From nobody Thu May 2 02:51:13 2024 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.zohomail.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; dmarc=fail(p=none dis=none) header.from=linux.intel.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 1544602452925622.2460400696757; Wed, 12 Dec 2018 00:14:12 -0800 (PST) Received: from localhost ([::1]:43054 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gWzel-0001Jk-TM for importer@patchew.org; Wed, 12 Dec 2018 03:14:11 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:40902) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gWzdG-0000D8-Lq for qemu-devel@nongnu.org; Wed, 12 Dec 2018 03:12:41 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1gWzcz-0007xa-Sx for qemu-devel@nongnu.org; Wed, 12 Dec 2018 03:12:34 -0500 Received: from mga09.intel.com ([134.134.136.24]:14548) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1gWzcz-0007x2-K9 for qemu-devel@nongnu.org; Wed, 12 Dec 2018 03:12:21 -0500 Received: from orsmga006.jf.intel.com ([10.7.209.51]) by orsmga102.jf.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 12 Dec 2018 00:12:20 -0800 Received: from linux.intel.com ([10.54.29.200]) by orsmga006.jf.intel.com with ESMTP; 12 Dec 2018 00:12:20 -0800 Received: from dazhang1-ssd.sh.intel.com (unknown [10.239.48.128]) by linux.intel.com (Postfix) with ESMTP id 7A9495803DC; Wed, 12 Dec 2018 00:12:18 -0800 (PST) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.56,343,1539673200"; d="scan'208";a="100051151" From: Zhang Yi To: xiaoguangrong.eric@gmail.com, dan.j.williams@intel.com, stefanha@redhat.com, pbonzini@redhat.com, pagupta@redhat.com, yu.c.zhang@linux.intel.com Date: Wed, 12 Dec 2018 16:12:11 +0800 Message-Id: <51ba6d7d0333a5517d824a870dd20887156dd15a.1544598069.git.yi.z.zhang@linux.intel.com> X-Mailer: git-send-email 2.7.4 In-Reply-To: References: X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 134.134.136.24 Subject: [Qemu-devel] [PATCH V6 1/6] numa: Fixed the memory leak of numa error message 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: imammedo@redhat.com, Zhang Yi , qemu-devel@nongnu.org, ehabkost@redhat.com, mst@redhat.com Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" object_get_canonical_path_component() returns a string which must be freed using g_free(). Signed-off-by: Zhang Yi Reviewed-by: Pankaj gupta Reviewed-by: Igor Mammedov Reviewed-by: Stefan Hajnoczi --- numa.c | 1 + 1 file changed, 1 insertion(+) diff --git a/numa.c b/numa.c index 50ec016..3875e1e 100644 --- a/numa.c +++ b/numa.c @@ -533,6 +533,7 @@ void memory_region_allocate_system_memory(MemoryRegion = *mr, Object *owner, error_report("memory backend %s is used multiple times. Each " "-numa option must use a different memdev value.", path); + g_free(path); exit(1); } =20 --=20 2.7.4 From nobody Thu May 2 02:51:13 2024 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.zohomail.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; dmarc=fail(p=none dis=none) header.from=linux.intel.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 154460257502761.57763640017936; Wed, 12 Dec 2018 00:16:15 -0800 (PST) Received: from localhost ([::1]:43071 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gWzgj-0002c7-Se for importer@patchew.org; Wed, 12 Dec 2018 03:16:13 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:41060) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gWzdO-0000Iv-QV for qemu-devel@nongnu.org; Wed, 12 Dec 2018 03:12:47 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1gWzdL-0008Cs-Mn for qemu-devel@nongnu.org; Wed, 12 Dec 2018 03:12:46 -0500 Received: from mga07.intel.com ([134.134.136.100]:54434) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1gWzdL-0008Bn-Dr for qemu-devel@nongnu.org; Wed, 12 Dec 2018 03:12:43 -0500 Received: from fmsmga006.fm.intel.com ([10.253.24.20]) by orsmga105.jf.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 12 Dec 2018 00:12:42 -0800 Received: from linux.intel.com ([10.54.29.200]) by fmsmga006.fm.intel.com with ESMTP; 12 Dec 2018 00:12:41 -0800 Received: from dazhang1-ssd.sh.intel.com (unknown [10.239.48.128]) by linux.intel.com (Postfix) with ESMTP id 926A558079D; Wed, 12 Dec 2018 00:12:39 -0800 (PST) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.56,343,1539673200"; d="scan'208";a="301478650" From: Zhang Yi To: xiaoguangrong.eric@gmail.com, dan.j.williams@intel.com, stefanha@redhat.com, pbonzini@redhat.com, pagupta@redhat.com, yu.c.zhang@linux.intel.com Date: Wed, 12 Dec 2018 16:12:33 +0800 Message-Id: <62a8796330b86f9f6571e48755d718db11855a6b.1544598069.git.yi.z.zhang@linux.intel.com> X-Mailer: git-send-email 2.7.4 In-Reply-To: References: X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 134.134.136.100 Subject: [Qemu-devel] [PATCH V6 2/6] util/mmap-alloc: switch qemu_ram_mmap() to 'flags' parameter 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: imammedo@redhat.com, Zhang Yi , qemu-devel@nongnu.org, ehabkost@redhat.com, mst@redhat.com Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" As more flag parameters besides the existing 'shared' are going to be added to qemu_ram_mmap(), let's switch 'shared' to a 'flags' parameter in advance, so as to ease the further additions. Signed-off-by: Haozhong Zhang Signed-off-by: Zhang Yi Reviewed-by: Stefan Hajnoczi --- exec.c | 7 ++++--- include/qemu/mmap-alloc.h | 19 ++++++++++++++++++- util/mmap-alloc.c | 8 +++++--- util/oslib-posix.c | 8 +++++++- 4 files changed, 34 insertions(+), 8 deletions(-) diff --git a/exec.c b/exec.c index bb6170d..e92a7da 100644 --- a/exec.c +++ b/exec.c @@ -1810,6 +1810,7 @@ static void *file_ram_alloc(RAMBlock *block, ram_addr_t memory, int fd, bool truncate, + uint32_t flags, Error **errp) { void *area; @@ -1859,8 +1860,7 @@ static void *file_ram_alloc(RAMBlock *block, perror("ftruncate"); } =20 - area =3D qemu_ram_mmap(fd, memory, block->mr->align, - block->flags & RAM_SHARED); + area =3D qemu_ram_mmap(fd, memory, block->mr->align, flags); if (area =3D=3D MAP_FAILED) { error_setg_errno(errp, errno, "unable to map backing store for guest RAM"); @@ -2279,7 +2279,8 @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, Mem= oryRegion *mr, new_block->used_length =3D size; new_block->max_length =3D size; new_block->flags =3D ram_flags; - new_block->host =3D file_ram_alloc(new_block, size, fd, !file_size, er= rp); + new_block->host =3D file_ram_alloc(new_block, size, fd, !file_size, + ram_flags, errp); if (!new_block->host) { g_free(new_block); return NULL; diff --git a/include/qemu/mmap-alloc.h b/include/qemu/mmap-alloc.h index 50385e3..6fe6ed4 100644 --- a/include/qemu/mmap-alloc.h +++ b/include/qemu/mmap-alloc.h @@ -7,7 +7,24 @@ size_t qemu_fd_getpagesize(int fd); =20 size_t qemu_mempath_getpagesize(const char *mem_path); =20 -void *qemu_ram_mmap(int fd, size_t size, size_t align, bool shared); +/** + * qemu_ram_mmap: mmap the specified file or device. + * + * Parameters: + * @fd: the file or the device to mmap + * @size: the number of bytes to be mmaped + * @align: if not zero, specify the alignment of the starting mapping add= ress; + * otherwise, the alignment in use will be determined by QEMU. + * @flags: specifies additional properties of the mapping, which can be o= ne or + * bit-or of following values + * - RAM_SHARED: mmap with MAP_SHARED flag + * Other bits are ignored. + * + * Return: + * On success, return a pointer to the mapped area. + * On failure, return MAP_FAILED. + */ +void *qemu_ram_mmap(int fd, size_t size, size_t align, uint32_t flags); =20 void qemu_ram_munmap(void *ptr, size_t size); =20 diff --git a/util/mmap-alloc.c b/util/mmap-alloc.c index fd329ec..8f0a740 100644 --- a/util/mmap-alloc.c +++ b/util/mmap-alloc.c @@ -13,6 +13,7 @@ #include "qemu/osdep.h" #include "qemu/mmap-alloc.h" #include "qemu/host-utils.h" +#include "exec/memory.h" =20 #define HUGETLBFS_MAGIC 0x958458f6 =20 @@ -75,7 +76,7 @@ size_t qemu_mempath_getpagesize(const char *mem_path) return getpagesize(); } =20 -void *qemu_ram_mmap(int fd, size_t size, size_t align, bool shared) +void *qemu_ram_mmap(int fd, size_t size, size_t align, uint32_t flags) { /* * Note: this always allocates at least one extra page of virtual addr= ess @@ -92,11 +93,12 @@ void *qemu_ram_mmap(int fd, size_t size, size_t align, = bool shared) * anonymous memory is OK. */ int anonfd =3D fd =3D=3D -1 || qemu_fd_getpagesize(fd) =3D=3D getpages= ize() ? -1 : fd; - int flags =3D anonfd =3D=3D -1 ? MAP_ANONYMOUS : MAP_NORESERVE; - void *ptr =3D mmap(0, total, PROT_NONE, flags | MAP_PRIVATE, anonfd, 0= ); + int mmap_flags =3D anonfd =3D=3D -1 ? MAP_ANONYMOUS : MAP_NORESERVE; + void *ptr =3D mmap(0, total, PROT_NONE, mmap_flags | MAP_PRIVATE, anon= fd, 0); #else void *ptr =3D mmap(0, total, PROT_NONE, MAP_ANONYMOUS | MAP_PRIVATE, -= 1, 0); #endif + bool shared =3D flags & RAM_SHARED; size_t offset; void *ptr1; =20 diff --git a/util/oslib-posix.c b/util/oslib-posix.c index fbd0dc8..121c31f 100644 --- a/util/oslib-posix.c +++ b/util/oslib-posix.c @@ -203,7 +203,13 @@ void *qemu_memalign(size_t alignment, size_t size) void *qemu_anon_ram_alloc(size_t size, uint64_t *alignment, bool shared) { size_t align =3D QEMU_VMALLOC_ALIGN; - void *ptr =3D qemu_ram_mmap(-1, size, align, shared); + uint32_t flags =3D 0; + void *ptr; + + if (shared) { + flags =3D MAP_SHARED; + } + ptr =3D qemu_ram_mmap(-1, size, align, flags); =20 if (ptr =3D=3D MAP_FAILED) { return NULL; --=20 2.7.4 From nobody Thu May 2 02:51:13 2024 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.zohomail.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; dmarc=fail(p=none dis=none) header.from=linux.intel.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 1544602530543155.7167124739999; Wed, 12 Dec 2018 00:15:30 -0800 (PST) Received: from localhost ([::1]:43067 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gWzg1-00029j-Dd for importer@patchew.org; Wed, 12 Dec 2018 03:15:29 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:41398) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gWzeD-0001EY-1E for qemu-devel@nongnu.org; Wed, 12 Dec 2018 03:13:38 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1gWze9-0000Ep-S8 for qemu-devel@nongnu.org; Wed, 12 Dec 2018 03:13:37 -0500 Received: from mga04.intel.com ([192.55.52.120]:42117) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1gWze9-0000Da-HX for qemu-devel@nongnu.org; Wed, 12 Dec 2018 03:13:33 -0500 Received: from fmsmga006.fm.intel.com ([10.253.24.20]) by fmsmga104.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 12 Dec 2018 00:13:32 -0800 Received: from linux.intel.com ([10.54.29.200]) by fmsmga006.fm.intel.com with ESMTP; 12 Dec 2018 00:13:32 -0800 Received: from dazhang1-ssd.sh.intel.com (unknown [10.239.48.128]) by linux.intel.com (Postfix) with ESMTP id 87DE258079D; Wed, 12 Dec 2018 00:13:29 -0800 (PST) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.56,343,1539673200"; d="scan'208";a="301478934" From: Zhang Yi To: xiaoguangrong.eric@gmail.com, dan.j.williams@intel.com, stefanha@redhat.com, pbonzini@redhat.com, pagupta@redhat.com, yu.c.zhang@linux.intel.com Date: Wed, 12 Dec 2018 16:13:23 +0800 Message-Id: <0b74ac642ab37ea912b8be8b3bf8dd74c10066e3.1544598069.git.yi.z.zhang@linux.intel.com> X-Mailer: git-send-email 2.7.4 In-Reply-To: References: X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 192.55.52.120 Subject: [Qemu-devel] [PATCH V6 3/6] util/mmap-alloc: support MAP_SYNC in qemu_ram_mmap() 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: imammedo@redhat.com, Zhang Yi , qemu-devel@nongnu.org, ehabkost@redhat.com, mst@redhat.com Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" When a file supporting DAX is used as vNVDIMM backend, mmap it with MAP_SYNC flag in addition can guarantee the persistence of guest write to the backend file without other QEMU actions (e.g., periodic fsync() by QEMU). A set of RAM_SYNC flags are added to qemu_ram_mmap(): Signed-off-by: Haozhong Zhang Signed-off-by: Zhang Yi Reviewed-by: Stefan Hajnoczi --- exec.c | 2 +- include/exec/memory.h | 3 +++ include/exec/ram_addr.h | 1 + include/qemu/mmap-alloc.h | 1 + include/qemu/osdep.h | 29 +++++++++++++++++++++++++++++ util/mmap-alloc.c | 13 +++++++++---- 6 files changed, 44 insertions(+), 5 deletions(-) diff --git a/exec.c b/exec.c index e92a7da..dc4d180 100644 --- a/exec.c +++ b/exec.c @@ -2241,7 +2241,7 @@ RAMBlock *qemu_ram_alloc_from_fd(ram_addr_t size, Mem= oryRegion *mr, int64_t file_size; =20 /* Just support these ram flags by now. */ - assert((ram_flags & ~(RAM_SHARED | RAM_PMEM)) =3D=3D 0); + assert((ram_flags & ~(RAM_SHARED | RAM_PMEM | RAM_SYNC)) =3D=3D 0); =20 if (xen_enabled()) { error_setg(errp, "-mem-path not supported with Xen"); diff --git a/include/exec/memory.h b/include/exec/memory.h index 667466b..33a4e2c 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -126,6 +126,9 @@ typedef struct IOMMUNotifier IOMMUNotifier; /* RAM is a persistent kind memory */ #define RAM_PMEM (1 << 5) =20 +/* RAM can be mmap by a MAP_SYNC flag */ +#define RAM_SYNC (1 << 6) + static inline void iommu_notifier_init(IOMMUNotifier *n, IOMMUNotify fn, IOMMUNotifierFlag flags, hwaddr start, hwaddr end, diff --git a/include/exec/ram_addr.h b/include/exec/ram_addr.h index 9ecd911..d239ce7 100644 --- a/include/exec/ram_addr.h +++ b/include/exec/ram_addr.h @@ -87,6 +87,7 @@ long qemu_getrampagesize(void); * or bit-or of following values * - RAM_SHARED: mmap the backing file or device with MAP_SHA= RED * - RAM_PMEM: the backend @mem_path or @fd is persistent mem= ory + * - RAM_SYNC: mmap with MAP_SYNC flag * Other bits are ignored. * @mem_path or @fd: specify the backing file or device * @errp: pointer to Error*, to store an error if it happens diff --git a/include/qemu/mmap-alloc.h b/include/qemu/mmap-alloc.h index 6fe6ed4..1755a8b 100644 --- a/include/qemu/mmap-alloc.h +++ b/include/qemu/mmap-alloc.h @@ -18,6 +18,7 @@ size_t qemu_mempath_getpagesize(const char *mem_path); * @flags: specifies additional properties of the mapping, which can be o= ne or * bit-or of following values * - RAM_SHARED: mmap with MAP_SHARED flag + * - RAM_SYNC: mmap with MAP_SYNC flag * Other bits are ignored. * * Return: diff --git a/include/qemu/osdep.h b/include/qemu/osdep.h index 3bf48bc..f94ea68 100644 --- a/include/qemu/osdep.h +++ b/include/qemu/osdep.h @@ -410,6 +410,35 @@ void qemu_anon_ram_free(void *ptr, size_t size); # define QEMU_VMALLOC_ALIGN getpagesize() #endif =20 +/* + * MAP_SHARED_VALIDATE and MAP_SYNC are introduced in Linux kernel + * 4.15, so they may not be defined when compiling on older kernels. + */ +#ifdef CONFIG_LINUX + +#include + +#ifndef MAP_SHARED_VALIDATE +#define MAP_SHARED_VALIDATE 0x3 +#endif + +#ifndef MAP_SYNC +#define MAP_SYNC 0x80000 +#endif + +/* MAP_SYNC is only available with MAP_SHARED_VALIDATE. */ +#define MAP_SYNC_FLAGS (MAP_SYNC | MAP_SHARED_VALIDATE) + +#else /* !CONFIG_LINUX */ + +#define MAP_SHARED_VALIDATE 0x0 +#define MAP_SYNC 0x0 + +#define QEMU_HAS_MAP_SYNC false +#define MAP_SYNC_FLAGS 0 + +#endif /* CONFIG_LINUX */ + #ifdef CONFIG_POSIX struct qemu_signalfd_siginfo { uint32_t ssi_signo; /* Signal number */ diff --git a/util/mmap-alloc.c b/util/mmap-alloc.c index 8f0a740..025ab6a 100644 --- a/util/mmap-alloc.c +++ b/util/mmap-alloc.c @@ -99,6 +99,7 @@ void *qemu_ram_mmap(int fd, size_t size, size_t align, ui= nt32_t flags) void *ptr =3D mmap(0, total, PROT_NONE, MAP_ANONYMOUS | MAP_PRIVATE, -= 1, 0); #endif bool shared =3D flags & RAM_SHARED; + int mmap_xflags =3D 0; size_t offset; void *ptr1; =20 @@ -109,16 +110,20 @@ void *qemu_ram_mmap(int fd, size_t size, size_t align= , uint32_t flags) assert(is_power_of_2(align)); /* Always align to host page size */ assert(align >=3D getpagesize()); + if ((flags & RAM_SYNC) && shared) { + mmap_xflags |=3D MAP_SYNC_FLAGS; + } =20 offset =3D QEMU_ALIGN_UP((uintptr_t)ptr, align) - (uintptr_t)ptr; + retry_mmap_fd: ptr1 =3D mmap(ptr + offset, size, PROT_READ | PROT_WRITE, MAP_FIXED | (fd =3D=3D -1 ? MAP_ANONYMOUS : 0) | - (shared ? MAP_SHARED : MAP_PRIVATE), + (shared ? MAP_SHARED : MAP_PRIVATE) | mmap_xflags, fd, 0); - if (ptr1 =3D=3D MAP_FAILED) { - munmap(ptr, total); - return MAP_FAILED; + if ((ptr1 =3D=3D MAP_FAILED) && (mmap_xflags & MAP_SYNC_FLAGS)) { + mmap_xflags &=3D ~MAP_SYNC_FLAGS; + goto retry_mmap_fd; } =20 if (offset > 0) { --=20 2.7.4 From nobody Thu May 2 02:51:13 2024 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.zohomail.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; dmarc=fail(p=none dis=none) header.from=linux.intel.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 1544602659431618.0344821932683; Wed, 12 Dec 2018 00:17:39 -0800 (PST) Received: from localhost ([::1]:43077 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gWzi6-0003PL-5Z for importer@patchew.org; Wed, 12 Dec 2018 03:17:38 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:41468) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gWzeL-0001Ir-Fc for qemu-devel@nongnu.org; Wed, 12 Dec 2018 03:13:46 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1gWzeI-0000OA-AE for qemu-devel@nongnu.org; Wed, 12 Dec 2018 03:13:45 -0500 Received: from mga12.intel.com ([192.55.52.136]:45117) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1gWzeH-0000NH-UK for qemu-devel@nongnu.org; Wed, 12 Dec 2018 03:13:42 -0500 Received: from fmsmga004.fm.intel.com ([10.253.24.48]) by fmsmga106.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 12 Dec 2018 00:13:40 -0800 Received: from linux.intel.com ([10.54.29.200]) by fmsmga004.fm.intel.com with ESMTP; 12 Dec 2018 00:13:40 -0800 Received: from dazhang1-ssd.sh.intel.com (unknown [10.239.48.128]) by linux.intel.com (Postfix) with ESMTP id 2D05A5803DC; Wed, 12 Dec 2018 00:13:38 -0800 (PST) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.56,343,1539673200"; d="scan'208";a="127193408" From: Zhang Yi To: xiaoguangrong.eric@gmail.com, dan.j.williams@intel.com, stefanha@redhat.com, pbonzini@redhat.com, pagupta@redhat.com, yu.c.zhang@linux.intel.com Date: Wed, 12 Dec 2018 16:13:31 +0800 Message-Id: <3b909bab9a2146d095eed73b61be97d3af2c2510.1544598069.git.yi.z.zhang@linux.intel.com> X-Mailer: git-send-email 2.7.4 In-Reply-To: References: X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 192.55.52.136 Subject: [Qemu-devel] [PATCH V6 4/6] util/mmap-alloc: Switch the RAM_SYNC flags to OnOffAuto 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: imammedo@redhat.com, Zhang Yi , qemu-devel@nongnu.org, ehabkost@redhat.com, mst@redhat.com Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Signed-off-by: Zhang Yi A set of RAM_SYNC_ON_OFF_AUTO{AUTO,ON,OFF} flags are added to qemu_ram_mmap(): - If RAM_SYNC_ON_OFF_AUTO_ON is present, qemu_ram_mmap() will try to pass MAP_SYNC to mmap(). It will then fail if the host OS or the backend file do not support MAP_SYNC, or MAP_SYNC is conflict with other flags. - If RAM_SYNC_ON_OFF_AUTO_OFF is present, qemu_ram_mmap() will never pass MAP_SYNC to mmap(). - If RAM_SYNC_ON_OFF_AUTO_AUTO is present, and * if the host OS and the backend file support MAP_SYNC, and MAP_SYNC is not conflict with other flags, qemu_ram_mmap() will work as if RAM_SYNC_ON_OFF_AUTO_ON is present; * otherwise, qemu_ram_mmap() will work as if RAM_SYNC_ON_OFF_AUTO_OFF is present. Reviewed-by: Stefan Hajnoczi --- include/exec/memory.h | 9 ++++++++- util/mmap-alloc.c | 13 +++++++++++-- 2 files changed, 19 insertions(+), 3 deletions(-) diff --git a/include/exec/memory.h b/include/exec/memory.h index 33a4e2c..c74c467 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -127,7 +127,14 @@ typedef struct IOMMUNotifier IOMMUNotifier; #define RAM_PMEM (1 << 5) =20 /* RAM can be mmap by a MAP_SYNC flag */ -#define RAM_SYNC (1 << 6) +#define RAM_SYNC_SHIFT 6 +#define RAM_SYNC_SHIFT_AUTO 7 + +#define RAM_SYNC_ON_OFF_AUTO_ON (1UL << RAM_SYNC_SHIFT) +#define RAM_SYNC_ON_OFF_AUTO_OFF (0UL << RAM_SYNC_SHIFT) +#define RAM_SYNC_ON_OFF_AUTO_AUTO (1UL << RAM_SYNC_SHIFT_AUTO) + +#define RAM_SYNC (RAM_SYNC_ON_OFF_AUTO_ON | RAM_SYNC_ON_OFF_AUTO_AUTO) =20 static inline void iommu_notifier_init(IOMMUNotifier *n, IOMMUNotify fn, IOMMUNotifierFlag flags, diff --git a/util/mmap-alloc.c b/util/mmap-alloc.c index 025ab6a..bda6024 100644 --- a/util/mmap-alloc.c +++ b/util/mmap-alloc.c @@ -110,6 +110,11 @@ void *qemu_ram_mmap(int fd, size_t size, size_t align,= uint32_t flags) assert(is_power_of_2(align)); /* Always align to host page size */ assert(align >=3D getpagesize()); + if ((flags & RAM_SYNC_ON_OFF_AUTO_ON) && + (!shared || !MAP_SYNC_FLAGS)) { + munmap(ptr, total); + return MAP_FAILED; + } if ((flags & RAM_SYNC) && shared) { mmap_xflags |=3D MAP_SYNC_FLAGS; } @@ -122,8 +127,12 @@ void *qemu_ram_mmap(int fd, size_t size, size_t align,= uint32_t flags) (shared ? MAP_SHARED : MAP_PRIVATE) | mmap_xflags, fd, 0); if ((ptr1 =3D=3D MAP_FAILED) && (mmap_xflags & MAP_SYNC_FLAGS)) { - mmap_xflags &=3D ~MAP_SYNC_FLAGS; - goto retry_mmap_fd; + if (flags & RAM_SYNC_ON_OFF_AUTO_AUTO) { + mmap_xflags &=3D ~MAP_SYNC_FLAGS; + goto retry_mmap_fd; + } + munmap(ptr, total); + return MAP_FAILED; } =20 if (offset > 0) { --=20 2.7.4 From nobody Thu May 2 02:51:13 2024 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.zohomail.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; dmarc=fail(p=none dis=none) header.from=linux.intel.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 15446027077781015.6402738549875; Wed, 12 Dec 2018 00:18:27 -0800 (PST) Received: from localhost ([::1]:43078 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gWzir-00044s-Ky for importer@patchew.org; Wed, 12 Dec 2018 03:18:25 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:41534) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gWzeV-0001QL-PV for qemu-devel@nongnu.org; Wed, 12 Dec 2018 03:13:57 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1gWzeR-0000UO-J2 for qemu-devel@nongnu.org; Wed, 12 Dec 2018 03:13:55 -0500 Received: from mga11.intel.com ([192.55.52.93]:29535) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1gWzeR-0000Ta-95 for qemu-devel@nongnu.org; Wed, 12 Dec 2018 03:13:51 -0500 Received: from fmsmga008.fm.intel.com ([10.253.24.58]) by fmsmga102.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 12 Dec 2018 00:13:50 -0800 Received: from linux.intel.com ([10.54.29.200]) by fmsmga008.fm.intel.com with ESMTP; 12 Dec 2018 00:13:49 -0800 Received: from dazhang1-ssd.sh.intel.com (unknown [10.239.48.128]) by linux.intel.com (Postfix) with ESMTP id F245658079D; Wed, 12 Dec 2018 00:13:47 -0800 (PST) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.56,343,1539673200"; d="scan'208";a="108896557" From: Zhang Yi To: xiaoguangrong.eric@gmail.com, dan.j.williams@intel.com, stefanha@redhat.com, pbonzini@redhat.com, pagupta@redhat.com, yu.c.zhang@linux.intel.com Date: Wed, 12 Dec 2018 16:13:41 +0800 Message-Id: X-Mailer: git-send-email 2.7.4 In-Reply-To: References: X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 192.55.52.93 Subject: [Qemu-devel] [PATCH V6 5/6] hostmem: add more information in error messages 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: imammedo@redhat.com, Zhang Yi , qemu-devel@nongnu.org, ehabkost@redhat.com, mst@redhat.com Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" When there are multiple memory backends in use, including the object type name, ID and the property name in the error message can help users to locate the error. Signed-off-by: Haozhong Zhang Signed-off-by: Zhang Yi Reviewed-by: Stefan Hajnoczi --- backends/hostmem-file.c | 6 ++++-- backends/hostmem.c | 8 +++++--- 2 files changed, 9 insertions(+), 5 deletions(-) diff --git a/backends/hostmem-file.c b/backends/hostmem-file.c index e640749..0dd7a90 100644 --- a/backends/hostmem-file.c +++ b/backends/hostmem-file.c @@ -82,7 +82,8 @@ static void set_mem_path(Object *o, const char *str, Erro= r **errp) HostMemoryBackendFile *fb =3D MEMORY_BACKEND_FILE(o); =20 if (host_memory_backend_mr_inited(backend)) { - error_setg(errp, "cannot change property value"); + error_setg(errp, "cannot change property 'mem-path' of %s", + object_get_typename(o)); return; } g_free(fb->mem_path); @@ -120,7 +121,8 @@ static void file_memory_backend_set_align(Object *o, Vi= sitor *v, uint64_t val; =20 if (host_memory_backend_mr_inited(backend)) { - error_setg(&local_err, "cannot change property value"); + error_setg(&local_err, "cannot change property '%s' of %s", + name, object_get_typename(o)); goto out; } =20 diff --git a/backends/hostmem.c b/backends/hostmem.c index 1a89342..e2bcf9f 100644 --- a/backends/hostmem.c +++ b/backends/hostmem.c @@ -47,7 +47,8 @@ host_memory_backend_set_size(Object *obj, Visitor *v, con= st char *name, uint64_t value; =20 if (host_memory_backend_mr_inited(backend)) { - error_setg(&local_err, "cannot change property value"); + error_setg(&local_err, "cannot change property %s of %s ", + name, object_get_typename(obj)); goto out; } =20 @@ -56,8 +57,9 @@ host_memory_backend_set_size(Object *obj, Visitor *v, con= st char *name, goto out; } if (!value) { - error_setg(&local_err, "Property '%s.%s' doesn't take value '%" - PRIu64 "'", object_get_typename(obj), name, value); + error_setg(&local_err, + "property '%s' of %s doesn't take value '%" PRIu64 "'", + name, object_get_typename(obj), value); goto out; } backend->size =3D value; --=20 2.7.4 From nobody Thu May 2 02:51:13 2024 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.zohomail.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; dmarc=fail(p=none dis=none) header.from=linux.intel.com Return-Path: Received: from lists.gnu.org (lists.gnu.org [208.118.235.17]) by mx.zohomail.com with SMTPS id 1544602793498615.0901496155368; Wed, 12 Dec 2018 00:19:53 -0800 (PST) Received: from localhost ([::1]:43083 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gWzkG-0004vy-Eo for importer@patchew.org; Wed, 12 Dec 2018 03:19:52 -0500 Received: from eggs.gnu.org ([2001:4830:134:3::10]:41667) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1gWzeq-0001cr-99 for qemu-devel@nongnu.org; Wed, 12 Dec 2018 03:14:17 -0500 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1gWzek-0000jw-K4 for qemu-devel@nongnu.org; Wed, 12 Dec 2018 03:14:14 -0500 Received: from mga14.intel.com ([192.55.52.115]:18902) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1gWzee-0000aC-Ql for qemu-devel@nongnu.org; Wed, 12 Dec 2018 03:14:07 -0500 Received: from fmsmga007.fm.intel.com ([10.253.24.52]) by fmsmga103.fm.intel.com with ESMTP/TLS/DHE-RSA-AES256-GCM-SHA384; 12 Dec 2018 00:14:00 -0800 Received: from linux.intel.com ([10.54.29.200]) by fmsmga007.fm.intel.com with ESMTP; 12 Dec 2018 00:14:00 -0800 Received: from dazhang1-ssd.sh.intel.com (unknown [10.239.48.128]) by linux.intel.com (Postfix) with ESMTP id A3ED05803DC; Wed, 12 Dec 2018 00:13:56 -0800 (PST) X-Amp-Result: SKIPPED(no attachment in message) X-Amp-File-Uploaded: False X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="5.56,343,1539673200"; d="scan'208";a="106794872" From: Zhang Yi To: xiaoguangrong.eric@gmail.com, dan.j.williams@intel.com, stefanha@redhat.com, pbonzini@redhat.com, pagupta@redhat.com, yu.c.zhang@linux.intel.com Date: Wed, 12 Dec 2018 16:13:50 +0800 Message-Id: <7235b9884021516a83ca017ff5e86d0f208d3b43.1544598069.git.yi.z.zhang@linux.intel.com> X-Mailer: git-send-email 2.7.4 In-Reply-To: References: X-detected-operating-system: by eggs.gnu.org: Genre and OS details not recognized. X-Received-From: 192.55.52.115 Subject: [Qemu-devel] [PATCH V6 6/6] hostmem-file: add 'sync' option 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: imammedo@redhat.com, Zhang Yi , qemu-devel@nongnu.org, ehabkost@redhat.com, mst@redhat.com Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" Content-Transfer-Encoding: quoted-printable MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" This option controls whether QEMU mmap(2) the memory backend file with MAP_SYNC flag, which could consistent filesystem metadata for each guest write, if MAP_SYNC flag is supported by the host kernel(Linux kernel 4.15 and later) and the backend is a file supporting DAX (e.g., file on ext4/xfs file system mounted with '-o dax'). It can take one of following values: - on: try to pass MAP_SYNC to mmap(2); if MAP_SYNC is not supported or 'share=3Doff', QEMU will abort - off: never pass MAP_SYNC to mmap(2) - auto (default): if MAP_SYNC is supported and 'share=3Don', work as if 'sync=3Don'; otherwise, work as if 'sync=3Doff' Signed-off-by: Haozhong Zhang Signed-off-by: Zhang Yi Reviewed-by: Stefan Hajnoczi --- backends/hostmem-file.c | 39 +++++++++++++++++++++++++++++++++++++++ docs/nvdimm.txt | 20 +++++++++++++++++++- include/exec/memory.h | 8 ++++++++ qemu-options.hx | 22 +++++++++++++++++++++- 4 files changed, 87 insertions(+), 2 deletions(-) diff --git a/backends/hostmem-file.c b/backends/hostmem-file.c index 0dd7a90..73cf181 100644 --- a/backends/hostmem-file.c +++ b/backends/hostmem-file.c @@ -16,6 +16,7 @@ #include "sysemu/hostmem.h" #include "sysemu/sysemu.h" #include "qom/object_interfaces.h" +#include "qapi/qapi-visit.h" =20 /* hostmem-file.c */ /** @@ -36,6 +37,7 @@ struct HostMemoryBackendFile { uint64_t align; bool discard_data; bool is_pmem; + OnOffAuto sync; }; =20 static void @@ -62,6 +64,7 @@ file_backend_memory_alloc(HostMemoryBackend *backend, Err= or **errp) path, backend->size, fb->align, (backend->share ? RAM_SHARED : 0) | + qemu_ram_sync_flags(fb->sync) | (fb->is_pmem ? RAM_PMEM : 0), fb->mem_path, errp); g_free(path); @@ -136,6 +139,39 @@ static void file_memory_backend_set_align(Object *o, V= isitor *v, error_propagate(errp, local_err); } =20 +static void file_memory_backend_get_sync( + Object *obj, Visitor *v, const char *name, void *opaque, Error **errp) +{ + HostMemoryBackendFile *fb =3D MEMORY_BACKEND_FILE(obj); + OnOffAuto value =3D fb->sync; + + visit_type_OnOffAuto(v, name, &value, errp); +} + +static void file_memory_backend_set_sync( + Object *obj, Visitor *v, const char *name, void *opaque, Error **errp) +{ + HostMemoryBackend *backend =3D MEMORY_BACKEND(obj); + HostMemoryBackendFile *fb =3D MEMORY_BACKEND_FILE(obj); + Error *local_err =3D NULL; + OnOffAuto value; + + if (host_memory_backend_mr_inited(backend)) { + error_setg(&local_err, "cannot change property '%s' of %s", + name, object_get_typename(obj)); + goto out; + } + + visit_type_OnOffAuto(v, name, &value, &local_err); + if (local_err) { + goto out; + } + fb->sync =3D value; + + out: + error_propagate(errp, local_err); +} + static bool file_memory_backend_get_pmem(Object *o, Error **errp) { return MEMORY_BACKEND_FILE(o)->is_pmem; @@ -203,6 +239,9 @@ file_backend_class_init(ObjectClass *oc, void *data) object_class_property_add_bool(oc, "pmem", file_memory_backend_get_pmem, file_memory_backend_set_pmem, &error_abort); + object_class_property_add(oc, "sync", "OnOffAuto", + file_memory_backend_get_sync, file_memory_backend_set_sync, + NULL, NULL, &error_abort); } =20 static void file_backend_instance_finalize(Object *o) diff --git a/docs/nvdimm.txt b/docs/nvdimm.txt index 5f158a6..3d89174 100644 --- a/docs/nvdimm.txt +++ b/docs/nvdimm.txt @@ -142,11 +142,29 @@ backend of vNVDIMM: Guest Data Persistence ---------------------- =20 +vNVDIMM is designed and implemented to guarantee the guest data +persistence on the backends even on the host crash and power +failures. However, there are still some requirements and limitations +as explained below. + Though QEMU supports multiple types of vNVDIMM backends on Linux, -currently the only one that can guarantee the guest write persistence +if MAP_SYNC is not supported by the host kernel and the backends, +the only backend that can guarantee the guest write persistence is the device DAX on the real NVDIMM device (e.g., /dev/dax0.0), to which all guest access do not involve any host-side kernel cache. =20 +mmap(2) flag MAP_SYNC is added since Linux kernel 4.15. On such +systems, QEMU can mmap(2) the backend with MAP_SYNC, which can +guarantee the guest write persistence to vNVDIMM. Besides the host +kernel support, enabling MAP_SYNC in QEMU also requires: + + - the backend is a file supporting DAX, e.g., a file on an ext4 or + xfs file system mounted with '-o dax', + + - 'sync' option of memory-backend-file is not 'off', and + + - 'share' option of memory-backend-file is 'on'. + When using other types of backends, it's suggested to set 'unarmed' option of '-device nvdimm' to 'on', which sets the unarmed flag of the guest NVDIMM region mapping structure. This unarmed flag indicates diff --git a/include/exec/memory.h b/include/exec/memory.h index c74c467..b398abb 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -26,6 +26,7 @@ #include "qom/object.h" #include "qemu/rcu.h" #include "hw/qdev-core.h" +#include "qapi/error.h" =20 #define RAM_ADDR_INVALID (~(ram_addr_t)0) =20 @@ -136,6 +137,13 @@ typedef struct IOMMUNotifier IOMMUNotifier; =20 #define RAM_SYNC (RAM_SYNC_ON_OFF_AUTO_ON | RAM_SYNC_ON_OFF_AUTO_AUTO) =20 +static inline uint64_t qemu_ram_sync_flags(OnOffAuto v) +{ + return v =3D=3D ON_OFF_AUTO_OFF ? RAM_SYNC_ON_OFF_AUTO_OFF : + v =3D=3D ON_OFF_AUTO_ON ? RAM_SYNC_ON_OFF_AUTO_ON : + RAM_SYNC_ON_OFF_AUTO_AUTO; +} + static inline void iommu_notifier_init(IOMMUNotifier *n, IOMMUNotify fn, IOMMUNotifierFlag flags, hwaddr start, hwaddr end, diff --git a/qemu-options.hx b/qemu-options.hx index 08f8516..77e8810 100644 --- a/qemu-options.hx +++ b/qemu-options.hx @@ -3928,7 +3928,7 @@ property must be set. These objects are placed in the =20 @table @option =20 -@item -object memory-backend-file,id=3D@var{id},size=3D@var{size},mem-path= =3D@var{dir},share=3D@var{on|off},discard-data=3D@var{on|off},merge=3D@var{= on|off},dump=3D@var{on|off},prealloc=3D@var{on|off},host-nodes=3D@var{host-= nodes},policy=3D@var{default|preferred|bind|interleave},align=3D@var{align} +@item -object memory-backend-file,id=3D@var{id},size=3D@var{size},mem-path= =3D@var{dir},share=3D@var{on|off},discard-data=3D@var{on|off},merge=3D@var{= on|off},dump=3D@var{on|off},prealloc=3D@var{on|off},host-nodes=3D@var{host-= nodes},policy=3D@var{default|preferred|bind|interleave},align=3D@var{align}= ,sync=3D@var{on|off|auto} =20 Creates a memory file backend object, which can be used to back the guest RAM with huge pages. @@ -4003,6 +4003,26 @@ If @option{pmem} is set to 'on', QEMU will take nece= ssary operations to guarantee the persistence of its own writes to @option{mem-path} (e.g. in vNVDIMM label emulation and live migration). =20 +The @option{sync} option specifies whether QEMU mmap(2) @option{mem-path} +with MAP_SYNC flag, which can guarantee the guest write persistence to +@option{mem-path} even on the host crash and power failures. MAP_SYNC +requires supports from both the host kernel (since Linux kernel 4.15) +and @option{mem-path} (only files supporting DAX). It can take one of +following values: + +@table @option +@item @var{on} +try to pass MAP_SYNC to mmap(2); if MAP_SYNC is not supported or +@option{share}=3D@var{off}, QEMU will abort + +@item @var{off} +never pass MAP_SYNC to mmap(2) + +@item @var{auto} (default) +if MAP_SYNC is supported and @option{share}=3D@var{on}, work as if +@option{sync}=3D@var{on}; otherwise, work as if @option{sync}=3D@var{off} +@end table + @item -object memory-backend-ram,id=3D@var{id},merge=3D@var{on|off},dump= =3D@var{on|off},share=3D@var{on|off},prealloc=3D@var{on|off},size=3D@var{si= ze},host-nodes=3D@var{host-nodes},policy=3D@var{default|preferred|bind|inte= rleave} =20 Creates a memory backend object, which can be used to back the guest RAM. --=20 2.7.4