public inbox for linux-arch@vger.kernel.org
 help / color / mirror / Atom feed
From: Andrew Morton <akpm@osdl.org>
To: Paul Mackerras <paulus@samba.org>
Cc: ak@suse.de, davem@davemloft.net, dwmw2@infradead.org,
	linux-arch@vger.kernel.org
Subject: Re: TASK_SIZE is variable.
Date: Thu, 27 Jan 2005 19:17:38 -0800	[thread overview]
Message-ID: <20050127191738.13d65896.akpm@osdl.org> (raw)
In-Reply-To: <16889.44363.612523.453157@cargo.ozlabs.ibm.com>

Paul Mackerras <paulus@samba.org> wrote:
>
> > Here is a patch that I did recently to reduce the overhead of
>  > clear_page_tables() when using 64k pages on ppc64.  It keeps a record
>  > of the maximum address that has been used in each mm_struct.  With
>  > this we can kill MM_VM_SIZE.
> 
>  And I sent the 2.6.10 version of the patch, unfortunately.  Here is a
>  patch against current BK.

OK..  I'll drop Anton's patch:


From: Anton Blanchard <anton@samba.org>

The 4 level pagetable code changed the exit_mmap code to rely on TASK_SIZE.
 On some architectures (eg ppc64 and ia64), this is a per task property and
bad things can happen in certain circumstances when using it.

It is possible for one task to end up "owning" an mm from another - we have
seen this with the procfs code when process 1 accesses /proc/pid/cmdline of
process 2 while it is exiting.  Process 2 exits but does not tear its mm
down.  Later on process 1 finishes with the proc file and the mm gets torn
down at this point.

Now if process 1 was 32bit and process 2 was 64bit then we end up using a
bad value for TASK_SIZE in exit_mmap.  We only tear down part of the
address space and leave half initialised pagetables and entries in the MMU
etc.

MM_VM_SIZE() was created for this purpose (and is used in the next line for
tlb_finish_mmu), so use it.  I moved the PGD round up of TASK_SIZE into the
default MM_VM_SIZE.

As an aside, all architectures except one define FIRST_USER_PGD_NR as 0:

include/asm-arm26/pgtable.h:#define FIRST_USER_PGD_NR       1

It would be nice to get rid of one more magic constant and just clear from
0 ...  MM_VM_SIZE().  That would make it consistent with the tlb_flush_mmu
call below it too.

Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
---

 25-akpm/include/linux/mm.h |    2 +-
 25-akpm/mm/mmap.c          |    3 +--
 2 files changed, 2 insertions(+), 3 deletions(-)

diff -puN include/linux/mm.h~use-mm_vm_size-in-exit_mmap include/linux/mm.h
--- 25/include/linux/mm.h~use-mm_vm_size-in-exit_mmap	2005-01-25 21:41:44.365536624 -0800
+++ 25-akpm/include/linux/mm.h	2005-01-25 21:41:44.371535712 -0800
@@ -38,7 +38,7 @@ extern int sysctl_legacy_va_layout;
 #include <asm/atomic.h>
 
 #ifndef MM_VM_SIZE
-#define MM_VM_SIZE(mm)	TASK_SIZE
+#define MM_VM_SIZE(mm)	((TASK_SIZE + PGDIR_SIZE - 1) & PGDIR_MASK)
 #endif
 
 #define nth_page(page,n) pfn_to_page(page_to_pfn((page)) + (n))
diff -puN mm/mmap.c~use-mm_vm_size-in-exit_mmap mm/mmap.c
--- 25/mm/mmap.c~use-mm_vm_size-in-exit_mmap	2005-01-25 21:41:44.367536320 -0800
+++ 25-akpm/mm/mmap.c	2005-01-25 21:41:44.373535408 -0800
@@ -1980,8 +1980,7 @@ void exit_mmap(struct mm_struct *mm)
 					~0UL, &nr_accounted, NULL);
 	vm_unacct_memory(nr_accounted);
 	BUG_ON(mm->map_count);	/* This is just debugging */
-	clear_page_range(tlb, FIRST_USER_PGD_NR * PGDIR_SIZE,
-			(TASK_SIZE + PGDIR_SIZE - 1) & PGDIR_MASK);
+	clear_page_range(tlb, FIRST_USER_PGD_NR * PGDIR_SIZE, MM_VM_SIZE(mm));
 	
 	tlb_finish_mmu(tlb, 0, MM_VM_SIZE(mm));
 
_

  reply	other threads:[~2005-01-28  3:17 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-01-25 22:26 TASK_SIZE is variable David Woodhouse
2005-01-25 23:52 ` David S. Miller
2005-01-26  6:36   ` Andi Kleen
2005-01-26  6:41     ` David S. Miller
2005-01-26  7:13       ` Andi Kleen
2005-01-26  7:24         ` Andrew Morton
2005-01-26  7:43           ` Andi Kleen
2005-01-26  8:01             ` Andrew Morton
2005-01-26  8:04               ` Andi Kleen
2005-01-28  2:58               ` Paul Mackerras
2005-01-28  3:11                 ` Paul Mackerras
2005-01-28  3:17                   ` Andrew Morton [this message]
2005-01-28  6:40                     ` Andi Kleen
2005-01-29 11:23                       ` Anton Blanchard
2005-01-28  8:46                     ` Russell King
2005-01-28  6:39                 ` Andi Kleen
2005-01-28 11:32                   ` David Woodhouse
2005-01-26  7:54   ` David Woodhouse
2005-01-29 20:23 ` Andrew Morton
2005-01-29 23:28   ` Paul Mackerras
2005-01-30 11:01     ` Andi Kleen
2005-01-30 12:10       ` Paul Mackerras
2005-01-31  2:23         ` David S. Miller
2005-01-31  9:23           ` Andi Kleen
2005-01-31 19:29             ` David S. Miller
2005-01-31 19:38               ` Andi Kleen
2005-01-31 20:35                 ` David S. Miller
2005-02-03  4:08                   ` Andrew Morton
2005-02-03  6:28                     ` David S. Miller
2005-02-03  7:19                       ` Andi Kleen
2005-02-03  9:23                         ` David Woodhouse
2005-01-31  2:33     ` Matthew Wilcox

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20050127191738.13d65896.akpm@osdl.org \
    --to=akpm@osdl.org \
    --cc=ak@suse.de \
    --cc=davem@davemloft.net \
    --cc=dwmw2@infradead.org \
    --cc=linux-arch@vger.kernel.org \
    --cc=paulus@samba.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox