| lists.openwall.net | lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC | |
|
Open Source and information security mailing list archives
| ||
|
Date: Wed, 18 Aug 2010 12:19:51 +0530
From: Nikanth Karthikesan <knikanth@...e.de>
To: balbir@...ux.vnet.ibm.com
Cc: Matt Mackall <mpm@...enic.com>,
Andrew Morton <akpm@...ux-foundation.org>,
linux-kernel@...r.kernel.org, linux-mm@...ck.org
Subject: Re: [PATCH] Export mlock information via smaps
On Wednesday 18 August 2010 11:22:53 Balbir Singh wrote:
> * Nikanth Karthikesan <knikanth@...e.de> [2010-08-18 10:23:41]:
> > On Tuesday 17 August 2010 21:55:36 Matt Mackall wrote:
> > > On Tue, 2010-08-17 at 10:39 +0530, Nikanth Karthikesan wrote:
> > > > Currently there is no way to find whether a process has locked its
> > > > pages in memory or not. And which of the memory regions are locked in
> > > > memory.
> > > >
> > > > Add a new field to perms field 'l' to export this information. The
> > > > information exported via maps file is not changed.
> > >
> > > I'm worried that your new 'l' flag will fatally surprise some naive
> > > parser of this file.
> >
> > So how to proceed? Create another "ssmaps" file or something? :) Or is
> > the following patch any better? Even the "Yes"/"No" could be changed to
> > "0 kB" or "x kB", if it would make it better.
> >
> > Thanks
> > Nikanth
> >
> > Currently there is no way to find whether a process has locked its pages
> > in memory or not. And which of the memory regions are locked in memory.
> >
> > Add a new field "Locked" to export this information via smaps file.
> >
> > Signed-off-by: Nikanth Karthikesan <knikanth@...e.de>
> >
> > ---
> >
> > diff --git a/Documentation/filesystems/proc.txt
> > b/Documentation/filesystems/proc.txt index a6aca87..6eafd26 100644
> > --- a/Documentation/filesystems/proc.txt
> > +++ b/Documentation/filesystems/proc.txt
> > @@ -373,6 +373,7 @@ Referenced: 892 kB
> > Swap: 0 kB
> > KernelPageSize: 4 kB
> > MMUPageSize: 4 kB
> > +Locked: No
> >
> > The first of these lines shows the same information as is displayed
> > for the mapping in /proc/PID/maps. The remaining lines show the size of
> > the mapping, @@ -397,6 +398,8 @@ To clear the bits for the file mapped
> > pages associated with the process
> >
> > > echo 3 > /proc/PID/clear_refs
> >
> > Any other value written to /proc/PID/clear_refs will have no effect.
> >
> > +The "Locked" indicates whether the mapping is locked in memory or not.
> > +
> >
> > 1.2 Kernel data
> > ---------------
> > diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
> > index aea1d3f..7bafbcf 100644
> > --- a/fs/proc/task_mmu.c
> > +++ b/fs/proc/task_mmu.c
> > @@ -405,7 +405,8 @@ static int show_smap(struct seq_file *m, void *v)
> > "Referenced: %8lu kB\n"
> > "Swap: %8lu kB\n"
> > "KernelPageSize: %8lu kB\n"
> > - "MMUPageSize: %8lu kB\n",
> > + "MMUPageSize: %8lu kB\n"
> > + "Locked: %s\n",
> > (vma->vm_end - vma->vm_start) >> 10,
> > mss.resident >> 10,
> > (unsigned long)(mss.pss >> (10 + PSS_SHIFT)),
> > @@ -416,7 +417,8 @@ static int show_smap(struct seq_file *m, void *v)
> > mss.referenced >> 10,
> > mss.swap >> 10,
> > vma_kernel_pagesize(vma) >> 10,
> > - vma_mmu_pagesize(vma) >> 10);
> > + vma_mmu_pagesize(vma) >> 10,
> > + (vma->vm_flags & VM_LOCKED) ? "Yes" : "No");
>
> Why not show the Locked as kB as well? I know that the entire VMA is
> locked, but ideally if we can show mss.pss as locked, one can write
> a simple script to accumulate locked memory for the process. NOTE:
> One could choose RSS or PSS, but I'd prefer PSS (even though the
> value is not stable across the system) since it is more accurate
> representation of the truly locked memory.
>
Agreed. Attached patch does this, i.e, uses PSS as amount of locked memory.
Matt, will this be okay?
Thanks
Nikanth
Currently there is no way to find whether a process has locked its pages in
memory or not. And which of the memory regions are locked in memory.
Add a new field "Locked" to export this information via smaps file.
Signed-off-by: Nikanth Karthikesan <knikanth@...e.de>
---
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index a6aca87..17b0ae0 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -373,6 +373,7 @@ Referenced: 892 kB
Swap: 0 kB
KernelPageSize: 4 kB
MMUPageSize: 4 kB
+Locked: 374 kB
The first of these lines shows the same information as is displayed for the
mapping in /proc/PID/maps. The remaining lines show the size of the mapping,
@@ -397,6 +398,8 @@ To clear the bits for the file mapped pages associated with the process
> echo 3 > /proc/PID/clear_refs
Any other value written to /proc/PID/clear_refs will have no effect.
+The "Locked" indicates whether the mapping is locked in memory or not.
+
1.2 Kernel data
---------------
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index aea1d3f..58e586c 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -405,7 +405,8 @@ static int show_smap(struct seq_file *m, void *v)
"Referenced: %8lu kB\n"
"Swap: %8lu kB\n"
"KernelPageSize: %8lu kB\n"
- "MMUPageSize: %8lu kB\n",
+ "MMUPageSize: %8lu kB\n"
+ "Locked: %8lu kB\n",
(vma->vm_end - vma->vm_start) >> 10,
mss.resident >> 10,
(unsigned long)(mss.pss >> (10 + PSS_SHIFT)),
@@ -416,7 +417,9 @@ static int show_smap(struct seq_file *m, void *v)
mss.referenced >> 10,
mss.swap >> 10,
vma_kernel_pagesize(vma) >> 10,
- vma_mmu_pagesize(vma) >> 10);
+ vma_mmu_pagesize(vma) >> 10,
+ (vma->vm_flags & VM_LOCKED) ?
+ (unsigned long)(mss.pss >> (10 + PSS_SHIFT)) : 0);
if (m->count < m->size) /* vma is copied successfully */
m->version = (vma != get_gate_vma(task)) ? vma->vm_start : 0;
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists