commit 11276d5306 upstream.
There are various problems and short-comings with the current
static_key interface:
- static_key_{true,false}() read like a branch depending on the key
value, instead of the actual likely/unlikely branch depending on
init value.
- static_key_{true,false}() are, as stated above, tied to the
static_key init values STATIC_KEY_INIT_{TRUE,FALSE}.
- we're limited to the 2 (out of 4) possible options that compile to
a default NOP because that's what our arch_static_branch() assembly
emits.
So provide a new static_key interface:
DEFINE_STATIC_KEY_TRUE(name);
DEFINE_STATIC_KEY_FALSE(name);
Which define a key of different types with an initial true/false
value.
Then allow:
static_branch_likely()
static_branch_unlikely()
to take a key of either type and emit the right instruction for the
case.
This means adding a second arch_static_branch_jump() assembly helper
which emits a JMP per default.
In order to determine the right instruction for the right state,
encode the branch type in the LSB of jump_entry::key.
This is the final step in removing the naming confusion that has led to
a stream of avoidable bugs such as:
a833581e37 ("x86, perf: Fix static_key bug in load_mm_cr4()")
... but it also allows new static key combinations that will give us
performance enhancements in the subsequent patches.
Tested-by: Rabin Vincent <rabin@rab.in> # arm
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Michael Ellerman <mpe@ellerman.id.au> # ppc
Acked-by: Heiko Carstens <heiko.carstens@de.ibm.com> # s390
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
[bwh: Backported to 3.16:
- For s390, use the 31-bit-compatible macros in arch_static_branch_jump()
-
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit 76b235c6bc upstream.
Since we've already stepped away from ENABLE is a JMP and DISABLE is a
NOP with the branch_default bits, and are going to make it even worse,
rename it to make it all clearer.
This way we don't mix multiple levels of logic attributes, but have a
plain 'physical' name for what the current instruction patching status
of a jump label is.
This is a first step in removing the naming confusion that has led to
a stream of avoidable bugs such as:
a833581e37 ("x86, perf: Fix static_key bug in load_mm_cr4()")
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
[ Beefed up the changelog. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
[bwh: Backported to 3.16: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit d5caa4dbf9 upstream.
Use a brcl 0,2 instruction for jump label nops during compile time,
so we don't mix up the different nops during mcount/hotpatch call
site detection.
The initial jump label code instruction replacement will exchange
these instructions with either a branch or a brcl 0,0 instruction.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit 5c6497c50f upstream.
Add sanity checks to verify that only expected code will be replaced.
If the code patterns do not match print the code patterns and panic,
since something went terribly wrong.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit 067bf2d4d3 upstream.
Use the more generic functions get_signal() signal_setup_done()
for signal delivery.
Signed-off-by: Richard Weinberger <richard@nod.at>
[bwh: Backported to 3.16 as dependency of commit 35634ffa17
"signal: Always notice exiting tasks"]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit b7cb707c37 upstream.
smp_rescan_cpus() is called without the device_hotplug_lock, which can lead
to a dedlock when a new CPU is found and immediately set online by a udev
rule.
This was observed on an older kernel version, where the cpu_hotplug_begin()
loop was still present, and it resulted in hanging chcpu and systemd-udev
processes. This specific deadlock will not show on current kernels. However,
there may be other possible deadlocks, and since smp_rescan_cpus() can still
trigger a CPU hotplug operation, the device_hotplug_lock should be held.
For reference, this was the deadlock with the old cpu_hotplug_begin() loop:
chcpu (rescan) systemd-udevd
echo 1 > /sys/../rescan
-> smp_rescan_cpus()
-> (*) get_online_cpus()
(increases refcount)
-> smp_add_present_cpu()
(new CPU found)
-> register_cpu()
-> device_add()
-> udev "add" event triggered -----------> udev rule sets CPU online
-> echo 1 > /sys/.../online
-> lock_device_hotplug_sysfs()
(this is missing in rescan path)
-> device_online()
-> (**) device_lock(new CPU dev)
-> cpu_up()
-> cpu_hotplug_begin()
(loops until refcount == 0)
-> deadlock with (*)
-> bus_probe_device()
-> device_attach()
-> device_lock(new CPU dev)
-> deadlock with (**)
Fix this by taking the device_hotplug_lock in the CPU rescan path.
Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit a38662084c upstream.
The ASCE of an mm_struct can be modified after a task has been created,
e.g. via crst_table_downgrade for a compat process. The active_mm logic
to avoid the switch_mm call if the next task is a kernel thread can
lead to a situation where switch_mm is called where 'prev == next' is
true but 'prev->context.asce == next->context.asce' is not.
This can lead to a situation where a CPU uses the outdated ASCE to run
a task. The result can be a crash, endless loops and really subtle
problem due to TLBs being created with an invalid ASCE.
Fixes: 53e857f308 ("s390/mm,tlb: race of lazy TLB flush vs. recreation")
Reported-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
[bwh: Backported to 3.16:
- Keep the updates of mm_context_t::attach_count conditional on prev != next
- Keep the update of mm_context_t::cpu_attach_mask conditional on both
MACHINE_HAS_TLB_LC and prev != next
- Adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit 03aa047ef2 upstream.
Right now the early machine detection code check stsi 3.2.2 for "KVM"
and set MACHINE_IS_VM if this is different. As the console detection
uses diagnose 8 if MACHINE_IS_VM returns true this will crash Linux
early for any non z/VM system that sets a different value than KVM.
So instead of assuming z/VM, do not set any of MACHINE_IS_LPAR,
MACHINE_IS_VM, or MACHINE_IS_KVM.
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
[bwh: Backported to 3.16: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit e38f978133 upstream.
For C language, it treats array parameter as a pointer, so sizeof for an
array parameter is equal to sizeof for a pointer, which causes compiler
warning (with allmodconfig by gcc 5):
./arch/s390/include/asm/timex.h: In function 'get_tod_clock_ext':
./arch/s390/include/asm/timex.h:76:32: warning: 'sizeof' on array function parameter 'clk' will return size of 'char *' [-Wsizeof-array-argument]
typedef struct { char _[sizeof(clk)]; } addrtype;
^
Can use macro CLOCK_STORE_SIZE instead of all related hard code numbers,
which also can avoid this warning. And also add a tab to CLOCK_TICK_RATE
definition to match coding styles.
[heiko.carstens@de.ibm.com]:
Chen's patch actually fixes a bug within the get_tod_clock_ext() inline assembly
where we incorrectly tell the compiler that only 8 bytes of memory get changed
instead of 16 bytes.
This would allow gcc to generate incorrect code. Right now this doesn't seem to
be the case.
Also slightly changed the patch a bit.
- renamed CLOCK_STORE_SIZE to STORE_CLOCK_EXT_SIZE
- changed get_tod_clock_ext() to receive a char pointer parameter
Signed-off-by: Chen Gang <gang.chen.5i5j@gmail.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit 866f3576a7 upstream.
During interrupt setup we allocate interrupt vectors, walk the list of msi
descriptors, and fill in the message data. Requesting more interrupts than
supported on s390 can lead to an out of bounds access.
When we restrict the number of interrupts we should also stop walking the
msi list after all supported interrupts are handled.
Signed-off-by: Sebastian Ott <sebott@linux.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit 306d6c49ac upstream.
When the oom killer kills a userspace process in the page fault handler
while in guest context, the fault handler fails to release the mm_sem
if the FAULT_FLAG_RETRY_NOWAIT option is set. This leads to a deadlock
when tearing down the mm when the process terminates. This bug can only
happen when pfault is enabled, so only KVM clients are affected.
The problem arises in the rare cases in which handle_mm_fault does not
release the mm_sem. This patch fixes the issue by manually releasing
the mm_sem when needed.
Fixes: 24eb3a824c ("KVM: s390: Add FAULT_FLAG_RETRY_NOWAIT for guest fault")
Signed-off-by: Claudio Imbrenda <imbrenda@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit 64e03ff726 upstream.
When allocating a new AOB fails, handle_outbound() is still capable of
transmitting the selected buffer (just without async completion).
But if a previous transfer on this queue slot used async completion, its
sbal_state flags field is still set to QDIO_OUTBUF_STATE_FLAG_PENDING.
So when the upper layer driver sees this stale flag, it expects an async
completion that never happens.
Fix this by unconditionally clearing the flags field.
Fixes: 104ea556ee ("qdio: support asynchronous delivery of storage blocks")
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit 77715b7ddb upstream.
The CPU Measurement sampling facility creates a trailer entry for each
Sample-Data-Block of stored samples. The trailer entry contains the sizes
(in bytes) of the stored sampling types:
- basic-sampling data entry size
- diagnostic-sampling data entry size
Both sizes are 2 bytes long.
This patch changes the trailer entry definition to reflect this.
Fixes: fcc77f5073 ("s390/cpum_sf: Atomically reset trailer entry fields of sample-data-blocks")
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit 3c0a83b14e upstream.
The s390 CPU measurement facility sampling mode supports basic entries
and diagnostic entries. Each entry has a valid bit to indicate the
status of the entry as valid or invalid.
This bit is bit 31 in the diagnostic entry, but the bit mask definition
refers to bit 30.
Fix this by making the reserved field one bit larger.
Fixes: 7e75fc3ff4 ("s390/cpum_sf: Add raw data sampling to support the diagnostic-sampling function")
Signed-off-by: Thomas Richter <tmricht@linux.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit a6e2f029ae upstream.
Added the x86 implementation of word-at-a-time to the
generic version, which previously only supported big-endian.
Omitted the x86-specific load_unaligned_zeropad(), which in
any case is also not present for the existing BE-only
implementation of a word-at-a-time, and is only used under
CONFIG_DCACHE_WORD_ACCESS.
Added as a "generic-y" to the Kbuilds of all architectures
that didn't previously have it.
Signed-off-by: Chris Metcalf <cmetcalf@ezchip.com>
[bwh: Backported to 3.16:
- Drop change in arch/nios2
- Adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit 4bbaf2584b upstream.
Correct a trinity finding for the perf_event_open() system call with
a perf event attribute structure that uses a frequency but has the
sampling frequency set to zero. This causes a FP divide exception during
the sample rate initialization for the hardware sampling facility.
Fixes: 8c069ff4bd ("s390/perf: add support for the CPU-Measurement Sampling Facility")
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Hendrik Brueckner <brueckner@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit a24cd49073 upstream.
hypfs_fill_super() might fail to allocate sbi; hypfs_kill_super()
should not oops on that.
Signed-off-by: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit 15deb080a6 upstream.
When loadparm is set in reipl parm block, the kernel should also set
DIAG308_FLAGS_LP_VALID flag.
This fixes loadparm ignoring during z/VM fcp -> ccw reipl and kvm direct
boot -> ccw reipl.
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Vasily Gorbik <gor@linux.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
[bwh: Backported to 3.16: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit 09a0fb6753 upstream.
We already count io interrupts, but we forgot to print them.
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Fixes: d8346b7d9b ("KVM: s390: Support for I/O interrupts.")
Reviewed-by: Cornelia Huck <cohuck@redhat.com>
Reviewed-by: David Hildenbrand <david@redhat.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit 6dd0d2d22a upstream.
For some reason, the implementation of some 16-bit ID system calls
(namely, setuid16/setgid16 and setfsuid16/setfsgid16) used type cast
instead of low2highgid/low2highuid macros for converting [GU]IDs, which
led to incorrect handling of value of -1 (which ought to be considered
invalid).
Discovered by strace test suite.
Signed-off-by: Eugene Syromiatnikov <esyr@redhat.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit bdcf0a423e upstream.
In testing, we found that nfsd threads may call set_groups in parallel
for the same entry cached in auth.unix.gid, racing in the call of
groups_sort, corrupting the groups for that entry and leading to
permission denials for the client.
This patch:
- Make groups_sort globally visible.
- Move the call to groups_sort to the modifiers of group_info
- Remove the call to groups_sort from set_groups
Link: http://lkml.kernel.org/r/20171211151420.18655-1-thiago.becker@gmail.com
Signed-off-by: Thiago Rafael Becker <thiago.becker@gmail.com>
Reviewed-by: Matthew Wilcox <mawilcox@microsoft.com>
Reviewed-by: NeilBrown <neilb@suse.com>
Acked-by: "J. Bruce Fields" <bfields@fieldses.org>
Cc: Al Viro <viro@zeniv.linux.org.uk>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
[bwh: Backported to 3.16: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit fbbd7f1a51 upstream.
The switch_to() macro has an optimization to avoid saving and
restoring register contents that aren't needed for kernel threads.
There is however the possibility that a kernel thread execve's a user
space program. In such a case the execve'd process can partially see
the contents of the previous process, which shouldn't be allowed.
To avoid this, simply always save and restore register contents on
context switch.
Fixes: fdb6d070ef ("switch_to: dont restore/save access & fpu regs for kernel threads")
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
[bwh: Backported to 3.16:
- The save/restore functions are different here
- FP restore is non-lazy, so drop the comment about it being lazy]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit a1c5befc1c upstream.
Dan Horák reported the following crash related to transactional execution:
User process fault: interruption code 0013 ilc:3 in libpthread-2.26.so[3ff93c00000+1b000]
CPU: 2 PID: 1 Comm: /init Not tainted 4.13.4-300.fc27.s390x #1
Hardware name: IBM 2827 H43 400 (z/VM 6.4.0)
task: 00000000fafc8000 task.stack: 00000000fafc4000
User PSW : 0705200180000000 000003ff93c14e70
R:0 T:1 IO:1 EX:1 Key:0 M:1 W:0 P:1 AS:0 CC:2 PM:0 RI:0 EA:3
User GPRS: 0000000000000077 000003ff00000000 000003ff93144d48 000003ff93144d5e
0000000000000000 0000000000000002 0000000000000000 000003ff00000000
0000000000000000 0000000000000418 0000000000000000 000003ffcc9fe770
000003ff93d28f50 000003ff9310acf0 000003ff92b0319a 000003ffcc9fe6d0
User Code: 000003ff93c14e62: 60e0b030 std %f14,48(%r11)
000003ff93c14e66: 60f0b038 std %f15,56(%r11)
#000003ff93c14e6a: e5600000ff0e tbegin 0,65294
>000003ff93c14e70: a7740006 brc 7,3ff93c14e7c
000003ff93c14e74: a7080000 lhi %r0,0
000003ff93c14e78: a7f40023 brc 15,3ff93c14ebe
000003ff93c14e7c: b2220000 ipm %r0
000003ff93c14e80: 8800001c srl %r0,28
There are several bugs with control register handling with respect to
transactional execution:
- on task switch update_per_regs() is only called if the next task has
an mm (is not a kernel thread). This however is incorrect. This
breaks e.g. for user mode helper handling, where the kernel creates
a kernel thread and then execve's a user space program. Control
register contents related to transactional execution won't be
updated on execve. If the previous task ran with transactional
execution disabled then the new task will also run with
transactional execution disabled, which is incorrect. Therefore call
update_per_regs() unconditionally within switch_to().
- on startup the transactional execution facility is not enabled for
the idle thread. This is not really a bug, but an inconsistency to
other facilities. Therefore enable the facility if it is available.
- on fork the new thread's per_flags field is not cleared. This means
that a child process inherits the PER_FLAG_NO_TE flag. This flag can
be set with a ptrace request to disable transactional execution for
the current process. It should not be inherited by new child
processes in order to be consistent with the handling of all other
PER related debugging options. Therefore clear the per_flags field in
copy_thread_tls().
Reported-and-tested-by: Dan Horák <dan@danny.cz>
Fixes: d35339a42d ("s390: add support for transactional memory")
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
Reviewed-by: Hendrik Brueckner <brueckner@linux.vnet.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
[bwh: Backported to 3.16: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit d6e646ad7c upstream.
For PREEMPT enabled kernels the runtime instrumentation (RI) code
contains a possible use-after-free bug. If a task that makes use of RI
exits, it will execute do_exit() while still enabled for preemption.
That function will call exit_thread_runtime_instr() via
exit_thread(). If exit_thread_runtime_instr() gets preempted after the
RI control block of the task has been freed but before the pointer to
it is set to NULL, then save_ri_cb(), called from switch_to(), will
write to already freed memory.
Avoid this and simply disable preemption while freeing the control
block and setting the pointer to NULL.
Fixes: e4b8b3f33f ("s390: add support for runtime instrumentation")
Reviewed-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
[bwh: Backported to 3.16: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit ba385c0594 upstream.
The check for the _SEGMENT_ENTRY_PROTECT bit in gup_huge_pmd() is the
wrong way around. It must not be set for write==1, and not be checked for
write==0. Fix this similar to how it was fixed for ptes long time ago in
commit 25591b0703 ("[S390] fix get_user_pages_fast").
One impact of this bug would be unnecessarily using the gup slow path for
write==0 on r/w mappings. A potentially more severe impact would be that
gup_huge_pmd() will succeed for write==1 on r/o mappings.
Signed-off-by: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
[bwh: Backported to 3.16: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit 60f07c8ec5 upstream.
The order in __tlb_flush_mm_lazy is to flush TLB first and then clear
the mm->context.flush_mm bit. This can lead to missed flushes as the
bit can be set anytime, the order needs to be the other way aronud.
But this leads to a different race, __tlb_flush_mm_lazy may be called
on two CPUs concurrently. If mm->context.flush_mm is cleared first then
another CPU can bypass __tlb_flush_mm_lazy although the first CPU has
not done the flush yet. In a virtualized environment the time until the
flush is finally completed can be arbitrarily long.
Add a spinlock to serialize __tlb_flush_mm_lazy and use the function
in finish_arch_post_lock_switch as well.
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
[bwh: Backported to 3.16: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit dc295880c6 upstream.
The syscall_set_return_value function of s390 negates the error argument
before storing the value to the return register gpr2. This is incorrect,
the seccomp code already passes the negative error value.
Store the unmodified error value to gpr2.
Signed-off-by: Jan Willeke <willeke@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit c46fc0424c upstream.
Zorro reported following crash while having enabled
syscall tracing (CONFIG_FTRACE_SYSCALLS):
Unable to handle kernel pointer dereference at virtual ...
Oops: 0011 [#1] SMP DEBUG_PAGEALLOC
SNIP
Call Trace:
([<000000000024d79c>] ftrace_syscall_enter+0xec/0x1d8)
[<00000000001099c6>] do_syscall_trace_enter+0x236/0x2f8
[<0000000000730f1c>] sysc_tracesys+0x1a/0x32
[<000003fffcf946a2>] 0x3fffcf946a2
INFO: lockdep is turned off.
Last Breaking-Event-Address:
[<000000000022dd44>] rb_event_data+0x34/0x40
---[ end trace 8c795f86b1b3f7b9 ]---
The crash happens in syscall_get_arguments function for
syscalls with zero arguments, that will try to access
first argument (args[0]) in event entry, but it's not
allocated.
Bail out of there are no arguments.
Reported-by: Zorro Lang <zlang@redhat.com>
Signed-off-by: Jiri Olsa <jolsa@kernel.org>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit a8f60d1fad upstream.
On heavy paging with KSM I see guest data corruption. Turns out that
KSM will add pages to its tree, where the mapping return true for
pte_unused (or might become as such later). KSM will unmap such pages
and reinstantiate with different attributes (e.g. write protected or
special, e.g. in replace_page or write_protect_page)). This uncovered
a bug in our pagetable handling: We must remove the unused flag as
soon as an entry becomes present again.
Signed-of-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
[bwh: Backported to 3.16: adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit d09c5373e8 upstream.
Commit fd2d2b191f ("s390: get_user() should zero on failure")
intended to fix s390's get_user() implementation which did not zero
the target operand if the read from user space faulted. Unfortunately
the patch has no effect: the corresponding inline assembly specifies
that the operand is only written to ("=") and the previous value is
discarded.
Therefore the compiler is free to and actually does omit the zero
initialization.
To fix this simply change the contraint modifier to "+", so the
compiler cannot omit the initialization anymore.
Fixes: c9ca78415a ("s390/uaccess: provide inline variants of get_user/put_user")
Fixes: fd2d2b191f ("s390: get_user() should zero on failure")
Cc: Al Viro <viro@zeniv.linux.org.uk>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit d82c0d12c9 upstream.
Reorder the operations in decompress_kernel() to ensure initrd is moved
to a safe location before the bss section is zeroed.
During decompression bss can overlap with the initrd and this can
corrupt the initrd contents depending on the size of the compressed
kernel (which affects where the initrd is placed by the bootloader) and
the size of the bss section of the decompressor.
Also use the correct initrd size when checking for overlaps with
parmblock.
Fixes: 06c0dd72ae ([S390] fix boot failures with compressed kernels)
Reviewed-by: Joy Latten <joy.latten@canonical.com>
Reviewed-by: Vineetha HariPai <vineetha.hari.pai@canonical.com>
Signed-off-by: Marcelo Henrique Cerri <marcelo.cerri@canonical.com>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit 2e4d88009f upstream.
While we can technically not run huge page guests right now, we can
setup a guest with huge pages. Trying to migrate it will trigger a
VM_BUG_ON and, if the kernel is not configured to panic on a BUG, it
will happily try to work on non-existing page table entries.
With this patch, we always return "dirty" if we encounter a large page
when migrating. This at least fixes the immediate problem until we
have proper handling for both kind of pages.
Fixes: 15f36eb ("KVM: s390: Add proper dirty bitmap support to S390 kvm.")
Signed-off-by: Janosch Frank <frankja@linux.vnet.ibm.com>
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
[bwh: Backported to 3.16:
- Use respectively gmap->mm, address and pte instead of mm, addr and ptep
- Adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit e1e8a9624f upstream.
User controlled KVM guests do not support the dirty log, as they have
no single gmap that we can check for changes.
As they have no single gmap, kvm->arch.gmap is NULL and all further
referencing to it for dirty checking will result in a NULL
dereference.
Let's return -EINVAL if a caller tries to sync dirty logs for a
UCONTROL guest.
Fixes: 15f36eb ("KVM: s390: Add proper dirty bitmap support to S390 kvm.")
Signed-off-by: Janosch Frank <frankja@linux.vnet.ibm.com>
Reported-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Reviewed-by: Cornelia Huck <cornelia.huck@de.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit 237d6e6884 upstream.
Since commit d86bd1bece ("mm/slub: support left redzone") it is no longer
guaranteed that kmalloc(PAGE_SIZE) returns page aligned memory.
After the above commit we get an error for diag224 because aligned
memory is required. This leads to the following user visible error:
# mount none -t s390_hypfs /sys/hypervisor/
mount: unknown filesystem type 's390_hypfs'
# dmesg | grep hypfs
hypfs.cccfb8: The hardware system does not provide all functions
required by hypfs
hypfs.7a79f0: Initialization of hypfs failed with rc=-61
Fix this problem and use get_free_page() instead of kmalloc() to get
correctly aligned memory.
Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit 68c5cf5a60 upstream.
AT_VECTOR_SIZE_ARCH should be defined with the maximum number of
NEW_AUX_ENT entries that ARCH_DLINFO can contain, but it wasn't defined
for s390 at all even though ARCH_DLINFO can contain one NEW_AUX_ENT when
VDSO is enabled.
This shouldn't be a problem as AT_VECTOR_SIZE_BASE includes space for
AT_BASE_PLATFORM which s390 doesn't use, but lets define it now and add
the comment above ARCH_DLINFO as found in several other architectures to
remind future modifiers of ARCH_DLINFO to keep AT_VECTOR_SIZE_ARCH up to
date.
Fixes: b020632e40 ("[S390] introduce vdso on s390")
Signed-off-by: James Hogan <james.hogan@imgtec.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: linux-s390@vger.kernel.org
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit f045402984 upstream.
__tlb_flush_asce() should never be used if multiple asce belong to a mm.
As this function changes mm logic determining if local or global tlb
flushes will be neded, we might end up flushing only the gmap asce on all
CPUs and a follow up mm asce flushes will only flush on the local CPU,
although that asce ran on multiple CPUs.
The missing tlb flushes will provoke strange faults in user space and even
low address protections in user space, crashing the kernel.
Fixes: 1b948d6cae ("s390/mm,tlb: optimize TLB flushing for zEC12")
Reported-by: Sascha Silbe <silbe@linux.vnet.ibm.com>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
[bwh: Backported to 3.16: adjust filename, context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit bcf4dd5f9e upstream.
The test_fp_ctl function is used to test if a given value is a valid
floating-point control. The inline assembly in test_fp_ctl uses an
incorrect constraint for the 'orig_fpc' variable. If the compiler
chooses the same register for 'fpc' and 'orig_fpc' the test_fp_ctl()
function always returns true. This allows user space to trigger
kernel oopses with invalid floating-point control values on the
signal stack.
This problem has been introduced with git commit 4725c86055
"s390: fix save and restore of the floating-point-control register"
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
[bwh: Backported to 3.16: adjust filename]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit c34a69059d upstream.
The identity mapping is suboptimal for the last 2GB frame. The mapping
will be established with a mix of 4KB and 1MB mappings instead of a
single 2GB mapping.
This happens because of a off-by-one bug introduced with
commit 50be634507 ("s390/mm: Convert bootmem to memblock").
Currently the identity mapping looks like this:
0x0000000080000000-0x0000000180000000 4G PUD RW
0x0000000180000000-0x00000001fff00000 2047M PMD RW
0x00000001fff00000-0x0000000200000000 1M PTE RW
With the bug fixed it looks like this:
0x0000000080000000-0x0000000200000000 6G PUD RW
Fixes: 50be634507 ("s390/mm: Convert bootmem to memblock")
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit 7f9be77555 upstream.
On s390 we only can enable hugepages if the underlying hardware/hypervisor
also does support this. Common code now would assume this to be
signaled by setting HPAGE_SHIFT to 0. But on s390, where we only
support one hugepage size, there is a link between HPAGE_SHIFT and
pageblock_order.
So instead of setting HPAGE_SHIFT to 0, we will implement the check for
the hardware capability.
Signed-off-by: Dominik Dingel <dingel@linux.vnet.ibm.com>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Cc: Gerald Schaefer <gerald.schaefer@de.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit 8497695243 upstream.
arch_spin_lock_wait_flags() checks if a spinlock is not held before
trying a compare and swap instruction. If the lock is unlocked it
tries the compare and swap instruction, however if a different cpu
grabbed the lock in the meantime the instruction will fail as
expected.
Subsequently the arch_spin_lock_wait_flags() incorrectly tries to
figure out if the cpu that holds the lock is running. However it is
using the wrong cpu number for this (-1) and then will also yield the
current cpu to the wrong cpu.
Fix this by adding a missing continue statement.
Fixes: 470ada6b1a ("s390/spinlock: refactor arch_spin_lock_wait[_flags]")
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Acked-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit 3446c13b26 upstream.
The fork of a process with four page table levels is broken since
git commit 6252d702c5 "[S390] dynamic page tables."
All new mm contexts are created with three page table levels and
an asce limit of 4TB. If the parent has four levels dup_mmap will
add vmas to the new context which are outside of the asce limit.
The subsequent call to copy_page_range will walk the three level
page table structure of the new process with non-zero pgd and pud
indexes. This leads to memory clobbers as the pgd_index *and* the
pud_index is added to the mm->pgd pointer without a pgd_deref
in between.
The init_new_context() function is selecting the number of page
table levels for a new context. The function is used by mm_init()
which in turn is called by dup_mm() and mm_alloc(). These two are
used by fork() and exec(). The init_new_context() function can
distinguish the two cases by looking at mm->context.asce_limit,
for fork() the mm struct has been copied and the number of page
table levels may not change. For exec() the mm_alloc() function
set the new mm structure to zero, in this case a three-level page
table is created as the temporary stack space is located at
STACK_TOP_MAX = 4TB.
This fixes CVE-2016-2143.
Reported-by: Marcin Kościelnicki <koriakin@0x04.net>
Reviewed-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
[bwh: Backported to 3.16:
- 31-bit s390 is still supported so keep the #ifdef CONFIG_64BIT conditions
- PMDs are not accounted so don't call mm_inc_nr_pmds()
- Adjust context]
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit 80c544ded2 upstream.
The function measurement block must not cross a page boundary. Ensure
that by raising the alignment requirement to the smallest power of 2
larger than the size of the fmb.
Fixes: d0b088531 ("s390/pci: performance statistics and debug infrastructure")
Signed-off-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit 6001018ae8 upstream.
The software counters are not a part of the function measurement
block. Also we do not check for zdev->fmb != NULL when using these
counters (function measurement can be toggled at runtime). Just move
the software counters to struct zpci_dev.
Signed-off-by: Sebastian Ott <sebott@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
commit bcb7825a77 upstream.
The normalization pass in the sorting routine of the relative exception
table serves two purposes:
- it ensures that the address fields of the exception table entries are
fully ordered, so that no ambiguities arise between entries with
identical instruction offsets (i.e., when two instructions that are
exactly 8 bytes apart each have an exception table entry associated with
them)
- it ensures that the offsets of both the instruction and the fixup fields
of each entry are relative to their final location after sorting.
Commit eb608fb366 ("s390/exceptions: switch to relative exception table
entries") ported the relative exception table format from x86, but modified
the sorting routine to only normalize the instruction offset field and not
the fixup offset field. The result is that the fixup offset of each entry
will be relative to the original location of the entry before sorting,
likely leading to crashes when those entries are dereferenced.
Fixes: eb608fb366 ("s390/exceptions: switch to relative exception table entries")
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
commit 272fa59ccb upstream.
The print_insn() function returns strings like "lghi %r1,0". To escape the
'%' character in sprintf() a second '%' is used. For example "lghi %%r1,0"
is converted into "lghi %r1,0".
After print_insn() the output string is passed to printk(). Because format
specifiers like "%r" or "%f" are ignored by printk() this works by chance
most of the time. But for instructions with control registers like
"lctl %c6,%c6,780" this fails because printk() interprets "%c" as
character format specifier.
Fix this problem and escape the '%' characters twice.
For example "lctl %%%%c6,%%%%c6,780" is then converted by sprintf()
into "lctl %%c6,%%c6,780" and by printk() into "lctl %c6,%c6,780".
Signed-off-by: Michael Holzheu <holzheu@linux.vnet.ibm.com>
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
[ luis: backported to 3.16:
- drop condition with OPERAND_VR introduced only with commit
3585cb0280 ("s390/disassembler: add vector instructions") ]
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
commit c5c2c39346 upstream.
We seemed to have missed a few corner cases in commit f6c137ff00
("KVM: s390: randomize sca address").
The SCA has a maximum size of 2112 bytes. By setting the sca_offset to
some unlucky numbers, we exceed the page.
0x7c0 (1984) -> Fits exactly
0x7d0 (2000) -> 16 bytes out
0x7e0 (2016) -> 32 bytes out
0x7f0 (2032) -> 48 bytes out
One VCPU entry is 32 bytes long.
For the last two cases, we actually write data to the other page.
1. The address of the VCPU.
2. Injection/delivery/clearing of SIGP externall calls via SIGP IF.
Especially the 2. happens regularly. So this could produce two problems:
1. The guest losing/getting external calls.
2. Random memory overwrites in the host.
So this problem happens on every 127 + 128 created VM with 64 VCPUs.
Acked-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: David Hildenbrand <dahi@linux.vnet.ibm.com>
Signed-off-by: Christian Borntraeger <borntraeger@de.ibm.com>
Signed-off-by: Luis Henriques <luis.henriques@canonical.com>
