On x86-64, __copy_instruction() always returns 0 (error) if the
instruction uses %rip-relative addressing. This is because
kernel_insn_init() is called the second time for 'insn' instance
in such cases and sets all its fields to 0.
Because of this, trying to place a kprobe on such instruction
will fail, register_kprobe() will return -EINVAL.
This patch fixes the problem.
Signed-off-by: Eugene Shatokhin <eugene.shatokhin@rosalab.ru>
Signed-off-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Link: http://lkml.kernel.org/r/20150317100918.28349.94654.stgit@localhost.localdomain
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Pull Intel Quark SoC support from Ingo Molnar:
"This adds support for Intel Quark X1000 SoC boards, used in the low
power 32-bit x86 Intel Galileo microcontroller board intended for the
Arduino space.
There's been some preparatory core x86 patches for Quark CPU quirks
merged already, but this rounds it all up and adds Kconfig enablement.
It's a clean hardware enablement addition tree at this point"
* 'x86-platform-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/intel/quark: Fix simple_return.cocci warnings
x86/intel/quark: Fix ptr_ret.cocci warnings
x86/intel/quark: Add Intel Quark platform support
x86/intel/quark: Add Isolated Memory Regions for Quark X1000
Pull locking fixes from Ingo Molnar:
"Two fixes: the paravirt spin_unlock() corruption/crash fix, and an
rtmutex NULL dereference crash fix"
* 'locking-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/spinlocks/paravirt: Fix memory corruption on unlock
locking/rtmutex: Avoid a NULL pointer dereference on deadlock
Pull misc x86 fixes from Ingo Molnar:
"This contains:
- EFI fixes
- a boot printout fix
- ASLR/kASLR fixes
- intel microcode driver fixes
- other misc fixes
Most of the linecount comes from an EFI revert"
* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/mm/ASLR: Avoid PAGE_SIZE redefinition for UML subarch
x86/microcode/intel: Handle truncated microcode images more robustly
x86/microcode/intel: Guard against stack overflow in the loader
x86, mm/ASLR: Fix stack randomization on 64-bit systems
x86/mm/init: Fix incorrect page size in init_memory_mapping() printks
x86/mm/ASLR: Propagate base load address calculation
Documentation/x86: Fix path in zero-page.txt
x86/apic: Fix the devicetree build in certain configs
Revert "efi/libstub: Call get_memory_map() to obtain map and desc sizes"
x86/efi: Avoid triple faults during EFI mixed mode calls
Pull x86 uprobe/kprobe fixes from Ingo Molnar:
"This contains two uprobes fixes, an uprobes comment update and a
kprobes fix"
* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
kprobes/x86: Mark 2 bytes NOP as boostable
uprobes/x86: Fix 2-byte opcode table
uprobes/x86: Fix 1-byte opcode tables
uprobes/x86: Add comment with insn opcodes, mnemonics and why we dont support them
Pull rcu fix and x86 irq fix from Ingo Molnar:
- Fix a bug that caused an RCU warning splat.
- Two x86 irq related fixes: a hotplug crash fix and an ACPI IRQ
registry fix.
* 'core-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
rcu: Clear need_qs flag to prevent splat
* 'irq-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
x86/irq: Check for valid irq descriptor in check_irq_vectors_for_cpu_disable()
x86/irq: Fix regression caused by commit b568b8601f
__recover_probed_insn() should always be called from an address
where an instructions starts. The check for ftrace_location()
might help to discover a potential inconsistency.
This patch adds WARN_ON() when the inconsistency is detected.
Also it adds handling of the situation when the original code
can not get recovered.
Suggested-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Signed-off-by: Petr Mladek <pmladek@suse.cz>
Cc: Ananth NMavinakayanahalli <ananth@in.ibm.com>
Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1424441250-27146-3-git-send-email-pmladek@suse.cz
Signed-off-by: Ingo Molnar <mingo@kernel.org>
can_probe() checks if the given address points to the beginning
of an instruction. It analyzes all the instructions from the
beginning of the function until the given address. The code
might be modified by another Kprobe. In this case, the current
code is read into a buffer, int3 breakpoint is replaced by the
saved opcode in the buffer, and can_probe() analyzes the buffer
instead.
There is a bug that __recover_probed_insn() tries to restore
the original code even for Kprobes using the ftrace framework.
But in this case, the opcode is not stored. See the difference
between arch_prepare_kprobe() and arch_prepare_kprobe_ftrace().
The opcode is stored by arch_copy_kprobe() only from
arch_prepare_kprobe().
This patch makes Kprobe to use the ideal 5-byte NOP when the
code can be modified by ftrace. It is the original instruction,
see ftrace_make_nop() and ftrace_nop_replace().
Note that we always need to use the NOP for ftrace locations.
Kprobes do not block ftrace and the instruction might get
modified at anytime. It might even be in an inconsistent state
because it is modified step by step using the int3 breakpoint.
The patch also fixes indentation of the touched comment.
Note that I found this problem when playing with Kprobes. I did
it on x86_64 with gcc-4.8.3 that supported -mfentry. I modified
samples/kprobes/kprobe_example.c and added offset 5 to put
the probe right after the fentry area:
static struct kprobe kp = {
.symbol_name = "do_fork",
+ .offset = 5,
};
Then I was able to load kprobe_example before jprobe_example
but not the other way around:
$> modprobe jprobe_example
$> modprobe kprobe_example
modprobe: ERROR: could not insert 'kprobe_example': Invalid or incomplete multibyte or wide character
It did not make much sense and debugging pointed to the bug
described above.
Signed-off-by: Petr Mladek <pmladek@suse.cz>
Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Ananth NMavinakayanahalli <ananth@in.ibm.com>
Cc: Anil S Keshavamurthy <anil.s.keshavamurthy@intel.com>
Cc: David S. Miller <davem@davemloft.net>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Steven Rostedt <rostedt@goodmis.org>
Link: http://lkml.kernel.org/r/1424441250-27146-2-git-send-email-pmladek@suse.cz
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Commit f47233c2d3 ("x86/mm/ASLR: Propagate base load address
calculation") causes PAGE_SIZE redefinition warnings for UML
subarch builds. This is caused by added includes that were
leftovers from previous patch versions are are not actually
needed (especially page_types.h inlcude in module.c). Drop
those stray includes.
Reported-by: kbuild test robot <fengguang.wu@intel.com>
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Cc: Borislav Petkov <bp@suse.de>
Cc: H. Peter Anvin <hpa@linux.intel.com>
Cc: Kees Cook <keescook@chromium.org>
Link: http://lkml.kernel.org/r/alpine.LNX.2.00.1502201017240.28769@pobox.suse.cz
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Since _PAGE_PROTNONE aliases _PAGE_GLOBAL it is only valid if
_PAGE_PRESENT is clear. Make pte_protnone() and pmd_protnone() check
for this.
This fixes a 64-bit Xen PV guest regression introduced by 8a0516ed8b
("mm: convert p[te|md]_numa users to p[te|md]_protnone_numa"). Any
userspace process would endlessly fault.
In a 64-bit PV guest, userspace page table entries have _PAGE_GLOBAL set
by the hypervisor. This meant that any fault on a present userspace
entry (e.g., a write to a read-only mapping) would be misinterpreted as
a NUMA hinting fault and the fault would not be correctly handled,
resulting in the access endlessly faulting.
Signed-off-by: David Vrabel <david.vrabel@citrix.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull kbuild updates from Michal Marek:
- several cleanups in kbuild
- serialize multiple *config targets so that 'make defconfig kvmconfig'
works
- The cc-ifversion macro got support for an else-branch
* 'kbuild' of git://git.kernel.org/pub/scm/linux/kernel/git/mmarek/kbuild:
kbuild,gcov: simplify kernel/gcov/Makefile more
kbuild: allow cc-ifversion to have the argument for false condition
kbuild,gcov: simplify kernel/gcov/Makefile
kbuild,gcov: remove unnecessary workaround
kbuild: do not add $(call ...) to invoke cc-version or cc-fullversion
kbuild: fix cc-ifversion macro
kbuild: drop $(version_h) from MRPROPER_FILES
kbuild: use mixed-targets when two or more config targets are given
kbuild: remove redundant line from bounds.h/asm-offsets.h
kbuild: merge bounds.h and asm-offsets.h rules
kbuild: Drop support for clean-rule
We do not check the input data bounds containing the microcode before
copying a struct microcode_intel_header from it. A specially crafted
microcode could cause the kernel to read invalid memory and lead to a
denial-of-service.
Signed-off-by: Quentin Casasnovas <quentin.casasnovas@oracle.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Link: http://lkml.kernel.org/r/1422964824-22056-3-git-send-email-quentin.casasnovas@oracle.com
[ Made error message differ from the next one and flipped comparison. ]
Signed-off-by: Borislav Petkov <bp@suse.de>
mc_saved_tmp is a static array allocated on the stack, we need to make
sure mc_saved_count stays within its bounds, otherwise we're overflowing
the stack in _save_mc(). A specially crafted microcode header could lead
to a kernel crash or potentially kernel execution.
Signed-off-by: Quentin Casasnovas <quentin.casasnovas@oracle.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Link: http://lkml.kernel.org/r/1422964824-22056-1-git-send-email-quentin.casasnovas@oracle.com
Signed-off-by: Borislav Petkov <bp@suse.de>
Pull ASLR and kASLR fixes from Borislav Petkov:
- Add a global flag announcing KASLR state so that relevant code can do
informed decisions based on its setting. (Jiri Kosina)
- Fix a stack randomization entropy decrease bug. (Hector Marco-Gisbert)
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The issue is that the stack for processes is not properly randomized on
64 bit architectures due to an integer overflow.
The affected function is randomize_stack_top() in file
"fs/binfmt_elf.c":
static unsigned long randomize_stack_top(unsigned long stack_top)
{
unsigned int random_variable = 0;
if ((current->flags & PF_RANDOMIZE) &&
!(current->personality & ADDR_NO_RANDOMIZE)) {
random_variable = get_random_int() & STACK_RND_MASK;
random_variable <<= PAGE_SHIFT;
}
return PAGE_ALIGN(stack_top) + random_variable;
return PAGE_ALIGN(stack_top) - random_variable;
}
Note that, it declares the "random_variable" variable as "unsigned int".
Since the result of the shifting operation between STACK_RND_MASK (which
is 0x3fffff on x86_64, 22 bits) and PAGE_SHIFT (which is 12 on x86_64):
random_variable <<= PAGE_SHIFT;
then the two leftmost bits are dropped when storing the result in the
"random_variable". This variable shall be at least 34 bits long to hold
the (22+12) result.
These two dropped bits have an impact on the entropy of process stack.
Concretely, the total stack entropy is reduced by four: from 2^28 to
2^30 (One fourth of expected entropy).
This patch restores back the entropy by correcting the types involved
in the operations in the functions randomize_stack_top() and
stack_maxrandom_size().
The successful fix can be tested with:
$ for i in `seq 1 10`; do cat /proc/self/maps | grep stack; done
7ffeda566000-7ffeda587000 rw-p 00000000 00:00 0 [stack]
7fff5a332000-7fff5a353000 rw-p 00000000 00:00 0 [stack]
7ffcdb7a1000-7ffcdb7c2000 rw-p 00000000 00:00 0 [stack]
7ffd5e2c4000-7ffd5e2e5000 rw-p 00000000 00:00 0 [stack]
...
Once corrected, the leading bytes should be between 7ffc and 7fff,
rather than always being 7fff.
Signed-off-by: Hector Marco-Gisbert <hecmargi@upv.es>
Signed-off-by: Ismael Ripoll <iripoll@upv.es>
[ Rebased, fixed 80 char bugs, cleaned up commit message, added test example and CVE ]
Signed-off-by: Kees Cook <keescook@chromium.org>
Cc: <stable@vger.kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Fixes: CVE-2015-1593
Link: http://lkml.kernel.org/r/20150214173350.GA18393@www.outflux.net
Signed-off-by: Borislav Petkov <bp@suse.de>
With 32-bit non-PAE kernels, we have 2 page sizes available
(at most): 4k and 4M.
Enabling PAE replaces that 4M size with a 2M one (which 64-bit
systems use too).
But, when booting a 32-bit non-PAE kernel, in one of our
early-boot printouts, we say:
init_memory_mapping: [mem 0x00000000-0x000fffff]
[mem 0x00000000-0x000fffff] page 4k
init_memory_mapping: [mem 0x37000000-0x373fffff]
[mem 0x37000000-0x373fffff] page 2M
init_memory_mapping: [mem 0x00100000-0x36ffffff]
[mem 0x00100000-0x003fffff] page 4k
[mem 0x00400000-0x36ffffff] page 2M
init_memory_mapping: [mem 0x37400000-0x377fdfff]
[mem 0x37400000-0x377fdfff] page 4k
Which is obviously wrong. There is no 2M page available. This
is probably because of a badly-named variable: in the map_range
code: PG_LEVEL_2M.
Instead of renaming all the PG_LEVEL_2M's. This patch just
fixes the printout:
init_memory_mapping: [mem 0x00000000-0x000fffff]
[mem 0x00000000-0x000fffff] page 4k
init_memory_mapping: [mem 0x37000000-0x373fffff]
[mem 0x37000000-0x373fffff] page 4M
init_memory_mapping: [mem 0x00100000-0x36ffffff]
[mem 0x00100000-0x003fffff] page 4k
[mem 0x00400000-0x36ffffff] page 4M
init_memory_mapping: [mem 0x37400000-0x377fdfff]
[mem 0x37400000-0x377fdfff] page 4k
BRK [0x03206000, 0x03206fff] PGTABLE
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: Yinghai Lu <yinghai@kernel.org>
Link: http://lkml.kernel.org/r/20150210212030.665EC267@viggo.jf.intel.com
Signed-off-by: Borislav Petkov <bp@suse.de>
Commit:
e2b32e6785 ("x86, kaslr: randomize module base load address")
makes the base address for module to be unconditionally randomized in
case when CONFIG_RANDOMIZE_BASE is defined and "nokaslr" option isn't
present on the commandline.
This is not consistent with how choose_kernel_location() decides whether
it will randomize kernel load base.
Namely, CONFIG_HIBERNATION disables kASLR (unless "kaslr" option is
explicitly specified on kernel commandline), which makes the state space
larger than what module loader is looking at. IOW CONFIG_HIBERNATION &&
CONFIG_RANDOMIZE_BASE is a valid config option, kASLR wouldn't be applied
by default in that case, but module loader is not aware of that.
Instead of fixing the logic in module.c, this patch takes more generic
aproach. It introduces a new bootparam setup data_type SETUP_KASLR and
uses that to pass the information whether kaslr has been applied during
kernel decompression, and sets a global 'kaslr_enabled' variable
accordingly, so that any kernel code (module loading, livepatching, ...)
can make decisions based on its value.
x86 module loader is converted to make use of this flag.
Signed-off-by: Jiri Kosina <jkosina@suse.cz>
Acked-by: Kees Cook <keescook@chromium.org>
Cc: "H. Peter Anvin" <hpa@linux.intel.com>
Link: https://lkml.kernel.org/r/alpine.LNX.2.00.1502101411280.10719@pobox.suse.cz
[ Always dump correct kaslr status when panicking ]
Signed-off-by: Borislav Petkov <bp@suse.de>
Add Intel Quark platform support. Quark needs to pull down all
unlocked IMRs to ensure agreement with the EFI memory map post
boot.
This patch adds an entry in Kconfig for Quark as a platform and
makes IMR support mandatory if selected.
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Suggested-by: Andy Shevchenko <andy.shevchenko@gmail.com>
Tested-by: Ong, Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: Bryan O'Donoghue <pure.logic@nexus-software.ie>
Reviewed-by: Andy Shevchenko <andy.schevchenko@gmail.com>
Reviewed-by: Darren Hart <dvhart@linux.intel.com>
Reviewed-by: Ong, Boon Leong <boon.leong.ong@intel.com>
Cc: dvhart@infradead.org
Link: http://lkml.kernel.org/r/1422635379-12476-3-git-send-email-pure.logic@nexus-software.ie
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Intel's Quark X1000 SoC contains a set of registers called
Isolated Memory Regions. IMRs are accessed over the IOSF mailbox
interface. IMRs are areas carved out of memory that define
read/write access rights to the various system agents within the
Quark system. For a given agent in the system it is possible to
specify if that agent may read or write an area of memory
defined by an IMR with a granularity of 1 KiB.
Quark_SecureBootPRM_330234_001.pdf section 4.5 details the
concept of IMRs quark-x1000-datasheet.pdf section 12.7.4 details
the implementation of IMRs in silicon.
eSRAM flush, CPU Snoop write-only, CPU SMM Mode, CPU non-SMM
mode, RMU and PCIe Virtual Channels (VC0 and VC1) can have
individual read/write access masks applied to them for a given
memory region in Quark X1000. This enables IMRs to treat each
memory transaction type listed above on an individual basis and
to filter appropriately based on the IMR access mask for the
memory region. Quark supports eight IMRs.
Since all of the DMA capable SoC components in the X1000 are
mapped to VC0 it is possible to define sections of memory as
invalid for DMA write operations originating from Ethernet, USB,
SD and any other DMA capable south-cluster component on VC0.
Similarly it is possible to mark kernel memory as non-SMM mode
read/write only or to mark BIOS runtime memory as SMM mode
accessible only depending on the particular memory footprint on
a given system.
On an IMR violation Quark SoC X1000 systems are configured to
reset the system, so ensuring that the IMR memory map is
consistent with the EFI provided memory map is critical to
ensure no IMR violations reset the system.
The API for accessing IMRs is based on MTRR code but doesn't
provide a /proc or /sys interface to manipulate IMRs. Defining
the size and extent of IMRs is exclusively the domain of
in-kernel code.
Quark firmware sets up a series of locked IMRs around pieces of
memory that firmware owns such as ACPI runtime data. During boot
a series of unlocked IMRs are placed around items in memory to
guarantee no DMA modification of those items can take place.
Grub also places an unlocked IMR around the kernel boot params
data structure and compressed kernel image. It is necessary for
the kernel to tear down all unlocked IMRs in order to ensure
that the kernel's view of memory passed via the EFI memory map
is consistent with the IMR memory map. Without tearing down all
unlocked IMRs on boot transitory IMRs such as those used to
protect the compressed kernel image will cause IMR violations and system reboots.
The IMR init code tears down all unlocked IMRs and sets a
protective IMR around the kernel .text and .rodata as one
contiguous block. This sanitizes the IMR memory map with respect
to the EFI memory map and protects the read-only portions of the
kernel from unwarranted DMA access.
Tested-by: Ong, Boon Leong <boon.leong.ong@intel.com>
Signed-off-by: Bryan O'Donoghue <pure.logic@nexus-software.ie>
Reviewed-by: Andy Shevchenko <andy.schevchenko@gmail.com>
Reviewed-by: Darren Hart <dvhart@linux.intel.com>
Reviewed-by: Ong, Boon Leong <boon.leong.ong@intel.com>
Cc: andy.shevchenko@gmail.com
Cc: dvhart@infradead.org
Link: http://lkml.kernel.org/r/1422635379-12476-2-git-send-email-pure.logic@nexus-software.ie
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Without this patch:
LD init/built-in.o
arch/x86/built-in.o: In function `dtb_lapic_setup': kernel/devicetree.c:155:
undefined reference to `apic_force_enable'
Makefile:923: recipe for target 'vmlinux' failed
make: *** [vmlinux] Error 1
Signed-off-by: Ricardo Ribalda Delgado <ricardo.ribalda@gmail.com>
Reviewed-by: Maciej W. Rozycki <macro@linux-mips.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Jan Beulich <JBeulich@suse.com>
Link: http://lkml.kernel.org/r/1422905231-16067-1-git-send-email-ricardo.ribalda@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Currently, x86 kprobes is unable to boost 2 bytes nop like:
nopl 0x0(%rax,%rax,1)
which is 0x0f 0x1f 0x44 0x00 0x00.
Such nops have exactly 5 bytes to hold a relative jmp
instruction. Boosting them should be obviously safe.
This patch enable boosting such nops by simply updating
twobyte_is_boostable[] array.
Signed-off-by: Wang Nan <wangnan0@huawei.com>
Acked-by: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: <lizefan@huawei.com>
Link: http://lkml.kernel.org/r/1423532045-41049-1-git-send-email-wangnan0@huawei.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Enabled probing of lar, lsl, popcnt, lddqu, prefetch insns.
They should be safe to probe, they throw no exceptions.
Enabled probing of 3-byte opcodes 0f 38-3f xx - these are
vector isns, so should be safe.
Enabled probing of many currently undefined 0f xx insns.
At the rate new vector instructions are getting added,
we don't want to constantly enable more bits.
We want to only occasionally *disable* ones which
for some reason can't be probed.
This includes 0f 24,26 opcodes, which are undefined
since Pentium. On 486, they were "mov to/from test register".
Explained more fully what 0f 78,79 opcodes are.
Explained what 0f ae opcode is. (It's unclear why we don't allow
probing it, but let's not change it for now).
Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Jim Keniston <jkenisto@us.ibm.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1423768732-32194-3-git-send-email-dvlasenk@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
This change fixes 1-byte opcode tables so that only insns
for which we have real reasons to disallow probing are marked
with unset bits.
To that end:
Set bits for all prefix bytes. Their setting is ignored anyway -
we check the bitmap against OPCODE1(insn), not against first
byte. Keeping them set to 0 only confuses code reader with
"why we don't support that opcode" question.
Thus: enable bytes c4,c5 in 64-bit mode (VEX prefixes).
Byte 62 (EVEX prefix) is not yet enabled since insn decoder
does not support that yet.
For 32-bit mode, enable probing of opcodes 63 (arpl) and d6
(salc). They don't require any special handling.
For 64-bit mode, disable 9a and ea - these undefined opcodes
were mistakenly left enabled.
Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Jim Keniston <jkenisto@us.ibm.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1423768732-32194-2-git-send-email-dvlasenk@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
After adding these, it's clear we have some awkward choices
there. Some valid instructions are prohibited from uprobing
while several invalid ones are allowed.
Hopefully future edits to the good-opcode tables will fix wrong
bits or explain why those bits are not wrong.
No actual code changes.
Signed-off-by: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Jim Keniston <jkenisto@us.ibm.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
Link: http://lkml.kernel.org/r/1423768732-32194-1-git-send-email-dvlasenk@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Like in 3.19, I once more have a multi-stage cleanup for one asm-generic
header file, this time the work was done by Michael Tsirkin and cleans
up the uaccess.h file in asm-generic, as well as all architectures for
which the respective maintainers did not pick up his patches directly.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.12 (GNU/Linux)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=LROx
-----END PGP SIGNATURE-----
Merge tag 'asm-generic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic
Pull asm-generic uaccess.h cleanup from Arnd Bergmann:
"Like in 3.19, I once more have a multi-stage cleanup for one
asm-generic header file, this time the work was done by Michael
Tsirkin and cleans up the uaccess.h file in asm-generic, as well as
all architectures for which the respective maintainers did not pick up
his patches directly"
* tag 'asm-generic-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/arnd/asm-generic: (37 commits)
sparc32: nocheck uaccess coding style tweaks
sparc64: nocheck uaccess coding style tweaks
xtensa: macro whitespace fixes
sh: macro whitespace fixes
parisc: macro whitespace fixes
m68k: macro whitespace fixes
m32r: macro whitespace fixes
frv: macro whitespace fixes
cris: macro whitespace fixes
avr32: macro whitespace fixes
arm64: macro whitespace fixes
arm: macro whitespace fixes
alpha: macro whitespace fixes
blackfin: macro whitespace fixes
sparc64: uaccess_64 macro whitespace fixes
sparc32: uaccess_32 macro whitespace fixes
avr32: whitespace fix
sh: fix put_user sparse errors
metag: fix put_user sparse errors
ia64: fix put_user sparse errors
...
On top of tht is the major rework of lguest, to use PCI and virtio 1.0, to
double-check the implementation.
Then comes the inevitable fixes and cleanups from that work.
Thanks,
Rusty.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=ivCe
-----END PGP SIGNATURE-----
Merge tag 'virtio-next-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux
Pull virtio updates from Rusty Russell:
"OK, this has the big virtio 1.0 implementation, as specified by OASIS.
On top of tht is the major rework of lguest, to use PCI and virtio
1.0, to double-check the implementation.
Then comes the inevitable fixes and cleanups from that work"
* tag 'virtio-next-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rusty/linux: (80 commits)
virtio: don't set VIRTIO_CONFIG_S_DRIVER_OK twice.
virtio_net: unconditionally define struct virtio_net_hdr_v1.
tools/lguest: don't use legacy definitions for net device in example launcher.
virtio: Don't expose legacy net features when VIRTIO_NET_NO_LEGACY defined.
tools/lguest: use common error macros in the example launcher.
tools/lguest: give virtqueues names for better error messages
tools/lguest: more documentation and checking of virtio 1.0 compliance.
lguest: don't look in console features to find emerg_wr.
tools/lguest: don't start devices until DRIVER_OK status set.
tools/lguest: handle indirect partway through chain.
tools/lguest: insert driver references from the 1.0 spec (4.1 Virtio Over PCI)
tools/lguest: insert device references from the 1.0 spec (4.1 Virtio Over PCI)
tools/lguest: rename virtio_pci_cfg_cap field to match spec.
tools/lguest: fix features_accepted logic in example launcher.
tools/lguest: handle device reset correctly in example launcher.
virtual: Documentation: simplify and generalize paravirt_ops.txt
lguest: remove NOTIFY call and eventfd facility.
lguest: remove NOTIFY facility from demonstration launcher.
lguest: use the PCI console device's emerg_wr for early boot messages.
lguest: always put console in PCI slot #1.
...
With LBR call stack feature enable, there are three callchain options.
Enable the 3rd callchain option (LBR callstack) to user space tooling.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: linux-api@vger.kernel.org
Link: http://lkml.kernel.org/r/20141105093759.GQ10501@worktop.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
"Zero length call" uses the attribute of the call instruction to push
the immediate instruction pointer on to the stack and then pops off
that address into a register. This is accomplished without any matching
return instruction. It confuses the hardware and make the recorded call
stack incorrect.
We can partially resolve this issue by: decode call instructions and
discard any zero length call entry in the LBR stack.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Signed-off-by: Kan Liang <kan.liang@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: eranian@google.com
Cc: jolsa@redhat.com
Link: http://lkml.kernel.org/r/1415156173-10035-16-git-send-email-kan.liang@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
LBR callstack is designed for PEBS, It does not work well with
FREEZE_LBRS_ON_PMI for non PEBS event. If FREEZE_LBRS_ON_PMI is set for
non PEBS event, PMIs near call/return instructions may cause superfluous
increase/decrease of LBR_TOS.
This patch modifies __intel_pmu_lbr_enable() to not enable
FREEZE_LBRS_ON_PMI when LBR operates in callstack mode. We currently
don't use LBR callstack to capture kernel space callchain, so disabling
FREEZE_LBRS_ON_PMI should not be a problem.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Signed-off-by: Kan Liang <kan.liang@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: eranian@google.com
Cc: jolsa@redhat.com
Link: http://lkml.kernel.org/r/1415156173-10035-15-git-send-email-kan.liang@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Use event->attr.branch_sample_type to replace
intel_pmu_needs_lbr_smpl() for avoiding duplicated code that
implicitly enables the LBR.
Currently, branch stack can be enabled by user explicitly requesting
branch sampling or implicit branch sampling to correct PEBS skid.
For user explicitly requested branch sampling, the branch_sample_type
is explicitly set by user. For PEBS case, the branch_sample_type is also
implicitly set to PERF_SAMPLE_BRANCH_ANY in x86_pmu_hw_config.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Signed-off-by: Kan Liang <kan.liang@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: eranian@google.com
Cc: jolsa@redhat.com
Link: http://lkml.kernel.org/r/1415156173-10035-11-git-send-email-kan.liang@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When the LBR call stack is enabled, it is necessary to save/restore
the LBR stack on context switch. The solution is saving/restoring
the LBR stack to/from task's perf event context.
The LBR stack is saved/restored only when there are events that use
the LBR call stack. If no event uses LBR call stack, the LBR stack
is reset when task is scheduled in.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Signed-off-by: Kan Liang <kan.liang@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: eranian@google.com
Cc: jolsa@redhat.com
Link: http://lkml.kernel.org/r/1415156173-10035-10-git-send-email-kan.liang@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When enabling/disabling an event, check if the event uses the LBR
callstack feature, adjust the LBR callstack usage count accordingly.
Later patch will use the usage count to decide if LBR stack should
be saved/restored.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Signed-off-by: Kan Liang <kan.liang@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: eranian@google.com
Cc: jolsa@redhat.com
Link: http://lkml.kernel.org/r/1415156173-10035-9-git-send-email-kan.liang@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When the LBR call stack is enabled, it is necessary to save/restore
the LBR stack on context switch. We can use pmu specific data to
store LBR stack when task is scheduled out. This patch adds code
that allocates the pmu specific data.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Signed-off-by: Kan Liang <kan.liang@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Stephane Eranian <eranian@google.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: jolsa@redhat.com
Link: http://lkml.kernel.org/r/1415156173-10035-8-git-send-email-kan.liang@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Haswell has a new feature that utilizes the existing LBR facility to
record call chains. To enable this feature, bits (JCC, NEAR_IND_JMP,
NEAR_REL_JMP, FAR_BRANCH, EN_CALLSTACK) in LBR_SELECT must be set to 1,
bits (NEAR_REL_CALL, NEAR-IND_CALL, NEAR_RET) must be cleared. Due to
a hardware bug of Haswell, this feature doesn't work well with
FREEZE_LBRS_ON_PMI.
When the call stack feature is enabled, the LBR stack will capture
unfiltered call data normally, but as return instructions are executed,
the last captured branch record is flushed from the on-chip registers
in a last-in first-out (LIFO) manner. Thus, branch information relative
to leaf functions will not be captured, while preserving the call stack
information of the main line execution path.
This patch defines a separate lbr_sel map for Haswell. The map contains
a new entry for the call stack feature.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Signed-off-by: Kan Liang <kan.liang@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: eranian@google.com
Cc: jolsa@redhat.com
Link: http://lkml.kernel.org/r/1415156173-10035-5-git-send-email-kan.liang@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Previous commit introduces context switch callback, its function
overlaps with the flush branch stack callback. So we can use the
context switch callback to flush LBR stack.
This patch adds code that uses the flush branch callback to
flush the LBR stack when task is being scheduled in. The callback
is enabled only when there are events use the LBR hardware. This
patch also removes all old flush branch stack code.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Signed-off-by: Kan Liang <kan.liang@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: eranian@google.com
Cc: jolsa@redhat.com
Link: http://lkml.kernel.org/r/1415156173-10035-4-git-send-email-kan.liang@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The callback is invoked when process is scheduled in or out.
It provides mechanism for later patches to save/store the LBR
stack. For the schedule in case, the callback is invoked at
the same place that flush branch stack callback is invoked.
So it also can replace the flush branch stack callback. To
avoid unnecessary overhead, the callback is enabled only when
there are events use the LBR stack.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Signed-off-by: Kan Liang <kan.liang@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: eranian@google.com
Cc: jolsa@redhat.com
Link: http://lkml.kernel.org/r/1415156173-10035-3-git-send-email-kan.liang@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The index of lbr_sel_map is bit value of perf branch_sample_type.
PERF_SAMPLE_BRANCH_MAX is 1024 at present, so each lbr_sel_map uses
4096 bytes. By using bit shift as index, we can reduce lbr_sel_map
size to 40 bytes. This patch defines 'bit shift' for branch types,
and use 'bit shift' to define lbr_sel_maps.
Signed-off-by: Yan, Zheng <zheng.z.yan@intel.com>
Signed-off-by: Kan Liang <kan.liang@intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Stephane Eranian <eranian@google.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: jolsa@redhat.com
Cc: linux-api@vger.kernel.org
Link: http://lkml.kernel.org/r/1415156173-10035-2-git-send-email-kan.liang@intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The caller of force_ibs_eilvt_setup() is ibs_eilvt_setup()
which does not care about the return values.
So mark it void and clean up the return statements.
Signed-off-by: Aravind Gopalakrishnan <aravind.gopalakrishnan@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: <hpa@zytor.com>
Cc: <paulus@samba.org>
Cc: <tglx@linutronix.de>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/1422037175-20957-1-git-send-email-aravind.gopalakrishnan@amd.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The pci_dev_put() function tests whether its argument is NULL and then
returns immediately. Thus the test around the call is not needed.
This issue was detected by using the Coccinelle software.
Signed-off-by: Markus Elfring <elfring@users.sourceforge.net>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/54D0B59C.2060106@users.sourceforge.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
When an interrupt is migrated away from a cpu it will stay
in its vector_irq array until smp_irq_move_cleanup_interrupt
succeeded. The cfg->move_in_progress flag is cleared already
when the IPI was sent.
When the interrupt is destroyed after migration its 'struct
irq_desc' is freed and the vector_irq arrays are cleaned up.
But since cfg->move_in_progress is already 0 the references
at cpus before the last migration will not be cleared. So
this would leave a reference to an already destroyed irq
alive.
When the cpu is taken down at this point, the
check_irq_vectors_for_cpu_disable() function finds a valid irq
number in the vector_irq array, but gets NULL for its
descriptor and dereferences it, causing a kernel panic.
This has been observed on real systems at shutdown. Add a
check to check_irq_vectors_for_cpu_disable() for a valid
'struct irq_desc' to prevent this issue.
Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Jiang Liu <jiang.liu@linux.intel.com>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Jan Beulich <JBeulich@suse.com>
Cc: K. Y. Srinivasan <kys@microsoft.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: alnovak@suse.com
Cc: joro@8bytes.org
Link: http://lkml.kernel.org/r/20150204132754.GA10078@suse.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Commit b568b8601f ("Treat SCI interrupt as normal GSI interrupt")
accidently removes support of legacy PIC interrupt when fixing a
regression for Xen, which causes a nasty regression on HP/Compaq
nc6000 where we fail to register the ACPI interrupt, and thus
lose eg. thermal notifications leading a potentially overheated
machine.
So reintroduce support of legacy PIC based ACPI SCI interrupt.
Reported-by: Ville Syrjälä <syrjala@sci.fi>
Tested-by: Ville Syrjälä <syrjala@sci.fi>
Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Pavel Machek <pavel@ucw.cz>
Cc: <stable@vger.kernel.org> # 3.19+
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Rafael J. Wysocki <rjw@rjwysocki.net>
Cc: Sander Eikelenboom <linux@eikelenboom.it>
Cc: linux-pm@vger.kernel.org
Link: http://lkml.kernel.org/r/1424052673-22974-1-git-send-email-jiang.liu@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Paravirt spinlock clears slowpath flag after doing unlock.
As explained by Linus currently it does:
prev = *lock;
add_smp(&lock->tickets.head, TICKET_LOCK_INC);
/* add_smp() is a full mb() */
if (unlikely(lock->tickets.tail & TICKET_SLOWPATH_FLAG))
__ticket_unlock_slowpath(lock, prev);
which is *exactly* the kind of things you cannot do with spinlocks,
because after you've done the "add_smp()" and released the spinlock
for the fast-path, you can't access the spinlock any more. Exactly
because a fast-path lock might come in, and release the whole data
structure.
Linus suggested that we should not do any writes to lock after unlock(),
and we can move slowpath clearing to fastpath lock.
So this patch implements the fix with:
1. Moving slowpath flag to head (Oleg):
Unlocked locks don't care about the slowpath flag; therefore we can keep
it set after the last unlock, and clear it again on the first (try)lock.
-- this removes the write after unlock. note that keeping slowpath flag would
result in unnecessary kicks.
By moving the slowpath flag from the tail to the head ticket we also avoid
the need to access both the head and tail tickets on unlock.
2. use xadd to avoid read/write after unlock that checks the need for
unlock_kick (Linus):
We further avoid the need for a read-after-release by using xadd;
the prev head value will include the slowpath flag and indicate if we
need to do PV kicking of suspended spinners -- on modern chips xadd
isn't (much) more expensive than an add + load.
Result:
setup: 16core (32 cpu +ht sandy bridge 8GB 16vcpu guest)
benchmark overcommit %improve
kernbench 1x -0.13
kernbench 2x 0.02
dbench 1x -1.77
dbench 2x -0.63
[Jeremy: Hinted missing TICKET_LOCK_INC for kick]
[Oleg: Moved slowpath flag to head, ticket_equals idea]
[PeterZ: Added detailed changelog]
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Tested-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Raghavendra K T <raghavendra.kt@linux.vnet.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Oleg Nesterov <oleg@redhat.com>
Cc: Andrew Jones <drjones@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: Dave Jones <davej@redhat.com>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Fernando Luis Vázquez Cao <fernando_b1@lab.ntt.co.jp>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Paolo Bonzini <pbonzini@redhat.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Ulrich Obergfell <uobergfe@redhat.com>
Cc: Waiman Long <Waiman.Long@hp.com>
Cc: a.ryabinin@samsung.com
Cc: dave@stgolabs.net
Cc: hpa@zytor.com
Cc: jasowang@redhat.com
Cc: jeremy@goop.org
Cc: paul.gortmaker@windriver.com
Cc: riel@redhat.com
Cc: tglx@linutronix.de
Cc: waiman.long@hp.com
Cc: xen-devel@lists.xenproject.org
Link: http://lkml.kernel.org/r/20150215173043.GA7471@linux.vnet.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
calls to avoid triple faults if an NMI/MCE is received.
* Revert Ard's change to the libstub get_memory_map() that went into
the v3.20 merge window because it causes boot regressions on Qemu and
Xen.
-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1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=I/nB
-----END PGP SIGNATURE-----
Merge tag 'efi-urgent' of git://git.kernel.org/pub/scm/linux/kernel/git/mfleming/efi into x86/urgent
Pull EFI fixes from Matt Fleming:
" - Leave a valid 64-bit IDT installed during runtime EFI mixed mode
calls to avoid triple faults if an NMI/MCE is received.
- Revert Ard's change to the libstub get_memory_map() that went into
the v3.20 merge window because it causes boot regressions on Qemu and
Xen. "
Signed-off-by: Ingo Molnar <mingo@kernel.org>
