From nobody Mon Apr 6 10:42:00 2026 Received: from mail-wr1-f44.google.com (mail-wr1-f44.google.com [209.85.221.44]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id AFE023F8DF0 for ; Thu, 19 Mar 2026 20:25:40 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=209.85.221.44 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1773951944; cv=none; b=gq4TUK/CYoW+BUBijMulA2kY8kzgBtd7mzhagFx3Oom3hIYonkPCPcLRoiMqut2d/mrULwTZW/zzc033UDgcI5jpFXeBPj/QAP9FY6HFk09ppNrOMYIL42QPqnl7S8mD3buoZa400LWc/jRhE8KTYIzfmkfzO6Vd6+ef/4EbnPQ= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1773951944; c=relaxed/simple; bh=G5yS/0Ks2668HL0F929eJ2RnsQeUhgHqOkkBonyENwU=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=s13xs36/QDIwgrnDULKEYANl8yLQHWigSk1WnPQn14C8af/zBHYzhgU5O0RhB7eWv4YKW7AnMblqoQqqlaopSkef1DoxXkSPpyUatbS6pyVQgoGSmR6i3nLqDVSxQNsC6d869wbzi5bPnh/GoSwisOHTr2bY9rzJ1lNWNYxRewQ= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=Gp1VzVVa; arc=none smtp.client-ip=209.85.221.44 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="Gp1VzVVa" Received: by mail-wr1-f44.google.com with SMTP id ffacd0b85a97d-439bcec8613so990720f8f.3 for ; Thu, 19 Mar 2026 13:25:40 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20230601; t=1773951939; x=1774556739; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=9gpXwUuuqUKCEuabXGr3mbEIEr9EepzLK4R1EIs1rd0=; b=Gp1VzVValD8gVa2YZH0HJYNR5MSHLfTCiRalkgEJi5ltJJdKzD2hdB/qwJnBI1zxLJ 8hp/qCi5B/DupdqTq0Pq8oURN3KqpapxYXm4TteoRx6cbPxJvNdGXp/+fbhIbkDfn9Ux SdklvUa7UG/PXeqtC4K78slgjH2Gv+JtKQQYmdlqHrv67rWPe24DUANL95bWbsMLkQef RwVMR3AuCcgoj8tm0SVKom9yWgcMjlpVrGraDMhWAzh+M9FWaEyNtx0SO+BFaCCwkaZF +VZL+9tAI0swpMUufPL4lWlw9zQCQ9iGYvrg3ef9n4ePlsa9rf+VXuSYyfK7Idi+tikg jacw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20251104; t=1773951939; x=1774556739; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-gg:x-gm-message-state:from :to:cc:subject:date:message-id:reply-to; bh=9gpXwUuuqUKCEuabXGr3mbEIEr9EepzLK4R1EIs1rd0=; b=Dr9ekK0HrKcVnok0wwogu897WREOQimMrhyQdbwIvi6pkdun9f3VYDi8fI/AFok/J4 DEdQ6knSerlCUaj4gRzmf1LaQqbPAEEa/Gk+YpO7HU2+6KWXGohsjnvb9LABuOZ3evdF of5Jvyr2LD/MK5B3neeFZvshQCNM59R1GJka++KoOIn7URqG6Kw5FpogUHpzDfqyV6Oy 8NQCdLgv6qAa9YWo5gfHXz2zjluQ7RqqjcUkDgavD1ey9B1fWHU3+f2I2UsLSIw4lqP8 xvTcn7bw06v0Qwg69IJGJ/AkfYUuLQduIsfiGsO5A/W3MD/CBdlndjitb8Jarw3dtp80 PZSA== X-Gm-Message-State: AOJu0Yy4XG09+ehCHDMjiqdXshvp2g0HbPzzQWHENiwFnhKpDD0OTWzl omBgxb949QJpwJ3wLaovTF3F27dJ+D+S7vspV5If2+GqxNvfqstFEVH2 X-Gm-Gg: ATEYQzw1k74OGoEUJKjn3wTfDiEinde3VbJ3yt9brnF1XosXSH09AC1h5YwrGAeVmPq FDYggfgjrZcrG90Iki2b67U5CkeFqfH6pS+uV2kWn2w9S+CSpjD9Lu3ZXimfAZYWJ3bnS/X4TPa KsUgPfLYs5Z5wAWgCJ6gO2gqRC+WOGqRmXnXYwFAg2LwQZtORNq5L3AltD0O6Hnd9OliaCvnMJW +P/8PvksfOa/5rUk/wOw0nUiKSxewE1XTAU89Jw5Vttoxr4jH96sXXc7XhI9qvdavosCRtvUVKH cCnChVhLhjsXxYEtMLrYGnWHRrpGejzWBSVH/HfxBAdrRvDpLIhee5n7CAhCbgKte/qFTJg9bj6 Am0QCeGxQ+kxfPdePe/u1fwpPMD27geN19TH9E0osqeLmLGEixAnCyxkCMb00Yt3+Q05gVOs064 xODHYjbMWm3OJtCT+XA6yDYqv6gAjeFSsKAs8ett7JvwVNfdQD X-Received: by 2002:a05:6000:2584:b0:43b:4e01:4aa9 with SMTP id ffacd0b85a97d-43b64242a6emr1209662f8f.10.1773951938920; Thu, 19 Mar 2026 13:25:38 -0700 (PDT) Received: from LQ5W56KC4T ([2001:8a0:672f:7800:e0e1:55cd:f0b:b1e5]) by smtp.gmail.com with ESMTPSA id ffacd0b85a97d-43b644ae16fsm1347544f8f.8.2026.03.19.13.25.37 (version=TLS1_3 cipher=TLS_CHACHA20_POLY1305_SHA256 bits=256/256); Thu, 19 Mar 2026 13:25:38 -0700 (PDT) From: Eric Curtin X-Google-Original-From: Eric Curtin To: linux-hyperv@vger.kernel.org Cc: linux-kernel@vger.kernel.org, iourit@linux.microsoft.com, wei.liu@kernel.org, decui@microsoft.com, haiyangz@microsoft.com Subject: [PATCH 22/55] drivers: hv: dxgkrnl: Ioctl to put device to error state Date: Thu, 19 Mar 2026 20:24:36 +0000 Message-ID: <20260319202509.63802-23-eric.curtin@docker.com> X-Mailer: git-send-email 2.51.0 In-Reply-To: <20260319202509.63802-1-eric.curtin@docker.com> References: <20260319202509.63802-1-eric.curtin@docker.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" From: Iouri Tarassov Implement the ioctl to put the virtual compute device to the error state (LX_DXMARKDEVICEASERROR). This ioctl is used by the user mode driver when it detects an unrecoverable error condition. When a compute device is put to the error state, all subsequent ioctl calls to the device will fail. Signed-off-by: Iouri Tarassov [kms: forward port to 6.6 from 6.1. No code changes made.] Signed-off-by: Kelsey Steele --- drivers/hv/dxgkrnl/dxgkrnl.h | 3 +++ drivers/hv/dxgkrnl/dxgvmbus.c | 25 +++++++++++++++++++++++ drivers/hv/dxgkrnl/dxgvmbus.h | 5 +++++ drivers/hv/dxgkrnl/ioctl.c | 38 ++++++++++++++++++++++++++++++++++- include/uapi/misc/d3dkmthk.h | 12 +++++++++++ 5 files changed, 82 insertions(+), 1 deletion(-) diff --git a/drivers/hv/dxgkrnl/dxgkrnl.h b/drivers/hv/dxgkrnl/dxgkrnl.h index dafc721ed6cf..b454c7430f06 100644 --- a/drivers/hv/dxgkrnl/dxgkrnl.h +++ b/drivers/hv/dxgkrnl/dxgkrnl.h @@ -856,6 +856,9 @@ 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); diff --git a/drivers/hv/dxgkrnl/dxgvmbus.c b/drivers/hv/dxgkrnl/dxgvmbus.c index 8bdd49bc7aa6..f7264b12a477 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.c +++ b/drivers/hv/dxgkrnl/dxgvmbus.c @@ -2730,6 +2730,31 @@ 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) + DXG_TRACE("err: %d", ret); + return ret; +} + int dxgvmb_send_set_allocation_priority(struct dxgprocess *process, struct dxgadapter *adapter, struct d3dkmt_setallocationpriority *args) diff --git a/drivers/hv/dxgkrnl/dxgvmbus.h b/drivers/hv/dxgkrnl/dxgvmbus.h index e1c2ed7b1580..a66e11097bb2 100644 --- a/drivers/hv/dxgkrnl/dxgvmbus.h +++ b/drivers/hv/dxgkrnl/dxgvmbus.h @@ -627,6 +627,11 @@ struct dxgkvmb_command_updateallocationproperty_return= { struct ntstatus status; }; =20 +struct dxgkvmb_command_markdeviceaserror { + struct dxgkvmb_command_vgpu_to_host hdr; + struct d3dkmt_markdeviceaserror args; +}; + /* Returns ntstatus */ struct dxgkvmb_command_changevideomemoryreservation { struct dxgkvmb_command_vgpu_to_host hdr; diff --git a/drivers/hv/dxgkrnl/ioctl.c b/drivers/hv/dxgkrnl/ioctl.c index 78de76abce2d..ce4af610ada7 100644 --- a/drivers/hv/dxgkrnl/ioctl.c +++ b/drivers/hv/dxgkrnl/ioctl.c @@ -3341,6 +3341,42 @@ dxgkio_update_alloc_property(struct dxgprocess *proc= ess, void *__user inargs) return ret; } =20 +static int +dxgkio_mark_device_as_error(struct dxgprocess *process, void *__user inarg= s) +{ + struct d3dkmt_markdeviceaserror args; + struct dxgadapter *adapter =3D NULL; + struct dxgdevice *device =3D NULL; + int ret; + + ret =3D copy_from_user(&args, inargs, sizeof(args)); + if (ret) { + DXG_ERR("failed to copy input args"); + 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); + DXG_TRACE("ioctl:%s %d", errorstr(ret), ret); + return ret; +} + static int dxgkio_query_alloc_residency(struct dxgprocess *process, void *__user inar= gs) { @@ -4404,7 +4440,7 @@ static struct ioctl_desc ioctls[] =3D { /* 0x23 */ {}, /* 0x24 */ {}, /* 0x25 */ {dxgkio_lock2, LX_DXLOCK2}, -/* 0x26 */ {}, +/* 0x26 */ {dxgkio_mark_device_as_error, LX_DXMARKDEVICEASERROR}, /* 0x27 */ {}, /* 0x28 */ {}, /* 0x29 */ {}, diff --git a/include/uapi/misc/d3dkmthk.h b/include/uapi/misc/d3dkmthk.h index 749edf28bd43..ce5a638a886d 100644 --- a/include/uapi/misc/d3dkmthk.h +++ b/include/uapi/misc/d3dkmthk.h @@ -790,6 +790,16 @@ struct d3dkmt_unlock2 { struct d3dkmthandle allocation; }; =20 +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; +}; + enum d3dkmt_standardallocationtype { _D3DKMT_STANDARDALLOCATIONTYPE_EXISTINGHEAP =3D 1, _D3DKMT_STANDARDALLOCATIONTYPE_CROSSADAPTER =3D 2, @@ -1290,6 +1300,8 @@ struct d3dkmt_shareobjectwithhost { _IOWR(0x47, 0x1f, struct d3dkmt_flushheaptransitions) #define LX_DXLOCK2 \ _IOWR(0x47, 0x25, struct d3dkmt_lock2) +#define LX_DXMARKDEVICEASERROR \ + _IOWR(0x47, 0x26, struct d3dkmt_markdeviceaserror) #define LX_DXQUERYALLOCATIONRESIDENCY \ _IOWR(0x47, 0x2a, struct d3dkmt_queryallocationresidency) #define LX_DXSETALLOCATIONPRIORITY \