Received: from eggs.gnu.org ([209.51.188.92]:46855) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1hHFlf-0001jm-Bd for qemu-devel@nongnu.org; Thu, 18 Apr 2019 18:44:32 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1hHFaf-0000yz-RX for qemu-devel@nongnu.org; Thu, 18 Apr 2019 18:33:10 -0400 Received: from mx1.redhat.com ([209.132.183.28]:60574) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1hHFaf-0000xR-J6 for qemu-devel@nongnu.org; Thu, 18 Apr 2019 18:33:09 -0400 Date: Thu, 18 Apr 2019 19:33:01 -0300 From: Eduardo Habkost Message-ID: <20190418223301.GQ25134@habkost.net> References: <5d07bf7e9a3e576f5a87e81d786e8886fb2bb551.1549555521.git.yi.z.zhang@linux.intel.com> <20190418220516.GP25134@habkost.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Content-Disposition: inline In-Reply-To: <20190418220516.GP25134@habkost.net> Subject: Re: [Qemu-devel] [PATCH V13 4/5] util/mmap-alloc: support MAP_SYNC in qemu_ram_mmap() List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , To: "Zhang, Yi" Cc: xiaoguangrong.eric@gmail.com, stefanha@redhat.com, pbonzini@redhat.com, pagupta@redhat.com, yu.c.zhang@linux.intel.com, richardw.yang@linux.intel.com, mst@redhat.com, imammedo@redhat.com, dan.j.williams@intel.com, qemu-devel@nongnu.org, Murilo Opsfelder Araujo , Greg Kurz , David Gibson On Thu, Apr 18, 2019 at 07:05:16PM -0300, Eduardo Habkost wrote: > Hi, > > I found out that this series missed QEMU 4.0 and I was going to > queue for 4.1, but unfortunately this patch conflicts with: > > commit 2044c3e7116eeac0449dcb4a4130cc8f8b9310da > Author: Murilo Opsfelder Araujo > Date: Wed Jan 30 21:36:04 2019 -0200 > > mmap-alloc: unfold qemu_ram_mmap() [...] > On Fri, Feb 08, 2019 at 06:11:11PM +0800, Zhang, Yi wrote: > > From: Zhang Yi > > > > When a file supporting DAX is used as vNVDIMM backend, mmap it with > > MAP_SYNC flag in addition which can ensure file system metadata > > synced in each guest writes to the backend file, without other QEMU > > actions (e.g., periodic fsync() by QEMU). > > > > Current, We have below different possible use cases: > > > > 1. pmem=on is set, shared=on is set, MAP_SYNC supported: > > a: backend is a dax supporting file. > > - MAP_SYNC will active. > > b: backend is not a dax supporting file. > > - mmap will trigger a warning. then MAP_SYNC flag will be ignored > > > > 2. The rest of cases: > > - we will never pass the MAP_SYNC to mmap2 > > > > Signed-off-by: Haozhong Zhang > > Signed-off-by: Zhang Yi Untested patch rebase is below. Can Intel help test it and submit v14? Signed-off-by: Haozhong Zhang Signed-off-by: Zhang Yi [ehabkost: Rebased patch to latest code on master] Signed-off-by: Eduardo Habkost --- util/mmap-alloc.c | 41 +++++++++++++++++++++++++++++++++++++++-- 1 file changed, 39 insertions(+), 2 deletions(-) diff --git a/util/mmap-alloc.c b/util/mmap-alloc.c index 9713f4b960..7063a44c7d 100644 --- a/util/mmap-alloc.c +++ b/util/mmap-alloc.c @@ -10,6 +10,13 @@ * later. See the COPYING file in the top-level directory. */ +#ifdef CONFIG_LINUX +#include +#else /* !CONFIG_LINUX */ +#define MAP_SYNC 0x0 +#define MAP_SHARED_VALIDATE 0x0 +#endif /* CONFIG_LINUX */ + #include "qemu/osdep.h" #include "qemu/mmap-alloc.h" #include "qemu/host-utils.h" @@ -82,6 +89,7 @@ void *qemu_ram_mmap(int fd, bool is_pmem) { int flags; + int map_sync_flags = 0; int guardfd; size_t offset; size_t pagesize; @@ -132,10 +140,39 @@ void *qemu_ram_mmap(int fd, flags = MAP_FIXED; flags |= fd == -1 ? MAP_ANONYMOUS : 0; flags |= shared ? MAP_SHARED : MAP_PRIVATE; + if (shared && is_pmem) { + map_sync_flags = MAP_SYNC | MAP_SHARED_VALIDATE; + } offset = QEMU_ALIGN_UP((uintptr_t)guardptr, align) - (uintptr_t)guardptr; - ptr = mmap(guardptr + offset, size, PROT_READ | PROT_WRITE, flags, fd, 0); - + ptr = mmap(guardptr + offset, size, PROT_READ | PROT_WRITE, + flags | map_sync_flags, fd, 0); + + if (ptr == MAP_FAILED && map_sync_flags) { + if (errno == ENOTSUP) { + char *proc_link, *file_name; + int len; + proc_link = g_strdup_printf("/proc/self/fd/%d", fd); + file_name = g_malloc0(PATH_MAX); + len = readlink(proc_link, file_name, PATH_MAX - 1); + if (len < 0) { + len = 0; + } + file_name[len] = '\0'; + fprintf(stderr, "Warning: requesting persistence across crashes " + "for backend file %s failed. Proceeding without " + "persistence, data might become corrupted in case of host " + "crash.\n", file_name); + g_free(proc_link); + g_free(file_name); + } + /* + * if map failed with MAP_SHARED_VALIDATE | MAP_SYNC, + * we will remove these flags to handle compatibility. + */ + ptr = mmap(guardptr + offset, size, PROT_READ | PROT_WRITE, + flags, fd, 0); + } if (ptr == MAP_FAILED) { munmap(guardptr, total); return MAP_FAILED; -- 2.18.0.rc1.1.g3f1ff2140