linux-toradex.git/fs/proc, branch v2.6.38.2

proc: protect mm start_code/end_code in /proc/pid/stat

2011-03-27T18:36:03+00:00

commit 5883f57ca0008ffc93e09cbb9847a1928e50c6f3 upstream.

While mm->start_stack was protected from cross-uid viewing (commit
f83ce3e6b02d5 ("proc: avoid information leaks to non-privileged
processes")), the start_code and end_code values were not.  This would
allow the text location of a PIE binary to leak, defeating ASLR.

Note that the value "1" is used instead of "0" for a protected value since
"ps", "killall", and likely other readers of /proc/pid/stat, take
start_code of "0" to mean a kernel thread and will misbehave.  Thanks to
Brad Spengler for pointing this out.

Addresses CVE-2011-0726

Signed-off-by: Kees Cook 
Cc: Alexey Dobriyan 
Cc: David Howells 
Cc: Eugene Teo 
Cc: Martin Schwidefsky 
Cc: Brad Spengler 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

procfs: fix /proc//maps heap check

2011-03-27T18:36:02+00:00

commit 0db0c01b53a1a421513f91573241aabafb87802a upstream.

The current code fails to print the "[heap]" marking if the heap is split
into multiple mappings.

Fix the check so that the marking is displayed in all possible cases:
	1. vma matches exactly the heap
	2. the heap vma is merged e.g. with bss
	3. the heap vma is splitted e.g. due to locked pages

Test cases. In all cases, the process should have mapping(s) with
[heap] marking:

	(1) vma matches exactly the heap

	#include 
	#include 
	#include 

	int main (void)
	{
		if (sbrk(4096) != (void *)-1) {
			printf("check /proc/%d/maps\n", (int)getpid());
			while (1)
				sleep(1);
		}
		return 0;
	}

	# ./test1
	check /proc/553/maps
	[1] + Stopped                    ./test1
	# cat /proc/553/maps | head -4
	00008000-00009000 r-xp 00000000 01:00 3113640    /test1
	00010000-00011000 rw-p 00000000 01:00 3113640    /test1
	00011000-00012000 rw-p 00000000 00:00 0          [heap]
	4006f000-40070000 rw-p 00000000 00:00 0

	(2) the heap vma is merged

	#include 
	#include 
	#include 

	char foo[4096] = "foo";
	char bar[4096];

	int main (void)
	{
		if (sbrk(4096) != (void *)-1) {
			printf("check /proc/%d/maps\n", (int)getpid());
			while (1)
				sleep(1);
		}
		return 0;
	}

	# ./test2
	check /proc/556/maps
	[2] + Stopped                    ./test2
	# cat /proc/556/maps | head -4
	00008000-00009000 r-xp 00000000 01:00 3116312    /test2
	00010000-00012000 rw-p 00000000 01:00 3116312    /test2
	00012000-00014000 rw-p 00000000 00:00 0          [heap]
	4004a000-4004b000 rw-p 00000000 00:00 0

	(3) the heap vma is splitted (this fails without the patch)

	#include 
	#include 
	#include 
	#include 

	int main (void)
	{
		if ((sbrk(4096) != (void *)-1) && !mlockall(MCL_FUTURE) &&
		    (sbrk(4096) != (void *)-1)) {
			printf("check /proc/%d/maps\n", (int)getpid());
			while (1)
				sleep(1);
		}
		return 0;
	}

	# ./test3
	check /proc/559/maps
	[1] + Stopped                    ./test3
	# cat /proc/559/maps|head -4
	00008000-00009000 r-xp 00000000 01:00 3119108    /test3
	00010000-00011000 rw-p 00000000 01:00 3119108    /test3
	00011000-00012000 rw-p 00000000 00:00 0          [heap]
	00012000-00013000 rw-p 00000000 00:00 0          [heap]

It looks like the bug has been there forever, and since it only results in
some information missing from a procfile, it does not fulfil the -stable
"critical issue" criteria.

Signed-off-by: Aaro Koskinen 
Reviewed-by: KOSAKI Motohiro 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds 
Signed-off-by: Greg Kroah-Hartman

/proc/self is never going to be invalidated...

2011-03-10T08:41:53+00:00

Signed-off-by: Al Viro

unfuck proc_sysctl ->d_compare()

2011-03-08T07:22:27+00:00

a) struct inode is not going to be freed under ->d_compare();
however, the thing PROC_I(inode)->sysctl points to just might.
Fortunately, it's enough to make freeing that sucker delayed,
provided that we don't step on its ->unregistering, clear
the pointer to it in PROC_I(inode) before dropping the reference
and check if it's NULL in ->d_compare().

b) I'm not sure that we *can* walk into NULL inode here (we recheck
dentry->seq between verifying that it's still hashed / fetching
dentry->d_inode and passing it to ->d_compare() and there's no
negative hashed dentries in /proc/sys/*), but if we can walk into
that, we really should not have ->d_compare() return 0 on it!
Said that, I really suspect that this check can be simply killed.
Nick?

Signed-off-by: Al Viro

of/flattree: Drop an uninteresting message to pr_debug level

2011-03-02T20:45:18+00:00

This message looks like an error (which it isn't) when booting with a
flattened device tree.  Remove the message from normal kernel builds.

Signed-off-by: Paul Bolle 
Signed-off-by: Grant Likely

s390: remove task_show_regs

2011-02-15T15:34:16+00:00

task_show_regs used to be a debugging aid in the early bringup days
of Linux on s390. /proc//status is a world readable file, it
is not a good idea to show the registers of a process. The only
correct fix is to remove task_show_regs.

Reported-by: Al Viro 
Signed-off-by: Martin Schwidefsky 
Signed-off-by: Linus Torvalds

console: rename acquire/release_console_sem() to console_lock/unlock()

2011-01-26T00:50:06+00:00

The -rt patches change the console_semaphore to console_mutex.  As a
result, a quite large chunk of the patches changes all
acquire/release_console_sem() to acquire/release_console_mutex()

This commit makes things use more neutral function names which dont make
implications about the underlying lock.

The only real change is the return value of console_trylock which is
inverted from try_acquire_console_sem()

This patch also paves the way to switching console_sem from a semaphore to
a mutex.

[akpm@linux-foundation.org: coding-style fixes]
[akpm@linux-foundation.org: make console_trylock return 1 on success, per Geert]
Signed-off-by: Torben Hohn 
Cc: Thomas Gleixner 
Cc: Greg KH 
Cc: Ingo Molnar 
Cc: Geert Uytterhoeven 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

kconfig: rename CONFIG_EMBEDDED to CONFIG_EXPERT

2011-01-21T01:02:05+00:00

The meaning of CONFIG_EMBEDDED has long since been obsoleted; the option
is used to configure any non-standard kernel with a much larger scope than
only small devices.

This patch renames the option to CONFIG_EXPERT in init/Kconfig and fixes
references to the option throughout the kernel.  A new CONFIG_EMBEDDED
option is added that automatically selects CONFIG_EXPERT when enabled and
can be used in the future to isolate options that should only be
considered for embedded systems (RISC architectures, SLOB, etc).

Calling the option "EXPERT" more accurately represents its intention: only
expert users who understand the impact of the configuration changes they
are making should enable it.

Reviewed-by: Ingo Molnar 
Acked-by: David Woodhouse 
Signed-off-by: David Rientjes 
Cc: Greg KH 
Cc: "David S. Miller" 
Cc: Jens Axboe 
Cc: Arnd Bergmann 
Cc: Robin Holt 
Cc: 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

thp: remove PG_buddy

2011-01-14T01:32:43+00:00

PG_buddy can be converted to _mapcount == -2.  So the PG_compound_lock can
be added to page->flags without overflowing (because of the sparse section
bits increasing) with CONFIG_X86_PAE=y and CONFIG_X86_PAT=y.  This also
has to move the memory hotplug code from _mapcount to lru.next to avoid
any risk of clashes.  We can't use lru.next for PG_buddy removal, but
memory hotplug can use lru.next even more easily than the mapcount
instead.

Signed-off-by: Andrea Arcangeli 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds

thp: transparent hugepage vmstat

2011-01-14T01:32:43+00:00

Add hugepage stat information to /proc/vmstat and /proc/meminfo.

Signed-off-by: Andrea Arcangeli 
Acked-by: Rik van Riel 
Signed-off-by: Andrew Morton 
Signed-off-by: Linus Torvalds