The translation performed by virt_to_page() is only valid for linear
addresses, and kernel symbols are no longer in the linear mapping.
So perform the __pa() translation explicitly, which does the right
thing in either case, and only then translate to a struct page offset.
Signed-off-by: NArd Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

This removes the relocate_initrd() implementation and invocation, which are
no longer needed now that the placement of the initrd is guaranteed to be
covered by the linear mapping.
Signed-off-by: NArd Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

Instead of going out of our way to relocate the initrd if it turns out
to occupy memory that is not covered by the linear mapping, just add the
initrd to the linear mapping. This puts the burden on the bootloader to
pass initrd= and mem= options that are mutually consistent.

Note that, since the placement of the linear region in the PA space is
also dependent on the placement of the kernel Image, which may reside
anywhere in memory, we may still end up with a situation where the initrd
and the kernel Image are simply too far apart to be covered by the linear
region.

Since we now leave it up to the bootloader to pass the initrd in memory
that is guaranteed to be accessible by the kernel, add a mention of this to
the arm64 boot protocol specification as well.
Signed-off-by: NArd Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

This reverts commit 36e5cd6b, since the
section alignment is now guaranteed by construction when choosing the
value of memstart_addr.
Signed-off-by: NArd Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

This redefines ARM64_MEMSTART_ALIGN in terms of the minimal alignment
required by sparsemem vmemmap. This comes down to using 1 GB for all
translation granules if CONFIG_SPARSEMEM_VMEMMAP is enabled.
Signed-off-by: NArd Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

After choosing memstart_addr to be the highest multiple of
ARM64_MEMSTART_ALIGN less than or equal to the first usable physical memory
address, we clip the memblocks to the maximum size of the linear region.
Since the kernel may be high up in memory, we take care not to clip the
kernel itself, which means we have to clip some memory from the bottom if
this occurs, to ensure that the distance between the first and the last
usable physical memory address can be covered by the linear region.

However, we fail to update memstart_addr if this clipping from the bottom
occurs, which means that we may still end up with virtual addresses that
wrap into the userland range. So increment memstart_addr as appropriate to
prevent this from happening.
Signed-off-by: NArd Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

Currently, we check two pointers: cpu_ops and cpu_suspend on every idle
state entry. These pointers check can be avoided:

If cpu_ops has not been registered, arm_cpuidle_init() will return
-EOPNOTSUPP, so arm_cpuidle_suspend() will never have chance to
run. In other word, the cpu_ops check can be avoid.

Similarly, the cpu_suspend check could be avoided in this hot path by
moving it into arm_cpuidle_init().

I measured the 4096 * time from arm_cpuidle_suspend entry point to the
cpu_psci_cpu_suspend entry point. HW platform is Marvell BG4CT STB
board.

1. only one shell, no other process, hot-unplug secondary cpus, execute
the following cmd

while true
do
	sleep 0.2
done

before the patch: 1581220ns

after the patch: 1579630ns

reduced by 0.1%

2. only one shell, no other process, hot-unplug secondary cpus, execute
the following cmd

while true
do
	md5sum /tmp/testfile
	sleep 0.2
done

NOTE: the testfile size should be larger than L1+L2 cache size

before the patch: 1961960ns
after the patch: 1912500ns

reduced by 2.5%

So the more complex the system load, the bigger the improvement.
Signed-off-by: NJisheng Zhang <jszhang@marvell.com>
Acked-by: NLorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

There are some new cpu features which can be identified by id_aa64mmfr2,
this patch appends all fields of it.
Signed-off-by: NKefeng Wang <wangkefeng.wang@huawei.com>
Signed-off-by: NWill Deacon <will.deacon@arm.com>

Update the comment to reflect the changes of commit 0de79858 (parisc: Use
generic extable search and sort routines).
Signed-off-by: NHelge Deller <deller@gmx.de>

Handling exceptions from modules never worked on parisc.
It was just masked by the fact that exceptions from modules
don't happen during normal use.

When a module triggers an exception in get_user() we need to load the
main kernel dp value before accessing the exception_data structure, and
afterwards restore the original dp value of the module on exit.
Noticed-by: NMikulas Patocka <mpatocka@redhat.com>
Signed-off-by: NHelge Deller <deller@gmx.de>
Cc: stable@vger.kernel.org

The kernel module testcase (lib/test_user_copy.c) exhibited a kernel
crash on parisc if the parameters for copy_from_user were reversed
("illegal reversed copy_to_user" testcase).

Fix this potential crash by checking the fault handler if the faulting
address is in the exception table.
Signed-off-by: NHelge Deller <deller@gmx.de>
Cc: stable@vger.kernel.org
Cc: Kees Cook <keescook@chromium.org>

We want to avoid the kernel module loader to create function pointers
for the kernel fixup routines of get_user() and put_user(). Changing
the external reference from function type to int type fixes this.

This unbreaks exception handling for get_user() and put_user() when
called from a kernel module.
Signed-off-by: NHelge Deller <deller@gmx.de>
Cc: stable@vger.kernel.org

Commit 0de79858 (parisc: Use generic extable search and sort routines)
changed the exception tables to use 32bit relative offsets.

This patch now adds support to the kernel module loader to handle such
R_PARISC_PCREL32 relocations for 32- and 64-bit modules.
Signed-off-by: NHelge Deller <deller@gmx.de>

It was reported that a kernel with CONFIG_ARM_PATCH_IDIV=y stopped
booting when compiled with the upcoming gcc 6.  Turns out that turning
a function address into a writable array is undefined and gcc 6 decided
it was OK to omit the store to the first word of the function while
still preserving the store to the second word.

Even though gcc 6 is now fixed to behave more coherently, it is a
mystery that gcc 4 and gcc 5 actually produce wanted code in the kernel.
And in fact the reduced test case to illustrate the issue does indeed
break with gcc < 6 as well.

In any case, let's guard the kernel against undefined compiler behavior
by hiding the nature of the array location as suggested by gcc
developers.

Reference: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=70128Signed-off-by: NNicolas Pitre <nico@linaro.org>
Reported-by: NMarcin Juszkiewicz <mjuszkiewicz@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: stable@vger.kernel.org # v4.5
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Wire up the preadv2 and pwritev2 syscalls for ARM.
Signed-off-by: NRussell King <rmk+kernel@arm.linux.org.uk>

Some processors use the Interrupt Response Time Limit (IRTL) MSR value
to describe the maximum IRQ response time latency for deep
package C-states.  (Though others have the register, but do not use it)
Lets print it out to give insight into the cases where it is used.

IRTL begain in SNB, with PC3/PC6/PC7, and HSW added PC8/PC9/PC10.
Signed-off-by: NLen Brown <len.brown@intel.com>
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>

Let's see if anybody even notices.  I doubt anybody uses this, and it
does expose addresses that should be randomized, so let's just remove
the code.  It's old and traditional, and it used to be cute, but we
should have removed this long ago.

If it turns out anybody notices and this breaks something, we'll have to
revert this, and maybe we'll end up using other approaches instead
(using %pK or similar).  But removing unnecessary code is always the
preferred option.
Noted-by: NEmrah Demir <ed@abdsec.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

When a vCPU runs on a nohz_full core, the hrtimer used by
the lapic emulation code can be migrated to another core.
When this happens, it's possible to observe milisecond
latency when delivering timer IRQs to KVM guests.

The huge latency is mainly due to the fact that
apic_timer_fn() expects to run during a kvm exit. It
sets KVM_REQ_PENDING_TIMER and let it be handled on kvm
entry. However, if the timer fires on a different core,
we have to wait until the next kvm exit for the guest
to see KVM_REQ_PENDING_TIMER set.

This problem became visible after commit 9642d18e. This
commit changed the timer migration code to always attempt
to migrate timers away from nohz_full cores. While it's
discussable if this is correct/desirable (I don't think
it is), it's clear that the lapic emulation code has
a requirement on firing the hrtimer in the same core
where it was started. This is achieved by making the
hrtimer pinned.

Lastly, note that KVM has code to migrate timers when a
vCPU is scheduled to run in different core. However, this
forced migration may fail. When this happens, we can have
the same problem. If we want 100% correctness, we'll have
to modify apic_timer_fn() to cause a kvm exit when it runs
on a different core than the vCPU. Not sure if this is
possible.

Here's a reproducer for the issue being fixed:

 1. Set all cores but core0 to be nohz_full cores
 2. Start a guest with a single vCPU
 3. Trace apic_timer_fn() and kvm_inject_apic_timer_irqs()

You'll see that apic_timer_fn() will run in core0 while
kvm_inject_apic_timer_irqs() runs in a different core. If
you get both on core0, try running a program that takes 100%
of the CPU and pin it to core0 to force the vCPU out.
Signed-off-by: NLuiz Capitulino <lcapitulino@redhat.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

commit 1e133ab2 ("s390/mm: split arch/s390/mm/pgtable.c") dropped
some changes from commit a3a92c31 ("KVM: s390: fix mismatch
between user and in-kernel guest limit") - this breaks KVM for some
memory sizes (kvm-s390: failed to commit memory region) like
exactly 2GB.

Cc: Dominik Dingel <dingel@linux.vnet.ibm.com>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Acked-by: NHeiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: NChristian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>

Mostly direct substitution with occasional adjustment or removing
outdated comments.
Signed-off-by: NKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: NMichal Hocko <mhocko@suse.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} macros were introduced *long* time
ago with promise that one day it will be possible to implement page
cache with bigger chunks than PAGE_SIZE.

This promise never materialized.  And unlikely will.

We have many places where PAGE_CACHE_SIZE assumed to be equal to
PAGE_SIZE.  And it's constant source of confusion on whether
PAGE_CACHE_* or PAGE_* constant should be used in a particular case,
especially on the border between fs and mm.

Global switching to PAGE_CACHE_SIZE != PAGE_SIZE would cause to much
breakage to be doable.

Let's stop pretending that pages in page cache are special.  They are
not.

The changes are pretty straight-forward:

 - <foo> << (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;

 - <foo> >> (PAGE_CACHE_SHIFT - PAGE_SHIFT) -> <foo>;

 - PAGE_CACHE_{SIZE,SHIFT,MASK,ALIGN} -> PAGE_{SIZE,SHIFT,MASK,ALIGN};

 - page_cache_get() -> get_page();

 - page_cache_release() -> put_page();

This patch contains automated changes generated with coccinelle using
script below.  For some reason, coccinelle doesn't patch header files.
I've called spatch for them manually.

The only adjustment after coccinelle is revert of changes to
PAGE_CAHCE_ALIGN definition: we are going to drop it later.

There are few places in the code where coccinelle didn't reach.  I'll
fix them manually in a separate patch.  Comments and documentation also
will be addressed with the separate patch.

virtual patch

@@
expression E;
@@
- E << (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E

@@
expression E;
@@
- E >> (PAGE_CACHE_SHIFT - PAGE_SHIFT)
+ E

@@
@@
- PAGE_CACHE_SHIFT
+ PAGE_SHIFT

@@
@@
- PAGE_CACHE_SIZE
+ PAGE_SIZE

@@
@@
- PAGE_CACHE_MASK
+ PAGE_MASK

@@
expression E;
@@
- PAGE_CACHE_ALIGN(E)
+ PAGE_ALIGN(E)

@@
expression E;
@@
- page_cache_get(E)
+ get_page(E)

@@
expression E;
@@
- page_cache_release(E)
+ put_page(E)
Signed-off-by: NKirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: NMichal Hocko <mhocko@suse.com>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Make sure it's the microMIPS rather than MIPS16 ISA before emulating
microMIPS RDHWR.  Mostly needed as an optimisation for configurations
where `cpu_has_mmips' is hardcoded to 0 and also a good measure in case
we add further microMIPS instructions to emulate in the future, as the
corresponding MIPS16 encoding is ADDIUSP, not supposed to trap.
Signed-off-by: NMaciej W. Rozycki <macro@imgtec.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/12282/Signed-off-by: NRalf Baechle <ralf@linux-mips.org>

The SUN GISB arbiter was added with the wrong compatible string, leading to
using the wrong register layout, use the correct compatible string for this
chip: brcm,bcm7435-gisb-arb.

Fixes: 8394968be4c7 ("MIPS: BMIPS: Add BCM7435 dtsi")
Signed-off-by: NFlorian Fainelli <f.fainelli@gmail.com>
Cc: blogic@openwrt.org
Cc: cernekee@gmail.com
Cc: jogo@openwrt.org
Cc: jaedon.shin@gmail.com
Cc: pgynther@google.com
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/12285/Signed-off-by: NRalf Baechle <ralf@linux-mips.org>

When an unsupported reloc is encountered in a module, we currently
blindly branch to whatever would be at its entry in the reloc handler
function pointer arrays. This may be NULL, or if the unsupported reloc
has a type greater than that of the supported reloc with the highest
type then we'll dereference some value after the function pointer array
& branch to that. The result is at best a kernel oops.

Fix this by checking that the reloc type has an entry in the function
pointer array (ie. is less than the number of items in the array) and
that the handler is non-NULL, returning an error code to fail the module
load if no handler is found.
Signed-off-by: NPaul Burton <paul.burton@imgtec.com>
Cc: James Hogan <james.hogan@imgtec.com>
Cc: Steven J. Hill <Steven.Hill@imgtec.com>
Cc: Andrey Ryabinin <ryabinin.a.a@gmail.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/12432/Signed-off-by: NRalf Baechle <ralf@linux-mips.org>

Current ath79 clock.c code does not read reference clock and
pll setup from devicetree. The ar724x_clocks_init() function
recreates the clocks from scratch so devicetree clock
information is dropped. After adding the code which picked up
reference clock from devicetree I have found
that kernel does not boot anymore. The SPI and UART drivers
can't get clk; here are the bootlog error messages:

    of_serial: probe of 18020000.uart failed with error -22
    ath79-spi: probe of 1f000000.spi failed with error -22

The problem is that clock code assumes that reference clock
name is "ref" but current dts-file uses another name: "oscillator".

This patch fixes the problem by changing external oscillator
dt node name to "ref".

Please note that there is an alternative solution for the problem:

    > --- a/arch/mips/boot/dts/qca/ar9132_tl_wr1043nd_v1.dts
    > +++ b/arch/mips/boot/dts/qca/ar9132_tl_wr1043nd_v1.dts
    > @@ -16,6 +16,7 @@
    >
    >         extosc: oscillator {
    >                 compatible = "fixed-clock";
    > +               clock-output-names = "ref";
    >                 #clock-cells = <0>;
    >                 clock-frequency = <40000000>;
    >         };
Signed-off-by: NAntony Pavlov <antonynpavlov@gmail.com>
Cc: Alban Bedel <albeu@free.fr>
Cc: Michael Turquette <mturquette@baylibre.com>
Cc: Rob Herring <robh+dt@kernel.org>
Cc: linux-clk@vger.kernel.org
Cc: linux-mips@linux-mips.org
Cc: devicetree@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/12874/Signed-off-by: NRalf Baechle <ralf@linux-mips.org>

The reference clock on ar913x is at 40MHz and not 5MHz. The current
implementation use the wrong reference rate because it doesn't take
the PLL divider in account. But if we fix the code to use the divider
it becomes identical with the implementation for ar724x, so just drop
the broken ar913x implementation.
Signed-off-by: NAlban Bedel <albeu@free.fr>
Tested-by: NAntony Pavlov <antonynpavlov@gmail.com>
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/12871/Signed-off-by: NRalf Baechle <ralf@linux-mips.org>

According to the AR7242 datasheet section 2.8, AR724X CPUs use a 40MHz
input clock as the REF_CLK instead of 5MHz.

The correct CPU PLL calculation procedure is as follows:
CPU_PLL = (FB * REF_CLK) / REF_DIV / 2.

This patch is compatible with the current calculation procedure with
default FB and REF_DIV values.

Tested on AR7240, AR7241 and AR7242.
Signed-off-by: NWeijie Gao <hackpascal@gmail.com>
Signed-off-by: Alban Bedel <albeu@free.fr> (Fixed the commit log message)
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/12870/Signed-off-by: NRalf Baechle <ralf@linux-mips.org>

Signed-off-by: NAntony Pavlov <antonynpavlov@gmail.com>
Acked-by: NRob Herring <robh@kernel.org>
Cc: Alban Bedel <albeu@free.fr>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: linux-mips@linux-mips.org
Cc: devicetree@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/12869/Signed-off-by: NRalf Baechle <ralf@linux-mips.org>

Follow our own rules set in <asm/siginfo.h> for SIGTRAP signals issued
from `do_watch' and `do_trap_or_bp' by setting the signal code to
TRAP_HWBKPT and TRAP_BRKPT respectively, for Watch exceptions and for
those Breakpoint exceptions whose originating BREAK instruction's code
does not have a special meaning.  Keep Trap exceptions unaffected as
these are not debug events.

No existing user software is expected to examine signal codes for these
signals as SI_KERNEL has been always used here.  This change makes the
MIPS port more like other Linux ports, which reduces the complexity and
provides for performance improvement in GDB.
Signed-off-by: NMaciej W. Rozycki <macro@imgtec.com>
Cc: Pedro Alves <palves@redhat.com>
Cc: Luis Machado <lgustavo@codesourcery.com>
Cc: linux-mips@linux-mips.org
Cc: gdb@sourceware.org
Patchwork: https://patchwork.linux-mips.org/patch/12758/Signed-off-by: NRalf Baechle <ralf@linux-mips.org>

Signed-off-by: NRalf Baechle <ralf@linux-mips.org>

Update the Ci20's defconfig to enable the JZ4780's NAND driver and
therefore access to the UBIFS rootfs.
Signed-off-by: NHarvey Hunt <harvey.hunt@imgtec.com>
Cc: Paul Burton <paul.burton@imgtec.com>
Cc: linux-kernel@vger.kernel.org
Cc: linux-mips@linux-mips.org
Patchwork: https://patchwork.linux-mips.org/patch/12699/Signed-off-by: NRalf Baechle <ralf@linux-mips.org>

Signed-off-by: NAdam Buchbinder <adam.buchbinder@gmail.com>
Cc: linux-mips@linux-mips.org
Cc: trivial@kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/12617/Signed-off-by: NRalf Baechle <ralf@linux-mips.org>

After writing the appropriate mask to the cop0 PageMask register, read
the register back & check it matches what we want. If it doesn't then
the MMU does not support the page size the kernel is configured for and
we're better off bailing than continuing to do odd things with TLB
exceptions.
Signed-off-by: NPaul Burton <paul.burton@imgtec.com>
Cc: Steven J. Hill <Steven.Hill@imgtec.com>
Cc: Joshua Kinard <kumba@gentoo.org>
Cc: Rafał Miłecki <zajec5@gmail.com>
Cc: James Hogan <james.hogan@imgtec.com>
Cc: Markos Chandras <markos.chandras@imgtec.com>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/10691/Signed-off-by: NRalf Baechle <ralf@linux-mips.org>

The copied source files must be added to the extra-y list to have them
removed on clean.
Signed-off-by: NAlban Bedel <albeu@free.fr>
Cc: Andrew Bresticker <abrestic@chromium.org>
Cc: Alex Smith <alex.smith@imgtec.com>
Cc: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/12233/Signed-off-by: NRalf Baechle <ralf@linux-mips.org>

Some older GCC version (at least 4.6) emits calls to __bswapsi2() when
building the XZ decompressor. The link of the compressed image then
fails with the following error:

arch/mips/boot/compressed/decompress.o: In function '__fswab32':
include/uapi/linux/swab.h:60: undefined reference to '__bswapsi2'

Add bswapsi.o to the link to fix the build with these versions.
Signed-off-by: NAlban Bedel <albeu@free.fr>
Cc: Andrew Bresticker <abrestic@chromium.org>
Cc: Alex Smith <alex.smith@imgtec.com>
Cc: Wu Zhangjin <wuzhangjin@gmail.com>
Cc: linux-mips@linux-mips.org
Cc: linux-kernel@vger.kernel.org
Patchwork: https://patchwork.linux-mips.org/patch/12232/Signed-off-by: NRalf Baechle <ralf@linux-mips.org>

Signed-off-by: NRalf Baechle <ralf@linux-mips.org>

Masahiro Yamada reports that we can fail to set the FW bit in the
auxiliary control register, which enables broadcasting the cache
maintanence operations.  This occurs because we only check that the
SMP/nAMP bit is set, rather than checking whether all the bits we
want to be set are set.

Rearrange the code to ensure that all desired bits are set, and only
update the register if we discover some required bits are not set.
Tested-by: NMasahiro Yamada <yamada.masahiro@socionext.com>

The recently introduced batched invalidations mechanism uses its own
mechanism for shootdown.  However, it does wrong accounting of
interrupts (e.g., inc_irq_stat is called for local invalidations),
trace-points (e.g., TLB_REMOTE_SHOOTDOWN for local invalidations) and
may break some platforms as it bypasses the invalidation mechanisms of
Xen and SGI UV.

This patch reuses the existing TLB flushing mechnaisms instead.  We use
NULL as mm to indicate a global invalidation is required.

Fixes 72b252ae ("mm: send one IPI per CPU to TLB flush all entries after unmapping pages")
Signed-off-by: NNadav Amit <namit@vmware.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

TLB_REMOTE_SEND_IPI was recently introduced, but it counts bytes instead
of pages.  In addition, it does not report correctly the case in which
flush_tlb_page flushes a page.  Fix it to be consistent with other TLB
counters.

Fixes: 5b74283a ("x86, mm: trace when an IPI is about to be sent")
Signed-off-by: NNadav Amit <namit@vmware.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Rik van Riel <riel@redhat.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

In absence of shadow dirty mask, there is no need to set page dirty
if page has never been writable. This is a tiny optimization but
good to have for people who care much about dirty page tracking.
Signed-off-by: NYu Zhao <yuzhao@google.com>
Signed-off-by: NPaolo Bonzini <pbonzini@redhat.com>