From nobody Sun Feb 8 23:16:25 2026 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zoho.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 1496733924385394.34496499692193; Tue, 6 Jun 2017 00:25:24 -0700 (PDT) Received: from localhost ([::1]:36569 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1dI8ri-0002bK-N0 for importer@patchew.org; Tue, 06 Jun 2017 03:25:22 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:38878) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1dI8pL-0000mr-Vp for qemu-devel@nongnu.org; Tue, 06 Jun 2017 03:22:59 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1dI8pK-0005LQ-02 for qemu-devel@nongnu.org; Tue, 06 Jun 2017 03:22:55 -0400 Received: from mga03.intel.com ([134.134.136.65]:58638) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1dI8pJ-0005K6-KL for qemu-devel@nongnu.org; Tue, 06 Jun 2017 03:22:53 -0400 Received: from fmsmga006.fm.intel.com ([10.253.24.20]) by orsmga103.jf.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 06 Jun 2017 00:22:53 -0700 Received: from hz-desktop.sh.intel.com (HELO localhost) ([10.239.159.149]) by fmsmga006.fm.intel.com with ESMTP; 06 Jun 2017 00:22:51 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.39,305,1493708400"; d="scan'208";a="111383309" From: Haozhong Zhang To: qemu-devel@nongnu.org Date: Tue, 6 Jun 2017 15:22:28 +0800 Message-Id: <20170606072229.9302-4-haozhong.zhang@intel.com> X-Mailer: git-send-email 2.11.0 In-Reply-To: <20170606072229.9302-1-haozhong.zhang@intel.com> References: <20170606072229.9302-1-haozhong.zhang@intel.com> X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 134.134.136.65 Subject: [Qemu-devel] [PATCH v2 3/4] nvdimm: add a boolean option "restrict" X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: Haozhong Zhang , "Michael S. Tsirkin" , Stefan Hajnoczi , Xiao Guangrong , Igor Mammedov , Dan Williams Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" If a vNVDIMM device is not backed by a DAX device and its "restrict" option is enabled, bit 3 of state flags in its region mapping structure will be set, in order to notify the guest of the lack of write persistence guarantee. Once this bit is set, the guest OS may mark the vNVDIMM device as read-only. This option is disabled by default for backwards compatibility. It's recommended to enable for the formal usage. Signed-off-by: Haozhong Zhang --- hw/acpi/nvdimm.c | 16 ++++++++++++++++ hw/mem/nvdimm.c | 38 +++++++++++++++++++++++++++++++++++++- include/hw/mem/nvdimm.h | 5 +++++ 3 files changed, 58 insertions(+), 1 deletion(-) diff --git a/hw/acpi/nvdimm.c b/hw/acpi/nvdimm.c index 8e7d6ec034..fd1ef6dc65 100644 --- a/hw/acpi/nvdimm.c +++ b/hw/acpi/nvdimm.c @@ -138,6 +138,8 @@ struct NvdimmNfitMemDev { } QEMU_PACKED; typedef struct NvdimmNfitMemDev NvdimmNfitMemDev; =20 +#define ACPI_NFIT_MEM_NOT_ARMED (1 << 3) + /* * NVDIMM Control Region Structure * @@ -289,6 +291,10 @@ nvdimm_build_structure_memdev(GArray *structures, Devi= ceState *dev) int slot =3D object_property_get_int(OBJECT(dev), PC_DIMM_SLOT_PROP, NULL); uint32_t handle =3D nvdimm_slot_to_handle(slot); + bool dev_dax =3D object_property_get_bool(OBJECT(dev), NVDIMM_DEV_DAX_= PROP, + NULL); + bool restrict_mode =3D object_property_get_bool(OBJECT(dev), + NVDIMM_RESTRICT_PROP, NU= LL); =20 nfit_memdev =3D acpi_data_push(structures, sizeof(*nfit_memdev)); =20 @@ -312,6 +318,16 @@ nvdimm_build_structure_memdev(GArray *structures, Devi= ceState *dev) =20 /* Only one interleave for PMEM. */ nfit_memdev->interleave_ways =3D cpu_to_le16(1); + + /* + * If a vNVDIMM device in the restrict mode and is not backed by a + * DAX device, QEMU will set ACPI_NFIT_MEM_NOT_ARMED bit of state + * flags in its region mapping structure, in order to notify the + * guest of the lack of write persistence guarantee. + */ + if (!dev_dax && restrict_mode) { + nfit_memdev->flags =3D cpu_to_le16(ACPI_NFIT_MEM_NOT_ARMED); + } } =20 /* diff --git a/hw/mem/nvdimm.c b/hw/mem/nvdimm.c index b23542fbdf..cda416e5c8 100644 --- a/hw/mem/nvdimm.c +++ b/hw/mem/nvdimm.c @@ -65,11 +65,46 @@ out: error_propagate(errp, local_err); } =20 +static bool nvdimm_get_backend_dev_dax(Object *obj, Error **errp) +{ + NVDIMMDevice *nvdimm =3D NVDIMM(obj); + + return nvdimm->backend_dev_dax; +} + +static bool nvdimm_get_restrict(Object *obj, Error **errp) +{ + NVDIMMDevice *nvdimm =3D NVDIMM(obj); + + return nvdimm->restrict_mode; +} + +static void nvdimm_set_restrict(Object *obj, bool val, Error **errp) +{ + DeviceState *dev =3D DEVICE(obj); + NVDIMMDevice *nvdimm =3D NVDIMM(obj); + Error *local_err =3D NULL; + + if (dev->realized) { + error_setg(&local_err, "cannot change property value"); + goto out; + } + + nvdimm->restrict_mode =3D val; + + out: + error_propagate(errp, local_err); +} + static void nvdimm_init(Object *obj) { object_property_add(obj, NVDIMM_LABEL_SIZE_PROP, "int", nvdimm_get_label_size, nvdimm_set_label_size, NULL, NULL, NULL); + object_property_add_bool(obj, NVDIMM_DEV_DAX_PROP, + nvdimm_get_backend_dev_dax, NULL, NULL); + object_property_add_bool(obj, NVDIMM_RESTRICT_PROP, + nvdimm_get_restrict, nvdimm_set_restrict, NUL= L); } =20 static MemoryRegion *nvdimm_get_memory_region(PCDIMMDevice *dimm) @@ -85,7 +120,8 @@ static void nvdimm_realize(PCDIMMDevice *dimm, Error **e= rrp) NVDIMMDevice *nvdimm =3D NVDIMM(dimm); uint64_t align, pmem_size, size =3D memory_region_size(mr); =20 - if (!qemu_fd_is_dev_dax(memory_region_get_fd(mr))) { + nvdimm->backend_dev_dax =3D qemu_fd_is_dev_dax(memory_region_get_fd(mr= )); + if (!nvdimm->backend_dev_dax) { error_report("warning: nvdimm backend does not look like a DAX dev= ice, " "unable to guarantee persistence of guest writes"); } diff --git a/include/hw/mem/nvdimm.h b/include/hw/mem/nvdimm.h index f1f3987055..2fbe0d7858 100644 --- a/include/hw/mem/nvdimm.h +++ b/include/hw/mem/nvdimm.h @@ -49,6 +49,8 @@ TYPE_NVDIMM) =20 #define NVDIMM_LABEL_SIZE_PROP "label-size" +#define NVDIMM_DEV_DAX_PROP "dev-dax" +#define NVDIMM_RESTRICT_PROP "restrict" =20 struct NVDIMMDevice { /* private */ @@ -74,6 +76,9 @@ struct NVDIMMDevice { * guest via ACPI NFIT and _FIT method if NVDIMM hotplug is supported. */ MemoryRegion nvdimm_mr; + + bool backend_dev_dax; + bool restrict_mode; }; typedef struct NVDIMMDevice NVDIMMDevice; =20 --=20 2.11.0