Skip to content

L
linux-davinci-2.6.23
An error occurred fetching the project authors.
Switch branch/tag
  1. 19 Sep, 2007 1 commit
    • Linus Torvalds's avatar
      x86-64: page faults from user mode are always user faults · dbe3ed1c
      Linus Torvalds authored 
      Randy Dunlap noticed an interesting "crashme" behaviour on his dual
Prescott Xeon setup, where he gets page faults with the error code
having a zero "user" bit, but the register state points back to user
mode.

This may be a CPU microcode buglet triggered by some strange instruction
pattern that crashme generates, and loading a microcode update seems to
possibly have fixed it.

Regardless, we really should trust the register state more than the
error code, since it's really the register state that determines whether
we can actually send a signal, or whether we're in kernel mode and need
to oops/kill the process in the case of a page fault.

Cc: Randy Dunlap <rdunlap@xenotime.net>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
      dbe3ed1c
  3. 22 Jul, 2007 4 commits
  5. 19 Jul, 2007 1 commit
    • Nick Piggin's avatar
      mm: fault feedback #2 · 83c54070
      Nick Piggin authored 
      This patch completes Linus's wish that the fault return codes be made into
bit flags, which I agree makes everything nicer.  This requires requires
all handle_mm_fault callers to be modified (possibly the modifications
should go further and do things like fault accounting in handle_mm_fault --
however that would be for another patch).

[akpm@linux-foundation.org: fix alpha build]
[akpm@linux-foundation.org: fix s390 build]
[akpm@linux-foundation.org: fix sparc build]
[akpm@linux-foundation.org: fix sparc64 build]
[akpm@linux-foundation.org: fix ia64 build]
Signed-off-by: default avatarNick Piggin <npiggin@suse.de>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: Ian Molton <spyro@f2s.com>
Cc: Bryan Wu <bryan.wu@analog.com>
Cc: Mikael Starvik <starvik@axis.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Yoshinori Sato <ysato@users.sourceforge.jp>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Hirokazu Takata <takata@linux-m32r.org>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Roman Zippel <zippel@linux-m68k.org>
Cc: Greg Ungerer <gerg@uclinux.org>
Cc: Matthew Wilcox <willy@debian.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp>
Cc: Richard Curnow <rc@rc0.org.uk>
Cc: William Lee Irwin III <wli@holomorphy.com>
Cc: "David S. Miller" <davem@davemloft.net>
Cc: Jeff Dike <jdike@addtoit.com>
Cc: Paolo 'Blaisorblade' Giarrusso <blaisorblade@yahoo.it>
Cc: Miles Bader <uclinux-v850@lsi.nec.co.jp>
Cc: Chris Zankel <chris@zankel.net>
Acked-by: default avatarKyle McMartin <kyle@mcmartin.ca>
Acked-by: default avatarHaavard Skinnemoen <hskinnemoen@atmel.com>
Acked-by: default avatarRalf Baechle <ralf@linux-mips.org>
Acked-by: default avatarAndi Kleen <ak@muc.de>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
[ Still apparently needs some ARM and PPC loving - Linus ]
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
      83c54070
  7. 08 Jun, 2007 1 commit
    • Steven Rostedt's avatar
      enable interrupts in user path of page fault. · e5e3c84b
      Steven Rostedt authored 
      This is a minor fix, but what is currently there is essentially wrong.
In do_page_fault, if the faulting address from user code happens to be
in kernel address space (int *p = (int*)-1; p = 0xbed;)  then the
do_page_fault handler will jump over the local_irq_enable with the

  goto bad_area_nosemaphore;

But the first line there sees this is user code and goes through the
process of sending a signal to send SIGSEGV to the user task. This whole
time interrupts are disabled and the task can not be preempted by a
higher priority task.

This patch always enables interrupts in the user path of the
bad_area_nosemaphore.
Signed-off-by: default avatarSteven Rostedt <rostedt@goodmis.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
      e5e3c84b
  9. 08 May, 2007 2 commits
  11. 02 May, 2007 1 commit
  13. 13 Feb, 2007 1 commit
  15. 11 Feb, 2007 1 commit
  17. 07 Dec, 2006 1 commit
  19. 29 Sep, 2006 2 commits
    • Sukadev Bhattiprolu's avatar
      [PATCH] pidspace: is_init() · f400e198
      Sukadev Bhattiprolu authored 
      This is an updated version of Eric Biederman's is_init() patch.
(http://lkml.org/lkml/2006/2/6/280).  It applies cleanly to 2.6.18-rc3 and
replaces a few more instances of ->pid == 1 with is_init().

Further, is_init() checks pid and thus removes dependency on Eric's other
patches for now.

Eric's original description:

	There are a lot of places in the kernel where we test for init
	because we give it special properties.  Most  significantly init
	must not die.  This results in code all over the kernel test
	->pid == 1.

	Introduce is_init to capture this case.

	With multiple pid spaces for all of the cases affected we are
	looking for only the first process on the system, not some other
	process that has pid == 1.
Signed-off-by: default avatarEric W. Biederman <ebiederm@xmission.com>
Signed-off-by: default avatarSukadev Bhattiprolu <sukadev@us.ibm.com>
Cc: Dave Hansen <haveblue@us.ibm.com>
Cc: Serge Hallyn <serue@us.ibm.com>
Cc: Cedric Le Goater <clg@fr.ibm.com>
Cc: <lxc-devel@lists.sourceforge.net>
Acked-by: default avatarPaul Mackerras <paulus@samba.org>
Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      f400e198
    • Jason Baron's avatar
      [PATCH] make PROT_WRITE imply PROT_READ · df67b3da
      Jason Baron authored 
      Make PROT_WRITE imply PROT_READ for a number of architectures which don't
support write only in hardware.

While looking at this, I noticed that some architectures which do not
support write only mappings already take the exact same approach.  For
example, in arch/alpha/mm/fault.c:

"
        if (cause < 0) {
                if (!(vma->vm_flags & VM_EXEC))
                        goto bad_area;
        } else if (!cause) {
                /* Allow reads even for write-only mappings */
                if (!(vma->vm_flags & (VM_READ | VM_WRITE)))
                        goto bad_area;
        } else {
                if (!(vma->vm_flags & VM_WRITE))
                        goto bad_area;
        }
"

Thus, this patch brings other architectures which do not support write only
mappings in-line and consistent with the rest.  I've verified the patch on
ia64, x86_64 and x86.

Additional discussion:

Several architectures, including x86, can not support write-only mappings.
The pte for x86 reserves a single bit for protection and its two states are
read only or read/write.  Thus, write only is not supported in h/w.

Currently, if i 'mmap' a page write-only, the first read attempt on that page
creates a page fault and will SEGV.  That check is enforced in
arch/blah/mm/fault.c.  However, if i first write that page it will fault in
and the pte will be set to read/write.  Thus, any subsequent reads to the page
will succeed.  It is this inconsistency in behavior that this patch is
attempting to address.  Furthermore, if the page is swapped out, and then
brought back the first read will also cause a SEGV.  Thus, any arbitrary read
on a page can potentially result in a SEGV.

According to the SuSv3 spec, "if the application requests only PROT_WRITE, the
implementation may also allow read access." Also as mentioned, some
archtectures, such as alpha, shown above already take the approach that i am
suggesting.

The counter-argument to this raised by Arjan, is that the kernel is enforcing
the write only mapping the best it can given the h/w limitations.  This is
true, however Alan Cox, and myself would argue that the inconsitency in
behavior, that is applications can sometimes work/sometimes fails is highly
undesireable.  If you read through the thread, i think people, came to an
agreement on the last patch i posted, as nobody has objected to it...
Signed-off-by: default avatarJason Baron <jbaron@redhat.com>
Cc: Russell King <rmk@arm.linux.org.uk>
Cc: "Luck, Tony" <tony.luck@intel.com>
Cc: Hugh Dickins <hugh@veritas.com>
Cc: Roman Zippel <zippel@linux-m68k.org>
Cc: Geert Uytterhoeven <geert@linux-m68k.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Acked-by: default avatarAndi Kleen <ak@muc.de>
Acked-by: default avatarAlan Cox <alan@lxorguk.ukuu.org.uk>
Cc: Arjan van de Ven <arjan@linux.intel.com>
Acked-by: default avatarPaul Mundt <lethal@linux-sh.org>
Cc: Kazumoto Kojima <kkojima@rr.iij4u.or.jp>
Cc: Ian Molton <spyro@f2s.com>
Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      df67b3da
  21. 26 Sep, 2006 3 commits
    • Dave McCracken's avatar
      [PATCH] Standardize pxx_page macros · 46a82b2d
      Dave McCracken authored 
      One of the changes necessary for shared page tables is to standardize the
pxx_page macros.  pte_page and pmd_page have always returned the struct
page associated with their entry, while pte_page_kernel and pmd_page_kernel
have returned the kernel virtual address.  pud_page and pgd_page, on the
other hand, return the kernel virtual address.

Shared page tables needs pud_page and pgd_page to return the actual page
structures.  There are very few actual users of these functions, so it is
simple to standardize their usage.

Since this is basic cleanup, I am submitting these changes as a standalone
patch.  Per Hugh Dickins' comments about it, I am also changing the
pxx_page_kernel macros to pxx_page_vaddr to clarify their meaning.
Signed-off-by: default avatarDave McCracken <dmccr@us.ibm.com>
Cc: Hugh Dickins <hugh@veritas.com>
Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      46a82b2d
    • Andi Kleen's avatar
      [PATCH] make fault notifier unconditional and export it · 273819a2
      Andi Kleen authored 
      It's needed for external debuggers and overhead is very small.

Also make the actual notifier chain they use static

Cc: jbeulich@novell.com
Signed-off-by: default avatarAndi Kleen <ak@suse.de>
      273819a2
    • Andi Kleen's avatar
      [PATCH] Add sparse annotations to quiet sparse in arch/x86_64/mm/fault.c · dd2994f6
      Andi Kleen authored 
      Fixes

linux/arch/x86_64/mm/fault.c:125:7: warning: incorrect type in argument 1 (different address spaces)
linux/arch/x86_64/mm/fault.c:125:7:    expected void [noderef] *<noident><asn:1>
linux/arch/x86_64/mm/fault.c:125:7:    got unsigned char *[assigned] instr
linux/arch/x86_64/mm/fault.c:163:8: warning: incorrect type in argument 1 (different address spaces)
linux/arch/x86_64/mm/fault.c:163:8:    expected void [noderef] *<noident><asn:1>
linux/arch/x86_64/mm/fault.c:163:8:    got unsigned char *[assigned] instr
linux/arch/x86_64/mm/fault.c:179:9: warning: incorrect type in argument 1 (different address spaces)
linux/arch/x86_64/mm/fault.c:179:9:    expected void [noderef] *<noident><asn:1>
linux/arch/x86_64/mm/fault.c:179:9:    got unsigned long *<noident>
Signed-off-by: default avatarAndi Kleen <ak@suse.de>
      dd2994f6
  23. 03 Jul, 2006 1 commit
  25. 30 Jun, 2006 2 commits
  27. 26 Jun, 2006 3 commits
    • Chuck Ebbert's avatar
      [PATCH] x86_64: enlarge window for stack growth · 03fdc2c2
      Chuck Ebbert authored 
      Allow stack growth so the 'enter' instruction works.  Also
fixes problem in compat_sys_kexec_load() which could allocate
more than 128 bytes using compat_alloc_user_space().
Signed-off-by: default avatarChuck Ebbert <76306.1226@compuserve.com>
Signed-off-by: default avatarAndi Kleen <ak@suse.de>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      03fdc2c2
    • Andi Kleen's avatar
      [PATCH] x86_64: Get rid of pud_offset_k / __pud_offset_k · d2ae5b5f
      Andi Kleen authored 
      pud_offset_k() equivalent to pud_offset() now.  Pointed out by Jan Beulich
Similar for __pud_offset_ok, which needs a small change in the callers.
Signed-off-by: default avatarAndi Kleen <ak@suse.de>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      d2ae5b5f
    • Anil S Keshavamurthy's avatar
      [PATCH] Notify page fault call chain for x86_64 · 1bd858a5
      Anil S Keshavamurthy authored 
      Currently in the do_page_fault() code path, we call notify_die(DIE_PAGE_FAULT,
...) to notify the page fault.  Since notify_die() is highly overloaded, this
page fault notification is currently being sent to all the components
registered with register_die_notification() which uses the same die_chain to
loop for all the registered components which is unnecessary.

In order to optimize the do_page_fault() code path, this critical page fault
notification is now moved to different call chain and the test results showed
great improvements.

And the kprobes which is interested in this notifications, now registers onto
this new call chain only when it need to, i.e Kprobes now registers for page
fault notification only when their are an active probes and unregisters from
this page fault notification when no probes are active.

I have incorporated all the feedback given by Ananth and Keith and everyone,
and thanks for all the review feedback.

This patch:

Overloading of page fault notification with the notify_die() has performance
issues(since the only interested components for page fault is kprobes and/or
kdb) and hence this patch introduces the new notifier call chain exclusively
for page fault notifications their by avoiding notifying unnecessary
components in the do_page_fault() code path.
Signed-off-by: default avatarAnil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      1bd858a5
  29. 31 Mar, 2006 1 commit
    • OGAWA Hirofumi's avatar
      [PATCH] Don't pass boot parameters to argv_init[] · 9b41046c
      OGAWA Hirofumi authored 
      The boot cmdline is parsed in parse_early_param() and
parse_args(,unknown_bootoption).

And __setup() is used in obsolete_checksetup().

	start_kernel()
		-> parse_args()
			-> unknown_bootoption()
				-> obsolete_checksetup()

If __setup()'s callback (->setup_func()) returns 1 in
obsolete_checksetup(), obsolete_checksetup() thinks a parameter was
handled.

If ->setup_func() returns 0, obsolete_checksetup() tries other
->setup_func().  If all ->setup_func() that matched a parameter returns 0,
a parameter is seted to argv_init[].

Then, when runing /sbin/init or init=app, argv_init[] is passed to the app.
If the app doesn't ignore those arguments, it will warning and exit.

This patch fixes a wrong usage of it, however fixes obvious one only.
Signed-off-by: default avatarOGAWA Hirofumi <hirofumi@mail.parknet.co.jp>
Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      9b41046c
  31. 25 Mar, 2006 2 commits
    • Arjan van de Ven's avatar
      [PATCH] x86_64: prefetch the mmap_sem in the fault path · a9ba9a3b
      Arjan van de Ven authored 
      In a micro-benchmark that stresses the pagefault path, the down_read_trylock
on the mmap_sem showed up quite high on the profile. Turns out this lock is
bouncing between cpus quite a bit and thus is cache-cold a lot. This patch
prefetches the lock (for write) as early as possible (and before some other
somewhat expensive operations). With this patch, the down_read_trylock
basically fell out of the top of profile.
Signed-off-by: default avatarArjan van de Ven <arjan@linux.intel.com>
Signed-off-by: default avatarAndi Kleen <ak@suse.de>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      a9ba9a3b
    • Jan Beulich's avatar
      [PATCH] x86_64: actively synchronize vmalloc area when registering certain callbacks · 8c914cb7
      Jan Beulich authored 
      While the modular aspect of the respective i386 patch doesn't apply to
x86-64 (as the top level page directory entry is shared between modules
and the base kernel), handlers registered with register_die_notifier()
are still under similar constraints for touching ioremap()ed or
vmalloc()ed memory. The likelihood of this problem becoming visible is
of course significantly lower, as the assigned virtual addresses would
have to cross a 2**39 byte boundary. This is because the callback gets
invoked
(a) in the page fault path before the top level page table propagation
gets carried out (hence a fault to propagate the top level page table
entry/entries mapping to module's code/data would nest infinitly) and
(b) in the NMI path, where nested faults must absolutely not happen,
since otherwise the IRET from the nested fault re-enables NMIs,
potentially resulting in nested NMI occurences.
Signed-off-by: default avatarJan Beulich <jbeulich@novell.com>
Signed-off-by: default avatarAndi Kleen <ak@suse.de>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      8c914cb7
  33. 05 Feb, 2006 1 commit
  35. 12 Jan, 2006 4 commits
  37. 15 Nov, 2005 1 commit
    • Andi Kleen's avatar
      [PATCH] x86_64: Remove CONFIG_CHECKING and add command line option for pagefault tracing · 9e43e1b7
      Andi Kleen authored 
      CONFIG_CHECKING covered some debugging code used in the early times
of the port. But it wasn't even SMP safe for quite some time
and the bugs it checked for seem to be gone.

This patch removes all the code to verify GS at kernel entry. There
haven't been any new bugs in this area for a long time.

Previously it also covered the sysctl for the page fault tracing.
That didn't make much sense because that code was unconditionally
compiled in. I made that a boot option now because it is typically
only useful at boot.
Signed-off-by: default avatarAndi Kleen <ak@suse.de>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      9e43e1b7
  39. 12 Sep, 2005 1 commit
  41. 07 Sep, 2005 1 commit
  43. 20 Aug, 2005 1 commit
  45. 04 Aug, 2005 1 commit
  47. 29 Jul, 2005 1 commit
  49. 23 Jun, 2005 1 commit
  51. 22 Jun, 2005 1 commit
    • Suresh Siddha's avatar
      [PATCH] x86_64: TASK_SIZE fixes for compatibility mode processes · 84929801
      Suresh Siddha authored 
      Appended patch will setup compatibility mode TASK_SIZE properly.  This will
fix atleast three known bugs that can be encountered while running
compatibility mode apps.

a) A malicious 32bit app can have an elf section at 0xffffe000.  During
   exec of this app, we will have a memory leak as insert_vm_struct() is
   not checking for return value in syscall32_setup_pages() and thus not
   freeing the vma allocated for the vsyscall page.  And instead of exec
   failing (as it has addresses > TASK_SIZE), we were allowing it to
   succeed previously.

b) With a 32bit app, hugetlb_get_unmapped_area/arch_get_unmapped_area
   may return addresses beyond 32bits, ultimately causing corruption
   because of wrap-around and resulting in SEGFAULT, instead of returning
   ENOMEM.

c) 32bit app doing this below mmap will now fail.

  mmap((void *)(0xFFFFE000UL), 0x10000UL, PROT_READ|PROT_WRITE,
	MAP_FIXED|MAP_PRIVATE|MAP_ANON, 0, 0);
Signed-off-by: default avatarZou Nan hai <nanhai.zou@intel.com>
Signed-off-by: default avatarSuresh Siddha <suresh.b.siddha@intel.com>
Cc: Andi Kleen <ak@muc.de>
Signed-off-by: default avatarAndrew Morton <akpm@osdl.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@osdl.org>
      84929801