Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752800AbcJMIjg (ORCPT ); Thu, 13 Oct 2016 04:39:36 -0400 Received: from mail-lf0-f68.google.com ([209.85.215.68]:35074 "EHLO mail-lf0-f68.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752180AbcJMIjV (ORCPT ); Thu, 13 Oct 2016 04:39:21 -0400 Cc: mtk.manpages@gmail.com, mhocko@kernel.org, mgorman@techsingularity.net, a.p.zijlstra@chello.nl, riel@redhat.com, linux-mm@kvack.org, linux-kernel@vger.kernel.org, linux-man@vger.kernel.org, Brice Goglin To: Christoph Lameter , Piotr Kwapulinski From: "Michael Kerrisk (man-pages)" Subject: Rewording language in mbind(2) to "threads" not "processes" Message-ID: Date: Thu, 13 Oct 2016 10:38:33 +0200 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:45.0) Gecko/20100101 Thunderbird/45.2.0 MIME-Version: 1.0 Content-Type: text/plain; charset=utf-8 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 6432 Lines: 173 Christoph, Piotr, and Brice Since you (Christoph and Piotr) helped with documenting MPOL_LOCAL just recently, I wonder if I might ask you to review a patch that I propose for the mbind(2) manual page. As far as I understand, memory policy, as set by set_mempolicy(2) is a per-thread attribute. The set_mempolicy(2) and get_mempolicy(2) pages already reflect this, thanks to a patch from Brice last year. However, such changes were not made in the mbind(2) page. I wonder if I could ask you (and Brice, and anyone who's willing) to look at the patch that I propose below to remedy this. (There are a couple questions "???" that I've injected in the patch.) Is it okay? Cheers, Michael diff --git a/man2/mbind.2 b/man2/mbind.2 index a5f26e2..9494854 100644 --- a/man2/mbind.2 +++ b/man2/mbind.2 @@ -75,16 +75,16 @@ page in the kernel containing all zeros. For a file mapped with .BR MAP_PRIVATE , an initial read access will allocate pages according to the -process policy of the process that causes the page to be allocated. -This may not be the process that called +memory policy of the thread that causes the page to be allocated. +This may not be the thread that called .BR mbind (). The specified policy will be ignored for any .B MAP_SHARED mappings in the specified memory range. -Rather the pages will be allocated according to the process policy -of the process that caused the page to be allocated. -Again, this may not be the process that called +Rather the pages will be allocated according to the memory policy +of the thread that caused the page to be allocated. +Again, this may not be the thread that called .BR mbind (). If the specified memory range includes a shared memory region @@ -100,7 +100,10 @@ If, however, the shared memory region was created with the .B SHM_HUGETLB flag, the huge pages will be allocated according to the policy specified -only if the page allocation is caused by the process that calls +only if the page allocation is caused by the thread that calls +.\" +.\" ??? Is it correct to change "process" to "thread" in the preceding line? +.\" .BR mbind () for that region. @@ -146,15 +149,15 @@ A nonempty specifies physical node IDs. Linux does not remap the .I nodemask -when the process moves to a different cpuset context, -nor when the set of nodes allowed by the process's +when the thread moves to a different cpuset context, +nor when the set of nodes allowed by the thread's current cpuset context changes. .TP .BR MPOL_F_RELATIVE_NODES " (since Linux-2.6.26)" A nonempty .I nodemask specifies node IDs that are relative to the set of -node IDs allowed by the process's current cpuset. +node IDs allowed by the thread's current cpuset. .PP .I nodemask points to a bit mask of nodes containing up to @@ -178,7 +181,7 @@ argument is ignored. Where a .I nodemask is required, it must contain at least one node that is on-line, -allowed by the process's current cpuset context +allowed by the thread's current cpuset context (unless the .B MPOL_F_STATIC_NODES mode flag is specified), @@ -194,10 +197,10 @@ mode requests that any nondefault policy be removed, restoring default behavior. When applied to a range of memory via .BR mbind (), -this means to use the process policy, +this means to use the thread memory policy, which may have been set with .BR set_mempolicy (2). -If the mode of the process policy is also +If the mode of the thread memory policy is also .BR MPOL_DEFAULT , the system-wide default policy will be used. The system-wide default policy allocates @@ -268,13 +271,13 @@ If the "local node" is low on free memory, the kernel will try to allocate memory from other nodes. The kernel will allocate memory from the "local node" whenever memory for this node is available. -If the "local node" is not allowed by the process's current cpuset context, +If the "local node" is not allowed by the thread's current cpuset context, the kernel will try to allocate memory from other nodes. The kernel will allocate memory from the "local node" whenever -it becomes allowed by the process's current cpuset context. +it becomes allowed by the thread's current cpuset context. By contrast, .B MPOL_DEFAULT -reverts to the policy of the process (which may be set via +reverts to the memory policy of the thread (which may be set via .BR set_mempolicy (2)); that policy may be something other than "local allocation". .PP @@ -300,7 +303,10 @@ is specified in .IR flags , then the kernel will attempt to move all the existing pages in the memory range so that they follow the policy. -Pages that are shared with other processes will not be moved. +Pages that are shared with other threads will not be moved. +.\" +.\" ??? Is it correct to change "processes" to "threads" in the preceding line? +.\" If .B MPOL_MF_STRICT is also specified, then the call will fail with the error @@ -312,8 +318,11 @@ If is passed in .IR flags , then the kernel will attempt to move all existing pages in the memory range -regardless of whether other processes use the pages. -The calling process must be privileged +regardless of whether other threads use the pages. +.\" +.\" ??? Is it correct to change "processes" to "threads" in the preceding line? +.\" +The calling thread must be privileged .RB ( CAP_SYS_NICE ) to use this flag. If @@ -383,7 +392,7 @@ specifies one or more node IDs that are greater than the maximum supported node ID. Or, none of the node IDs specified by .I nodemask -are on-line and allowed by the process's current cpuset context, +are on-line and allowed by the thread's current cpuset context, or none of the specified nodes contain memory. Or, the .I mode @@ -440,14 +449,14 @@ When .B MPOL_DEFAULT is specified for .BR set_mempolicy (2), -the process's policy reverts to system default policy +the thread's memory policy reverts to the system default policy or local allocation. When .B MPOL_DEFAULT is specified for a range of memory using .BR mbind (), any pages subsequently allocated for that range will use -the process's policy, as set by +the thread's memory policy, as set by .BR set_mempolicy (2). This effectively removes the explicit policy from the specified range, "falling back" to a possibly nondefault -- Michael Kerrisk Linux man-pages maintainer; http://www.kernel.org/doc/man-pages/ Linux/UNIX System Programming Training: http://man7.org/training/