject { + struct d3dkmthandle shared_handle; + struct d3dkmthandle sync_object; + __u64 reserved[8]; +}; + +struct d3dkmt_submitcommandflags { + __u32 null_rendering:1; + __u32 present_redirected:1; + __u32 reserved:30; +}; + +struct d3dkmt_submitcommand { + __u64 command_buffer; + __u32 command_length; + struct d3dkmt_submitcommandflags flags; + __u64 present_history_token; + __u32 broadcast_context_count; + struct d3dkmthandle broadcast_context[D3DDDI_MAX_BROADCAST_CONTEXT]; + __u32 reserved; +#ifdef __KERNEL__ + void *priv_drv_data; +#else + __u64 priv_drv_data; +#endif + __u32 priv_drv_data_size; + __u32 num_primaries; + struct d3dkmthandle written_primaries[D3DDDI_MAX_WRITTEN_PRIMARIES]; + __u32 num_history_buffers; + __u32 reserved1; +#ifdef __KERNEL__ + struct d3dkmthandle *history_buffer_array; +#else + __u64 history_buffer_array; +#endif +}; + +struct d3dkmt_submitcommandtohwqueue { + struct d3dkmthandle hwqueue; + __u32 reserved; + __u64 hwqueue_progress_fence_id; + __u64 command_buffer; + __u32 command_length; + __u32 priv_drv_data_size; +#ifdef __KERNEL__ + void *priv_drv_data; +#else + __u64 priv_drv_data; +#endif + __u32 num_primaries; + __u32 reserved1; +#ifdef __KERNEL__ + struct d3dkmthandle *written_primaries; +#else + __u64 written_primaries; +#endif +}; + +struct d3dkmt_setcontextschedulingpriority { + struct d3dkmthandle context; + int priority; +}; + +struct d3dkmt_setcontextinprocessschedulingpriority { + struct d3dkmthandle context; + int priority; +}; + +struct d3dkmt_getcontextschedulingpriority { + struct d3dkmthandle context; + int priority; +}; + +struct d3dkmt_getcontextinprocessschedulingpriority { + struct d3dkmthandle context; + int priority; +}; + +struct d3dkmt_setallocationpriority { + struct d3dkmthandle device; + struct d3dkmthandle resource; +#ifdef __KERNEL__ + const struct d3dkmthandle *allocation_list; +#else + __u64 allocation_list; +#endif + __u32 allocation_count; + __u32 reserved; +#ifdef __KERNEL__ + const __u32 *priorities; +#else + __u64 priorities; +#endif +}; + +struct d3dkmt_getallocationpriority { + struct d3dkmthandle device; + struct d3dkmthandle resource; +#ifdef __KERNEL__ + const struct d3dkmthandle *allocation_list; +#else + __u64 allocation_list; +#endif + __u32 allocation_count; + __u32 reserved; +#ifdef __KERNEL__ + __u32 *priorities; +#else + __u64 priorities; +#endif +}; + +enum d3dkmt_allocationresidencystatus { + _D3DKMT_ALLOCATIONRESIDENCYSTATUS_RESIDENTINGPUMEMORY =3D 1, + _D3DKMT_ALLOCATIONRESIDENCYSTATUS_RESIDENTINSHAREDMEMORY =3D 2, + _D3DKMT_ALLOCATIONRESIDENCYSTATUS_NOTRESIDENT =3D 3, +}; + +struct d3dkmt_queryallocationresidency { + struct d3dkmthandle device; + struct d3dkmthandle resource; +#ifdef __KERNEL__ + struct d3dkmthandle *allocations; +#else + __u64 allocations; +#endif + __u32 allocation_count; + __u32 reserved; +#ifdef __KERNEL__ + enum d3dkmt_allocationresidencystatus *residency_status; +#else + __u64 residency_status; +#endif +}; + +struct d3dddicb_lock2flags { + union { + struct { + __u32 reserved:32; + }; + __u32 value; + }; +}; + +struct d3dkmt_lock2 { + struct d3dkmthandle device; + struct d3dkmthandle allocation; + struct d3dddicb_lock2flags flags; + __u32 reserved; +#ifdef __KERNEL__ + void *data; +#else + __u64 data; +#endif +}; + +struct d3dkmt_unlock2 { + struct d3dkmthandle device; + struct d3dkmthandle allocation; +}; + +enum d3dkmt_device_error_reason { + _D3DKMT_DEVICE_ERROR_REASON_GENERIC =3D 0x80000000, + _D3DKMT_DEVICE_ERROR_REASON_DRIVER_ERROR =3D 0x80000006, +}; + +struct d3dkmt_markdeviceaserror { + struct d3dkmthandle device; + enum d3dkmt_device_error_reason reason; +}; + +struct d3dddi_updateallocproperty_flags { + union { + struct { + __u32 accessed_physically:1; + __u32 reserved:31; + }; + __u32 value; + }; +}; + +struct d3dddi_segmentpreference { + union { + struct { + __u32 segment_id0:5; + __u32 direction0:1; + __u32 segment_id1:5; + __u32 direction1:1; + __u32 segment_id2:5; + __u32 direction2:1; + __u32 segment_id3:5; + __u32 direction3:1; + __u32 segment_id4:5; + __u32 direction4:1; + __u32 reserved:2; + }; + __u32 value; + }; +}; + +struct d3dddi_updateallocproperty { + struct d3dkmthandle paging_queue; + struct d3dkmthandle allocation; + __u32 supported_segment_set; + struct d3dddi_segmentpreference preferred_segment; + struct d3dddi_updateallocproperty_flags flags; + __u64 paging_fence_value; + union { + struct { + __u32 set_accessed_physically:1; + __u32 set_supported_segmentSet:1; + __u32 set_preferred_segment:1; + __u32 reserved:29; + }; + __u32 property_mask_value; + }; +}; + +enum d3dkmt_offer_priority { + _D3DKMT_OFFER_PRIORITY_LOW =3D 1, + _D3DKMT_OFFER_PRIORITY_NORMAL =3D 2, + _D3DKMT_OFFER_PRIORITY_HIGH =3D 3, + _D3DKMT_OFFER_PRIORITY_AUTO =3D 4, +}; + +struct d3dkmt_offer_flags { + union { + struct { + __u32 offer_immediately:1; + __u32 allow_decommit:1; + __u32 reserved:30; + }; + __u32 value; + }; +}; + +struct d3dkmt_offerallocations { + struct d3dkmthandle device; + __u32 reserved; +#ifdef __KERNEL__ + struct d3dkmthandle *resources; + const struct d3dkmthandle *allocations; +#else + __u64 resources; + __u64 allocations; +#endif + __u32 allocation_count; + enum d3dkmt_offer_priority priority; + struct d3dkmt_offer_flags flags; + __u32 reserved1; +}; + +enum d3dddi_reclaim_result { + _D3DDDI_RECLAIM_RESULT_OK =3D 0, + _D3DDDI_RECLAIM_RESULT_DISCARDED =3D 1, + _D3DDDI_RECLAIM_RESULT_NOT_COMMITTED =3D 2, +}; + +struct d3dkmt_reclaimallocations2 { + struct d3dkmthandle paging_queue; + __u32 allocation_count; +#ifdef __KERNEL__ + struct d3dkmthandle *resources; + struct d3dkmthandle *allocations; +#else + __u64 resources; + __u64 allocations; +#endif + union { +#ifdef __KERNEL__ + __u32 *discarded; + enum d3dddi_reclaim_result *results; +#else + __u64 discarded; + __u64 results; +#endif + }; + __u64 paging_fence_value; +}; + +struct d3dkmt_changevideomemoryreservation { + __u64 process; + struct d3dkmthandle adapter; + enum d3dkmt_memory_segment_group memory_segment_group; + __u64 reservation; + __u32 physical_adapter_index; +}; + +struct d3dkmt_createhwcontext { + struct d3dkmthandle device; + __u32 node_ordinal; + __u32 engine_affinity; + struct d3dddi_createhwcontextflags flags; + __u32 priv_drv_data_size; +#ifdef __KERNEL__ + void *priv_drv_data; +#else + __u64 priv_drv_data; +#endif + struct d3dkmthandle context; +}; + +struct d3dkmt_destroyhwcontext { + struct d3dkmthandle context; +}; + +struct d3dkmt_createhwqueue { + struct d3dkmthandle context; + struct d3dddi_createhwqueueflags flags; + __u32 priv_drv_data_size; + __u32 reserved; +#ifdef __KERNEL__ + void *priv_drv_data; +#else + __u64 priv_drv_data; +#endif + struct d3dkmthandle queue; + struct d3dkmthandle queue_progress_fence; +#ifdef __KERNEL__ + void *queue_progress_fence_cpu_va; +#else + __u64 queue_progress_fence_cpu_va; +#endif + __u64 queue_progress_fence_gpu_va; +}; + +struct d3dkmt_destroyhwqueue { + struct d3dkmthandle queue; +}; + +struct d3dkmt_submitwaitforsyncobjectstohwqueue { + struct d3dkmthandle hwqueue; + __u32 object_count; +#ifdef __KERNEL__ + struct d3dkmthandle *objects; + __u64 *fence_values; +#else + __u64 objects; + __u64 fence_values; +#endif +}; + +struct d3dkmt_submitsignalsyncobjectstohwqueue { + struct d3dddicb_signalflags flags; + __u32 hwqueue_count; +#ifdef __KERNEL__ + struct d3dkmthandle *hwqueues; +#else + __u64 hwqueues; +#endif + __u32 object_count; + __u32 reserved; +#ifdef __KERNEL__ + struct d3dkmthandle *objects; + __u64 *fence_values; +#else + __u64 objects; + __u64 fence_values; +#endif +}; + +#pragma pack(push, 1) + +struct dxgk_gpuclockdata_flags { + union { + struct { + __u32 context_management_processor:1; + __u32 reserved:31; + }; + __u32 value; + }; +}; + +struct dxgk_gpuclockdata { + __u64 gpu_frequency; + __u64 gpu_clock_counter; + __u64 cpu_clock_counter; + struct dxgk_gpuclockdata_flags flags; +} __packed; + +struct d3dkmt_queryclockcalibration { + struct d3dkmthandle adapter; + __u32 node_ordinal; + __u32 physical_adapter_index; + struct dxgk_gpuclockdata clock_data; +}; + +#pragma pack(pop) + +struct d3dkmt_flushheaptransitions { + struct d3dkmthandle adapter; +}; + +struct d3dkmt_getsharedresourceadapterluid { + struct d3dkmthandle global_share; + __u64 handle; + struct winluid adapter_luid; +}; + +struct d3dkmt_invalidatecache { + struct d3dkmthandle device; + struct d3dkmthandle allocation; + __u64 offset; + __u64 length; +}; + +struct d3dddi_openallocationinfo2 { + struct d3dkmthandle allocation; +#ifdef __KERNEL__ + void *priv_drv_data; +#else + __u64 priv_drv_data; +#endif + __u32 priv_drv_data_size; + __u64 gpu_va; + __u64 reserved[6]; +}; + +struct d3dkmt_opensyncobjectfromnthandle { + __u64 nt_handle; + struct d3dkmthandle sync_object; +}; + +struct d3dkmt_opensyncobjectfromnthandle2 { + __u64 nt_handle; + struct d3dkmthandle device; + struct d3dddi_synchronizationobject_flags flags; + struct d3dkmthandle sync_object; + __u32 reserved1; + union { + struct { +#ifdef __KERNEL__ + void *fence_value_cpu_va; +#else + __u64 fence_value_cpu_va; +#endif + __u64 fence_value_gpu_va; + __u32 engine_affinity; + } monitored_fence; + __u64 reserved[8]; + }; +}; + +struct d3dkmt_openresource { + struct d3dkmthandle device; + struct d3dkmthandle global_share; + __u32 allocation_count; +#ifdef __KERNEL__ + struct d3dddi_openallocationinfo2 *open_alloc_info; + void *private_runtime_data; +#else + __u64 open_alloc_info; + __u64 private_runtime_data; +#endif + int private_runtime_data_size; +#ifdef __KERNEL__ + void *resource_priv_drv_data; +#else + __u64 resource_priv_drv_data; +#endif + __u32 resource_priv_drv_data_size; +#ifdef __KERNEL__ + void *total_priv_drv_data; +#else + __u64 total_priv_drv_data; +#endif + __u32 total_priv_drv_data_size; + struct d3dkmthandle resource; +}; + +struct d3dkmt_openresourcefromnthandle { + struct d3dkmthandle device; + __u32 reserved; + __u64 nt_handle; + __u32 allocation_count; + __u32 reserved1; +#ifdef __KERNEL__ + struct d3dddi_openallocationinfo2 *open_alloc_info; +#else + __u64 open_alloc_info; +#endif + int private_runtime_data_size; + __u32 reserved2; +#ifdef __KERNEL__ + void *private_runtime_data; +#else + __u64 private_runtime_data; +#endif + __u32 resource_priv_drv_data_size; + __u32 reserved3; +#ifdef __KERNEL__ + void *resource_priv_drv_data; +#else + __u64 resource_priv_drv_data; +#endif + __u32 total_priv_drv_data_size; +#ifdef __KERNEL__ + void *total_priv_drv_data; +#else + __u64 total_priv_drv_data; +#endif + struct d3dkmthandle resource; + struct d3dkmthandle keyed_mutex; +#ifdef __KERNEL__ + void *keyed_mutex_private_data; +#else + __u64 keyed_mutex_private_data; +#endif + __u32 keyed_mutex_private_data_size; + struct d3dkmthandle sync_object; +}; + +struct d3dkmt_queryresourceinfofromnthandle { + struct d3dkmthandle device; + __u32 reserved; + __u64 nt_handle; +#ifdef __KERNEL__ + void *private_runtime_data; +#else + __u64 private_runtime_data; +#endif + __u32 private_runtime_data_size; + __u32 total_priv_drv_data_size; + __u32 resource_priv_drv_data_size; + __u32 allocation_count; +}; + +struct d3dkmt_queryresourceinfo { + struct d3dkmthandle device; + struct d3dkmthandle global_share; +#ifdef __KERNEL__ + void *private_runtime_data; +#else + __u64 private_runtime_data; +#endif + __u32 private_runtime_data_size; + __u32 total_priv_drv_data_size; + __u32 resource_priv_drv_data_size; + __u32 allocation_count; +}; + +struct d3dkmt_shareobjects { + __u32 object_count; + __u32 reserved; +#ifdef __KERNEL__ + const struct d3dkmthandle *objects; + void *object_attr; /* security attributes */ +#else + __u64 objects; + __u64 object_attr; +#endif + __u32 desired_access; + __u32 reserved1; +#ifdef __KERNEL__ + __u64 *shared_handle; /* output file descriptors */ +#else + __u64 shared_handle; +#endif +}; + +union d3dkmt_enumadapters_filter { + struct { + __u64 include_compute_only:1; + __u64 include_display_only:1; + __u64 reserved:62; + }; + __u64 value; +}; + +struct d3dkmt_enumadapters3 { + union d3dkmt_enumadapters_filter filter; + __u32 adapter_count; + __u32 reserved; +#ifdef __KERNEL__ + struct d3dkmt_adapterinfo *adapters; +#else + __u64 adapters; +#endif +}; + +enum d3dkmt_querystatistics_type { + _D3DKMT_QUERYSTATISTICS_ADAPTER =3D 0, + _D3DKMT_QUERYSTATISTICS_PROCESS =3D 1, + _D3DKMT_QUERYSTATISTICS_PROCESS_ADAPTER =3D 2, + _D3DKMT_QUERYSTATISTICS_SEGMENT =3D 3, + _D3DKMT_QUERYSTATISTICS_PROCESS_SEGMENT =3D 4, + _D3DKMT_QUERYSTATISTICS_NODE =3D 5, + _D3DKMT_QUERYSTATISTICS_PROCESS_NODE =3D 6, + _D3DKMT_QUERYSTATISTICS_VIDPNSOURCE =3D 7, + _D3DKMT_QUERYSTATISTICS_PROCESS_VIDPNSOURCE =3D 8, + _D3DKMT_QUERYSTATISTICS_PROCESS_SEGMENT_GROUP =3D 9, + _D3DKMT_QUERYSTATISTICS_PHYSICAL_ADAPTER =3D 10, +}; + +struct d3dkmt_querystatistics_result { + char size[0x308]; +}; + +struct d3dkmt_querystatistics { + union { + struct { + enum d3dkmt_querystatistics_type type; + struct winluid adapter_luid; + __u64 process; + struct d3dkmt_querystatistics_result result; + }; + char size[0x328]; + }; +}; + +struct d3dkmt_shareobjectwithhost { + struct d3dkmthandle device_handle; + struct d3dkmthandle object_handle; + __u64 reserved; + __u64 object_vail_nt_handle; +}; + +/* + * Dxgkrnl Graphics Port Driver ioctl definitions + * + */ + +#define LX_DXOPENADAPTERFROMLUID \ + _IOWR(0x47, 0x01, struct d3dkmt_openadapterfromluid) +#define LX_DXCREATEDEVICE \ + _IOWR(0x47, 0x02, struct d3dkmt_createdevice) +#define LX_DXCREATECONTEXT \ + _IOWR(0x47, 0x03, struct d3dkmt_createcontext) +#define LX_DXCREATECONTEXTVIRTUAL \ + _IOWR(0x47, 0x04, struct d3dkmt_createcontextvirtual) +#define LX_DXDESTROYCONTEXT \ + _IOWR(0x47, 0x05, struct d3dkmt_destroycontext) +#define LX_DXCREATEALLOCATION \ + _IOWR(0x47, 0x06, struct d3dkmt_createallocation) +#define LX_DXCREATEPAGINGQUEUE \ + _IOWR(0x47, 0x07, struct d3dkmt_createpagingqueue) +#define LX_DXRESERVEGPUVIRTUALADDRESS \ + _IOWR(0x47, 0x08, struct d3dddi_reservegpuvirtualaddress) +#define LX_DXQUERYADAPTERINFO \ + _IOWR(0x47, 0x09, struct d3dkmt_queryadapterinfo) +#define LX_DXQUERYVIDEOMEMORYINFO \ + _IOWR(0x47, 0x0a, struct d3dkmt_queryvideomemoryinfo) +#define LX_DXMAKERESIDENT \ + _IOWR(0x47, 0x0b, struct d3dddi_makeresident) +#define LX_DXMAPGPUVIRTUALADDRESS \ + _IOWR(0x47, 0x0c, struct d3dddi_mapgpuvirtualaddress) +#define LX_DXESCAPE \ + _IOWR(0x47, 0x0d, struct d3dkmt_escape) +#define LX_DXGETDEVICESTATE \ + _IOWR(0x47, 0x0e, struct d3dkmt_getdevicestate) +#define LX_DXSUBMITCOMMAND \ + _IOWR(0x47, 0x0f, struct d3dkmt_submitcommand) +#define LX_DXCREATESYNCHRONIZATIONOBJECT \ + _IOWR(0x47, 0x10, struct d3dkmt_createsynchronizationobject2) +#define LX_DXSIGNALSYNCHRONIZATIONOBJECT \ + _IOWR(0x47, 0x11, struct d3dkmt_signalsynchronizationobject2) +#define LX_DXWAITFORSYNCHRONIZATIONOBJECT \ + _IOWR(0x47, 0x12, struct d3dkmt_waitforsynchronizationobject2) +#define LX_DXDESTROYALLOCATION2 \ + _IOWR(0x47, 0x13, struct d3dkmt_destroyallocation2) +#define LX_DXENUMADAPTERS2 \ + _IOWR(0x47, 0x14, struct d3dkmt_enumadapters2) +#define LX_DXCLOSEADAPTER \ + _IOWR(0x47, 0x15, struct d3dkmt_closeadapter) +#define LX_DXCHANGEVIDEOMEMORYRESERVATION \ + _IOWR(0x47, 0x16, struct d3dkmt_changevideomemoryreservation) +#define LX_DXCREATEHWCONTEXT \ + _IOWR(0x47, 0x17, struct d3dkmt_createhwcontext) +#define LX_DXCREATEHWQUEUE \ + _IOWR(0x47, 0x18, struct d3dkmt_createhwqueue) +#define LX_DXDESTROYDEVICE \ + _IOWR(0x47, 0x19, struct d3dkmt_destroydevice) +#define LX_DXDESTROYHWCONTEXT \ + _IOWR(0x47, 0x1a, struct d3dkmt_destroyhwcontext) +#define LX_DXDESTROYHWQUEUE \ + _IOWR(0x47, 0x1b, struct d3dkmt_destroyhwqueue) +#define LX_DXDESTROYPAGINGQUEUE \ + _IOWR(0x47, 0x1c, struct d3dddi_destroypagingqueue) +#define LX_DXDESTROYSYNCHRONIZATIONOBJECT \ + _IOWR(0x47, 0x1d, struct d3dkmt_destroysynchronizationobject) +#define LX_DXEVICT \ + _IOWR(0x47, 0x1e, struct d3dkmt_evict) +#define LX_DXFLUSHHEAPTRANSITIONS \ + _IOWR(0x47, 0x1f, struct d3dkmt_flushheaptransitions) +#define LX_DXFREEGPUVIRTUALADDRESS \ + _IOWR(0x47, 0x20, struct d3dkmt_freegpuvirtualaddress) +#define LX_DXGETCONTEXTINPROCESSSCHEDULINGPRIORITY \ + _IOWR(0x47, 0x21, struct d3dkmt_getcontextinprocessschedulingpriority) +#define LX_DXGETCONTEXTSCHEDULINGPRIORITY \ + _IOWR(0x47, 0x22, struct d3dkmt_getcontextschedulingpriority) +#define LX_DXGETSHAREDRESOURCEADAPTERLUID \ + _IOWR(0x47, 0x23, struct d3dkmt_getsharedresourceadapterluid) +#define LX_DXINVALIDATECACHE \ + _IOWR(0x47, 0x24, struct d3dkmt_invalidatecache) +#define LX_DXLOCK2 \ + _IOWR(0x47, 0x25, struct d3dkmt_lock2) +#define LX_DXMARKDEVICEASERROR \ + _IOWR(0x47, 0x26, struct d3dkmt_markdeviceaserror) +#define LX_DXOFFERALLOCATIONS \ + _IOWR(0x47, 0x27, struct d3dkmt_offerallocations) +#define LX_DXOPENRESOURCE \ + _IOWR(0x47, 0x28, struct d3dkmt_openresource) +#define LX_DXOPENSYNCHRONIZATIONOBJECT \ + _IOWR(0x47, 0x29, struct d3dkmt_opensynchronizationobject) +#define LX_DXQUERYALLOCATIONRESIDENCY \ + _IOWR(0x47, 0x2a, struct d3dkmt_queryallocationresidency) +#define LX_DXQUERYRESOURCEINFO \ + _IOWR(0x47, 0x2b, struct d3dkmt_queryresourceinfo) +#define LX_DXRECLAIMALLOCATIONS2 \ + _IOWR(0x47, 0x2c, struct d3dkmt_reclaimallocations2) +#define LX_DXRENDER \ + _IOWR(0x47, 0x2d, struct d3dkmt_render) +#define LX_DXSETALLOCATIONPRIORITY \ + _IOWR(0x47, 0x2e, struct d3dkmt_setallocationpriority) +#define LX_DXSETCONTEXTINPROCESSSCHEDULINGPRIORITY \ + _IOWR(0x47, 0x2f, struct d3dkmt_setcontextinprocessschedulingpriority) +#define LX_DXSETCONTEXTSCHEDULINGPRIORITY \ + _IOWR(0x47, 0x30, struct d3dkmt_setcontextschedulingpriority) +#define LX_DXSIGNALSYNCHRONIZATIONOBJECTFROMCPU \ + _IOWR(0x47, 0x31, struct d3dkmt_signalsynchronizationobjectfromcpu) +#define LX_DXSIGNALSYNCHRONIZATIONOBJECTFROMGPU \ + _IOWR(0x47, 0x32, struct d3dkmt_signalsynchronizationobjectfromgpu) +#define LX_DXSIGNALSYNCHRONIZATIONOBJECTFROMGPU2 \ + _IOWR(0x47, 0x33, struct d3dkmt_signalsynchronizationobjectfromgpu2) +#define LX_DXSUBMITCOMMANDTOHWQUEUE \ + _IOWR(0x47, 0x34, struct d3dkmt_submitcommandtohwqueue) +#define LX_DXSUBMITSIGNALSYNCOBJECTSTOHWQUEUE \ + _IOWR(0x47, 0x35, struct d3dkmt_submitsignalsyncobjectstohwqueue) +#define LX_DXSUBMITWAITFORSYNCOBJECTSTOHWQUEUE \ + _IOWR(0x47, 0x36, struct d3dkmt_submitwaitforsyncobjectstohwqueue) +#define LX_DXUNLOCK2 \ + _IOWR(0x47, 0x37, struct d3dkmt_unlock2) +#define LX_DXUPDATEALLOCPROPERTY \ + _IOWR(0x47, 0x38, struct d3dddi_updateallocproperty) +#define LX_DXUPDATEGPUVIRTUALADDRESS \ + _IOWR(0x47, 0x39, struct d3dkmt_updategpuvirtualaddress) +#define LX_DXWAITFORSYNCHRONIZATIONOBJECTFROMCPU \ + _IOWR(0x47, 0x3a, struct d3dkmt_waitforsynchronizationobjectfromcpu) +#define LX_DXWAITFORSYNCHRONIZATIONOBJECTFROMGPU \ + _IOWR(0x47, 0x3b, struct d3dkmt_waitforsynchronizationobjectfromgpu) +#define LX_DXGETALLOCATIONPRIORITY \ + _IOWR(0x47, 0x3c, struct d3dkmt_getallocationpriority) +#define LX_DXQUERYCLOCKCALIBRATION \ + _IOWR(0x47, 0x3d, struct d3dkmt_queryclockcalibration) +#define LX_DXENUMADAPTERS3 \ + _IOWR(0x47, 0x3e, struct d3dkmt_enumadapters3) +#define LX_DXSHAREOBJECTS \ + _IOWR(0x47, 0x3f, struct d3dkmt_shareobjects) +#define LX_DXOPENSYNCOBJECTFROMNTHANDLE2 \ + _IOWR(0x47, 0x40, struct d3dkmt_opensyncobjectfromnthandle2) +#define LX_DXQUERYRESOURCEINFOFROMNTHANDLE \ + _IOWR(0x47, 0x41, struct d3dkmt_queryresourceinfofromnthandle) +#define LX_DXOPENRESOURCEFROMNTHANDLE \ + _IOWR(0x47, 0x42, struct d3dkmt_openresourcefromnthandle) +#define LX_DXQUERYSTATISTICS \ + _IOWR(0x47, 0x43, struct d3dkmt_querystatistics) +#define LX_DXSHAREOBJECTWITHHOST \ + _IOWR(0x47, 0x44, struct d3dkmt_shareobjectwithhost) + +#define LX_IO_MAX 0x45 + +#endif /* _D3DKMTHK_H */ --=20 2.35.1 From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 7A43EC4167D for ; Sat, 5 Feb 2022 02:34:34 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1379057AbiBECec (ORCPT ); Fri, 4 Feb 2022 21:34:32 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45084 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1378992AbiBECeX (ORCPT ); Fri, 4 Feb 2022 21:34:23 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id 9C01B20B800A; Fri, 4 Feb 2022 18:34:23 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com 9C01B20B800A DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028463; bh=6HJaLTSeNvjGysNIR2t9jPI334jD3/xt14zstcg0ZtE=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=c+KoPtgT61Q6bp6uRUQs6/PAoC9mQb5FRCFtE2W1fETWTFA7tUTze4YFRMKnhwjCF ABQvJd6ymZo532iVNCYZh6MLP4BxbJG5ua0MiQr/OdKNSI/UnOeiyGIh1OueXUYbOi 1jmdE7nkppNiCDxpfzkaCtXL9xyOzxngECszEkK0= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 02/24] drivers: hv: dxgkrnl: Open device file and dxgprocess creation Date: Fri, 4 Feb 2022 18:34:00 -0800 Message-Id: X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Implement opening of the device (/dev/dxg) file object and creation of dxgprocess. dxgprocess is created for each process, which opens /dev/dxg. dxgprocess is ref counted, so the existing dxgprocess objects is used for a process, which opens the device object multiple time. dxgprocess is destroyed when the device object is released. A corresponding process object is created on the host for every dxgprocess object in the guest. Added a VM bus message to create and destroy the host side of a dxgprocess object. Implement the handle manager, which manages d3dkmthandle handles for the internal process objects. Signed-off-by: Iouri Tarassov --- drivers/hv/dxgkrnl/dxgkrnl.h | 39 ++- drivers/hv/dxgkrnl/dxgmodule.c | 67 +++- drivers/hv/dxgkrnl/dxgprocess.c | 80 +++++ drivers/hv/dxgkrnl/dxgvmbus.c | 79 +++++ drivers/hv/dxgkrnl/dxgvmbus.h | 1 + drivers/hv/dxgkrnl/hmgr.c | 543 ++++++++++++++++++++++++++++++++ drivers/hv/dxgkrnl/hmgr.h | 37 +++ drivers/hv/dxgkrnl/ioctl.c | 70 ++++ drivers/hv/dxgkrnl/misc.h | 1 - 9 files changed, 914 insertions(+), 3 deletions(-) diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index 15208328cb71..61512463baa4 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -27,6 +27,7 @@ #include #include =20 +struct dxgprocess; struct dxgadapter; =20 #include "misc.h" @@ -138,10 +139,44 @@ struct dxgvmbuschannel *dxgglobal_get_dxgvmbuschannel= (void); int dxgglobal_acquire_channel_lock(void); void dxgglobal_release_channel_lock(void); =20 +/* + * The structure represents a process, which opened the /dev/dxg device. + * A corresponding object is created on the host. + */ struct dxgprocess { - /* Placeholder */ + /* + * Process list entry in dxgglobal. + * Protected by the dxgglobal->plistmutex. + */ + struct list_head plistentry; + struct task_struct *process; + pid_t pid; + pid_t tgid; + /* how many time the process was opened */ + struct kref process_kref; + /* + * This handle table is used for all objects except dxgadapter + * The handle table lock order is higher than the local_handle_table + * lock + */ + struct hmgrtable handle_table; + /* + * This handle table is used for dxgadapter objects. + * The handle table lock order is lowest. + */ + struct hmgrtable local_handle_table; + /* Handle of the corresponding objec on the host */ + struct d3dkmthandle host_handle; }; =20 +struct dxgprocess *dxgprocess_create(void); +void dxgprocess_destroy(struct dxgprocess *process); +void dxgprocess_release(struct kref *refcount); +void dxgprocess_ht_lock_shared_down(struct dxgprocess *process); +void dxgprocess_ht_lock_shared_up(struct dxgprocess *process); +void dxgprocess_ht_lock_exclusive_down(struct dxgprocess *process); +void dxgprocess_ht_lock_exclusive_up(struct dxgprocess *process); + enum dxgadapter_state { DXGADAPTER_STATE_ACTIVE =3D 0, DXGADAPTER_STATE_STOPPED =3D 1, @@ -211,6 +246,8 @@ static inline void guid_to_luid(guid_t *guid, struct wi= nluid *luid) void dxgvmb_initialize(void); int dxgvmb_send_set_iospace_region(u64 start, u64 len, struct vmbus_gpadl *shared_mem_gpadl); +int dxgvmb_send_create_process(struct dxgprocess *process); +int dxgvmb_send_destroy_process(struct d3dkmthandle process); int dxgvmb_send_open_adapter(struct dxgadapter *adapter); int dxgvmb_send_close_adapter(struct dxgadapter *adapter); int dxgvmb_send_get_internal_adapter_info(struct dxgadapter *adapter); diff --git a/drivers/hv/dxgkrnl/dxgmodule.c b/drivers/hv/dxgkrnl/dxgmodule.c index a9a00dae2088..64ac35e1863b 100644 --- a/drivers/hv/dxgkrnl/dxgmodule.c +++ b/drivers/hv/dxgkrnl/dxgmodule.c @@ -204,17 +204,80 @@ static void dxgglobal_stop_adapters(void) dxgglobal_release_adapter_list_lock(DXGLOCK_EXCL); } =20 +/* + * Returns dxgprocess for the current executing process. + * Creates dxgprocess if it doesn't exist. + */ +static struct dxgprocess *dxgglobal_get_current_process(void) +{ + /* + * Find the DXG process for the current process. + * A new process is created if necessary. + */ + struct dxgprocess *process =3D NULL; + struct dxgprocess *entry =3D NULL; + + mutex_lock(&dxgglobal->plistmutex); + list_for_each_entry(entry, &dxgglobal->plisthead, plistentry) { + /* All threads of a process have the same thread group ID */ + if (entry->process->tgid =3D=3D current->tgid) { + if (kref_get_unless_zero(&entry->process_kref)) { + process =3D entry; + pr_debug("found dxgprocess"); + } else { + pr_debug("process is destroyed"); + } + break; + } + } + mutex_unlock(&dxgglobal->plistmutex); + + if (process =3D=3D NULL) + process =3D dxgprocess_create(); + + return process; +} + /* * File operations for the /dev/dxg device */ =20 static int dxgk_open(struct inode *n, struct file *f) { - return 0; + int ret =3D 0; + struct dxgprocess *process; + + pr_debug("%s %p %d %d", + __func__, f, current->pid, current->tgid); + + + /* Find/create a dxgprocess structure for this process */ + process =3D dxgglobal_get_current_process(); + + if (process) { + f->private_data =3D process; + } else { + pr_debug("cannot create dxgprocess for open\n"); + ret =3D -EBADF; + } + + pr_debug("%s end %x", __func__, ret); + return ret; } =20 static int dxgk_release(struct inode *n, struct file *f) { + struct dxgprocess *process; + + process =3D (struct dxgprocess *)f->private_data; + pr_debug("%s %p, %p", __func__, f, process); + + if (process =3D=3D NULL) + return -EINVAL; + + kref_put(&process->process_kref, dxgprocess_release); + + f->private_data =3D NULL; return 0; } =20 @@ -236,6 +299,8 @@ const struct file_operations dxgk_fops =3D { .owner =3D THIS_MODULE, .open =3D dxgk_open, .release =3D dxgk_release, + .compat_ioctl =3D dxgk_compat_ioctl, + .unlocked_ioctl =3D dxgk_unlocked_ioctl, .write =3D dxgk_write, .read =3D dxgk_read, }; diff --git a/drivers/hv/dxgkrnl/dxgprocess.c b/drivers/hv/dxgkrnl/dxgproces= s.c index 81e5b4a137e7..2a86ba1b4b1b 100644 --- a/drivers/hv/dxgkrnl/dxgprocess.c +++ b/drivers/hv/dxgkrnl/dxgprocess.c @@ -15,3 +15,83 @@ =20 #undef pr_fmt #define pr_fmt(fmt) "dxgk: " fmt + +/* + * Creates a new dxgprocess object + * Must be called when dxgglobal->plistmutex is held + */ +struct dxgprocess *dxgprocess_create(void) +{ + struct dxgprocess *process; + int ret; + + process =3D vzalloc(sizeof(struct dxgprocess)); + if (process !=3D NULL) { + pr_debug("new dxgprocess created\n"); + process->process =3D current; + process->pid =3D current->pid; + process->tgid =3D current->tgid; + ret =3D dxgvmb_send_create_process(process); + if (ret < 0) { + pr_debug("send_create_process failed\n"); + vfree(process); + process =3D NULL; + } else { + INIT_LIST_HEAD(&process->plistentry); + kref_init(&process->process_kref); + + mutex_lock(&dxgglobal->plistmutex); + list_add_tail(&process->plistentry, + &dxgglobal->plisthead); + mutex_unlock(&dxgglobal->plistmutex); + + hmgrtable_init(&process->handle_table, process); + hmgrtable_init(&process->local_handle_table, process); + } + } + return process; +} + +void dxgprocess_destroy(struct dxgprocess *process) +{ + hmgrtable_destroy(&process->handle_table); + hmgrtable_destroy(&process->local_handle_table); +} + +void dxgprocess_release(struct kref *refcount) +{ + struct dxgprocess *process; + + process =3D container_of(refcount, struct dxgprocess, process_kref); + + mutex_lock(&dxgglobal->plistmutex); + list_del(&process->plistentry); + process->plistentry.next =3D NULL; + mutex_unlock(&dxgglobal->plistmutex); + + dxgprocess_destroy(process); + + if (process->host_handle.v) + dxgvmb_send_destroy_process(process->host_handle); + vfree(process); +} + +void dxgprocess_ht_lock_shared_down(struct dxgprocess *process) +{ + hmgrtable_lock(&process->handle_table, DXGLOCK_SHARED); +} + +void dxgprocess_ht_lock_shared_up(struct dxgprocess *process) +{ + hmgrtable_unlock(&process->handle_table, DXGLOCK_SHARED); +} + +void dxgprocess_ht_lock_exclusive_down(struct dxgprocess *process) +{ + hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL); +} + +void dxgprocess_ht_lock_exclusive_up(struct dxgprocess *process) +{ + hmgrtable_unlock(&process->handle_table, DXGLOCK_EXCL); +} diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index 84693c98a4af..056d86c1859a 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -484,6 +484,85 @@ int dxgvmb_send_set_iospace_region(u64 start, u64 len, return ret; } =20 +int dxgvmb_send_create_process(struct dxgprocess *process) +{ + int ret; + struct dxgkvmb_command_createprocess *command; + struct dxgkvmb_command_createprocess_return result =3D { 0 }; + struct dxgvmbusmsg msg; + char s[WIN_MAX_PATH]; + int i; + + ret =3D init_message(&msg, NULL, process, sizeof(*command)); + if (ret) + return ret; + command =3D (void *)msg.msg; + + ret =3D dxgglobal_acquire_channel_lock(); + if (ret < 0) + goto cleanup; + + command_vm_to_host_init1(&command->hdr, DXGK_VMBCOMMAND_CREATEPROCESS); + command->process =3D process; + command->process_id =3D process->process->pid; + command->linux_process =3D 1; + s[0] =3D 0; + __get_task_comm(s, WIN_MAX_PATH, process->process); + for (i =3D 0; i < WIN_MAX_PATH; i++) { + command->process_name[i] =3D s[i]; + if (s[i] =3D=3D 0) + break; + } + + ret =3D dxgvmb_send_sync_msg(&dxgglobal->channel, msg.hdr, msg.size, + &result, sizeof(result)); + if (ret < 0) { + pr_err("create_process failed %d", ret); + } else if (result.hprocess.v =3D=3D 0) { + pr_err("create_process returned 0 handle"); + ret =3D -ENOTRECOVERABLE; + } else { + process->host_handle =3D result.hprocess; + pr_debug("create_process returned %x", + process->host_handle.v); + } + + dxgglobal_release_channel_lock(); + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +int dxgvmb_send_destroy_process(struct d3dkmthandle process) +{ + int ret; + struct dxgkvmb_command_destroyprocess *command; + struct dxgvmbusmsg msg; + + ret =3D init_message(&msg, NULL, NULL, sizeof(*command)); + if (ret) + return ret; + command =3D (void *)msg.msg; + + ret =3D dxgglobal_acquire_channel_lock(); + if (ret < 0) + goto cleanup; + command_vm_to_host_init2(&command->hdr, DXGK_VMBCOMMAND_DESTROYPROCESS, + process); + ret =3D dxgvmb_send_sync_msg_ntstatus(&dxgglobal->channel, + msg.hdr, msg.size); + dxgglobal_release_channel_lock(); + +cleanup: + free_message(&msg, NULL); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + /* * Virtual GPU messages to the host */ diff --git a/drivers/hv/dxgkrnl/dxgvmbus.h b/drivers/hv/dxgkrnl/dxgvmbus.h index 93cce587158b..5b455618a2a2 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.h +++ b/drivers/hv/dxgkrnl/dxgvmbus.h @@ -14,6 +14,7 @@ #ifndef _DXGVMBUS_H #define _DXGVMBUS_H =20 +struct dxgprocess; struct dxgadapter; =20 #define DXG_MAX_VM_BUS_PACKET_SIZE (1024 * 128) diff --git a/drivers/hv/dxgkrnl/hmgr.c b/drivers/hv/dxgkrnl/hmgr.c index 216e0956f8f8..4c012046dcaf 100644 --- a/drivers/hv/dxgkrnl/hmgr.c +++ b/drivers/hv/dxgkrnl/hmgr.c @@ -21,3 +21,546 @@ =20 #undef pr_fmt #define pr_fmt(fmt) "dxgk: " fmt + +const struct d3dkmthandle zerohandle; + +/* + * Handle parameters + */ +#define HMGRHANDLE_INSTANCE_BITS 6 +#define HMGRHANDLE_INDEX_BITS 24 +#define HMGRHANDLE_UNIQUE_BITS 2 + +#define HMGRHANDLE_INSTANCE_SHIFT 0 +#define HMGRHANDLE_INDEX_SHIFT \ + (HMGRHANDLE_INSTANCE_BITS + HMGRHANDLE_INSTANCE_SHIFT) +#define HMGRHANDLE_UNIQUE_SHIFT \ + (HMGRHANDLE_INDEX_BITS + HMGRHANDLE_INDEX_SHIFT) + +#define HMGRHANDLE_INSTANCE_MASK \ + (((1 << HMGRHANDLE_INSTANCE_BITS) - 1) << HMGRHANDLE_INSTANCE_SHIFT) +#define HMGRHANDLE_INDEX_MASK \ + (((1 << HMGRHANDLE_INDEX_BITS) - 1) << HMGRHANDLE_INDEX_SHIFT) +#define HMGRHANDLE_UNIQUE_MASK \ + (((1 << HMGRHANDLE_UNIQUE_BITS) - 1) << HMGRHANDLE_UNIQUE_SHIFT) + +#define HMGRHANDLE_INSTANCE_MAX ((1 << HMGRHANDLE_INSTANCE_BITS) - 1) +#define HMGRHANDLE_INDEX_MAX ((1 << HMGRHANDLE_INDEX_BITS) - 1) +#define HMGRHANDLE_UNIQUE_MAX ((1 << HMGRHANDLE_UNIQUE_BITS) - 1) + +/* + * Handle entry + */ +struct hmgrentry { + union { + void *object; + struct { + u32 prev_free_index; + u32 next_free_index; + }; + }; + u32 type:HMGRENTRY_TYPE_BITS + 1; + u32 unique:HMGRHANDLE_UNIQUE_BITS; + u32 instance:HMGRHANDLE_INSTANCE_BITS; + u32 destroyed:1; +}; + +#define HMGRTABLE_SIZE_INCREMENT 1024 +#define HMGRTABLE_MIN_FREE_ENTRIES 128 +#define HMGRTABLE_INVALID_INDEX (~((1 << HMGRHANDLE_INDEX_BITS) - 1)) +#define HMGRTABLE_SIZE_MAX 0xFFFFFFF + +static u32 table_size_increment =3D HMGRTABLE_SIZE_INCREMENT; + +static u32 get_unique(struct d3dkmthandle h) +{ + return (h.v & HMGRHANDLE_UNIQUE_MASK) >> HMGRHANDLE_UNIQUE_SHIFT; +} + +static u32 get_index(struct d3dkmthandle h) +{ + return (h.v & HMGRHANDLE_INDEX_MASK) >> HMGRHANDLE_INDEX_SHIFT; +} + +static bool is_handle_valid(struct hmgrtable *table, struct d3dkmthandle h, + bool ignore_destroyed, enum hmgrentry_type t) +{ + u32 index =3D get_index(h); + u32 unique =3D get_unique(h); + struct hmgrentry *entry; + + if (index >=3D table->table_size) { + pr_err("%s Invalid index %x %d\n", __func__, h.v, index); + return false; + } + + entry =3D &table->entry_table[index]; + if (unique !=3D entry->unique) { + pr_err("%s Invalid unique %x %d %d %d %p", + __func__, h.v, unique, entry->unique, + index, entry->object); + return false; + } + + if (entry->destroyed && !ignore_destroyed) { + pr_err("%s Invalid destroyed", __func__); + return false; + } + + if (entry->type =3D=3D HMGRENTRY_TYPE_FREE) { + pr_err("%s Entry is freed %x %d", __func__, h.v, index); + return false; + } + + if (t !=3D HMGRENTRY_TYPE_FREE && t !=3D entry->type) { + pr_err("%s type mismatch %x %d %d", __func__, h.v, + t, entry->type); + return false; + } + + return true; +} + +static struct d3dkmthandle build_handle(u32 index, u32 unique, u32 instanc= e) +{ + struct d3dkmthandle handle; + + handle.v =3D (index << HMGRHANDLE_INDEX_SHIFT) & HMGRHANDLE_INDEX_MASK; + handle.v |=3D (unique << HMGRHANDLE_UNIQUE_SHIFT) & + HMGRHANDLE_UNIQUE_MASK; + handle.v |=3D (instance << HMGRHANDLE_INSTANCE_SHIFT) & + HMGRHANDLE_INSTANCE_MASK; + + return handle; +} + +inline u32 hmgrtable_get_used_entry_count(struct hmgrtable *table) +{ + DXGKRNL_ASSERT(table->table_size >=3D table->free_count); + return (table->table_size - table->free_count); +} + +bool hmgrtable_mark_destroyed(struct hmgrtable *table, struct d3dkmthandle= h) +{ + if (!is_handle_valid(table, h, false, HMGRENTRY_TYPE_FREE)) + return false; + + table->entry_table[get_index(h)].destroyed =3D true; + return true; +} + +bool hmgrtable_unmark_destroyed(struct hmgrtable *table, struct d3dkmthand= le h) +{ + if (!is_handle_valid(table, h, true, HMGRENTRY_TYPE_FREE)) + return true; + + DXGKRNL_ASSERT(table->entry_table[get_index(h)].destroyed); + table->entry_table[get_index(h)].destroyed =3D 0; + return true; +} + +static bool expand_table(struct hmgrtable *table, u32 NumEntries) +{ + u32 new_table_size; + struct hmgrentry *new_entry; + u32 table_index; + u32 new_free_count; + u32 prev_free_index; + u32 tail_index =3D table->free_handle_list_tail; + + /* The tail should point to the last free element in the list */ + if (table->free_count !=3D 0) { + if (tail_index >=3D table->table_size || + table->entry_table[tail_index].next_free_index !=3D + HMGRTABLE_INVALID_INDEX) { + pr_err("%s:corruption\n", __func__); + pr_err("tail_index: %x", tail_index); + pr_err("table size: %x", table->table_size); + pr_err("free_count: %d", table->free_count); + pr_err("NumEntries: %x", NumEntries); + return false; + } + } + + new_free_count =3D table_size_increment + table->free_count; + new_table_size =3D table->table_size + table_size_increment; + if (new_table_size < NumEntries) { + new_free_count +=3D NumEntries - new_table_size; + new_table_size =3D NumEntries; + } + + if (new_table_size > HMGRHANDLE_INDEX_MAX) { + pr_err("%s:corruption\n", __func__); + return false; + } + + new_entry =3D (struct hmgrentry *) + vzalloc(new_table_size * sizeof(struct hmgrentry)); + if (new_entry =3D=3D NULL) { + pr_err("%s:allocation failed\n", __func__); + return false; + } + + if (table->entry_table) { + memcpy(new_entry, table->entry_table, + table->table_size * sizeof(struct hmgrentry)); + vfree(table->entry_table); + } else { + table->free_handle_list_head =3D 0; + } + + table->entry_table =3D new_entry; + + /* Initialize new table entries and add to the free list */ + table_index =3D table->table_size; + + prev_free_index =3D table->free_handle_list_tail; + + while (table_index < new_table_size) { + struct hmgrentry *entry =3D &table->entry_table[table_index]; + + entry->prev_free_index =3D prev_free_index; + entry->next_free_index =3D table_index + 1; + entry->type =3D HMGRENTRY_TYPE_FREE; + entry->unique =3D 1; + entry->instance =3D 0; + prev_free_index =3D table_index; + + table_index++; + } + + table->entry_table[table_index - 1].next_free_index =3D + (u32) HMGRTABLE_INVALID_INDEX; + + if (table->free_count !=3D 0) { + /* Link the current free list with the new entries */ + struct hmgrentry *entry; + + entry =3D &table->entry_table[table->free_handle_list_tail]; + entry->next_free_index =3D table->table_size; + } + table->free_handle_list_tail =3D new_table_size - 1; + if (table->free_handle_list_head =3D=3D HMGRTABLE_INVALID_INDEX) + table->free_handle_list_head =3D table->table_size; + + table->table_size =3D new_table_size; + table->free_count =3D new_free_count; + + return true; +} + +void hmgrtable_init(struct hmgrtable *table, struct dxgprocess *process) +{ + table->process =3D process; + table->entry_table =3D NULL; + table->table_size =3D 0; + table->free_handle_list_head =3D HMGRTABLE_INVALID_INDEX; + table->free_handle_list_tail =3D HMGRTABLE_INVALID_INDEX; + table->free_count =3D 0; + init_rwsem(&table->table_lock); +} + +void hmgrtable_destroy(struct hmgrtable *table) +{ + if (table->entry_table) { + vfree(table->entry_table); + table->entry_table =3D NULL; + } +} + +void hmgrtable_lock(struct hmgrtable *table, enum dxglockstate state) +{ + if (state =3D=3D DXGLOCK_EXCL) + down_write(&table->table_lock); + else + down_read(&table->table_lock); +} + +void hmgrtable_unlock(struct hmgrtable *table, enum dxglockstate state) +{ + if (state =3D=3D DXGLOCK_EXCL) + up_write(&table->table_lock); + else + up_read(&table->table_lock); +} + +struct d3dkmthandle hmgrtable_alloc_handle(struct hmgrtable *table, + void *object, + enum hmgrentry_type type, + bool make_valid) +{ + u32 index; + struct hmgrentry *entry; + u32 unique; + + DXGKRNL_ASSERT(type <=3D HMGRENTRY_TYPE_LIMIT); + DXGKRNL_ASSERT(type > HMGRENTRY_TYPE_FREE); + + if (table->free_count <=3D HMGRTABLE_MIN_FREE_ENTRIES) { + if (!expand_table(table, 0)) { + pr_err("hmgrtable expand_table failed\n"); + return zerohandle; + } + } + + if (table->free_handle_list_head >=3D table->table_size) { + pr_err("hmgrtable corrupted handle table head\n"); + return zerohandle; + } + + index =3D table->free_handle_list_head; + entry =3D &table->entry_table[index]; + + if (entry->type !=3D HMGRENTRY_TYPE_FREE) { + pr_err("hmgrtable expected free handle\n"); + return zerohandle; + } + + table->free_handle_list_head =3D entry->next_free_index; + + if (entry->next_free_index !=3D table->free_handle_list_tail) { + if (entry->next_free_index >=3D table->table_size) { + pr_err("hmgrtable invalid next free index\n"); + return zerohandle; + } + table->entry_table[entry->next_free_index].prev_free_index =3D + HMGRTABLE_INVALID_INDEX; + } + + unique =3D table->entry_table[index].unique; + + table->entry_table[index].object =3D object; + table->entry_table[index].type =3D type; + table->entry_table[index].instance =3D 0; + table->entry_table[index].destroyed =3D !make_valid; + table->free_count--; + DXGKRNL_ASSERT(table->free_count <=3D table->table_size); + + return build_handle(index, unique, table->entry_table[index].instance); +} + +int hmgrtable_assign_handle_safe(struct hmgrtable *table, + void *object, + enum hmgrentry_type type, + struct d3dkmthandle h) +{ + int ret; + + hmgrtable_lock(table, DXGLOCK_EXCL); + ret =3D hmgrtable_assign_handle(table, object, type, h); + hmgrtable_unlock(table, DXGLOCK_EXCL); + return ret; +} + +int hmgrtable_assign_handle(struct hmgrtable *table, void *object, + enum hmgrentry_type type, struct d3dkmthandle h) +{ + u32 index =3D get_index(h); + u32 unique =3D get_unique(h); + struct hmgrentry *entry =3D NULL; + + pr_debug("%s %x, %d %p, %p\n", + __func__, h.v, index, object, table); + + if (index >=3D HMGRHANDLE_INDEX_MAX) { + pr_err("handle index is too big: %x %d", h.v, index); + return -EINVAL; + } + + if (index >=3D table->table_size) { + u32 new_size =3D index + table_size_increment; + + if (new_size > HMGRHANDLE_INDEX_MAX) + new_size =3D HMGRHANDLE_INDEX_MAX; + if (!expand_table(table, new_size)) { + pr_err("failed to expand handle table %d", new_size); + return -ENOMEM; + } + } + + entry =3D &table->entry_table[index]; + + if (entry->type !=3D HMGRENTRY_TYPE_FREE) { + pr_err("the entry is already busy: %d %x", + entry->type, + hmgrtable_build_entry_handle(table, index).v); + return -EINVAL; + } + + if (index !=3D table->free_handle_list_tail) { + if (entry->next_free_index >=3D table->table_size) { + pr_err("hmgr: invalid next free index %d\n", + entry->next_free_index); + return -EINVAL; + } + table->entry_table[entry->next_free_index].prev_free_index =3D + entry->prev_free_index; + } else { + table->free_handle_list_tail =3D entry->prev_free_index; + } + + if (index !=3D table->free_handle_list_head) { + if (entry->prev_free_index >=3D table->table_size) { + pr_err("hmgr: invalid next prev index %d\n", + entry->prev_free_index); + return -EINVAL; + } + table->entry_table[entry->prev_free_index].next_free_index =3D + entry->next_free_index; + } else { + table->free_handle_list_head =3D entry->next_free_index; + } + + entry->prev_free_index =3D HMGRTABLE_INVALID_INDEX; + entry->next_free_index =3D HMGRTABLE_INVALID_INDEX; + entry->object =3D object; + entry->type =3D type; + entry->instance =3D 0; + entry->unique =3D unique; + entry->destroyed =3D false; + + table->free_count--; + DXGKRNL_ASSERT(table->free_count <=3D table->table_size); + return 0; +} + +struct d3dkmthandle hmgrtable_alloc_handle_safe(struct hmgrtable *table, + void *obj, + enum hmgrentry_type type, + bool make_valid) +{ + struct d3dkmthandle h; + + hmgrtable_lock(table, DXGLOCK_EXCL); + h =3D hmgrtable_alloc_handle(table, obj, type, make_valid); + hmgrtable_unlock(table, DXGLOCK_EXCL); + return h; +} + +void hmgrtable_free_handle(struct hmgrtable *table, enum hmgrentry_type t, + struct d3dkmthandle h) +{ + struct hmgrentry *entry; + u32 i =3D get_index(h); + + pr_debug("%s: %p %x\n", __func__, table, h.v); + + /* Ignore the destroyed flag when checking the handle */ + if (is_handle_valid(table, h, true, t)) { + DXGKRNL_ASSERT(table->free_count < table->table_size); + entry =3D &table->entry_table[i]; + entry->unique =3D 1; + entry->type =3D HMGRENTRY_TYPE_FREE; + entry->destroyed =3D 0; + if (entry->unique !=3D HMGRHANDLE_UNIQUE_MAX) + entry->unique +=3D 1; + else + entry->unique =3D 1; + + table->free_count++; + DXGKRNL_ASSERT(table->free_count <=3D table->table_size); + + /* + * Insert the index to the free list at the tail. + */ + entry->next_free_index =3D HMGRTABLE_INVALID_INDEX; + entry->prev_free_index =3D table->free_handle_list_tail; + entry =3D &table->entry_table[table->free_handle_list_tail]; + entry->next_free_index =3D i; + table->free_handle_list_tail =3D i; + } else { + pr_err("%s:error: %d %x\n", __func__, i, h.v); + } +} + +void hmgrtable_free_handle_safe(struct hmgrtable *table, enum hmgrentry_ty= pe t, + struct d3dkmthandle h) +{ + hmgrtable_lock(table, DXGLOCK_EXCL); + hmgrtable_free_handle(table, t, h); + hmgrtable_unlock(table, DXGLOCK_EXCL); +} + +struct d3dkmthandle hmgrtable_build_entry_handle(struct hmgrtable *table, + u32 index) +{ + DXGKRNL_ASSERT(index < table->table_size); + + return build_handle(index, table->entry_table[index].unique, + table->entry_table[index].instance); +} + +void *hmgrtable_get_object(struct hmgrtable *table, struct d3dkmthandle h) +{ + if (!is_handle_valid(table, h, false, HMGRENTRY_TYPE_FREE)) + return NULL; + + return table->entry_table[get_index(h)].object; +} + +void *hmgrtable_get_object_by_type(struct hmgrtable *table, + enum hmgrentry_type type, + struct d3dkmthandle h) +{ + if (!is_handle_valid(table, h, false, type)) { + pr_err("%s invalid handle %x\n", __func__, h.v); + return NULL; + } + return table->entry_table[get_index(h)].object; +} + +void *hmgrtable_get_entry_object(struct hmgrtable *table, u32 index) +{ + DXGKRNL_ASSERT(index < table->table_size); + DXGKRNL_ASSERT(table->entry_table[index].type !=3D HMGRENTRY_TYPE_FREE); + + return table->entry_table[index].object; +} + +static enum hmgrentry_type hmgrtable_get_entry_type(struct hmgrtable *tabl= e, + u32 index) +{ + DXGKRNL_ASSERT(index < table->table_size); + return (enum hmgrentry_type)table->entry_table[index].type; +} + +enum hmgrentry_type hmgrtable_get_object_type(struct hmgrtable *table, + struct d3dkmthandle h) +{ + if (!is_handle_valid(table, h, false, HMGRENTRY_TYPE_FREE)) + return HMGRENTRY_TYPE_FREE; + + return hmgrtable_get_entry_type(table, get_index(h)); +} + +void *hmgrtable_get_object_ignore_destroyed(struct hmgrtable *table, + struct d3dkmthandle h, + enum hmgrentry_type type) +{ + if (!is_handle_valid(table, h, true, type)) + return NULL; + return table->entry_table[get_index(h)].object; +} + +bool hmgrtable_next_entry(struct hmgrtable *tbl, + u32 *index, + enum hmgrentry_type *type, + struct d3dkmthandle *handle, + void **object) +{ + u32 i; + struct hmgrentry *entry; + + for (i =3D *index; i < tbl->table_size; i++) { + entry =3D &tbl->entry_table[i]; + if (entry->type !=3D HMGRENTRY_TYPE_FREE) { + *index =3D i + 1; + *object =3D entry->object; + *handle =3D build_handle(i, entry->unique, + entry->instance); + *type =3D entry->type; + return true; + } + } + return false; +} diff --git a/drivers/hv/dxgkrnl/hmgr.h b/drivers/hv/dxgkrnl/hmgr.h index b8b8f3ae5939..9ce4f536bf29 100644 --- a/drivers/hv/dxgkrnl/hmgr.h +++ b/drivers/hv/dxgkrnl/hmgr.h @@ -72,4 +72,41 @@ enum hmgrentry_type { HMGRENTRY_TYPE_MONITOREDFENCE =3D HMGRENTRY_TYPE_LIMIT + 1, }; =20 +void hmgrtable_init(struct hmgrtable *tbl, struct dxgprocess *process); +void hmgrtable_destroy(struct hmgrtable *tbl); +void hmgrtable_lock(struct hmgrtable *tbl, enum dxglockstate state); +void hmgrtable_unlock(struct hmgrtable *tbl, enum dxglockstate state); +struct d3dkmthandle hmgrtable_alloc_handle(struct hmgrtable *tbl, void *ob= ject, + enum hmgrentry_type t, bool make_valid); +struct d3dkmthandle hmgrtable_alloc_handle_safe(struct hmgrtable *tbl, + void *obj, + enum hmgrentry_type t, + bool reserve); +int hmgrtable_assign_handle(struct hmgrtable *tbl, void *obj, + enum hmgrentry_type, struct d3dkmthandle h); +int hmgrtable_assign_handle_safe(struct hmgrtable *tbl, void *obj, + enum hmgrentry_type t, struct d3dkmthandle h); +void hmgrtable_free_handle(struct hmgrtable *tbl, enum hmgrentry_type t, + struct d3dkmthandle h); +void hmgrtable_free_handle_safe(struct hmgrtable *tbl, enum hmgrentry_type= t, + struct d3dkmthandle h); +struct d3dkmthandle hmgrtable_build_entry_handle(struct hmgrtable *tbl, + u32 index); +enum hmgrentry_type hmgrtable_get_object_type(struct hmgrtable *tbl, + struct d3dkmthandle h); +void *hmgrtable_get_object(struct hmgrtable *tbl, struct d3dkmthandle h); +void *hmgrtable_get_object_by_type(struct hmgrtable *tbl, enum hmgrentry_t= ype t, + struct d3dkmthandle h); +void *hmgrtable_get_object_ignore_destroyed(struct hmgrtable *tbl, + struct d3dkmthandle h, + enum hmgrentry_type t); +bool hmgrtable_mark_destroyed(struct hmgrtable *tbl, struct d3dkmthandle h= ); +bool hmgrtable_unmark_destroyed(struct hmgrtable *tbl, struct d3dkmthandle= h); +void *hmgrtable_get_entry_object(struct hmgrtable *tbl, u32 index); +bool hmgrtable_next_entry(struct hmgrtable *tbl, + u32 *start_index, + enum hmgrentry_type *type, + struct d3dkmthandle *handle, + void **object); + #endif diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index 277e25e5d8c6..fa7fc321addb 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -22,3 +22,73 @@ =20 #undef pr_fmt #define pr_fmt(fmt) "dxgk: " fmt + +struct ioctl_desc { + int (*ioctl_callback)(struct dxgprocess *p, void __user *arg); + u32 ioctl; + u32 arg_size; +}; +static struct ioctl_desc ioctls[LX_IO_MAX + 1]; + +static char *errorstr(int ret) +{ + return ret < 0 ? "err" : ""; +} + +/* + * IOCTL processing + * The driver IOCTLs return + * - 0 in case of success + * - positive values, which are Windows NTSTATUS (for example, STATUS_PEND= ING). + * Positive values are success codes. + * - Linux negative error codes + */ +static int dxgk_ioctl(struct file *f, unsigned int p1, unsigned long p2) +{ + int code =3D _IOC_NR(p1); + int status; + struct dxgprocess *process; + + if (code < 1 || code > LX_IO_MAX) { + pr_err("bad ioctl %x %x %x %x", + code, _IOC_TYPE(p1), _IOC_SIZE(p1), _IOC_DIR(p1)); + return -ENOTTY; + } + if (ioctls[code].ioctl_callback =3D=3D NULL) { + pr_err("ioctl callback is NULL %x", code); + return -ENOTTY; + } + if (ioctls[code].ioctl !=3D p1) { + pr_err("ioctl mismatch. Code: %x User: %x Kernel: %x", + code, p1, ioctls[code].ioctl); + return -ENOTTY; + } + process =3D (struct dxgprocess *)f->private_data; + if (process->tgid !=3D current->tgid) { + pr_err("Call from a wrong process: %d %d", + process->tgid, current->tgid); + return -ENOTTY; + } + status =3D ioctls[code].ioctl_callback(process, (void *__user)p2); + return status; +} + +long dxgk_compat_ioctl(struct file *f, unsigned int p1, unsigned long p2) +{ + pr_debug(" compat ioctl %x", p1); + return dxgk_ioctl(f, p1, p2); +} + +long dxgk_unlocked_ioctl(struct file *f, unsigned int p1, unsigned long p2) +{ + pr_debug(" unlocked ioctl %x Code:%d", p1, _IOC_NR(p1)); + return dxgk_ioctl(f, p1, p2); +} + +#define SET_IOCTL(callback, v) \ + ioctls[_IOC_NR(v)].ioctl_callback =3D callback; \ + ioctls[_IOC_NR(v)].ioctl =3D v + +void init_ioctls(void) +{ +} diff --git a/drivers/hv/dxgkrnl/misc.h b/drivers/hv/dxgkrnl/misc.h index 1ff0c0e28332..433b59d3eb23 100644 --- a/drivers/hv/dxgkrnl/misc.h +++ b/drivers/hv/dxgkrnl/misc.h @@ -31,7 +31,6 @@ extern const struct d3dkmthandle zerohandle; * table_lock * core_lock * device_lock - * process->process_mutex * adapter_list_lock * device_mutex */ --=20 2.35.1 From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id BD291C433EF for ; Sat, 5 Feb 2022 02:34:42 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1379093AbiBECel (ORCPT ); Fri, 4 Feb 2022 21:34:41 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45090 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1378994AbiBECeY (ORCPT ); Fri, 4 Feb 2022 21:34:24 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id C916C20B8010; Fri, 4 Feb 2022 18:34:23 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com C916C20B8010 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028463; bh=x2ddbfPflgo1xk0q09bWkfLkxkgoehLuHkNOTPHI3p8=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=CREHnL2YeTw/YNhljnqeRWF7O2LXP7yEOAsAhf75nhiNQF7IFg5ZgCXCvVLetCr77 iZffl3ulc9Pi6b9I4/On+cTZ5g/+PEtX9Q9o527vscP+bfL6amua6KIi7YBMS/yGw/ rWyCGCWGSSRIVqRwJVzCStRlafUp7x2AgnVLVFXQ= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 03/24] drivers: hv: dxgkrnl: Enumerate and open dxgadapter objects Date: Fri, 4 Feb 2022 18:34:01 -0800 Message-Id: <975c73e47ac6ecd92a65df19ee233cc10975b453.1644025661.git.iourit@linux.microsoft.com> X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Implement IOCTLs to enumerate and open dxgadapter objects: LX_DXENUMADAPTERS2(D3DKMTEnumAdapters2) LX_DXENUMADAPTERS3(D3DKMTEnumAdapters2) Implement IOCTLS to open adapter by LUID and to close adapter handle: LX_DXOPENADAPTERFROMLUID(D3DKMTOpenAdapterFromLuid), LX_DXCLOSEADAPTER(D3DKMTCloseAdapter). Impllement IOCTL to query dxgadapter information: LX_DXQUERYADAPTERINFO.(D3DKMTQueryAdapterInfo). When a dxgadapter is enumerated, a process handle (d3dkmthandle) is created in the current process and returned to the caller. The caller is responsible to close the adapter when it is not longer used by calling D3DKMTCloseAdapter. A dxgprocess has a list of opened dxgadapter objects (dxgprocess_adapter is used to represent the entry in the list). A dxgadapter also has a list of dxgprocess_adapter objects. This is needed for cleanup because either a process or an adapter could be destroyed first. Signed-off-by: Iouri Tarassov --- drivers/hv/dxgkrnl/dxgadapter.c | 77 ++++++ drivers/hv/dxgkrnl/dxgkrnl.h | 49 ++++ drivers/hv/dxgkrnl/dxgmodule.c | 12 + drivers/hv/dxgkrnl/dxgprocess.c | 166 +++++++++++++ drivers/hv/dxgkrnl/dxgvmbus.c | 82 +++++++ drivers/hv/dxgkrnl/ioctl.c | 412 ++++++++++++++++++++++++++++++++ drivers/hv/dxgkrnl/misc.h | 1 + 7 files changed, 799 insertions(+) diff --git a/drivers/hv/dxgkrnl/dxgadapter.c b/drivers/hv/dxgkrnl/dxgadapte= r.c index e0a6fea00bd5..2c7823713547 100644 --- a/drivers/hv/dxgkrnl/dxgadapter.c +++ b/drivers/hv/dxgkrnl/dxgadapter.c @@ -102,6 +102,7 @@ void dxgadapter_start(struct dxgadapter *adapter) =20 void dxgadapter_stop(struct dxgadapter *adapter) { + struct dxgprocess_adapter *entry; bool adapter_stopped =3D false; =20 down_write(&adapter->core_lock); @@ -114,6 +115,15 @@ void dxgadapter_stop(struct dxgadapter *adapter) if (adapter_stopped) return; =20 + dxgglobal_acquire_process_adapter_lock(); + + list_for_each_entry(entry, &adapter->adapter_process_list_head, + adapter_process_list_entry) { + dxgprocess_adapter_stop(entry); + } + + dxgglobal_release_process_adapter_lock(); + if (dxgadapter_acquire_lock_exclusive(adapter) =3D=3D 0) { dxgvmb_send_close_adapter(adapter); dxgadapter_release_lock_exclusive(adapter); @@ -137,6 +147,24 @@ bool dxgadapter_is_active(struct dxgadapter *adapter) return adapter->adapter_state =3D=3D DXGADAPTER_STATE_ACTIVE; } =20 +/* Protected by dxgglobal_acquire_process_adapter_lock */ +void dxgadapter_add_process(struct dxgadapter *adapter, + struct dxgprocess_adapter *process_info) +{ + pr_debug("%s %p %p", __func__, adapter, process_info); + list_add_tail(&process_info->adapter_process_list_entry, + &adapter->adapter_process_list_head); +} + +void dxgadapter_remove_process(struct dxgprocess_adapter *process_info) +{ + pr_debug("%s %p %p", __func__, + process_info->adapter, process_info); + list_del(&process_info->adapter_process_list_entry); + process_info->adapter_process_list_entry.next =3D NULL; + process_info->adapter_process_list_entry.prev =3D NULL; +} + int dxgadapter_acquire_lock_exclusive(struct dxgadapter *adapter) { down_write(&adapter->core_lock); @@ -170,3 +198,52 @@ void dxgadapter_release_lock_shared(struct dxgadapter = *adapter) { up_read(&adapter->core_lock); } + +struct dxgprocess_adapter *dxgprocess_adapter_create(struct dxgprocess *pr= ocess, + struct dxgadapter *adapter) +{ + struct dxgprocess_adapter *adapter_info; + + adapter_info =3D vzalloc(sizeof(*adapter_info)); + if (adapter_info) { + if (kref_get_unless_zero(&adapter->adapter_kref) =3D=3D 0) { + pr_err("failed to acquire adapter reference"); + goto cleanup; + } + adapter_info->adapter =3D adapter; + adapter_info->process =3D process; + adapter_info->refcount =3D 1; + list_add_tail(&adapter_info->process_adapter_list_entry, + &process->process_adapter_list_head); + dxgadapter_add_process(adapter, adapter_info); + } + return adapter_info; +cleanup: + if (adapter_info) + vfree(adapter_info); + return NULL; +} + +void dxgprocess_adapter_stop(struct dxgprocess_adapter *adapter_info) +{ +} + +void dxgprocess_adapter_destroy(struct dxgprocess_adapter *adapter_info) +{ + dxgadapter_remove_process(adapter_info); + kref_put(&adapter_info->adapter->adapter_kref, dxgadapter_release); + list_del(&adapter_info->process_adapter_list_entry); + vfree(adapter_info); +} + +/* + * Must be called when dxgglobal::process_adapter_mutex is held + */ +void dxgprocess_adapter_release(struct dxgprocess_adapter *adapter_info) +{ + pr_debug("%s %p %d", + __func__, adapter_info, adapter_info->refcount); + adapter_info->refcount--; + if (adapter_info->refcount =3D=3D 0) + dxgprocess_adapter_destroy(adapter_info); +} diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index 61512463baa4..fbc15731cbd5 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -119,6 +119,9 @@ struct dxgglobal { /* protects acces to the global VM bus channel */ struct rw_semaphore channel_lock; =20 + /* protects the dxgprocess_adapter lists */ + struct mutex process_adapter_mutex; + bool dxg_dev_initialized; bool vmbus_registered; bool pci_registered; @@ -136,9 +139,31 @@ int dxgglobal_init_global_channel(void); void dxgglobal_destroy_global_channel(void); struct vmbus_channel *dxgglobal_get_vmbus(void); struct dxgvmbuschannel *dxgglobal_get_dxgvmbuschannel(void); +void dxgglobal_acquire_process_adapter_lock(void); +void dxgglobal_release_process_adapter_lock(void); int dxgglobal_acquire_channel_lock(void); void dxgglobal_release_channel_lock(void); =20 +/* + * Describes adapter information for each process + */ +struct dxgprocess_adapter { + /* Entry in dxgadapter::adapter_process_list_head */ + struct list_head adapter_process_list_entry; + /* Entry in dxgprocess::process_adapter_list_head */ + struct list_head process_adapter_list_entry; + struct dxgadapter *adapter; + struct dxgprocess *process; + int refcount; +}; + +struct dxgprocess_adapter *dxgprocess_adapter_create(struct dxgprocess *pr= ocess, + struct dxgadapter + *adapter); +void dxgprocess_adapter_release(struct dxgprocess_adapter *adapter); +void dxgprocess_adapter_stop(struct dxgprocess_adapter *adapter_info); +void dxgprocess_adapter_destroy(struct dxgprocess_adapter *adapter_info); + /* * The structure represents a process, which opened the /dev/dxg device. * A corresponding object is created on the host. @@ -167,15 +192,31 @@ struct dxgprocess { struct hmgrtable local_handle_table; /* Handle of the corresponding objec on the host */ struct d3dkmthandle host_handle; + + /* List of opened adapters (dxgprocess_adapter) */ + struct list_head process_adapter_list_head; }; =20 struct dxgprocess *dxgprocess_create(void); void dxgprocess_destroy(struct dxgprocess *process); void dxgprocess_release(struct kref *refcount); +int dxgprocess_open_adapter(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmthandle *handle); +int dxgprocess_close_adapter(struct dxgprocess *process, + struct d3dkmthandle handle); +struct dxgadapter *dxgprocess_get_adapter(struct dxgprocess *process, + struct d3dkmthandle handle); +struct dxgadapter *dxgprocess_adapter_by_handle(struct dxgprocess *process, + struct d3dkmthandle handle); void dxgprocess_ht_lock_shared_down(struct dxgprocess *process); void dxgprocess_ht_lock_shared_up(struct dxgprocess *process); void dxgprocess_ht_lock_exclusive_down(struct dxgprocess *process); void dxgprocess_ht_lock_exclusive_up(struct dxgprocess *process); +struct dxgprocess_adapter *dxgprocess_get_adapter_info(struct dxgprocess + *process, + struct dxgadapter + *adapter); =20 enum dxgadapter_state { DXGADAPTER_STATE_ACTIVE =3D 0, @@ -194,6 +235,8 @@ struct dxgadapter { struct kref adapter_kref; /* Entry in the list of adapters in dxgglobal */ struct list_head adapter_list_entry; + /* The list of dxgprocess_adapter entries */ + struct list_head adapter_process_list_head; struct pci_dev *pci_dev; struct hv_device *hv_dev; struct dxgvmbuschannel channel; @@ -217,6 +260,9 @@ void dxgadapter_release_lock_shared(struct dxgadapter *= adapter); int dxgadapter_acquire_lock_exclusive(struct dxgadapter *adapter); void dxgadapter_acquire_lock_forced(struct dxgadapter *adapter); void dxgadapter_release_lock_exclusive(struct dxgadapter *adapter); +void dxgadapter_add_process(struct dxgadapter *adapter, + struct dxgprocess_adapter *process_info); +void dxgadapter_remove_process(struct dxgprocess_adapter *process_info); =20 void init_ioctls(void); long dxgk_compat_ioctl(struct file *f, unsigned int p1, unsigned long p2); @@ -251,6 +297,9 @@ int dxgvmb_send_destroy_process(struct d3dkmthandle pro= cess); int dxgvmb_send_open_adapter(struct dxgadapter *adapter); int dxgvmb_send_close_adapter(struct dxgadapter *adapter); int dxgvmb_send_get_internal_adapter_info(struct dxgadapter *adapter); +int dxgvmb_send_query_adapter_info(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_queryadapterinfo *args); int dxgvmb_send_async_msg(struct dxgvmbuschannel *channel, void *command, u32 cmd_size); diff --git a/drivers/hv/dxgkrnl/dxgmodule.c b/drivers/hv/dxgkrnl/dxgmodule.c index 64ac35e1863b..fafe0b6a6389 100644 --- a/drivers/hv/dxgkrnl/dxgmodule.c +++ b/drivers/hv/dxgkrnl/dxgmodule.c @@ -124,6 +124,16 @@ static struct dxgadapter *find_adapter(struct winluid = *luid) return adapter; } =20 +void dxgglobal_acquire_process_adapter_lock(void) +{ + mutex_lock(&dxgglobal->process_adapter_mutex); +} + +void dxgglobal_release_process_adapter_lock(void) +{ + mutex_unlock(&dxgglobal->process_adapter_mutex); +} + /* * Creates a new dxgadapter object, which represents a virtual GPU, projec= ted * by the host. @@ -147,6 +157,7 @@ int dxgglobal_create_adapter(struct pci_dev *dev, guid_= t *guid, kref_init(&adapter->adapter_kref); init_rwsem(&adapter->core_lock); =20 + INIT_LIST_HEAD(&adapter->adapter_process_list_head); adapter->pci_dev =3D dev; guid_to_luid(guid, &adapter->luid); =20 @@ -721,6 +732,7 @@ static int dxgglobal_create(void) INIT_LIST_HEAD(&dxgglobal->plisthead); mutex_init(&dxgglobal->plistmutex); mutex_init(&dxgglobal->device_mutex); + mutex_init(&dxgglobal->process_adapter_mutex); =20 INIT_LIST_HEAD(&dxgglobal->thread_info_list_head); mutex_init(&dxgglobal->thread_info_mutex); diff --git a/drivers/hv/dxgkrnl/dxgprocess.c b/drivers/hv/dxgkrnl/dxgproces= s.c index 2a86ba1b4b1b..1fd7b7659792 100644 --- a/drivers/hv/dxgkrnl/dxgprocess.c +++ b/drivers/hv/dxgkrnl/dxgprocess.c @@ -47,6 +47,7 @@ struct dxgprocess *dxgprocess_create(void) =20 hmgrtable_init(&process->handle_table, process); hmgrtable_init(&process->local_handle_table, process); + INIT_LIST_HEAD(&process->process_adapter_list_head); } } return process; @@ -54,6 +55,35 @@ struct dxgprocess *dxgprocess_create(void) =20 void dxgprocess_destroy(struct dxgprocess *process) { + int i; + enum hmgrentry_type t; + struct d3dkmthandle h; + void *o; + struct dxgprocess_adapter *entry; + struct dxgprocess_adapter *tmp; + + /* Destroy all adapter state */ + dxgglobal_acquire_process_adapter_lock(); + list_for_each_entry_safe(entry, tmp, + &process->process_adapter_list_head, + process_adapter_list_entry) { + dxgprocess_adapter_destroy(entry); + } + dxgglobal_release_process_adapter_lock(); + + i =3D 0; + while (hmgrtable_next_entry(&process->local_handle_table, + &i, &t, &h, &o)) { + switch (t) { + case HMGRENTRY_TYPE_DXGADAPTER: + dxgprocess_close_adapter(process, h); + break; + default: + pr_err("invalid entry in local handle table %d", t); + break; + } + } + hmgrtable_destroy(&process->handle_table); hmgrtable_destroy(&process->local_handle_table); } @@ -76,6 +106,142 @@ void dxgprocess_release(struct kref *refcount) vfree(process); } =20 +struct dxgprocess_adapter *dxgprocess_get_adapter_info(struct dxgprocess + *process, + struct dxgadapter + *adapter) +{ + struct dxgprocess_adapter *entry; + + list_for_each_entry(entry, &process->process_adapter_list_head, + process_adapter_list_entry) { + if (adapter =3D=3D entry->adapter) { + pr_debug("Found process info %p", entry); + return entry; + } + } + return NULL; +} + +/* + * Dxgprocess takes references on dxgadapter and dxgprocess_adapter. + */ +int dxgprocess_open_adapter(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmthandle *h) +{ + int ret =3D 0; + struct dxgprocess_adapter *adapter_info; + struct d3dkmthandle handle; + + h->v =3D 0; + adapter_info =3D dxgprocess_get_adapter_info(process, adapter); + if (adapter_info =3D=3D NULL) { + pr_debug("creating new process adapter info\n"); + adapter_info =3D dxgprocess_adapter_create(process, adapter); + if (adapter_info =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + } else { + adapter_info->refcount++; + } + + handle =3D hmgrtable_alloc_handle_safe(&process->local_handle_table, + adapter, HMGRENTRY_TYPE_DXGADAPTER, + true); + if (handle.v) { + *h =3D handle; + } else { + pr_err("failed to create adapter handle\n"); + ret =3D -ENOMEM; + goto cleanup; + } + +cleanup: + + if (ret < 0) { + if (adapter_info) { + dxgglobal_acquire_process_adapter_lock(); + dxgprocess_adapter_release(adapter_info); + dxgglobal_release_process_adapter_lock(); + } + } + + return ret; +} + +int dxgprocess_close_adapter(struct dxgprocess *process, + struct d3dkmthandle handle) +{ + struct dxgadapter *adapter; + struct dxgprocess_adapter *adapter_info; + int ret =3D 0; + + if (handle.v =3D=3D 0) + return 0; + + hmgrtable_lock(&process->local_handle_table, DXGLOCK_EXCL); + adapter =3D dxgprocess_get_adapter(process, handle); + if (adapter) + hmgrtable_free_handle(&process->local_handle_table, + HMGRENTRY_TYPE_DXGADAPTER, handle); + hmgrtable_unlock(&process->local_handle_table, DXGLOCK_EXCL); + + if (adapter) { + adapter_info =3D dxgprocess_get_adapter_info(process, adapter); + if (adapter_info) { + dxgglobal_acquire_process_adapter_lock(); + dxgprocess_adapter_release(adapter_info); + dxgglobal_release_process_adapter_lock(); + } else { + ret =3D -EINVAL; + } + } else { + pr_err("%s failed %x", __func__, handle.v); + ret =3D -EINVAL; + } + + return ret; +} + +struct dxgadapter *dxgprocess_get_adapter(struct dxgprocess *process, + struct d3dkmthandle handle) +{ + struct dxgadapter *adapter; + + adapter =3D hmgrtable_get_object_by_type(&process->local_handle_table, + HMGRENTRY_TYPE_DXGADAPTER, + handle); + if (adapter =3D=3D NULL) + pr_err("%s failed %x\n", __func__, handle.v); + return adapter; +} + +/* + * Gets the adapter object from the process handle table. + * The adapter object is referenced. + * The function acquired the handle table lock shared. + */ +struct dxgadapter *dxgprocess_adapter_by_handle(struct dxgprocess *process, + struct d3dkmthandle handle) +{ + struct dxgadapter *adapter; + + hmgrtable_lock(&process->local_handle_table, DXGLOCK_SHARED); + adapter =3D hmgrtable_get_object_by_type(&process->local_handle_table, + HMGRENTRY_TYPE_DXGADAPTER, + handle); + if (adapter =3D=3D NULL) + pr_err("adapter_by_handle failed %x\n", handle.v); + else if (kref_get_unless_zero(&adapter->adapter_kref) =3D=3D 0) { + pr_err("failed to acquire adapter reference\n"); + adapter =3D NULL; + } + hmgrtable_unlock(&process->local_handle_table, DXGLOCK_SHARED); + return adapter; +} + void dxgprocess_ht_lock_shared_down(struct dxgprocess *process) { hmgrtable_lock(&process->handle_table, DXGLOCK_SHARED); diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index 056d86c1859a..8b8e0aa0fa5d 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -655,3 +655,85 @@ int dxgvmb_send_get_internal_adapter_info(struct dxgad= apter *adapter) pr_debug("err: %s %d", __func__, ret); return ret; } + +int dxgvmb_send_query_adapter_info(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_queryadapterinfo *args) +{ + struct dxgkvmb_command_queryadapterinfo *command; + u32 cmd_size =3D sizeof(*command) + args->private_data_size - 1; + int ret; + u32 private_data_size; + void *private_data; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, adapter, process, cmd_size); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + ret =3D copy_from_user(command->private_data, + args->private_data, args->private_data_size); + if (ret) { + pr_err("%s Faled to copy private data", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_QUERYADAPTERINFO, + process->host_handle); + command->private_data_size =3D args->private_data_size; + command->query_type =3D args->type; + + if (dxgglobal->vmbus_ver >=3D DXGK_VMBUS_INTERFACE_VERSION) { + private_data =3D msg.msg; + private_data_size =3D command->private_data_size + + sizeof(struct ntstatus); + } else { + private_data =3D command->private_data; + private_data_size =3D command->private_data_size; + } + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, + private_data, private_data_size); + if (ret < 0) + goto cleanup; + + if (dxgglobal->vmbus_ver >=3D DXGK_VMBUS_INTERFACE_VERSION) { + ret =3D ntstatus2int(*(struct ntstatus *)private_data); + if (ret < 0) + goto cleanup; + private_data =3D (char *)private_data + sizeof(struct ntstatus); + } + + switch (args->type) { + case _KMTQAITYPE_ADAPTERTYPE: + case _KMTQAITYPE_ADAPTERTYPE_RENDER: + { + struct d3dkmt_adaptertype *adapter_type =3D + (void *)private_data; + adapter_type->paravirtualized =3D 1; + adapter_type->display_supported =3D 0; + adapter_type->post_device =3D 0; + adapter_type->indirect_display_device =3D 0; + adapter_type->acg_supported =3D 0; + adapter_type->support_set_timings_from_vidpn =3D 0; + break; + } + default: + break; + } + ret =3D copy_to_user(args->private_data, private_data, + args->private_data_size); + if (ret) { + pr_err("%s Faled to copy private data to user", __func__); + ret =3D -EINVAL; + } + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index fa7fc321addb..62a958f6f146 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -35,6 +35,408 @@ static char *errorstr(int ret) return ret < 0 ? "err" : ""; } =20 +static int dxgk_open_adapter_from_luid(struct dxgprocess *process, + void *__user inargs) +{ + struct d3dkmt_openadapterfromluid args; + int ret; + struct dxgadapter *entry; + struct dxgadapter *adapter =3D NULL; + struct d3dkmt_openadapterfromluid *__user result =3D inargs; + + pr_debug("ioctl: %s", __func__); + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s Faled to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + dxgglobal_acquire_adapter_list_lock(DXGLOCK_SHARED); + dxgglobal_acquire_process_adapter_lock(); + + list_for_each_entry(entry, &dxgglobal->adapter_list_head, + adapter_list_entry) { + if (dxgadapter_acquire_lock_shared(entry) =3D=3D 0) { + pr_debug("Compare luids: %d:%d %d:%d", + entry->luid.b, entry->luid.a, + args.adapter_luid.b, args.adapter_luid.a); + if (*(u64 *) &entry->luid =3D=3D + *(u64 *) &args.adapter_luid) { + ret =3D + dxgprocess_open_adapter(process, entry, + &args.adapter_handle); + + if (ret >=3D 0) { + ret =3D copy_to_user( + &result->adapter_handle, + &args.adapter_handle, + sizeof(struct d3dkmthandle)); + if (ret) + ret =3D -EINVAL; + } + adapter =3D entry; + } + dxgadapter_release_lock_shared(entry); + if (adapter) + break; + } + } + + dxgglobal_release_process_adapter_lock(); + dxgglobal_release_adapter_list_lock(DXGLOCK_SHARED); + + if (args.adapter_handle.v =3D=3D 0) + ret =3D -EINVAL; + +cleanup: + + if (ret < 0) + dxgprocess_close_adapter(process, args.adapter_handle); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgkp_enum_adapters(struct dxgprocess *process, + union d3dkmt_enumadapters_filter filter, + u32 adapter_count_max, + struct d3dkmt_adapterinfo *__user info_out, + u32 * __user adapter_count_out) +{ + int ret =3D 0; + struct dxgadapter *entry; + struct d3dkmt_adapterinfo *info =3D NULL; + struct dxgadapter **adapters =3D NULL; + int adapter_count =3D 0; + int i; + + pr_debug("ioctl: %s", __func__); + if (info_out =3D=3D NULL || adapter_count_max =3D=3D 0) { + pr_debug("buffer is NULL"); + ret =3D copy_to_user(adapter_count_out, + &dxgglobal->num_adapters, sizeof(u32)); + if (ret) { + pr_err("%s copy_to_user faled", __func__); + ret =3D -EINVAL; + } + goto cleanup; + } + + if (adapter_count_max > 0xFFFF) { + pr_err("too many adapters"); + ret =3D -EINVAL; + goto cleanup; + } + + info =3D vzalloc(sizeof(struct d3dkmt_adapterinfo) * adapter_count_max); + if (info =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + + adapters =3D vzalloc(sizeof(struct dxgadapter *) * adapter_count_max); + if (adapters =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + + dxgglobal_acquire_adapter_list_lock(DXGLOCK_SHARED); + dxgglobal_acquire_process_adapter_lock(); + + list_for_each_entry(entry, &dxgglobal->adapter_list_head, + adapter_list_entry) { + if (dxgadapter_acquire_lock_shared(entry) =3D=3D 0) { + struct d3dkmt_adapterinfo *inf =3D &info[adapter_count]; + + ret =3D dxgprocess_open_adapter(process, entry, + &inf->adapter_handle); + if (ret >=3D 0) { + inf->adapter_luid =3D entry->luid; + adapters[adapter_count] =3D entry; + pr_debug("adapter: %x %x:%x", + inf->adapter_handle.v, + inf->adapter_luid.b, + inf->adapter_luid.a); + adapter_count++; + } + dxgadapter_release_lock_shared(entry); + } + if (ret < 0) + break; + } + + dxgglobal_release_process_adapter_lock(); + dxgglobal_release_adapter_list_lock(DXGLOCK_SHARED); + + if (adapter_count > adapter_count_max) { + ret =3D STATUS_BUFFER_TOO_SMALL; + pr_debug("Too many adapters"); + ret =3D copy_to_user(adapter_count_out, + &dxgglobal->num_adapters, sizeof(u32)); + if (ret) { + pr_err("%s copy_to_user failed", __func__); + ret =3D -EINVAL; + } + goto cleanup; + } + + ret =3D copy_to_user(adapter_count_out, &adapter_count, + sizeof(adapter_count)); + if (ret) { + pr_err("%s failed to copy adapter_count", __func__); + ret =3D -EINVAL; + goto cleanup; + } + ret =3D copy_to_user(info_out, info, sizeof(info[0]) * adapter_count); + if (ret) { + pr_err("%s failed to copy adapter info", __func__); + ret =3D -EINVAL; + } + +cleanup: + + if (ret >=3D 0) { + pr_debug("found %d adapters", adapter_count); + goto success; + } + if (info) { + for (i =3D 0; i < adapter_count; i++) + dxgprocess_close_adapter(process, + info[i].adapter_handle); + } +success: + if (info) + vfree(info); + if (adapters) + vfree(adapters); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_enum_adapters(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmt_enumadapters2 args; + int ret; + struct dxgadapter *entry; + struct d3dkmt_adapterinfo *info =3D NULL; + struct dxgadapter **adapters =3D NULL; + int adapter_count =3D 0; + int i; + + pr_debug("ioctl: %s", __func__); + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.adapters =3D=3D NULL) { + pr_debug("buffer is NULL"); + args.num_adapters =3D dxgglobal->num_adapters; + ret =3D copy_to_user(inargs, &args, sizeof(args)); + if (ret) { + pr_err("%s failed to copy args to user", __func__); + ret =3D -EINVAL; + } + goto cleanup; + } + if (args.num_adapters < dxgglobal->num_adapters) { + args.num_adapters =3D dxgglobal->num_adapters; + pr_debug("buffer is too small"); + ret =3D -EOVERFLOW; + goto cleanup; + } + + if (args.num_adapters > D3DKMT_ADAPTERS_MAX) { + pr_debug("too many adapters"); + ret =3D -EINVAL; + goto cleanup; + } + + info =3D vzalloc(sizeof(struct d3dkmt_adapterinfo) * args.num_adapters); + if (info =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + + adapters =3D vzalloc(sizeof(struct dxgadapter *) * args.num_adapters); + if (adapters =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + + dxgglobal_acquire_adapter_list_lock(DXGLOCK_SHARED); + dxgglobal_acquire_process_adapter_lock(); + + list_for_each_entry(entry, &dxgglobal->adapter_list_head, + adapter_list_entry) { + if (dxgadapter_acquire_lock_shared(entry) =3D=3D 0) { + struct d3dkmt_adapterinfo *inf =3D &info[adapter_count]; + + ret =3D dxgprocess_open_adapter(process, entry, + &inf->adapter_handle); + if (ret >=3D 0) { + inf->adapter_luid =3D entry->luid; + adapters[adapter_count] =3D entry; + pr_debug("adapter: %x %llx", + inf->adapter_handle.v, + *(u64 *) &inf->adapter_luid); + adapter_count++; + } + dxgadapter_release_lock_shared(entry); + } + if (ret < 0) + break; + } + + dxgglobal_release_process_adapter_lock(); + dxgglobal_release_adapter_list_lock(DXGLOCK_SHARED); + + args.num_adapters =3D adapter_count; + + ret =3D copy_to_user(inargs, &args, sizeof(args)); + if (ret) { + pr_err("%s failed to copy args to user", __func__); + ret =3D -EINVAL; + goto cleanup; + } + ret =3D copy_to_user(args.adapters, info, + sizeof(info[0]) * args.num_adapters); + if (ret) { + pr_err("%s failed to copy adapter info to user", __func__); + ret =3D -EINVAL; + } + +cleanup: + + if (ret < 0) { + if (info) { + for (i =3D 0; i < args.num_adapters; i++) { + dxgprocess_close_adapter(process, + info[i].adapter_handle); + } + } + } else { + pr_debug("found %d adapters", args.num_adapters); + } + + if (info) + vfree(info); + if (adapters) + vfree(adapters); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_enum_adapters3(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmt_enumadapters3 args; + int ret; + + pr_debug("ioctl: %s", __func__); + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgkp_enum_adapters(process, args.filter, + args.adapter_count, + args.adapters, + &((struct d3dkmt_enumadapters3 *)inargs)-> + adapter_count); + +cleanup: + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_close_adapter(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmthandle args; + int ret; + + pr_debug("ioctl: %s", __func__); + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgprocess_close_adapter(process, args); + if (ret < 0) + pr_err("%s failed", __func__); + +cleanup: + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_query_adapter_info(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmt_queryadapterinfo args; + int ret; + struct dxgadapter *adapter =3D NULL; + + pr_debug("ioctl: %s", __func__); + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.private_data_size > DXG_MAX_VM_BUS_PACKET_SIZE || + args.private_data_size =3D=3D 0) { + pr_err("invalid private data size"); + ret =3D -EINVAL; + goto cleanup; + } + + pr_debug("Type: %d Size: %x", + args.type, args.private_data_size); + + adapter =3D dxgprocess_adapter_by_handle(process, args.adapter); + if (adapter =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) + goto cleanup; + + ret =3D dxgvmb_send_query_adapter_info(process, adapter, &args); + + dxgadapter_release_lock_shared(adapter); + +cleanup: + + if (adapter) + kref_put(&adapter->adapter_kref, dxgadapter_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + /* * IOCTL processing * The driver IOCTLs return @@ -91,4 +493,14 @@ long dxgk_unlocked_ioctl(struct file *f, unsigned int p= 1, unsigned long p2) =20 void init_ioctls(void) { + SET_IOCTL(/*0x1 */ dxgk_open_adapter_from_luid, + LX_DXOPENADAPTERFROMLUID); + SET_IOCTL(/*0x9 */ dxgk_query_adapter_info, + LX_DXQUERYADAPTERINFO); + SET_IOCTL(/*0x14 */ dxgk_enum_adapters, + LX_DXENUMADAPTERS2); + SET_IOCTL(/*0x15 */ dxgk_close_adapter, + LX_DXCLOSEADAPTER); + SET_IOCTL(/*0x3e */ dxgk_enum_adapters3, + LX_DXENUMADAPTERS3); } diff --git a/drivers/hv/dxgkrnl/misc.h b/drivers/hv/dxgkrnl/misc.h index 433b59d3eb23..d00e7cc00470 100644 --- a/drivers/hv/dxgkrnl/misc.h +++ b/drivers/hv/dxgkrnl/misc.h @@ -31,6 +31,7 @@ extern const struct d3dkmthandle zerohandle; * table_lock * core_lock * device_lock + * process_adapter_mutex * adapter_list_lock * device_mutex */ --=20 2.35.1 From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 6973DC433EF for ; Sat, 5 Feb 2022 02:34:39 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1379080AbiBECei (ORCPT ); Fri, 4 Feb 2022 21:34:38 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45108 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1378997AbiBECeY (ORCPT ); Fri, 4 Feb 2022 21:34:24 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id 0122A20B8013; Fri, 4 Feb 2022 18:34:23 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com 0122A20B8013 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028464; bh=CMdGZRlhMdcOXOPZIsWCIf52c+KFQSKTAraiwATUkKg=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=RGpaGCGayIqJ7ASKvX5EUinTct7+MBtR1jfVeGTHWvtjbvPWO3xfNFTiKDuuF7gIf 2gPQNZK6OwX1kkCOtWEsFjfRNoL6yICVQQppf61od/tIeyQKXcyBh1IbTKeNJ7Lzuj CTFwFbUoHphZaehqgKaeyXHul3FTR3s5/irOK6fQ= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 04/24] drivers: hv: dxgkrnl: Creation of dxgdevice Date: Fri, 4 Feb 2022 18:34:02 -0800 Message-Id: <3cd773385baf50fba168d3c293363cd4584ad77c.1644025661.git.iourit@linux.microsoft.com> X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" A dxgdevice object represents a container of GPU allocations, GPU sync objects, GPU contexts, etc. It belongs to a dxgadapter object. Signed-off-by: Iouri Tarassov --- drivers/hv/dxgkrnl/dxgadapter.c | 183 ++++++++++++++++++++++++++++++++ drivers/hv/dxgkrnl/dxgkrnl.h | 52 +++++++++ drivers/hv/dxgkrnl/dxgprocess.c | 43 ++++++++ drivers/hv/dxgkrnl/dxgvmbus.c | 54 ++++++++++ drivers/hv/dxgkrnl/ioctl.c | 134 +++++++++++++++++++++++ drivers/hv/dxgkrnl/misc.h | 1 + 6 files changed, 467 insertions(+) diff --git a/drivers/hv/dxgkrnl/dxgadapter.c b/drivers/hv/dxgkrnl/dxgadapte= r.c index 2c7823713547..c7e1dc55de49 100644 --- a/drivers/hv/dxgkrnl/dxgadapter.c +++ b/drivers/hv/dxgkrnl/dxgadapter.c @@ -199,6 +199,120 @@ void dxgadapter_release_lock_shared(struct dxgadapter= *adapter) up_read(&adapter->core_lock); } =20 +struct dxgdevice *dxgdevice_create(struct dxgadapter *adapter, + struct dxgprocess *process) +{ + struct dxgdevice *device =3D vzalloc(sizeof(struct dxgdevice)); + int ret; + + if (device) { + kref_init(&device->device_kref); + device->adapter =3D adapter; + device->process =3D process; + kref_get(&adapter->adapter_kref); + init_rwsem(&device->device_lock); + INIT_LIST_HEAD(&device->pqueue_list_head); + device->object_state =3D DXGOBJECTSTATE_CREATED; + device->execution_state =3D _D3DKMT_DEVICEEXECUTION_ACTIVE; + + ret =3D dxgprocess_adapter_add_device(process, adapter, device); + if (ret < 0) { + kref_put(&device->device_kref, dxgdevice_release); + device =3D NULL; + } + } + return device; +} + +void dxgdevice_stop(struct dxgdevice *device) +{ +} + +void dxgdevice_mark_destroyed(struct dxgdevice *device) +{ + down_write(&device->device_lock); + device->object_state =3D DXGOBJECTSTATE_DESTROYED; + up_write(&device->device_lock); +} + +void dxgdevice_destroy(struct dxgdevice *device) +{ + struct dxgprocess *process =3D device->process; + struct dxgadapter *adapter =3D device->adapter; + struct d3dkmthandle device_handle =3D {}; + + pr_debug("%s: %p\n", __func__, device); + + down_write(&device->device_lock); + + if (device->object_state !=3D DXGOBJECTSTATE_ACTIVE) + goto cleanup; + + device->object_state =3D DXGOBJECTSTATE_DESTROYED; + + dxgdevice_stop(device); + + /* Guest handles need to be released before the host handles */ + hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL); + if (device->handle_valid) { + hmgrtable_free_handle(&process->handle_table, + HMGRENTRY_TYPE_DXGDEVICE, device->handle); + device_handle =3D device->handle; + device->handle_valid =3D 0; + } + hmgrtable_unlock(&process->handle_table, DXGLOCK_EXCL); + + if (device_handle.v) { + up_write(&device->device_lock); + if (dxgadapter_acquire_lock_shared(adapter) =3D=3D 0) { + dxgvmb_send_destroy_device(adapter, process, + device_handle); + dxgadapter_release_lock_shared(adapter); + } + down_write(&device->device_lock); + } + +cleanup: + + if (device->adapter) { + dxgprocess_adapter_remove_device(device); + kref_put(&device->adapter->adapter_kref, dxgadapter_release); + } + + up_write(&device->device_lock); + + kref_put(&device->device_kref, dxgdevice_release); + pr_debug("dxgdevice_destroy_end\n"); +} + +int dxgdevice_acquire_lock_shared(struct dxgdevice *device) +{ + down_read(&device->device_lock); + if (!dxgdevice_is_active(device)) { + up_read(&device->device_lock); + return -ENODEV; + } + return 0; +} + +void dxgdevice_release_lock_shared(struct dxgdevice *device) +{ + up_read(&device->device_lock); +} + +bool dxgdevice_is_active(struct dxgdevice *device) +{ + return device->object_state =3D=3D DXGOBJECTSTATE_ACTIVE; +} + +void dxgdevice_release(struct kref *refcount) +{ + struct dxgdevice *device; + + device =3D container_of(refcount, struct dxgdevice, device_kref); + vfree(device); +} + struct dxgprocess_adapter *dxgprocess_adapter_create(struct dxgprocess *pr= ocess, struct dxgadapter *adapter) { @@ -213,6 +327,8 @@ struct dxgprocess_adapter *dxgprocess_adapter_create(st= ruct dxgprocess *process, adapter_info->adapter =3D adapter; adapter_info->process =3D process; adapter_info->refcount =3D 1; + mutex_init(&adapter_info->device_list_mutex); + INIT_LIST_HEAD(&adapter_info->device_list_head); list_add_tail(&adapter_info->process_adapter_list_entry, &process->process_adapter_list_head); dxgadapter_add_process(adapter, adapter_info); @@ -226,10 +342,32 @@ struct dxgprocess_adapter *dxgprocess_adapter_create(= struct dxgprocess *process, =20 void dxgprocess_adapter_stop(struct dxgprocess_adapter *adapter_info) { + struct dxgdevice *device; + + mutex_lock(&adapter_info->device_list_mutex); + list_for_each_entry(device, &adapter_info->device_list_head, + device_list_entry) { + dxgdevice_stop(device); + } + mutex_unlock(&adapter_info->device_list_mutex); } =20 void dxgprocess_adapter_destroy(struct dxgprocess_adapter *adapter_info) { + struct dxgdevice *device; + + mutex_lock(&adapter_info->device_list_mutex); + while (!list_empty(&adapter_info->device_list_head)) { + device =3D list_first_entry(&adapter_info->device_list_head, + struct dxgdevice, device_list_entry); + list_del(&device->device_list_entry); + device->device_list_entry.next =3D NULL; + mutex_unlock(&adapter_info->device_list_mutex); + dxgdevice_destroy(device); + mutex_lock(&adapter_info->device_list_mutex); + } + mutex_unlock(&adapter_info->device_list_mutex); + dxgadapter_remove_process(adapter_info); kref_put(&adapter_info->adapter->adapter_kref, dxgadapter_release); list_del(&adapter_info->process_adapter_list_entry); @@ -247,3 +385,48 @@ void dxgprocess_adapter_release(struct dxgprocess_adap= ter *adapter_info) if (adapter_info->refcount =3D=3D 0) dxgprocess_adapter_destroy(adapter_info); } + +int dxgprocess_adapter_add_device(struct dxgprocess *process, + struct dxgadapter *adapter, + struct dxgdevice *device) +{ + struct dxgprocess_adapter *entry; + struct dxgprocess_adapter *adapter_info =3D NULL; + int ret =3D 0; + + dxgglobal_acquire_process_adapter_lock(); + + list_for_each_entry(entry, &process->process_adapter_list_head, + process_adapter_list_entry) { + if (entry->adapter =3D=3D adapter) { + adapter_info =3D entry; + break; + } + } + if (adapter_info =3D=3D NULL) { + pr_err("failed to find process adapter info\n"); + ret =3D -EINVAL; + goto cleanup; + } + mutex_lock(&adapter_info->device_list_mutex); + list_add_tail(&device->device_list_entry, + &adapter_info->device_list_head); + device->adapter_info =3D adapter_info; + mutex_unlock(&adapter_info->device_list_mutex); + +cleanup: + + dxgglobal_release_process_adapter_lock(); + return ret; +} + +void dxgprocess_adapter_remove_device(struct dxgdevice *device) +{ + pr_debug("%s %p\n", __func__, device); + mutex_lock(&device->adapter_info->device_list_mutex); + if (device->device_list_entry.next) { + list_del(&device->device_list_entry); + device->device_list_entry.next =3D NULL; + } + mutex_unlock(&device->adapter_info->device_list_mutex); +} diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index fbc15731cbd5..e0a433c36a06 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -29,6 +29,7 @@ =20 struct dxgprocess; struct dxgadapter; +struct dxgdevice; =20 #include "misc.h" #include "hmgr.h" @@ -152,6 +153,9 @@ struct dxgprocess_adapter { struct list_head adapter_process_list_entry; /* Entry in dxgprocess::process_adapter_list_head */ struct list_head process_adapter_list_entry; + /* List of all dxgdevice objects created for the process on adapter */ + struct list_head device_list_head; + struct mutex device_list_mutex; struct dxgadapter *adapter; struct dxgprocess *process; int refcount; @@ -161,6 +165,10 @@ struct dxgprocess_adapter *dxgprocess_adapter_create(s= truct dxgprocess *process, struct dxgadapter *adapter); void dxgprocess_adapter_release(struct dxgprocess_adapter *adapter); +int dxgprocess_adapter_add_device(struct dxgprocess *process, + struct dxgadapter *adapter, + struct dxgdevice *device); +void dxgprocess_adapter_remove_device(struct dxgdevice *device); void dxgprocess_adapter_stop(struct dxgprocess_adapter *adapter_info); void dxgprocess_adapter_destroy(struct dxgprocess_adapter *adapter_info); =20 @@ -209,6 +217,11 @@ struct dxgadapter *dxgprocess_get_adapter(struct dxgpr= ocess *process, struct d3dkmthandle handle); struct dxgadapter *dxgprocess_adapter_by_handle(struct dxgprocess *process, struct d3dkmthandle handle); +struct dxgdevice *dxgprocess_device_by_handle(struct dxgprocess *process, + struct d3dkmthandle handle); +struct dxgdevice *dxgprocess_device_by_object_handle(struct dxgprocess *pr= ocess, + enum hmgrentry_type t, + struct d3dkmthandle h); void dxgprocess_ht_lock_shared_down(struct dxgprocess *process); void dxgprocess_ht_lock_shared_up(struct dxgprocess *process); void dxgprocess_ht_lock_exclusive_down(struct dxgprocess *process); @@ -228,6 +241,7 @@ enum dxgadapter_state { * This object represents the grapchis adapter. * Objects, which take reference on the adapter: * - dxgglobal + * - dxgdevice * - adapter handle (struct d3dkmthandle) */ struct dxgadapter { @@ -264,6 +278,38 @@ void dxgadapter_add_process(struct dxgadapter *adapter, struct dxgprocess_adapter *process_info); void dxgadapter_remove_process(struct dxgprocess_adapter *process_info); =20 +/* + * The object represent the device object. + * The following objects take reference on the device + * - device handle (struct d3dkmthandle) + */ +struct dxgdevice { + enum dxgobjectstate object_state; + /* Device takes reference on the adapter */ + struct dxgadapter *adapter; + struct dxgprocess_adapter *adapter_info; + struct dxgprocess *process; + /* Entry in the DGXPROCESS_ADAPTER device list */ + struct list_head device_list_entry; + struct kref device_kref; + /* Protects destcruction of the device object */ + struct rw_semaphore device_lock; + /* List of paging queues. Protected by process handle table lock. */ + struct list_head pqueue_list_head; + struct d3dkmthandle handle; + enum d3dkmt_deviceexecution_state execution_state; + u32 handle_valid; +}; + +struct dxgdevice *dxgdevice_create(struct dxgadapter *a, struct dxgprocess= *p); +void dxgdevice_destroy(struct dxgdevice *device); +void dxgdevice_stop(struct dxgdevice *device); +void dxgdevice_mark_destroyed(struct dxgdevice *device); +int dxgdevice_acquire_lock_shared(struct dxgdevice *dev); +void dxgdevice_release_lock_shared(struct dxgdevice *dev); +void dxgdevice_release(struct kref *refcount); +bool dxgdevice_is_active(struct dxgdevice *dev); + void init_ioctls(void); long dxgk_compat_ioctl(struct file *f, unsigned int p1, unsigned long p2); long dxgk_unlocked_ioctl(struct file *f, unsigned int p1, unsigned long p2= ); @@ -297,6 +343,12 @@ int dxgvmb_send_destroy_process(struct d3dkmthandle pr= ocess); int dxgvmb_send_open_adapter(struct dxgadapter *adapter); int dxgvmb_send_close_adapter(struct dxgadapter *adapter); int dxgvmb_send_get_internal_adapter_info(struct dxgadapter *adapter); +struct d3dkmthandle dxgvmb_send_create_device(struct dxgadapter *adapter, + struct dxgprocess *process, + struct d3dkmt_createdevice *args); +int dxgvmb_send_destroy_device(struct dxgadapter *adapter, + struct dxgprocess *process, + struct d3dkmthandle h); int dxgvmb_send_query_adapter_info(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_queryadapterinfo *args); diff --git a/drivers/hv/dxgkrnl/dxgprocess.c b/drivers/hv/dxgkrnl/dxgproces= s.c index 1fd7b7659792..734585689213 100644 --- a/drivers/hv/dxgkrnl/dxgprocess.c +++ b/drivers/hv/dxgkrnl/dxgprocess.c @@ -242,6 +242,49 @@ struct dxgadapter *dxgprocess_adapter_by_handle(struct= dxgprocess *process, return adapter; } =20 +struct dxgdevice *dxgprocess_device_by_object_handle(struct dxgprocess *pr= ocess, + enum hmgrentry_type t, + struct d3dkmthandle handle) +{ + struct dxgdevice *device =3D NULL; + void *obj; + + hmgrtable_lock(&process->handle_table, DXGLOCK_SHARED); + obj =3D hmgrtable_get_object_by_type(&process->handle_table, t, handle); + if (obj) { + struct d3dkmthandle device_handle =3D {}; + + switch (t) { + case HMGRENTRY_TYPE_DXGDEVICE: + device =3D obj; + break; + default: + pr_err("invalid handle type: %d\n", t); + break; + } + if (device =3D=3D NULL) + device =3D hmgrtable_get_object_by_type( + &process->handle_table, + HMGRENTRY_TYPE_DXGDEVICE, + device_handle); + if (device) + if (kref_get_unless_zero(&device->device_kref) =3D=3D 0) + device =3D NULL; + } + if (device =3D=3D NULL) + pr_err("device_by_handle failed: %d %x\n", t, handle.v); + hmgrtable_unlock(&process->handle_table, DXGLOCK_SHARED); + return device; +} + +struct dxgdevice *dxgprocess_device_by_handle(struct dxgprocess *process, + struct d3dkmthandle handle) +{ + return dxgprocess_device_by_object_handle(process, + HMGRENTRY_TYPE_DXGDEVICE, + handle); +} + void dxgprocess_ht_lock_shared_down(struct dxgprocess *process) { hmgrtable_lock(&process->handle_table, DXGLOCK_SHARED); diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index 8b8e0aa0fa5d..5b560754ac0d 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -656,6 +656,60 @@ int dxgvmb_send_get_internal_adapter_info(struct dxgad= apter *adapter) return ret; } =20 +struct d3dkmthandle dxgvmb_send_create_device(struct dxgadapter *adapter, + struct dxgprocess *process, + struct d3dkmt_createdevice *args) +{ + int ret; + struct dxgkvmb_command_createdevice *command; + struct dxgkvmb_command_createdevice_return result =3D { }; + struct dxgvmbusmsg msg; + + ret =3D init_message(&msg, adapter, process, sizeof(*command)); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, DXGK_VMBCOMMAND_CREATEDEVICE, + process->host_handle); + command->flags =3D args->flags; + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, + &result, sizeof(result)); + if (ret < 0) + result.device.v =3D 0; + free_message(&msg, process); +cleanup: + if (ret) + pr_debug("err: %s %d", __func__, ret); + return result.device; +} + +int dxgvmb_send_destroy_device(struct dxgadapter *adapter, + struct dxgprocess *process, + struct d3dkmthandle h) +{ + int ret; + struct dxgkvmb_command_destroydevice *command; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, adapter, process, sizeof(*command)); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, DXGK_VMBCOMMAND_DESTROYDEVICE, + process->host_handle); + command->device =3D h; + + ret =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, msg.size); +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + int dxgvmb_send_query_adapter_info(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_queryadapterinfo *args) diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index 62a958f6f146..a6be88b6c792 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -437,6 +437,136 @@ dxgk_query_adapter_info(struct dxgprocess *process, v= oid *__user inargs) return ret; } =20 +static int +dxgk_create_device(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmt_createdevice args; + int ret; + struct dxgadapter *adapter =3D NULL; + struct dxgdevice *device =3D NULL; + struct d3dkmthandle host_device_handle =3D {}; + bool adapter_locked =3D false; + + pr_debug("ioctl: %s", __func__); + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + /* The call acquires reference on the adapter */ + adapter =3D dxgprocess_adapter_by_handle(process, args.adapter); + if (adapter =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + device =3D dxgdevice_create(adapter, process); + if (device =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) + goto cleanup; + + adapter_locked =3D true; + + host_device_handle =3D dxgvmb_send_create_device(adapter, process, &args); + if (host_device_handle.v) { + ret =3D copy_to_user(&((struct d3dkmt_createdevice *)inargs)-> + device, &host_device_handle, + sizeof(struct d3dkmthandle)); + if (ret) { + pr_err("%s failed to copy device handle", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL); + ret =3D hmgrtable_assign_handle(&process->handle_table, device, + HMGRENTRY_TYPE_DXGDEVICE, + host_device_handle); + if (ret >=3D 0) { + device->handle =3D host_device_handle; + device->handle_valid =3D 1; + device->object_state =3D DXGOBJECTSTATE_ACTIVE; + } + hmgrtable_unlock(&process->handle_table, DXGLOCK_EXCL); + } + +cleanup: + + if (ret < 0) { + if (host_device_handle.v) + dxgvmb_send_destroy_device(adapter, process, + host_device_handle); + if (device) + dxgdevice_destroy(device); + } + + if (adapter_locked) + dxgadapter_release_lock_shared(adapter); + + if (adapter) + kref_put(&adapter->adapter_kref, dxgadapter_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_destroy_device(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmt_destroydevice args; + int ret; + struct dxgadapter *adapter =3D NULL; + struct dxgdevice *device =3D NULL; + + pr_debug("ioctl: %s", __func__); + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL); + device =3D hmgrtable_get_object_by_type(&process->handle_table, + HMGRENTRY_TYPE_DXGDEVICE, + args.device); + if (device) { + hmgrtable_free_handle(&process->handle_table, + HMGRENTRY_TYPE_DXGDEVICE, args.device); + device->handle_valid =3D 0; + } + hmgrtable_unlock(&process->handle_table, DXGLOCK_EXCL); + + if (device =3D=3D NULL) { + pr_err("invalid device handle: %x", args.device.v); + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D device->adapter; + + dxgdevice_destroy(device); + + if (dxgadapter_acquire_lock_shared(adapter) =3D=3D 0) { + dxgvmb_send_destroy_device(adapter, process, args.device); + dxgadapter_release_lock_shared(adapter); + } + +cleanup: + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + /* * IOCTL processing * The driver IOCTLs return @@ -495,12 +625,16 @@ void init_ioctls(void) { SET_IOCTL(/*0x1 */ dxgk_open_adapter_from_luid, LX_DXOPENADAPTERFROMLUID); + SET_IOCTL(/*0x2 */ dxgk_create_device, + LX_DXCREATEDEVICE); SET_IOCTL(/*0x9 */ dxgk_query_adapter_info, LX_DXQUERYADAPTERINFO); SET_IOCTL(/*0x14 */ dxgk_enum_adapters, LX_DXENUMADAPTERS2); SET_IOCTL(/*0x15 */ dxgk_close_adapter, LX_DXCLOSEADAPTER); + SET_IOCTL(/*0x19 */ dxgk_destroy_device, + LX_DXDESTROYDEVICE); SET_IOCTL(/*0x3e */ dxgk_enum_adapters3, LX_DXENUMADAPTERS3); } diff --git a/drivers/hv/dxgkrnl/misc.h b/drivers/hv/dxgkrnl/misc.h index d00e7cc00470..8948f48ec9dc 100644 --- a/drivers/hv/dxgkrnl/misc.h +++ b/drivers/hv/dxgkrnl/misc.h @@ -25,6 +25,7 @@ extern const struct d3dkmthandle zerohandle; * The higher enum value, the higher is the lock order. * When a lower lock ois held, the higher lock should not be acquired. * + * device_list_mutex * channel_lock * fd_mutex * plistmutex --=20 2.35.1 From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 84DA4C43219 for ; Sat, 5 Feb 2022 02:34:46 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1379119AbiBECep (ORCPT ); Fri, 4 Feb 2022 21:34:45 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45114 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1378998AbiBECeY (ORCPT ); Fri, 4 Feb 2022 21:34:24 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id 2949720B8016; Fri, 4 Feb 2022 18:34:24 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com 2949720B8016 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028464; bh=CahL0oKsEAEfsNodpmdi8i8lS2lqexuEIoauSrJUCRM=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=rXHXK7QNQVOEau7K4M2vPL79gcYUtKk/Go/8XZBCTl6L+HCYf/4PWCTe4/7+GSWQd ecwEI/vfWijhyC9BCXtCG+BUPWiwWFJw1V3e2drjcPdeAl9koMVmglmR7M9E+yxSC3 UewKOX90E6AzqAG+ZFdixmyYlT/SRdtR4PXrUJIM= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 05/24] drivers: hv: dxgkrnl: Creation of dxgcontext objects Date: Fri, 4 Feb 2022 18:34:03 -0800 Message-Id: <577c5c430924be2b64b0032d51cacd01268cbb93.1644025661.git.iourit@linux.microsoft.com> X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Implement ioctls for dxgcontext creation/destruction: LX_DXCREATECONTEXTVIRTUAL(D3DKMTCreateContextVirtual), LX_DXDESTROYCONTEXT(D3DKMTDestroyContext) A dxgcontext object represents a GPU execution thread. GPU DMA buffers and synchronization operations are submitted for execution to a GPU context. GPU contexts belong to a dxgdevice object. Signed-off-by: Iouri Tarassov --- drivers/hv/dxgkrnl/dxgadapter.c | 102 +++++++++++++++++++ drivers/hv/dxgkrnl/dxgkrnl.h | 38 +++++++ drivers/hv/dxgkrnl/dxgprocess.c | 4 + drivers/hv/dxgkrnl/dxgvmbus.c | 99 ++++++++++++++++++ drivers/hv/dxgkrnl/ioctl.c | 172 ++++++++++++++++++++++++++++++++ drivers/hv/dxgkrnl/misc.h | 1 + 6 files changed, 416 insertions(+) diff --git a/drivers/hv/dxgkrnl/dxgadapter.c b/drivers/hv/dxgkrnl/dxgadapte= r.c index c7e1dc55de49..9cdc81d4db4a 100644 --- a/drivers/hv/dxgkrnl/dxgadapter.c +++ b/drivers/hv/dxgkrnl/dxgadapter.c @@ -210,7 +210,9 @@ struct dxgdevice *dxgdevice_create(struct dxgadapter *a= dapter, device->adapter =3D adapter; device->process =3D process; kref_get(&adapter->adapter_kref); + INIT_LIST_HEAD(&device->context_list_head); init_rwsem(&device->device_lock); + init_rwsem(&device->context_list_lock); INIT_LIST_HEAD(&device->pqueue_list_head); device->object_state =3D DXGOBJECTSTATE_CREATED; device->execution_state =3D _D3DKMT_DEVICEEXECUTION_ACTIVE; @@ -252,6 +254,20 @@ void dxgdevice_destroy(struct dxgdevice *device) =20 dxgdevice_stop(device); =20 + { + struct dxgcontext *context; + struct dxgcontext *tmp; + + pr_debug("destroying contexts\n"); + dxgdevice_acquire_context_list_lock(device); + list_for_each_entry_safe(context, tmp, + &device->context_list_head, + context_list_entry) { + dxgcontext_destroy(process, context); + } + dxgdevice_release_context_list_lock(device); + } + /* Guest handles need to be released before the host handles */ hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL); if (device->handle_valid) { @@ -305,6 +321,32 @@ bool dxgdevice_is_active(struct dxgdevice *device) return device->object_state =3D=3D DXGOBJECTSTATE_ACTIVE; } =20 +void dxgdevice_acquire_context_list_lock(struct dxgdevice *device) +{ + down_write(&device->context_list_lock); +} + +void dxgdevice_release_context_list_lock(struct dxgdevice *device) +{ + up_write(&device->context_list_lock); +} + +void dxgdevice_add_context(struct dxgdevice *device, struct dxgcontext *co= ntext) +{ + down_write(&device->context_list_lock); + list_add_tail(&context->context_list_entry, &device->context_list_head); + up_write(&device->context_list_lock); +} + +void dxgdevice_remove_context(struct dxgdevice *device, + struct dxgcontext *context) +{ + if (context->context_list_entry.next) { + list_del(&context->context_list_entry); + context->context_list_entry.next =3D NULL; + } +} + void dxgdevice_release(struct kref *refcount) { struct dxgdevice *device; @@ -313,6 +355,66 @@ void dxgdevice_release(struct kref *refcount) vfree(device); } =20 +struct dxgcontext *dxgcontext_create(struct dxgdevice *device) +{ + struct dxgcontext *context =3D vzalloc(sizeof(struct dxgcontext)); + + if (context) { + kref_init(&context->context_kref); + context->device =3D device; + context->process =3D device->process; + context->device_handle =3D device->handle; + kref_get(&device->device_kref); + INIT_LIST_HEAD(&context->hwqueue_list_head); + init_rwsem(&context->hwqueue_list_lock); + dxgdevice_add_context(device, context); + context->object_state =3D DXGOBJECTSTATE_ACTIVE; + } + return context; +} + +/* + * Called when the device context list lock is held + */ +void dxgcontext_destroy(struct dxgprocess *process, struct dxgcontext *con= text) +{ + pr_debug("%s %p\n", __func__, context); + context->object_state =3D DXGOBJECTSTATE_DESTROYED; + if (context->device) { + if (context->handle.v) { + hmgrtable_free_handle_safe(&process->handle_table, + HMGRENTRY_TYPE_DXGCONTEXT, + context->handle); + } + dxgdevice_remove_context(context->device, context); + kref_put(&context->device->device_kref, dxgdevice_release); + } + kref_put(&context->context_kref, dxgcontext_release); +} + +void dxgcontext_destroy_safe(struct dxgprocess *process, + struct dxgcontext *context) +{ + struct dxgdevice *device =3D context->device; + + dxgdevice_acquire_context_list_lock(device); + dxgcontext_destroy(process, context); + dxgdevice_release_context_list_lock(device); +} + +bool dxgcontext_is_active(struct dxgcontext *context) +{ + return context->object_state =3D=3D DXGOBJECTSTATE_ACTIVE; +} + +void dxgcontext_release(struct kref *refcount) +{ + struct dxgcontext *context; + + context =3D container_of(refcount, struct dxgcontext, context_kref); + vfree(context); +} + struct dxgprocess_adapter *dxgprocess_adapter_create(struct dxgprocess *pr= ocess, struct dxgadapter *adapter) { diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index e0a433c36a06..b4ca479cdd1a 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -30,6 +30,7 @@ struct dxgprocess; struct dxgadapter; struct dxgdevice; +struct dxgcontext; =20 #include "misc.h" #include "hmgr.h" @@ -281,6 +282,7 @@ void dxgadapter_remove_process(struct dxgprocess_adapte= r *process_info); /* * The object represent the device object. * The following objects take reference on the device + * - dxgcontext * - device handle (struct d3dkmthandle) */ struct dxgdevice { @@ -294,6 +296,8 @@ struct dxgdevice { struct kref device_kref; /* Protects destcruction of the device object */ struct rw_semaphore device_lock; + struct rw_semaphore context_list_lock; + struct list_head context_list_head; /* List of paging queues. Protected by process handle table lock. */ struct list_head pqueue_list_head; struct d3dkmthandle handle; @@ -308,7 +312,33 @@ void dxgdevice_mark_destroyed(struct dxgdevice *device= ); int dxgdevice_acquire_lock_shared(struct dxgdevice *dev); void dxgdevice_release_lock_shared(struct dxgdevice *dev); void dxgdevice_release(struct kref *refcount); +void dxgdevice_add_context(struct dxgdevice *dev, struct dxgcontext *ctx); +void dxgdevice_remove_context(struct dxgdevice *dev, struct dxgcontext *ct= x); bool dxgdevice_is_active(struct dxgdevice *dev); +void dxgdevice_acquire_context_list_lock(struct dxgdevice *dev); +void dxgdevice_release_context_list_lock(struct dxgdevice *dev); + +/* + * The object represent the execution context of a device. + */ +struct dxgcontext { + enum dxgobjectstate object_state; + struct dxgdevice *device; + struct dxgprocess *process; + /* entry in the device context list */ + struct list_head context_list_entry; + struct list_head hwqueue_list_head; + struct rw_semaphore hwqueue_list_lock; + struct kref context_kref; + struct d3dkmthandle handle; + struct d3dkmthandle device_handle; +}; + +struct dxgcontext *dxgcontext_create(struct dxgdevice *dev); +void dxgcontext_destroy(struct dxgprocess *pr, struct dxgcontext *ctx); +void dxgcontext_destroy_safe(struct dxgprocess *pr, struct dxgcontext *ctx= ); +void dxgcontext_release(struct kref *refcount); +bool dxgcontext_is_active(struct dxgcontext *ctx); =20 void init_ioctls(void); long dxgk_compat_ioctl(struct file *f, unsigned int p1, unsigned long p2); @@ -349,6 +379,14 @@ struct d3dkmthandle dxgvmb_send_create_device(struct d= xgadapter *adapter, int dxgvmb_send_destroy_device(struct dxgadapter *adapter, struct dxgprocess *process, struct d3dkmthandle h); +struct d3dkmthandle +dxgvmb_send_create_context(struct dxgadapter *adapter, + struct dxgprocess *process, + struct d3dkmt_createcontextvirtual + *args); +int dxgvmb_send_destroy_context(struct dxgadapter *adapter, + struct dxgprocess *process, + struct d3dkmthandle h); int dxgvmb_send_query_adapter_info(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_queryadapterinfo *args); diff --git a/drivers/hv/dxgkrnl/dxgprocess.c b/drivers/hv/dxgkrnl/dxgproces= s.c index 734585689213..1e6500e12a22 100644 --- a/drivers/hv/dxgkrnl/dxgprocess.c +++ b/drivers/hv/dxgkrnl/dxgprocess.c @@ -258,6 +258,10 @@ struct dxgdevice *dxgprocess_device_by_object_handle(s= truct dxgprocess *process, case HMGRENTRY_TYPE_DXGDEVICE: device =3D obj; break; + case HMGRENTRY_TYPE_DXGCONTEXT: + device_handle =3D + ((struct dxgcontext *)obj)->device_handle; + break; default: pr_err("invalid handle type: %d\n", t); break; diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index 5b560754ac0d..bfd09f98f82c 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -710,6 +710,105 @@ int dxgvmb_send_destroy_device(struct dxgadapter *ada= pter, return ret; } =20 +struct d3dkmthandle +dxgvmb_send_create_context(struct dxgadapter *adapter, + struct dxgprocess *process, + struct d3dkmt_createcontextvirtual *args) +{ + struct dxgkvmb_command_createcontextvirtual *command =3D NULL; + u32 cmd_size; + int ret; + struct d3dkmthandle context =3D {}; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + if (args->priv_drv_data_size > DXG_MAX_VM_BUS_PACKET_SIZE) { + pr_err("PrivateDriverDataSize is invalid"); + ret =3D -EINVAL; + goto cleanup; + } + cmd_size =3D sizeof(struct dxgkvmb_command_createcontextvirtual) + + args->priv_drv_data_size - 1; + + ret =3D init_message(&msg, adapter, process, cmd_size); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_CREATECONTEXTVIRTUAL, + process->host_handle); + command->device =3D args->device; + command->node_ordinal =3D args->node_ordinal; + command->engine_affinity =3D args->engine_affinity; + command->flags =3D args->flags; + command->client_hint =3D args->client_hint; + command->priv_drv_data_size =3D args->priv_drv_data_size; + if (args->priv_drv_data_size) { + ret =3D copy_from_user(command->priv_drv_data, + args->priv_drv_data, + args->priv_drv_data_size); + if (ret) { + pr_err("%s Faled to copy private data", + __func__); + ret =3D -EINVAL; + goto cleanup; + } + } + /* Input command is returned back as output */ + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, + command, cmd_size); + if (ret < 0) { + goto cleanup; + } else { + context =3D command->context; + if (args->priv_drv_data_size) { + ret =3D copy_to_user(args->priv_drv_data, + command->priv_drv_data, + args->priv_drv_data_size); + if (ret) { + pr_err("%s Faled to copy private data to user", + __func__); + ret =3D -EINVAL; + dxgvmb_send_destroy_context(adapter, process, + context); + context.v =3D 0; + } + } + } + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return context; +} + +int dxgvmb_send_destroy_context(struct dxgadapter *adapter, + struct dxgprocess *process, + struct d3dkmthandle h) +{ + int ret; + struct dxgkvmb_command_destroycontext *command; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, adapter, process, sizeof(*command)); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_DESTROYCONTEXT, + process->host_handle); + command->context =3D h; + + ret =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, msg.size); +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + int dxgvmb_send_query_adapter_info(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_queryadapterinfo *args) diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index a6be88b6c792..879fb3c6b7b2 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -567,6 +567,174 @@ dxgk_destroy_device(struct dxgprocess *process, void = *__user inargs) return ret; } =20 +static int +dxgk_create_context_virtual(struct dxgprocess *process, void *__user inarg= s) +{ + struct d3dkmt_createcontextvirtual args; + int ret; + struct dxgadapter *adapter =3D NULL; + struct dxgdevice *device =3D NULL; + struct dxgcontext *context =3D NULL; + struct d3dkmthandle host_context_handle =3D {}; + bool device_lock_acquired =3D false; + + pr_debug("ioctl: %s", __func__); + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + /* + * The call acquires reference on the device. It is safe to access the + * adapter, because the device holds reference on it. + */ + device =3D dxgprocess_device_by_handle(process, args.device); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgdevice_acquire_lock_shared(device); + if (ret < 0) + goto cleanup; + + device_lock_acquired =3D true; + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + context =3D dxgcontext_create(device); + if (context =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + + host_context_handle =3D dxgvmb_send_create_context(adapter, + process, &args); + if (host_context_handle.v) { + hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL); + ret =3D hmgrtable_assign_handle(&process->handle_table, context, + HMGRENTRY_TYPE_DXGCONTEXT, + host_context_handle); + if (ret >=3D 0) + context->handle =3D host_context_handle; + hmgrtable_unlock(&process->handle_table, DXGLOCK_EXCL); + if (ret < 0) + goto cleanup; + ret =3D copy_to_user(&((struct d3dkmt_createcontextvirtual *) + inargs)->context, &host_context_handle, + sizeof(struct d3dkmthandle)); + if (ret) { + pr_err("%s failed to copy context handle", __func__); + ret =3D -EINVAL; + } + } else { + pr_err("invalid host handle"); + ret =3D -EINVAL; + } + +cleanup: + + if (ret < 0) { + if (host_context_handle.v) { + dxgvmb_send_destroy_context(adapter, process, + host_context_handle); + } + if (context) + dxgcontext_destroy_safe(process, context); + } + + if (adapter) + dxgadapter_release_lock_shared(adapter); + + if (device) { + if (device_lock_acquired) + dxgdevice_release_lock_shared(device); + kref_put(&device->device_kref, dxgdevice_release); + } + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_destroy_context(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmt_destroycontext args; + int ret; + struct dxgadapter *adapter =3D NULL; + struct dxgcontext *context =3D NULL; + struct dxgdevice *device =3D NULL; + struct d3dkmthandle device_handle =3D {}; + + pr_debug("ioctl: %s", __func__); + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL); + context =3D hmgrtable_get_object_by_type(&process->handle_table, + HMGRENTRY_TYPE_DXGCONTEXT, + args.context); + if (context) { + hmgrtable_free_handle(&process->handle_table, + HMGRENTRY_TYPE_DXGCONTEXT, args.context); + context->handle.v =3D 0; + device_handle =3D context->device_handle; + context->object_state =3D DXGOBJECTSTATE_DESTROYED; + } + hmgrtable_unlock(&process->handle_table, DXGLOCK_EXCL); + + if (context =3D=3D NULL) { + pr_err("invalid context handle: %x", args.context.v); + ret =3D -EINVAL; + goto cleanup; + } + + /* + * The call acquires reference on the device. It is safe to access the + * adapter, because the device holds reference on it. + */ + device =3D dxgprocess_device_by_handle(process, device_handle); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_destroy_context(adapter, process, args.context); + + dxgcontext_destroy_safe(process, context); + +cleanup: + + if (adapter) + dxgadapter_release_lock_shared(adapter); + + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + /* * IOCTL processing * The driver IOCTLs return @@ -627,6 +795,10 @@ void init_ioctls(void) LX_DXOPENADAPTERFROMLUID); SET_IOCTL(/*0x2 */ dxgk_create_device, LX_DXCREATEDEVICE); + SET_IOCTL(/*0x4 */ dxgk_create_context_virtual, + LX_DXCREATECONTEXTVIRTUAL); + SET_IOCTL(/*0x5 */ dxgk_destroy_context, + LX_DXDESTROYCONTEXT); SET_IOCTL(/*0x9 */ dxgk_query_adapter_info, LX_DXQUERYADAPTERINFO); SET_IOCTL(/*0x14 */ dxgk_enum_adapters, diff --git a/drivers/hv/dxgkrnl/misc.h b/drivers/hv/dxgkrnl/misc.h index 8948f48ec9dc..8f7b37049308 100644 --- a/drivers/hv/dxgkrnl/misc.h +++ b/drivers/hv/dxgkrnl/misc.h @@ -30,6 +30,7 @@ extern const struct d3dkmthandle zerohandle; * fd_mutex * plistmutex * table_lock + * context_list_lock * core_lock * device_lock * process_adapter_mutex --=20 2.35.1 From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 403C0C433F5 for ; Sat, 5 Feb 2022 02:34:50 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1379068AbiBECes (ORCPT ); Fri, 4 Feb 2022 21:34:48 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45084 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1379001AbiBECeY (ORCPT ); Fri, 4 Feb 2022 21:34:24 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id 5153820B8019; Fri, 4 Feb 2022 18:34:24 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com 5153820B8019 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028464; bh=/+PHDGwJnbjIUQ6Gs1MnXriutgbNHLn8+CSb0M89Om8=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=FgRwfxdznAqWZug23cPnlJZ44zDVKb0VEhbYLibLjYuSoE/A3rESeOpMnVhux4oeI NBAD/t5H5k0LJs19HxuedfHXpuBDZvoZcPUYX8m9qslDcooaBk1GUZW5sM8w59/rOv yeIM2gKG+tB9QjHQJobsdFsm+Npn3ve5AW8JH6yE= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 06/24] drivers: hv: dxgkrnl: Creation of GPU allocations and resources Date: Fri, 4 Feb 2022 18:34:04 -0800 Message-Id: <72b26c8d74b5037e243c0814d5ad17b418a8dd08.1644025661.git.iourit@linux.microsoft.com> X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Implemented ioctls to create and destroy GPU allocations and resources: LX_DXCREATEALLOCATION(D3DKMTCreateAllocation), LX_DXDESTROYALLOCATION2(D3DKMTDestroyAllocation2). GPU allocations (dxgallocation objects) represent memory allocation, which could be accessible by GPU. Allocations can be created around existing system memory (provided by the application) or memory, allocated by dxgkrnl. GPU resources (dxgresource objects) represent containers ofr GPU allocations. Allocations could be dynamically added, removed from a resource. Each allocation/resource has associated driver private data, which is provided during creation. Signed-off-by: Iouri Tarassov --- drivers/hv/dxgkrnl/dxgadapter.c | 274 ++++++++++++++ drivers/hv/dxgkrnl/dxgkrnl.h | 109 ++++++ drivers/hv/dxgkrnl/dxgmodule.c | 1 + drivers/hv/dxgkrnl/dxgvmbus.c | 645 ++++++++++++++++++++++++++++++++ drivers/hv/dxgkrnl/ioctl.c | 637 +++++++++++++++++++++++++++++++ drivers/hv/dxgkrnl/misc.h | 3 + 6 files changed, 1669 insertions(+) diff --git a/drivers/hv/dxgkrnl/dxgadapter.c b/drivers/hv/dxgkrnl/dxgadapte= r.c index 9cdc81d4db4a..3f51456272cc 100644 --- a/drivers/hv/dxgkrnl/dxgadapter.c +++ b/drivers/hv/dxgkrnl/dxgadapter.c @@ -211,8 +211,11 @@ struct dxgdevice *dxgdevice_create(struct dxgadapter *= adapter, device->process =3D process; kref_get(&adapter->adapter_kref); INIT_LIST_HEAD(&device->context_list_head); + INIT_LIST_HEAD(&device->alloc_list_head); + INIT_LIST_HEAD(&device->resource_list_head); init_rwsem(&device->device_lock); init_rwsem(&device->context_list_lock); + init_rwsem(&device->alloc_list_lock); INIT_LIST_HEAD(&device->pqueue_list_head); device->object_state =3D DXGOBJECTSTATE_CREATED; device->execution_state =3D _D3DKMT_DEVICEEXECUTION_ACTIVE; @@ -228,6 +231,16 @@ struct dxgdevice *dxgdevice_create(struct dxgadapter *= adapter, =20 void dxgdevice_stop(struct dxgdevice *device) { + struct dxgallocation *alloc; + + pr_debug("%s: %p", __func__, device); + dxgdevice_acquire_alloc_list_lock(device); + list_for_each_entry(alloc, &device->alloc_list_head, alloc_list_entry) { + dxgallocation_stop(alloc); + } + dxgdevice_release_alloc_list_lock(device); + + pr_debug("%s: end %p\n", __func__, device); } =20 void dxgdevice_mark_destroyed(struct dxgdevice *device) @@ -254,6 +267,33 @@ void dxgdevice_destroy(struct dxgdevice *device) =20 dxgdevice_stop(device); =20 + dxgdevice_acquire_alloc_list_lock(device); + + { + struct dxgallocation *alloc; + struct dxgallocation *tmp; + + pr_debug("destroying allocations\n"); + list_for_each_entry_safe(alloc, tmp, &device->alloc_list_head, + alloc_list_entry) { + dxgallocation_destroy(alloc); + } + } + + { + struct dxgresource *resource; + struct dxgresource *tmp; + + pr_debug("destroying resources\n"); + list_for_each_entry_safe(resource, tmp, + &device->resource_list_head, + resource_list_entry) { + dxgresource_destroy(resource); + } + } + + dxgdevice_release_alloc_list_lock(device); + { struct dxgcontext *context; struct dxgcontext *tmp; @@ -331,6 +371,26 @@ void dxgdevice_release_context_list_lock(struct dxgdev= ice *device) up_write(&device->context_list_lock); } =20 +void dxgdevice_acquire_alloc_list_lock(struct dxgdevice *device) +{ + down_write(&device->alloc_list_lock); +} + +void dxgdevice_release_alloc_list_lock(struct dxgdevice *device) +{ + up_write(&device->alloc_list_lock); +} + +void dxgdevice_acquire_alloc_list_lock_shared(struct dxgdevice *device) +{ + down_read(&device->alloc_list_lock); +} + +void dxgdevice_release_alloc_list_lock_shared(struct dxgdevice *device) +{ + up_read(&device->alloc_list_lock); +} + void dxgdevice_add_context(struct dxgdevice *device, struct dxgcontext *co= ntext) { down_write(&device->context_list_lock); @@ -347,6 +407,160 @@ void dxgdevice_remove_context(struct dxgdevice *devic= e, } } =20 +void dxgdevice_add_alloc(struct dxgdevice *device, struct dxgallocation *a= lloc) +{ + dxgdevice_acquire_alloc_list_lock(device); + list_add_tail(&alloc->alloc_list_entry, &device->alloc_list_head); + kref_get(&device->device_kref); + alloc->owner.device =3D device; + dxgdevice_release_alloc_list_lock(device); +} + +void dxgdevice_remove_alloc(struct dxgdevice *device, + struct dxgallocation *alloc) +{ + if (alloc->alloc_list_entry.next) { + list_del(&alloc->alloc_list_entry); + alloc->alloc_list_entry.next =3D NULL; + kref_put(&device->device_kref, dxgdevice_release); + } +} + +void dxgdevice_remove_alloc_safe(struct dxgdevice *device, + struct dxgallocation *alloc) +{ + dxgdevice_acquire_alloc_list_lock(device); + dxgdevice_remove_alloc(device, alloc); + dxgdevice_release_alloc_list_lock(device); +} + +void dxgdevice_add_resource(struct dxgdevice *device, struct dxgresource *= res) +{ + dxgdevice_acquire_alloc_list_lock(device); + list_add_tail(&res->resource_list_entry, &device->resource_list_head); + kref_get(&device->device_kref); + dxgdevice_release_alloc_list_lock(device); +} + +void dxgdevice_remove_resource(struct dxgdevice *device, + struct dxgresource *res) +{ + if (res->resource_list_entry.next) { + list_del(&res->resource_list_entry); + res->resource_list_entry.next =3D NULL; + kref_put(&device->device_kref, dxgdevice_release); + } +} + +struct dxgresource *dxgresource_create(struct dxgdevice *device) +{ + struct dxgresource *resource =3D vzalloc(sizeof(struct dxgresource)); + + if (resource) { + kref_init(&resource->resource_kref); + resource->device =3D device; + resource->process =3D device->process; + resource->object_state =3D DXGOBJECTSTATE_ACTIVE; + mutex_init(&resource->resource_mutex); + INIT_LIST_HEAD(&resource->alloc_list_head); + dxgdevice_add_resource(device, resource); + } + return resource; +} + +void dxgresource_free_handle(struct dxgresource *resource) +{ + struct dxgallocation *alloc; + struct dxgprocess *process; + + if (resource->handle_valid) { + process =3D resource->device->process; + hmgrtable_free_handle_safe(&process->handle_table, + HMGRENTRY_TYPE_DXGRESOURCE, + resource->handle); + resource->handle_valid =3D 0; + } + list_for_each_entry(alloc, &resource->alloc_list_head, + alloc_list_entry) { + dxgallocation_free_handle(alloc); + } +} + +void dxgresource_destroy(struct dxgresource *resource) +{ + /* device->alloc_list_lock is held */ + struct dxgallocation *alloc; + struct dxgallocation *tmp; + struct d3dkmt_destroyallocation2 args =3D { }; + int destroyed =3D test_and_set_bit(0, &resource->flags); + struct dxgdevice *device =3D resource->device; + + if (!destroyed) { + dxgresource_free_handle(resource); + if (resource->handle.v) { + args.device =3D device->handle; + args.resource =3D resource->handle; + dxgvmb_send_destroy_allocation(device->process, + device, &args, NULL); + resource->handle.v =3D 0; + } + list_for_each_entry_safe(alloc, tmp, &resource->alloc_list_head, + alloc_list_entry) { + dxgallocation_destroy(alloc); + } + dxgdevice_remove_resource(device, resource); + } + kref_put(&resource->resource_kref, dxgresource_release); +} + +void dxgresource_release(struct kref *refcount) +{ + struct dxgresource *resource; + + resource =3D container_of(refcount, struct dxgresource, resource_kref); + vfree(resource); +} + +bool dxgresource_is_active(struct dxgresource *resource) +{ + return resource->object_state =3D=3D DXGOBJECTSTATE_ACTIVE; +} + +int dxgresource_add_alloc(struct dxgresource *resource, + struct dxgallocation *alloc) +{ + int ret =3D -ENODEV; + struct dxgdevice *device =3D resource->device; + + dxgdevice_acquire_alloc_list_lock(device); + if (dxgresource_is_active(resource)) { + list_add_tail(&alloc->alloc_list_entry, + &resource->alloc_list_head); + alloc->owner.resource =3D resource; + ret =3D 0; + } + alloc->resource_owner =3D 1; + dxgdevice_release_alloc_list_lock(device); + return ret; +} + +void dxgresource_remove_alloc(struct dxgresource *resource, + struct dxgallocation *alloc) +{ + if (alloc->alloc_list_entry.next) { + list_del(&alloc->alloc_list_entry); + alloc->alloc_list_entry.next =3D NULL; + } +} + +void dxgresource_remove_alloc_safe(struct dxgresource *resource, + struct dxgallocation *alloc) +{ + dxgdevice_acquire_alloc_list_lock(resource->device); + dxgresource_remove_alloc(resource, alloc); + dxgdevice_release_alloc_list_lock(resource->device); +} + void dxgdevice_release(struct kref *refcount) { struct dxgdevice *device; @@ -415,6 +629,66 @@ void dxgcontext_release(struct kref *refcount) vfree(context); } =20 +struct dxgallocation *dxgallocation_create(struct dxgprocess *process) +{ + struct dxgallocation *alloc =3D vzalloc(sizeof(struct dxgallocation)); + + if (alloc) + alloc->process =3D process; + return alloc; +} + +void dxgallocation_stop(struct dxgallocation *alloc) +{ + if (alloc->pages) { + release_pages(alloc->pages, alloc->num_pages); + vfree(alloc->pages); + alloc->pages =3D NULL; + } +} + +void dxgallocation_free_handle(struct dxgallocation *alloc) +{ + dxgprocess_ht_lock_exclusive_down(alloc->process); + if (alloc->handle_valid) { + hmgrtable_free_handle(&alloc->process->handle_table, + HMGRENTRY_TYPE_DXGALLOCATION, + alloc->alloc_handle); + alloc->handle_valid =3D 0; + } + dxgprocess_ht_lock_exclusive_up(alloc->process); +} + +void dxgallocation_destroy(struct dxgallocation *alloc) +{ + struct dxgprocess *process =3D alloc->process; + struct d3dkmt_destroyallocation2 args =3D { }; + + dxgallocation_stop(alloc); + if (alloc->resource_owner) + dxgresource_remove_alloc(alloc->owner.resource, alloc); + else if (alloc->owner.device) + dxgdevice_remove_alloc(alloc->owner.device, alloc); + dxgallocation_free_handle(alloc); + if (alloc->alloc_handle.v && !alloc->resource_owner) { + args.device =3D alloc->owner.device->handle; + args.alloc_count =3D 1; + dxgvmb_send_destroy_allocation(process, + alloc->owner.device, + &args, &alloc->alloc_handle); + } + if (alloc->gpadl.gpadl_handle) { + pr_debug("Teardown gpadl %d", + alloc->gpadl.gpadl_handle); + vmbus_teardown_gpadl(dxgglobal_get_vmbus(), &alloc->gpadl); + pr_debug("Teardown gpadl end"); + alloc->gpadl.gpadl_handle =3D 0; + } + if (alloc->priv_drv_data) + vfree(alloc->priv_drv_data); + vfree(alloc); +} + struct dxgprocess_adapter *dxgprocess_adapter_create(struct dxgprocess *pr= ocess, struct dxgadapter *adapter) { diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index b4ca479cdd1a..28c3dbef0ef3 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -31,6 +31,8 @@ struct dxgprocess; struct dxgadapter; struct dxgdevice; struct dxgcontext; +struct dxgallocation; +struct dxgresource; =20 #include "misc.h" #include "hmgr.h" @@ -252,6 +254,8 @@ struct dxgadapter { struct list_head adapter_list_entry; /* The list of dxgprocess_adapter entries */ struct list_head adapter_process_list_head; + /* This lock protects shared resource and syncobject lists */ + struct rw_semaphore shared_resource_list_lock; struct pci_dev *pci_dev; struct hv_device *hv_dev; struct dxgvmbuschannel channel; @@ -298,6 +302,10 @@ struct dxgdevice { struct rw_semaphore device_lock; struct rw_semaphore context_list_lock; struct list_head context_list_head; + /* List of device allocations */ + struct rw_semaphore alloc_list_lock; + struct list_head alloc_list_head; + struct list_head resource_list_head; /* List of paging queues. Protected by process handle table lock. */ struct list_head pqueue_list_head; struct d3dkmthandle handle; @@ -314,9 +322,19 @@ void dxgdevice_release_lock_shared(struct dxgdevice *d= ev); void dxgdevice_release(struct kref *refcount); void dxgdevice_add_context(struct dxgdevice *dev, struct dxgcontext *ctx); void dxgdevice_remove_context(struct dxgdevice *dev, struct dxgcontext *ct= x); +void dxgdevice_add_alloc(struct dxgdevice *dev, struct dxgallocation *a); +void dxgdevice_remove_alloc(struct dxgdevice *dev, struct dxgallocation *a= ); +void dxgdevice_remove_alloc_safe(struct dxgdevice *dev, + struct dxgallocation *a); +void dxgdevice_add_resource(struct dxgdevice *dev, struct dxgresource *res= ); +void dxgdevice_remove_resource(struct dxgdevice *dev, struct dxgresource *= res); bool dxgdevice_is_active(struct dxgdevice *dev); void dxgdevice_acquire_context_list_lock(struct dxgdevice *dev); void dxgdevice_release_context_list_lock(struct dxgdevice *dev); +void dxgdevice_acquire_alloc_list_lock(struct dxgdevice *dev); +void dxgdevice_release_alloc_list_lock(struct dxgdevice *dev); +void dxgdevice_acquire_alloc_list_lock_shared(struct dxgdevice *dev); +void dxgdevice_release_alloc_list_lock_shared(struct dxgdevice *dev); =20 /* * The object represent the execution context of a device. @@ -340,6 +358,79 @@ void dxgcontext_destroy_safe(struct dxgprocess *pr, st= ruct dxgcontext *ctx); void dxgcontext_release(struct kref *refcount); bool dxgcontext_is_active(struct dxgcontext *ctx); =20 +struct dxgresource { + struct kref resource_kref; + enum dxgobjectstate object_state; + struct d3dkmthandle handle; + struct list_head alloc_list_head; + struct list_head resource_list_entry; + struct list_head shared_resource_list_entry; + struct dxgdevice *device; + struct dxgprocess *process; + /* Protects adding allocations to resource and resource destruction */ + struct mutex resource_mutex; + u64 private_runtime_handle; + union { + struct { + u32 destroyed:1; /* Must be the first */ + u32 handle_valid:1; + u32 reserved:30; + }; + long flags; + }; +}; + +struct dxgresource *dxgresource_create(struct dxgdevice *dev); +void dxgresource_destroy(struct dxgresource *res); +void dxgresource_free_handle(struct dxgresource *res); +void dxgresource_release(struct kref *refcount); +int dxgresource_add_alloc(struct dxgresource *res, + struct dxgallocation *a); +void dxgresource_remove_alloc(struct dxgresource *res, struct dxgallocatio= n *a); +void dxgresource_remove_alloc_safe(struct dxgresource *res, + struct dxgallocation *a); +bool dxgresource_is_active(struct dxgresource *res); + +struct privdata { + u32 data_size; + u8 data[1]; +}; + +struct dxgallocation { + /* Entry in the device list or resource list (when resource exists) */ + struct list_head alloc_list_entry; + /* Allocation owner */ + union { + struct dxgdevice *device; + struct dxgresource *resource; + } owner; + struct dxgprocess *process; + /* Pointer to private driver data desc. Used for shared resources */ + struct privdata *priv_drv_data; + struct d3dkmthandle alloc_handle; + /* Set to 1 when allocation belongs to resource. */ + u32 resource_owner:1; + /* Set to 1 when the allocatio is mapped as cached */ + u32 cached:1; + u32 handle_valid:1; + /* GPADL address list for existing sysmem allocations */ + struct vmbus_gpadl gpadl; + /* Number of pages in the 'pages' array */ + u32 num_pages; + /* + * CPU address from the existing sysmem allocation, or + * mapped to the CPU visible backing store in the IO space + */ + void *cpu_address; + /* Describes pages for the existing sysmem allocation */ + struct page **pages; +}; + +struct dxgallocation *dxgallocation_create(struct dxgprocess *process); +void dxgallocation_stop(struct dxgallocation *a); +void dxgallocation_destroy(struct dxgallocation *a); +void dxgallocation_free_handle(struct dxgallocation *a); + void init_ioctls(void); long dxgk_compat_ioctl(struct file *f, unsigned int p1, unsigned long p2); long dxgk_unlocked_ioctl(struct file *f, unsigned int p1, unsigned long p2= ); @@ -387,9 +478,27 @@ dxgvmb_send_create_context(struct dxgadapter *adapter, int dxgvmb_send_destroy_context(struct dxgadapter *adapter, struct dxgprocess *process, struct d3dkmthandle h); +int dxgvmb_send_create_allocation(struct dxgprocess *pr, struct dxgdevice = *dev, + struct d3dkmt_createallocation *args, + struct d3dkmt_createallocation *__user inargs, + struct dxgresource *res, + struct dxgallocation **allocs, + struct d3dddi_allocationinfo2 *alloc_info, + struct d3dkmt_createstandardallocation *stda); +int dxgvmb_send_destroy_allocation(struct dxgprocess *pr, struct dxgdevice= *dev, + struct d3dkmt_destroyallocation2 *args, + struct d3dkmthandle *alloc_handles); int dxgvmb_send_query_adapter_info(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_queryadapterinfo *args); +int dxgvmb_send_get_stdalloc_data(struct dxgdevice *device, + enum d3dkmdt_standardallocationtype t, + struct d3dkmdt_gdisurfacedata *data, + u32 physical_adapter_index, + u32 *alloc_priv_driver_size, + void *prive_alloc_data, + u32 *res_priv_data_size, + void *priv_res_data); int dxgvmb_send_async_msg(struct dxgvmbuschannel *channel, void *command, u32 cmd_size); diff --git a/drivers/hv/dxgkrnl/dxgmodule.c b/drivers/hv/dxgkrnl/dxgmodule.c index fafe0b6a6389..d865ac45f89d 100644 --- a/drivers/hv/dxgkrnl/dxgmodule.c +++ b/drivers/hv/dxgkrnl/dxgmodule.c @@ -158,6 +158,7 @@ int dxgglobal_create_adapter(struct pci_dev *dev, guid_= t *guid, init_rwsem(&adapter->core_lock); =20 INIT_LIST_HEAD(&adapter->adapter_process_list_head); + init_rwsem(&adapter->shared_resource_list_lock); adapter->pci_dev =3D dev; guid_to_luid(guid, &adapter->luid); =20 diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index bfd09f98f82c..541182c0b728 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -108,6 +108,40 @@ static int init_message(struct dxgvmbusmsg *msg, struc= t dxgadapter *adapter, return 0; } =20 +static int init_message_res(struct dxgvmbusmsgres *msg, + struct dxgadapter *adapter, + struct dxgprocess *process, + u32 size, + u32 result_size) +{ + bool use_ext_header =3D dxgglobal->vmbus_ver >=3D + DXGK_VMBUS_INTERFACE_VERSION; + + if (use_ext_header) + size +=3D sizeof(struct dxgvmb_ext_header); + msg->size =3D size; + msg->res_size +=3D (result_size + 7) & ~7; + size +=3D msg->res_size; + msg->hdr =3D vzalloc(size); + if (msg->hdr =3D=3D NULL) { + pr_err("Failed to allocate VM bus message: %d", size); + return -ENOMEM; + } + if (use_ext_header) { + msg->msg =3D (char *)&msg->hdr[1]; + msg->hdr->command_offset =3D sizeof(msg->hdr[0]); + msg->hdr->vgpu_luid =3D adapter->host_vgpu_luid; + } else { + msg->msg =3D (char *)msg->hdr; + } + msg->res =3D (char *)msg->hdr + msg->size; + if (dxgglobal->async_msg_enabled) + msg->channel =3D &dxgglobal->channel; + else + msg->channel =3D &adapter->channel; + return 0; +} + static void free_message(struct dxgvmbusmsg *msg, struct dxgprocess *proce= ss) { if (msg->hdr && (char *)msg->hdr !=3D msg->msg_on_stack) @@ -809,6 +843,617 @@ int dxgvmb_send_destroy_context(struct dxgadapter *ad= apter, return ret; } =20 +static int +copy_private_data(struct d3dkmt_createallocation *args, + struct dxgkvmb_command_createallocation *command, + struct d3dddi_allocationinfo2 *input_alloc_info, + struct d3dkmt_createstandardallocation *standard_alloc) +{ + struct dxgkvmb_command_createallocation_allocinfo *alloc_info; + struct d3dddi_allocationinfo2 *input_alloc; + int ret =3D 0; + int i; + u8 *private_data_dest =3D (u8 *) &command[1] + + (args->alloc_count * + sizeof(struct dxgkvmb_command_createallocation_allocinfo)); + + if (args->private_runtime_data_size) { + ret =3D copy_from_user(private_data_dest, + args->private_runtime_data, + args->private_runtime_data_size); + if (ret) { + pr_err("%s failed to copy runtime data", __func__); + ret =3D -EINVAL; + goto cleanup; + } + private_data_dest +=3D args->private_runtime_data_size; + } + + if (args->flags.standard_allocation) { + pr_debug("private data offset %d", + (u32) (private_data_dest - (u8 *) command)); + + args->priv_drv_data_size =3D sizeof(*args->standard_allocation); + memcpy(private_data_dest, standard_alloc, + sizeof(*standard_alloc)); + private_data_dest +=3D args->priv_drv_data_size; + } else if (args->priv_drv_data_size) { + ret =3D copy_from_user(private_data_dest, + args->priv_drv_data, + args->priv_drv_data_size); + if (ret) { + pr_err("%s failed to copy private data", __func__); + ret =3D -EINVAL; + goto cleanup; + } + private_data_dest +=3D args->priv_drv_data_size; + } + + alloc_info =3D (void *)&command[1]; + input_alloc =3D input_alloc_info; + if (input_alloc_info[0].sysmem) + command->flags.existing_sysmem =3D 1; + for (i =3D 0; i < args->alloc_count; i++) { + alloc_info->flags =3D input_alloc->flags.value; + alloc_info->vidpn_source_id =3D input_alloc->vidpn_source_id; + alloc_info->priv_drv_data_size =3D + input_alloc->priv_drv_data_size; + if (input_alloc->priv_drv_data_size) { + ret =3D copy_from_user(private_data_dest, + input_alloc->priv_drv_data, + input_alloc->priv_drv_data_size); + if (ret) { + pr_err("%s failed to copy alloc data", + __func__); + ret =3D -EINVAL; + goto cleanup; + } + private_data_dest +=3D input_alloc->priv_drv_data_size; + } + alloc_info++; + input_alloc++; + } + +cleanup: + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +static +int create_existing_sysmem(struct dxgdevice *device, + struct dxgkvmb_command_allocinfo_return *host_alloc, + struct dxgallocation *dxgalloc, + bool read_only, + const void *sysmem) +{ + int ret1 =3D 0; + void *kmem =3D NULL; + int ret =3D 0; + struct dxgkvmb_command_setexistingsysmemstore *set_store_command; + u64 alloc_size =3D host_alloc->allocation_size; + u32 npages =3D alloc_size >> PAGE_SHIFT; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, device->adapter, device->process, + sizeof(*set_store_command)); + if (ret) + goto cleanup; + set_store_command =3D (void *)msg.msg; + + /* + * Create a guest physical address list and set it as the allocation + * backing store in the host. This is done after creating the host + * allocation, because only now the allocation size is known. + */ + + pr_debug(" Alloc size: %lld", alloc_size); + + dxgalloc->cpu_address =3D (void *)sysmem; + dxgalloc->pages =3D vzalloc(npages * sizeof(void *)); + if (dxgalloc->pages =3D=3D NULL) { + pr_err("failed to allocate pages"); + ret =3D -ENOMEM; + goto cleanup; + } + ret1 =3D get_user_pages_fast((unsigned long)sysmem, npages, !read_only, + dxgalloc->pages); + if (ret1 !=3D npages) { + pr_err("get_user_pages_fast failed: %d", ret1); + if (ret1 > 0 && ret1 < npages) + release_pages(dxgalloc->pages, ret1); + vfree(dxgalloc->pages); + dxgalloc->pages =3D NULL; + ret =3D -ENOMEM; + goto cleanup; + } + kmem =3D vmap(dxgalloc->pages, npages, VM_MAP, PAGE_KERNEL); + if (kmem =3D=3D NULL) { + pr_err("vmap failed"); + ret =3D -ENOMEM; + goto cleanup; + } + ret1 =3D vmbus_establish_gpadl(dxgglobal_get_vmbus(), kmem, + alloc_size, &dxgalloc->gpadl); + if (ret1) { + pr_err("establish_gpadl failed: %d", ret1); + ret =3D -ENOMEM; + goto cleanup; + } + pr_debug("New gpadl %d", dxgalloc->gpadl.gpadl_handle); + + command_vgpu_to_host_init2(&set_store_command->hdr, + DXGK_VMBCOMMAND_SETEXISTINGSYSMEMSTORE, + device->process->host_handle); + set_store_command->device =3D device->handle; + set_store_command->device =3D device->handle; + set_store_command->allocation =3D host_alloc->allocation; + set_store_command->gpadl =3D dxgalloc->gpadl.gpadl_handle; + ret =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, msg.size); + if (ret < 0) + pr_err("failed to set existing store: %x", ret); + +cleanup: + if (kmem) + vunmap(kmem); + free_message(&msg, device->process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +static int +process_allocation_handles(struct dxgprocess *process, + struct dxgdevice *device, + struct d3dkmt_createallocation *args, + struct dxgkvmb_command_createallocation_return *res, + struct dxgallocation **dxgalloc, + struct dxgresource *resource) +{ + int ret =3D 0; + int i; + + hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL); + if (args->flags.create_resource) { + ret =3D hmgrtable_assign_handle(&process->handle_table, resource, + HMGRENTRY_TYPE_DXGRESOURCE, + res->resource); + if (ret < 0) { + pr_err("failed to assign resource handle %x", + res->resource.v); + } else { + resource->handle =3D res->resource; + resource->handle_valid =3D 1; + } + } + for (i =3D 0; i < args->alloc_count; i++) { + struct dxgkvmb_command_allocinfo_return *host_alloc; + + host_alloc =3D &res->allocation_info[i]; + ret =3D hmgrtable_assign_handle(&process->handle_table, + dxgalloc[i], + HMGRENTRY_TYPE_DXGALLOCATION, + host_alloc->allocation); + if (ret < 0) { + pr_err("failed to assign alloc handle %x %d %d", + host_alloc->allocation.v, + args->alloc_count, i); + break; + } + dxgalloc[i]->alloc_handle =3D host_alloc->allocation; + dxgalloc[i]->handle_valid =3D 1; + } + hmgrtable_unlock(&process->handle_table, DXGLOCK_EXCL); + + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +static int +create_local_allocations(struct dxgprocess *process, + struct dxgdevice *device, + struct d3dkmt_createallocation *args, + struct d3dkmt_createallocation *__user input_args, + struct d3dddi_allocationinfo2 *alloc_info, + struct dxgkvmb_command_createallocation_return *result, + struct dxgresource *resource, + struct dxgallocation **dxgalloc, + u32 destroy_buffer_size) +{ + int i; + int alloc_count =3D args->alloc_count; + u8 *alloc_private_data =3D NULL; + int ret =3D 0; + int ret1; + struct dxgkvmb_command_destroyallocation *destroy_buf; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, device->adapter, process, + destroy_buffer_size); + if (ret) + goto cleanup; + destroy_buf =3D (void *)msg.msg; + + /* Prepare the command to destroy allocation in case of failure */ + command_vgpu_to_host_init2(&destroy_buf->hdr, + DXGK_VMBCOMMAND_DESTROYALLOCATION, + process->host_handle); + destroy_buf->device =3D args->device; + destroy_buf->resource =3D args->resource; + destroy_buf->alloc_count =3D alloc_count; + destroy_buf->flags.assume_not_in_use =3D 1; + for (i =3D 0; i < alloc_count; i++) { + pr_debug("host allocation: %d %x", + i, result->allocation_info[i].allocation.v); + destroy_buf->allocations[i] =3D + result->allocation_info[i].allocation; + } + + if (args->flags.create_resource) { + pr_debug("new resource: %x", result->resource.v); + ret =3D copy_to_user(&input_args->resource, &result->resource, + sizeof(struct d3dkmthandle)); + if (ret) { + pr_err("%s failed to copy resource handle", __func__); + ret =3D -EINVAL; + goto cleanup; + } + } + + alloc_private_data =3D (u8 *) result + + sizeof(struct dxgkvmb_command_createallocation_return) + + sizeof(struct dxgkvmb_command_allocinfo_return) * (alloc_count - 1); + + for (i =3D 0; i < alloc_count; i++) { + struct dxgkvmb_command_allocinfo_return *host_alloc; + struct d3dddi_allocationinfo2 *user_alloc; + + host_alloc =3D &result->allocation_info[i]; + user_alloc =3D &alloc_info[i]; + dxgalloc[i]->num_pages =3D + host_alloc->allocation_size >> PAGE_SHIFT; + if (user_alloc->sysmem) { + ret =3D create_existing_sysmem(device, host_alloc, + dxgalloc[i], + args->flags.read_only !=3D 0, + user_alloc->sysmem); + if (ret < 0) + goto cleanup; + } + dxgalloc[i]->cached =3D host_alloc->allocation_flags.cached; + if (host_alloc->priv_drv_data_size) { + ret =3D copy_to_user(user_alloc->priv_drv_data, + alloc_private_data, + host_alloc->priv_drv_data_size); + if (ret) { + pr_err("%s failed to copy private data", + __func__); + ret =3D -EINVAL; + goto cleanup; + } + alloc_private_data +=3D host_alloc->priv_drv_data_size; + } + ret =3D copy_to_user(&args->allocation_info[i].allocation, + &host_alloc->allocation, + sizeof(struct d3dkmthandle)); + if (ret) { + pr_err("%s failed to copy alloc handle", __func__); + ret =3D -EINVAL; + goto cleanup; + } + } + + ret =3D process_allocation_handles(process, device, args, result, + dxgalloc, resource); + if (ret < 0) + goto cleanup; + + ret =3D copy_to_user(&input_args->global_share, &args->global_share, + sizeof(struct d3dkmthandle)); + if (ret) { + pr_err("%s failed to copy global share", __func__); + ret =3D -EINVAL; + } + +cleanup: + + if (ret < 0) { + /* Free local handles before freeing the handles in the host */ + dxgdevice_acquire_alloc_list_lock(device); + if (dxgalloc) + for (i =3D 0; i < alloc_count; i++) + if (dxgalloc[i]) + dxgallocation_free_handle(dxgalloc[i]); + if (resource && args->flags.create_resource) + dxgresource_free_handle(resource); + dxgdevice_release_alloc_list_lock(device); + + /* Destroy allocations in the host to unmap gpadls */ + ret1 =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, + msg.size); + if (ret1 < 0) + pr_err("failed to destroy allocations: %x", ret1); + + dxgdevice_acquire_alloc_list_lock(device); + if (dxgalloc) { + for (i =3D 0; i < alloc_count; i++) { + if (dxgalloc[i]) { + dxgalloc[i]->alloc_handle.v =3D 0; + dxgallocation_destroy(dxgalloc[i]); + dxgalloc[i] =3D NULL; + } + } + } + if (resource && args->flags.create_resource) { + /* + * Prevent the resource memory from freeing. + * It will be freed in the top level function. + */ + kref_get(&resource->resource_kref); + dxgresource_destroy(resource); + } + dxgdevice_release_alloc_list_lock(device); + } + + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +int dxgvmb_send_create_allocation(struct dxgprocess *process, + struct dxgdevice *device, + struct d3dkmt_createallocation *args, + struct d3dkmt_createallocation *__user + input_args, + struct dxgresource *resource, + struct dxgallocation **dxgalloc, + struct d3dddi_allocationinfo2 *alloc_info, + struct d3dkmt_createstandardallocation + *standard_alloc) +{ + struct dxgkvmb_command_createallocation *command =3D NULL; + struct dxgkvmb_command_createallocation_return *result =3D NULL; + int ret =3D -EINVAL; + int i; + u32 result_size =3D 0; + u32 cmd_size =3D 0; + u32 destroy_buffer_size =3D 0; + u32 priv_drv_data_size; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + if (args->private_runtime_data_size >=3D DXG_MAX_VM_BUS_PACKET_SIZE || + args->priv_drv_data_size >=3D DXG_MAX_VM_BUS_PACKET_SIZE) { + ret =3D -EOVERFLOW; + goto cleanup; + } + + /* + * Preallocate the buffer, which will be used for destruction in case + * of a failure + */ + destroy_buffer_size =3D sizeof(struct dxgkvmb_command_destroyallocation) + + args->alloc_count * sizeof(struct d3dkmthandle); + + /* Compute the total private driver size */ + + priv_drv_data_size =3D 0; + + for (i =3D 0; i < args->alloc_count; i++) { + if (alloc_info[i].priv_drv_data_size >=3D + DXG_MAX_VM_BUS_PACKET_SIZE) { + ret =3D -EOVERFLOW; + goto cleanup; + } else { + priv_drv_data_size +=3D alloc_info[i].priv_drv_data_size; + } + if (priv_drv_data_size >=3D DXG_MAX_VM_BUS_PACKET_SIZE) { + ret =3D -EOVERFLOW; + goto cleanup; + } + } + + /* + * Private driver data for the result includes only per allocation + * private data + */ + result_size =3D sizeof(struct dxgkvmb_command_createallocation_return) + + (args->alloc_count - 1) * + sizeof(struct dxgkvmb_command_allocinfo_return) + + priv_drv_data_size; + result =3D vzalloc(result_size); + if (result =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + + /* Private drv data for the command includes the global private data */ + priv_drv_data_size +=3D args->priv_drv_data_size; + + cmd_size =3D sizeof(struct dxgkvmb_command_createallocation) + + args->alloc_count * + sizeof(struct dxgkvmb_command_createallocation_allocinfo) + + args->private_runtime_data_size + priv_drv_data_size; + if (cmd_size > DXG_MAX_VM_BUS_PACKET_SIZE) { + ret =3D -EOVERFLOW; + goto cleanup; + } + + pr_debug("command size, driver_data_size %d %d %ld %ld", + cmd_size, priv_drv_data_size, + sizeof(struct dxgkvmb_command_createallocation), + sizeof(struct dxgkvmb_command_createallocation_allocinfo)); + + ret =3D init_message(&msg, device->adapter, process, + cmd_size); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_CREATEALLOCATION, + process->host_handle); + command->device =3D args->device; + command->flags =3D args->flags; + command->resource =3D args->resource; + command->private_runtime_resource_handle =3D + args->private_runtime_resource_handle; + command->alloc_count =3D args->alloc_count; + command->private_runtime_data_size =3D args->private_runtime_data_size; + command->priv_drv_data_size =3D args->priv_drv_data_size; + + ret =3D copy_private_data(args, command, alloc_info, standard_alloc); + if (ret < 0) + goto cleanup; + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, + result, result_size); + if (ret < 0) { + pr_err("send_create_allocation failed %x", ret); + goto cleanup; + } + + ret =3D create_local_allocations(process, device, args, input_args, + alloc_info, result, resource, dxgalloc, + destroy_buffer_size); +cleanup: + + if (result) + vfree(result); + free_message(&msg, process); + + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +int dxgvmb_send_destroy_allocation(struct dxgprocess *process, + struct dxgdevice *device, + struct d3dkmt_destroyallocation2 *args, + struct d3dkmthandle *alloc_handles) +{ + struct dxgkvmb_command_destroyallocation *destroy_buffer; + u32 destroy_buffer_size; + int ret; + int allocations_size =3D args->alloc_count * sizeof(struct d3dkmthandle); + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + destroy_buffer_size =3D sizeof(struct dxgkvmb_command_destroyallocation) + + allocations_size; + + ret =3D init_message(&msg, device->adapter, process, + destroy_buffer_size); + if (ret) + goto cleanup; + destroy_buffer =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&destroy_buffer->hdr, + DXGK_VMBCOMMAND_DESTROYALLOCATION, + process->host_handle); + destroy_buffer->device =3D args->device; + destroy_buffer->resource =3D args->resource; + destroy_buffer->alloc_count =3D args->alloc_count; + destroy_buffer->flags =3D args->flags; + if (allocations_size) + memcpy(destroy_buffer->allocations, alloc_handles, + allocations_size); + + ret =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, msg.size); + +cleanup: + + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +int dxgvmb_send_get_stdalloc_data(struct dxgdevice *device, + enum d3dkmdt_standardallocationtype alloctype, + struct d3dkmdt_gdisurfacedata *alloc_data, + u32 physical_adapter_index, + u32 *alloc_priv_driver_size, + void *priv_alloc_data, + u32 *res_priv_data_size, + void *priv_res_data) +{ + struct dxgkvmb_command_getstandardallocprivdata *command; + struct dxgkvmb_command_getstandardallocprivdata_return *result =3D NULL; + u32 result_size =3D sizeof(*result); + int ret; + struct dxgvmbusmsgres msg =3D {.hdr =3D NULL}; + + if (priv_alloc_data) + result_size +=3D *alloc_priv_driver_size; + if (priv_res_data) + result_size +=3D *res_priv_data_size; + ret =3D init_message_res(&msg, device->adapter, device->process, + sizeof(*command), result_size); + if (ret) + goto cleanup; + command =3D msg.msg; + result =3D msg.res; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_DDIGETSTANDARDALLOCATIONDRIVERDATA, + device->process->host_handle); + + command->alloc_type =3D alloctype; + command->priv_driver_data_size =3D *alloc_priv_driver_size; + command->physical_adapter_index =3D physical_adapter_index; + command->priv_driver_resource_size =3D *res_priv_data_size; + switch (alloctype) { + case _D3DKMDT_STANDARDALLOCATION_GDISURFACE: + command->gdi_surface =3D *alloc_data; + break; + case _D3DKMDT_STANDARDALLOCATION_SHAREDPRIMARYSURFACE: + case _D3DKMDT_STANDARDALLOCATION_SHADOWSURFACE: + case _D3DKMDT_STANDARDALLOCATION_STAGINGSURFACE: + default: + pr_err("Invalid standard alloc type"); + goto cleanup; + } + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, + result, msg.res_size); + if (ret < 0) + goto cleanup; + + ret =3D ntstatus2int(result->status); + if (ret < 0) + goto cleanup; + + if (*alloc_priv_driver_size && + result->priv_driver_data_size !=3D *alloc_priv_driver_size) { + pr_err("Priv data size mismatch"); + goto cleanup; + } + if (*res_priv_data_size && + result->priv_driver_resource_size !=3D *res_priv_data_size) { + pr_err("Resource priv data size mismatch"); + goto cleanup; + } + *alloc_priv_driver_size =3D result->priv_driver_data_size; + *res_priv_data_size =3D result->priv_driver_resource_size; + if (priv_alloc_data) { + memcpy(priv_alloc_data, &result[1], + result->priv_driver_data_size); + } + if (priv_res_data) { + memcpy(priv_res_data, + (char *)(&result[1]) + result->priv_driver_data_size, + result->priv_driver_resource_size); + } + +cleanup: + + free_message((struct dxgvmbusmsg *)&msg, device->process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + int dxgvmb_send_query_adapter_info(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_queryadapterinfo *args) diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index 879fb3c6b7b2..1f07a883debb 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -735,6 +735,639 @@ dxgk_destroy_context(struct dxgprocess *process, void= *__user inargs) return ret; } =20 +static int +get_standard_alloc_priv_data(struct dxgdevice *device, + struct d3dkmt_createstandardallocation *alloc_info, + u32 *standard_alloc_priv_data_size, + void **standard_alloc_priv_data, + u32 *standard_res_priv_data_size, + void **standard_res_priv_data) +{ + int ret; + struct d3dkmdt_gdisurfacedata gdi_data =3D { }; + u32 priv_data_size =3D 0; + u32 res_priv_data_size =3D 0; + void *priv_data =3D NULL; + void *res_priv_data =3D NULL; + + gdi_data.type =3D _D3DKMDT_GDISURFACE_TEXTURE_CROSSADAPTER; + gdi_data.width =3D alloc_info->existing_heap_data.size; + gdi_data.height =3D 1; + gdi_data.format =3D _D3DDDIFMT_UNKNOWN; + + *standard_alloc_priv_data_size =3D 0; + ret =3D dxgvmb_send_get_stdalloc_data(device, + _D3DKMDT_STANDARDALLOCATION_GDISURFACE, + &gdi_data, 0, + &priv_data_size, NULL, + &res_priv_data_size, + NULL); + if (ret < 0) + goto cleanup; + pr_debug("Priv data size: %d", priv_data_size); + if (priv_data_size =3D=3D 0) { + ret =3D -EINVAL; + goto cleanup; + } + priv_data =3D vzalloc(priv_data_size); + if (priv_data =3D=3D NULL) { + ret =3D -ENOMEM; + pr_err("failed to allocate memory for priv data: %d", + priv_data_size); + goto cleanup; + } + if (res_priv_data_size) { + res_priv_data =3D vzalloc(res_priv_data_size); + if (res_priv_data =3D=3D NULL) { + ret =3D -ENOMEM; + pr_err("failed to alloc memory for res priv data: %d", + res_priv_data_size); + goto cleanup; + } + } + ret =3D dxgvmb_send_get_stdalloc_data(device, + _D3DKMDT_STANDARDALLOCATION_GDISURFACE, + &gdi_data, 0, + &priv_data_size, + priv_data, + &res_priv_data_size, + res_priv_data); + if (ret < 0) + goto cleanup; + *standard_alloc_priv_data_size =3D priv_data_size; + *standard_alloc_priv_data =3D priv_data; + *standard_res_priv_data_size =3D res_priv_data_size; + *standard_res_priv_data =3D res_priv_data; + priv_data =3D NULL; + res_priv_data =3D NULL; + +cleanup: + if (priv_data) + vfree(priv_data); + if (res_priv_data) + vfree(res_priv_data); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +static int +dxgk_create_allocation(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmt_createallocation args; + int ret; + struct dxgadapter *adapter =3D NULL; + struct dxgdevice *device =3D NULL; + struct d3dddi_allocationinfo2 *alloc_info =3D NULL; + struct d3dkmt_createstandardallocation standard_alloc; + u32 alloc_info_size =3D 0; + struct dxgresource *resource =3D NULL; + struct dxgallocation **dxgalloc =3D NULL; + bool resource_mutex_acquired =3D false; + u32 standard_alloc_priv_data_size =3D 0; + void *standard_alloc_priv_data =3D NULL; + u32 res_priv_data_size =3D 0; + void *res_priv_data =3D NULL; + int i; + + pr_debug("ioctl: %s", __func__); + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.alloc_count > D3DKMT_CREATEALLOCATION_MAX || + args.alloc_count =3D=3D 0) { + pr_err("invalid number of allocations to create"); + ret =3D -EINVAL; + goto cleanup; + } + + alloc_info_size =3D sizeof(struct d3dddi_allocationinfo2) * + args.alloc_count; + alloc_info =3D vzalloc(alloc_info_size); + if (alloc_info =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + ret =3D copy_from_user(alloc_info, args.allocation_info, + alloc_info_size); + if (ret) { + pr_err("%s failed to copy alloc info", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + for (i =3D 0; i < args.alloc_count; i++) { + if (args.flags.standard_allocation) { + if (alloc_info[i].priv_drv_data_size !=3D 0) { + pr_err("private data size is not zero"); + ret =3D -EINVAL; + goto cleanup; + } + } + if (alloc_info[i].priv_drv_data_size >=3D + DXG_MAX_VM_BUS_PACKET_SIZE) { + pr_err("private data size is too big: %d %d %ld", + i, alloc_info[i].priv_drv_data_size, + sizeof(alloc_info[0])); + ret =3D -EINVAL; + goto cleanup; + } + } + + if (args.flags.existing_section || args.flags.create_protected) { + pr_err("invalid allocation flags"); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.flags.standard_allocation) { + if (args.standard_allocation =3D=3D NULL) { + pr_err("invalid standard allocation"); + ret =3D -EINVAL; + goto cleanup; + } + ret =3D copy_from_user(&standard_alloc, + args.standard_allocation, + sizeof(standard_alloc)); + if (ret) { + pr_err("%s failed to copy std alloc data", __func__); + ret =3D -EINVAL; + goto cleanup; + } + if (standard_alloc.type =3D=3D + _D3DKMT_STANDARDALLOCATIONTYPE_EXISTINGHEAP) { + if (alloc_info[0].sysmem =3D=3D NULL || + (unsigned long)alloc_info[0].sysmem & + (PAGE_SIZE - 1)) { + pr_err("invalid sysmem pointer"); + ret =3D STATUS_INVALID_PARAMETER; + goto cleanup; + } + if (!args.flags.existing_sysmem) { + pr_err("expected existing_sysmem flag"); + ret =3D STATUS_INVALID_PARAMETER; + goto cleanup; + } + } else if (standard_alloc.type =3D=3D + _D3DKMT_STANDARDALLOCATIONTYPE_CROSSADAPTER) { + if (args.flags.existing_sysmem) { + pr_err("existing_sysmem flag is invalid"); + ret =3D STATUS_INVALID_PARAMETER; + goto cleanup; + + } + if (alloc_info[0].sysmem !=3D NULL) { + pr_err("sysmem should be NULL"); + ret =3D STATUS_INVALID_PARAMETER; + goto cleanup; + } + } else { + pr_err("invalid standard allocation type"); + ret =3D STATUS_INVALID_PARAMETER; + goto cleanup; + } + + if (args.priv_drv_data_size !=3D 0 || + args.alloc_count !=3D 1 || + standard_alloc.existing_heap_data.size =3D=3D 0 || + standard_alloc.existing_heap_data.size & (PAGE_SIZE - 1)) { + pr_err("invalid standard allocation"); + ret =3D -EINVAL; + goto cleanup; + } + args.priv_drv_data_size =3D + sizeof(struct d3dkmt_createstandardallocation); + } + + if (args.flags.create_shared && !args.flags.create_resource) { + pr_err("create_resource must be set for create_shared"); + ret =3D -EINVAL; + goto cleanup; + } + + /* + * The call acquires reference on the device. It is safe to access the + * adapter, because the device holds reference on it. + */ + device =3D dxgprocess_device_by_handle(process, args.device); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgdevice_acquire_lock_shared(device); + if (ret < 0) { + kref_put(&device->device_kref, dxgdevice_release); + device =3D NULL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + if (args.flags.standard_allocation) { + ret =3D get_standard_alloc_priv_data(device, + &standard_alloc, + &standard_alloc_priv_data_size, + &standard_alloc_priv_data, + &res_priv_data_size, + &res_priv_data); + if (ret < 0) + goto cleanup; + pr_debug("Alloc private data: %d", + standard_alloc_priv_data_size); + } + + if (args.flags.create_resource) { + resource =3D dxgresource_create(device); + if (resource =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + resource->private_runtime_handle =3D + args.private_runtime_resource_handle; + } else { + if (args.resource.v) { + /* Adding new allocations to the given resource */ + + dxgprocess_ht_lock_shared_down(process); + resource =3D hmgrtable_get_object_by_type( + &process->handle_table, + HMGRENTRY_TYPE_DXGRESOURCE, + args.resource); + kref_get(&resource->resource_kref); + dxgprocess_ht_lock_shared_up(process); + + if (resource =3D=3D NULL || resource->device !=3D device) { + pr_err("invalid resource handle %x", + args.resource.v); + ret =3D -EINVAL; + goto cleanup; + } + /* Synchronize with resource destruction */ + mutex_lock(&resource->resource_mutex); + if (!dxgresource_is_active(resource)) { + mutex_unlock(&resource->resource_mutex); + ret =3D -EINVAL; + goto cleanup; + } + resource_mutex_acquired =3D true; + } + } + + dxgalloc =3D vzalloc(sizeof(struct dxgallocation *) * args.alloc_count); + if (dxgalloc =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + + for (i =3D 0; i < args.alloc_count; i++) { + struct dxgallocation *alloc; + u32 priv_data_size; + + if (args.flags.standard_allocation) + priv_data_size =3D standard_alloc_priv_data_size; + else + priv_data_size =3D alloc_info[i].priv_drv_data_size; + + if (alloc_info[i].sysmem && !args.flags.standard_allocation) { + if ((unsigned long) + alloc_info[i].sysmem & (PAGE_SIZE - 1)) { + pr_err("invalid sysmem alloc %d, %p", + i, alloc_info[i].sysmem); + ret =3D -EINVAL; + goto cleanup; + } + } + if ((alloc_info[0].sysmem =3D=3D NULL) !=3D + (alloc_info[i].sysmem =3D=3D NULL)) { + pr_err("All allocations must have sysmem pointer"); + ret =3D -EINVAL; + goto cleanup; + } + + dxgalloc[i] =3D dxgallocation_create(process); + if (dxgalloc[i] =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + alloc =3D dxgalloc[i]; + + if (resource) { + ret =3D dxgresource_add_alloc(resource, alloc); + if (ret < 0) + goto cleanup; + } else { + dxgdevice_add_alloc(device, alloc); + } + if (args.flags.create_shared) { + /* Remember alloc private data to use it during open */ + alloc->priv_drv_data =3D vzalloc(priv_data_size + + offsetof(struct privdata, data) - 1); + if (alloc->priv_drv_data =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + if (args.flags.standard_allocation) { + memcpy(alloc->priv_drv_data->data, + standard_alloc_priv_data, + standard_alloc_priv_data_size); + alloc->priv_drv_data->data_size =3D + standard_alloc_priv_data_size; + } else { + ret =3D copy_from_user( + alloc->priv_drv_data->data, + alloc_info[i].priv_drv_data, + priv_data_size); + if (ret) { + pr_err("%s failed to copy priv data", + __func__); + ret =3D -EINVAL; + goto cleanup; + } + alloc->priv_drv_data->data_size =3D + priv_data_size; + } + } + } + + ret =3D dxgvmb_send_create_allocation(process, device, &args, inargs, + resource, dxgalloc, alloc_info, + &standard_alloc); +cleanup: + + if (resource_mutex_acquired) { + mutex_unlock(&resource->resource_mutex); + kref_put(&resource->resource_kref, dxgresource_release); + } + if (ret < 0) { + if (dxgalloc) { + for (i =3D 0; i < args.alloc_count; i++) { + if (dxgalloc[i]) + dxgallocation_destroy(dxgalloc[i]); + } + } + if (resource && args.flags.create_resource) { + dxgresource_destroy(resource); + } + } + if (dxgalloc) + vfree(dxgalloc); + if (standard_alloc_priv_data) + vfree(standard_alloc_priv_data); + if (res_priv_data) + vfree(res_priv_data); + if (alloc_info) + vfree(alloc_info); + + if (adapter) + dxgadapter_release_lock_shared(adapter); + + if (device) { + dxgdevice_release_lock_shared(device); + kref_put(&device->device_kref, dxgdevice_release); + } + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int validate_alloc(struct dxgallocation *alloc0, + struct dxgallocation *alloc, + struct dxgdevice *device, + struct d3dkmthandle alloc_handle) +{ + u32 fail_reason; + + if (alloc =3D=3D NULL) { + fail_reason =3D 1; + goto cleanup; + } + if (alloc->resource_owner !=3D alloc0->resource_owner) { + fail_reason =3D 2; + goto cleanup; + } + if (alloc->resource_owner) { + if (alloc->owner.resource !=3D alloc0->owner.resource) { + fail_reason =3D 3; + goto cleanup; + } + if (alloc->owner.resource->device !=3D device) { + fail_reason =3D 4; + goto cleanup; + } + } else { + if (alloc->owner.device !=3D device) { + fail_reason =3D 6; + goto cleanup; + } + } + return 0; +cleanup: + pr_err("Alloc validation failed: reason: %d %x", + fail_reason, alloc_handle.v); + return -EINVAL; +} + +static int +dxgk_destroy_allocation(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmt_destroyallocation2 args; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + int ret; + struct d3dkmthandle *alloc_handles =3D NULL; + struct dxgallocation **allocs =3D NULL; + struct dxgresource *resource =3D NULL; + int i; + + pr_debug("ioctl: %s", __func__); + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.alloc_count > D3DKMT_CREATEALLOCATION_MAX || + ((args.alloc_count =3D=3D 0) =3D=3D (args.resource.v =3D=3D 0))) { + pr_err("invalid number of allocations"); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.alloc_count) { + u32 handle_size =3D sizeof(struct d3dkmthandle) * + args.alloc_count; + + alloc_handles =3D vzalloc(handle_size); + if (alloc_handles =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + allocs =3D vzalloc(sizeof(struct dxgallocation *) * + args.alloc_count); + if (allocs =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + ret =3D copy_from_user(alloc_handles, args.allocations, + handle_size); + if (ret) { + pr_err("%s failed to copy alloc handles", __func__); + ret =3D -EINVAL; + goto cleanup; + } + } + + /* + * The call acquires reference on the device. It is safe to access the + * adapter, because the device holds reference on it. + */ + device =3D dxgprocess_device_by_handle(process, args.device); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + /* Acquire the device lock to synchronize with the device destriction */ + ret =3D dxgdevice_acquire_lock_shared(device); + if (ret < 0) { + kref_put(&device->device_kref, dxgdevice_release); + device =3D NULL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + /* + * Destroy the local allocation handles first. If the host handle + * is destroyed first, another object could be assigned to the process + * table at the same place as the allocation handle and it will fail. + */ + if (args.alloc_count) { + dxgprocess_ht_lock_exclusive_down(process); + for (i =3D 0; i < args.alloc_count; i++) { + allocs[i] =3D + hmgrtable_get_object_by_type(&process->handle_table, + HMGRENTRY_TYPE_DXGALLOCATION, + alloc_handles[i]); + ret =3D + validate_alloc(allocs[0], allocs[i], device, + alloc_handles[i]); + if (ret < 0) { + dxgprocess_ht_lock_exclusive_up(process); + goto cleanup; + } + } + dxgprocess_ht_lock_exclusive_up(process); + for (i =3D 0; i < args.alloc_count; i++) + dxgallocation_free_handle(allocs[i]); + } else { + struct dxgallocation *alloc; + + dxgprocess_ht_lock_exclusive_down(process); + resource =3D hmgrtable_get_object_by_type(&process->handle_table, + HMGRENTRY_TYPE_DXGRESOURCE, + args.resource); + if (resource =3D=3D NULL) { + pr_err("Invalid resource handle: %x", + args.resource.v); + ret =3D -EINVAL; + } else if (resource->device !=3D device) { + pr_err("Resource belongs to wrong device: %x", + args.resource.v); + ret =3D -EINVAL; + } else { + hmgrtable_free_handle(&process->handle_table, + HMGRENTRY_TYPE_DXGRESOURCE, + args.resource); + resource->object_state =3D DXGOBJECTSTATE_DESTROYED; + resource->handle.v =3D 0; + resource->handle_valid =3D 0; + } + dxgprocess_ht_lock_exclusive_up(process); + + if (ret < 0) + goto cleanup; + + dxgdevice_acquire_alloc_list_lock_shared(device); + list_for_each_entry(alloc, &resource->alloc_list_head, + alloc_list_entry) { + dxgallocation_free_handle(alloc); + } + dxgdevice_release_alloc_list_lock_shared(device); + } + + if (args.alloc_count && allocs[0]->resource_owner) + resource =3D allocs[0]->owner.resource; + + if (resource) { + kref_get(&resource->resource_kref); + mutex_lock(&resource->resource_mutex); + } + + ret =3D dxgvmb_send_destroy_allocation(process, device, &args, + alloc_handles); + + /* + * Destroy the allocations after the host destroyed it. + * The allocation gpadl teardown will wait until the host unmaps its + * gpadl. + */ + dxgdevice_acquire_alloc_list_lock(device); + if (args.alloc_count) { + for (i =3D 0; i < args.alloc_count; i++) { + if (allocs[i]) { + allocs[i]->alloc_handle.v =3D 0; + dxgallocation_destroy(allocs[i]); + } + } + } else { + dxgresource_destroy(resource); + } + dxgdevice_release_alloc_list_lock(device); + + if (resource) { + mutex_unlock(&resource->resource_mutex); + kref_put(&resource->resource_kref, dxgresource_release); + } + +cleanup: + + if (adapter) + dxgadapter_release_lock_shared(adapter); + + if (device) { + dxgdevice_release_lock_shared(device); + kref_put(&device->device_kref, dxgdevice_release); + } + + if (alloc_handles) + vfree(alloc_handles); + + if (allocs) + vfree(allocs); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + /* * IOCTL processing * The driver IOCTLs return @@ -799,8 +1432,12 @@ void init_ioctls(void) LX_DXCREATECONTEXTVIRTUAL); SET_IOCTL(/*0x5 */ dxgk_destroy_context, LX_DXDESTROYCONTEXT); + SET_IOCTL(/*0x6 */ dxgk_create_allocation, + LX_DXCREATEALLOCATION); SET_IOCTL(/*0x9 */ dxgk_query_adapter_info, LX_DXQUERYADAPTERINFO); + SET_IOCTL(/*0x13 */ dxgk_destroy_allocation, + LX_DXDESTROYALLOCATION2); SET_IOCTL(/*0x14 */ dxgk_enum_adapters, LX_DXENUMADAPTERS2); SET_IOCTL(/*0x15 */ dxgk_close_adapter, diff --git a/drivers/hv/dxgkrnl/misc.h b/drivers/hv/dxgkrnl/misc.h index 8f7b37049308..41abdc504bc2 100644 --- a/drivers/hv/dxgkrnl/misc.h +++ b/drivers/hv/dxgkrnl/misc.h @@ -31,6 +31,9 @@ extern const struct d3dkmthandle zerohandle; * plistmutex * table_lock * context_list_lock + * alloc_list_lock + * resource_mutex + * shared_resource_list_lock * core_lock * device_lock * process_adapter_mutex --=20 2.35.1 From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 2420BC433EF for ; Sat, 5 Feb 2022 02:34:53 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1379144AbiBECew (ORCPT ); Fri, 4 Feb 2022 21:34:52 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45090 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1379004AbiBECeY (ORCPT ); Fri, 4 Feb 2022 21:34:24 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id 837C820B8029; Fri, 4 Feb 2022 18:34:24 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com 837C820B8029 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028464; bh=EIrjHbheOQ0PQHv7kwOqUhp+IROFKpCdIzkkDL6D0nE=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=fIqVipIU0LZup4AwJCLTkIYcQCVcheM+mABNabtLdrejt5RACDzFEVoew8IBno7wY /AhCEtVMALDsA4oljosQHaiTD2e03euwUlM1XRZKMD3dTIr3pstGjbSWshyBNgNzU6 MRcogaLvclmNJD2GDu2QK78g/ROZVpVXizdZJyJw= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 07/24] drivers: hv: dxgkrnl: Create and destroy GPU sync objects Date: Fri, 4 Feb 2022 18:34:05 -0800 Message-Id: X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" GPU synchronization objects are used to synchornize GPU command execution between different execution contexts. Implement ioctls to create and destroy sync objects: LX_DXCREATESYNCHRONIZATIONOBJECT(D3DKMTCreateSynchronizationObject), LX_DXDESTROYSYNCHRONIZATIONOBJECT(D3DKMTDestroySynchronizationObject) Monitored fence sync objects have a CPU virtual address to allow an application to read the fence value. dxg_map_iospace and dxg_unmap_iospace implement creation of the CPU virtual address. This is done as follow: - The host allocates a portion of the guest IO space, which is mapped to the actual fence value memory on the host - The host returns the guest IO space address to the guest - The guest allocates a CPU virtual address and updates page tables to point to the IO space address Signed-off-by: Iouri Tarassov --- drivers/hv/dxgkrnl/dxgadapter.c | 184 +++++++++++++++++++++++++++++ drivers/hv/dxgkrnl/dxgkrnl.h | 80 +++++++++++++ drivers/hv/dxgkrnl/dxgmodule.c | 1 + drivers/hv/dxgkrnl/dxgprocess.c | 16 +++ drivers/hv/dxgkrnl/dxgvmbus.c | 199 ++++++++++++++++++++++++++++++++ drivers/hv/dxgkrnl/ioctl.c | 130 +++++++++++++++++++++ 6 files changed, 610 insertions(+) diff --git a/drivers/hv/dxgkrnl/dxgadapter.c b/drivers/hv/dxgkrnl/dxgadapte= r.c index 3f51456272cc..2a9a731c3352 100644 --- a/drivers/hv/dxgkrnl/dxgadapter.c +++ b/drivers/hv/dxgkrnl/dxgadapter.c @@ -165,6 +165,24 @@ void dxgadapter_remove_process(struct dxgprocess_adapt= er *process_info) process_info->adapter_process_list_entry.prev =3D NULL; } =20 +void dxgadapter_add_syncobj(struct dxgadapter *adapter, + struct dxgsyncobject *object) +{ + down_write(&adapter->shared_resource_list_lock); + list_add_tail(&object->syncobj_list_entry, &adapter->syncobj_list_head); + up_write(&adapter->shared_resource_list_lock); +} + +void dxgadapter_remove_syncobj(struct dxgsyncobject *object) +{ + down_write(&object->adapter->shared_resource_list_lock); + if (object->syncobj_list_entry.next) { + list_del(&object->syncobj_list_entry); + object->syncobj_list_entry.next =3D NULL; + } + up_write(&object->adapter->shared_resource_list_lock); +} + int dxgadapter_acquire_lock_exclusive(struct dxgadapter *adapter) { down_write(&adapter->core_lock); @@ -217,6 +235,7 @@ struct dxgdevice *dxgdevice_create(struct dxgadapter *a= dapter, init_rwsem(&device->context_list_lock); init_rwsem(&device->alloc_list_lock); INIT_LIST_HEAD(&device->pqueue_list_head); + INIT_LIST_HEAD(&device->syncobj_list_head); device->object_state =3D DXGOBJECTSTATE_CREATED; device->execution_state =3D _D3DKMT_DEVICEEXECUTION_ACTIVE; =20 @@ -232,6 +251,7 @@ struct dxgdevice *dxgdevice_create(struct dxgadapter *a= dapter, void dxgdevice_stop(struct dxgdevice *device) { struct dxgallocation *alloc; + struct dxgsyncobject *syncobj; =20 pr_debug("%s: %p", __func__, device); dxgdevice_acquire_alloc_list_lock(device); @@ -240,6 +260,12 @@ void dxgdevice_stop(struct dxgdevice *device) } dxgdevice_release_alloc_list_lock(device); =20 + hmgrtable_lock(&device->process->handle_table, DXGLOCK_EXCL); + list_for_each_entry(syncobj, &device->syncobj_list_head, + syncobj_list_entry) { + dxgsyncobject_stop(syncobj); + } + hmgrtable_unlock(&device->process->handle_table, DXGLOCK_EXCL); pr_debug("%s: end %p\n", __func__, device); } =20 @@ -269,6 +295,20 @@ void dxgdevice_destroy(struct dxgdevice *device) =20 dxgdevice_acquire_alloc_list_lock(device); =20 + while (!list_empty(&device->syncobj_list_head)) { + struct dxgsyncobject *syncobj =3D + list_first_entry(&device->syncobj_list_head, + struct dxgsyncobject, + syncobj_list_entry); + list_del(&syncobj->syncobj_list_entry); + syncobj->syncobj_list_entry.next =3D NULL; + dxgdevice_release_alloc_list_lock(device); + + dxgsyncobject_destroy(process, syncobj); + + dxgdevice_acquire_alloc_list_lock(device); + } + { struct dxgallocation *alloc; struct dxgallocation *tmp; @@ -569,6 +609,30 @@ void dxgdevice_release(struct kref *refcount) vfree(device); } =20 +void dxgdevice_add_syncobj(struct dxgdevice *device, + struct dxgsyncobject *syncobj) +{ + dxgdevice_acquire_alloc_list_lock(device); + list_add_tail(&syncobj->syncobj_list_entry, &device->syncobj_list_head); + kref_get(&syncobj->syncobj_kref); + dxgdevice_release_alloc_list_lock(device); +} + +void dxgdevice_remove_syncobj(struct dxgsyncobject *entry) +{ + struct dxgdevice *device =3D entry->device; + + dxgdevice_acquire_alloc_list_lock(device); + if (entry->syncobj_list_entry.next) { + list_del(&entry->syncobj_list_entry); + entry->syncobj_list_entry.next =3D NULL; + kref_put(&entry->syncobj_kref, dxgsyncobject_release); + } + dxgdevice_release_alloc_list_lock(device); + kref_put(&device->device_kref, dxgdevice_release); + entry->device =3D NULL; +} + struct dxgcontext *dxgcontext_create(struct dxgdevice *device) { struct dxgcontext *context =3D vzalloc(sizeof(struct dxgcontext)); @@ -806,3 +870,123 @@ void dxgprocess_adapter_remove_device(struct dxgdevic= e *device) } mutex_unlock(&device->adapter_info->device_list_mutex); } + +struct dxgsyncobject *dxgsyncobject_create(struct dxgprocess *process, + struct dxgdevice *device, + struct dxgadapter *adapter, + enum + d3dddi_synchronizationobject_type + type, + struct + d3dddi_synchronizationobject_flags + flags) +{ + struct dxgsyncobject *syncobj; + + syncobj =3D vzalloc(sizeof(*syncobj)); + if (syncobj =3D=3D NULL) + goto cleanup; + syncobj->type =3D type; + syncobj->process =3D process; + switch (type) { + case _D3DDDI_MONITORED_FENCE: + case _D3DDDI_PERIODIC_MONITORED_FENCE: + syncobj->monitored_fence =3D 1; + break; + default: + break; + } + if (flags.shared) { + syncobj->shared =3D 1; + if (!flags.nt_security_sharing) { + dev_err(dxgglobaldev, + "%s: nt_security_sharing must be set", + __func__); + goto cleanup; + } + } + + kref_init(&syncobj->syncobj_kref); + + if (syncobj->monitored_fence) { + syncobj->device =3D device; + syncobj->device_handle =3D device->handle; + kref_get(&device->device_kref); + dxgdevice_add_syncobj(device, syncobj); + } else { + dxgadapter_add_syncobj(adapter, syncobj); + } + syncobj->adapter =3D adapter; + kref_get(&adapter->adapter_kref); + + pr_debug("%s 0x%p\n", __func__, syncobj); + return syncobj; +cleanup: + if (syncobj) + vfree(syncobj); + return NULL; +} + +void dxgsyncobject_destroy(struct dxgprocess *process, + struct dxgsyncobject *syncobj) +{ + int destroyed; + + pr_debug("%s 0x%p", __func__, syncobj); + + dxgsyncobject_stop(syncobj); + + destroyed =3D test_and_set_bit(0, &syncobj->flags); + if (!destroyed) { + pr_debug("Deleting handle: %x", syncobj->handle.v); + hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL); + if (syncobj->handle.v) { + hmgrtable_free_handle(&process->handle_table, + HMGRENTRY_TYPE_DXGSYNCOBJECT, + syncobj->handle); + syncobj->handle.v =3D 0; + kref_put(&syncobj->syncobj_kref, dxgsyncobject_release); + } + hmgrtable_unlock(&process->handle_table, DXGLOCK_EXCL); + + if (syncobj->monitored_fence) + dxgdevice_remove_syncobj(syncobj); + else + dxgadapter_remove_syncobj(syncobj); + if (syncobj->adapter) { + kref_put(&syncobj->adapter->adapter_kref, + dxgadapter_release); + syncobj->adapter =3D NULL; + } + } + kref_put(&syncobj->syncobj_kref, dxgsyncobject_release); +} + +void dxgsyncobject_stop(struct dxgsyncobject *syncobj) +{ + int stopped =3D test_and_set_bit(1, &syncobj->flags); + + if (!stopped) { + pr_debug("stopping"); + if (syncobj->monitored_fence) { + if (syncobj->mapped_address) { + int ret =3D + dxg_unmap_iospace(syncobj->mapped_address, + PAGE_SIZE); + + (void)ret; + pr_debug("unmap fence %d %p\n", + ret, syncobj->mapped_address); + syncobj->mapped_address =3D NULL; + } + } + } +} + +void dxgsyncobject_release(struct kref *refcount) +{ + struct dxgsyncobject *syncobj; + + syncobj =3D container_of(refcount, struct dxgsyncobject, syncobj_kref); + vfree(syncobj); +} diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index 28c3dbef0ef3..bffa7f1a21c1 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -33,6 +33,7 @@ struct dxgdevice; struct dxgcontext; struct dxgallocation; struct dxgresource; +struct dxgsyncobject; =20 #include "misc.h" #include "hmgr.h" @@ -81,6 +82,56 @@ int dxgvmbuschannel_init(struct dxgvmbuschannel *ch, str= uct hv_device *hdev); void dxgvmbuschannel_destroy(struct dxgvmbuschannel *ch); void dxgvmbuschannel_receive(void *ctx); =20 +/* + * This is GPU synchronization object, which is used to synchronize execut= ion + * between GPU contextx/hardware queues or for tracking GPU execution prog= ress. + * A dxgsyncobject is created when somebody creates a syncobject or opens a + * shared syncobject. + * A syncobject belongs to an adapter, unless it is a cross-adapter object. + * Cross adapter syncobjects are currently not implemented. + * + * D3DDDI_MONITORED_FENCE and D3DDDI_PERIODIC_MONITORED_FENCE are called + * "device" syncobject, because the belong to a device (dxgdevice). + * Device syncobjects are inserted to a list in dxgdevice. + * + */ +struct dxgsyncobject { + struct kref syncobj_kref; + enum d3dddi_synchronizationobject_type type; + /* + * List entry in dxgdevice for device sync objects. + * List entry in dxgadapter for other objects + */ + struct list_head syncobj_list_entry; + /* Adapter, the syncobject belongs to. NULL for stopped sync obejcts. */ + struct dxgadapter *adapter; + /* + * Pointer to the device, which was used to create the object. + * This is NULL for non-device syncbjects + */ + struct dxgdevice *device; + struct dxgprocess *process; + /* CPU virtual address of the fence value for "device" syncobjects */ + void *mapped_address; + /* Handle in the process handle table */ + struct d3dkmthandle handle; + /* Cached handle of the device. Used to avoid device dereference. */ + struct d3dkmthandle device_handle; + union { + struct { + /* Must be the first bit */ + u32 destroyed:1; + /* Must be the second bit */ + u32 stopped:1; + /* device syncobject */ + u32 monitored_fence:1; + u32 shared:1; + u32 reserved:27; + }; + long flags; + }; +}; + /* * The structure defines an offered vGPU vm bus channel. */ @@ -90,6 +141,20 @@ struct dxgvgpuchannel { struct hv_device *hdev; }; =20 +struct dxgsyncobject *dxgsyncobject_create(struct dxgprocess *process, + struct dxgdevice *device, + struct dxgadapter *adapter, + enum + d3dddi_synchronizationobject_type + type, + struct + d3dddi_synchronizationobject_flags + flags); +void dxgsyncobject_destroy(struct dxgprocess *process, + struct dxgsyncobject *syncobj); +void dxgsyncobject_stop(struct dxgsyncobject *syncobj); +void dxgsyncobject_release(struct kref *refcount); + struct dxgglobal { struct dxgvmbuschannel channel; struct delayed_work dwork; @@ -254,6 +319,8 @@ struct dxgadapter { struct list_head adapter_list_entry; /* The list of dxgprocess_adapter entries */ struct list_head adapter_process_list_head; + /* List of all non-device dxgsyncobject objects */ + struct list_head syncobj_list_head; /* This lock protects shared resource and syncobject lists */ struct rw_semaphore shared_resource_list_lock; struct pci_dev *pci_dev; @@ -279,6 +346,9 @@ void dxgadapter_release_lock_shared(struct dxgadapter *= adapter); int dxgadapter_acquire_lock_exclusive(struct dxgadapter *adapter); void dxgadapter_acquire_lock_forced(struct dxgadapter *adapter); void dxgadapter_release_lock_exclusive(struct dxgadapter *adapter); +void dxgadapter_add_syncobj(struct dxgadapter *adapter, + struct dxgsyncobject *so); +void dxgadapter_remove_syncobj(struct dxgsyncobject *so); void dxgadapter_add_process(struct dxgadapter *adapter, struct dxgprocess_adapter *process_info); void dxgadapter_remove_process(struct dxgprocess_adapter *process_info); @@ -308,6 +378,7 @@ struct dxgdevice { struct list_head resource_list_head; /* List of paging queues. Protected by process handle table lock. */ struct list_head pqueue_list_head; + struct list_head syncobj_list_head; struct d3dkmthandle handle; enum d3dkmt_deviceexecution_state execution_state; u32 handle_valid; @@ -328,6 +399,8 @@ void dxgdevice_remove_alloc_safe(struct dxgdevice *dev, struct dxgallocation *a); void dxgdevice_add_resource(struct dxgdevice *dev, struct dxgresource *res= ); void dxgdevice_remove_resource(struct dxgdevice *dev, struct dxgresource *= res); +void dxgdevice_add_syncobj(struct dxgdevice *dev, struct dxgsyncobject *so= ); +void dxgdevice_remove_syncobj(struct dxgsyncobject *so); bool dxgdevice_is_active(struct dxgdevice *dev); void dxgdevice_acquire_context_list_lock(struct dxgdevice *dev); void dxgdevice_release_context_list_lock(struct dxgdevice *dev); @@ -435,6 +508,7 @@ void init_ioctls(void); long dxgk_compat_ioctl(struct file *f, unsigned int p1, unsigned long p2); long dxgk_unlocked_ioctl(struct file *f, unsigned int p1, unsigned long p2= ); =20 +int dxg_unmap_iospace(void *va, u32 size); static inline void guid_to_luid(guid_t *guid, struct winluid *luid) { *luid =3D *(struct winluid *)&guid->b[0]; @@ -488,6 +562,12 @@ int dxgvmb_send_create_allocation(struct dxgprocess *p= r, struct dxgdevice *dev, int dxgvmb_send_destroy_allocation(struct dxgprocess *pr, struct dxgdevice= *dev, struct d3dkmt_destroyallocation2 *args, struct d3dkmthandle *alloc_handles); +int dxgvmb_send_create_sync_object(struct dxgprocess *pr, + struct dxgadapter *adapter, + struct d3dkmt_createsynchronizationobject2 + *args, struct dxgsyncobject *so); +int dxgvmb_send_destroy_sync_object(struct dxgprocess *pr, + struct d3dkmthandle h); int dxgvmb_send_query_adapter_info(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_queryadapterinfo *args); diff --git a/drivers/hv/dxgkrnl/dxgmodule.c b/drivers/hv/dxgkrnl/dxgmodule.c index d865ac45f89d..9d339f15a4b7 100644 --- a/drivers/hv/dxgkrnl/dxgmodule.c +++ b/drivers/hv/dxgkrnl/dxgmodule.c @@ -158,6 +158,7 @@ int dxgglobal_create_adapter(struct pci_dev *dev, guid_= t *guid, init_rwsem(&adapter->core_lock); =20 INIT_LIST_HEAD(&adapter->adapter_process_list_head); + INIT_LIST_HEAD(&adapter->syncobj_list_head); init_rwsem(&adapter->shared_resource_list_lock); adapter->pci_dev =3D dev; guid_to_luid(guid, &adapter->luid); diff --git a/drivers/hv/dxgkrnl/dxgprocess.c b/drivers/hv/dxgkrnl/dxgproces= s.c index 1e6500e12a22..30af930cc8c0 100644 --- a/drivers/hv/dxgkrnl/dxgprocess.c +++ b/drivers/hv/dxgkrnl/dxgprocess.c @@ -59,6 +59,7 @@ void dxgprocess_destroy(struct dxgprocess *process) enum hmgrentry_type t; struct d3dkmthandle h; void *o; + struct dxgsyncobject *syncobj; struct dxgprocess_adapter *entry; struct dxgprocess_adapter *tmp; =20 @@ -84,6 +85,21 @@ void dxgprocess_destroy(struct dxgprocess *process) } } =20 + i =3D 0; + while (hmgrtable_next_entry(&process->handle_table, &i, &t, &h, &o)) { + switch (t) { + case HMGRENTRY_TYPE_DXGSYNCOBJECT: + pr_debug("Destroy syncobj: %p %d", o, i); + syncobj =3D o; + syncobj->handle.v =3D 0; + dxgsyncobject_destroy(process, syncobj); + break; + default: + pr_err("invalid entry in handle table %d", t); + break; + } + } + hmgrtable_destroy(&process->handle_table); hmgrtable_destroy(&process->local_handle_table); } diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index 541182c0b728..2cc49283c090 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -479,6 +479,86 @@ dxgvmb_send_sync_msg_ntstatus(struct dxgvmbuschannel *= channel, return ret; } =20 +static int check_iospace_address(unsigned long address, u32 size) +{ + if (address < dxgglobal->mmiospace_base || + size > dxgglobal->mmiospace_size || + address >=3D (dxgglobal->mmiospace_base + + dxgglobal->mmiospace_size - size)) { + pr_err("invalid iospace address %lx", address); + return -EINVAL; + } + return 0; +} + +int dxg_unmap_iospace(void *va, u32 size) +{ + int ret =3D 0; + + pr_debug("%s %p %x", __func__, va, size); + + /* + * When an app calls exit(), dxgkrnl is called to close the device + * with current->mm equal to NULL. + */ + if (current->mm) { + ret =3D vm_munmap((unsigned long)va, size); + if (ret) { + pr_err("vm_munmap failed %d", ret); + return -ENOTRECOVERABLE; + } + } + return 0; +} + +static u8 *dxg_map_iospace(u64 iospace_address, u32 size, + unsigned long protection, bool cached) +{ + struct vm_area_struct *vma; + unsigned long va; + int ret =3D 0; + + pr_debug("%s: %llx %x %lx", + __func__, iospace_address, size, protection); + if (check_iospace_address(iospace_address, size) < 0) { + pr_err("%s: invalid address", __func__); + return NULL; + } + + va =3D vm_mmap(NULL, 0, size, protection, MAP_SHARED | MAP_ANONYMOUS, 0); + if ((long)va <=3D 0) { + pr_err("vm_mmap failed %lx %d", va, size); + return NULL; + } + + mmap_read_lock(current->mm); + vma =3D find_vma(current->mm, (unsigned long)va); + if (vma) { + pgprot_t prot =3D vma->vm_page_prot; + + if (!cached) + prot =3D pgprot_writecombine(prot); + pr_debug("vma: %lx %lx %lx", + vma->vm_start, vma->vm_end, va); + vma->vm_pgoff =3D iospace_address >> PAGE_SHIFT; + ret =3D io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, + size, prot); + if (ret) + pr_err("io_remap_pfn_range failed: %d", ret); + } else { + pr_err("failed to find vma: %p %lx", vma, va); + ret =3D -ENOMEM; + } + mmap_read_unlock(current->mm); + + if (ret) { + dxg_unmap_iospace((void *)va, size); + return NULL; + } + pr_debug("%s end: %lx", __func__, va); + return (u8 *) va; +} + /* * Global messages to the host */ @@ -597,6 +677,39 @@ int dxgvmb_send_destroy_process(struct d3dkmthandle pr= ocess) return ret; } =20 +int dxgvmb_send_destroy_sync_object(struct dxgprocess *process, + struct d3dkmthandle sync_object) +{ + struct dxgkvmb_command_destroysyncobject *command; + int ret; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, NULL, process, sizeof(*command)); + if (ret) + return ret; + command =3D (void *)msg.msg; + + ret =3D dxgglobal_acquire_channel_lock(); + if (ret < 0) + goto cleanup; + + command_vm_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_DESTROYSYNCOBJECT, + process->host_handle); + command->sync_object =3D sync_object; + + ret =3D dxgvmb_send_sync_msg_ntstatus(dxgglobal_get_dxgvmbuschannel(), + msg.hdr, msg.size); + + dxgglobal_release_channel_lock(); + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + /* * Virtual GPU messages to the host */ @@ -1454,6 +1567,92 @@ int dxgvmb_send_get_stdalloc_data(struct dxgdevice *= device, return ret; } =20 +static void set_result(struct d3dkmt_createsynchronizationobject2 *args, + u64 fence_gpu_va, u8 *va) +{ + args->info.periodic_monitored_fence.fence_gpu_virtual_address =3D + fence_gpu_va; + args->info.periodic_monitored_fence.fence_cpu_virtual_address =3D va; +} + +int +dxgvmb_send_create_sync_object(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_createsynchronizationobject2 *args, + struct dxgsyncobject *syncobj) +{ + struct dxgkvmb_command_createsyncobject_return result =3D { }; + struct dxgkvmb_command_createsyncobject *command; + int ret; + u8 *va =3D 0; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, adapter, process, sizeof(*command)); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_CREATESYNCOBJECT, + process->host_handle); + command->args =3D *args; + command->client_hint =3D 1; /* CLIENTHINT_UMD */ + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, &result, + sizeof(result)); + if (ret < 0) { + pr_err("%s failed %d", __func__, ret); + goto cleanup; + } + args->sync_object =3D result.sync_object; + if (syncobj->shared) { + if (result.global_sync_object.v =3D=3D 0) { + pr_err("shared handle is 0"); + ret =3D -EINVAL; + goto cleanup; + } + args->info.shared_handle =3D result.global_sync_object; + } + + if (syncobj->monitored_fence) { + va =3D dxg_map_iospace(result.fence_storage_address, PAGE_SIZE, + PROT_READ | PROT_WRITE, true); + if (va =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + if (args->info.type =3D=3D _D3DDDI_MONITORED_FENCE) { + args->info.monitored_fence.fence_gpu_virtual_address =3D + result.fence_gpu_va; + args->info.monitored_fence.fence_cpu_virtual_address =3D + va; + { + unsigned long value; + + pr_debug("fence cpu va: %p", va); + ret =3D copy_from_user(&value, va, + sizeof(u64)); + if (ret) { + pr_err("failed to read fence"); + ret =3D -EINVAL; + } else { + pr_debug("fence value:%lx", + value); + } + } + } else { + set_result(args, result.fence_gpu_va, va); + } + syncobj->mapped_address =3D va; + } + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + int dxgvmb_send_query_adapter_info(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_queryadapterinfo *args) diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index 1f07a883debb..bc1ac2dd302f 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -1368,6 +1368,132 @@ dxgk_destroy_allocation(struct dxgprocess *process,= void *__user inargs) return ret; } =20 +static int +dxgk_create_sync_object(struct dxgprocess *process, void *__user inargs) +{ + int ret; + struct d3dkmt_createsynchronizationobject2 args; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + struct dxgsyncobject *syncobj =3D NULL; + bool device_lock_acquired =3D false; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + device =3D dxgprocess_device_by_handle(process, args.device); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgdevice_acquire_lock_shared(device); + if (ret < 0) + goto cleanup; + + device_lock_acquired =3D true; + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + syncobj =3D dxgsyncobject_create(process, device, adapter, args.info.type, + args.info.flags); + if (syncobj =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgvmb_send_create_sync_object(process, adapter, &args, syncobj); + if (ret < 0) + goto cleanup; + + ret =3D copy_to_user(inargs, &args, sizeof(args)); + if (ret) { + pr_err("%s failed to copy output args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL); + ret =3D hmgrtable_assign_handle(&process->handle_table, syncobj, + HMGRENTRY_TYPE_DXGSYNCOBJECT, + args.sync_object); + if (ret >=3D 0) + syncobj->handle =3D args.sync_object; + hmgrtable_unlock(&process->handle_table, DXGLOCK_EXCL); + +cleanup: + + if (ret < 0) { + if (syncobj) { + dxgsyncobject_destroy(process, syncobj); + if (args.sync_object.v) + dxgvmb_send_destroy_sync_object(process, + args.sync_object); + } + } + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device_lock_acquired) + dxgdevice_release_lock_shared(device); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_destroy_sync_object(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmt_destroysynchronizationobject args; + struct dxgsyncobject *syncobj =3D NULL; + int ret; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + pr_debug("handle 0x%x", args.sync_object.v); + hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL); + syncobj =3D hmgrtable_get_object_by_type(&process->handle_table, + HMGRENTRY_TYPE_DXGSYNCOBJECT, + args.sync_object); + if (syncobj) { + pr_debug("syncobj 0x%p", syncobj); + syncobj->handle.v =3D 0; + hmgrtable_free_handle(&process->handle_table, + HMGRENTRY_TYPE_DXGSYNCOBJECT, + args.sync_object); + } + hmgrtable_unlock(&process->handle_table, DXGLOCK_EXCL); + + if (syncobj =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + dxgsyncobject_destroy(process, syncobj); + + ret =3D dxgvmb_send_destroy_sync_object(process, args.sync_object); + +cleanup: + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + /* * IOCTL processing * The driver IOCTLs return @@ -1436,6 +1562,8 @@ void init_ioctls(void) LX_DXCREATEALLOCATION); SET_IOCTL(/*0x9 */ dxgk_query_adapter_info, LX_DXQUERYADAPTERINFO); + SET_IOCTL(/*0x10 */ dxgk_create_sync_object, + LX_DXCREATESYNCHRONIZATIONOBJECT); SET_IOCTL(/*0x13 */ dxgk_destroy_allocation, LX_DXDESTROYALLOCATION2); SET_IOCTL(/*0x14 */ dxgk_enum_adapters, @@ -1444,6 +1572,8 @@ void init_ioctls(void) LX_DXCLOSEADAPTER); SET_IOCTL(/*0x19 */ dxgk_destroy_device, LX_DXDESTROYDEVICE); + SET_IOCTL(/*0x1d */ dxgk_destroy_sync_object, + LX_DXDESTROYSYNCHRONIZATIONOBJECT); SET_IOCTL(/*0x3e */ dxgk_enum_adapters3, LX_DXENUMADAPTERS3); } --=20 2.35.1 From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 0E4D5C433EF for ; Sat, 5 Feb 2022 02:34:56 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1379106AbiBECez (ORCPT ); Fri, 4 Feb 2022 21:34:55 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45108 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1379005AbiBECeY (ORCPT ); Fri, 4 Feb 2022 21:34:24 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id AF7F020B83C9; Fri, 4 Feb 2022 18:34:24 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com AF7F020B83C9 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028464; bh=2oUmMaHhkHiKYGn2uHocRmboLCEPkgzCc3igeH+cB3k=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=snyy0JyS9aixPmvEsodPVfcfVtTw7KXBkuKOyiRkKsYQN6+43XRdRRNCOdSkz23uY Z+CNjhYHQ3bU42asPD+4Ds5R9Ln88m2mUUOd3k20oK4y/BUQ6ZqQBfbee7wPBA343k 61nbeQ21DazdGoq5e1f3qA9qjQWSq9ih1G2fGJro= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 08/24] drivers: hv: dxgkrnl: Operations using GPU sync objects Date: Fri, 4 Feb 2022 18:34:06 -0800 Message-Id: <1612eed53a63f4ee1576e23e82616114e6f6625c.1644025661.git.iourit@linux.microsoft.com> X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Implement ioctls to submit operations with GPU sync objects: LX_DXSIGNALSYNCHRONIZATIONOBJECT(D3DKMTSignalSynchronizationObject), LX_DXWAITFORSYNCHRONIZATIONOBJECT(D3DKMTWaitForSynchronizationObject), LX_DXSIGNALSYNCHRONIZATIONOBJECTFROMCPU(D3DKMTSignalSynchronizationObjectFr= omCpu), LX_DXSIGNALSYNCHRONIZATIONOBJECTFROMGPU(D3DKMTSignalSynchronizationObjectFr= omGpu), LX_DXSIGNALSYNCHRONIZATIONOBJECTFROMGPU2(D3DKMTSignalSynchronizationObjectF= romGpu2), LX_DXWAITFORSYNCHRONIZATIONOBJECTFROMGPU(D3DKMTWaitForSynchronizationObject= FromGpu). GPU synchronization objects are used to synchornize GPU DMA buffer execution between different execution contexts. Operation with sync objects include "signal" and "wait". The wait for a sync object is satisfied when the sync object is signaled. A signal operation could be submitted to a GPU context or could be signaled by a CPU thread. The ioctls have common implementation: - input data is read and validated - a VM bus message is sent to the host - the operation status is returned to the caller To improve performance submitting operations to the host is done asynchronously when the host supports it. Signed-off-by: Iouri Tarassov --- drivers/hv/dxgkrnl/dxgadapter.c | 25 +- drivers/hv/dxgkrnl/dxgkrnl.h | 62 +++ drivers/hv/dxgkrnl/dxgmodule.c | 97 +++++ drivers/hv/dxgkrnl/dxgvmbus.c | 213 ++++++++++ drivers/hv/dxgkrnl/ioctl.c | 693 ++++++++++++++++++++++++++++++++ drivers/hv/dxgkrnl/misc.h | 1 + 6 files changed, 1088 insertions(+), 3 deletions(-) diff --git a/drivers/hv/dxgkrnl/dxgadapter.c b/drivers/hv/dxgkrnl/dxgadapte= r.c index 2a9a731c3352..f9aa92d17d52 100644 --- a/drivers/hv/dxgkrnl/dxgadapter.c +++ b/drivers/hv/dxgkrnl/dxgadapter.c @@ -893,15 +893,19 @@ struct dxgsyncobject *dxgsyncobject_create(struct dxg= process *process, case _D3DDDI_PERIODIC_MONITORED_FENCE: syncobj->monitored_fence =3D 1; break; + case _D3DDDI_CPU_NOTIFICATION: + syncobj->cpu_event =3D 1; + syncobj->host_event =3D vzalloc(sizeof(struct dxghostevent)); + if (syncobj->host_event =3D=3D NULL) + goto cleanup; + break; default: break; } if (flags.shared) { syncobj->shared =3D 1; if (!flags.nt_security_sharing) { - dev_err(dxgglobaldev, - "%s: nt_security_sharing must be set", - __func__); + pr_err("%s: nt_security_sharing must be set", __func__); goto cleanup; } } @@ -922,6 +926,8 @@ struct dxgsyncobject *dxgsyncobject_create(struct dxgpr= ocess *process, pr_debug("%s 0x%p\n", __func__, syncobj); return syncobj; cleanup: + if (syncobj->host_event) + vfree(syncobj->host_event); if (syncobj) vfree(syncobj); return NULL; @@ -931,6 +937,7 @@ void dxgsyncobject_destroy(struct dxgprocess *process, struct dxgsyncobject *syncobj) { int destroyed; + struct dxghosteventcpu *host_event; =20 pr_debug("%s 0x%p", __func__, syncobj); =20 @@ -949,6 +956,16 @@ void dxgsyncobject_destroy(struct dxgprocess *process, } hmgrtable_unlock(&process->handle_table, DXGLOCK_EXCL); =20 + if (syncobj->cpu_event) { + host_event =3D syncobj->host_event; + if (host_event->cpu_event) { + eventfd_ctx_put(host_event->cpu_event); + if (host_event->hdr.event_id) + dxgglobal_remove_host_event( + &host_event->hdr); + host_event->cpu_event =3D NULL; + } + } if (syncobj->monitored_fence) dxgdevice_remove_syncobj(syncobj); else @@ -988,5 +1005,7 @@ void dxgsyncobject_release(struct kref *refcount) struct dxgsyncobject *syncobj; =20 syncobj =3D container_of(refcount, struct dxgsyncobject, syncobj_kref); + if (syncobj->host_event) + vfree(syncobj->host_event); vfree(syncobj); } diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index bffa7f1a21c1..ce403cc58151 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -82,6 +82,29 @@ int dxgvmbuschannel_init(struct dxgvmbuschannel *ch, str= uct hv_device *hdev); void dxgvmbuschannel_destroy(struct dxgvmbuschannel *ch); void dxgvmbuschannel_receive(void *ctx); =20 +/* + * The structure describes an event, which will be signaled by + * a message from host. + */ +enum dxghosteventtype { + dxghostevent_cpu_event =3D 1, +}; + +struct dxghostevent { + struct list_head host_event_list_entry; + u64 event_id; + enum dxghosteventtype event_type; +}; + +struct dxghosteventcpu { + struct dxghostevent hdr; + struct dxgprocess *process; + struct eventfd_ctx *cpu_event; + struct completion *completion_event; + bool destroy_after_signal; + bool remove_from_list; +}; + /* * This is GPU synchronization object, which is used to synchronize execut= ion * between GPU contextx/hardware queues or for tracking GPU execution prog= ress. @@ -111,6 +134,8 @@ struct dxgsyncobject { */ struct dxgdevice *device; struct dxgprocess *process; + /* Used by D3DDDI_CPU_NOTIFICATION objects */ + struct dxghosteventcpu *host_event; /* CPU virtual address of the fence value for "device" syncobjects */ void *mapped_address; /* Handle in the process handle table */ @@ -125,6 +150,7 @@ struct dxgsyncobject { u32 stopped:1; /* device syncobject */ u32 monitored_fence:1; + u32 cpu_event:1; u32 shared:1; u32 reserved:27; }; @@ -191,6 +217,11 @@ struct dxgglobal { /* protects the dxgprocess_adapter lists */ struct mutex process_adapter_mutex; =20 + /* list of events, waiting to be signaled by the host */ + struct list_head host_event_list_head; + spinlock_t host_event_list_mutex; + atomic64_t host_event_id; + bool dxg_dev_initialized; bool vmbus_registered; bool pci_registered; @@ -210,6 +241,11 @@ struct vmbus_channel *dxgglobal_get_vmbus(void); struct dxgvmbuschannel *dxgglobal_get_dxgvmbuschannel(void); void dxgglobal_acquire_process_adapter_lock(void); void dxgglobal_release_process_adapter_lock(void); +void dxgglobal_add_host_event(struct dxghostevent *hostevent); +void dxgglobal_remove_host_event(struct dxghostevent *hostevent); +u64 dxgglobal_new_host_event_id(void); +void dxgglobal_signal_host_event(u64 event_id); +struct dxghostevent *dxgglobal_get_host_event(u64 event_id); int dxgglobal_acquire_channel_lock(void); void dxgglobal_release_channel_lock(void); =20 @@ -568,6 +604,31 @@ int dxgvmb_send_create_sync_object(struct dxgprocess *= pr, *args, struct dxgsyncobject *so); int dxgvmb_send_destroy_sync_object(struct dxgprocess *pr, struct d3dkmthandle h); +int dxgvmb_send_signal_sync_object(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dddicb_signalflags flags, + u64 legacy_fence_value, + struct d3dkmthandle context, + u32 object_count, + struct d3dkmthandle *object, + u32 context_count, + struct d3dkmthandle *contexts, + u32 fence_count, u64 *fences, + struct eventfd_ctx *cpu_event, + struct d3dkmthandle device); +int dxgvmb_send_wait_sync_object_gpu(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmthandle context, + u32 object_count, + struct d3dkmthandle *objects, + u64 *fences, + bool legacy_fence); +int dxgvmb_send_wait_sync_object_cpu(struct dxgprocess *process, + struct dxgadapter *adapter, + struct + d3dkmt_waitforsynchronizationobjectfromcpu + *args, + u64 cpu_event); int dxgvmb_send_query_adapter_info(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_queryadapterinfo *args); @@ -583,6 +644,7 @@ int dxgvmb_send_async_msg(struct dxgvmbuschannel *chann= el, void *command, u32 cmd_size); =20 +void signal_host_cpu_event(struct dxghostevent *eventhdr); int ntstatus2int(struct ntstatus status); =20 #endif diff --git a/drivers/hv/dxgkrnl/dxgmodule.c b/drivers/hv/dxgkrnl/dxgmodule.c index 9d339f15a4b7..1815df8e45fe 100644 --- a/drivers/hv/dxgkrnl/dxgmodule.c +++ b/drivers/hv/dxgkrnl/dxgmodule.c @@ -124,6 +124,98 @@ static struct dxgadapter *find_adapter(struct winluid = *luid) return adapter; } =20 +void dxgglobal_add_host_event(struct dxghostevent *event) +{ + spin_lock_irq(&dxgglobal->host_event_list_mutex); + list_add_tail(&event->host_event_list_entry, + &dxgglobal->host_event_list_head); + spin_unlock_irq(&dxgglobal->host_event_list_mutex); +} + +void dxgglobal_remove_host_event(struct dxghostevent *event) +{ + spin_lock_irq(&dxgglobal->host_event_list_mutex); + if (event->host_event_list_entry.next !=3D NULL) { + list_del(&event->host_event_list_entry); + event->host_event_list_entry.next =3D NULL; + } + spin_unlock_irq(&dxgglobal->host_event_list_mutex); +} + +void signal_host_cpu_event(struct dxghostevent *eventhdr) +{ + struct dxghosteventcpu *event =3D (struct dxghosteventcpu *)eventhdr; + + if (event->remove_from_list || + event->destroy_after_signal) { + list_del(&eventhdr->host_event_list_entry); + eventhdr->host_event_list_entry.next =3D NULL; + } + if (event->cpu_event) { + pr_debug("signal cpu event\n"); + eventfd_signal(event->cpu_event, 1); + if (event->destroy_after_signal) + eventfd_ctx_put(event->cpu_event); + } else { + pr_debug("signal completion\n"); + complete(event->completion_event); + } + if (event->destroy_after_signal) { + pr_debug("destroying event %p\n", + event); + vfree(event); + } +} + +void dxgglobal_signal_host_event(u64 event_id) +{ + struct dxghostevent *event; + unsigned long flags; + + pr_debug("%s %lld\n", __func__, event_id); + + spin_lock_irqsave(&dxgglobal->host_event_list_mutex, flags); + list_for_each_entry(event, &dxgglobal->host_event_list_head, + host_event_list_entry) { + if (event->event_id =3D=3D event_id) { + pr_debug("found event to signal %lld\n", + event_id); + if (event->event_type =3D=3D dxghostevent_cpu_event) + signal_host_cpu_event(event); + else + pr_err("Unknown host event type"); + break; + } + } + spin_unlock_irqrestore(&dxgglobal->host_event_list_mutex, flags); + pr_debug("dxgglobal_signal_host_event_end %lld\n", + event_id); +} + +struct dxghostevent *dxgglobal_get_host_event(u64 event_id) +{ + struct dxghostevent *entry; + struct dxghostevent *event =3D NULL; + + spin_lock_irq(&dxgglobal->host_event_list_mutex); + list_for_each_entry(entry, &dxgglobal->host_event_list_head, + host_event_list_entry) { + if (entry->event_id =3D=3D event_id) { + list_del(&entry->host_event_list_entry); + entry->host_event_list_entry.next =3D NULL; + event =3D entry; + break; + } + } + spin_unlock_irq(&dxgglobal->host_event_list_mutex); + return event; +} + +u64 dxgglobal_new_host_event_id(void) +{ + return atomic64_inc_return(&dxgglobal->host_event_id); +} + void dxgglobal_acquire_process_adapter_lock(void) { mutex_lock(&dxgglobal->process_adapter_mutex); @@ -745,6 +837,11 @@ static int dxgglobal_create(void) =20 init_rwsem(&dxgglobal->channel_lock); =20 + INIT_LIST_HEAD(&dxgglobal->host_event_list_head); + spin_lock_init(&dxgglobal->host_event_list_mutex); + atomic64_set(&dxgglobal->host_event_id, 1); + + pr_debug("dxgglobal_init end\n"); pr_debug("dxgglobal_init end\n"); return ret; } diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index 2cc49283c090..6d81069e4a9a 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -275,6 +275,22 @@ static void command_vm_to_host_init1(struct dxgkvmb_co= mmand_vm_to_host *command, command->channel_type =3D DXGKVMB_VM_TO_HOST; } =20 +static void signal_guest_event(struct dxgkvmb_command_host_to_vm *packet, + u32 packet_length) +{ + struct dxgkvmb_command_signalguestevent *command =3D (void *)packet; + + if (packet_length < sizeof(struct dxgkvmb_command_signalguestevent)) { + pr_err("invalid packet size"); + return; + } + if (command->event =3D=3D 0) { + pr_err("invalid event pointer"); + return; + } + dxgglobal_signal_host_event(command->event); +} + static void process_inband_packet(struct dxgvmbuschannel *channel, struct vmpacket_descriptor *desc) { @@ -291,6 +307,7 @@ static void process_inband_packet(struct dxgvmbuschanne= l *channel, switch (packet->command_type) { case DXGK_VMBCOMMAND_SIGNALGUESTEVENT: case DXGK_VMBCOMMAND_SIGNALGUESTEVENTPASSIVE: + signal_guest_event(packet, packet_length); break; case DXGK_VMBCOMMAND_SENDWNFNOTIFICATION: break; @@ -1653,6 +1670,202 @@ dxgvmb_send_create_sync_object(struct dxgprocess *p= rocess, return ret; } =20 +int dxgvmb_send_signal_sync_object(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dddicb_signalflags flags, + u64 legacy_fence_value, + struct d3dkmthandle context, + u32 object_count, + struct d3dkmthandle __user *objects, + u32 context_count, + struct d3dkmthandle __user *contexts, + u32 fence_count, + u64 __user *fences, + struct eventfd_ctx *cpu_event_handle, + struct d3dkmthandle device) +{ + int ret; + struct dxgkvmb_command_signalsyncobject *command; + u32 object_size =3D object_count * sizeof(struct d3dkmthandle); + u32 context_size =3D context_count * sizeof(struct d3dkmthandle); + u32 fence_size =3D fences ? fence_count * sizeof(u64) : 0; + u8 *current_pos; + u32 cmd_size =3D sizeof(struct dxgkvmb_command_signalsyncobject) + + object_size + context_size + fence_size; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + if (context.v) + cmd_size +=3D sizeof(struct d3dkmthandle); + + ret =3D init_message(&msg, adapter, process, cmd_size); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_SIGNALSYNCOBJECT, + process->host_handle); + + if (flags.enqueue_cpu_event) + command->cpu_event_handle =3D (u64) cpu_event_handle; + else + command->device =3D device; + command->flags =3D flags; + command->fence_value =3D legacy_fence_value; + command->object_count =3D object_count; + command->context_count =3D context_count; + current_pos =3D (u8 *) &command[1]; + ret =3D copy_from_user(current_pos, objects, object_size); + if (ret) { + pr_err("Failed to read objects %p %d", + objects, object_size); + ret =3D -EINVAL; + goto cleanup; + } + current_pos +=3D object_size; + if (context.v) { + command->context_count++; + *(struct d3dkmthandle *) current_pos =3D context; + current_pos +=3D sizeof(struct d3dkmthandle); + } + if (context_size) { + ret =3D copy_from_user(current_pos, contexts, context_size); + if (ret) { + pr_err("Failed to read contexts %p %d", + contexts, context_size); + ret =3D -EINVAL; + goto cleanup; + } + current_pos +=3D context_size; + } + if (fence_size) { + ret =3D copy_from_user(current_pos, fences, fence_size); + if (ret) { + pr_err("Failed to read fences %p %d", + fences, fence_size); + ret =3D -EINVAL; + goto cleanup; + } + } + + if (dxgglobal->async_msg_enabled) { + command->hdr.async_msg =3D 1; + ret =3D dxgvmb_send_async_msg(msg.channel, msg.hdr, msg.size); + } else { + ret =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, + msg.size); + } + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +int dxgvmb_send_wait_sync_object_cpu(struct dxgprocess *process, + struct dxgadapter *adapter, + struct + d3dkmt_waitforsynchronizationobjectfromcpu + *args, + u64 cpu_event) +{ + int ret =3D -EINVAL; + struct dxgkvmb_command_waitforsyncobjectfromcpu *command; + u32 object_size =3D args->object_count * sizeof(struct d3dkmthandle); + u32 fence_size =3D args->object_count * sizeof(u64); + u8 *current_pos; + u32 cmd_size =3D sizeof(*command) + object_size + fence_size; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, adapter, process, cmd_size); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_WAITFORSYNCOBJECTFROMCPU, + process->host_handle); + command->device =3D args->device; + command->flags =3D args->flags; + command->object_count =3D args->object_count; + command->guest_event_pointer =3D (u64) cpu_event; + current_pos =3D (u8 *) &command[1]; + ret =3D copy_from_user(current_pos, args->objects, object_size); + if (ret) { + pr_err("%s failed to copy objects", __func__); + ret =3D -EINVAL; + goto cleanup; + } + current_pos +=3D object_size; + ret =3D copy_from_user(current_pos, args->fence_values, fence_size); + if (ret) { + pr_err("%s failed to copy fences", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, msg.size); + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +int dxgvmb_send_wait_sync_object_gpu(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmthandle context, + u32 object_count, + struct d3dkmthandle *objects, + u64 *fences, + bool legacy_fence) +{ + int ret; + struct dxgkvmb_command_waitforsyncobjectfromgpu *command; + u32 fence_size =3D object_count * sizeof(u64); + u32 object_size =3D object_count * sizeof(struct d3dkmthandle); + u8 *current_pos; + u32 cmd_size =3D object_size + fence_size - sizeof(u64) + + sizeof(struct dxgkvmb_command_waitforsyncobjectfromgpu); + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + if (object_count =3D=3D 0 || object_count > D3DDDI_MAX_OBJECT_WAITED_ON) { + ret =3D -EINVAL; + goto cleanup; + } + ret =3D init_message(&msg, adapter, process, cmd_size); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_WAITFORSYNCOBJECTFROMGPU, + process->host_handle); + command->context =3D context; + command->object_count =3D object_count; + command->legacy_fence_object =3D legacy_fence; + current_pos =3D (u8 *) command->fence_values; + memcpy(current_pos, fences, fence_size); + current_pos +=3D fence_size; + memcpy(current_pos, objects, object_size); + + if (dxgglobal->async_msg_enabled) { + command->hdr.async_msg =3D 1; + ret =3D dxgvmb_send_async_msg(msg.channel, msg.hdr, msg.size); + } else { + ret =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, + msg.size); + } + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + int dxgvmb_send_query_adapter_info(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_queryadapterinfo *args) diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index bc1ac2dd302f..b945da0da55a 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -1375,8 +1375,10 @@ dxgk_create_sync_object(struct dxgprocess *process, = void *__user inargs) struct d3dkmt_createsynchronizationobject2 args; struct dxgdevice *device =3D NULL; struct dxgadapter *adapter =3D NULL; + struct eventfd_ctx *event =3D NULL; struct dxgsyncobject *syncobj =3D NULL; bool device_lock_acquired =3D false; + struct dxghosteventcpu *host_event =3D NULL; =20 ret =3D copy_from_user(&args, inargs, sizeof(args)); if (ret) { @@ -1411,6 +1413,27 @@ dxgk_create_sync_object(struct dxgprocess *process, = void *__user inargs) goto cleanup; } =20 + if (args.info.type =3D=3D _D3DDDI_CPU_NOTIFICATION) { + event =3D eventfd_ctx_fdget((int) + args.info.cpu_notification.event); + if (IS_ERR(event)) { + pr_err("failed to reference the event"); + event =3D NULL; + ret =3D -EINVAL; + goto cleanup; + } + host_event =3D syncobj->host_event; + host_event->hdr.event_id =3D dxgglobal_new_host_event_id(); + host_event->cpu_event =3D event; + host_event->remove_from_list =3D false; + host_event->destroy_after_signal =3D false; + host_event->hdr.event_type =3D dxghostevent_cpu_event; + dxgglobal_add_host_event(&host_event->hdr); + args.info.cpu_notification.event =3D host_event->hdr.event_id; + pr_debug("creating CPU notification event: %lld", + args.info.cpu_notification.event); + } + ret =3D dxgvmb_send_create_sync_object(process, adapter, &args, syncobj); if (ret < 0) goto cleanup; @@ -1438,7 +1461,10 @@ dxgk_create_sync_object(struct dxgprocess *process, = void *__user inargs) if (args.sync_object.v) dxgvmb_send_destroy_sync_object(process, args.sync_object); + event =3D NULL; } + if (event) + eventfd_ctx_put(event); } if (adapter) dxgadapter_release_lock_shared(adapter); @@ -1494,6 +1520,659 @@ dxgk_destroy_sync_object(struct dxgprocess *process= , void *__user inargs) return ret; } =20 +static int +dxgk_signal_sync_object(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmt_signalsynchronizationobject2 args; + struct d3dkmt_signalsynchronizationobject2 *__user in_args =3D inargs; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + int ret; + u32 fence_count =3D 1; + struct eventfd_ctx *event =3D NULL; + struct dxghosteventcpu *host_event =3D NULL; + bool host_event_added =3D false; + u64 host_event_id =3D 0; + + pr_debug("ioctl: %s", __func__); + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.context_count >=3D D3DDDI_MAX_BROADCAST_CONTEXT || + args.object_count > D3DDDI_MAX_OBJECT_SIGNALED) { + ret =3D -EINVAL; + goto cleanup; + } + + if (args.flags.enqueue_cpu_event) { + host_event =3D vzalloc(sizeof(*host_event)); + if (host_event =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + host_event->process =3D process; + event =3D eventfd_ctx_fdget((int)args.cpu_event_handle); + if (IS_ERR(event)) { + pr_err("failed to reference the event"); + event =3D NULL; + ret =3D -EINVAL; + goto cleanup; + } + fence_count =3D 0; + host_event->cpu_event =3D event; + host_event_id =3D dxgglobal_new_host_event_id(); + host_event->hdr.event_type =3D dxghostevent_cpu_event; + host_event->hdr.event_id =3D host_event_id; + host_event->remove_from_list =3D true; + host_event->destroy_after_signal =3D true; + dxgglobal_add_host_event(&host_event->hdr); + host_event_added =3D true; + } + + device =3D dxgprocess_device_by_object_handle(process, + HMGRENTRY_TYPE_DXGCONTEXT, + args.context); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_signal_sync_object(process, adapter, + args.flags, args.fence.fence_value, + args.context, args.object_count, + in_args->object_array, + args.context_count, + in_args->contexts, fence_count, + NULL, (void *)host_event_id, + zerohandle); + + /* + * When the send operation succeeds, the host event will be destroyed + * after signal from the host + */ + +cleanup: + + if (ret < 0) { + if (host_event_added) { + /* The event might be signaled and destroyed by host */ + host_event =3D (struct dxghosteventcpu *) + dxgglobal_get_host_event(host_event_id); + if (host_event) { + eventfd_ctx_put(event); + event =3D NULL; + vfree(host_event); + host_event =3D NULL; + } + } + if (event) + eventfd_ctx_put(event); + if (host_event) + vfree(host_event); + } + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_signal_sync_object_cpu(struct dxgprocess *process, void *__user inarg= s) +{ + struct d3dkmt_signalsynchronizationobjectfromcpu args; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + int ret; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + if (args.object_count =3D=3D 0 || + args.object_count > D3DDDI_MAX_OBJECT_SIGNALED) { + pr_debug("Too many objects: %d", + args.object_count); + ret =3D -EINVAL; + goto cleanup; + } + + device =3D dxgprocess_device_by_handle(process, args.device); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_signal_sync_object(process, adapter, + args.flags, 0, zerohandle, + args.object_count, args.objects, 0, + NULL, args.object_count, + args.fence_values, NULL, + args.device); + +cleanup: + + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_signal_sync_object_gpu(struct dxgprocess *process, void *__user inarg= s) +{ + struct d3dkmt_signalsynchronizationobjectfromgpu args; + struct d3dkmt_signalsynchronizationobjectfromgpu *__user user_args =3D + inargs; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + struct d3dddicb_signalflags flags =3D { }; + int ret; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.object_count =3D=3D 0 || + args.object_count > DXG_MAX_VM_BUS_PACKET_SIZE) { + ret =3D -EINVAL; + goto cleanup; + } + + device =3D dxgprocess_device_by_object_handle(process, + HMGRENTRY_TYPE_DXGCONTEXT, + args.context); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_signal_sync_object(process, adapter, + flags, 0, zerohandle, + args.object_count, + args.objects, 1, + &user_args->context, + args.object_count, + args.monitored_fence_values, NULL, + zerohandle); + +cleanup: + + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_signal_sync_object_gpu2(struct dxgprocess *process, void *__user inar= gs) +{ + struct d3dkmt_signalsynchronizationobjectfromgpu2 args; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + struct d3dkmthandle context_handle; + struct eventfd_ctx *event =3D NULL; + u64 *fences =3D NULL; + u32 fence_count =3D 0; + int ret; + struct dxghosteventcpu *host_event =3D NULL; + bool host_event_added =3D false; + u64 host_event_id =3D 0; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.flags.enqueue_cpu_event) { + if (args.object_count !=3D 0 || args.cpu_event_handle =3D=3D 0) { + pr_err("Bad input for EnqueueCpuEvent: %d %lld", + args.object_count, args.cpu_event_handle); + ret =3D -EINVAL; + goto cleanup; + } + } else if (args.object_count =3D=3D 0 || + args.object_count > DXG_MAX_VM_BUS_PACKET_SIZE || + args.context_count =3D=3D 0 || + args.context_count > DXG_MAX_VM_BUS_PACKET_SIZE) { + pr_err("Invalid input: %d %d", + args.object_count, args.context_count); + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D copy_from_user(&context_handle, args.contexts, + sizeof(struct d3dkmthandle)); + if (ret) { + pr_err("%s failed to copy context handle", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.flags.enqueue_cpu_event) { + host_event =3D vzalloc(sizeof(*host_event)); + if (host_event =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + host_event->process =3D process; + event =3D eventfd_ctx_fdget((int)args.cpu_event_handle); + if (IS_ERR(event)) { + pr_err("failed to reference the event"); + event =3D NULL; + ret =3D -EINVAL; + goto cleanup; + } + fence_count =3D 0; + host_event->cpu_event =3D event; + host_event_id =3D dxgglobal_new_host_event_id(); + host_event->hdr.event_id =3D host_event_id; + host_event->hdr.event_type =3D dxghostevent_cpu_event; + host_event->remove_from_list =3D true; + host_event->destroy_after_signal =3D true; + dxgglobal_add_host_event(&host_event->hdr); + host_event_added =3D true; + } else { + fences =3D args.monitored_fence_values; + fence_count =3D args.object_count; + } + + device =3D dxgprocess_device_by_object_handle(process, + HMGRENTRY_TYPE_DXGCONTEXT, + context_handle); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_signal_sync_object(process, adapter, + args.flags, 0, zerohandle, + args.object_count, args.objects, + args.context_count, args.contexts, + fence_count, fences, + (void *)host_event_id, zerohandle); + +cleanup: + + if (ret < 0) { + if (host_event_added) { + /* The event might be signaled and destroyed by host */ + host_event =3D (struct dxghosteventcpu *) + dxgglobal_get_host_event(host_event_id); + if (host_event) { + eventfd_ctx_put(event); + event =3D NULL; + vfree(host_event); + host_event =3D NULL; + } + } + if (event) + eventfd_ctx_put(event); + if (host_event) + vfree(host_event); + } + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_wait_sync_object(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmt_waitforsynchronizationobject2 args; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + int ret; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.object_count > D3DDDI_MAX_OBJECT_WAITED_ON || + args.object_count =3D=3D 0) { + ret =3D -EINVAL; + goto cleanup; + } + + device =3D dxgprocess_device_by_object_handle(process, + HMGRENTRY_TYPE_DXGCONTEXT, + args.context); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + pr_debug("Fence value: %lld", args.fence.fence_value); + ret =3D dxgvmb_send_wait_sync_object_gpu(process, adapter, + args.context, args.object_count, + args.object_array, + &args.fence.fence_value, true); + +cleanup: + + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_wait_sync_object_cpu(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmt_waitforsynchronizationobjectfromcpu args; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + struct eventfd_ctx *event =3D NULL; + struct dxghosteventcpu host_event =3D { }; + struct dxghosteventcpu *async_host_event =3D NULL; + struct completion local_event =3D { }; + u64 event_id =3D 0; + int ret; + bool host_event_added =3D false; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.object_count > DXG_MAX_VM_BUS_PACKET_SIZE || + args.object_count =3D=3D 0) { + ret =3D -EINVAL; + goto cleanup; + } + + if (args.async_event) { + async_host_event =3D vzalloc(sizeof(*async_host_event)); + if (async_host_event =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + async_host_event->process =3D process; + event =3D eventfd_ctx_fdget((int)args.async_event); + if (IS_ERR(event)) { + pr_err("failed to reference the event"); + event =3D NULL; + ret =3D -EINVAL; + goto cleanup; + } + async_host_event->cpu_event =3D event; + async_host_event->hdr.event_id =3D dxgglobal_new_host_event_id(); + async_host_event->destroy_after_signal =3D true; + async_host_event->hdr.event_type =3D dxghostevent_cpu_event; + dxgglobal_add_host_event(&async_host_event->hdr); + event_id =3D async_host_event->hdr.event_id; + host_event_added =3D true; + } else { + init_completion(&local_event); + host_event.completion_event =3D &local_event; + host_event.hdr.event_id =3D dxgglobal_new_host_event_id(); + host_event.hdr.event_type =3D dxghostevent_cpu_event; + dxgglobal_add_host_event(&host_event.hdr); + event_id =3D host_event.hdr.event_id; + } + + device =3D dxgprocess_device_by_handle(process, args.device); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_wait_sync_object_cpu(process, adapter, + &args, event_id); + if (ret < 0) + goto cleanup; + + if (args.async_event =3D=3D 0) { + dxgadapter_release_lock_shared(adapter); + adapter =3D NULL; + ret =3D wait_for_completion_interruptible(&local_event); + if (ret) { + pr_err("%s: wait_completion_interruptible failed: %d", + __func__, ret); + ret =3D -ERESTARTSYS; + } + } + +cleanup: + + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + if (host_event.hdr.event_id) + dxgglobal_remove_host_event(&host_event.hdr); + if (ret < 0) { + if (host_event_added) { + async_host_event =3D (struct dxghosteventcpu *) + dxgglobal_get_host_event(event_id); + if (async_host_event) { + if (async_host_event->hdr.event_type =3D=3D + dxghostevent_cpu_event) { + eventfd_ctx_put(event); + event =3D NULL; + vfree(async_host_event); + async_host_event =3D NULL; + } else { + pr_err("Invalid event type"); + DXGKRNL_ASSERT(0); + } + } + } + if (event) + eventfd_ctx_put(event); + if (async_host_event) + vfree(async_host_event); + } + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_wait_sync_object_gpu(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmt_waitforsynchronizationobjectfromgpu args; + struct dxgcontext *context =3D NULL; + struct d3dkmthandle device_handle =3D {}; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + struct dxgsyncobject *syncobj =3D NULL; + struct d3dkmthandle *objects =3D NULL; + u32 object_size; + u64 *fences =3D NULL; + int ret; + enum hmgrentry_type syncobj_type =3D HMGRENTRY_TYPE_FREE; + bool monitored_fence =3D false; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.object_count > DXG_MAX_VM_BUS_PACKET_SIZE || + args.object_count =3D=3D 0) { + pr_err("Invalid object count: %d", args.object_count); + ret =3D -EINVAL; + goto cleanup; + } + + object_size =3D sizeof(struct d3dkmthandle) * args.object_count; + objects =3D vzalloc(object_size); + if (objects =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + ret =3D copy_from_user(objects, args.objects, object_size); + if (ret) { + pr_err("%s failed to copy objects", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + hmgrtable_lock(&process->handle_table, DXGLOCK_SHARED); + context =3D hmgrtable_get_object_by_type(&process->handle_table, + HMGRENTRY_TYPE_DXGCONTEXT, + args.context); + if (context) { + device_handle =3D context->device_handle; + syncobj_type =3D + hmgrtable_get_object_type(&process->handle_table, + objects[0]); + } + if (device_handle.v =3D=3D 0) { + pr_err("Invalid context handle: %x", args.context.v); + ret =3D -EINVAL; + } else { + if (syncobj_type =3D=3D HMGRENTRY_TYPE_MONITOREDFENCE) { + monitored_fence =3D true; + } else if (syncobj_type =3D=3D HMGRENTRY_TYPE_DXGSYNCOBJECT) { + syncobj =3D + hmgrtable_get_object_by_type(&process->handle_table, + HMGRENTRY_TYPE_DXGSYNCOBJECT, + objects[0]); + if (syncobj =3D=3D NULL) { + pr_err("Invalid syncobj: %x", objects[0].v); + ret =3D -EINVAL; + } else { + monitored_fence =3D syncobj->monitored_fence; + } + } else { + pr_err("Invalid syncobj type: %x", objects[0].v); + ret =3D -EINVAL; + } + } + hmgrtable_unlock(&process->handle_table, DXGLOCK_SHARED); + + if (ret < 0) + goto cleanup; + + if (monitored_fence) { + object_size =3D sizeof(u64) * args.object_count; + fences =3D vzalloc(object_size); + if (fences =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + ret =3D copy_from_user(fences, args.monitored_fence_values, + object_size); + if (ret) { + pr_err("%s failed to copy fences", __func__); + ret =3D -EINVAL; + goto cleanup; + } + } else { + fences =3D &args.fence_value; + } + + device =3D dxgprocess_device_by_handle(process, device_handle); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_wait_sync_object_gpu(process, adapter, + args.context, args.object_count, + objects, fences, + !monitored_fence); + +cleanup: + + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + if (objects) + vfree(objects); + if (fences && fences !=3D &args.fence_value) + vfree(fences); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + /* * IOCTL processing * The driver IOCTLs return @@ -1564,6 +2243,10 @@ void init_ioctls(void) LX_DXQUERYADAPTERINFO); SET_IOCTL(/*0x10 */ dxgk_create_sync_object, LX_DXCREATESYNCHRONIZATIONOBJECT); + SET_IOCTL(/*0x11 */ dxgk_signal_sync_object, + LX_DXSIGNALSYNCHRONIZATIONOBJECT); + SET_IOCTL(/*0x12 */ dxgk_wait_sync_object, + LX_DXWAITFORSYNCHRONIZATIONOBJECT); SET_IOCTL(/*0x13 */ dxgk_destroy_allocation, LX_DXDESTROYALLOCATION2); SET_IOCTL(/*0x14 */ dxgk_enum_adapters, @@ -1574,6 +2257,16 @@ void init_ioctls(void) LX_DXDESTROYDEVICE); SET_IOCTL(/*0x1d */ dxgk_destroy_sync_object, LX_DXDESTROYSYNCHRONIZATIONOBJECT); + SET_IOCTL(/*0x31 */ dxgk_signal_sync_object_cpu, + LX_DXSIGNALSYNCHRONIZATIONOBJECTFROMCPU); + SET_IOCTL(/*0x32 */ dxgk_signal_sync_object_gpu, + LX_DXSIGNALSYNCHRONIZATIONOBJECTFROMGPU); + SET_IOCTL(/*0x33 */ dxgk_signal_sync_object_gpu2, + LX_DXSIGNALSYNCHRONIZATIONOBJECTFROMGPU2); + SET_IOCTL(/*0x3a */ dxgk_wait_sync_object_cpu, + LX_DXWAITFORSYNCHRONIZATIONOBJECTFROMCPU); + SET_IOCTL(/*0x3b */ dxgk_wait_sync_object_gpu, + LX_DXWAITFORSYNCHRONIZATIONOBJECTFROMGPU); SET_IOCTL(/*0x3e */ dxgk_enum_adapters3, LX_DXENUMADAPTERS3); } diff --git a/drivers/hv/dxgkrnl/misc.h b/drivers/hv/dxgkrnl/misc.h index 41abdc504bc2..f56d21b48814 100644 --- a/drivers/hv/dxgkrnl/misc.h +++ b/drivers/hv/dxgkrnl/misc.h @@ -26,6 +26,7 @@ extern const struct d3dkmthandle zerohandle; * When a lower lock ois held, the higher lock should not be acquired. * * device_list_mutex + * host_event_list_mutex * channel_lock * fd_mutex * plistmutex --=20 2.35.1 From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 9916CC433F5 for ; Sat, 5 Feb 2022 02:34:58 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1379154AbiBECe6 (ORCPT ); Fri, 4 Feb 2022 21:34:58 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45114 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1379007AbiBECeZ (ORCPT ); Fri, 4 Feb 2022 21:34:25 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id E24BF20B83F2; Fri, 4 Feb 2022 18:34:24 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com E24BF20B83F2 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028465; bh=tz+qTzrumeIyc+TN4zKInmKvJDSXllu3mN/sBcNbrMY=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=r9udJGl+CCwYqvHsc54yVl7fX1Ki6F9/Fdo9issG2PUMvu6n0AsoKg4Upjq/rBOAV A4A27RuAOcKJh7ogxDJpoGcmY1abx/RqlP8iPk8Z2T31kNdXP17uC8hQuiKpQ/WpWG TUkDKgpIixSRpOjHZNJI9sCJu9US1w85cEfBB9JI= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 09/24] drivers: hv: dxgkrnl: Sharing of dxgresource objects Date: Fri, 4 Feb 2022 18:34:07 -0800 Message-Id: <1c02879d1a3bdf8d5c8b568d722366a26a283128.1644025661.git.iourit@linux.microsoft.com> X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Implement creation of shared resource and IOCTLs for sharing dxgresource objects between processes in the virtual machine. A dxgresource object is a collection of dxgallocation objects. The WDDM API allows addition/removal allocations to a resource, but has limitations on addition/removal of allocations to a shared resource. When a resource is "sealed", addition/removal of allocations is not allowed. Resources are shared using FD (file descriptor) handles. The name "NT handle" is used to be compatible with Windows implementation. An FD handle is created by the LX_DXSHAREOBJECTS ioctl. The given FD handle could be sent to another process using any Linux API. To use a shared resource object in WDDM API calls, the object needs to be opened using its FD handle. An resource object is opened by the following ioctl: LX_DXOPENRESOURCEFROMNTHANDLE. The LX_DXQUERYRESOURCEINFOFROMNTHANDLE ioctl is used to query private driver data of a shared resource object. This private data needs to be used to actually open the object using LX_DXOPENRESOURCEFROMNTHANDLE. Signed-off-by: Iouri Tarassov --- drivers/hv/dxgkrnl/dxgadapter.c | 81 ++++ drivers/hv/dxgkrnl/dxgkrnl.h | 77 ++++ drivers/hv/dxgkrnl/dxgmodule.c | 1 + drivers/hv/dxgkrnl/dxgvmbus.c | 127 ++++++ drivers/hv/dxgkrnl/ioctl.c | 786 ++++++++++++++++++++++++++++++++ 5 files changed, 1072 insertions(+) diff --git a/drivers/hv/dxgkrnl/dxgadapter.c b/drivers/hv/dxgkrnl/dxgadapte= r.c index f9aa92d17d52..1b8f2b63eb6d 100644 --- a/drivers/hv/dxgkrnl/dxgadapter.c +++ b/drivers/hv/dxgkrnl/dxgadapter.c @@ -165,6 +165,17 @@ void dxgadapter_remove_process(struct dxgprocess_adapt= er *process_info) process_info->adapter_process_list_entry.prev =3D NULL; } =20 +void dxgadapter_remove_shared_resource(struct dxgadapter *adapter, + struct dxgsharedresource *object) +{ + down_write(&adapter->shared_resource_list_lock); + if (object->shared_resource_list_entry.next) { + list_del(&object->shared_resource_list_entry); + object->shared_resource_list_entry.next =3D NULL; + } + up_write(&adapter->shared_resource_list_lock); +} + void dxgadapter_add_syncobj(struct dxgadapter *adapter, struct dxgsyncobject *object) { @@ -492,6 +503,69 @@ void dxgdevice_remove_resource(struct dxgdevice *devic= e, } } =20 +struct dxgsharedresource *dxgsharedresource_create(struct dxgadapter *adap= ter) +{ + struct dxgsharedresource *resource; + + resource =3D vzalloc(sizeof(*resource)); + if (resource) { + INIT_LIST_HEAD(&resource->resource_list_head); + kref_init(&resource->sresource_kref); + mutex_init(&resource->fd_mutex); + resource->adapter =3D adapter; + } + return resource; +} + +void dxgsharedresource_destroy(struct kref *refcount) +{ + struct dxgsharedresource *resource; + + resource =3D container_of(refcount, struct dxgsharedresource, + sresource_kref); + if (resource->runtime_private_data) + vfree(resource->runtime_private_data); + if (resource->resource_private_data) + vfree(resource->resource_private_data); + if (resource->alloc_private_data_sizes) + vfree(resource->alloc_private_data_sizes); + if (resource->alloc_private_data) + vfree(resource->alloc_private_data); + vfree(resource); +} + +void dxgsharedresource_add_resource(struct dxgsharedresource *shared_resou= rce, + struct dxgresource *resource) +{ + down_write(&shared_resource->adapter->shared_resource_list_lock); + pr_debug("%s: %p %p", __func__, shared_resource, resource); + list_add_tail(&resource->shared_resource_list_entry, + &shared_resource->resource_list_head); + kref_get(&shared_resource->sresource_kref); + kref_get(&resource->resource_kref); + resource->shared_owner =3D shared_resource; + up_write(&shared_resource->adapter->shared_resource_list_lock); +} + +void dxgsharedresource_remove_resource(struct dxgsharedresource + *shared_resource, + struct dxgresource *resource) +{ + struct dxgadapter *adapter =3D shared_resource->adapter; + + down_write(&adapter->shared_resource_list_lock); + pr_debug("%s: %p %p", __func__, shared_resource, resource); + if (resource->shared_resource_list_entry.next) { + list_del(&resource->shared_resource_list_entry); + resource->shared_resource_list_entry.next =3D NULL; + kref_put(&shared_resource->sresource_kref, + dxgsharedresource_destroy); + resource->shared_owner =3D NULL; + kref_put(&resource->resource_kref, dxgresource_release); + } + up_write(&adapter->shared_resource_list_lock); +} + struct dxgresource *dxgresource_create(struct dxgdevice *device) { struct dxgresource *resource =3D vzalloc(sizeof(struct dxgresource)); @@ -534,6 +608,7 @@ void dxgresource_destroy(struct dxgresource *resource) struct d3dkmt_destroyallocation2 args =3D { }; int destroyed =3D test_and_set_bit(0, &resource->flags); struct dxgdevice *device =3D resource->device; + struct dxgsharedresource *shared_resource; =20 if (!destroyed) { dxgresource_free_handle(resource); @@ -549,6 +624,12 @@ void dxgresource_destroy(struct dxgresource *resource) dxgallocation_destroy(alloc); } dxgdevice_remove_resource(device, resource); + shared_resource =3D resource->shared_owner; + if (shared_resource) { + dxgsharedresource_remove_resource(shared_resource, + resource); + resource->shared_owner =3D NULL; + } } kref_put(&resource->resource_kref, dxgresource_release); } diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index ce403cc58151..f3ea98f0b384 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -33,6 +33,7 @@ struct dxgdevice; struct dxgcontext; struct dxgallocation; struct dxgresource; +struct dxgsharedresource; struct dxgsyncobject; =20 #include "misc.h" @@ -355,6 +356,8 @@ struct dxgadapter { struct list_head adapter_list_entry; /* The list of dxgprocess_adapter entries */ struct list_head adapter_process_list_head; + /* List of all dxgsharedresource objects */ + struct list_head shared_resource_list_head; /* List of all non-device dxgsyncobject objects */ struct list_head syncobj_list_head; /* This lock protects shared resource and syncobject lists */ @@ -388,6 +391,8 @@ void dxgadapter_remove_syncobj(struct dxgsyncobject *so= ); void dxgadapter_add_process(struct dxgadapter *adapter, struct dxgprocess_adapter *process_info); void dxgadapter_remove_process(struct dxgprocess_adapter *process_info); +void dxgadapter_remove_shared_resource(struct dxgadapter *adapter, + struct dxgsharedresource *object); =20 /* * The object represent the device object. @@ -467,6 +472,64 @@ void dxgcontext_destroy_safe(struct dxgprocess *pr, st= ruct dxgcontext *ctx); void dxgcontext_release(struct kref *refcount); bool dxgcontext_is_active(struct dxgcontext *ctx); =20 +/* + * A shared resource object is created to track the list of dxgresource ob= jects, + * which are opened for the same underlying shared resource. + * Objects are shared by using a file descriptor handle. + * FD is created by calling dxgk_share_objects and providing shandle to + * dxgsharedresource. The FD points to a dxgresource object, which is crea= ted + * by calling dxgk_open_resource_nt. dxgresource object is referenced by = the + * FD. + * + * The object is referenced by every dxgresource in its list. + * + */ +struct dxgsharedresource { + /* Every dxgresource object in the resource list takes a reference */ + struct kref sresource_kref; + struct dxgadapter *adapter; + /* List of dxgresource objects, opened for the shared resource. */ + /* Protected by dxgadapter::shared_resource_list_lock */ + struct list_head resource_list_head; + /* Entry in the list of dxgsharedresource in dxgadapter */ + /* Protected by dxgadapter::shared_resource_list_lock */ + struct list_head shared_resource_list_entry; + struct mutex fd_mutex; + /* Referenced by file descriptors */ + int host_shared_handle_nt_reference; + /* Corresponding global handle in the host */ + struct d3dkmthandle host_shared_handle; + /* + * When the sync object is shared by NT handle, this is the + * corresponding handle in the host + */ + struct d3dkmthandle host_shared_handle_nt; + /* Values below are computed when the resource is sealed */ + u32 runtime_private_data_size; + u32 alloc_private_data_size; + u32 resource_private_data_size; + u32 allocation_count; + union { + struct { + /* Cannot add new allocations */ + u32 sealed:1; + u32 reserved:31; + }; + long flags; + }; + u32 *alloc_private_data_sizes; + u8 *alloc_private_data; + u8 *runtime_private_data; + u8 *resource_private_data; +}; + +struct dxgsharedresource *dxgsharedresource_create(struct dxgadapter *adap= ter); +void dxgsharedresource_destroy(struct kref *refcount); +void dxgsharedresource_add_resource(struct dxgsharedresource *sres, + struct dxgresource *res); +void dxgsharedresource_remove_resource(struct dxgsharedresource *sres, + struct dxgresource *res); + struct dxgresource { struct kref resource_kref; enum dxgobjectstate object_state; @@ -487,6 +550,8 @@ struct dxgresource { }; long flags; }; + /* Owner of the shared resource */ + struct dxgsharedresource *shared_owner; }; =20 struct dxgresource *dxgresource_create(struct dxgdevice *dev); @@ -632,6 +697,18 @@ int dxgvmb_send_wait_sync_object_cpu(struct dxgprocess= *process, int dxgvmb_send_query_adapter_info(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_queryadapterinfo *args); +int dxgvmb_send_create_nt_shared_object(struct dxgprocess *process, + struct d3dkmthandle object, + struct d3dkmthandle *shared_handle); +int dxgvmb_send_destroy_nt_shared_object(struct d3dkmthandle shared_handle= ); +int dxgvmb_send_open_resource(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmthandle device, + struct d3dkmthandle global_share, + u32 allocation_count, + u32 total_priv_drv_data_size, + struct d3dkmthandle *resource_handle, + struct d3dkmthandle *alloc_handles); int dxgvmb_send_get_stdalloc_data(struct dxgdevice *device, enum d3dkmdt_standardallocationtype t, struct d3dkmdt_gdisurfacedata *data, diff --git a/drivers/hv/dxgkrnl/dxgmodule.c b/drivers/hv/dxgkrnl/dxgmodule.c index 1815df8e45fe..3af5a7a3ac74 100644 --- a/drivers/hv/dxgkrnl/dxgmodule.c +++ b/drivers/hv/dxgkrnl/dxgmodule.c @@ -250,6 +250,7 @@ int dxgglobal_create_adapter(struct pci_dev *dev, guid_= t *guid, init_rwsem(&adapter->core_lock); =20 INIT_LIST_HEAD(&adapter->adapter_process_list_head); + INIT_LIST_HEAD(&adapter->shared_resource_list_head); INIT_LIST_HEAD(&adapter->syncobj_list_head); init_rwsem(&adapter->shared_resource_list_lock); adapter->pci_dev =3D dev; diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index 6d81069e4a9a..af8d1aab871f 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -694,6 +694,79 @@ int dxgvmb_send_destroy_process(struct d3dkmthandle pr= ocess) return ret; } =20 +int dxgvmb_send_create_nt_shared_object(struct dxgprocess *process, + struct d3dkmthandle object, + struct d3dkmthandle *shared_handle) +{ + struct dxgkvmb_command_createntsharedobject *command; + int ret; + struct dxgvmbusmsg msg; + + ret =3D init_message(&msg, NULL, process, sizeof(*command)); + if (ret) + return ret; + command =3D (void *)msg.msg; + + command_vm_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_CREATENTSHAREDOBJECT, + process->host_handle); + command->object =3D object; + + ret =3D dxgglobal_acquire_channel_lock(); + if (ret < 0) + goto cleanup; + + ret =3D dxgvmb_send_sync_msg(dxgglobal_get_dxgvmbuschannel(), + msg.hdr, msg.size, shared_handle, + sizeof(*shared_handle)); + + dxgglobal_release_channel_lock(); + + if (ret < 0) + goto cleanup; + if (shared_handle->v =3D=3D 0) { + pr_err("failed to create NT shared object"); + ret =3D -ENOTRECOVERABLE; + } + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +int dxgvmb_send_destroy_nt_shared_object(struct d3dkmthandle shared_handle) +{ + struct dxgkvmb_command_destroyntsharedobject *command; + int ret; + struct dxgvmbusmsg msg; + + ret =3D init_message(&msg, NULL, NULL, sizeof(*command)); + if (ret) + return ret; + command =3D (void *)msg.msg; + + command_vm_to_host_init1(&command->hdr, + DXGK_VMBCOMMAND_DESTROYNTSHAREDOBJECT); + command->shared_handle =3D shared_handle; + + ret =3D dxgglobal_acquire_channel_lock(); + if (ret < 0) + goto cleanup; + + ret =3D dxgvmb_send_sync_msg_ntstatus(dxgglobal_get_dxgvmbuschannel(), + msg.hdr, msg.size); + + dxgglobal_release_channel_lock(); + +cleanup: + free_message(&msg, NULL); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + int dxgvmb_send_destroy_sync_object(struct dxgprocess *process, struct d3dkmthandle sync_object) { @@ -1499,6 +1572,60 @@ int dxgvmb_send_destroy_allocation(struct dxgprocess= *process, return ret; } =20 +int dxgvmb_send_open_resource(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmthandle device, + struct d3dkmthandle global_share, + u32 allocation_count, + u32 total_priv_drv_data_size, + struct d3dkmthandle *resource_handle, + struct d3dkmthandle *alloc_handles) +{ + struct dxgkvmb_command_openresource *command; + struct dxgkvmb_command_openresource_return *result; + struct d3dkmthandle *handles; + int ret; + int i; + u32 result_size =3D allocation_count * sizeof(struct d3dkmthandle) + + sizeof(*result); + struct dxgvmbusmsgres msg =3D {.hdr =3D NULL}; + + ret =3D init_message_res(&msg, adapter, process, sizeof(*command), + result_size); + if (ret) + goto cleanup; + command =3D msg.msg; + result =3D msg.res; + + command_vgpu_to_host_init2(&command->hdr, DXGK_VMBCOMMAND_OPENRESOURCE, + process->host_handle); + command->device =3D device; + command->nt_security_sharing =3D 1; + command->global_share =3D global_share; + command->allocation_count =3D allocation_count; + command->total_priv_drv_data_size =3D total_priv_drv_data_size; + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, + result, msg.res_size); + if (ret < 0) + goto cleanup; + + ret =3D ntstatus2int(result->status); + if (ret < 0) + goto cleanup; + + *resource_handle =3D result->resource; + handles =3D (struct d3dkmthandle *) &result[1]; + for (i =3D 0; i < allocation_count; i++) + alloc_handles[i] =3D handles[i]; + +cleanup: + free_message((struct dxgvmbusmsg *)&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + int dxgvmb_send_get_stdalloc_data(struct dxgdevice *device, enum d3dkmdt_standardallocationtype alloctype, struct d3dkmdt_gdisurfacedata *alloc_data, diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index b945da0da55a..05f59854cbbf 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -35,6 +35,33 @@ static char *errorstr(int ret) return ret < 0 ? "err" : ""; } =20 +static int dxgsharedresource_release(struct inode *inode, struct file *fil= e) +{ + struct dxgsharedresource *resource =3D file->private_data; + + pr_debug("%s: %p", __func__, resource); + mutex_lock(&resource->fd_mutex); + kref_get(&resource->sresource_kref); + resource->host_shared_handle_nt_reference--; + if (resource->host_shared_handle_nt_reference =3D=3D 0) { + if (resource->host_shared_handle_nt.v) { + dxgvmb_send_destroy_nt_shared_object( + resource->host_shared_handle_nt); + pr_debug("Resource host_handle_nt destroyed: %x", + resource->host_shared_handle_nt.v); + resource->host_shared_handle_nt.v =3D 0; + } + kref_put(&resource->sresource_kref, dxgsharedresource_destroy); + } + mutex_unlock(&resource->fd_mutex); + kref_put(&resource->sresource_kref, dxgsharedresource_destroy); + return 0; +} + +static const struct file_operations dxg_resource_fops =3D { + .release =3D dxgsharedresource_release, +}; + static int dxgk_open_adapter_from_luid(struct dxgprocess *process, void *__user inargs) { @@ -217,6 +244,97 @@ dxgkp_enum_adapters(struct dxgprocess *process, return ret; } =20 +static int dxgsharedresource_seal(struct dxgsharedresource *shared_resourc= e) +{ + int ret =3D 0; + int i =3D 0; + u8 *private_data; + u32 data_size; + struct dxgresource *resource; + struct dxgallocation *alloc; + + pr_debug("Sealing resource: %p", shared_resource); + + down_write(&shared_resource->adapter->shared_resource_list_lock); + if (shared_resource->sealed) { + pr_debug("Resource already sealed"); + goto cleanup; + } + shared_resource->sealed =3D 1; + if (!list_empty(&shared_resource->resource_list_head)) { + resource =3D + list_first_entry(&shared_resource->resource_list_head, + struct dxgresource, + shared_resource_list_entry); + pr_debug("First resource: %p", resource); + mutex_lock(&resource->resource_mutex); + list_for_each_entry(alloc, &resource->alloc_list_head, + alloc_list_entry) { + pr_debug("Resource alloc: %p %d", alloc, + alloc->priv_drv_data->data_size); + shared_resource->allocation_count++; + shared_resource->alloc_private_data_size +=3D + alloc->priv_drv_data->data_size; + if (shared_resource->alloc_private_data_size < + alloc->priv_drv_data->data_size) { + pr_err("alloc private data overflow"); + ret =3D -EINVAL; + goto cleanup1; + } + } + if (shared_resource->alloc_private_data_size =3D=3D 0) { + ret =3D -EINVAL; + goto cleanup1; + } + shared_resource->alloc_private_data =3D + vzalloc(shared_resource->alloc_private_data_size); + if (shared_resource->alloc_private_data =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup1; + } + shared_resource->alloc_private_data_sizes =3D + vzalloc(sizeof(u32)*shared_resource->allocation_count); + if (shared_resource->alloc_private_data_sizes =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup1; + } + private_data =3D shared_resource->alloc_private_data; + data_size =3D shared_resource->alloc_private_data_size; + i =3D 0; + list_for_each_entry(alloc, &resource->alloc_list_head, + alloc_list_entry) { + u32 alloc_data_size =3D alloc->priv_drv_data->data_size; + + if (alloc_data_size) { + if (data_size < alloc_data_size) { + pr_err("Invalid private data size"); + ret =3D -EINVAL; + goto cleanup1; + } + shared_resource->alloc_private_data_sizes[i] =3D + alloc_data_size; + memcpy(private_data, + alloc->priv_drv_data->data, + alloc_data_size); + vfree(alloc->priv_drv_data); + alloc->priv_drv_data =3D NULL; + private_data +=3D alloc_data_size; + data_size -=3D alloc_data_size; + } + i++; + } + if (data_size !=3D 0) { + pr_err("Data size mismatch"); + ret =3D -EINVAL; + } +cleanup1: + mutex_unlock(&resource->resource_mutex); + } +cleanup: + up_write(&shared_resource->adapter->shared_resource_list_lock); + return ret; +} + static int dxgk_enum_adapters(struct dxgprocess *process, void *__user inargs) { @@ -823,6 +941,7 @@ dxgk_create_allocation(struct dxgprocess *process, void= *__user inargs) u32 alloc_info_size =3D 0; struct dxgresource *resource =3D NULL; struct dxgallocation **dxgalloc =3D NULL; + struct dxgsharedresource *shared_resource =3D NULL; bool resource_mutex_acquired =3D false; u32 standard_alloc_priv_data_size =3D 0; void *standard_alloc_priv_data =3D NULL; @@ -995,6 +1114,76 @@ dxgk_create_allocation(struct dxgprocess *process, vo= id *__user inargs) } resource->private_runtime_handle =3D args.private_runtime_resource_handle; + if (args.flags.create_shared) { + if (!args.flags.nt_security_sharing) { + pr_err("%s: nt_security_sharing must be set", + __func__); + ret =3D -EINVAL; + goto cleanup; + } + shared_resource =3D dxgsharedresource_create(adapter); + if (shared_resource =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + shared_resource->runtime_private_data_size =3D + args.priv_drv_data_size; + shared_resource->resource_private_data_size =3D + args.priv_drv_data_size; + + shared_resource->runtime_private_data_size =3D + args.private_runtime_data_size; + shared_resource->resource_private_data_size =3D + args.priv_drv_data_size; + dxgsharedresource_add_resource(shared_resource, + resource); + if (args.flags.standard_allocation) { + shared_resource->resource_private_data =3D + res_priv_data; + shared_resource->resource_private_data_size =3D + res_priv_data_size; + res_priv_data =3D NULL; + } + if (args.private_runtime_data_size) { + shared_resource->runtime_private_data =3D + vzalloc(args.private_runtime_data_size); + if (shared_resource->runtime_private_data =3D=3D + NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + ret =3D copy_from_user( + shared_resource->runtime_private_data, + args.private_runtime_data, + args.private_runtime_data_size); + if (ret) { + pr_err("%s failed to copy runtime data", + __func__); + ret =3D -EINVAL; + goto cleanup; + } + } + if (args.priv_drv_data_size && + !args.flags.standard_allocation) { + shared_resource->resource_private_data =3D + vzalloc(args.priv_drv_data_size); + if (shared_resource->resource_private_data =3D=3D + NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + ret =3D copy_from_user( + shared_resource->resource_private_data, + args.priv_drv_data, + args.priv_drv_data_size); + if (ret) { + pr_err("%s failed to copy res data", + __func__); + ret =3D -EINVAL; + goto cleanup; + } + } + } } else { if (args.resource.v) { /* Adding new allocations to the given resource */ @@ -1013,6 +1202,12 @@ dxgk_create_allocation(struct dxgprocess *process, v= oid *__user inargs) ret =3D -EINVAL; goto cleanup; } + if (resource->shared_owner && + resource->shared_owner->sealed) { + pr_err("Resource is sealed"); + ret =3D -EINVAL; + goto cleanup; + } /* Synchronize with resource destruction */ mutex_lock(&resource->resource_mutex); if (!dxgresource_is_active(resource)) { @@ -1117,9 +1312,16 @@ dxgk_create_allocation(struct dxgprocess *process, v= oid *__user inargs) } } if (resource && args.flags.create_resource) { + if (shared_resource) { + dxgsharedresource_remove_resource + (shared_resource, resource); + } dxgresource_destroy(resource); } } + if (shared_resource) + kref_put(&shared_resource->sresource_kref, + dxgsharedresource_destroy); if (dxgalloc) vfree(dxgalloc); if (standard_alloc_priv_data) @@ -1165,6 +1367,10 @@ static int validate_alloc(struct dxgallocation *allo= c0, fail_reason =3D 4; goto cleanup; } + if (alloc->owner.resource->shared_owner) { + fail_reason =3D 5; + goto cleanup; + } } else { if (alloc->owner.device !=3D device) { fail_reason =3D 6; @@ -2173,6 +2379,580 @@ dxgk_wait_sync_object_gpu(struct dxgprocess *proces= s, void *__user inargs) return ret; } =20 +static int +dxgsharedresource_get_host_nt_handle(struct dxgsharedresource *resource, + struct dxgprocess *process, + struct d3dkmthandle objecthandle) +{ + int ret =3D 0; + + mutex_lock(&resource->fd_mutex); + if (resource->host_shared_handle_nt_reference =3D=3D 0) { + ret =3D dxgvmb_send_create_nt_shared_object(process, + objecthandle, + &resource->host_shared_handle_nt); + if (ret < 0) + goto cleanup; + pr_debug("Resource host_shared_handle_ht: %x", + resource->host_shared_handle_nt.v); + kref_get(&resource->sresource_kref); + } + resource->host_shared_handle_nt_reference++; +cleanup: + mutex_unlock(&resource->fd_mutex); + return ret; +} + +enum dxg_sharedobject_type { + DXG_SHARED_RESOURCE +}; + +static int get_object_fd(enum dxg_sharedobject_type type, + void *object, int *fdout) +{ + struct file *file; + int fd; + + fd =3D get_unused_fd_flags(O_CLOEXEC); + if (fd < 0) { + pr_err("get_unused_fd_flags failed: %x", fd); + return -ENOTRECOVERABLE; + } + + switch (type) { + case DXG_SHARED_RESOURCE: + file =3D anon_inode_getfile("dxgresource", + &dxg_resource_fops, object, 0); + break; + default: + return -EINVAL; + }; + if (IS_ERR(file)) { + pr_err("anon_inode_getfile failed: %x", fd); + put_unused_fd(fd); + return -ENOTRECOVERABLE; + } + + fd_install(fd, file); + *fdout =3D fd; + return 0; +} + +static int +dxgk_share_objects(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmt_shareobjects args; + enum hmgrentry_type object_type; + struct dxgsyncobject *syncobj =3D NULL; + struct dxgresource *resource =3D NULL; + struct dxgsharedresource *shared_resource =3D NULL; + struct d3dkmthandle *handles =3D NULL; + int object_fd =3D 0; + void *obj =3D NULL; + u32 handle_size; + int ret; + u64 tmp =3D 0; + + pr_debug("ioctl: %s", __func__); + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.object_count =3D=3D 0 || args.object_count > 1) { + pr_err("invalid object count %d", args.object_count); + ret =3D -EINVAL; + goto cleanup; + } + + handle_size =3D args.object_count * sizeof(struct d3dkmthandle); + + handles =3D vzalloc(handle_size); + if (handles =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + ret =3D copy_from_user(handles, args.objects, handle_size); + if (ret) { + pr_err("%s failed to copy object handles", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + pr_debug("Sharing handle: %x", handles[0].v); + + hmgrtable_lock(&process->handle_table, DXGLOCK_SHARED); + object_type =3D hmgrtable_get_object_type(&process->handle_table, + handles[0]); + obj =3D hmgrtable_get_object(&process->handle_table, handles[0]); + if (obj =3D=3D NULL) { + pr_err("invalid object handle %x", handles[0].v); + ret =3D -EINVAL; + } else { + switch (object_type) { + case HMGRENTRY_TYPE_DXGRESOURCE: + resource =3D obj; + if (resource->shared_owner) { + kref_get(&resource->resource_kref); + shared_resource =3D resource->shared_owner; + } else { + resource =3D NULL; + pr_err("resource object is not shared"); + ret =3D -EINVAL; + } + break; + default: + pr_err("invalid object type %d", object_type); + ret =3D -EINVAL; + break; + } + } + hmgrtable_unlock(&process->handle_table, DXGLOCK_SHARED); + + if (ret < 0) + goto cleanup; + + switch (object_type) { + case HMGRENTRY_TYPE_DXGRESOURCE: + ret =3D get_object_fd(DXG_SHARED_RESOURCE, shared_resource, + &object_fd); + if (ret < 0) { + pr_err("%s get_object_fd failed for resource", + __func__); + goto cleanup; + } + ret =3D dxgsharedresource_get_host_nt_handle(shared_resource, + process, handles[0]); + if (ret < 0) { + pr_err("%s get_host_res_nt_handle failed", __func__); + goto cleanup; + } + ret =3D dxgsharedresource_seal(shared_resource); + if (ret < 0) { + pr_err("%s dxgsharedresource_seal failed", __func__); + goto cleanup; + } + break; + default: + ret =3D -EINVAL; + break; + } + + if (ret < 0) + goto cleanup; + + pr_debug("Object FD: %x", object_fd); + + tmp =3D (u64) object_fd; + + ret =3D copy_to_user(args.shared_handle, &tmp, sizeof(u64)); + if (ret < 0) + pr_err("%s failed to copy shared handle", __func__); + +cleanup: + if (ret < 0) { + if (object_fd > 0) + put_unused_fd(object_fd); + } + + if (handles) + vfree(handles); + + if (syncobj) + kref_put(&syncobj->syncobj_kref, dxgsyncobject_release); + + if (resource) + kref_put(&resource->resource_kref, dxgresource_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_query_resource_info_nt(struct dxgprocess *process, void *__user inarg= s) +{ + struct d3dkmt_queryresourceinfofromnthandle args; + int ret; + struct dxgdevice *device =3D NULL; + struct dxgsharedresource *shared_resource =3D NULL; + struct file *file =3D NULL; + + pr_debug("ioctl: %s", __func__); + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + file =3D fget(args.nt_handle); + if (!file) { + pr_err("failed to get file from handle: %llx", + args.nt_handle); + ret =3D -EINVAL; + goto cleanup; + } + + if (file->f_op !=3D &dxg_resource_fops) { + pr_err("invalid fd: %llx", args.nt_handle); + ret =3D -EINVAL; + goto cleanup; + } + + shared_resource =3D file->private_data; + if (shared_resource =3D=3D NULL) { + pr_err("invalid private data: %llx", args.nt_handle); + ret =3D -EINVAL; + goto cleanup; + } + + device =3D dxgprocess_device_by_handle(process, args.device); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgdevice_acquire_lock_shared(device); + if (ret < 0) { + kref_put(&device->device_kref, dxgdevice_release); + device =3D NULL; + goto cleanup; + } + + ret =3D dxgsharedresource_seal(shared_resource); + if (ret < 0) + goto cleanup; + + args.private_runtime_data_size =3D + shared_resource->runtime_private_data_size; + args.resource_priv_drv_data_size =3D + shared_resource->resource_private_data_size; + args.allocation_count =3D shared_resource->allocation_count; + args.total_priv_drv_data_size =3D + shared_resource->alloc_private_data_size; + + ret =3D copy_to_user(inargs, &args, sizeof(args)); + if (ret < 0) + pr_err("%s failed to copy output args", __func__); + +cleanup: + + if (file) + fput(file); + if (device) + dxgdevice_release_lock_shared(device); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +assign_resource_handles(struct dxgprocess *process, + struct dxgsharedresource *shared_resource, + struct d3dkmt_openresourcefromnthandle *args, + struct d3dkmthandle resource_handle, + struct dxgresource *resource, + struct dxgallocation **allocs, + struct d3dkmthandle *handles) +{ + int ret; + int i; + u8 *cur_priv_data; + u32 total_priv_data_size =3D 0; + struct d3dddi_openallocationinfo2 open_alloc_info =3D { }; + + hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL); + ret =3D hmgrtable_assign_handle(&process->handle_table, resource, + HMGRENTRY_TYPE_DXGRESOURCE, + resource_handle); + if (ret < 0) + goto cleanup; + resource->handle =3D resource_handle; + resource->handle_valid =3D 1; + cur_priv_data =3D args->total_priv_drv_data; + for (i =3D 0; i < args->allocation_count; i++) { + ret =3D hmgrtable_assign_handle(&process->handle_table, allocs[i], + HMGRENTRY_TYPE_DXGALLOCATION, + handles[i]); + if (ret < 0) + goto cleanup; + allocs[i]->alloc_handle =3D handles[i]; + allocs[i]->handle_valid =3D 1; + open_alloc_info.allocation =3D handles[i]; + if (shared_resource->alloc_private_data_sizes) + open_alloc_info.priv_drv_data_size =3D + shared_resource->alloc_private_data_sizes[i]; + else + open_alloc_info.priv_drv_data_size =3D 0; + + total_priv_data_size +=3D open_alloc_info.priv_drv_data_size; + open_alloc_info.priv_drv_data =3D cur_priv_data; + cur_priv_data +=3D open_alloc_info.priv_drv_data_size; + + ret =3D copy_to_user(&args->open_alloc_info[i], + &open_alloc_info, + sizeof(open_alloc_info)); + if (ret < 0) { + pr_err("%s failed to copy alloc info", __func__); + goto cleanup; + } + } + args->total_priv_drv_data_size =3D total_priv_data_size; +cleanup: + hmgrtable_unlock(&process->handle_table, DXGLOCK_EXCL); + if (ret < 0) { + for (i =3D 0; i < args->allocation_count; i++) + dxgallocation_free_handle(allocs[i]); + dxgresource_free_handle(resource); + } + pr_debug("%s end %x", __func__, ret); + return ret; +} + +static int +open_resource(struct dxgprocess *process, + struct d3dkmt_openresourcefromnthandle *args, + __user struct d3dkmthandle *res_out, + __user u32 *total_driver_data_size_out) +{ + int ret =3D 0; + int i; + struct d3dkmthandle *alloc_handles =3D NULL; + int alloc_handles_size =3D sizeof(struct d3dkmthandle) * + args->allocation_count; + struct dxgsharedresource *shared_resource =3D NULL; + struct dxgresource *resource =3D NULL; + struct dxgallocation **allocs =3D NULL; + struct d3dkmthandle global_share =3D {}; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + struct d3dkmthandle resource_handle =3D {}; + struct file *file =3D NULL; + + pr_debug("Opening resource handle: %llx", args->nt_handle); + + file =3D fget(args->nt_handle); + if (!file) { + pr_err("failed to get file from handle: %llx", + args->nt_handle); + ret =3D -EINVAL; + goto cleanup; + } + if (file->f_op !=3D &dxg_resource_fops) { + pr_err("invalid fd type: %llx", args->nt_handle); + ret =3D -EINVAL; + goto cleanup; + } + shared_resource =3D file->private_data; + if (shared_resource =3D=3D NULL) { + pr_err("invalid private data: %llx", + args->nt_handle); + ret =3D -EINVAL; + goto cleanup; + } + if (kref_get_unless_zero(&shared_resource->sresource_kref) =3D=3D 0) + shared_resource =3D NULL; + else + global_share =3D shared_resource->host_shared_handle_nt; + + if (shared_resource =3D=3D NULL) { + pr_err("Invalid shared resource handle: %x", + (u32)args->nt_handle); + ret =3D -EINVAL; + goto cleanup; + } + + pr_debug("Shared resource: %p %x", shared_resource, + global_share.v); + + device =3D dxgprocess_device_by_handle(process, args->device); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgdevice_acquire_lock_shared(device); + if (ret < 0) { + kref_put(&device->device_kref, dxgdevice_release); + device =3D NULL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgsharedresource_seal(shared_resource); + if (ret < 0) + goto cleanup; + + if (args->allocation_count !=3D shared_resource->allocation_count || + args->private_runtime_data_size < + shared_resource->runtime_private_data_size || + args->resource_priv_drv_data_size < + shared_resource->resource_private_data_size || + args->total_priv_drv_data_size < + shared_resource->alloc_private_data_size) { + ret =3D -EINVAL; + pr_err("Invalid data sizes"); + goto cleanup; + } + + alloc_handles =3D vzalloc(alloc_handles_size); + if (alloc_handles =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + + allocs =3D vzalloc(sizeof(void *) * args->allocation_count); + if (allocs =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + + resource =3D dxgresource_create(device); + if (resource =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + dxgsharedresource_add_resource(shared_resource, resource); + + for (i =3D 0; i < args->allocation_count; i++) { + allocs[i] =3D dxgallocation_create(process); + if (allocs[i] =3D=3D NULL) + goto cleanup; + ret =3D dxgresource_add_alloc(resource, allocs[i]); + if (ret < 0) + goto cleanup; + } + + ret =3D dxgvmb_send_open_resource(process, adapter, + device->handle, global_share, + args->allocation_count, + args->total_priv_drv_data_size, + &resource_handle, alloc_handles); + if (ret < 0) { + pr_err("dxgvmb_send_open_resource failed"); + goto cleanup; + } + + if (shared_resource->runtime_private_data_size) { + ret =3D copy_to_user(args->private_runtime_data, + shared_resource->runtime_private_data, + shared_resource->runtime_private_data_size); + if (ret < 0) { + pr_err("%s failed to copy runtime data", __func__); + goto cleanup; + } + } + + if (shared_resource->resource_private_data_size) { + ret =3D copy_to_user(args->resource_priv_drv_data, + shared_resource->resource_private_data, + shared_resource->resource_private_data_size); + if (ret < 0) { + pr_err("%s failed to copy resource data", __func__); + goto cleanup; + } + } + + if (shared_resource->alloc_private_data_size) { + ret =3D copy_to_user(args->total_priv_drv_data, + shared_resource->alloc_private_data, + shared_resource->alloc_private_data_size); + if (ret < 0) { + pr_err("%s failed to copy alloc data", __func__); + goto cleanup; + } + } + + ret =3D assign_resource_handles(process, shared_resource, args, + resource_handle, resource, allocs, + alloc_handles); + if (ret < 0) + goto cleanup; + + ret =3D copy_to_user(res_out, &resource_handle, + sizeof(struct d3dkmthandle)); + if (ret < 0) { + pr_err("%s failed to copy resource handle to user", __func__); + goto cleanup; + } + + ret =3D copy_to_user(total_driver_data_size_out, + &args->total_priv_drv_data_size, sizeof(u32)); + if (ret < 0) + pr_err("%s failed to copy total driver data size", __func__); + +cleanup: + + if (ret < 0) { + if (resource_handle.v) { + struct d3dkmt_destroyallocation2 tmp =3D { }; + + tmp.flags.assume_not_in_use =3D 1; + tmp.device =3D args->device; + tmp.resource =3D resource_handle; + ret =3D dxgvmb_send_destroy_allocation(process, device, + &tmp, NULL); + } + if (resource) + dxgresource_destroy(resource); + } + + if (file) + fput(file); + if (allocs) + vfree(allocs); + if (shared_resource) + kref_put(&shared_resource->sresource_kref, + dxgsharedresource_destroy); + if (alloc_handles) + vfree(alloc_handles); + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + dxgdevice_release_lock_shared(device); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + return ret; +} + +static int +dxgk_open_resource_nt(struct dxgprocess *process, + void *__user inargs) +{ + struct d3dkmt_openresourcefromnthandle args; + struct d3dkmt_openresourcefromnthandle *__user args_user =3D inargs; + int ret; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D open_resource(process, &args, + &args_user->resource, + &args_user->total_priv_drv_data_size); + +cleanup: + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + /* * IOCTL processing * The driver IOCTLs return @@ -2269,4 +3049,10 @@ void init_ioctls(void) LX_DXWAITFORSYNCHRONIZATIONOBJECTFROMGPU); SET_IOCTL(/*0x3e */ dxgk_enum_adapters3, LX_DXENUMADAPTERS3); + SET_IOCTL(/*0x3f */ dxgk_share_objects, + LX_DXSHAREOBJECTS); + SET_IOCTL(/*0x41 */ dxgk_query_resource_info_nt, + LX_DXQUERYRESOURCEINFOFROMNTHANDLE); + SET_IOCTL(/*0x42 */ dxgk_open_resource_nt, + LX_DXOPENRESOURCEFROMNTHANDLE); } --=20 2.35.1 From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 34F5AC433EF for ; Sat, 5 Feb 2022 02:35:06 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1379193AbiBECfD (ORCPT ); Fri, 4 Feb 2022 21:35:03 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45084 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1379011AbiBECeZ (ORCPT ); Fri, 4 Feb 2022 21:34:25 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id 1C6C320B83DE; Fri, 4 Feb 2022 18:34:25 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com 1C6C320B83DE DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028465; bh=8BHGH5p78TXG0DKQOUPapuXC2TvlZuX5xmDKMWPHU6A=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=VYUFLBYaiAcf1jba/0RXPoiTRLjcYL6gHIvhkOxL1ApxA1r4GYPDlhqQ4WMYSBRJz c6/r2zdlNBNHbhNY3ZzWiAE42qg1c7TQXDo8Zv4yudV5TI2qGbvCVU2UJZFJGveZEC OIqDpZqkQ78Husw1mFc/Znl1VhBSXy87o739nLu8= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 10/24] drivers: hv: dxgkrnl: Sharing of sync objects Date: Fri, 4 Feb 2022 18:34:08 -0800 Message-Id: <7ed5233e738f34e884a136534460bac00cc536b5.1644025661.git.iourit@linux.microsoft.com> X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Implement creation of a shared sync object and IOCTLs for sharing dxgsyncobject objects between processes in the virtual machine. Sync objects are shared using FD (file descriptor) handles. The name "NT handle" is used to be compatible with Windows implementation. An FD handle is created by the LX_DXSHAREOBJECTS ioctl. The created FD handle could be sent to another process using any Linux API. To use a shared sync object in WDDM API calls, the object needs to be opened using its FD handle. A sync object is opened by the following ioctl: LX_DXOPENSYNCOBJECTFROMNTHANDLE2. Signed-off-by: Iouri Tarassov --- drivers/hv/dxgkrnl/dxgadapter.c | 83 +++++++++++ drivers/hv/dxgkrnl/dxgkrnl.h | 63 +++++++++ drivers/hv/dxgkrnl/dxgmodule.c | 1 + drivers/hv/dxgkrnl/dxgvmbus.c | 63 +++++++++ drivers/hv/dxgkrnl/ioctl.c | 240 ++++++++++++++++++++++++++++++++ 5 files changed, 450 insertions(+) diff --git a/drivers/hv/dxgkrnl/dxgadapter.c b/drivers/hv/dxgkrnl/dxgadapte= r.c index 1b8f2b63eb6d..e32b4bc16ab8 100644 --- a/drivers/hv/dxgkrnl/dxgadapter.c +++ b/drivers/hv/dxgkrnl/dxgadapter.c @@ -176,6 +176,26 @@ void dxgadapter_remove_shared_resource(struct dxgadapt= er *adapter, up_write(&adapter->shared_resource_list_lock); } =20 +void dxgadapter_add_shared_syncobj(struct dxgadapter *adapter, + struct dxgsharedsyncobject *object) +{ + down_write(&adapter->shared_resource_list_lock); + list_add_tail(&object->adapter_shared_syncobj_list_entry, + &adapter->adapter_shared_syncobj_list_head); + up_write(&adapter->shared_resource_list_lock); +} + +void dxgadapter_remove_shared_syncobj(struct dxgadapter *adapter, + struct dxgsharedsyncobject *object) +{ + down_write(&adapter->shared_resource_list_lock); + if (object->adapter_shared_syncobj_list_entry.next) { + list_del(&object->adapter_shared_syncobj_list_entry); + object->adapter_shared_syncobj_list_entry.next =3D NULL; + } + up_write(&adapter->shared_resource_list_lock); +} + void dxgadapter_add_syncobj(struct dxgadapter *adapter, struct dxgsyncobject *object) { @@ -952,6 +972,63 @@ void dxgprocess_adapter_remove_device(struct dxgdevice= *device) mutex_unlock(&device->adapter_info->device_list_mutex); } =20 +struct dxgsharedsyncobject *dxgsharedsyncobj_create(struct dxgadapter *ada= pter, + struct dxgsyncobject *so) +{ + struct dxgsharedsyncobject *syncobj; + + syncobj =3D vzalloc(sizeof(*syncobj)); + if (syncobj) { + kref_init(&syncobj->ssyncobj_kref); + INIT_LIST_HEAD(&syncobj->shared_syncobj_list_head); + syncobj->adapter =3D adapter; + syncobj->type =3D so->type; + syncobj->monitored_fence =3D so->monitored_fence; + dxgadapter_add_shared_syncobj(adapter, syncobj); + kref_get(&adapter->adapter_kref); + init_rwsem(&syncobj->syncobj_list_lock); + mutex_init(&syncobj->fd_mutex); + } + return syncobj; +} + +void dxgsharedsyncobj_release(struct kref *refcount) +{ + struct dxgsharedsyncobject *syncobj; + + syncobj =3D container_of(refcount, struct dxgsharedsyncobject, + ssyncobj_kref); + pr_debug("Destroying shared sync object %p", syncobj); + if (syncobj->adapter) { + dxgadapter_remove_shared_syncobj(syncobj->adapter, + syncobj); + kref_put(&syncobj->adapter->adapter_kref, + dxgadapter_release); + } + vfree(syncobj); +} + +void dxgsharedsyncobj_add_syncobj(struct dxgsharedsyncobject *shared, + struct dxgsyncobject *syncobj) +{ + pr_debug("%s 0x%p 0x%p", __func__, shared, syncobj); + kref_get(&shared->ssyncobj_kref); + down_write(&shared->syncobj_list_lock); + list_add(&syncobj->shared_syncobj_list_entry, + &shared->shared_syncobj_list_head); + syncobj->shared_owner =3D shared; + up_write(&shared->syncobj_list_lock); +} + +void dxgsharedsyncobj_remove_syncobj(struct dxgsharedsyncobject *shared, + struct dxgsyncobject *syncobj) +{ + pr_debug("%s 0x%p", __func__, shared); + down_write(&shared->syncobj_list_lock); + list_del(&syncobj->shared_syncobj_list_entry); + up_write(&shared->syncobj_list_lock); +} + struct dxgsyncobject *dxgsyncobject_create(struct dxgprocess *process, struct dxgdevice *device, struct dxgadapter *adapter, @@ -1086,6 +1163,12 @@ void dxgsyncobject_release(struct kref *refcount) struct dxgsyncobject *syncobj; =20 syncobj =3D container_of(refcount, struct dxgsyncobject, syncobj_kref); + if (syncobj->shared_owner) { + dxgsharedsyncobj_remove_syncobj(syncobj->shared_owner, + syncobj); + kref_put(&syncobj->shared_owner->ssyncobj_kref, + dxgsharedsyncobj_release); + } if (syncobj->host_event) vfree(syncobj->host_event); vfree(syncobj); diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index f3ea98f0b384..662fa27fd1ed 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -35,6 +35,7 @@ struct dxgallocation; struct dxgresource; struct dxgsharedresource; struct dxgsyncobject; +struct dxgsharedsyncobject; =20 #include "misc.h" #include "hmgr.h" @@ -118,6 +119,18 @@ struct dxghosteventcpu { * "device" syncobject, because the belong to a device (dxgdevice). * Device syncobjects are inserted to a list in dxgdevice. * + * A syncobject can be "shared", meaning that it could be opened by many + * processes. + * + * Shared syncobjects are inserted to a list in its owner + * (dxgsharedsyncobject). + * A syncobject can be shared by using a global handle or by using + * "NT security handle". + * When global handle sharing is used, the handle is created durinig object + * creation. + * When "NT security" is used, the handle for sharing is create be calling + * dxgk_share_objects. On Linux "NT handle" is represented by a file + * descriptor. FD points to dxgsharedsyncobject. */ struct dxgsyncobject { struct kref syncobj_kref; @@ -127,6 +140,8 @@ struct dxgsyncobject { * List entry in dxgadapter for other objects */ struct list_head syncobj_list_entry; + /* List entry in the dxgsharedsyncobject object for shared synobjects */ + struct list_head shared_syncobj_list_entry; /* Adapter, the syncobject belongs to. NULL for stopped sync obejcts. */ struct dxgadapter *adapter; /* @@ -137,6 +152,8 @@ struct dxgsyncobject { struct dxgprocess *process; /* Used by D3DDDI_CPU_NOTIFICATION objects */ struct dxghosteventcpu *host_event; + /* Owner object for shared syncobjects */ + struct dxgsharedsyncobject *shared_owner; /* CPU virtual address of the fence value for "device" syncobjects */ void *mapped_address; /* Handle in the process handle table */ @@ -168,6 +185,41 @@ struct dxgvgpuchannel { struct hv_device *hdev; }; =20 +/* + * The object is used as parent of all sync objects, created for a shared + * syncobject. When a shared syncobject is created without NT security, the + * handle in the global handle table will point to this object. + */ +struct dxgsharedsyncobject { + struct kref ssyncobj_kref; + /* Referenced by file descriptors */ + int host_shared_handle_nt_reference; + /* Corresponding handle in the host global handle table */ + struct d3dkmthandle host_shared_handle; + /* + * When the sync object is shared by NT handle, this is the + * corresponding handle in the host + */ + struct d3dkmthandle host_shared_handle_nt; + /* Protects access to host_shared_handle_nt */ + struct mutex fd_mutex; + struct rw_semaphore syncobj_list_lock; + struct list_head shared_syncobj_list_head; + struct list_head adapter_shared_syncobj_list_entry; + struct dxgadapter *adapter; + enum d3dddi_synchronizationobject_type type; + u32 monitored_fence:1; +}; + +struct dxgsharedsyncobject *dxgsharedsyncobj_create(struct dxgadapter *ada= pter, + struct dxgsyncobject + *syncobj); +void dxgsharedsyncobj_release(struct kref *refcount); +void dxgsharedsyncobj_add_syncobj(struct dxgsharedsyncobject *sharedsyncob= j, + struct dxgsyncobject *syncobj); +void dxgsharedsyncobj_remove_syncobj(struct dxgsharedsyncobject *sharedsyn= cobj, + struct dxgsyncobject *syncobj); + struct dxgsyncobject *dxgsyncobject_create(struct dxgprocess *process, struct dxgdevice *device, struct dxgadapter *adapter, @@ -358,6 +410,8 @@ struct dxgadapter { struct list_head adapter_process_list_head; /* List of all dxgsharedresource objects */ struct list_head shared_resource_list_head; + /* List of all dxgsharedsyncobject objects */ + struct list_head adapter_shared_syncobj_list_head; /* List of all non-device dxgsyncobject objects */ struct list_head syncobj_list_head; /* This lock protects shared resource and syncobject lists */ @@ -385,6 +439,10 @@ void dxgadapter_release_lock_shared(struct dxgadapter = *adapter); int dxgadapter_acquire_lock_exclusive(struct dxgadapter *adapter); void dxgadapter_acquire_lock_forced(struct dxgadapter *adapter); void dxgadapter_release_lock_exclusive(struct dxgadapter *adapter); +void dxgadapter_add_shared_syncobj(struct dxgadapter *adapter, + struct dxgsharedsyncobject *so); +void dxgadapter_remove_shared_syncobj(struct dxgadapter *adapter, + struct dxgsharedsyncobject *so); void dxgadapter_add_syncobj(struct dxgadapter *adapter, struct dxgsyncobject *so); void dxgadapter_remove_syncobj(struct dxgsyncobject *so); @@ -697,6 +755,11 @@ int dxgvmb_send_wait_sync_object_cpu(struct dxgprocess= *process, int dxgvmb_send_query_adapter_info(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_queryadapterinfo *args); +int dxgvmb_send_open_sync_object_nt(struct dxgprocess *process, + struct dxgvmbuschannel *channel, + struct d3dkmt_opensyncobjectfromnthandle2 + *args, + struct dxgsyncobject *syncobj); int dxgvmb_send_create_nt_shared_object(struct dxgprocess *process, struct d3dkmthandle object, struct d3dkmthandle *shared_handle); diff --git a/drivers/hv/dxgkrnl/dxgmodule.c b/drivers/hv/dxgkrnl/dxgmodule.c index 3af5a7a3ac74..3928512bcc64 100644 --- a/drivers/hv/dxgkrnl/dxgmodule.c +++ b/drivers/hv/dxgkrnl/dxgmodule.c @@ -251,6 +251,7 @@ int dxgglobal_create_adapter(struct pci_dev *dev, guid_= t *guid, =20 INIT_LIST_HEAD(&adapter->adapter_process_list_head); INIT_LIST_HEAD(&adapter->shared_resource_list_head); + INIT_LIST_HEAD(&adapter->adapter_shared_syncobj_list_head); INIT_LIST_HEAD(&adapter->syncobj_list_head); init_rwsem(&adapter->shared_resource_list_lock); adapter->pci_dev =3D dev; diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index af8d1aab871f..659afb59b4fd 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -694,6 +694,69 @@ int dxgvmb_send_destroy_process(struct d3dkmthandle pr= ocess) return ret; } =20 +int dxgvmb_send_open_sync_object_nt(struct dxgprocess *process, + struct dxgvmbuschannel *channel, + struct d3dkmt_opensyncobjectfromnthandle2 + *args, + struct dxgsyncobject *syncobj) +{ + struct dxgkvmb_command_opensyncobject *command; + struct dxgkvmb_command_opensyncobject_return result =3D { }; + int ret; + struct dxgvmbusmsg msg; + + ret =3D init_message(&msg, NULL, process, sizeof(*command)); + if (ret) + return ret; + command =3D (void *)msg.msg; + + command_vm_to_host_init2(&command->hdr, DXGK_VMBCOMMAND_OPENSYNCOBJECT, + process->host_handle); + command->device =3D args->device; + command->global_sync_object =3D syncobj->shared_owner->host_shared_handle; + command->flags =3D args->flags; + if (syncobj->monitored_fence) + command->engine_affinity =3D + args->monitored_fence.engine_affinity; + + ret =3D dxgglobal_acquire_channel_lock(); + if (ret < 0) + goto cleanup; + + ret =3D dxgvmb_send_sync_msg(channel, msg.hdr, msg.size, + &result, sizeof(result)); + + dxgglobal_release_channel_lock(); + + if (ret < 0) + goto cleanup; + + ret =3D ntstatus2int(result.status); + if (ret < 0) + goto cleanup; + + args->sync_object =3D result.sync_object; + if (syncobj->monitored_fence) { + void *va =3D dxg_map_iospace(result.guest_cpu_physical_address, + PAGE_SIZE, PROT_READ | PROT_WRITE, + true); + if (va =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + args->monitored_fence.fence_value_cpu_va =3D va; + args->monitored_fence.fence_value_gpu_va =3D + result.gpu_virtual_address; + syncobj->mapped_address =3D va; + } + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + int dxgvmb_send_create_nt_shared_object(struct dxgprocess *process, struct d3dkmthandle object, struct d3dkmthandle *shared_handle) diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index 05f59854cbbf..be9d72c4ae4e 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -35,6 +35,33 @@ static char *errorstr(int ret) return ret < 0 ? "err" : ""; } =20 +static int dxgsyncobj_release(struct inode *inode, struct file *file) +{ + struct dxgsharedsyncobject *syncobj =3D file->private_data; + + pr_debug("%s: %p", __func__, syncobj); + mutex_lock(&syncobj->fd_mutex); + kref_get(&syncobj->ssyncobj_kref); + syncobj->host_shared_handle_nt_reference--; + if (syncobj->host_shared_handle_nt_reference =3D=3D 0) { + if (syncobj->host_shared_handle_nt.v) { + dxgvmb_send_destroy_nt_shared_object( + syncobj->host_shared_handle_nt); + pr_debug("Syncobj host_handle_nt destroyed: %x", + syncobj->host_shared_handle_nt.v); + syncobj->host_shared_handle_nt.v =3D 0; + } + kref_put(&syncobj->ssyncobj_kref, dxgsharedsyncobj_release); + } + mutex_unlock(&syncobj->fd_mutex); + kref_put(&syncobj->ssyncobj_kref, dxgsharedsyncobj_release); + return 0; +} + +static const struct file_operations dxg_syncobj_fops =3D { + .release =3D dxgsyncobj_release, +}; + static int dxgsharedresource_release(struct inode *inode, struct file *fil= e) { struct dxgsharedresource *resource =3D file->private_data; @@ -1584,6 +1611,7 @@ dxgk_create_sync_object(struct dxgprocess *process, v= oid *__user inargs) struct eventfd_ctx *event =3D NULL; struct dxgsyncobject *syncobj =3D NULL; bool device_lock_acquired =3D false; + struct dxgsharedsyncobject *syncobjgbl =3D NULL; struct dxghosteventcpu *host_event =3D NULL; =20 ret =3D copy_from_user(&args, inargs, sizeof(args)); @@ -1644,6 +1672,22 @@ dxgk_create_sync_object(struct dxgprocess *process, = void *__user inargs) if (ret < 0) goto cleanup; =20 + if (args.info.flags.shared) { + if (args.info.shared_handle.v =3D=3D 0) { + pr_err("shared handle should not be 0"); + ret =3D -EINVAL; + goto cleanup; + } + syncobjgbl =3D dxgsharedsyncobj_create(device->adapter, syncobj); + if (syncobjgbl =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + dxgsharedsyncobj_add_syncobj(syncobjgbl, syncobj); + + syncobjgbl->host_shared_handle =3D args.info.shared_handle; + } + ret =3D copy_to_user(inargs, &args, sizeof(args)); if (ret) { pr_err("%s failed to copy output args", __func__); @@ -1672,6 +1716,8 @@ dxgk_create_sync_object(struct dxgprocess *process, v= oid *__user inargs) if (event) eventfd_ctx_put(event); } + if (syncobjgbl) + kref_put(&syncobjgbl->ssyncobj_kref, dxgsharedsyncobj_release); if (adapter) dxgadapter_release_lock_shared(adapter); if (device_lock_acquired) @@ -1726,6 +1772,141 @@ dxgk_destroy_sync_object(struct dxgprocess *process= , void *__user inargs) return ret; } =20 +static int +dxgk_open_sync_object_nt(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmt_opensyncobjectfromnthandle2 args; + struct dxgsyncobject *syncobj =3D NULL; + struct dxgsharedsyncobject *syncobj_fd =3D NULL; + struct file *file =3D NULL; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + struct d3dddi_synchronizationobject_flags flags =3D { }; + int ret; + bool device_lock_acquired =3D false; + + pr_debug("ioctl: %s", __func__); + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + args.sync_object.v =3D 0; + + if (args.device.v) { + device =3D dxgprocess_device_by_handle(process, args.device); + if (device =3D=3D NULL) { + return -EINVAL; + goto cleanup; + } + } else { + pr_err("device handle is missing"); + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgdevice_acquire_lock_shared(device); + if (ret < 0) + goto cleanup; + + device_lock_acquired =3D true; + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + file =3D fget(args.nt_handle); + if (!file) { + pr_err("failed to get file from handle: %llx", + args.nt_handle); + ret =3D -EINVAL; + goto cleanup; + } + + if (file->f_op !=3D &dxg_syncobj_fops) { + pr_err("invalid fd: %llx", args.nt_handle); + ret =3D -EINVAL; + goto cleanup; + } + + syncobj_fd =3D file->private_data; + if (syncobj_fd =3D=3D NULL) { + pr_err("invalid private data: %llx", args.nt_handle); + ret =3D -EINVAL; + goto cleanup; + } + + flags.shared =3D 1; + flags.nt_security_sharing =3D 1; + syncobj =3D dxgsyncobject_create(process, device, adapter, + syncobj_fd->type, flags); + if (syncobj =3D=3D NULL) { + pr_err("failed to create sync object"); + ret =3D -ENOMEM; + goto cleanup; + } + + dxgsharedsyncobj_add_syncobj(syncobj_fd, syncobj); + + ret =3D dxgvmb_send_open_sync_object_nt(process, &dxgglobal->channel, + &args, syncobj); + if (ret < 0) { + pr_err("failed to open sync object on host: %x", + syncobj_fd->host_shared_handle.v); + goto cleanup; + } + + hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL); + ret =3D hmgrtable_assign_handle(&process->handle_table, syncobj, + HMGRENTRY_TYPE_DXGSYNCOBJECT, + args.sync_object); + if (ret >=3D 0) { + syncobj->handle =3D args.sync_object; + kref_get(&syncobj->syncobj_kref); + } + hmgrtable_unlock(&process->handle_table, DXGLOCK_EXCL); + + if (ret < 0) + goto cleanup; + + ret =3D copy_to_user(inargs, &args, sizeof(args)); + if (ret >=3D 0) + goto success; + pr_err("%s failed to copy output args", __func__); + +cleanup: + + if (syncobj) { + dxgsyncobject_destroy(process, syncobj); + syncobj =3D NULL; + } + + if (args.sync_object.v) + dxgvmb_send_destroy_sync_object(process, args.sync_object); + +success: + + if (file) + fput(file); + if (syncobj) + kref_put(&syncobj->syncobj_kref, dxgsyncobject_release); + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device_lock_acquired) + dxgdevice_release_lock_shared(device); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + static int dxgk_signal_sync_object(struct dxgprocess *process, void *__user inargs) { @@ -2379,6 +2560,30 @@ dxgk_wait_sync_object_gpu(struct dxgprocess *process= , void *__user inargs) return ret; } =20 +static int +dxgsharedsyncobj_get_host_nt_handle(struct dxgsharedsyncobject *syncobj, + struct dxgprocess *process, + struct d3dkmthandle objecthandle) +{ + int ret =3D 0; + + mutex_lock(&syncobj->fd_mutex); + if (syncobj->host_shared_handle_nt_reference =3D=3D 0) { + ret =3D dxgvmb_send_create_nt_shared_object(process, + objecthandle, + &syncobj->host_shared_handle_nt); + if (ret < 0) + goto cleanup; + pr_debug("Host_shared_handle_ht: %x", + syncobj->host_shared_handle_nt.v); + kref_get(&syncobj->ssyncobj_kref); + } + syncobj->host_shared_handle_nt_reference++; +cleanup: + mutex_unlock(&syncobj->fd_mutex); + return ret; +} + static int dxgsharedresource_get_host_nt_handle(struct dxgsharedresource *resource, struct dxgprocess *process, @@ -2404,6 +2609,7 @@ dxgsharedresource_get_host_nt_handle(struct dxgshared= resource *resource, } =20 enum dxg_sharedobject_type { + DXG_SHARED_SYNCOBJECT, DXG_SHARED_RESOURCE }; =20 @@ -2420,6 +2626,10 @@ static int get_object_fd(enum dxg_sharedobject_type = type, } =20 switch (type) { + case DXG_SHARED_SYNCOBJECT: + file =3D anon_inode_getfile("dxgsyncobj", + &dxg_syncobj_fops, object, 0); + break; case DXG_SHARED_RESOURCE: file =3D anon_inode_getfile("dxgresource", &dxg_resource_fops, object, 0); @@ -2445,6 +2655,7 @@ dxgk_share_objects(struct dxgprocess *process, void *= __user inargs) enum hmgrentry_type object_type; struct dxgsyncobject *syncobj =3D NULL; struct dxgresource *resource =3D NULL; + struct dxgsharedsyncobject *shared_syncobj =3D NULL; struct dxgsharedresource *shared_resource =3D NULL; struct d3dkmthandle *handles =3D NULL; int object_fd =3D 0; @@ -2493,6 +2704,17 @@ dxgk_share_objects(struct dxgprocess *process, void = *__user inargs) ret =3D -EINVAL; } else { switch (object_type) { + case HMGRENTRY_TYPE_DXGSYNCOBJECT: + syncobj =3D obj; + if (syncobj->shared) { + kref_get(&syncobj->syncobj_kref); + shared_syncobj =3D syncobj->shared_owner; + } else { + pr_err("sync object is not shared"); + syncobj =3D NULL; + ret =3D -EINVAL; + } + break; case HMGRENTRY_TYPE_DXGRESOURCE: resource =3D obj; if (resource->shared_owner) { @@ -2516,6 +2738,22 @@ dxgk_share_objects(struct dxgprocess *process, void = *__user inargs) goto cleanup; =20 switch (object_type) { + case HMGRENTRY_TYPE_DXGSYNCOBJECT: + ret =3D get_object_fd(DXG_SHARED_SYNCOBJECT, shared_syncobj, + &object_fd); + if (ret < 0) { + pr_err("%s get_object_fd failed for sync object", + __func__); + goto cleanup; + } + ret =3D dxgsharedsyncobj_get_host_nt_handle(shared_syncobj, + process, + handles[0]); + if (ret < 0) { + pr_err("%s get_host_nt_handle failed", __func__); + goto cleanup; + } + break; case HMGRENTRY_TYPE_DXGRESOURCE: ret =3D get_object_fd(DXG_SHARED_RESOURCE, shared_resource, &object_fd); @@ -3051,6 +3289,8 @@ void init_ioctls(void) LX_DXENUMADAPTERS3); SET_IOCTL(/*0x3f */ dxgk_share_objects, LX_DXSHAREOBJECTS); + SET_IOCTL(/*0x40 */ dxgk_open_sync_object_nt, + LX_DXOPENSYNCOBJECTFROMNTHANDLE2); SET_IOCTL(/*0x41 */ dxgk_query_resource_info_nt, LX_DXQUERYRESOURCEINFOFROMNTHANDLE); SET_IOCTL(/*0x42 */ dxgk_open_resource_nt, --=20 2.35.1 From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 2F1B6C433EF for ; Sat, 5 Feb 2022 02:35:10 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1379212AbiBECfI (ORCPT ); Fri, 4 Feb 2022 21:35:08 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45090 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1379012AbiBECeZ (ORCPT ); Fri, 4 Feb 2022 21:34:25 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id 46D6020B83F5; Fri, 4 Feb 2022 18:34:25 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com 46D6020B83F5 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028465; bh=kEA7BHHGun4V03S8kX3XpXTA8lXW0xnyFp2ZSKU6yuA=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=T1UaCDXWKYEbVk3dVp2FMeWdwxWD6anmlzYvWabtZ55uI/UZV+gTGzecZ3sUew1W5 717vndRPY60rH1zTMTYMxlFwDGJ08zdNoiEIXL9dNA83UBeA+OaZ4DRYvrkFyNzUO/ r8PGCMAEOqLSlxFZ//GLio084n6WigpHBlz2QbmQ= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 11/24] drivers: hv: dxgkrnl: Creation of hardware queue. Sync object operations to hw queue. Date: Fri, 4 Feb 2022 18:34:09 -0800 Message-Id: <526272291b930e2fc2ccc5d1b9f401586cc88549.1644025661.git.iourit@linux.microsoft.com> X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" - Implement ioctls for creation of the hardware queue objects: LX_DXCREATEHWQUEUE(D3DKMTCreateHardwareQueue), LX_DXDESTROYHWQUEUE(D3DKMTDestroyHardwareQueue) - Implement ioctls for sync object operations in hardware queues: LX_DXSUBMITSIGNALSYNCOBJECTSTOHWQUEUE(D3DKMTSubmitSignalSyncObjectsToHwQueu= e), LX_DXSUBMITWAITFORSYNCOBJECTSTOHWQUEUE (D3DKMTSubmitWaitForSyncObjectsToHwQ= ueue) Hardware queues are used when a compute device supports "hardware scheduling". This means that the compute device itself schedules execution of DMA buffers from hardware queues without CPU intervention. This is as oppose to the "packet scheduling" mode where the software GPU scheduler on the host schedules DMA buffer execution. A hardware queue belongs to a dxgcontext object and has an associated monitored fence object to track execution progress. The monitored fence object has a mapped CPU address to read the fence value by CPU. - LX_DXCREATEHWQUEUE, LX_DXDESTROYHWQUEUE These IOCTLs are used to create/destroy hardware queue objects. - LX_DXSUBMITSIGNALSYNCOBJECTSTOHWQUEUE, LX_DXSUBMITWAITFORSYNCOBJECTSTOHWQUEUE These IOCTLs are used to submit a signal or wait operation for monitored fences to a hardware queue. Monitored fences are used to synchronize execution of commands in queues. Signed-off-by: Iouri Tarassov --- drivers/hv/dxgkrnl/dxgadapter.c | 96 ++++++++++ drivers/hv/dxgkrnl/dxgkrnl.h | 33 ++++ drivers/hv/dxgkrnl/dxgprocess.c | 4 + drivers/hv/dxgkrnl/dxgvmbus.c | 155 +++++++++++++++ drivers/hv/dxgkrnl/ioctl.c | 321 ++++++++++++++++++++++++++++++++ 5 files changed, 609 insertions(+) diff --git a/drivers/hv/dxgkrnl/dxgadapter.c b/drivers/hv/dxgkrnl/dxgadapte= r.c index e32b4bc16ab8..78530b40839f 100644 --- a/drivers/hv/dxgkrnl/dxgadapter.c +++ b/drivers/hv/dxgkrnl/dxgadapter.c @@ -757,6 +757,9 @@ struct dxgcontext *dxgcontext_create(struct dxgdevice *= device) */ void dxgcontext_destroy(struct dxgprocess *process, struct dxgcontext *con= text) { + struct dxghwqueue *hwqueue; + struct dxghwqueue *tmp; + pr_debug("%s %p\n", __func__, context); context->object_state =3D DXGOBJECTSTATE_DESTROYED; if (context->device) { @@ -768,6 +771,10 @@ void dxgcontext_destroy(struct dxgprocess *process, st= ruct dxgcontext *context) dxgdevice_remove_context(context->device, context); kref_put(&context->device->device_kref, dxgdevice_release); } + list_for_each_entry_safe(hwqueue, tmp, &context->hwqueue_list_head, + hwqueue_list_entry) { + dxghwqueue_destroy(process, hwqueue); + } kref_put(&context->context_kref, dxgcontext_release); } =20 @@ -794,6 +801,38 @@ void dxgcontext_release(struct kref *refcount) vfree(context); } =20 +int dxgcontext_add_hwqueue(struct dxgcontext *context, + struct dxghwqueue *hwqueue) +{ + int ret =3D 0; + + down_write(&context->hwqueue_list_lock); + if (dxgcontext_is_active(context)) + list_add_tail(&hwqueue->hwqueue_list_entry, + &context->hwqueue_list_head); + else + ret =3D -ENODEV; + up_write(&context->hwqueue_list_lock); + return ret; +} + +void dxgcontext_remove_hwqueue(struct dxgcontext *context, + struct dxghwqueue *hwqueue) +{ + if (hwqueue->hwqueue_list_entry.next) { + list_del(&hwqueue->hwqueue_list_entry); + hwqueue->hwqueue_list_entry.next =3D NULL; + } +} + +void dxgcontext_remove_hwqueue_safe(struct dxgcontext *context, + struct dxghwqueue *hwqueue) +{ + down_write(&context->hwqueue_list_lock); + dxgcontext_remove_hwqueue(context, hwqueue); + up_write(&context->hwqueue_list_lock); +} + struct dxgallocation *dxgallocation_create(struct dxgprocess *process) { struct dxgallocation *alloc =3D vzalloc(sizeof(struct dxgallocation)); @@ -1173,3 +1212,60 @@ void dxgsyncobject_release(struct kref *refcount) vfree(syncobj->host_event); vfree(syncobj); } + +struct dxghwqueue *dxghwqueue_create(struct dxgcontext *context) +{ + struct dxgprocess *process =3D context->device->process; + struct dxghwqueue *hwqueue =3D vzalloc(sizeof(*hwqueue)); + + if (hwqueue) { + kref_init(&hwqueue->hwqueue_kref); + hwqueue->context =3D context; + hwqueue->process =3D process; + hwqueue->device_handle =3D context->device->handle; + if (dxgcontext_add_hwqueue(context, hwqueue) < 0) { + kref_put(&hwqueue->hwqueue_kref, dxghwqueue_release); + hwqueue =3D NULL; + } else { + kref_get(&context->context_kref); + } + } + return hwqueue; +} + +void dxghwqueue_destroy(struct dxgprocess *process, struct dxghwqueue *hwq= ueue) +{ + pr_debug("%s %p\n", __func__, hwqueue); + hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL); + if (hwqueue->handle.v) { + hmgrtable_free_handle(&process->handle_table, + HMGRENTRY_TYPE_DXGHWQUEUE, + hwqueue->handle); + hwqueue->handle.v =3D 0; + } + if (hwqueue->progress_fence_sync_object.v) { + hmgrtable_free_handle(&process->handle_table, + HMGRENTRY_TYPE_MONITOREDFENCE, + hwqueue->progress_fence_sync_object); + hwqueue->progress_fence_sync_object.v =3D 0; + } + hmgrtable_unlock(&process->handle_table, DXGLOCK_EXCL); + + if (hwqueue->progress_fence_mapped_address) { + dxg_unmap_iospace(hwqueue->progress_fence_mapped_address, + PAGE_SIZE); + hwqueue->progress_fence_mapped_address =3D NULL; + } + dxgcontext_remove_hwqueue_safe(hwqueue->context, hwqueue); + + kref_put(&hwqueue->context->context_kref, dxgcontext_release); + kref_put(&hwqueue->hwqueue_kref, dxghwqueue_release); +} + +void dxghwqueue_release(struct kref *refcount) +{ + struct dxghwqueue *hwqueue; + + hwqueue =3D container_of(refcount, struct dxghwqueue, hwqueue_kref); + vfree(hwqueue); +} diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index 662fa27fd1ed..ac699e27b4cb 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -36,6 +36,7 @@ struct dxgresource; struct dxgsharedresource; struct dxgsyncobject; struct dxgsharedsyncobject; +struct dxghwqueue; =20 #include "misc.h" #include "hmgr.h" @@ -528,8 +529,32 @@ struct dxgcontext *dxgcontext_create(struct dxgdevice = *dev); void dxgcontext_destroy(struct dxgprocess *pr, struct dxgcontext *ctx); void dxgcontext_destroy_safe(struct dxgprocess *pr, struct dxgcontext *ctx= ); void dxgcontext_release(struct kref *refcount); +int dxgcontext_add_hwqueue(struct dxgcontext *ctx, + struct dxghwqueue *hq); +void dxgcontext_remove_hwqueue(struct dxgcontext *ctx, struct dxghwqueue *= hq); +void dxgcontext_remove_hwqueue_safe(struct dxgcontext *ctx, + struct dxghwqueue *hq); bool dxgcontext_is_active(struct dxgcontext *ctx); =20 +/* + * The object represent the execution hardware queue of a device. + */ +struct dxghwqueue { + /* entry in the context hw queue list */ + struct list_head hwqueue_list_entry; + struct kref hwqueue_kref; + struct dxgcontext *context; + struct dxgprocess *process; + struct d3dkmthandle progress_fence_sync_object; + struct d3dkmthandle handle; + struct d3dkmthandle device_handle; + void *progress_fence_mapped_address; +}; + +struct dxghwqueue *dxghwqueue_create(struct dxgcontext *ctx); +void dxghwqueue_destroy(struct dxgprocess *pr, struct dxghwqueue *hq); +void dxghwqueue_release(struct kref *refcount); + /* * A shared resource object is created to track the list of dxgresource ob= jects, * which are opened for the same underlying shared resource. @@ -752,6 +777,14 @@ int dxgvmb_send_wait_sync_object_cpu(struct dxgprocess= *process, d3dkmt_waitforsynchronizationobjectfromcpu *args, u64 cpu_event); +int dxgvmb_send_create_hwqueue(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_createhwqueue *args, + struct d3dkmt_createhwqueue *__user inargs, + struct dxghwqueue *hq); +int dxgvmb_send_destroy_hwqueue(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmthandle handle); int dxgvmb_send_query_adapter_info(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_queryadapterinfo *args); diff --git a/drivers/hv/dxgkrnl/dxgprocess.c b/drivers/hv/dxgkrnl/dxgproces= s.c index 30af930cc8c0..32aad8bfa1a5 100644 --- a/drivers/hv/dxgkrnl/dxgprocess.c +++ b/drivers/hv/dxgkrnl/dxgprocess.c @@ -278,6 +278,10 @@ struct dxgdevice *dxgprocess_device_by_object_handle(s= truct dxgprocess *process, device_handle =3D ((struct dxgcontext *)obj)->device_handle; break; + case HMGRENTRY_TYPE_DXGHWQUEUE: + device_handle =3D + ((struct dxghwqueue *)obj)->device_handle; + break; default: pr_err("invalid handle type: %d\n", t); break; diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index 659afb59b4fd..c2c9f592480a 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -2056,6 +2056,161 @@ int dxgvmb_send_wait_sync_object_gpu(struct dxgproc= ess *process, return ret; } =20 +int dxgvmb_send_create_hwqueue(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_createhwqueue *args, + struct d3dkmt_createhwqueue *__user inargs, + struct dxghwqueue *hwqueue) +{ + struct dxgkvmb_command_createhwqueue *command =3D NULL; + u32 cmd_size =3D sizeof(struct dxgkvmb_command_createhwqueue); + int ret; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + if (args->priv_drv_data_size > DXG_MAX_VM_BUS_PACKET_SIZE) { + pr_err("invalid private driver data size"); + ret =3D -EINVAL; + goto cleanup; + } + + if (args->priv_drv_data_size) + cmd_size +=3D args->priv_drv_data_size - 1; + + ret =3D init_message(&msg, adapter, process, cmd_size); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_CREATEHWQUEUE, + process->host_handle); + command->context =3D args->context; + command->flags =3D args->flags; + command->priv_drv_data_size =3D args->priv_drv_data_size; + if (args->priv_drv_data_size) { + ret =3D copy_from_user(command->priv_drv_data, + args->priv_drv_data, + args->priv_drv_data_size); + if (ret) { + pr_err("%s failed to copy private data", __func__); + ret =3D -EINVAL; + goto cleanup; + } + } + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, + command, cmd_size); + if (ret < 0) + goto cleanup; + + ret =3D ntstatus2int(command->status); + if (ret < 0) { + pr_err("dxgvmb_send_sync_msg failed: %x", command->status.v); + goto cleanup; + } + + ret =3D hmgrtable_assign_handle_safe(&process->handle_table, hwqueue, + HMGRENTRY_TYPE_DXGHWQUEUE, + command->hwqueue); + if (ret < 0) + goto cleanup; + + ret =3D hmgrtable_assign_handle_safe(&process->handle_table, + NULL, + HMGRENTRY_TYPE_MONITOREDFENCE, + command->hwqueue_progress_fence); + if (ret < 0) + goto cleanup; + + hwqueue->handle =3D command->hwqueue; + hwqueue->progress_fence_sync_object =3D command->hwqueue_progress_fence; + + hwqueue->progress_fence_mapped_address =3D + dxg_map_iospace((u64)command->hwqueue_progress_fence_cpuva, + PAGE_SIZE, PROT_READ | PROT_WRITE, true); + if (hwqueue->progress_fence_mapped_address =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + + ret =3D copy_to_user(&inargs->queue, &command->hwqueue, + sizeof(struct d3dkmthandle)); + if (ret < 0) { + pr_err("%s failed to copy hwqueue handle", __func__); + goto cleanup; + } + ret =3D copy_to_user(&inargs->queue_progress_fence, + &command->hwqueue_progress_fence, + sizeof(struct d3dkmthandle)); + if (ret < 0) { + pr_err("%s failed to progress fence", __func__); + goto cleanup; + } + ret =3D copy_to_user(&inargs->queue_progress_fence_cpu_va, + &hwqueue->progress_fence_mapped_address, + sizeof(inargs->queue_progress_fence_cpu_va)); + if (ret < 0) { + pr_err("%s failed to copy fence cpu va", __func__); + goto cleanup; + } + ret =3D copy_to_user(&inargs->queue_progress_fence_gpu_va, + &command->hwqueue_progress_fence_gpuva, + sizeof(u64)); + if (ret < 0) { + pr_err("%s failed to copy fence gpu va", __func__); + goto cleanup; + } + if (args->priv_drv_data_size) { + ret =3D copy_to_user(args->priv_drv_data, + command->priv_drv_data, + args->priv_drv_data_size); + if (ret < 0) + pr_err("%s failed to copy private data", __func__); + } + +cleanup: + if (ret < 0) { + pr_err("%s failed %x", __func__, ret); + if (hwqueue->handle.v) { + hmgrtable_free_handle_safe(&process->handle_table, + HMGRENTRY_TYPE_DXGHWQUEUE, + hwqueue->handle); + hwqueue->handle.v =3D 0; + } + if (command && command->hwqueue.v) + dxgvmb_send_destroy_hwqueue(process, adapter, + command->hwqueue); + } + free_message(&msg, process); + return ret; +} + +int dxgvmb_send_destroy_hwqueue(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmthandle handle) +{ + int ret; + struct dxgkvmb_command_destroyhwqueue *command; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, adapter, process, sizeof(*command)); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_DESTROYHWQUEUE, + process->host_handle); + command->hwqueue =3D handle; + + ret =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, msg.size); +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + int dxgvmb_send_query_adapter_info(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_queryadapterinfo *args) diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index be9d72c4ae4e..111a63235627 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -880,6 +880,160 @@ dxgk_destroy_context(struct dxgprocess *process, void= *__user inargs) return ret; } =20 +static int +dxgk_create_hwqueue(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmt_createhwqueue args; + struct dxgdevice *device =3D NULL; + struct dxgcontext *context =3D NULL; + struct dxgadapter *adapter =3D NULL; + struct dxghwqueue *hwqueue =3D NULL; + int ret; + bool device_lock_acquired =3D false; + + pr_debug("ioctl: %s", __func__); + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + /* + * The call acquires reference on the device. It is safe to access the + * adapter, because the device holds reference on it. + */ + device =3D dxgprocess_device_by_object_handle(process, + HMGRENTRY_TYPE_DXGCONTEXT, + args.context); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgdevice_acquire_lock_shared(device); + if (ret < 0) + goto cleanup; + + device_lock_acquired =3D true; + + hmgrtable_lock(&process->handle_table, DXGLOCK_SHARED); + context =3D hmgrtable_get_object_by_type(&process->handle_table, + HMGRENTRY_TYPE_DXGCONTEXT, + args.context); + hmgrtable_unlock(&process->handle_table, DXGLOCK_SHARED); + + if (context =3D=3D NULL) { + pr_err("Invalid context handle %x", args.context.v); + ret =3D -EINVAL; + goto cleanup; + } + + hwqueue =3D dxghwqueue_create(context); + if (hwqueue =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_create_hwqueue(process, adapter, &args, + inargs, hwqueue); + +cleanup: + + if (ret < 0 && hwqueue) + dxghwqueue_destroy(process, hwqueue); + + if (adapter) + dxgadapter_release_lock_shared(adapter); + + if (device_lock_acquired) + dxgdevice_release_lock_shared(device); + + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int dxgk_destroy_hwqueue(struct dxgprocess *process, + void *__user inargs) +{ + struct d3dkmt_destroyhwqueue args; + int ret; + struct dxgadapter *adapter =3D NULL; + struct dxgdevice *device =3D NULL; + struct dxghwqueue *hwqueue =3D NULL; + struct d3dkmthandle device_handle =3D {}; + + pr_debug("ioctl: %s", __func__); + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL); + hwqueue =3D hmgrtable_get_object_by_type(&process->handle_table, + HMGRENTRY_TYPE_DXGHWQUEUE, + args.queue); + if (hwqueue) { + hmgrtable_free_handle(&process->handle_table, + HMGRENTRY_TYPE_DXGHWQUEUE, args.queue); + hwqueue->handle.v =3D 0; + device_handle =3D hwqueue->device_handle; + } + hmgrtable_unlock(&process->handle_table, DXGLOCK_EXCL); + + if (hwqueue =3D=3D NULL) { + pr_err("invalid hwqueue handle: %x", args.queue.v); + ret =3D -EINVAL; + goto cleanup; + } + + /* + * The call acquires reference on the device. It is safe to access the + * adapter, because the device holds reference on it. + */ + device =3D dxgprocess_device_by_handle(process, device_handle); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_destroy_hwqueue(process, adapter, args.queue); + + dxghwqueue_destroy(process, hwqueue); + +cleanup: + + if (adapter) + dxgadapter_release_lock_shared(adapter); + + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + static int get_standard_alloc_priv_data(struct dxgdevice *device, struct d3dkmt_createstandardallocation *alloc_info, @@ -1601,6 +1755,165 @@ dxgk_destroy_allocation(struct dxgprocess *process,= void *__user inargs) return ret; } =20 +static int +dxgk_submit_signal_to_hwqueue(struct dxgprocess *process, void *__user ina= rgs) +{ + int ret; + struct d3dkmt_submitsignalsyncobjectstohwqueue args; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + struct d3dkmthandle hwqueue =3D {}; + + pr_debug("ioctl: %s", __func__); + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.hwqueue_count > D3DDDI_MAX_BROADCAST_CONTEXT || + args.hwqueue_count =3D=3D 0) { + pr_err("invalid hwqueue count"); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.object_count > D3DDDI_MAX_OBJECT_SIGNALED || + args.object_count =3D=3D 0) { + pr_err("invalid number of syn cobject"); + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D copy_from_user(&hwqueue, args.hwqueues, + sizeof(struct d3dkmthandle)); + if (ret) { + pr_err("%s failed to copy hwqueue handle", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + device =3D dxgprocess_device_by_object_handle(process, + HMGRENTRY_TYPE_DXGHWQUEUE, + hwqueue); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_signal_sync_object(process, adapter, + args.flags, 0, zerohandle, + args.object_count, args.objects, + args.hwqueue_count, args.hwqueues, + args.object_count, + args.fence_values, NULL, + zerohandle); + +cleanup: + + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_submit_wait_to_hwqueue(struct dxgprocess *process, void *__user inarg= s) +{ + struct d3dkmt_submitwaitforsyncobjectstohwqueue args; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + int ret; + struct d3dkmthandle *objects =3D NULL; + u32 object_size; + u64 *fences =3D NULL; + + pr_debug("ioctl: %s", __func__); + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.object_count > D3DDDI_MAX_OBJECT_WAITED_ON || + args.object_count =3D=3D 0) { + ret =3D -EINVAL; + goto cleanup; + } + + object_size =3D sizeof(struct d3dkmthandle) * args.object_count; + objects =3D vzalloc(object_size); + if (objects =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + ret =3D copy_from_user(objects, args.objects, object_size); + if (ret) { + pr_err("%s failed to copy objects", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + object_size =3D sizeof(u64) * args.object_count; + fences =3D vzalloc(object_size); + if (fences =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + ret =3D copy_from_user(fences, args.fence_values, object_size); + if (ret) { + pr_err("%s failed to copy fence values", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + device =3D dxgprocess_device_by_object_handle(process, + HMGRENTRY_TYPE_DXGHWQUEUE, + args.hwqueue); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_wait_sync_object_gpu(process, adapter, + args.hwqueue, args.object_count, + objects, fences, false); + +cleanup: + + if (objects) + vfree(objects); + if (fences) + vfree(fences); + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + static int dxgk_create_sync_object(struct dxgprocess *process, void *__user inargs) { @@ -3271,8 +3584,12 @@ void init_ioctls(void) LX_DXENUMADAPTERS2); SET_IOCTL(/*0x15 */ dxgk_close_adapter, LX_DXCLOSEADAPTER); + SET_IOCTL(/*0x18 */ dxgk_create_hwqueue, + LX_DXCREATEHWQUEUE); SET_IOCTL(/*0x19 */ dxgk_destroy_device, LX_DXDESTROYDEVICE); + SET_IOCTL(/*0x1b */ dxgk_destroy_hwqueue, + LX_DXDESTROYHWQUEUE); SET_IOCTL(/*0x1d */ dxgk_destroy_sync_object, LX_DXDESTROYSYNCHRONIZATIONOBJECT); SET_IOCTL(/*0x31 */ dxgk_signal_sync_object_cpu, @@ -3281,6 +3598,10 @@ void init_ioctls(void) LX_DXSIGNALSYNCHRONIZATIONOBJECTFROMGPU); SET_IOCTL(/*0x33 */ dxgk_signal_sync_object_gpu2, LX_DXSIGNALSYNCHRONIZATIONOBJECTFROMGPU2); + SET_IOCTL(/*0x35 */ dxgk_submit_wait_to_hwqueue, + LX_DXSUBMITWAITFORSYNCOBJECTSTOHWQUEUE); + SET_IOCTL(/*0x36 */ dxgk_submit_signal_to_hwqueue, + LX_DXSUBMITSIGNALSYNCOBJECTSTOHWQUEUE); SET_IOCTL(/*0x3a */ dxgk_wait_sync_object_cpu, LX_DXWAITFORSYNCHRONIZATIONOBJECTFROMCPU); SET_IOCTL(/*0x3b */ dxgk_wait_sync_object_gpu, --=20 2.35.1 From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id E2A16C433EF for ; Sat, 5 Feb 2022 02:35:15 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1379247AbiBECfN (ORCPT ); Fri, 4 Feb 2022 21:35:13 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45108 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1379014AbiBECeZ (ORCPT ); Fri, 4 Feb 2022 21:34:25 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id 712DF20B83F6; Fri, 4 Feb 2022 18:34:25 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com 712DF20B83F6 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028465; bh=IktbIEA3ObkesGE6Ql/GwY3jV7Sno1l+zZcIiFuX6rQ=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=QZPxLR92mcwX5Nn8Z8p5+1SDyOjStWn4Z85Cguv9X+0BBnNpvxHUlFkZuxvGQdT0/ VzuDVvUqpcp4pU8T8x1hf54uIP/1QRJ/BJYJc6yD7CNYarOS7u+36CO7H7dt6Bgx83 Jme0fUPFAnhxXmTw/0qWIznSh9b35OQM5S1BnNuw= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 12/24] drivers: hv: dxgkrnl: Creation of paging queue objects. Date: Fri, 4 Feb 2022 18:34:10 -0800 Message-Id: X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" LX_DXCREATEPAGINGQUEUE (D3DKMTCreatePagingQueue), LX_DXDESTROYPAGINGQUEUE (D3DKMTDestroyPagingQueue) These IOCTLs are used to create/destroy a paging queue. Paging queues contains operations, which handle residency of device accessible allocations. An allocation is resident, when the device has access to it. For example, the allocation resides in local device memory or device page tables point to system memory which is made non-pageable. Signed-off-by: Iouri Tarassov --- drivers/hv/dxgkrnl/dxgadapter.c | 89 +++++++++++++++ drivers/hv/dxgkrnl/dxgkrnl.h | 24 +++++ drivers/hv/dxgkrnl/dxgprocess.c | 4 + drivers/hv/dxgkrnl/dxgvmbus.c | 74 +++++++++++++ drivers/hv/dxgkrnl/ioctl.c | 184 ++++++++++++++++++++++++++++++++ 5 files changed, 375 insertions(+) diff --git a/drivers/hv/dxgkrnl/dxgadapter.c b/drivers/hv/dxgkrnl/dxgadapte= r.c index 78530b40839f..f4e1d402fdbe 100644 --- a/drivers/hv/dxgkrnl/dxgadapter.c +++ b/drivers/hv/dxgkrnl/dxgadapter.c @@ -282,6 +282,7 @@ struct dxgdevice *dxgdevice_create(struct dxgadapter *a= dapter, void dxgdevice_stop(struct dxgdevice *device) { struct dxgallocation *alloc; + struct dxgpagingqueue *pqueue; struct dxgsyncobject *syncobj; =20 pr_debug("%s: %p", __func__, device); @@ -292,6 +293,10 @@ void dxgdevice_stop(struct dxgdevice *device) dxgdevice_release_alloc_list_lock(device); =20 hmgrtable_lock(&device->process->handle_table, DXGLOCK_EXCL); + list_for_each_entry(pqueue, &device->pqueue_list_head, + pqueue_list_entry) { + dxgpagingqueue_stop(pqueue); + } list_for_each_entry(syncobj, &device->syncobj_list_head, syncobj_list_entry) { dxgsyncobject_stop(syncobj); @@ -379,6 +384,17 @@ void dxgdevice_destroy(struct dxgdevice *device) dxgdevice_release_context_list_lock(device); } =20 + { + struct dxgpagingqueue *tmp; + struct dxgpagingqueue *pqueue; + + pr_debug("destroying paging queues\n"); + list_for_each_entry_safe(pqueue, tmp, &device->pqueue_list_head, + pqueue_list_entry) { + dxgpagingqueue_destroy(pqueue); + } + } + /* Guest handles need to be released before the host handles */ hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL); if (device->handle_valid) { @@ -710,6 +726,26 @@ void dxgdevice_release(struct kref *refcount) vfree(device); } =20 +void dxgdevice_add_paging_queue(struct dxgdevice *device, + struct dxgpagingqueue *entry) +{ + dxgdevice_acquire_alloc_list_lock(device); + list_add_tail(&entry->pqueue_list_entry, &device->pqueue_list_head); + dxgdevice_release_alloc_list_lock(device); +} + +void dxgdevice_remove_paging_queue(struct dxgpagingqueue *pqueue) +{ + struct dxgdevice *device =3D pqueue->device; + + dxgdevice_acquire_alloc_list_lock(device); + if (pqueue->pqueue_list_entry.next) { + list_del(&pqueue->pqueue_list_entry); + pqueue->pqueue_list_entry.next =3D NULL; + } + dxgdevice_release_alloc_list_lock(device); +} + void dxgdevice_add_syncobj(struct dxgdevice *device, struct dxgsyncobject *syncobj) { @@ -893,6 +929,59 @@ void dxgallocation_destroy(struct dxgallocation *alloc) vfree(alloc); } =20 +struct dxgpagingqueue *dxgpagingqueue_create(struct dxgdevice *device) +{ + struct dxgpagingqueue *pqueue; + + pqueue =3D vzalloc(sizeof(*pqueue)); + if (pqueue) { + pqueue->device =3D device; + pqueue->process =3D device->process; + pqueue->device_handle =3D device->handle; + dxgdevice_add_paging_queue(device, pqueue); + } + return pqueue; +} + +void dxgpagingqueue_stop(struct dxgpagingqueue *pqueue) +{ + int ret; + + if (pqueue->mapped_address) { + ret =3D dxg_unmap_iospace(pqueue->mapped_address, PAGE_SIZE); + pr_debug("fence is unmapped %d %p", + ret, pqueue->mapped_address); + pqueue->mapped_address =3D NULL; + } +} + +void dxgpagingqueue_destroy(struct dxgpagingqueue *pqueue) +{ + struct dxgprocess *process =3D pqueue->process; + + pr_debug("%s %p %x\n", __func__, pqueue, pqueue->handle.v); + + dxgpagingqueue_stop(pqueue); + + hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL); + if (pqueue->handle.v) { + hmgrtable_free_handle(&process->handle_table, + HMGRENTRY_TYPE_DXGPAGINGQUEUE, + pqueue->handle); + pqueue->handle.v =3D 0; + } + if (pqueue->syncobj_handle.v) { + hmgrtable_free_handle(&process->handle_table, + HMGRENTRY_TYPE_MONITOREDFENCE, + pqueue->syncobj_handle); + pqueue->syncobj_handle.v =3D 0; + } + hmgrtable_unlock(&process->handle_table, DXGLOCK_EXCL); + if (pqueue->device) + dxgdevice_remove_paging_queue(pqueue); + vfree(pqueue); +} + struct dxgprocess_adapter *dxgprocess_adapter_create(struct dxgprocess *pr= ocess, struct dxgadapter *adapter) { diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index ac699e27b4cb..887a23a5bbf8 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -85,6 +85,16 @@ int dxgvmbuschannel_init(struct dxgvmbuschannel *ch, str= uct hv_device *hdev); void dxgvmbuschannel_destroy(struct dxgvmbuschannel *ch); void dxgvmbuschannel_receive(void *ctx); =20 +struct dxgpagingqueue { + struct dxgdevice *device; + struct dxgprocess *process; + struct list_head pqueue_list_entry; + struct d3dkmthandle device_handle; + struct d3dkmthandle handle; + struct d3dkmthandle syncobj_handle; + void *mapped_address; +}; + /* * The structure describes an event, which will be signaled by * a message from host. @@ -108,6 +118,10 @@ struct dxghosteventcpu { bool remove_from_list; }; =20 +struct dxgpagingqueue *dxgpagingqueue_create(struct dxgdevice *device); +void dxgpagingqueue_destroy(struct dxgpagingqueue *pqueue); +void dxgpagingqueue_stop(struct dxgpagingqueue *pqueue); + /* * This is GPU synchronization object, which is used to synchronize execut= ion * between GPU contextx/hardware queues or for tracking GPU execution prog= ress. @@ -499,6 +513,9 @@ void dxgdevice_remove_alloc_safe(struct dxgdevice *dev, struct dxgallocation *a); void dxgdevice_add_resource(struct dxgdevice *dev, struct dxgresource *res= ); void dxgdevice_remove_resource(struct dxgdevice *dev, struct dxgresource *= res); +void dxgdevice_add_paging_queue(struct dxgdevice *dev, + struct dxgpagingqueue *pqueue); +void dxgdevice_remove_paging_queue(struct dxgpagingqueue *pqueue); void dxgdevice_add_syncobj(struct dxgdevice *dev, struct dxgsyncobject *so= ); void dxgdevice_remove_syncobj(struct dxgsyncobject *so); bool dxgdevice_is_active(struct dxgdevice *dev); @@ -736,6 +753,13 @@ dxgvmb_send_create_context(struct dxgadapter *adapter, int dxgvmb_send_destroy_context(struct dxgadapter *adapter, struct dxgprocess *process, struct d3dkmthandle h); +int dxgvmb_send_create_paging_queue(struct dxgprocess *pr, + struct dxgdevice *dev, + struct d3dkmt_createpagingqueue *args, + struct dxgpagingqueue *pq); +int dxgvmb_send_destroy_paging_queue(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmthandle h); int dxgvmb_send_create_allocation(struct dxgprocess *pr, struct dxgdevice = *dev, struct d3dkmt_createallocation *args, struct d3dkmt_createallocation *__user inargs, diff --git a/drivers/hv/dxgkrnl/dxgprocess.c b/drivers/hv/dxgkrnl/dxgproces= s.c index 32aad8bfa1a5..d4199995d279 100644 --- a/drivers/hv/dxgkrnl/dxgprocess.c +++ b/drivers/hv/dxgkrnl/dxgprocess.c @@ -278,6 +278,10 @@ struct dxgdevice *dxgprocess_device_by_object_handle(s= truct dxgprocess *process, device_handle =3D ((struct dxgcontext *)obj)->device_handle; break; + case HMGRENTRY_TYPE_DXGPAGINGQUEUE: + device_handle =3D + ((struct dxgpagingqueue *)obj)->device_handle; + break; case HMGRENTRY_TYPE_DXGHWQUEUE: device_handle =3D ((struct dxghwqueue *)obj)->device_handle; diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index c2c9f592480a..4acfe11d5b90 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -1109,6 +1109,80 @@ int dxgvmb_send_destroy_context(struct dxgadapter *a= dapter, return ret; } =20 +int dxgvmb_send_create_paging_queue(struct dxgprocess *process, + struct dxgdevice *device, + struct d3dkmt_createpagingqueue *args, + struct dxgpagingqueue *pqueue) +{ + struct dxgkvmb_command_createpagingqueue_return result; + struct dxgkvmb_command_createpagingqueue *command; + int ret; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, device->adapter, process, sizeof(*command)); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_CREATEPAGINGQUEUE, + process->host_handle); + command->args =3D *args; + args->paging_queue.v =3D 0; + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, &result, + sizeof(result)); + if (ret < 0) { + pr_err("send_create_paging_queue failed %x", ret); + goto cleanup; + } + + args->paging_queue =3D result.paging_queue; + args->sync_object =3D result.sync_object; + args->fence_cpu_virtual_address =3D + dxg_map_iospace(result.fence_storage_physical_address, PAGE_SIZE, + PROT_READ | PROT_WRITE, true); + if (args->fence_cpu_virtual_address =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + pqueue->mapped_address =3D args->fence_cpu_virtual_address; + pqueue->handle =3D args->paging_queue; + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +int dxgvmb_send_destroy_paging_queue(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmthandle h) +{ + int ret; + struct dxgkvmb_command_destroypagingqueue *command; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, adapter, process, sizeof(*command)); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_DESTROYPAGINGQUEUE, + process->host_handle); + command->paging_queue =3D h; + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, NULL, 0); + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + static int copy_private_data(struct d3dkmt_createallocation *args, struct dxgkvmb_command_createallocation *command, diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index 111a63235627..8992679de5c4 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -1034,6 +1034,186 @@ static int dxgk_destroy_hwqueue(struct dxgprocess *= process, return ret; } =20 +static int +dxgk_create_paging_queue(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmt_createpagingqueue args; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + struct dxgpagingqueue *pqueue =3D NULL; + int ret; + struct d3dkmthandle host_handle =3D {}; + bool device_lock_acquired =3D false; + + pr_debug("ioctl: %s", __func__); + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + /* + * The call acquires reference on the device. It is safe to access the + * adapter, because the device holds reference on it. + */ + device =3D dxgprocess_device_by_handle(process, args.device); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgdevice_acquire_lock_shared(device); + if (ret < 0) + goto cleanup; + + device_lock_acquired =3D true; + adapter =3D device->adapter; + + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + pqueue =3D dxgpagingqueue_create(device); + if (pqueue =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + + ret =3D dxgvmb_send_create_paging_queue(process, device, &args, pqueue); + if (ret >=3D 0) { + host_handle =3D args.paging_queue; + + ret =3D copy_to_user(inargs, &args, sizeof(args)); + if (ret < 0) { + pr_err("%s failed to copy input args", __func__); + goto cleanup; + } + + hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL); + ret =3D hmgrtable_assign_handle(&process->handle_table, pqueue, + HMGRENTRY_TYPE_DXGPAGINGQUEUE, + host_handle); + if (ret >=3D 0) { + pqueue->handle =3D host_handle; + ret =3D hmgrtable_assign_handle(&process->handle_table, + NULL, + HMGRENTRY_TYPE_MONITOREDFENCE, + args.sync_object); + if (ret >=3D 0) + pqueue->syncobj_handle =3D args.sync_object; + } + hmgrtable_unlock(&process->handle_table, DXGLOCK_EXCL); + /* should not fail after this */ + } + +cleanup: + + if (ret < 0) { + if (pqueue) + dxgpagingqueue_destroy(pqueue); + if (host_handle.v) + dxgvmb_send_destroy_paging_queue(process, + adapter, + host_handle); + } + + if (adapter) + dxgadapter_release_lock_shared(adapter); + + if (device) { + if (device_lock_acquired) + dxgdevice_release_lock_shared(device); + kref_put(&device->device_kref, dxgdevice_release); + } + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_destroy_paging_queue(struct dxgprocess *process, void *__user inargs) +{ + struct d3dddi_destroypagingqueue args; + struct dxgpagingqueue *paging_queue =3D NULL; + int ret; + struct d3dkmthandle device_handle =3D {}; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + + pr_debug("ioctl: %s", __func__); + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL); + paging_queue =3D hmgrtable_get_object_by_type(&process->handle_table, + HMGRENTRY_TYPE_DXGPAGINGQUEUE, + args.paging_queue); + if (paging_queue) { + device_handle =3D paging_queue->device_handle; + hmgrtable_free_handle(&process->handle_table, + HMGRENTRY_TYPE_DXGPAGINGQUEUE, + args.paging_queue); + hmgrtable_free_handle(&process->handle_table, + HMGRENTRY_TYPE_MONITOREDFENCE, + paging_queue->syncobj_handle); + paging_queue->syncobj_handle.v =3D 0; + paging_queue->handle.v =3D 0; + } + hmgrtable_unlock(&process->handle_table, DXGLOCK_EXCL); + + /* + * The call acquires reference on the device. It is safe to access the + * adapter, because the device holds reference on it. + */ + if (device_handle.v) + device =3D dxgprocess_device_by_handle(process, device_handle); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgdevice_acquire_lock_shared(device); + if (ret < 0) { + kref_put(&device->device_kref, dxgdevice_release); + device =3D NULL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_destroy_paging_queue(process, adapter, + args.paging_queue); + + dxgpagingqueue_destroy(paging_queue); + +cleanup: + + if (adapter) + dxgadapter_release_lock_shared(adapter); + + if (device) { + dxgdevice_release_lock_shared(device); + kref_put(&device->device_kref, dxgdevice_release); + } + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + static int get_standard_alloc_priv_data(struct dxgdevice *device, struct d3dkmt_createstandardallocation *alloc_info, @@ -3570,6 +3750,8 @@ void init_ioctls(void) LX_DXDESTROYCONTEXT); SET_IOCTL(/*0x6 */ dxgk_create_allocation, LX_DXCREATEALLOCATION); + SET_IOCTL(/*0x7 */ dxgk_create_paging_queue, + LX_DXCREATEPAGINGQUEUE); SET_IOCTL(/*0x9 */ dxgk_query_adapter_info, LX_DXQUERYADAPTERINFO); SET_IOCTL(/*0x10 */ dxgk_create_sync_object, @@ -3590,6 +3772,8 @@ void init_ioctls(void) LX_DXDESTROYDEVICE); SET_IOCTL(/*0x1b */ dxgk_destroy_hwqueue, LX_DXDESTROYHWQUEUE); + SET_IOCTL(/*0x1c */ dxgk_destroy_paging_queue, + LX_DXDESTROYPAGINGQUEUE); SET_IOCTL(/*0x1d */ dxgk_destroy_sync_object, LX_DXDESTROYSYNCHRONIZATIONOBJECT); SET_IOCTL(/*0x31 */ dxgk_signal_sync_object_cpu, --=20 2.35.1 From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id EEA81C433EF for ; Sat, 5 Feb 2022 02:35:20 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1379262AbiBECfS (ORCPT ); Fri, 4 Feb 2022 21:35:18 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45084 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1379015AbiBECeZ (ORCPT ); Fri, 4 Feb 2022 21:34:25 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id 9A4E720B83F8; Fri, 4 Feb 2022 18:34:25 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com 9A4E720B83F8 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028465; bh=RojMZ2F7nOOds6BfWkZDgCGSeVXZSAnagFLgTkdvJ18=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=k4oasDoZG+0o0mnbgxd92JQbI3mGXUGTCPunHAAV8wkkbVeUkbsmhHuNRfV30CW+N Bmt29nkmNUN3dbXA436HfudNmqDeQPKa4f7LYs5y3+UYVMQr3tg0HhtYloD4bvBBMY 0SlQ2/1LF+0xTgRUUhpjVMHjYwOQu2gZLxR8SGMY= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 13/24] drivers: hv: dxgkrnl: Submit execution commands to the compute device Date: Fri, 4 Feb 2022 18:34:11 -0800 Message-Id: X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" - LX_DXSUBMITCOMMAND(D3DKMTSubmitCommand) The IOCTL is used to submit a command buffer to the device, working in the software packet scheduling mode. - LX_DXSUBMITCOMMANDTOHWQUEUE(D3DKMTSubmitCommandToHwQueue) The IOCTL is used to submit a command buffer to the device, working in the hardware scheduling mode. Both IOCTLs are asynchronous to improve performance as these are high frequency operations. Signed-off-by: Iouri Tarassov --- drivers/hv/dxgkrnl/dxgkrnl.h | 6 ++ drivers/hv/dxgkrnl/dxgvmbus.c | 111 +++++++++++++++++++++++++++++ drivers/hv/dxgkrnl/ioctl.c | 129 ++++++++++++++++++++++++++++++++++ 3 files changed, 246 insertions(+) diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index 887a23a5bbf8..cb533d5fe797 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -770,6 +770,9 @@ int dxgvmb_send_create_allocation(struct dxgprocess *pr= , struct dxgdevice *dev, int dxgvmb_send_destroy_allocation(struct dxgprocess *pr, struct dxgdevice= *dev, struct d3dkmt_destroyallocation2 *args, struct d3dkmthandle *alloc_handles); +int dxgvmb_send_submit_command(struct dxgprocess *pr, + struct dxgadapter *adapter, + struct d3dkmt_submitcommand *args); int dxgvmb_send_create_sync_object(struct dxgprocess *pr, struct dxgadapter *adapter, struct d3dkmt_createsynchronizationobject2 @@ -812,6 +815,9 @@ int dxgvmb_send_destroy_hwqueue(struct dxgprocess *proc= ess, int dxgvmb_send_query_adapter_info(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_queryadapterinfo *args); +int dxgvmb_send_submit_command_hwqueue(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_submitcommandtohwqueue *a); int dxgvmb_send_open_sync_object_nt(struct dxgprocess *process, struct dxgvmbuschannel *channel, struct d3dkmt_opensyncobjectfromnthandle2 diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index 4acfe11d5b90..b474c63df653 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -1848,6 +1848,60 @@ int dxgvmb_send_get_stdalloc_data(struct dxgdevice *= device, return ret; } =20 +int dxgvmb_send_submit_command(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_submitcommand *args) +{ + int ret; + u32 cmd_size; + struct dxgkvmb_command_submitcommand *command; + u32 hbufsize =3D args->num_history_buffers * sizeof(struct d3dkmthandle); + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + cmd_size =3D sizeof(struct dxgkvmb_command_submitcommand) + + hbufsize + args->priv_drv_data_size; + + ret =3D init_message(&msg, adapter, process, cmd_size); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + ret =3D copy_from_user(&command[1], args->history_buffer_array, + hbufsize); + if (ret) { + pr_err("%s failed to copy history buffer", __func__); + ret =3D -EINVAL; + goto cleanup; + } + ret =3D copy_from_user((u8 *) &command[1] + hbufsize, + args->priv_drv_data, args->priv_drv_data_size); + if (ret) { + pr_err("%s failed to copy history priv data", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_SUBMITCOMMAND, + process->host_handle); + command->args =3D *args; + + if (dxgglobal->async_msg_enabled) { + command->hdr.async_msg =3D 1; + ret =3D dxgvmb_send_async_msg(msg.channel, msg.hdr, msg.size); + } else { + ret =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, + msg.size); + } + +cleanup: + + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + static void set_result(struct d3dkmt_createsynchronizationobject2 *args, u64 fence_gpu_va, u8 *va) { @@ -2366,3 +2420,60 @@ int dxgvmb_send_query_adapter_info(struct dxgprocess= *process, pr_debug("err: %s %d", __func__, ret); return ret; } + +int dxgvmb_send_submit_command_hwqueue(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_submitcommandtohwqueue + *args) +{ + int ret =3D -EINVAL; + u32 cmd_size; + struct dxgkvmb_command_submitcommandtohwqueue *command; + u32 primaries_size =3D args->num_primaries * sizeof(struct d3dkmthandle); + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + cmd_size =3D sizeof(*command) + args->priv_drv_data_size + primaries_size; + ret =3D init_message(&msg, adapter, process, cmd_size); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + if (primaries_size) { + ret =3D copy_from_user(&command[1], args->written_primaries, + primaries_size); + if (ret) { + pr_err("%s failed to copy primaries handles", __func__); + ret =3D -EINVAL; + goto cleanup; + } + } + if (args->priv_drv_data_size) { + ret =3D copy_from_user((char *)&command[1] + primaries_size, + args->priv_drv_data, + args->priv_drv_data_size); + if (ret) { + pr_err("%s failed to copy primaries data", __func__); + ret =3D -EINVAL; + goto cleanup; + } + } + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_SUBMITCOMMANDTOHWQUEUE, + process->host_handle); + command->args =3D *args; + + if (dxgglobal->async_msg_enabled) { + command->hdr.async_msg =3D 1; + ret =3D dxgvmb_send_async_msg(msg.channel, msg.hdr, msg.size); + } else { + ret =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, + msg.size); + } + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index 8992679de5c4..38d28d1792df 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -1935,6 +1935,131 @@ dxgk_destroy_allocation(struct dxgprocess *process,= void *__user inargs) return ret; } =20 +static int +dxgk_submit_command(struct dxgprocess *process, void *__user inargs) +{ + int ret; + struct d3dkmt_submitcommand args; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + + pr_debug("ioctl: %s", __func__); + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.broadcast_context_count > D3DDDI_MAX_BROADCAST_CONTEXT || + args.broadcast_context_count =3D=3D 0) { + pr_err("invalid number of contexts"); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.priv_drv_data_size > DXG_MAX_VM_BUS_PACKET_SIZE) { + pr_err("invalid private data size"); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.num_history_buffers > 1024) { + pr_err("invalid number of history buffers"); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.num_primaries > DXG_MAX_VM_BUS_PACKET_SIZE) { + pr_err("invalid number of primaries"); + ret =3D -EINVAL; + goto cleanup; + } + + device =3D dxgprocess_device_by_object_handle(process, + HMGRENTRY_TYPE_DXGCONTEXT, + args.broadcast_context[0]); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_submit_command(process, adapter, &args); + +cleanup: + + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_submit_command_to_hwqueue(struct dxgprocess *process, void *__user in= args) +{ + int ret; + struct d3dkmt_submitcommandtohwqueue args; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + + pr_debug("ioctl: %s", __func__); + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.priv_drv_data_size > DXG_MAX_VM_BUS_PACKET_SIZE) { + pr_err("invalid private data size"); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.num_primaries > DXG_MAX_VM_BUS_PACKET_SIZE) { + pr_err("invalid number of primaries"); + ret =3D -EINVAL; + goto cleanup; + } + + device =3D dxgprocess_device_by_object_handle(process, + HMGRENTRY_TYPE_DXGHWQUEUE, + args.hwqueue); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_submit_command_hwqueue(process, adapter, &args); + +cleanup: + + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + static int dxgk_submit_signal_to_hwqueue(struct dxgprocess *process, void *__user ina= rgs) { @@ -3754,6 +3879,8 @@ void init_ioctls(void) LX_DXCREATEPAGINGQUEUE); SET_IOCTL(/*0x9 */ dxgk_query_adapter_info, LX_DXQUERYADAPTERINFO); + SET_IOCTL(/*0xf */ dxgk_submit_command, + LX_DXSUBMITCOMMAND); SET_IOCTL(/*0x10 */ dxgk_create_sync_object, LX_DXCREATESYNCHRONIZATIONOBJECT); SET_IOCTL(/*0x11 */ dxgk_signal_sync_object, @@ -3782,6 +3909,8 @@ void init_ioctls(void) LX_DXSIGNALSYNCHRONIZATIONOBJECTFROMGPU); SET_IOCTL(/*0x33 */ dxgk_signal_sync_object_gpu2, LX_DXSIGNALSYNCHRONIZATIONOBJECTFROMGPU2); + SET_IOCTL(/*0x34 */ dxgk_submit_command_to_hwqueue, + LX_DXSUBMITCOMMANDTOHWQUEUE); SET_IOCTL(/*0x35 */ dxgk_submit_wait_to_hwqueue, LX_DXSUBMITWAITFORSYNCOBJECTSTOHWQUEUE); SET_IOCTL(/*0x36 */ dxgk_submit_signal_to_hwqueue, --=20 2.35.1 From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id A1D11C433EF for ; Sat, 5 Feb 2022 02:35:26 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1379294AbiBECfX (ORCPT ); Fri, 4 Feb 2022 21:35:23 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45114 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1379002AbiBECe0 (ORCPT ); Fri, 4 Feb 2022 21:34:26 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id CB25420B83FA; Fri, 4 Feb 2022 18:34:25 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com CB25420B83FA DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028465; bh=LlJklw6/Tpsj/joypGQrEMqpv8SvTVlBa+qVzpGChj4=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=rm+kSceuks2ijkQZjjuXoi7LWK0TmBBYFuXYFpdWgTZVylMqgDPnG1QiTckAT+qxJ cAILck8MaHV4BaTTz+h8OJewJ3aGIEZWA/Ops7AlMha4GfoQ83aoT+RJi7GCp+SBVm EHYHP4MFIGh/1MTxc7fNTRBcWzg9SPtAyu6Iujnk= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 14/24] drivers: hv: dxgkrnl: Implement LX_DXSHAREOBJECTWITHHOST ioctl Date: Fri, 4 Feb 2022 18:34:12 -0800 Message-Id: X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" - Implement the LX_DXSHAREOBJECTWITHHOST (D3DKMTShareObjectWithHost) IOCTL. This IOCTL is used to create an NT handle on the host for the given shared object. The NT handle is returned to the caller. The caller (usually a compositor) could share the NT handle with the host client, which renders the guest window. The host client can open the shared resource using the NT handle. This way the guest and the host have access to the same object (for example, dxgresource or dxgsyncobject). - Fix incorrect handling of error results from copy_from_user(). Signed-off-by: Iouri Tarassov --- drivers/hv/dxgkrnl/dxgkrnl.h | 2 ++ drivers/hv/dxgkrnl/dxgvmbus.c | 60 ++++++++++++++++++++++++++++--- drivers/hv/dxgkrnl/dxgvmbus.h | 14 ++++++++ drivers/hv/dxgkrnl/ioctl.c | 68 ++++++++++++++++++++++++++++------- 4 files changed, 127 insertions(+), 17 deletions(-) diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index cb533d5fe797..e1c718e7b8eb 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -846,6 +846,8 @@ int dxgvmb_send_get_stdalloc_data(struct dxgdevice *dev= ice, int dxgvmb_send_async_msg(struct dxgvmbuschannel *channel, void *command, u32 cmd_size); +int dxgvmb_send_share_object_with_host(struct dxgprocess *process, + struct d3dkmt_shareobjectwithhost *args); =20 void signal_host_cpu_event(struct dxghostevent *eventhdr); int ntstatus2int(struct ntstatus status); diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index b474c63df653..8ad290b2b482 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -863,6 +863,50 @@ int dxgvmb_send_destroy_sync_object(struct dxgprocess = *process, return ret; } =20 +int dxgvmb_send_share_object_with_host(struct dxgprocess *process, + struct d3dkmt_shareobjectwithhost *args) +{ + struct dxgkvmb_command_shareobjectwithhost *command; + struct dxgkvmb_command_shareobjectwithhost_return result =3D {}; + int ret; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, NULL, process, sizeof(*command)); + if (ret) + return ret; + command =3D (void *)msg.msg; + + ret =3D dxgglobal_acquire_channel_lock(); + if (ret < 0) + goto cleanup; + + command_vm_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_SHAREOBJECTWITHHOST, + process->host_handle); + command->device_handle =3D args->device_handle; + command->object_handle =3D args->object_handle; + + ret =3D dxgvmb_send_sync_msg(dxgglobal_get_dxgvmbuschannel(), + msg.hdr, msg.size, &result, sizeof(result)); + + dxgglobal_release_channel_lock(); + + if (ret || !NT_SUCCESS(result.status)) { + if (ret =3D=3D 0) + ret =3D ntstatus2int(result.status); + pr_err("DXGK_VMBCOMMAND_SHAREOBJECTWITHHOST failed: %d %x", + ret, result.status.v); + goto cleanup; + } + args->object_vail_nt_handle =3D result.vail_nt_handle; + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + /* * Virtual GPU messages to the host */ @@ -2263,37 +2307,43 @@ int dxgvmb_send_create_hwqueue(struct dxgprocess *p= rocess, =20 ret =3D copy_to_user(&inargs->queue, &command->hwqueue, sizeof(struct d3dkmthandle)); - if (ret < 0) { + if (ret) { pr_err("%s failed to copy hwqueue handle", __func__); + ret =3D -EINVAL; goto cleanup; } ret =3D copy_to_user(&inargs->queue_progress_fence, &command->hwqueue_progress_fence, sizeof(struct d3dkmthandle)); - if (ret < 0) { + if (ret) { pr_err("%s failed to progress fence", __func__); + ret =3D -EINVAL; goto cleanup; } ret =3D copy_to_user(&inargs->queue_progress_fence_cpu_va, &hwqueue->progress_fence_mapped_address, sizeof(inargs->queue_progress_fence_cpu_va)); - if (ret < 0) { + if (ret) { pr_err("%s failed to copy fence cpu va", __func__); + ret =3D -EINVAL; goto cleanup; } ret =3D copy_to_user(&inargs->queue_progress_fence_gpu_va, &command->hwqueue_progress_fence_gpuva, sizeof(u64)); - if (ret < 0) { + if (ret) { pr_err("%s failed to copy fence gpu va", __func__); + ret =3D -EINVAL; goto cleanup; } if (args->priv_drv_data_size) { ret =3D copy_to_user(args->priv_drv_data, command->priv_drv_data, args->priv_drv_data_size); - if (ret < 0) + if (ret) { pr_err("%s failed to copy private data", __func__); + ret =3D -EINVAL; + } } =20 cleanup: diff --git a/drivers/hv/dxgkrnl/dxgvmbus.h b/drivers/hv/dxgkrnl/dxgvmbus.h index 5b455618a2a2..b1434742fa80 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.h +++ b/drivers/hv/dxgkrnl/dxgvmbus.h @@ -63,6 +63,7 @@ enum dxgkvmb_commandtype_global { DXGK_VMBCOMMAND_QUERYETWSESSION =3D 1009, DXGK_VMBCOMMAND_SETIOSPACEREGION =3D 1010, DXGK_VMBCOMMAND_COMPLETETRANSACTION =3D 1011, + DXGK_VMBCOMMAND_SHAREOBJECTWITHHOST =3D 1021, DXGK_VMBCOMMAND_INVALID_VM_TO_HOST }; =20 @@ -848,6 +849,19 @@ struct dxgkvmb_command_getdevicestate_return { struct ntstatus status; }; =20 +struct dxgkvmb_command_shareobjectwithhost { + struct dxgkvmb_command_vm_to_host hdr; + struct d3dkmthandle device_handle; + struct d3dkmthandle object_handle; + u64 reserved; +}; + +struct dxgkvmb_command_shareobjectwithhost_return { + struct ntstatus status; + u32 alignment; + u64 vail_nt_handle; +}; + int dxgvmb_send_sync_msg(struct dxgvmbuschannel *channel, void *command, u32 command_size, void *result, diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index 38d28d1792df..71ba7b75c60f 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -1088,8 +1088,9 @@ dxgk_create_paging_queue(struct dxgprocess *process, = void *__user inargs) host_handle =3D args.paging_queue; =20 ret =3D copy_to_user(inargs, &args, sizeof(args)); - if (ret < 0) { + if (ret) { pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; goto cleanup; } =20 @@ -2494,8 +2495,9 @@ dxgk_open_sync_object_nt(struct dxgprocess *process, = void *__user inargs) goto cleanup; =20 ret =3D copy_to_user(inargs, &args, sizeof(args)); - if (ret >=3D 0) + if (ret =3D=3D 0) goto success; + ret =3D -EINVAL; pr_err("%s failed to copy output args", __func__); =20 cleanup: @@ -3405,8 +3407,10 @@ dxgk_share_objects(struct dxgprocess *process, void = *__user inargs) tmp =3D (u64) object_fd; =20 ret =3D copy_to_user(args.shared_handle, &tmp, sizeof(u64)); - if (ret < 0) + if (ret) { pr_err("%s failed to copy shared handle", __func__); + ret =3D -EINVAL; + } =20 cleanup: if (ret < 0) { @@ -3436,8 +3440,6 @@ dxgk_query_resource_info_nt(struct dxgprocess *proces= s, void *__user inargs) struct dxgsharedresource *shared_resource =3D NULL; struct file *file =3D NULL; =20 - pr_debug("ioctl: %s", __func__); - ret =3D copy_from_user(&args, inargs, sizeof(args)); if (ret) { pr_err("%s failed to copy input args", __func__); @@ -3492,8 +3494,10 @@ dxgk_query_resource_info_nt(struct dxgprocess *proce= ss, void *__user inargs) shared_resource->alloc_private_data_size; =20 ret =3D copy_to_user(inargs, &args, sizeof(args)); - if (ret < 0) + if (ret) { pr_err("%s failed to copy output args", __func__); + ret =3D -EINVAL; + } =20 cleanup: =20 @@ -3554,8 +3558,9 @@ assign_resource_handles(struct dxgprocess *process, ret =3D copy_to_user(&args->open_alloc_info[i], &open_alloc_info, sizeof(open_alloc_info)); - if (ret < 0) { + if (ret) { pr_err("%s failed to copy alloc info", __func__); + ret =3D -EINVAL; goto cleanup; } } @@ -3705,8 +3710,9 @@ open_resource(struct dxgprocess *process, ret =3D copy_to_user(args->private_runtime_data, shared_resource->runtime_private_data, shared_resource->runtime_private_data_size); - if (ret < 0) { + if (ret) { pr_err("%s failed to copy runtime data", __func__); + ret =3D -EINVAL; goto cleanup; } } @@ -3715,8 +3721,9 @@ open_resource(struct dxgprocess *process, ret =3D copy_to_user(args->resource_priv_drv_data, shared_resource->resource_private_data, shared_resource->resource_private_data_size); - if (ret < 0) { + if (ret) { pr_err("%s failed to copy resource data", __func__); + ret =3D -EINVAL; goto cleanup; } } @@ -3725,8 +3732,9 @@ open_resource(struct dxgprocess *process, ret =3D copy_to_user(args->total_priv_drv_data, shared_resource->alloc_private_data, shared_resource->alloc_private_data_size); - if (ret < 0) { + if (ret) { pr_err("%s failed to copy alloc data", __func__); + ret =3D -EINVAL; goto cleanup; } } @@ -3739,15 +3747,18 @@ open_resource(struct dxgprocess *process, =20 ret =3D copy_to_user(res_out, &resource_handle, sizeof(struct d3dkmthandle)); - if (ret < 0) { + if (ret) { pr_err("%s failed to copy resource handle to user", __func__); + ret =3D -EINVAL; goto cleanup; } =20 ret =3D copy_to_user(total_driver_data_size_out, &args->total_priv_drv_data_size, sizeof(u32)); - if (ret < 0) + if (ret) { pr_err("%s failed to copy total driver data size", __func__); + ret =3D -EINVAL; + } =20 cleanup: =20 @@ -3809,6 +3820,37 @@ dxgk_open_resource_nt(struct dxgprocess *process, return ret; } =20 +static int +dxgk_share_object_with_host(struct dxgprocess *process, void *__user inarg= s) +{ + struct d3dkmt_shareobjectwithhost args; + int ret; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgvmb_send_share_object_with_host(process, &args); + if (ret) { + pr_err("dxgvmb_send_share_object_with_host dailed"); + goto cleanup; + } + + ret =3D copy_to_user(inargs, &args, sizeof(args)); + if (ret) { + pr_err("%s failed to copy data to user", __func__); + ret =3D -EINVAL; + } + +cleanup: + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + /* * IOCTL processing * The driver IOCTLs return @@ -3929,4 +3971,6 @@ void init_ioctls(void) LX_DXQUERYRESOURCEINFOFROMNTHANDLE); SET_IOCTL(/*0x42 */ dxgk_open_resource_nt, LX_DXOPENRESOURCEFROMNTHANDLE); + SET_IOCTL(/*0x44 */ dxgk_share_object_with_host, + LX_DXSHAREOBJECTWITHHOST); } --=20 2.35.1 From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 2F820C433EF for ; Sat, 5 Feb 2022 02:35:34 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1379117AbiBECfd (ORCPT ); Fri, 4 Feb 2022 21:35:33 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45090 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1379017AbiBECe0 (ORCPT ); Fri, 4 Feb 2022 21:34:26 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id 008FC20B83FE; Fri, 4 Feb 2022 18:34:25 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com 008FC20B83FE DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028466; bh=d18zkhHC6TSDSRAJZCBoNwae432DSb+vi0iUQIZ2+2o=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=Qm81vx8xLDieSop1ezQt+3SgI07jVKH4zxif5JK2xTK+ziMrtE2uG6Jeh6lhTC639 ovtcZphfqzJQ8B1bF0eRgzcxF2KMEgUn54fqH+krZG56vKPuM7LA0znoHB/EpfASBw qEgYWhIjEbkMLBSAme7BaETXPFv1mwz/aAO7E++w= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 15/24] drivers: hv: dxgkrnl: IOCTL to get the dxgdevice state LX_DXGETDEVICESTATE Date: Fri, 4 Feb 2022 18:34:13 -0800 Message-Id: <611d92448a015fa54dbd839147ef696ab1f28328.1644025661.git.iourit@linux.microsoft.com> X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" LX_DXGETDEVICESTATE(D3DKMTGetDeviceState) The IOCTL is used to query the state of the given dxgdevice object (active, error, etc.). A call to the dxgdevice execution state could be high frequency. The followin method is used to avoid sending a synchronous VM bus message to the host for every call: - When a dxgdevice is created, a pointer to dxgglobal->device_state_counter is sent to the host - Every time the device state on the host is changed, the host will send an asynchronous message to the guest (DXGK_VMBCOMMAND_SETGUESTDATA) and the guest will increment the device_state_counter counter. - the dxgdevice object has execution_state_counter counter, which is equal to dxgglobal->device_state_counte at the time when LX_DXGETDEVICESTATE was last called. - if execution_state_counter is different from evice_state_counter, the dxgk_vmbcommand_getdevicestate VM bus message is sent to the host. Otherwise, the cached value is returned. Signed-off-by: Iouri Tarassov --- drivers/hv/dxgkrnl/dxgkrnl.h | 11 ++++++ drivers/hv/dxgkrnl/dxgvmbus.c | 66 +++++++++++++++++++++++++++++++++++ drivers/hv/dxgkrnl/ioctl.c | 66 +++++++++++++++++++++++++++++++++++ 3 files changed, 143 insertions(+) diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index e1c718e7b8eb..892c95a11368 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -249,12 +249,18 @@ void dxgsyncobject_destroy(struct dxgprocess *process, void dxgsyncobject_stop(struct dxgsyncobject *syncobj); void dxgsyncobject_release(struct kref *refcount); =20 +/* + * device_state_counter - incremented every time the execition state of + * a DXGDEVICE is changed in the host. Used to optimize access to the + * device execution state. + */ struct dxgglobal { struct dxgvmbuschannel channel; struct delayed_work dwork; struct hv_device *hdev; u32 num_adapters; u32 vmbus_ver; /* Interface version */ + atomic_t device_state_counter; struct resource *mem; u64 mmiospace_base; u64 mmiospace_size; @@ -495,6 +501,7 @@ struct dxgdevice { struct list_head syncobj_list_head; struct d3dkmthandle handle; enum d3dkmt_deviceexecution_state execution_state; + int execution_state_counter; u32 handle_valid; }; =20 @@ -823,6 +830,10 @@ int dxgvmb_send_open_sync_object_nt(struct dxgprocess = *process, struct d3dkmt_opensyncobjectfromnthandle2 *args, struct dxgsyncobject *syncobj); +int dxgvmb_send_get_device_state(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_getdevicestate *args, + struct d3dkmt_getdevicestate *__user inargs); int dxgvmb_send_create_nt_shared_object(struct dxgprocess *process, struct d3dkmthandle object, struct d3dkmthandle *shared_handle); diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index 8ad290b2b482..b5225756ee6e 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -275,6 +275,23 @@ static void command_vm_to_host_init1(struct dxgkvmb_co= mmand_vm_to_host *command, command->channel_type =3D DXGKVMB_VM_TO_HOST; } =20 +static void set_guest_data(struct dxgkvmb_command_host_to_vm *packet, + u32 packet_length) +{ + struct dxgkvmb_command_setguestdata *command =3D (void *)packet; + + pr_debug("%s: %d %d %p %p", __func__, + command->data_type, + command->data32, + command->guest_pointer, + &dxgglobal->device_state_counter); + if (command->data_type =3D=3D SETGUESTDATA_DATATYPE_DWORD && + command->guest_pointer =3D=3D &dxgglobal->device_state_counter && + command->data32 !=3D 0) { + atomic_inc(&dxgglobal->device_state_counter); + } +} + static void signal_guest_event(struct dxgkvmb_command_host_to_vm *packet, u32 packet_length) { @@ -305,6 +322,9 @@ static void process_inband_packet(struct dxgvmbuschanne= l *channel, pr_debug("global packet %d", packet->command_type); switch (packet->command_type) { + case DXGK_VMBCOMMAND_SETGUESTDATA: + set_guest_data(packet, packet_length); + break; case DXGK_VMBCOMMAND_SIGNALGUESTEVENT: case DXGK_VMBCOMMAND_SIGNALGUESTEVENTPASSIVE: signal_guest_event(packet, packet_length); @@ -1017,6 +1037,7 @@ struct d3dkmthandle dxgvmb_send_create_device(struct = dxgadapter *adapter, command_vgpu_to_host_init2(&command->hdr, DXGK_VMBCOMMAND_CREATEDEVICE, process->host_handle); command->flags =3D args->flags; + command->error_code =3D &dxgglobal->device_state_counter; =20 ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, &result, sizeof(result)); @@ -1753,6 +1774,51 @@ int dxgvmb_send_destroy_allocation(struct dxgprocess= *process, return ret; } =20 +int dxgvmb_send_get_device_state(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_getdevicestate *args, + struct d3dkmt_getdevicestate *__user output) +{ + int ret; + struct dxgkvmb_command_getdevicestate *command; + struct dxgkvmb_command_getdevicestate_return result =3D { }; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, adapter, process, sizeof(*command)); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_GETDEVICESTATE, + process->host_handle); + command->args =3D *args; + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, + &result, sizeof(result)); + if (ret < 0) + goto cleanup; + + ret =3D ntstatus2int(result.status); + if (ret < 0) + goto cleanup; + + ret =3D copy_to_user(output, &result.args, sizeof(result.args)); + if (ret) { + pr_err("%s failed to copy output args", __func__); + ret =3D -EINVAL; + } + + if (args->state_type =3D=3D _D3DKMT_DEVICESTATE_EXECUTION) + args->execution_state =3D result.args.execution_state; + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + int dxgvmb_send_open_resource(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmthandle device, diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index 71ba7b75c60f..bb6eab08898f 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -3180,6 +3180,70 @@ dxgk_wait_sync_object_gpu(struct dxgprocess *process= , void *__user inargs) return ret; } =20 +static int +dxgk_get_device_state(struct dxgprocess *process, void *__user inargs) +{ + int ret; + struct d3dkmt_getdevicestate args; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + int global_device_state_counter =3D 0; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + device =3D dxgprocess_device_by_handle(process, args.device); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + if (args.state_type =3D=3D _D3DKMT_DEVICESTATE_EXECUTION) { + global_device_state_counter =3D + atomic_read(&dxgglobal->device_state_counter); + if (device->execution_state_counter =3D=3D + global_device_state_counter) { + args.execution_state =3D device->execution_state; + ret =3D copy_to_user(inargs, &args, sizeof(args)); + if (ret) { + pr_err("%s failed to copy args to user", + __func__); + ret =3D -EINVAL; + } + goto cleanup; + } + } + + ret =3D dxgvmb_send_get_device_state(process, adapter, &args, inargs); + + if (ret =3D=3D 0 && args.state_type =3D=3D _D3DKMT_DEVICESTATE_EXECUTION)= { + device->execution_state =3D args.execution_state; + device->execution_state_counter =3D global_device_state_counter; + } + +cleanup: + + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + if (ret < 0) + pr_err("%s failed %x", __func__, ret); + + return ret; +} + static int dxgsharedsyncobj_get_host_nt_handle(struct dxgsharedsyncobject *syncobj, struct dxgprocess *process, @@ -3921,6 +3985,8 @@ void init_ioctls(void) LX_DXCREATEPAGINGQUEUE); SET_IOCTL(/*0x9 */ dxgk_query_adapter_info, LX_DXQUERYADAPTERINFO); + SET_IOCTL(/*0xe */ dxgk_get_device_state, + LX_DXGETDEVICESTATE); SET_IOCTL(/*0xf */ dxgk_submit_command, LX_DXSUBMITCOMMAND); SET_IOCTL(/*0x10 */ dxgk_create_sync_object, --=20 2.35.1 From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 979BEC433F5 for ; Sat, 5 Feb 2022 02:35:29 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1379120AbiBECf2 (ORCPT ); Fri, 4 Feb 2022 21:35:28 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45108 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1379019AbiBECe0 (ORCPT ); Fri, 4 Feb 2022 21:34:26 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id 2C16120B8760; Fri, 4 Feb 2022 18:34:26 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com 2C16120B8760 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028466; bh=LHFlARVfrvYGBVgoaLmkeoVY7a4xLhgT894jLDs/UwY=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=ReV1Mzh5MpRMoF23uaCSXE/x330Bjlzo59CZclBTSeCGm4xG9OICrG59jD09NRdGQ 9stM500e2wVqPPSYXwjMqr5bnCIrzJPos7riO8RJ4jMGookS0QR+dH1NtxF+8is2/1 yiEG5xX9k66zEe/SVEYp7YNLj7dZp+VQBn9NutbI= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 16/24] drivers: hv: dxgkrnl: Mmap(unmap) CPU address to device allocation: LX_DXLOCK2, LX_DXUNLOCK2 Date: Fri, 4 Feb 2022 18:34:14 -0800 Message-Id: <6f9cd2927847c32e3fe7fa45290e9c9d40787758.1644025661.git.iourit@linux.microsoft.com> X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" - LX_DXLOCK2(D3DKMTLock2) maps a CPU virtual address to a compute device allocation. The allocation could be located in system memory or local device memory. When the device allocation is created from the guest system memory (existing sysmem allocation), the allocation CPU address is known and is returned to the caller. For other CPU visible allocations the code flow is the following: 1. A VM bus message is sent to the host 2. The host allocates a portion of the guest IO space and maps it to the allocation backing store. The IO space address is returned back to the guest. 3. The guest allocates a CPU virtual address and maps it to the IO space (dxg_map_iospace). 4. The CPU VA is returned back to the caller cpu_address_mapped and cpu_address_refcount are used to track how many times an allocation was mapped. - LX_DXUNLOCK2(D3DKMTUnlock2) unmaps a CPU virtual address from a compute device allocation. Signed-off-by: Iouri Tarassov --- drivers/hv/dxgkrnl/dxgadapter.c | 11 +++ drivers/hv/dxgkrnl/dxgkrnl.h | 14 +++ drivers/hv/dxgkrnl/dxgvmbus.c | 107 +++++++++++++++++++++ drivers/hv/dxgkrnl/ioctl.c | 161 ++++++++++++++++++++++++++++++++ 4 files changed, 293 insertions(+) diff --git a/drivers/hv/dxgkrnl/dxgadapter.c b/drivers/hv/dxgkrnl/dxgadapte= r.c index f4e1d402fdbe..e28f5d3e4210 100644 --- a/drivers/hv/dxgkrnl/dxgadapter.c +++ b/drivers/hv/dxgkrnl/dxgadapter.c @@ -885,6 +885,15 @@ void dxgallocation_stop(struct dxgallocation *alloc) vfree(alloc->pages); alloc->pages =3D NULL; } + dxgprocess_ht_lock_exclusive_down(alloc->process); + if (alloc->cpu_address_mapped) { + dxg_unmap_iospace(alloc->cpu_address, + alloc->num_pages << PAGE_SHIFT); + alloc->cpu_address_mapped =3D false; + alloc->cpu_address =3D NULL; + alloc->cpu_address_refcount =3D 0; + } + dxgprocess_ht_lock_exclusive_up(alloc->process); } =20 void dxgallocation_free_handle(struct dxgallocation *alloc) @@ -926,6 +935,8 @@ void dxgallocation_destroy(struct dxgallocation *alloc) } if (alloc->priv_drv_data) vfree(alloc->priv_drv_data); + if (alloc->cpu_address_mapped) + pr_err("Alloc IO space is mapped: %p", alloc); vfree(alloc); } =20 diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index 892c95a11368..fa46abf0350a 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -691,6 +691,8 @@ struct dxgallocation { struct d3dkmthandle alloc_handle; /* Set to 1 when allocation belongs to resource. */ u32 resource_owner:1; + /* Set to 1 when 'cpu_address' is mapped to the IO space. */ + u32 cpu_address_mapped:1; /* Set to 1 when the allocatio is mapped as cached */ u32 cached:1; u32 handle_valid:1; @@ -698,6 +700,11 @@ struct dxgallocation { struct vmbus_gpadl gpadl; /* Number of pages in the 'pages' array */ u32 num_pages; + /* + * How many times dxgk_lock2 is called to allocation, which is mapped + * to IO space. + */ + u32 cpu_address_refcount; /* * CPU address from the existing sysmem allocation, or * mapped to the CPU visible backing store in the IO space @@ -811,6 +818,13 @@ int dxgvmb_send_wait_sync_object_cpu(struct dxgprocess= *process, d3dkmt_waitforsynchronizationobjectfromcpu *args, u64 cpu_event); +int dxgvmb_send_lock2(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_lock2 *args, + struct d3dkmt_lock2 *__user outargs); +int dxgvmb_send_unlock2(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_unlock2 *args); int dxgvmb_send_create_hwqueue(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_createhwqueue *args, diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index b5225756ee6e..a064efa320cf 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -2294,6 +2294,113 @@ int dxgvmb_send_wait_sync_object_gpu(struct dxgproc= ess *process, return ret; } =20 +int dxgvmb_send_lock2(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_lock2 *args, + struct d3dkmt_lock2 *__user outargs) +{ + int ret; + struct dxgkvmb_command_lock2 *command; + struct dxgkvmb_command_lock2_return result =3D { }; + struct dxgallocation *alloc =3D NULL; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, adapter, process, sizeof(*command)); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_LOCK2, process->host_handle); + command->args =3D *args; + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, + &result, sizeof(result)); + if (ret < 0) + goto cleanup; + + ret =3D ntstatus2int(result.status); + if (ret < 0) + goto cleanup; + + hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL); + alloc =3D hmgrtable_get_object_by_type(&process->handle_table, + HMGRENTRY_TYPE_DXGALLOCATION, + args->allocation); + if (alloc =3D=3D NULL) { + pr_err("%s invalid alloc", __func__); + ret =3D -EINVAL; + } else { + if (alloc->cpu_address) { + args->data =3D alloc->cpu_address; + if (alloc->cpu_address_mapped) + alloc->cpu_address_refcount++; + } else { + u64 offset =3D (u64)result.cpu_visible_buffer_offset; + + args->data =3D dxg_map_iospace(offset, + alloc->num_pages << PAGE_SHIFT, + PROT_READ | PROT_WRITE, alloc->cached); + if (args->data) { + alloc->cpu_address_refcount =3D 1; + alloc->cpu_address_mapped =3D true; + alloc->cpu_address =3D args->data; + } + } + if (args->data =3D=3D NULL) { + ret =3D -ENOMEM; + } else { + ret =3D copy_to_user(&outargs->data, &args->data, + sizeof(args->data)); + if (ret) { + pr_err("%s failed to copy data", __func__); + ret =3D -EINVAL; + alloc->cpu_address_refcount--; + if (alloc->cpu_address_refcount =3D=3D 0) { + dxg_unmap_iospace(alloc->cpu_address, + alloc->num_pages << PAGE_SHIFT); + alloc->cpu_address_mapped =3D false; + alloc->cpu_address =3D NULL; + } + } + } + } + hmgrtable_unlock(&process->handle_table, DXGLOCK_EXCL); + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +int dxgvmb_send_unlock2(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_unlock2 *args) +{ + int ret; + struct dxgkvmb_command_unlock2 *command; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, adapter, process, sizeof(*command)); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_UNLOCK2, + process->host_handle); + command->args =3D *args; + + ret =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, msg.size); + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + int dxgvmb_send_create_hwqueue(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_createhwqueue *args, diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index bb6eab08898f..12a4593c6aa5 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -3180,6 +3180,163 @@ dxgk_wait_sync_object_gpu(struct dxgprocess *proces= s, void *__user inargs) return ret; } =20 +static int +dxgk_lock2(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmt_lock2 args; + struct d3dkmt_lock2 *__user result =3D inargs; + int ret; + struct dxgadapter *adapter =3D NULL; + struct dxgdevice *device =3D NULL; + struct dxgallocation *alloc =3D NULL; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + args.data =3D NULL; + hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL); + alloc =3D hmgrtable_get_object_by_type(&process->handle_table, + HMGRENTRY_TYPE_DXGALLOCATION, + args.allocation); + if (alloc =3D=3D NULL) { + ret =3D -EINVAL; + } else { + if (alloc->cpu_address) { + ret =3D copy_to_user(&result->data, + &alloc->cpu_address, + sizeof(args.data)); + if (ret =3D=3D 0) { + args.data =3D alloc->cpu_address; + if (alloc->cpu_address_mapped) + alloc->cpu_address_refcount++; + } else { + pr_err("%s Failed to copy cpu address", + __func__); + ret =3D -EINVAL; + } + } + } + hmgrtable_unlock(&process->handle_table, DXGLOCK_EXCL); + if (ret < 0) + goto cleanup; + if (args.data) + goto success; + + /* + * The call acquires reference on the device. It is safe to access the + * adapter, because the device holds reference on it. + */ + device =3D dxgprocess_device_by_handle(process, args.device); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_lock2(process, adapter, &args, result); + +cleanup: + + if (adapter) + dxgadapter_release_lock_shared(adapter); + + if (device) + kref_put(&device->device_kref, dxgdevice_release); + +success: + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_unlock2(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmt_unlock2 args; + int ret; + struct dxgadapter *adapter =3D NULL; + struct dxgdevice *device =3D NULL; + struct dxgallocation *alloc =3D NULL; + bool done =3D false; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + hmgrtable_lock(&process->handle_table, DXGLOCK_EXCL); + alloc =3D hmgrtable_get_object_by_type(&process->handle_table, + HMGRENTRY_TYPE_DXGALLOCATION, + args.allocation); + if (alloc =3D=3D NULL) { + ret =3D -EINVAL; + } else { + if (alloc->cpu_address =3D=3D NULL) { + pr_err("Allocation is not locked: %p", alloc); + ret =3D -EINVAL; + } else if (alloc->cpu_address_mapped) { + if (alloc->cpu_address_refcount > 0) { + alloc->cpu_address_refcount--; + if (alloc->cpu_address_refcount !=3D 0) { + done =3D true; + } else { + dxg_unmap_iospace(alloc->cpu_address, + alloc->num_pages << PAGE_SHIFT); + alloc->cpu_address_mapped =3D false; + alloc->cpu_address =3D NULL; + } + } else { + pr_err("Invalid cpu access refcount"); + done =3D true; + } + } + } + hmgrtable_unlock(&process->handle_table, DXGLOCK_EXCL); + if (done) + goto success; + if (ret < 0) + goto cleanup; + + /* + * The call acquires reference on the device. It is safe to access the + * adapter, because the device holds reference on it. + */ + device =3D dxgprocess_device_by_handle(process, args.device); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_unlock2(process, adapter, &args); + +cleanup: + if (adapter) + dxgadapter_release_lock_shared(adapter); + + if (device) + kref_put(&device->device_kref, dxgdevice_release); + +success: + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + static int dxgk_get_device_state(struct dxgprocess *process, void *__user inargs) { @@ -4011,6 +4168,8 @@ void init_ioctls(void) LX_DXDESTROYPAGINGQUEUE); SET_IOCTL(/*0x1d */ dxgk_destroy_sync_object, LX_DXDESTROYSYNCHRONIZATIONOBJECT); + SET_IOCTL(/*0x25 */ dxgk_lock2, + LX_DXLOCK2); SET_IOCTL(/*0x31 */ dxgk_signal_sync_object_cpu, LX_DXSIGNALSYNCHRONIZATIONOBJECTFROMCPU); SET_IOCTL(/*0x32 */ dxgk_signal_sync_object_gpu, @@ -4023,6 +4182,8 @@ void init_ioctls(void) LX_DXSUBMITWAITFORSYNCOBJECTSTOHWQUEUE); SET_IOCTL(/*0x36 */ dxgk_submit_signal_to_hwqueue, LX_DXSUBMITSIGNALSYNCOBJECTSTOHWQUEUE); + SET_IOCTL(/*0x37 */ dxgk_unlock2, + LX_DXUNLOCK2); SET_IOCTL(/*0x3a */ dxgk_wait_sync_object_cpu, LX_DXWAITFORSYNCHRONIZATIONOBJECTFROMCPU); SET_IOCTL(/*0x3b */ dxgk_wait_sync_object_gpu, --=20 2.35.1 From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 71367C433EF for ; Sat, 5 Feb 2022 02:35:37 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1379339AbiBECfg (ORCPT ); Fri, 4 Feb 2022 21:35:36 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45144 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1379021AbiBECe0 (ORCPT ); Fri, 4 Feb 2022 21:34:26 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id 561AD20B8761; Fri, 4 Feb 2022 18:34:26 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com 561AD20B8761 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028466; bh=8fvVMjdllpeKBqGvvkWOFsZlDq64y3KJ5drWV15MeSk=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=BpWzBbTEx6S8mFwfWOFeUn458MmiIZEjRLjF0sffhdcuy4OjamGEall0jxT8QYP64 TzlqIw9O5PFYTvSfc56TcloATcwG6iukOdN5+3Ylk8jT7XHzbKKJD1aCMGnIHmBJ9t 7GCze9kMmjE9ePkAaqCPo1+Zk5xKri2NQ6TBmFXo= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 17/24] drivers: hv: dxgkrnl: IOCTLs to handle GPU allocation properties Date: Fri, 4 Feb 2022 18:34:15 -0800 Message-Id: <60ae85e5fed288205df8fdaeec720fd91946200e.1644025661.git.iourit@linux.microsoft.com> X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" LX_DXCHANGEVIDEOMEMORYRESERVATION, LX_DXUPDATEALLOCPROPERTY, LX_DXSETALLOCATIONPRIORITY, LX_DXGETALLOCATIONPRIORITY, LX_DXQUERYALLOCATIONRESIDENCY. Implement various IOCTLs related to GPU allocations. The IOCTLs are logically simple and have the same implementation pattern: - Read input data - Build and send a VM bus message to the host - Return results to the caller - LX_DXCHANGEVIDEOMEMORYRESERVATION (D3DKMTChangeMemoryReservation) - LX_DXUPDATEALLOCPROPERTY (D3DKMTUpdateAllocationProperty) Request the host to update verious properties of an allocation. - LX_DXSETALLOCATIONPRIORITY, LX_DXGETALLOCATIONPRIORITY Set/get allocation priority, which defines how soon the allocation is evicted from GPU accessible memory. - LX_DXQUERYALLOCATIONRESIDENCY (D3DKMTQueryAllocationResidency) Queries if the allocation is located in the GPU accessible memory. Signed-off-by: Iouri Tarassov --- drivers/hv/dxgkrnl/dxgkrnl.h | 21 +++ drivers/hv/dxgkrnl/dxgvmbus.c | 300 ++++++++++++++++++++++++++++++++++ drivers/hv/dxgkrnl/ioctl.c | 212 ++++++++++++++++++++++++ 3 files changed, 533 insertions(+) diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index fa46abf0350a..128c5cd2be3d 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -825,6 +825,23 @@ int dxgvmb_send_lock2(struct dxgprocess *process, int dxgvmb_send_unlock2(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_unlock2 *args); +int dxgvmb_send_update_alloc_property(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dddi_updateallocproperty *args, + struct d3dddi_updateallocproperty *__user + inargs); +int dxgvmb_send_set_allocation_priority(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_setallocationpriority *a); +int dxgvmb_send_get_allocation_priority(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_getallocationpriority *a); +int dxgvmb_send_change_vidmem_reservation(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmthandle other_process, + struct + d3dkmt_changevideomemoryreservation + *args); int dxgvmb_send_create_hwqueue(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_createhwqueue *args, @@ -844,6 +861,10 @@ int dxgvmb_send_open_sync_object_nt(struct dxgprocess = *process, struct d3dkmt_opensyncobjectfromnthandle2 *args, struct dxgsyncobject *syncobj); +int dxgvmb_send_query_alloc_residency(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_queryallocationresidency + *args); int dxgvmb_send_get_device_state(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_getdevicestate *args, diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index a064efa320cf..a1bb7a10bf60 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -1774,6 +1774,79 @@ int dxgvmb_send_destroy_allocation(struct dxgprocess= *process, return ret; } =20 +int dxgvmb_send_query_alloc_residency(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_queryallocationresidency + *args) +{ + int ret =3D -EINVAL; + struct dxgkvmb_command_queryallocationresidency *command =3D NULL; + u32 cmd_size =3D sizeof(*command); + u32 alloc_size =3D 0; + u32 result_allocation_size =3D 0; + struct dxgkvmb_command_queryallocationresidency_return *result =3D NULL; + u32 result_size =3D sizeof(*result); + struct dxgvmbusmsgres msg =3D {.hdr =3D NULL}; + + if (args->allocation_count > DXG_MAX_VM_BUS_PACKET_SIZE) { + ret =3D -EINVAL; + goto cleanup; + } + + if (args->allocation_count) { + alloc_size =3D args->allocation_count * + sizeof(struct d3dkmthandle); + cmd_size +=3D alloc_size; + result_allocation_size =3D args->allocation_count * + sizeof(args->residency_status[0]); + } else { + result_allocation_size =3D sizeof(args->residency_status[0]); + } + result_size +=3D result_allocation_size; + + ret =3D init_message_res(&msg, adapter, process, cmd_size, result_size); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + result =3D msg.res; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_QUERYALLOCATIONRESIDENCY, + process->host_handle); + command->args =3D *args; + if (alloc_size) { + ret =3D copy_from_user(&command[1], args->allocations, + alloc_size); + if (ret) { + pr_err("%s failed to copy alloc handles", __func__); + ret =3D -EINVAL; + goto cleanup; + } + } + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, + result, msg.res_size); + if (ret < 0) + goto cleanup; + + ret =3D ntstatus2int(result->status); + if (ret < 0) + goto cleanup; + + ret =3D copy_to_user(args->residency_status, &result[1], + result_allocation_size); + if (ret) { + pr_err("%s failed to copy residency status", __func__); + ret =3D -EINVAL; + } + +cleanup: + free_message((struct dxgvmbusmsg *)&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + int dxgvmb_send_get_device_state(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_getdevicestate *args, @@ -2401,6 +2474,233 @@ int dxgvmb_send_unlock2(struct dxgprocess *process, return ret; } =20 +int dxgvmb_send_update_alloc_property(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dddi_updateallocproperty *args, + struct d3dddi_updateallocproperty *__user + inargs) +{ + int ret; + int ret1; + struct dxgkvmb_command_updateallocationproperty *command; + struct dxgkvmb_command_updateallocationproperty_return result =3D { }; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, adapter, process, sizeof(*command)); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_UPDATEALLOCATIONPROPERTY, + process->host_handle); + command->args =3D *args; + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, + &result, sizeof(result)); + + if (ret < 0) + goto cleanup; + ret =3D ntstatus2int(result.status); + /* STATUS_PENING is a success code > 0 */ + if (ret =3D=3D STATUS_PENDING) { + ret1 =3D copy_to_user(&inargs->paging_fence_value, + &result.paging_fence_value, + sizeof(u64)); + if (ret1) { + pr_err("%s failed to copy paging fence", __func__); + ret =3D -EINVAL; + } + } +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +int dxgvmb_send_set_allocation_priority(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_setallocationpriority *args) +{ + u32 cmd_size =3D sizeof(struct dxgkvmb_command_setallocationpriority); + u32 alloc_size =3D 0; + u32 priority_size =3D 0; + struct dxgkvmb_command_setallocationpriority *command; + int ret; + struct d3dkmthandle *allocations; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + if (args->allocation_count > DXG_MAX_VM_BUS_PACKET_SIZE) { + ret =3D -EINVAL; + goto cleanup; + } + if (args->resource.v) { + priority_size =3D sizeof(u32); + if (args->allocation_count !=3D 0) { + ret =3D -EINVAL; + goto cleanup; + } + } else { + if (args->allocation_count =3D=3D 0) { + ret =3D -EINVAL; + goto cleanup; + } + alloc_size =3D args->allocation_count * + sizeof(struct d3dkmthandle); + cmd_size +=3D alloc_size; + priority_size =3D sizeof(u32) * args->allocation_count; + } + cmd_size +=3D priority_size; + + ret =3D init_message(&msg, adapter, process, cmd_size); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_SETALLOCATIONPRIORITY, + process->host_handle); + command->device =3D args->device; + command->allocation_count =3D args->allocation_count; + command->resource =3D args->resource; + allocations =3D (struct d3dkmthandle *) &command[1]; + ret =3D copy_from_user(allocations, args->allocation_list, + alloc_size); + if (ret) { + pr_err("%s failed to copy alloc handle", __func__); + ret =3D -EINVAL; + goto cleanup; + } + ret =3D copy_from_user((u8 *) allocations + alloc_size, + args->priorities, priority_size); + if (ret) { + pr_err("%s failed to copy alloc priority", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, msg.size); + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +int dxgvmb_send_get_allocation_priority(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_getallocationpriority *args) +{ + u32 cmd_size =3D sizeof(struct dxgkvmb_command_getallocationpriority); + u32 result_size; + u32 alloc_size =3D 0; + u32 priority_size =3D 0; + struct dxgkvmb_command_getallocationpriority *command; + struct dxgkvmb_command_getallocationpriority_return *result; + int ret; + struct d3dkmthandle *allocations; + struct dxgvmbusmsgres msg =3D {.hdr =3D NULL}; + + if (args->allocation_count > DXG_MAX_VM_BUS_PACKET_SIZE) { + ret =3D -EINVAL; + goto cleanup; + } + if (args->resource.v) { + priority_size =3D sizeof(u32); + if (args->allocation_count !=3D 0) { + ret =3D -EINVAL; + goto cleanup; + } + } else { + if (args->allocation_count =3D=3D 0) { + ret =3D -EINVAL; + goto cleanup; + } + alloc_size =3D args->allocation_count * + sizeof(struct d3dkmthandle); + cmd_size +=3D alloc_size; + priority_size =3D sizeof(u32) * args->allocation_count; + } + result_size =3D sizeof(*result) + priority_size; + + ret =3D init_message_res(&msg, adapter, process, cmd_size, result_size); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + result =3D msg.res; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_GETALLOCATIONPRIORITY, + process->host_handle); + command->device =3D args->device; + command->allocation_count =3D args->allocation_count; + command->resource =3D args->resource; + allocations =3D (struct d3dkmthandle *) &command[1]; + ret =3D copy_from_user(allocations, args->allocation_list, + alloc_size); + if (ret) { + pr_err("%s failed to copy alloc handles", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, + msg.size + msg.res_size, + result, msg.res_size); + if (ret < 0) + goto cleanup; + + ret =3D ntstatus2int(result->status); + if (ret < 0) + goto cleanup; + + ret =3D copy_to_user(args->priorities, + (u8 *) result + sizeof(*result), + priority_size); + if (ret) { + pr_err("%s failed to copy priorities", __func__); + ret =3D -EINVAL; + } + +cleanup: + free_message((struct dxgvmbusmsg *)&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +int dxgvmb_send_change_vidmem_reservation(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmthandle other_process, + struct + d3dkmt_changevideomemoryreservation + *args) +{ + struct dxgkvmb_command_changevideomemoryreservation *command; + int ret; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, adapter, process, sizeof(*command)); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_CHANGEVIDEOMEMORYRESERVATION, + process->host_handle); + command->args =3D *args; + command->args.process =3D other_process.v; + + ret =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, msg.size); +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + int dxgvmb_send_create_hwqueue(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_createhwqueue *args, diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index 12a4593c6aa5..7ebad4524f94 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -3337,6 +3337,208 @@ dxgk_unlock2(struct dxgprocess *process, void *__us= er inargs) return ret; } =20 +static int +dxgk_update_alloc_property(struct dxgprocess *process, void *__user inargs) +{ + struct d3dddi_updateallocproperty args; + int ret; + struct dxgadapter *adapter =3D NULL; + struct dxgdevice *device =3D NULL; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + device =3D dxgprocess_device_by_object_handle(process, + HMGRENTRY_TYPE_DXGPAGINGQUEUE, + args.paging_queue); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_update_alloc_property(process, adapter, + &args, inargs); + +cleanup: + if (adapter) + dxgadapter_release_lock_shared(adapter); + + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_query_alloc_residency(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmt_queryallocationresidency args; + struct dxgadapter *adapter =3D NULL; + struct dxgdevice *device =3D NULL; + int ret; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + if ((args.allocation_count =3D=3D 0) =3D=3D (args.resource.v =3D=3D 0)) { + ret =3D -EINVAL; + goto cleanup; + } + + device =3D dxgprocess_device_by_handle(process, args.device); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + ret =3D dxgvmb_send_query_alloc_residency(process, adapter, &args); +cleanup: + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_set_allocation_priority(struct dxgprocess *process, void *__user inar= gs) +{ + struct d3dkmt_setallocationpriority args; + struct dxgadapter *adapter =3D NULL; + struct dxgdevice *device =3D NULL; + int ret; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + device =3D dxgprocess_device_by_handle(process, args.device); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + ret =3D dxgvmb_send_set_allocation_priority(process, adapter, &args); +cleanup: + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_get_allocation_priority(struct dxgprocess *process, void *__user inar= gs) +{ + struct d3dkmt_getallocationpriority args; + struct dxgadapter *adapter =3D NULL; + struct dxgdevice *device =3D NULL; + int ret; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + device =3D dxgprocess_device_by_handle(process, args.device); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + ret =3D dxgvmb_send_get_allocation_priority(process, adapter, &args); +cleanup: + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_change_vidmem_reservation(struct dxgprocess *process, void *__user in= args) +{ + struct d3dkmt_changevideomemoryreservation args; + int ret; + struct dxgadapter *adapter =3D NULL; + bool adapter_locked =3D false; + + pr_debug("ioctl: %s", __func__); + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.process !=3D 0) { + pr_err("setting memory reservation for other process"); + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D dxgprocess_adapter_by_handle(process, args.adapter); + if (adapter =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + adapter_locked =3D true; + args.adapter.v =3D 0; + ret =3D dxgvmb_send_change_vidmem_reservation(process, adapter, + zerohandle, &args); + +cleanup: + + if (adapter_locked) + dxgadapter_release_lock_shared(adapter); + if (adapter) + kref_put(&adapter->adapter_kref, dxgadapter_release); + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + static int dxgk_get_device_state(struct dxgprocess *process, void *__user inargs) { @@ -4158,6 +4360,8 @@ void init_ioctls(void) LX_DXENUMADAPTERS2); SET_IOCTL(/*0x15 */ dxgk_close_adapter, LX_DXCLOSEADAPTER); + SET_IOCTL(/*0x16 */ dxgk_change_vidmem_reservation, + LX_DXCHANGEVIDEOMEMORYRESERVATION); SET_IOCTL(/*0x18 */ dxgk_create_hwqueue, LX_DXCREATEHWQUEUE); SET_IOCTL(/*0x19 */ dxgk_destroy_device, @@ -4170,6 +4374,10 @@ void init_ioctls(void) LX_DXDESTROYSYNCHRONIZATIONOBJECT); SET_IOCTL(/*0x25 */ dxgk_lock2, LX_DXLOCK2); + SET_IOCTL(/*0x2a */ dxgk_query_alloc_residency, + LX_DXQUERYALLOCATIONRESIDENCY); + SET_IOCTL(/*0x2e */ dxgk_set_allocation_priority, + LX_DXSETALLOCATIONPRIORITY); SET_IOCTL(/*0x31 */ dxgk_signal_sync_object_cpu, LX_DXSIGNALSYNCHRONIZATIONOBJECTFROMCPU); SET_IOCTL(/*0x32 */ dxgk_signal_sync_object_gpu, @@ -4184,10 +4392,14 @@ void init_ioctls(void) LX_DXSUBMITSIGNALSYNCOBJECTSTOHWQUEUE); SET_IOCTL(/*0x37 */ dxgk_unlock2, LX_DXUNLOCK2); + SET_IOCTL(/*0x38 */ dxgk_update_alloc_property, + LX_DXUPDATEALLOCPROPERTY); SET_IOCTL(/*0x3a */ dxgk_wait_sync_object_cpu, LX_DXWAITFORSYNCHRONIZATIONOBJECTFROMCPU); SET_IOCTL(/*0x3b */ dxgk_wait_sync_object_gpu, LX_DXWAITFORSYNCHRONIZATIONOBJECTFROMGPU); + SET_IOCTL(/*0x3c */ dxgk_get_allocation_priority, + LX_DXGETALLOCATIONPRIORITY); SET_IOCTL(/*0x3e */ dxgk_enum_adapters3, LX_DXENUMADAPTERS3); SET_IOCTL(/*0x3f */ dxgk_share_objects, --=20 2.35.1 From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id AF8B3C433EF for ; Sat, 5 Feb 2022 02:35:41 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1379162AbiBECfi (ORCPT ); Fri, 4 Feb 2022 21:35:38 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45146 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1379022AbiBECe0 (ORCPT ); Fri, 4 Feb 2022 21:34:26 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id 807BD20B8763; Fri, 4 Feb 2022 18:34:26 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com 807BD20B8763 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028466; bh=kQh2dK88XuPow6y/yDSrqkhjm9kQ0UZOA4nLmOlKjd8=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=AD7WHFhvcJEw494Fzf06puQ+jqNp0Yd8bM+DyOSsXSTFghZQfE6WsC1DPmTMDhBb8 crUnYom5OdyWYdhEOaxRAtD/9690b9HBCnAx+OvVa9yV0xXx+B5m3vGEFymwONauXk R17fJ2pzEvup6JZ9fPhqjZYbGhdNai/HcL+T4HaM= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 18/24] drivers: hv: dxgkrnl: Various simple IOCTLs and unused ones LX_DXQUERYVIDEOMEMORYINFO, LX_DXFLUSHHEAPTRANSITIONS, LX_DXINVALIDATECACHE LX_DXGETSHAREDRESOURCEADAPTERLUID Date: Fri, 4 Feb 2022 18:34:16 -0800 Message-Id: <8ec3cb5deb955dd377b264209f50c7d774365e7d.1644025661.git.iourit@linux.microsoft.com> X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Simple IOCTLs have the same implementation pattern: - read data from input - send a synchronous VM bus message to the host - return result to the caller Signed-off-by: Iouri Tarassov --- drivers/hv/dxgkrnl/dxgkrnl.h | 8 ++ drivers/hv/dxgkrnl/dxgvmbus.c | 87 ++++++++++++++++ drivers/hv/dxgkrnl/ioctl.c | 181 ++++++++++++++++++++++++++++++++++ 3 files changed, 276 insertions(+) diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index 128c5cd2be3d..2efad824ae72 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -856,6 +856,9 @@ int dxgvmb_send_query_adapter_info(struct dxgprocess *p= rocess, int dxgvmb_send_submit_command_hwqueue(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_submitcommandtohwqueue *a); +int dxgvmb_send_flush_heap_transitions(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_flushheaptransitions *arg); int dxgvmb_send_open_sync_object_nt(struct dxgprocess *process, struct dxgvmbuschannel *channel, struct d3dkmt_opensyncobjectfromnthandle2 @@ -865,6 +868,11 @@ int dxgvmb_send_query_alloc_residency(struct dxgproces= s *process, struct dxgadapter *adapter, struct d3dkmt_queryallocationresidency *args); +int dxgvmb_send_query_vidmem_info(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_queryvideomemoryinfo *args, + struct d3dkmt_queryvideomemoryinfo + *__user iargs); int dxgvmb_send_get_device_state(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_getdevicestate *args, diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index a1bb7a10bf60..684d9cecc804 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -1774,6 +1774,29 @@ int dxgvmb_send_destroy_allocation(struct dxgprocess= *process, return ret; } =20 +int dxgvmb_send_flush_heap_transitions(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_flushheaptransitions *args) +{ + struct dxgkvmb_command_flushheaptransitions *command; + int ret; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, adapter, process, sizeof(*command)); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_FLUSHHEAPTRANSITIONS, + process->host_handle); + ret =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, msg.size); +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + int dxgvmb_send_query_alloc_residency(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_queryallocationresidency @@ -1847,6 +1870,70 @@ int dxgvmb_send_query_alloc_residency(struct dxgproc= ess *process, return ret; } =20 +int dxgvmb_send_query_vidmem_info(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_queryvideomemoryinfo *args, + struct d3dkmt_queryvideomemoryinfo *__user + output) +{ + int ret; + struct dxgkvmb_command_queryvideomemoryinfo *command; + struct dxgkvmb_command_queryvideomemoryinfo_return result =3D { }; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, adapter, process, sizeof(*command)); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + command_vgpu_to_host_init2(&command->hdr, + dxgk_vmbcommand_queryvideomemoryinfo, + process->host_handle); + command->adapter =3D args->adapter; + command->memory_segment_group =3D args->memory_segment_group; + command->physical_adapter_index =3D args->physical_adapter_index; + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, + &result, sizeof(result)); + if (ret < 0) + goto cleanup; + + ret =3D copy_to_user(&output->budget, &result.budget, + sizeof(output->budget)); + if (ret) { + pr_err("%s failed to copy budget", __func__); + ret =3D -EINVAL; + goto cleanup; + } + ret =3D copy_to_user(&output->current_usage, &result.current_usage, + sizeof(output->current_usage)); + if (ret) { + pr_err("%s failed to copy current usage", __func__); + ret =3D -EINVAL; + goto cleanup; + } + ret =3D copy_to_user(&output->current_reservation, + &result.current_reservation, + sizeof(output->current_reservation)); + if (ret) { + pr_err("%s failed to copy reservation", __func__); + ret =3D -EINVAL; + goto cleanup; + } + ret =3D copy_to_user(&output->available_for_reservation, + &result.available_for_reservation, + sizeof(output->available_for_reservation)); + if (ret) { + pr_err("%s failed to copy avail reservation", __func__); + ret =3D -EINVAL; + } + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + int dxgvmb_send_get_device_state(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_getdevicestate *args, diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index 7ebad4524f94..8dd5b64a7dd5 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -880,6 +880,20 @@ dxgk_destroy_context(struct dxgprocess *process, void = *__user inargs) return ret; } =20 +static int dxgk_create_hwcontext(struct dxgprocess *process, + void *__user inargs) +{ + /* This is obsolete entry point */ + return -ENOTTY; +} + +static int dxgk_destroy_hwcontext(struct dxgprocess *process, + void *__user inargs) +{ + /* This is obsolete entry point */ + return -ENOTTY; +} + static int dxgk_create_hwqueue(struct dxgprocess *process, void *__user inargs) { @@ -2527,6 +2541,13 @@ dxgk_open_sync_object_nt(struct dxgprocess *process,= void *__user inargs) return ret; } =20 +static int +dxgk_open_sync_object(struct dxgprocess *process, void *__user inargs) +{ + pr_err("%s is not supported", __func__); + return -ENOTTY; +} + static int dxgk_signal_sync_object(struct dxgprocess *process, void *__user inargs) { @@ -3539,6 +3560,101 @@ dxgk_change_vidmem_reservation(struct dxgprocess *p= rocess, void *__user inargs) return ret; } =20 +static int +dxgk_flush_heap_transitions(struct dxgprocess *process, void *__user inarg= s) +{ + struct d3dkmt_flushheaptransitions args; + int ret; + struct dxgadapter *adapter =3D NULL; + bool adapter_locked =3D false; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D dxgprocess_adapter_by_handle(process, args.adapter); + if (adapter =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + adapter_locked =3D true; + + args.adapter =3D adapter->host_handle; + ret =3D dxgvmb_send_flush_heap_transitions(process, adapter, &args); + if (ret < 0) + goto cleanup; + ret =3D copy_to_user(inargs, &args, sizeof(args)); + if (ret) { + pr_err("%s failed to copy output args", __func__); + ret =3D -EINVAL; + } + +cleanup: + + if (adapter_locked) + dxgadapter_release_lock_shared(adapter); + if (adapter) + kref_put(&adapter->adapter_kref, dxgadapter_release); + return ret; +} + +static int +dxgk_query_vidmem_info(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmt_queryvideomemoryinfo args; + int ret; + struct dxgadapter *adapter =3D NULL; + bool adapter_locked =3D false; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.process !=3D 0) { + pr_err("query vidmem info from another process "); + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D dxgprocess_adapter_by_handle(process, args.adapter); + if (adapter =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + adapter_locked =3D true; + + args.adapter =3D adapter->host_handle; + ret =3D dxgvmb_send_query_vidmem_info(process, adapter, &args, inargs); + +cleanup: + + if (adapter_locked) + dxgadapter_release_lock_shared(adapter); + if (adapter) + kref_put(&adapter->adapter_kref, dxgadapter_release); + if (ret < 0) + pr_err("%s failed: %x", __func__, ret); + return ret; +} + static int dxgk_get_device_state(struct dxgprocess *process, void *__user inargs) { @@ -3854,6 +3970,20 @@ dxgk_share_objects(struct dxgprocess *process, void = *__user inargs) return ret; } =20 +static int +dxgk_invalidate_cache(struct dxgprocess *process, void *__user inargs) +{ + pr_err("%s is not implemented", __func__); + return -ENOTTY; +} + +static int +dxgk_query_resource_info(struct dxgprocess *process, void *__user inargs) +{ + pr_err("%s is not supported", __func__); + return -ENOTTY; +} + static int dxgk_query_resource_info_nt(struct dxgprocess *process, void *__user inarg= s) { @@ -4218,6 +4348,13 @@ open_resource(struct dxgprocess *process, return ret; } =20 +static int +dxgk_open_resource(struct dxgprocess *process, void *__user inargs) +{ + pr_err("%s is not supported", __func__); + return -ENOTTY; +} + static int dxgk_open_resource_nt(struct dxgprocess *process, void *__user inargs) @@ -4274,6 +4411,28 @@ dxgk_share_object_with_host(struct dxgprocess *proce= ss, void *__user inargs) return ret; } =20 +static int +dxgk_render(struct dxgprocess *process, void *__user inargs) +{ + pr_err("%s is not implemented", __func__); + return -ENOTTY; +} + +static int +dxgk_create_context(struct dxgprocess *process, void *__user inargs) +{ + pr_err("%s is not implemented", __func__); + return -ENOTTY; +} + +static int +dxgk_get_shared_resource_adapter_luid(struct dxgprocess *process, + void *__user inargs) +{ + pr_err("shared_resource_adapter_luid is not implemented"); + return -ENOTTY; +} + /* * IOCTL processing * The driver IOCTLs return @@ -4334,6 +4493,8 @@ void init_ioctls(void) LX_DXOPENADAPTERFROMLUID); SET_IOCTL(/*0x2 */ dxgk_create_device, LX_DXCREATEDEVICE); + SET_IOCTL(/*0x3 */ dxgk_create_context, + LX_DXCREATECONTEXT); SET_IOCTL(/*0x4 */ dxgk_create_context_virtual, LX_DXCREATECONTEXTVIRTUAL); SET_IOCTL(/*0x5 */ dxgk_destroy_context, @@ -4344,6 +4505,8 @@ void init_ioctls(void) LX_DXCREATEPAGINGQUEUE); SET_IOCTL(/*0x9 */ dxgk_query_adapter_info, LX_DXQUERYADAPTERINFO); + SET_IOCTL(/*0xa */ dxgk_query_vidmem_info, + LX_DXQUERYVIDEOMEMORYINFO); SET_IOCTL(/*0xe */ dxgk_get_device_state, LX_DXGETDEVICESTATE); SET_IOCTL(/*0xf */ dxgk_submit_command, @@ -4362,20 +4525,38 @@ void init_ioctls(void) LX_DXCLOSEADAPTER); SET_IOCTL(/*0x16 */ dxgk_change_vidmem_reservation, LX_DXCHANGEVIDEOMEMORYRESERVATION); + SET_IOCTL(/*0x17 */ dxgk_create_hwcontext, + LX_DXCREATEHWCONTEXT); SET_IOCTL(/*0x18 */ dxgk_create_hwqueue, LX_DXCREATEHWQUEUE); SET_IOCTL(/*0x19 */ dxgk_destroy_device, LX_DXDESTROYDEVICE); + SET_IOCTL(/*0x1a */ dxgk_destroy_hwcontext, + LX_DXDESTROYHWCONTEXT); SET_IOCTL(/*0x1b */ dxgk_destroy_hwqueue, LX_DXDESTROYHWQUEUE); SET_IOCTL(/*0x1c */ dxgk_destroy_paging_queue, LX_DXDESTROYPAGINGQUEUE); SET_IOCTL(/*0x1d */ dxgk_destroy_sync_object, LX_DXDESTROYSYNCHRONIZATIONOBJECT); + SET_IOCTL(/*0x1f */ dxgk_flush_heap_transitions, + LX_DXFLUSHHEAPTRANSITIONS); + SET_IOCTL(/*0x23 */ dxgk_get_shared_resource_adapter_luid, + LX_DXGETSHAREDRESOURCEADAPTERLUID); + SET_IOCTL(/*0x24 */ dxgk_invalidate_cache, + LX_DXINVALIDATECACHE); SET_IOCTL(/*0x25 */ dxgk_lock2, LX_DXLOCK2); + SET_IOCTL(/*0x28 */ dxgk_open_resource, + LX_DXOPENRESOURCE); + SET_IOCTL(/*0x29 */ dxgk_open_sync_object, + LX_DXOPENSYNCHRONIZATIONOBJECT); SET_IOCTL(/*0x2a */ dxgk_query_alloc_residency, LX_DXQUERYALLOCATIONRESIDENCY); + SET_IOCTL(/*0x2b */ dxgk_query_resource_info, + LX_DXQUERYRESOURCEINFO); + SET_IOCTL(/*0x2d */ dxgk_render, + LX_DXRENDER); SET_IOCTL(/*0x2e */ dxgk_set_allocation_priority, LX_DXSETALLOCATIONPRIORITY); SET_IOCTL(/*0x31 */ dxgk_signal_sync_object_cpu, --=20 2.35.1 From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 44DCAC433EF for ; Sat, 5 Feb 2022 02:35:46 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1379364AbiBECfp (ORCPT ); Fri, 4 Feb 2022 21:35:45 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45084 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1379024AbiBECe0 (ORCPT ); Fri, 4 Feb 2022 21:34:26 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id A89A620B8764; Fri, 4 Feb 2022 18:34:26 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com A89A620B8764 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028466; bh=sSxpXZZdqewSu/72oXnc+RjB2wtST49wbWTvhCc+OlI=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=hQptrbSl/2DFJuIubFeFcp6rs6j0hw6SbKJD/J5IUzIujzAhNZHT1jJ5GdZmaACkS Y9t0REaR9Iw4rb9YAZalyKk31uBHsc/PVvaFo/uRI/OA7vhew7/RH1D6EmXl+t2y9D k87DNk5wixoicsaji3p+0RykHkvzCP5820kLcfP8= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 19/24] drivers: hv: dxgkrnl: Simple IOCTLs LX_DXESCAPE, LX_DXMARKDEVICEASERROR, LX_DXQUERYSTATISTICS, LX_DXQUERYCLOCKCALIBRATION Date: Fri, 4 Feb 2022 18:34:17 -0800 Message-Id: <07c352a82707304cc5836313b97dfd97be8c7354.1644025661.git.iourit@linux.microsoft.com> X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" These IOCTLs are logically simple: - input data is read - a message is sent to the host - the result is returned to the caller - LX_DXESCAPE (D3DKMTEscape) This IOCTL is used to send/receive private data between user mode driver and kernel mode driver. This is an extension of the WDDM APIs. - LX_DXMARKDEVICEASERROR (D3DKMTMarkDeviceAsError) The IOCTL is used to bring the dxgdevice object to the error state. Subsequent calls to use the device object will fail. - LX_DXQUERYSTATISTICS (D3DKMTQuerystatistics) The IOCTL is used to query various statistics from the compute device on the host. - LX_DXQUERYCLOCKCALIBRATION The IOCTL queries clock from the compute device. Signed-off-by: Iouri Tarassov --- drivers/hv/dxgkrnl/dxgkrnl.h | 14 +++ drivers/hv/dxgkrnl/dxgvmbus.c | 167 +++++++++++++++++++++++++++++ drivers/hv/dxgkrnl/ioctl.c | 193 ++++++++++++++++++++++++++++++++++ 3 files changed, 374 insertions(+) diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index 2efad824ae72..8310dd9b7843 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -830,6 +830,9 @@ int dxgvmb_send_update_alloc_property(struct dxgprocess= *process, struct d3dddi_updateallocproperty *args, struct d3dddi_updateallocproperty *__user inargs); +int dxgvmb_send_mark_device_as_error(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_markdeviceaserror *args); int dxgvmb_send_set_allocation_priority(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_setallocationpriority *a); @@ -856,6 +859,11 @@ int dxgvmb_send_query_adapter_info(struct dxgprocess *= process, int dxgvmb_send_submit_command_hwqueue(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_submitcommandtohwqueue *a); +int dxgvmb_send_query_clock_calibration(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_queryclockcalibration *a, + struct d3dkmt_queryclockcalibration + *__user inargs); int dxgvmb_send_flush_heap_transitions(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_flushheaptransitions *arg); @@ -868,6 +876,9 @@ int dxgvmb_send_query_alloc_residency(struct dxgprocess= *process, struct dxgadapter *adapter, struct d3dkmt_queryallocationresidency *args); +int dxgvmb_send_escape(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_escape *args); int dxgvmb_send_query_vidmem_info(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_queryvideomemoryinfo *args, @@ -897,6 +908,9 @@ int dxgvmb_send_get_stdalloc_data(struct dxgdevice *dev= ice, void *prive_alloc_data, u32 *res_priv_data_size, void *priv_res_data); +int dxgvmb_send_query_statistics(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_querystatistics *args); int dxgvmb_send_async_msg(struct dxgvmbuschannel *channel, void *command, u32 cmd_size); diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index 684d9cecc804..f7fcbf62f95b 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -1774,6 +1774,48 @@ int dxgvmb_send_destroy_allocation(struct dxgprocess= *process, return ret; } =20 +int dxgvmb_send_query_clock_calibration(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_queryclockcalibration + *args, + struct d3dkmt_queryclockcalibration + *__user inargs) +{ + struct dxgkvmb_command_queryclockcalibration *command; + struct dxgkvmb_command_queryclockcalibration_return result; + int ret; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, adapter, process, sizeof(*command)); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_QUERYCLOCKCALIBRATION, + process->host_handle); + command->args =3D *args; + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, + &result, sizeof(result)); + if (ret < 0) + goto cleanup; + ret =3D copy_to_user(&inargs->clock_data, &result.clock_data, + sizeof(result.clock_data)); + if (ret) { + pr_err("%s failed to copy clock data", __func__); + ret =3D -EINVAL; + goto cleanup; + } + ret =3D ntstatus2int(result.status); + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + int dxgvmb_send_flush_heap_transitions(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_flushheaptransitions *args) @@ -1870,6 +1912,70 @@ int dxgvmb_send_query_alloc_residency(struct dxgproc= ess *process, return ret; } =20 +int dxgvmb_send_escape(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_escape *args) +{ + int ret; + struct dxgkvmb_command_escape *command =3D NULL; + u32 cmd_size =3D sizeof(*command); + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + if (args->priv_drv_data_size > DXG_MAX_VM_BUS_PACKET_SIZE) { + ret =3D -EINVAL; + goto cleanup; + } + + cmd_size =3D cmd_size - sizeof(args->priv_drv_data[0]) + + args->priv_drv_data_size; + + ret =3D init_message(&msg, adapter, process, cmd_size); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_ESCAPE, + process->host_handle); + command->adapter =3D args->adapter; + command->device =3D args->device; + command->type =3D args->type; + command->flags =3D args->flags; + command->priv_drv_data_size =3D args->priv_drv_data_size; + command->context =3D args->context; + if (args->priv_drv_data_size) { + ret =3D copy_from_user(command->priv_drv_data, + args->priv_drv_data, + args->priv_drv_data_size); + if (ret) { + pr_err("%s failed to copy priv data", __func__); + ret =3D -EINVAL; + goto cleanup; + } + } + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, + command->priv_drv_data, + args->priv_drv_data_size); + if (ret < 0) + goto cleanup; + + if (args->priv_drv_data_size) { + ret =3D copy_to_user(args->priv_drv_data, + command->priv_drv_data, + args->priv_drv_data_size); + if (ret) { + pr_err("%s failed to copy priv data", __func__); + ret =3D -EINVAL; + } + } + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + int dxgvmb_send_query_vidmem_info(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_queryvideomemoryinfo *args, @@ -2606,6 +2712,31 @@ int dxgvmb_send_update_alloc_property(struct dxgproc= ess *process, return ret; } =20 +int dxgvmb_send_mark_device_as_error(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_markdeviceaserror *args) +{ + struct dxgkvmb_command_markdeviceaserror *command; + int ret; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, adapter, process, sizeof(*command)); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_MARKDEVICEASERROR, + process->host_handle); + command->args =3D *args; + ret =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, msg.size); +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + int dxgvmb_send_set_allocation_priority(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_setallocationpriority *args) @@ -3087,3 +3218,39 @@ int dxgvmb_send_submit_command_hwqueue(struct dxgpro= cess *process, pr_debug("err: %s %d", __func__, ret); return ret; } + +int dxgvmb_send_query_statistics(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_querystatistics *args) +{ + struct dxgkvmb_command_querystatistics *command; + struct dxgkvmb_command_querystatistics_return *result; + int ret; + struct dxgvmbusmsgres msg =3D {.hdr =3D NULL}; + + ret =3D init_message_res(&msg, adapter, process, sizeof(*command), + sizeof(*result)); + if (ret) + goto cleanup; + command =3D msg.msg; + result =3D msg.res; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_QUERYSTATISTICS, + process->host_handle); + command->args =3D *args; + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, + result, msg.res_size); + if (ret < 0) + goto cleanup; + + args->result =3D result->result; + ret =3D ntstatus2int(result->status); + +cleanup: + free_message((struct dxgvmbusmsg *)&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index 8dd5b64a7dd5..6c9b6e6ea296 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -153,6 +153,66 @@ static int dxgk_open_adapter_from_luid(struct dxgproce= ss *process, return ret; } =20 +static int dxgk_query_statistics(struct dxgprocess *process, + void __user *inargs) +{ + struct d3dkmt_querystatistics *args; + int ret; + struct dxgadapter *entry; + struct dxgadapter *adapter =3D NULL; + struct winluid tmp; + + pr_debug("ioctl: %s", __func__); + + args =3D vzalloc(sizeof(struct d3dkmt_querystatistics)); + if (args =3D=3D NULL) { + ret =3D -ENOMEM; + goto cleanup; + } + + ret =3D copy_from_user(args, inargs, sizeof(*args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + dxgglobal_acquire_adapter_list_lock(DXGLOCK_SHARED); + list_for_each_entry(entry, &dxgglobal->adapter_list_head, + adapter_list_entry) { + if (dxgadapter_acquire_lock_shared(entry) =3D=3D 0) { + if (*(u64 *) &entry->luid =3D=3D + *(u64 *) &args->adapter_luid) { + adapter =3D entry; + break; + } + dxgadapter_release_lock_shared(entry); + } + } + dxgglobal_release_adapter_list_lock(DXGLOCK_SHARED); + if (adapter) { + tmp =3D args->adapter_luid; + args->adapter_luid =3D adapter->host_adapter_luid; + ret =3D dxgvmb_send_query_statistics(process, adapter, args); + if (ret >=3D 0) { + args->adapter_luid =3D tmp; + ret =3D copy_to_user(inargs, args, sizeof(*args)); + if (ret) { + pr_err("%s failed to copy args", __func__); + ret =3D -EINVAL; + } + } + dxgadapter_release_lock_shared(adapter); + } + +cleanup: + if (args) + vfree(args); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + static int dxgkp_enum_adapters(struct dxgprocess *process, union d3dkmt_enumadapters_filter filter, @@ -3401,6 +3461,43 @@ dxgk_update_alloc_property(struct dxgprocess *proces= s, void *__user inargs) return ret; } =20 +static int +dxgk_mark_device_as_error(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmt_markdeviceaserror args; + struct dxgadapter *adapter =3D NULL; + struct dxgdevice *device =3D NULL; + int ret; + + pr_debug("ioctl: %s", __func__); + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + device =3D dxgprocess_device_by_handle(process, args.device); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + device->execution_state =3D _D3DKMT_DEVICEEXECUTION_RESET; + ret =3D dxgvmb_send_mark_device_as_error(process, adapter, &args); +cleanup: + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + static int dxgk_query_alloc_residency(struct dxgprocess *process, void *__user inargs) { @@ -3560,6 +3657,54 @@ dxgk_change_vidmem_reservation(struct dxgprocess *pr= ocess, void *__user inargs) return ret; } =20 +static int +dxgk_query_clock_calibration(struct dxgprocess *process, void *__user inar= gs) +{ + struct d3dkmt_queryclockcalibration args; + int ret; + struct dxgadapter *adapter =3D NULL; + bool adapter_locked =3D false; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D dxgprocess_adapter_by_handle(process, args.adapter); + if (adapter =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + adapter_locked =3D true; + + args.adapter =3D adapter->host_handle; + ret =3D dxgvmb_send_query_clock_calibration(process, adapter, + &args, inargs); + if (ret < 0) + goto cleanup; + ret =3D copy_to_user(inargs, &args, sizeof(args)); + if (ret) { + pr_err("%s failed to copy output args", __func__); + ret =3D -EINVAL; + } + +cleanup: + + if (adapter_locked) + dxgadapter_release_lock_shared(adapter); + if (adapter) + kref_put(&adapter->adapter_kref, dxgadapter_release); + return ret; +} + static int dxgk_flush_heap_transitions(struct dxgprocess *process, void *__user inarg= s) { @@ -3607,6 +3752,46 @@ dxgk_flush_heap_transitions(struct dxgprocess *proce= ss, void *__user inargs) return ret; } =20 +static int +dxgk_escape(struct dxgprocess *process, void *__user inargs) +{ + struct d3dkmt_escape args; + int ret; + struct dxgadapter *adapter =3D NULL; + bool adapter_locked =3D false; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D dxgprocess_adapter_by_handle(process, args.adapter); + if (adapter =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + adapter_locked =3D true; + + args.adapter =3D adapter->host_handle; + ret =3D dxgvmb_send_escape(process, adapter, &args); + +cleanup: + + if (adapter_locked) + dxgadapter_release_lock_shared(adapter); + if (adapter) + kref_put(&adapter->adapter_kref, dxgadapter_release); + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + static int dxgk_query_vidmem_info(struct dxgprocess *process, void *__user inargs) { @@ -4507,6 +4692,8 @@ void init_ioctls(void) LX_DXQUERYADAPTERINFO); SET_IOCTL(/*0xa */ dxgk_query_vidmem_info, LX_DXQUERYVIDEOMEMORYINFO); + SET_IOCTL(/*0xd */ dxgk_escape, + LX_DXESCAPE); SET_IOCTL(/*0xe */ dxgk_get_device_state, LX_DXGETDEVICESTATE); SET_IOCTL(/*0xf */ dxgk_submit_command, @@ -4547,6 +4734,8 @@ void init_ioctls(void) LX_DXINVALIDATECACHE); SET_IOCTL(/*0x25 */ dxgk_lock2, LX_DXLOCK2); + SET_IOCTL(/*0x26 */ dxgk_mark_device_as_error, + LX_DXMARKDEVICEASERROR); SET_IOCTL(/*0x28 */ dxgk_open_resource, LX_DXOPENRESOURCE); SET_IOCTL(/*0x29 */ dxgk_open_sync_object, @@ -4581,6 +4770,8 @@ void init_ioctls(void) LX_DXWAITFORSYNCHRONIZATIONOBJECTFROMGPU); SET_IOCTL(/*0x3c */ dxgk_get_allocation_priority, LX_DXGETALLOCATIONPRIORITY); + SET_IOCTL(/*0x3d */ dxgk_query_clock_calibration, + LX_DXQUERYCLOCKCALIBRATION); SET_IOCTL(/*0x3e */ dxgk_enum_adapters3, LX_DXENUMADAPTERS3); SET_IOCTL(/*0x3f */ dxgk_share_objects, @@ -4591,6 +4782,8 @@ void init_ioctls(void) LX_DXQUERYRESOURCEINFOFROMNTHANDLE); SET_IOCTL(/*0x42 */ dxgk_open_resource_nt, LX_DXOPENRESOURCEFROMNTHANDLE); + SET_IOCTL(/*0x43 */ dxgk_query_statistics, + LX_DXQUERYSTATISTICS); SET_IOCTL(/*0x44 */ dxgk_share_object_with_host, LX_DXSHAREOBJECTWITHHOST); } --=20 2.35.1 From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 211B1C433FE for ; Sat, 5 Feb 2022 02:35:48 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1379378AbiBECfr (ORCPT ); Fri, 4 Feb 2022 21:35:47 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45148 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1379026AbiBECe1 (ORCPT ); Fri, 4 Feb 2022 21:34:27 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id D1E4420B8766; Fri, 4 Feb 2022 18:34:26 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com D1E4420B8766 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028466; bh=REg1wzAgsHnIu7eVFzviONLszSqaQDbxJ41Fb0yEQf8=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=ik9xm+LIvlq8njg36bYHYWT750B3+QPEV5WoRaNxowJhOlb8xZdqJqSJzkzucLyiH jYjswF0oOG9uqx5W2N8j+AvwoOLLgqIRWBwTWRxorkxvUlnFB38z0jtlGAWcEfv8r8 QB/28Tqe9Y+YJ0B/cXXC2cByK7jrBPUh3sLCk/94= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 20/24] drivers: hv: dxgkrnl: IOCTLs to offer and reclaim allocations Date: Fri, 4 Feb 2022 18:34:18 -0800 Message-Id: <874915869e5d0e1fb3446bfdfab25ab94599dfd8.1644025661.git.iourit@linux.microsoft.com> X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" LX_DXOFFERALLOCATIONS {D3DKMTOfferAllocations), LX_DXRECLAIMALLOCATIONS2 (D3DKMTReclaimAllocations) When a user mode driver does not need to access an allocation, it can "offer" it. This means that the allocation is not in use and it local device memory could be reclaimed and given to another allocation. When the allocation is again needed, the UMD can attempt to"reclaim" the allocation. If the allocation is still in the device local memory, the reclaim operation succeeds. If not the called must restore the content of the allocation before it can be used by the device. The IOCTLs are implemented by sending messages to the host and returning results back to the caller. Signed-off-by: Iouri Tarassov --- drivers/hv/dxgkrnl/dxgkrnl.h | 8 +++ drivers/hv/dxgkrnl/dxgvmbus.c | 122 ++++++++++++++++++++++++++++++++++ drivers/hv/dxgkrnl/ioctl.c | 119 +++++++++++++++++++++++++++++++++ 3 files changed, 249 insertions(+) diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index 8310dd9b7843..52d7d74a93e4 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -839,6 +839,14 @@ int dxgvmb_send_set_allocation_priority(struct dxgproc= ess *process, int dxgvmb_send_get_allocation_priority(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_getallocationpriority *a); +int dxgvmb_send_offer_allocations(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_offerallocations *args); +int dxgvmb_send_reclaim_allocations(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmthandle device, + struct d3dkmt_reclaimallocations2 *args, + u64 __user *paging_fence_value); int dxgvmb_send_change_vidmem_reservation(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmthandle other_process, diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index f7fcbf62f95b..84034c4fafe2 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -2889,6 +2889,128 @@ int dxgvmb_send_get_allocation_priority(struct dxgp= rocess *process, return ret; } =20 +int dxgvmb_send_offer_allocations(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_offerallocations *args) +{ + struct dxgkvmb_command_offerallocations *command; + int ret =3D -EINVAL; + u32 alloc_size =3D sizeof(struct d3dkmthandle) * args->allocation_count; + u32 cmd_size =3D sizeof(struct dxgkvmb_command_offerallocations) + + alloc_size - sizeof(struct d3dkmthandle); + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, adapter, process, cmd_size); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_OFFERALLOCATIONS, + process->host_handle); + command->flags =3D args->flags; + command->priority =3D args->priority; + command->device =3D args->device; + command->allocation_count =3D args->allocation_count; + if (args->resources) { + command->resources =3D true; + ret =3D copy_from_user(command->allocations, args->resources, + alloc_size); + } else { + ret =3D copy_from_user(command->allocations, + args->allocations, alloc_size); + } + if (ret) { + pr_err("%s failed to copy input handles", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, msg.size); + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +int dxgvmb_send_reclaim_allocations(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmthandle device, + struct d3dkmt_reclaimallocations2 *args, + u64 __user *paging_fence_value) +{ + struct dxgkvmb_command_reclaimallocations *command; + struct dxgkvmb_command_reclaimallocations_return *result; + int ret; + u32 alloc_size =3D sizeof(struct d3dkmthandle) * args->allocation_count; + u32 cmd_size =3D sizeof(struct dxgkvmb_command_reclaimallocations) + + alloc_size - sizeof(struct d3dkmthandle); + u32 result_size =3D sizeof(*result); + struct dxgvmbusmsgres msg =3D {.hdr =3D NULL}; + + if (args->results) + result_size +=3D (args->allocation_count - 1) * + sizeof(enum d3dddi_reclaim_result); + + ret =3D init_message_res(&msg, adapter, process, cmd_size, result_size); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + result =3D msg.res; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_RECLAIMALLOCATIONS, + process->host_handle); + command->device =3D device; + command->paging_queue =3D args->paging_queue; + command->allocation_count =3D args->allocation_count; + command->write_results =3D args->results !=3D NULL; + if (args->resources) { + command->resources =3D true; + ret =3D copy_from_user(command->allocations, args->resources, + alloc_size); + } else { + ret =3D copy_from_user(command->allocations, + args->allocations, alloc_size); + } + if (ret) { + pr_err("%s failed to copy input handles", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, + result, msg.res_size); + if (ret < 0) + goto cleanup; + ret =3D copy_to_user(paging_fence_value, + &result->paging_fence_value, sizeof(u64)); + if (ret) { + pr_err("%s failed to copy paging fence", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D ntstatus2int(result->status); + if (NT_SUCCESS(result->status) && args->results) { + ret =3D copy_to_user(args->results, result->discarded, + sizeof(result->discarded[0]) * + args->allocation_count); + if (ret) { + pr_err("%s failed to copy results", __func__); + ret =3D -EINVAL; + } + } + +cleanup: + free_message((struct dxgvmbusmsg *)&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + int dxgvmb_send_change_vidmem_reservation(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmthandle other_process, diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index 6c9b6e6ea296..3370e5de4314 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -2010,6 +2010,121 @@ dxgk_destroy_allocation(struct dxgprocess *process,= void *__user inargs) return ret; } =20 +static int +dxgk_offer_allocations(struct dxgprocess *process, void *__user inargs) +{ + int ret; + struct d3dkmt_offerallocations args; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + + pr_debug("ioctl: %s", __func__); + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.allocation_count > D3DKMT_MAKERESIDENT_ALLOC_MAX || + args.allocation_count =3D=3D 0) { + pr_err("invalid number of allocations"); + ret =3D -EINVAL; + goto cleanup; + } + + if ((args.resources =3D=3D NULL) =3D=3D (args.allocations =3D=3D NULL)) { + pr_err("invalid pointer to resources/allocations"); + ret =3D -EINVAL; + goto cleanup; + } + + device =3D dxgprocess_device_by_handle(process, args.device); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_offer_allocations(process, adapter, &args); + +cleanup: + + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_reclaim_allocations(struct dxgprocess *process, void *__user inargs) +{ + int ret; + struct d3dkmt_reclaimallocations2 args; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + struct d3dkmt_reclaimallocations2 * __user in_args =3D inargs; + + pr_debug("ioctl: %s", __func__); + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.allocation_count > D3DKMT_MAKERESIDENT_ALLOC_MAX || + args.allocation_count =3D=3D 0) { + pr_err("invalid number of allocations"); + ret =3D -EINVAL; + goto cleanup; + } + + if ((args.resources =3D=3D NULL) =3D=3D (args.allocations =3D=3D NULL)) { + pr_err("invalid pointer to resources/allocations"); + ret =3D -EINVAL; + goto cleanup; + } + + device =3D dxgprocess_device_by_object_handle(process, + HMGRENTRY_TYPE_DXGPAGINGQUEUE, + args.paging_queue); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_reclaim_allocations(process, adapter, + device->handle, &args, + &in_args->paging_fence_value); + +cleanup: + + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + static int dxgk_submit_command(struct dxgprocess *process, void *__user inargs) { @@ -4736,6 +4851,8 @@ void init_ioctls(void) LX_DXLOCK2); SET_IOCTL(/*0x26 */ dxgk_mark_device_as_error, LX_DXMARKDEVICEASERROR); + SET_IOCTL(/*0x27 */ dxgk_offer_allocations, + LX_DXOFFERALLOCATIONS); SET_IOCTL(/*0x28 */ dxgk_open_resource, LX_DXOPENRESOURCE); SET_IOCTL(/*0x29 */ dxgk_open_sync_object, @@ -4744,6 +4861,8 @@ void init_ioctls(void) LX_DXQUERYALLOCATIONRESIDENCY); SET_IOCTL(/*0x2b */ dxgk_query_resource_info, LX_DXQUERYRESOURCEINFO); + SET_IOCTL(/*0x2c */ dxgk_reclaim_allocations, + LX_DXRECLAIMALLOCATIONS2); SET_IOCTL(/*0x2d */ dxgk_render, LX_DXRENDER); SET_IOCTL(/*0x2e */ dxgk_set_allocation_priority, --=20 2.35.1 From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id A6703C433F5 for ; Sat, 5 Feb 2022 02:35:50 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S244924AbiBECft (ORCPT ); Fri, 4 Feb 2022 21:35:49 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45152 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1379027AbiBECe1 (ORCPT ); Fri, 4 Feb 2022 21:34:27 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id 0906120B8767; Fri, 4 Feb 2022 18:34:27 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com 0906120B8767 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028467; bh=DuzXMHcZ96cA1pXst1JBDrvagkC2PbXVSU+HSg2RTK8=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=IV6q/ecF1i/mfYCcfqsU1uEcDYVHIGuqZZOi0M0hK/kP/ZKrWC2Ag4UMaworzh+TM 5NRCdSnqlPhSnm97OewSiYXMWG/AeuRyCL0sd53Fi+cKQsOiDbxtLIJJoQFqrZ2GAk 2/Mf7sOQX9h9YEkF/ny9xpsDFK9CamnEy8raW78o= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 21/24] drivers: hv: dxgkrnl: Ioctls to set/get scheduling priority Date: Fri, 4 Feb 2022 18:34:19 -0800 Message-Id: X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" LX_DXGETCONTEXTINPROCESSSCHEDULINGPRIORITY LX_DXGETCONTEXTSCHEDULINGPRIORITY LX_DXSETCONTEXTINPROCESSSCHEDULINGPRIORITY LX_DXSETCONTEXTSCHEDULINGPRIORITY A GPU context could have an assigned scheduling priority. The host dxgkrnl driver submits work from contexts to GPU, based on the priority of the contexts. The IOCTLs simply send requests to the host and return the result back to the caller. Signed-off-by: Iouri Tarassov --- drivers/hv/dxgkrnl/dxgkrnl.h | 9 ++ drivers/hv/dxgkrnl/dxgvmbus.c | 63 +++++++++++++ drivers/hv/dxgkrnl/ioctl.c | 173 ++++++++++++++++++++++++++++++++++ 3 files changed, 245 insertions(+) diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index 52d7d74a93e4..eebb9cee39c3 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -839,6 +839,15 @@ int dxgvmb_send_set_allocation_priority(struct dxgproc= ess *process, int dxgvmb_send_get_allocation_priority(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_getallocationpriority *a); +int dxgvmb_send_set_context_sch_priority(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmthandle context, + int priority, bool in_process); +int dxgvmb_send_get_context_sch_priority(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmthandle context, + int *priority, + bool in_process); int dxgvmb_send_offer_allocations(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_offerallocations *args); diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index 84034c4fafe2..2b64d53685a0 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -2889,6 +2889,69 @@ int dxgvmb_send_get_allocation_priority(struct dxgpr= ocess *process, return ret; } =20 +int dxgvmb_send_set_context_sch_priority(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmthandle context, + int priority, + bool in_process) +{ + struct dxgkvmb_command_setcontextschedulingpriority2 *command; + int ret; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, adapter, process, sizeof(*command)); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_SETCONTEXTSCHEDULINGPRIORITY, + process->host_handle); + command->context =3D context; + command->priority =3D priority; + command->in_process =3D in_process; + ret =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, msg.size); +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +int dxgvmb_send_get_context_sch_priority(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmthandle context, + int *priority, + bool in_process) +{ + struct dxgkvmb_command_getcontextschedulingpriority *command; + struct dxgkvmb_command_getcontextschedulingpriority_return result =3D { }; + int ret; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, adapter, process, sizeof(*command)); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_GETCONTEXTSCHEDULINGPRIORITY, + process->host_handle); + command->context =3D context; + command->in_process =3D in_process; + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, + &result, sizeof(result)); + if (ret >=3D 0) { + ret =3D ntstatus2int(result.status); + *priority =3D result.priority; + } +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + int dxgvmb_send_offer_allocations(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_offerallocations *args) diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index 3370e5de4314..61bdc9a91903 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -3724,6 +3724,171 @@ dxgk_get_allocation_priority(struct dxgprocess *pro= cess, void *__user inargs) return ret; } =20 +static int +set_context_scheduling_priority(struct dxgprocess *process, + struct d3dkmthandle hcontext, + int priority, bool in_process) +{ + int ret =3D 0; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + + device =3D dxgprocess_device_by_object_handle(process, + HMGRENTRY_TYPE_DXGCONTEXT, + hcontext); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + ret =3D dxgvmb_send_set_context_sch_priority(process, adapter, + hcontext, priority, + in_process); + if (ret < 0) + pr_err("send_set_context_scheduling_priority failed"); +cleanup: + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + return ret; +} + +static int +dxgk_set_context_scheduling_priority(struct dxgprocess *process, + void *__user inargs) +{ + struct d3dkmt_setcontextschedulingpriority args; + int ret; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D set_context_scheduling_priority(process, args.context, + args.priority, false); +cleanup: + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +get_context_scheduling_priority(struct dxgprocess *process, + struct d3dkmthandle hcontext, + int __user *priority, + bool in_process) +{ + int ret; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + int pri =3D 0; + + device =3D dxgprocess_device_by_object_handle(process, + HMGRENTRY_TYPE_DXGCONTEXT, + hcontext); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + ret =3D dxgvmb_send_get_context_sch_priority(process, adapter, + hcontext, &pri, in_process); + if (ret < 0) + goto cleanup; + ret =3D copy_to_user(priority, &pri, sizeof(pri)); + if (ret) { + pr_err("%s failed to copy priority to user", __func__); + ret =3D -EINVAL; + } + +cleanup: + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + return ret; +} + +static int +dxgk_get_context_scheduling_priority(struct dxgprocess *process, + void *__user inargs) +{ + struct d3dkmt_getcontextschedulingpriority args; + struct d3dkmt_getcontextschedulingpriority __user *input =3D inargs; + int ret; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D get_context_scheduling_priority(process, args.context, + &input->priority, false); +cleanup: + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_set_context_process_scheduling_priority(struct dxgprocess *process, + void *__user inargs) +{ + struct d3dkmt_setcontextinprocessschedulingpriority args; + int ret; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D set_context_scheduling_priority(process, args.context, + args.priority, true); +cleanup: + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_get_context_process_scheduling_priority(struct dxgprocess *process, + void __user *inargs) +{ + struct d3dkmt_getcontextinprocessschedulingpriority args; + int ret; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D get_context_scheduling_priority(process, args.context, + &((struct d3dkmt_getcontextinprocessschedulingpriority *) + inargs)->priority, true); +cleanup: + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + static int dxgk_change_vidmem_reservation(struct dxgprocess *process, void *__user in= args) { @@ -4843,6 +5008,10 @@ void init_ioctls(void) LX_DXDESTROYSYNCHRONIZATIONOBJECT); SET_IOCTL(/*0x1f */ dxgk_flush_heap_transitions, LX_DXFLUSHHEAPTRANSITIONS); + SET_IOCTL(/*0x21 */ dxgk_get_context_process_scheduling_priority, + LX_DXGETCONTEXTINPROCESSSCHEDULINGPRIORITY); + SET_IOCTL(/*0x22 */ dxgk_get_context_scheduling_priority, + LX_DXGETCONTEXTSCHEDULINGPRIORITY); SET_IOCTL(/*0x23 */ dxgk_get_shared_resource_adapter_luid, LX_DXGETSHAREDRESOURCEADAPTERLUID); SET_IOCTL(/*0x24 */ dxgk_invalidate_cache, @@ -4867,6 +5036,10 @@ void init_ioctls(void) LX_DXRENDER); SET_IOCTL(/*0x2e */ dxgk_set_allocation_priority, LX_DXSETALLOCATIONPRIORITY); + SET_IOCTL(/*0x2f */ dxgk_set_context_process_scheduling_priority, + LX_DXSETCONTEXTINPROCESSSCHEDULINGPRIORITY); + SET_IOCTL(/*0x30 */ dxgk_set_context_scheduling_priority, + LX_DXSETCONTEXTSCHEDULINGPRIORITY); SET_IOCTL(/*0x31 */ dxgk_signal_sync_object_cpu, LX_DXSIGNALSYNCHRONIZATIONOBJECTFROMCPU); SET_IOCTL(/*0x32 */ dxgk_signal_sync_object_gpu, --=20 2.35.1 From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 71180C433F5 for ; Sat, 5 Feb 2022 02:35:54 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1379403AbiBECfx (ORCPT ); Fri, 4 Feb 2022 21:35:53 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45154 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1379029AbiBECe1 (ORCPT ); Fri, 4 Feb 2022 21:34:27 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id 3138420B8769; Fri, 4 Feb 2022 18:34:27 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com 3138420B8769 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028467; bh=99UP3cnEF3/f5M3gd4wk5ndz7/g7hC8jubu6pPc0/Yc=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=p8fJrQKGNa/9u4HpN0cNXOfRfLALWyn5vJy8avTEouOejKLZWVfgx/SuOZjfkEF/r D+gm6sfD1g/yjpj/uL12etV41fW8Tr9PW9Stl4f5f0thtt0cgUSoJgIEXKF50xtDgE YZCwNxdlRzjFphgJfeyAllVRKOHdZhSc5z2Y3Ch4= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 22/24] drivers: hv: dxgkrnl: IOCTLs to manage allocation residency Date: Fri, 4 Feb 2022 18:34:20 -0800 Message-Id: <32cf9cd4bd2dbb766d45dd50de983a71c78dca33.1644025661.git.iourit@linux.microsoft.com> X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" LX_DXMAKERESIDENT (D3DKMTMakeResident) LX_DXEVICT (D3DKMTEvict) An allocation is resident when GPU is setup to access it. The current WDDM design does not support on demand GPU page faulting. An allocation must be resident (be in the local device memory or in non-pageable system memory) before GPU is allowed to access it. Applications need to call D3DKMTMAkeResident to make an allocation resident and D3DKMTEvict to evict it from GPU accessible memory. The IOCTLs send the requests to the host and return the result back. Signed-off-by: Iouri Tarassov --- drivers/hv/dxgkrnl/dxgkrnl.h | 4 + drivers/hv/dxgkrnl/dxgvmbus.c | 98 +++++++++++++++++++++++ drivers/hv/dxgkrnl/ioctl.c | 144 ++++++++++++++++++++++++++++++++++ 3 files changed, 246 insertions(+) diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index eebb9cee39c3..70cb31654aac 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -784,6 +784,10 @@ int dxgvmb_send_create_allocation(struct dxgprocess *p= r, struct dxgdevice *dev, int dxgvmb_send_destroy_allocation(struct dxgprocess *pr, struct dxgdevice= *dev, struct d3dkmt_destroyallocation2 *args, struct d3dkmthandle *alloc_handles); +int dxgvmb_send_make_resident(struct dxgprocess *pr, struct dxgadapter *ad= apter, + struct d3dddi_makeresident *args); +int dxgvmb_send_evict(struct dxgprocess *pr, struct dxgadapter *adapter, + struct d3dkmt_evict *args); int dxgvmb_send_submit_command(struct dxgprocess *pr, struct dxgadapter *adapter, struct d3dkmt_submitcommand *args); diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index 2b64d53685a0..4299127af863 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -2224,6 +2224,104 @@ int dxgvmb_send_get_stdalloc_data(struct dxgdevice = *device, return ret; } =20 +int dxgvmb_send_make_resident(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dddi_makeresident *args) +{ + int ret; + u32 cmd_size; + struct dxgkvmb_command_makeresident_return result =3D { }; + struct dxgkvmb_command_makeresident *command =3D NULL; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + cmd_size =3D (args->alloc_count - 1) * sizeof(struct d3dkmthandle) + + sizeof(struct dxgkvmb_command_makeresident); + + ret =3D init_message(&msg, adapter, process, cmd_size); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + ret =3D copy_from_user(command->allocations, args->allocation_list, + args->alloc_count * + sizeof(struct d3dkmthandle)); + if (ret) { + pr_err("%s failed to copy alloc handles", __func__); + ret =3D -EINVAL; + goto cleanup; + } + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_MAKERESIDENT, + process->host_handle); + command->alloc_count =3D args->alloc_count; + command->paging_queue =3D args->paging_queue; + command->flags =3D args->flags; + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, + &result, sizeof(result)); + if (ret < 0) { + pr_err("send_make_resident failed %x", ret); + goto cleanup; + } + + args->paging_fence_value =3D result.paging_fence_value; + args->num_bytes_to_trim =3D result.num_bytes_to_trim; + ret =3D ntstatus2int(result.status); + +cleanup: + + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +int dxgvmb_send_evict(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_evict *args) +{ + int ret; + u32 cmd_size; + struct dxgkvmb_command_evict_return result =3D { }; + struct dxgkvmb_command_evict *command =3D NULL; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + cmd_size =3D (args->alloc_count - 1) * sizeof(struct d3dkmthandle) + + sizeof(struct dxgkvmb_command_evict); + ret =3D init_message(&msg, adapter, process, cmd_size); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + ret =3D copy_from_user(command->allocations, args->allocations, + args->alloc_count * + sizeof(struct d3dkmthandle)); + if (ret) { + pr_err("%s failed to copy alloc handles", __func__); + ret =3D -EINVAL; + goto cleanup; + } + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_EVICT, process->host_handle); + command->alloc_count =3D args->alloc_count; + command->device =3D args->device; + command->flags =3D args->flags; + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, + &result, sizeof(result)); + if (ret < 0) { + pr_err("send_evict failed %x", ret); + goto cleanup; + } + args->num_bytes_to_trim =3D result.num_bytes_to_trim; + +cleanup: + + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + int dxgvmb_send_submit_command(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_submitcommand *args) diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index 61bdc9a91903..317a4f2938d1 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -2010,6 +2010,146 @@ dxgk_destroy_allocation(struct dxgprocess *process,= void *__user inargs) return ret; } =20 +static int +dxgk_make_resident(struct dxgprocess *process, void *__user inargs) +{ + int ret, ret2; + struct d3dddi_makeresident args; + struct d3dddi_makeresident *input =3D inargs; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + + pr_debug("ioctl: %s", __func__); + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.alloc_count > D3DKMT_MAKERESIDENT_ALLOC_MAX || + args.alloc_count =3D=3D 0) { + pr_err("invalid number of allocations"); + ret =3D -EINVAL; + goto cleanup; + } + if (args.paging_queue.v =3D=3D 0) { + pr_err("paging queue is missing"); + ret =3D -EINVAL; + goto cleanup; + } + + device =3D dxgprocess_device_by_object_handle(process, + HMGRENTRY_TYPE_DXGPAGINGQUEUE, + args.paging_queue); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_make_resident(process, adapter, &args); + if (ret < 0) + goto cleanup; + /* STATUS_PENING is a success code > 0. It is returned to user mode */ + if (!(ret =3D=3D STATUS_PENDING || ret =3D=3D 0)) { + pr_err("%s Unexpected error %x", __func__, ret); + goto cleanup; + } + + ret2 =3D copy_to_user(&input->paging_fence_value, + &args.paging_fence_value, sizeof(u64)); + if (ret2) { + pr_err("%s failed to copy paging fence", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + ret2 =3D copy_to_user(&input->num_bytes_to_trim, + &args.num_bytes_to_trim, sizeof(u64)); + if (ret2) { + pr_err("%s failed to copy bytes to trim", __func__); + ret =3D -EINVAL; + goto cleanup; + } + +cleanup: + + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + + return ret; +} + +static int +dxgk_evict(struct dxgprocess *process, void *__user inargs) +{ + int ret; + struct d3dkmt_evict args; + struct d3dkmt_evict *input =3D inargs; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + + pr_debug("ioctl: %s", __func__); + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + if (args.alloc_count > D3DKMT_MAKERESIDENT_ALLOC_MAX || + args.alloc_count =3D=3D 0) { + pr_err("invalid number of allocations"); + ret =3D -EINVAL; + goto cleanup; + } + + device =3D dxgprocess_device_by_handle(process, args.device); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_evict(process, adapter, &args); + if (ret < 0) + goto cleanup; + + ret =3D copy_to_user(&input->num_bytes_to_trim, + &args.num_bytes_to_trim, sizeof(u64)); + if (ret) { + pr_err("%s failed to copy bytes to trim to user", __func__); + ret =3D -EINVAL; + } +cleanup: + + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + static int dxgk_offer_allocations(struct dxgprocess *process, void *__user inargs) { @@ -4972,6 +5112,8 @@ void init_ioctls(void) LX_DXQUERYADAPTERINFO); SET_IOCTL(/*0xa */ dxgk_query_vidmem_info, LX_DXQUERYVIDEOMEMORYINFO); + SET_IOCTL(/*0xb */ dxgk_make_resident, + LX_DXMAKERESIDENT); SET_IOCTL(/*0xd */ dxgk_escape, LX_DXESCAPE); SET_IOCTL(/*0xe */ dxgk_get_device_state, @@ -5006,6 +5148,8 @@ void init_ioctls(void) LX_DXDESTROYPAGINGQUEUE); SET_IOCTL(/*0x1d */ dxgk_destroy_sync_object, LX_DXDESTROYSYNCHRONIZATIONOBJECT); + SET_IOCTL(/*0x1e */ dxgk_evict, + LX_DXEVICT); SET_IOCTL(/*0x1f */ dxgk_flush_heap_transitions, LX_DXFLUSHHEAPTRANSITIONS); SET_IOCTL(/*0x21 */ dxgk_get_context_process_scheduling_priority, --=20 2.35.1 From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 1C52DC433EF for ; Sat, 5 Feb 2022 02:35:57 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1379429AbiBECf4 (ORCPT ); Fri, 4 Feb 2022 21:35:56 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45156 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1379031AbiBECe1 (ORCPT ); Fri, 4 Feb 2022 21:34:27 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id 5C33420B876A; Fri, 4 Feb 2022 18:34:27 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com 5C33420B876A DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028467; bh=eDbYbBvNHVyaqdTAIrUnMr41QRli6VRpvJQ+JXeSjyI=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=akc2WSDNEyr9QRwprFRiVIZbPVA17oed+kAIzsku/GnxtOs9RvpZJCurm1E1/sIZx mzGapU7MOADPcYuGLORCw0MLednI6BZWA8PUP6eW9M0e7tIZphnoQSR9EFg179vGfG a4ytO1GRpm1o+SUNm10Rz2TEeGuKfwyomnH9zLTs= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 23/24] drivers: hv: dxgkrnl: IOCTLs to handle GPU virtual addressing (GPU VA) Date: Fri, 4 Feb 2022 18:34:21 -0800 Message-Id: <4d66df0e8d589163add6afbc40be340b7740df8d.1644025661.git.iourit@linux.microsoft.com> X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" LX_DXRESERVEGPUVIRTUALADDRESS(D3DKMTReserveGpuVertualAddress) LX_DXFREEGPUVIRTUALADDRESS(D3DKMTFreeGpuVertualAddress) LX_DXMAPGPUVIRTUALADDRESS(D3DKMTMapGpuVertualAddress) LX_DXUPDATEGPUVIRTUALADDRESS(D3DKMTUpdateGpuVertualAddress) WDDM supports accessing GPU memory by using GPU VAs. Each process has a dedicated GPU VA address space. A GPU VA could be reserved, mapped to a GPU allocation, updated or freed. The video memory manager on the host updates GPU page tables for the GPU virtual addresses. The IOCTLs are simply forwarded to the host and return results to the caller. Signed-off-by: Iouri Tarassov --- drivers/hv/dxgkrnl/dxgkrnl.h | 10 ++ drivers/hv/dxgkrnl/dxgvmbus.c | 150 ++++++++++++++++++++++ drivers/hv/dxgkrnl/ioctl.c | 230 ++++++++++++++++++++++++++++++++++ 3 files changed, 390 insertions(+) diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index 70cb31654aac..4a2b4c7611ff 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -791,6 +791,16 @@ int dxgvmb_send_evict(struct dxgprocess *pr, struct dx= gadapter *adapter, int dxgvmb_send_submit_command(struct dxgprocess *pr, struct dxgadapter *adapter, struct d3dkmt_submitcommand *args); +int dxgvmb_send_map_gpu_va(struct dxgprocess *pr, struct d3dkmthandle h, + struct dxgadapter *adapter, + struct d3dddi_mapgpuvirtualaddress *args); +int dxgvmb_send_reserve_gpu_va(struct dxgprocess *pr, + struct dxgadapter *adapter, + struct d3dddi_reservegpuvirtualaddress *args); +int dxgvmb_send_free_gpu_va(struct dxgprocess *pr, struct dxgadapter *adap= ter, + struct d3dkmt_freegpuvirtualaddress *args); +int dxgvmb_send_update_gpu_va(struct dxgprocess *pr, struct dxgadapter *ad= apter, + struct d3dkmt_updategpuvirtualaddress *args); int dxgvmb_send_create_sync_object(struct dxgprocess *pr, struct dxgadapter *adapter, struct d3dkmt_createsynchronizationobject2 diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index 4299127af863..7a4b17938f53 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -2376,6 +2376,156 @@ int dxgvmb_send_submit_command(struct dxgprocess *p= rocess, return ret; } =20 +int dxgvmb_send_map_gpu_va(struct dxgprocess *process, + struct d3dkmthandle device, + struct dxgadapter *adapter, + struct d3dddi_mapgpuvirtualaddress *args) +{ + struct dxgkvmb_command_mapgpuvirtualaddress *command; + struct dxgkvmb_command_mapgpuvirtualaddress_return result; + int ret; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, adapter, process, sizeof(*command)); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_MAPGPUVIRTUALADDRESS, + process->host_handle); + command->args =3D *args; + command->device =3D device; + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, &result, + sizeof(result)); + if (ret < 0) + goto cleanup; + args->virtual_address =3D result.virtual_address; + args->paging_fence_value =3D result.paging_fence_value; + ret =3D ntstatus2int(result.status); + +cleanup: + + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +int dxgvmb_send_reserve_gpu_va(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dddi_reservegpuvirtualaddress *args) +{ + struct dxgkvmb_command_reservegpuvirtualaddress *command; + struct dxgkvmb_command_reservegpuvirtualaddress_return result; + int ret; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, adapter, process, sizeof(*command)); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_RESERVEGPUVIRTUALADDRESS, + process->host_handle); + command->args =3D *args; + + ret =3D dxgvmb_send_sync_msg(msg.channel, msg.hdr, msg.size, &result, + sizeof(result)); + args->virtual_address =3D result.virtual_address; + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +int dxgvmb_send_free_gpu_va(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_freegpuvirtualaddress *args) +{ + struct dxgkvmb_command_freegpuvirtualaddress *command; + int ret; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + ret =3D init_message(&msg, adapter, process, sizeof(*command)); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_FREEGPUVIRTUALADDRESS, + process->host_handle); + command->args =3D *args; + + ret =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, msg.size); + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + +int dxgvmb_send_update_gpu_va(struct dxgprocess *process, + struct dxgadapter *adapter, + struct d3dkmt_updategpuvirtualaddress *args) +{ + struct dxgkvmb_command_updategpuvirtualaddress *command; + u32 cmd_size; + u32 op_size; + int ret; + struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; + + if (args->num_operations =3D=3D 0 || + (DXG_MAX_VM_BUS_PACKET_SIZE / + sizeof(struct d3dddi_updategpuvirtualaddress_operation)) < + args->num_operations) { + ret =3D -EINVAL; + pr_err("Invalid number of operations: %d", + args->num_operations); + goto cleanup; + } + + op_size =3D args->num_operations * + sizeof(struct d3dddi_updategpuvirtualaddress_operation); + cmd_size =3D sizeof(struct dxgkvmb_command_updategpuvirtualaddress) + + op_size - sizeof(args->operations[0]); + + ret =3D init_message(&msg, adapter, process, cmd_size); + if (ret) + goto cleanup; + command =3D (void *)msg.msg; + + command_vgpu_to_host_init2(&command->hdr, + DXGK_VMBCOMMAND_UPDATEGPUVIRTUALADDRESS, + process->host_handle); + command->fence_value =3D args->fence_value; + command->device =3D args->device; + command->context =3D args->context; + command->fence_object =3D args->fence_object; + command->num_operations =3D args->num_operations; + command->flags =3D args->flags.value; + ret =3D copy_from_user(command->operations, args->operations, + op_size); + if (ret) { + pr_err("%s failed to copy operations", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, msg.size); + +cleanup: + free_message(&msg, process); + if (ret) + pr_debug("err: %s %d", __func__, ret); + return ret; +} + static void set_result(struct d3dkmt_createsynchronizationobject2 *args, u64 fence_gpu_va, u8 *va) { diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index 317a4f2938d1..26bdcdfeba86 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -2549,6 +2549,228 @@ dxgk_submit_wait_to_hwqueue(struct dxgprocess *proc= ess, void *__user inargs) return ret; } =20 +static int +dxgk_map_gpu_va(struct dxgprocess *process, void *__user inargs) +{ + int ret, ret2; + struct d3dddi_mapgpuvirtualaddress args; + struct d3dddi_mapgpuvirtualaddress *input =3D inargs; + struct dxgdevice *device =3D NULL; + struct dxgadapter *adapter =3D NULL; + + pr_debug("ioctl: %s", __func__); + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + device =3D dxgprocess_device_by_object_handle(process, + HMGRENTRY_TYPE_DXGPAGINGQUEUE, + args.paging_queue); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_map_gpu_va(process, zerohandle, adapter, &args); + if (ret < 0) + goto cleanup; + /* STATUS_PENING is a success code > 0. It is returned to user mode */ + if (!(ret =3D=3D STATUS_PENDING || ret =3D=3D 0)) { + pr_err("%s Unexpected error %x", __func__, ret); + goto cleanup; + } + + ret2 =3D copy_to_user(&input->paging_fence_value, + &args.paging_fence_value, sizeof(u64)); + if (ret2) { + pr_err("%s failed to copy paging fence to user", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + ret2 =3D copy_to_user(&input->virtual_address, &args.virtual_address, + sizeof(args.virtual_address)); + if (ret2) { + pr_err("%s failed to copy va to user", __func__); + ret =3D -EINVAL; + goto cleanup; + } + +cleanup: + + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_reserve_gpu_va(struct dxgprocess *process, void *__user inargs) +{ + int ret; + struct d3dddi_reservegpuvirtualaddress args; + struct d3dddi_reservegpuvirtualaddress *input =3D inargs; + struct dxgadapter *adapter =3D NULL; + struct dxgdevice *device =3D NULL; + + pr_debug("ioctl: %s", __func__); + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D dxgprocess_adapter_by_handle(process, args.adapter); + if (adapter =3D=3D NULL) { + device =3D dxgprocess_device_by_object_handle(process, + HMGRENTRY_TYPE_DXGPAGINGQUEUE, + args.adapter); + if (device =3D=3D NULL) { + pr_err("invalid adapter or paging queue: 0x%x", + args.adapter.v); + ret =3D -EINVAL; + goto cleanup; + } + adapter =3D device->adapter; + kref_get(&adapter->adapter_kref); + kref_put(&device->device_kref, dxgdevice_release); + } else { + args.adapter =3D adapter->host_handle; + } + + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + kref_put(&adapter->adapter_kref, dxgadapter_release); + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_reserve_gpu_va(process, adapter, &args); + if (ret < 0) + goto cleanup; + + ret =3D copy_to_user(&input->virtual_address, &args.virtual_address, + sizeof(args.virtual_address)); + if (ret) { + pr_err("%s failed to copy VA to user", __func__); + ret =3D -EINVAL; + } + +cleanup: + + if (adapter) { + dxgadapter_release_lock_shared(adapter); + kref_put(&adapter->adapter_kref, dxgadapter_release); + } + + pr_debug("ioctl:%s %s %d", errorstr(ret), __func__, ret); + return ret; +} + +static int +dxgk_free_gpu_va(struct dxgprocess *process, void *__user inargs) +{ + int ret; + struct d3dkmt_freegpuvirtualaddress args; + struct dxgadapter *adapter =3D NULL; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D dxgprocess_adapter_by_handle(process, args.adapter); + if (adapter =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + kref_put(&adapter->adapter_kref, dxgadapter_release); + adapter =3D NULL; + goto cleanup; + } + + args.adapter =3D adapter->host_handle; + ret =3D dxgvmb_send_free_gpu_va(process, adapter, &args); + +cleanup: + + if (adapter) { + dxgadapter_release_lock_shared(adapter); + kref_put(&adapter->adapter_kref, dxgadapter_release); + } + + return ret; +} + +static int +dxgk_update_gpu_va(struct dxgprocess *process, void *__user inargs) +{ + int ret; + struct d3dkmt_updategpuvirtualaddress args; + struct d3dkmt_updategpuvirtualaddress *input =3D inargs; + struct dxgadapter *adapter =3D NULL; + struct dxgdevice *device =3D NULL; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + pr_err("%s failed to copy input args", __func__); + ret =3D -EINVAL; + goto cleanup; + } + + device =3D dxgprocess_device_by_handle(process, args.device); + if (device =3D=3D NULL) { + ret =3D -EINVAL; + goto cleanup; + } + + adapter =3D device->adapter; + ret =3D dxgadapter_acquire_lock_shared(adapter); + if (ret < 0) { + adapter =3D NULL; + goto cleanup; + } + + ret =3D dxgvmb_send_update_gpu_va(process, adapter, &args); + if (ret < 0) + goto cleanup; + + ret =3D copy_to_user(&input->fence_value, &args.fence_value, + sizeof(args.fence_value)); + if (ret) { + pr_err("%s failed to copy fence value to user", __func__); + ret =3D -EINVAL; + } + +cleanup: + + if (adapter) + dxgadapter_release_lock_shared(adapter); + if (device) + kref_put(&device->device_kref, dxgdevice_release); + + return ret; +} + static int dxgk_create_sync_object(struct dxgprocess *process, void *__user inargs) { @@ -5108,12 +5330,16 @@ void init_ioctls(void) LX_DXCREATEALLOCATION); SET_IOCTL(/*0x7 */ dxgk_create_paging_queue, LX_DXCREATEPAGINGQUEUE); + SET_IOCTL(/*0x8 */ dxgk_reserve_gpu_va, + LX_DXRESERVEGPUVIRTUALADDRESS); SET_IOCTL(/*0x9 */ dxgk_query_adapter_info, LX_DXQUERYADAPTERINFO); SET_IOCTL(/*0xa */ dxgk_query_vidmem_info, LX_DXQUERYVIDEOMEMORYINFO); SET_IOCTL(/*0xb */ dxgk_make_resident, LX_DXMAKERESIDENT); + SET_IOCTL(/*0xc */ dxgk_map_gpu_va, + LX_DXMAPGPUVIRTUALADDRESS); SET_IOCTL(/*0xd */ dxgk_escape, LX_DXESCAPE); SET_IOCTL(/*0xe */ dxgk_get_device_state, @@ -5152,6 +5378,8 @@ void init_ioctls(void) LX_DXEVICT); SET_IOCTL(/*0x1f */ dxgk_flush_heap_transitions, LX_DXFLUSHHEAPTRANSITIONS); + SET_IOCTL(/*0x20 */ dxgk_free_gpu_va, + LX_DXFREEGPUVIRTUALADDRESS); SET_IOCTL(/*0x21 */ dxgk_get_context_process_scheduling_priority, LX_DXGETCONTEXTINPROCESSSCHEDULINGPRIORITY); SET_IOCTL(/*0x22 */ dxgk_get_context_scheduling_priority, @@ -5200,6 +5428,8 @@ void init_ioctls(void) LX_DXUNLOCK2); SET_IOCTL(/*0x38 */ dxgk_update_alloc_property, LX_DXUPDATEALLOCPROPERTY); + SET_IOCTL(/*0x39 */ dxgk_update_gpu_va, + LX_DXUPDATEGPUVIRTUALADDRESS); SET_IOCTL(/*0x3a */ dxgk_wait_sync_object_cpu, LX_DXWAITFORSYNCHRONIZATIONOBJECTFROMCPU); SET_IOCTL(/*0x3b */ dxgk_wait_sync_object_gpu, --=20 2.35.1 From nobody Tue Jun 30 19:34:03 2026 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 vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 7A2DAC433EF for ; Sat, 5 Feb 2022 02:35:59 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1379450AbiBECf6 (ORCPT ); Fri, 4 Feb 2022 21:35:58 -0500 Received: from linux.microsoft.com ([13.77.154.182]:45114 "EHLO linux.microsoft.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1379090AbiBECel (ORCPT ); Fri, 4 Feb 2022 21:34:41 -0500 Received: from IOURIT-Z4.ntdev.corp.microsoft.com (unknown [192.182.151.181]) by linux.microsoft.com (Postfix) with ESMTPSA id 8591620B876C; Fri, 4 Feb 2022 18:34:27 -0800 (PST) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com 8591620B876C DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1644028467; bh=QRMNYTPNMSqnVfHuxVfo8vle8yuKMubYRnCcGl9y8+U=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=K7guHpLMlvJGEchvsndrV/smvz8gidzyYtPTL5QjasZpWNWDS3nAIX+FHZWmoj/9Q e4HEAQIRBVnLCHRZD56wvCs2ANFsoswrGXj2TsjV3MVrniyFigKfe2VwCkbxg3gDsX LomQQX6UuS6GhLB7oYTaLkPpf0ddH3kDGtOjPK6I= From: Iouri Tarassov To: kys@microsoft.com, haiyangz@microsoft.com, sthemmin@microsoft.com, wei.liu@kernel.org, linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, spronovo@microsoft.com, gregkh@linuxfoundation.org Subject: [PATCH v2 24/24] drivers: hv: dxgkrnl: Add support to map guest pages by host Date: Fri, 4 Feb 2022 18:34:22 -0800 Message-Id: X-Mailer: git-send-email 2.35.1 In-Reply-To: References: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Type: text/plain; charset="utf-8" Dxgkrnl uses GPADLs to implement GPU allocations around existing system memory. This method has limitations: - a single GPADL can represent only ~32MB of memory - there is a limit of how much memory the total size of GPADLs in a VM can be. To avoid these limitations the host implemented mapping guest pages. Presence of this support is determined by reading PCI config space. When the support is enabled, dxgkrnl does not use GPADLs and instead - pins memory pages of an existing system memory buffer - sends PFNs of the pages to the host via a new VM bus message - the host maps the PFNs to get access to the memory Signed-off-by: Iouri Tarassov --- drivers/hv/dxgkrnl/Makefile | 2 +- drivers/hv/dxgkrnl/dxgkrnl.h | 2 + drivers/hv/dxgkrnl/dxgmodule.c | 30 ++++++- drivers/hv/dxgkrnl/dxgvmbus.c | 145 +++++++++++++++++++++++---------- drivers/hv/dxgkrnl/dxgvmbus.h | 12 +++ drivers/hv/dxgkrnl/ioctl.c | 7 +- drivers/hv/dxgkrnl/misc.c | 6 ++ drivers/hv/dxgkrnl/misc.h | 1 + 8 files changed, 155 insertions(+), 50 deletions(-) diff --git a/drivers/hv/dxgkrnl/Makefile b/drivers/hv/dxgkrnl/Makefile index 745c66bebe5d..eedc678c9c2d 100644 --- a/drivers/hv/dxgkrnl/Makefile +++ b/drivers/hv/dxgkrnl/Makefile @@ -2,4 +2,4 @@ # Makefile for the Linux video drivers. =20 obj-$(CONFIG_DXGKRNL) +=3D dxgkrnl.o -dxgkrnl-y :=3D dxgmodule.o hmgr.o misc.o dxgadapter.o ioctl.o dxgvmbus.o = dxgprocess.o +dxgkrnl-y :=3D dxgmodule.o hmgr.o misc.o dxgadapter.o ioctl.o dxgvmbus.o d= xgprocess.o diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index 4a2b4c7611ff..2f1399ccc668 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -301,6 +301,7 @@ struct dxgglobal { bool pci_registered; bool global_channel_initialized; bool async_msg_enabled; + bool map_guest_pages_enabled; }; =20 extern struct dxgglobal *dxgglobal; @@ -831,6 +832,7 @@ int dxgvmb_send_wait_sync_object_cpu(struct dxgprocess = *process, struct d3dkmt_waitforsynchronizationobjectfromcpu *args, + bool user_address, u64 cpu_event); int dxgvmb_send_lock2(struct dxgprocess *process, struct dxgadapter *adapter, diff --git a/drivers/hv/dxgkrnl/dxgmodule.c b/drivers/hv/dxgkrnl/dxgmodule.c index 3928512bcc64..0447035eb402 100644 --- a/drivers/hv/dxgkrnl/dxgmodule.c +++ b/drivers/hv/dxgkrnl/dxgmodule.c @@ -144,7 +144,7 @@ void dxgglobal_remove_host_event(struct dxghostevent *e= vent) =20 void signal_host_cpu_event(struct dxghostevent *eventhdr) { - struct dxghosteventcpu *event =3D (struct dxghosteventcpu *)eventhdr; + struct dxghosteventcpu *event =3D (struct dxghosteventcpu *)eventhdr; =20 if (event->remove_from_list || event->destroy_after_signal) { @@ -430,6 +430,9 @@ const struct file_operations dxgk_fops =3D { /* Luid of the virtual GPU on the host (struct winluid) */ #define DXGK_VMBUS_VGPU_LUID_OFFSET (DXGK_VMBUS_VERSION_OFFSET + \ sizeof(u32)) +/* The host caps (dxgk_vmbus_hostcaps) */ +#define DXGK_VMBUS_HOSTCAPS_OFFSET (DXGK_VMBUS_VGPU_LUID_OFFSET + \ + sizeof(struct winluid)) /* The guest writes its capavilities to this adderss */ #define DXGK_VMBUS_GUESTCAPS_OFFSET (DXGK_VMBUS_VERSION_OFFSET + \ sizeof(u32)) @@ -445,6 +448,23 @@ struct dxgk_vmbus_guestcaps { }; }; =20 +/* + * The structure defines features, supported by the host. + * + * map_guest_memory + * Host can map guest memory pages, so the guest can avoid using GPADLs + * to represent existing system memory allocations. + */ +struct dxgk_vmbus_hostcaps { + union { + struct { + u32 map_guest_memory : 1; + u32 reserved : 31; + }; + u32 host_caps; + }; +}; + /* * A helper function to read PCI config space. */ @@ -474,6 +494,7 @@ static int dxg_pci_probe_device(struct pci_dev *dev, u32 vmbus_interface_ver =3D DXGK_VMBUS_INTERFACE_VERSION; struct winluid vgpu_luid =3D {}; struct dxgk_vmbus_guestcaps guest_caps =3D {.wsl2 =3D 1}; + struct dxgk_vmbus_hostcaps host_caps =3D {}; =20 mutex_lock(&dxgglobal->device_mutex); =20 @@ -502,6 +523,13 @@ static int dxg_pci_probe_device(struct pci_dev *dev, if (ret) goto cleanup; =20 + ret =3D pci_read_config_dword(dev, DXGK_VMBUS_HOSTCAPS_OFFSET, + &host_caps.host_caps); + if (ret =3D=3D 0) { + if (host_caps.map_guest_memory) + dxgglobal->map_guest_pages_enabled =3D true; + } + if (dxgglobal->vmbus_ver > DXGK_VMBUS_INTERFACE_VERSION) dxgglobal->vmbus_ver =3D DXGK_VMBUS_INTERFACE_VERSION; } diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index 7a4b17938f53..3e8db1843830 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -1336,15 +1336,18 @@ int create_existing_sysmem(struct dxgdevice *device, void *kmem =3D NULL; int ret =3D 0; struct dxgkvmb_command_setexistingsysmemstore *set_store_command; + struct dxgkvmb_command_setexistingsysmempages *set_pages_command; u64 alloc_size =3D host_alloc->allocation_size; u32 npages =3D alloc_size >> PAGE_SHIFT; struct dxgvmbusmsg msg =3D {.hdr =3D NULL}; - - ret =3D init_message(&msg, device->adapter, device->process, - sizeof(*set_store_command)); - if (ret) - goto cleanup; - set_store_command =3D (void *)msg.msg; + const u32 max_pfns_in_message =3D + (DXG_MAX_VM_BUS_PACKET_SIZE - sizeof(*set_pages_command) - + PAGE_SIZE) / sizeof(__u64); + u32 alloc_offset_in_pages =3D 0; + struct page **page_in; + u64 *pfn; + u32 pages_to_send; + u32 i; =20 /* * Create a guest physical address list and set it as the allocation @@ -1355,6 +1358,7 @@ int create_existing_sysmem(struct dxgdevice *device, pr_debug(" Alloc size: %lld", alloc_size); =20 dxgalloc->cpu_address =3D (void *)sysmem; + dxgalloc->pages =3D vzalloc(npages * sizeof(void *)); if (dxgalloc->pages =3D=3D NULL) { pr_err("failed to allocate pages"); @@ -1372,31 +1376,80 @@ int create_existing_sysmem(struct dxgdevice *device, ret =3D -ENOMEM; goto cleanup; } - kmem =3D vmap(dxgalloc->pages, npages, VM_MAP, PAGE_KERNEL); - if (kmem =3D=3D NULL) { - pr_err("vmap failed"); - ret =3D -ENOMEM; - goto cleanup; - } - ret1 =3D vmbus_establish_gpadl(dxgglobal_get_vmbus(), kmem, - alloc_size, &dxgalloc->gpadl); - if (ret1) { - pr_err("establish_gpadl failed: %d", ret1); - ret =3D -ENOMEM; - goto cleanup; - } - pr_debug("New gpadl %d", dxgalloc->gpadl.gpadl_handle); + if (!dxgglobal->map_guest_pages_enabled) { + ret =3D init_message(&msg, device->adapter, device->process, + sizeof(*set_store_command)); + if (ret) + goto cleanup; + set_store_command =3D (void *)msg.msg; =20 - command_vgpu_to_host_init2(&set_store_command->hdr, - DXGK_VMBCOMMAND_SETEXISTINGSYSMEMSTORE, - device->process->host_handle); - set_store_command->device =3D device->handle; - set_store_command->device =3D device->handle; - set_store_command->allocation =3D host_alloc->allocation; - set_store_command->gpadl =3D dxgalloc->gpadl.gpadl_handle; - ret =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, msg.size); - if (ret < 0) - pr_err("failed to set existing store: %x", ret); + kmem =3D vmap(dxgalloc->pages, npages, VM_MAP, PAGE_KERNEL); + if (kmem =3D=3D NULL) { + pr_err("vmap failed"); + ret =3D -ENOMEM; + goto cleanup; + } + ret1 =3D vmbus_establish_gpadl(dxgglobal_get_vmbus(), kmem, + alloc_size, &dxgalloc->gpadl); + if (ret1) { + pr_err("establish_gpadl failed: %d", ret1); + ret =3D -ENOMEM; + goto cleanup; + } + pr_debug("New gpadl %d", + dxgalloc->gpadl.gpadl_handle); + + command_vgpu_to_host_init2(&set_store_command->hdr, + DXGK_VMBCOMMAND_SETEXISTINGSYSMEMSTORE, + device->process->host_handle); + set_store_command->device =3D device->handle; + set_store_command->allocation =3D host_alloc->allocation; + set_store_command->gpadl =3D dxgalloc->gpadl.gpadl_handle; + ret =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, + msg.size); + if (ret < 0) + pr_err("failed to set existing store: %x", ret); + } else { + /* + * Send the list of the allocation PFNs to the host. The host + * will map the pages for GPU access. + */ + + ret =3D init_message(&msg, device->adapter, device->process, + sizeof(*set_pages_command) + + max_pfns_in_message * sizeof(u64)); + if (ret) + goto cleanup; + set_pages_command =3D (void *)msg.msg; + command_vgpu_to_host_init2(&set_pages_command->hdr, + DXGK_VMBCOMMAND_SETEXISTINGSYSMEMPAGES, + device->process->host_handle); + set_pages_command->device =3D device->handle; + set_pages_command->allocation =3D host_alloc->allocation; + + page_in =3D dxgalloc->pages; + while (alloc_offset_in_pages < npages) { + pfn =3D (u64 *)((char *)msg.msg + + sizeof(*set_pages_command)); + pages_to_send =3D min(npages - alloc_offset_in_pages, + max_pfns_in_message); + set_pages_command->num_pages =3D pages_to_send; + set_pages_command->alloc_offset_in_pages =3D + alloc_offset_in_pages; + + for (i =3D 0; i < pages_to_send; i++) + *pfn++ =3D page_to_pfn(*page_in++); + + ret =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, + msg.hdr, + msg.size); + if (ret < 0) { + pr_err("failed to set existing pages: %x", ret); + break; + } + alloc_offset_in_pages +=3D pages_to_send; + } + } =20 cleanup: if (kmem) @@ -2710,6 +2763,7 @@ int dxgvmb_send_wait_sync_object_cpu(struct dxgproces= s *process, struct d3dkmt_waitforsynchronizationobjectfromcpu *args, + bool user_address, u64 cpu_event) { int ret =3D -EINVAL; @@ -2733,18 +2787,25 @@ int dxgvmb_send_wait_sync_object_cpu(struct dxgproc= ess *process, command->object_count =3D args->object_count; command->guest_event_pointer =3D (u64) cpu_event; current_pos =3D (u8 *) &command[1]; - ret =3D copy_from_user(current_pos, args->objects, object_size); - if (ret) { - pr_err("%s failed to copy objects", __func__); - ret =3D -EINVAL; - goto cleanup; - } - current_pos +=3D object_size; - ret =3D copy_from_user(current_pos, args->fence_values, fence_size); - if (ret) { - pr_err("%s failed to copy fences", __func__); - ret =3D -EINVAL; - goto cleanup; + if (user_address) { + ret =3D copy_from_user(current_pos, args->objects, object_size); + if (ret) { + pr_err("%s failed to copy objects", __func__); + ret =3D -EINVAL; + goto cleanup; + } + current_pos +=3D object_size; + ret =3D copy_from_user(current_pos, args->fence_values, + fence_size); + if (ret) { + pr_err("%s failed to copy fences", __func__); + ret =3D -EINVAL; + goto cleanup; + } + } else { + memcpy(current_pos, args->objects, object_size); + current_pos +=3D object_size; + memcpy(current_pos, args->fence_values, fence_size); } =20 ret =3D dxgvmb_send_sync_msg_ntstatus(msg.channel, msg.hdr, msg.size); diff --git a/drivers/hv/dxgkrnl/dxgvmbus.h b/drivers/hv/dxgkrnl/dxgvmbus.h index b1434742fa80..48e97f87e329 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.h +++ b/drivers/hv/dxgkrnl/dxgvmbus.h @@ -139,6 +139,8 @@ enum dxgkvmb_commandtype { DXGK_VMBCOMMAND_GETCONTEXTSCHEDULINGPRIORITY =3D 61, DXGK_VMBCOMMAND_QUERYCLOCKCALIBRATION =3D 62, DXGK_VMBCOMMAND_QUERYRESOURCEINFO =3D 64, + DXGK_VMBCOMMAND_LOGEVENT =3D 65, + DXGK_VMBCOMMAND_SETEXISTINGSYSMEMPAGES =3D 66, DXGK_VMBCOMMAND_INVALID }; =20 @@ -245,6 +247,16 @@ struct dxgkvmb_command_setexistingsysmemstore { u32 gpadl; }; =20 +/* Returns ntstatus */ +struct dxgkvmb_command_setexistingsysmempages { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmthandle device; + struct d3dkmthandle allocation; + u32 num_pages; + u32 alloc_offset_in_pages; + /* u64 pfn_array[num_pages] */ +}; + struct dxgkvmb_command_createprocess { struct dxgkvmb_command_vm_to_host hdr; void *process; diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index 26bdcdfeba86..333168f8d813 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -30,11 +30,6 @@ struct ioctl_desc { }; static struct ioctl_desc ioctls[LX_IO_MAX + 1]; =20 -static char *errorstr(int ret) -{ - return ret < 0 ? "err" : ""; -} - static int dxgsyncobj_release(struct inode *inode, struct file *file) { struct dxgsharedsyncobject *syncobj =3D file->private_data; @@ -3557,7 +3552,7 @@ dxgk_wait_sync_object_cpu(struct dxgprocess *process,= void *__user inargs) } =20 ret =3D dxgvmb_send_wait_sync_object_cpu(process, adapter, - &args, event_id); + &args, true, event_id); if (ret < 0) goto cleanup; =20 diff --git a/drivers/hv/dxgkrnl/misc.c b/drivers/hv/dxgkrnl/misc.c index cb1e0635bebc..39e52b165b27 100644 --- a/drivers/hv/dxgkrnl/misc.c +++ b/drivers/hv/dxgkrnl/misc.c @@ -35,3 +35,9 @@ u16 *wcsncpy(u16 *dest, const u16 *src, size_t n) dest[i - 1] =3D 0; return dest; } + +char *errorstr(int ret) +{ + return ret < 0 ? "err" : ""; +} + diff --git a/drivers/hv/dxgkrnl/misc.h b/drivers/hv/dxgkrnl/misc.h index f56d21b48814..721d4f5be235 100644 --- a/drivers/hv/dxgkrnl/misc.h +++ b/drivers/hv/dxgkrnl/misc.h @@ -43,6 +43,7 @@ extern const struct d3dkmthandle zerohandle; */ =20 u16 *wcsncpy(u16 *dest, const u16 *src, size_t n); +char *errorstr(int ret); =20 enum dxglockstate { DXGLOCK_SHARED, --=20 2.35.1