The Intel(R) Xeon Phi(TM) Processor x200 Family (codename: Knights
Landing) has an erratum where a processor thread setting the Accessed
or Dirty bits may not do so atomically against its checks for the
Present bit.  This may cause a thread (which is about to page fault)
to set A and/or D, even though the Present bit had already been
atomically cleared.

These bits are truly "stray".  In the case of the Dirty bit, the
thread associated with the stray set was *not* allowed to write to
the page.  This means that we do not have to launder the bit(s); we
can simply ignore them.

If the PTE is used for storing a swap index or a NUMA migration index,
the A bit could be misinterpreted as part of the swap type.  The stray
bits being set cause a software-cleared PTE to be interpreted as a
swap entry.  In some cases (like when the swap index ends up being
for a non-existent swapfile), the kernel detects the stray value
and WARN()s about it, but there is no guarantee that the kernel can
always detect it.

When we have 64-bit PTEs (64-bit mode or 32-bit PAE), we were able
to move the swap PTE format around to avoid these troublesome bits.
But, 32-bit non-PAE is tight on bits.  So, disallow it from running
on this hardware.  I can't imagine anyone wanting to run 32-bit
non-highmem kernels on this hardware, but disallowing them from
running entirely is surely the safe thing to do.
Signed-off-by: NDave Hansen <dave.hansen@linux.intel.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Dave Hansen <dave@sr71.net>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Luis R. Rodriguez <mcgrof@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Toshi Kani <toshi.kani@hp.com>
Cc: dave.hansen@intel.com
Cc: linux-mm@kvack.org
Cc: mhocko@suse.com
Link: http://lkml.kernel.org/r/20160708001914.D0B50110@viggo.jf.intel.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

Recent PAT patchset has caused issue on 32-bit PAE machines:

  page:eea45000 count:0 mapcount:-128 mapping:  (null) index:0x0 flags: 0x40000000()
  page dumped because: VM_BUG_ON_PAGE(page_mapcount(page) < 0)
  ------------[ cut here ]------------
  kernel BUG at /home/build/linux-boris/mm/huge_memory.c:1485!
  invalid opcode: 0000 [#1] SMP
  [...]
  Call Trace:
   unmap_single_vma
   ? __wake_up
   unmap_vmas
   unmap_region
   do_munmap
   vm_munmap
   SyS_munmap
   do_fast_syscall_32
   ? __do_page_fault
   sysenter_past_esp
  Code: ...
  EIP: [<c11bde80>] zap_huge_pmd+0x240/0x260 SS:ESP 0068:f6459d98

The problem is in pmd_pfn_mask() and pmd_flags_mask(). These
helpers use PMD_PAGE_MASK to calculate resulting mask.
PMD_PAGE_MASK is 'unsigned long', not 'unsigned long long' as
phys_addr_t is on 32-bit PAE (ARCH_PHYS_ADDR_T_64BIT). As a
result, the upper bits of resulting mask get truncated.

pud_pfn_mask() and pud_flags_mask() aren't problematic since we
don't have PUD page table level on 32-bit systems, but it's
reasonable to keep them consistent with PMD counterpart.

Introduce PHYSICAL_PMD_PAGE_MASK and PHYSICAL_PUD_PAGE_MASK in
addition to existing PHYSICAL_PAGE_MASK and reworks helpers to
use them.
Reported-and-Tested-by: NBoris Ostrovsky <boris.ostrovsky@oracle.com>
Signed-off-by: NKirill A. Shutemov <kirill.shutemov@linux.intel.com>
[ Fix -Woverflow warnings from the realmode code. ]
Signed-off-by: NBorislav Petkov <bp@suse.de>
Reviewed-by: NToshi Kani <toshi.kani@hpe.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jürgen Gross <jgross@suse.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: elliott@hpe.com
Cc: konrad.wilk@oracle.com
Cc: linux-mm <linux-mm@kvack.org>
Fixes: f70abb0f ("x86/asm: Fix pud/pmd interfaces to handle large PAT bit")
Link: http://lkml.kernel.org/r/1448878233-11390-2-git-send-email-bp@alien8.deSigned-off-by: NIngo Molnar <mingo@kernel.org>
Signed-off-by: NIngo Molnar <mingo@kernel.org>

The kernel does not support the MCA bus anymroe, so mark sys_desc_table
as obsolete: remove any reference from the code together with the remaining
of MCA logic.

bloat-o-meter output:

  add/remove: 0/0 grow/shrink: 0/2 up/down: 0/-55 (-55)
  function                                     old     new   delta
  i386_start_kernel                            128     119      -9
  setup_arch                                  1421    1375     -46
Signed-off-by: NPaolo Pisati <p.pisati@gmail.com>
Cc: Josh Triplett <josh@joshtriplett.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1437409430-8491-1-git-send-email-p.pisati@gmail.comSigned-off-by: NIngo Molnar <mingo@kernel.org>

Try to treat memcmp() in same way as memcpy() and memset(). Provide a
declaration in boot/string.h and by default user gets a memcmp() which
maps to builtin function.

Move optimized definition of memcmp() in boot/string.c. Now a user can
do #undef memcmp and link against string.c to use optimzied memcmp().

It also simplifies boot/compressed/string.c where we had to redefine
memcmp(). That extra definition is gone now.
Signed-off-by: NVivek Goyal <vgoyal@redhat.com>
Link: http://lkml.kernel.org/r/1395170800-11059-5-git-send-email-vgoyal@redhat.comSigned-off-by: NH. Peter Anvin <hpa@linux.intel.com>

Create a separate arch/x86/boot/string.h file to provide declaration of
some of the common string functions.

By default memcpy, memset and memcmp functions will default to gcc
builtin functions. If code wants to use an optimized version of any
of these functions, they need to #undef the respective macro and link
against a local file providing definition of undefed function.

For example, arch/x86/boot/* code links against copy.S to get memcpy()
and memcmp() definitions. arch/86/boot/compressed/* links against
compressed/string.c.

There are quite a few places in arch/x86/ where these functions are
used. Idea is to try to consilidate  their declaration and possibly
definitions so that it can be reused.

I am planning to reuse boot/string.h in arch/x86/purgatory/ and use
gcc builtin functions for memcpy, memset and memcmp.
Signed-off-by: NVivek Goyal <vgoyal@redhat.com>
Link: http://lkml.kernel.org/r/1395170800-11059-3-git-send-email-vgoyal@redhat.comSigned-off-by: NH. Peter Anvin <hpa@linux.intel.com>

Refactor the CPU flags handling out of the cpucheck routines so that
they can be reused by the future ASLR routines (in order to detect CPU
features like RDRAND and RDTSC).

This reworks has_eflag() and has_fpu() to be used on both 32-bit and
64-bit, and refactors the calls to cpuid to make them PIC-safe on 32-bit.
Signed-off-by: NKees Cook <keescook@chromium.org>
Link: http://lkml.kernel.org/r/1381450698-28710-2-git-send-email-keescook@chromium.orgSigned-off-by: NH. Peter Anvin <hpa@linux.intel.com>

Below is a patch that fixes sparse error
"arch/x86/boot/string.c:119:8: warning: symbol 'strlen' was not
declared." by declaring it in arch/x86/boot/boot.h.
Signed-off-by: NFred Chen <fchen@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1376417580-11554-1-git-send-email-fchen@linux.vnet.ibm.comSigned-off-by: NH. Peter Anvin <hpa@linux.intel.com>

boot/compressed/misc.c is used for bzImage in 64bit and 32bit, and
cmd_line_ptr could point to buffer that is above 4g, cmd_line_ptr
should be 64bit otherwise high 32bit will be capped out.

So need to change data type to unsigned long, that will be 64bit get
correct address of command line buffer.

And it is still ok with 32bit bzImage, because unsigned long on 32bit kernel
is still 32bit.
Signed-off-by: NYinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/1359058816-7615-19-git-send-email-yinghai@kernel.orgSigned-off-by: NH. Peter Anvin <hpa@linux.intel.com>

cmdline.c::__cmdline_find_option... are shared between 16-bit setup code
and 32/64 bit decompressor code.

for 32/64 only path via kexec, we should not check if ptr is less 1M.
as those cmdline could be put above 1M, or even 4G.

Move out accessible checking out of __cmdline_find_option()
So decompressor in misc.c can parse cmdline correctly.
Signed-off-by: NYinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/1359058816-7615-18-git-send-email-yinghai@kernel.orgSigned-off-by: NH. Peter Anvin <hpa@linux.intel.com>

"u32 port" in inl() should be "u16 port".

[ hpa: it's a bug, but it doesn't produce incorrect code, so no need
  to put this into urgent or stable. ]
Signed-off-by: NHe Chunhui <hchunhui@mail.ustc.edu.cn>
Link: http://lkml.kernel.org/r/32892299.2931391328028508117.JavaMail.coremail@mailwebSigned-off-by: NH. Peter Anvin <hpa@linux.intel.com>

It is a subset of <ctype.h> functionality, so name it ctype.h.  Also,
reorganize header files so #include statements are clustered near the
top as they should be.
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>
LKML-Reference: <4C5752F2.8030206@kernel.org>

Separate early_serial_console from tty.c

This allows for reuse of
early_serial_console.c/string.c/printf.c/cmdline.c in boot/compressed/.

-v2: according to hpa, don't include string.c etc
-v3: compressed/misc.c must have early_serial_base as static, so move it back to tty.c
     for setup code
Signed-off-by: NYinghai Lu <yinghai@kernel.org>
LKML-Reference: <4C568D2B.205@kernel.org>
Signed-off-by: NH. Peter Anvin <hpa@linux.intel.com>

This patch adds serial I/O support to the real-mode setup (very early
boot) printf(). It's useful for debugging boot code when running Linux
under KVM, for example. The actual code was lifted from early printk.

Cc: Cyrill Gorcunov <gorcunov@gmail.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Signed-off-by: NPekka Enberg <penberg@cs.helsinki.fi>
LKML-Reference: <1278835617-11368-1-git-send-email-penberg@cs.helsinki.fi>
Signed-off-by: NH. Peter Anvin <hpa@linux.intel.com>

Impact: new interfaces (not yet used)

For all the platforms out there, there is an infinite number of buggy
BIOSes.  This adds infrastructure to treat BIOS interrupts more like
toxic waste and "glove box" them -- we switch out the register set,
perform the BIOS interrupt, and then restore the previous state.

LKML-Reference: <49DE7F79.4030106@zytor.com>
Signed-off-by: NH. Peter Anvin <hpa@linux.intel.com>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Rafael J. Wysocki <rjw@sisk.pl>

Impact: remove unused/broken code

The Voyager subarch last built successfully on the v2.6.26 kernel
and has been stale since then and does not build on the v2.6.27,
v2.6.28 and v2.6.29-rc5 kernels.

No actual users beyond the maintainer reported this breakage.
Patches were sent and most of the fixes were accepted but the
discussion around how to do a few remaining issues cleanly
fizzled out with no resolution and the code remained broken.

In the v2.6.30 x86 tree development cycle 32-bit subarch support
has been reworked and removed - and the Voyager code, beyond the
build problems already known, needs serious and significant
changes and probably a rewrite to support it.

CONFIG_X86_VOYAGER has been marked BROKEN then. The maintainer has
been notified but no patches have been sent so far to fix it.

While all other subarchs have been converted to the new scheme,
voyager is still broken. We'd prefer to receive patches which
clean up the current situation in a constructive way, but even in
case of removal there is no obstacle to add that support back
after the issues have been sorted out in a mutually acceptable
fashion.

So remove this inactive code for now.
Signed-off-by: NIngo Molnar <mingo@elte.hu>

This recent patch

commit c3965bd1
Author: Paul Jackson <pj@sgi.com>
Date:   Wed May 14 08:15:34 2008 -0700

    x86 boot: proper use of ARRAY_SIZE instead of repeated E820MAX constant

caused these new warnings during a normal build:

In file included from linux-2.6/arch/x86/boot/memory.c:17:
linux-2.6/include/linux/log2.h: In function '__ilog2_u32':
linux-2.6/include/linux/log2.h:34: warning: implicit declaration of function 'fls'
linux-2.6/include/linux/log2.h: In function '__ilog2_u64':
linux-2.6/include/linux/log2.h:42: warning: implicit declaration of function 'fls64'
linux-2.6/include/linux/log2.h: In function '__roundup_pow_of_two ':
linux-2.6/include/linux/log2.h:63: warning: implicit declaration of function 'fls_long'

I tried to fix them in log2.h, but it's difficult because the real mode
environment is completely different from a normal kernel environment. Instead
define an own ARRAY_SIZE macro in boot.h, similar to the other private
macros there.
Signed-off-by: NAndi Kleen <ak@linux.intel.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Clean up the code for crashes during SpeedStep probing on older
machines.
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

yesterday I tried to reactivate my old 486 box and wanted to install a
current Linux with latest kernel on it. But it turned out that the
latest kernel does not boot because the machine crashes early in the
setup code.

After some debugging it turned out that the problem is the query_ist()
function. If this interrupt with that function is called the machine
simply locks up. It looks like a BIOS bug. Looking for a workaround for
this problem I wrote the attached patch. It checks for the CPUID
instruction and if it is not implemented it does not call the speedstep
BIOS function. As far as I know speedstep should be available since some
Pentium earliest.

Alan Cox observed that it's available since the Pentium II, so cpuid
levels 4 and 5 can be excluded altogether.

H. Peter Anvin cleaned up the code some more:

> Right in concept, but I dislike the implementation (duplication of the
> CPU detect code we already have).  Could you try this patch and see if
> it works for you?

which, with a small modification to fix a build error with it the
resulting kernel boots on my machine.
Signed-off-by: NJoerg Roedel <joro@8bytes.org>
Signed-off-by: N"H. Peter Anvin" <hpa@zytor.com>
Cc: <stable@kernel.org>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Remove old comments that include the old arch/i386 directory.
Signed-off-by: NWANG Cong <xiyou.wangcong@gmail.com>
Acked-by: NH. Peter Anvin <hpa@zytor.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Move wakeup code to .c, so that video mode setting code can be shared
between boot and wakeup. Remove nasty assembly code in 64-bit case by
re-using trampoline code. Stack setup was fixed to clear high 16bits
of %esp, maybe that fixes some machines.

.c code sharing and morse code was done H. Peter Anvin, Sam Ravnborg
reviewed kbuild related stuff, and it seems okay to him. Rafael did
some cleanups.

[rjw:
* Made the patch stop breaking compilation on x86-32
* Added arch/x86/kernel/acpi/sleep.h
* Got rid of compiler warnings in arch/x86/kernel/acpi/sleep.c
* Fixed 32-bit compilation on x86-64 systems
* Added include/asm-x86/trampoline.h and fixed the non-SMP
  compilation on 64-bit x86
* Removed arch/x86/kernel/acpi/sleep_32.c which was not used
* Fixed some breakage caused by the integration of smpboot.c done
  under us in the meantime]
Signed-off-by: NPavel Machek <pavel@suse.cz>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>
Reviewed-by: NSam Ravnborg <sam@ravnborg.org>
Signed-off-by: NRafael J. Wysocki <rjw@sisk.pl>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

Add prototype for cmdline_find_option_bool() missing from:

    x86 setup: early cmdline parser handle boolean options

Also, fix up a minor formatting error in that patch.
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Fix the operand constraints for the segment accessor functions,
{rd,wr}{fs,gs}*.  In particular, the 8-bit functions used "r"
constraints instead of "q" constraints.
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

We use signed values for limit checking since the values can go
negative under certain circumstances.  However, sizeof() is unsigned
and forces the comparison to be unsigned, so move the comparison into
the heap_free() macros so we can ensure it is a signed comparison.
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

Apparently some specific versions of LILO enter the kernel with a
stack pointer that doesn't match the rest of the segments.  Make our
best attempt at untangling the resulting mess.
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

Make <asm/setup.h> usable by the boot code.

Clean up vestiges of the old command-line protocol from setup.h and
head_32.S (it is still supported from the boot loader point of
view, since it is converted to the new command-line protocol by the
boot code.)
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>

Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Signed-off-by: NIngo Molnar <mingo@elte.hu>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Signed-off-by: NIngo Molnar <mingo@elte.hu>

asm() statements need to be volatile when:

a. They have side effects (other than value returned).
b. When the value returned can vary over time.
c. When they have ordering constraints that cannot be expressed to gcc.

In particular, the keyboard and timer reads were violating constraint (b),
which resulted in the keyboard/timeout poll getting
loop-invariant-removed when compiling with gcc 4.2.0.

Thanks to an anonymous bug reporter for pointing this out.
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

Fix incorrect assembly constraints.  In particular, fix memory
constraints used inside push..pop, which can cause invalid operation
since gcc may generate %esp-relative references.

Additionally:

outl() should have "dN" not "dn".

query_mca() shouldn't listen 16/32-bit registers in an 8-bit only
context.

has_eflag(): the "mask" is only used well after both the stack pointer
and the output registers have been touched; this requires the output
registers to be earlyclobbers (=&) and the input to exclude memory (so
"ri", not "g").

Thanks to Etienne Lorrain and Chuck Ebbert for prompting this review.

Cc: Etienne Lorrain <etienne_lorrain@yahoo.fr>
Cc: Chuck Ebbert <cebbert@redhat.com>
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>

Top header file for the new x86 setup code.
Signed-off-by: NH. Peter Anvin <hpa@zytor.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>