The per-cpu preempt count of x86 contains two values, the actual preempt
count and the inverted PREEMPT_NEED_RESCHED bit. If a corrupted preempt
count is detected the preempt_count_set() function is used to reset the
preempt count.
In case the inverted PREEMPT_NEED_RESCHED bit is zero at the time of the
reset, the preemption indication is lost. Use raw_cpu_cmpxchg_4() to reset
only the count part and leave the PREEMPT_NEED_RESCHED bit as it is.
This improves the kernel's behavior when it runs into preempt count leaks
and tries to fix them up.
Signed-off-by: Martin Schwidefsky <schwidefsky@de.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1478523660-733-1-git-send-email-schwidefsky@de.ibm.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Change the lexical defintion of the GEN_*_RMWcc() macros to not take
the condition code as a quoted string. This will help support
changing them to use the new __GCC_ASM_FLAG_OUTPUTS__ feature in a
subsequent patch.
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Link: http://lkml.kernel.org/r/1465414726-197858-4-git-send-email-hpa@linux.intel.com
Reviewed-by: Andy Lutomirski <luto@kernel.org>
Reviewed-by: Borislav Petkov <bp@suse.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
If __preempt_schedule() or __preempt_schedule_notrace() is referenced at
the beginning of a function, gcc can insert the asm inline "call
___preempt_schedule[_notrace]" instruction before setting up a stack
frame, which breaks frame pointer convention if CONFIG_FRAME_POINTER is
enabled and can result in bad stack traces.
Force a stack frame to be created if CONFIG_FRAME_POINTER is enabled by
listing the stack pointer as an output operand for the inline asm
statements.
Specifically this fixes the following stacktool warnings:
stacktool: drivers/scsi/hpsa.o: hpsa_scsi_do_simple_cmd.constprop.106()+0x79: call without frame pointer save/setup
stacktool: fs/mbcache.o: mb_cache_entry_find_first()+0x70: call without frame pointer save/setup
stacktool: fs/mbcache.o: mb_cache_entry_find_first()+0x92: call without frame pointer save/setup
stacktool: fs/mbcache.o: mb_cache_entry_free()+0xff: call without frame pointer save/setup
stacktool: fs/mbcache.o: mb_cache_entry_free()+0xf5: call without frame pointer save/setup
stacktool: fs/mbcache.o: mb_cache_entry_free()+0x11a: call without frame pointer save/setup
stacktool: fs/mbcache.o: mb_cache_entry_get()+0x225: call without frame pointer save/setup
stacktool: kernel/locking/percpu-rwsem.o: percpu_up_read()+0x27: call without frame pointer save/setup
stacktool: kernel/profile.o: do_profile_hits.isra.5()+0x139: call without frame pointer save/setup
stacktool: lib/nmi_backtrace.o: nmi_trigger_all_cpu_backtrace()+0x2b6: call without frame pointer save/setup
stacktool: net/rds/ib_cm.o: rds_ib_cq_comp_handler_recv()+0x58: call without frame pointer save/setup
stacktool: net/rds/ib_cm.o: rds_ib_cq_comp_handler_send()+0x58: call without frame pointer save/setup
stacktool: net/rds/ib_recv.o: rds_ib_attempt_ack()+0xc1: call without frame pointer save/setup
stacktool: net/rds/iw_recv.o: rds_iw_attempt_ack()+0xc1: call without frame pointer save/setup
stacktool: net/rds/iw_recv.o: rds_iw_recv_cq_comp_handler()+0x55: call without frame pointer save/setup
So it only adds a stack frame to 15 call sites out of ~5000 calls to
___preempt_schedule[_notrace](). All the others already had stack frames.
Oddly, this change actually seems to make things faster in a lot of
cases. For many smaller functions it causes the stack frame creation to
get moved out of the common path and into the unlikely path.
For example, here's the original cyc2ns_read_end():
ffffffff8101f8c0 <cyc2ns_read_end>:
ffffffff8101f8c0: 55 push %rbp
ffffffff8101f8c1: 48 89 e5 mov %rsp,%rbp
ffffffff8101f8c4: 83 6f 10 01 subl $0x1,0x10(%rdi)
ffffffff8101f8c8: 75 08 jne ffffffff8101f8d2 <cyc2ns_read_end+0x12>
ffffffff8101f8ca: 65 48 89 3d e6 5a ff mov %rdi,%gs:0x7eff5ae6(%rip) # 153b8 <cyc2ns+0x38>
ffffffff8101f8d1: 7e
ffffffff8101f8d2: 65 ff 0d 77 c4 fe 7e decl %gs:0x7efec477(%rip) # bd50 <__preempt_count>
ffffffff8101f8d9: 74 02 je ffffffff8101f8dd <cyc2ns_read_end+0x1d>
ffffffff8101f8db: 5d pop %rbp
ffffffff8101f8dc: c3 retq
ffffffff8101f8dd: e8 1e 37 fe ff callq ffffffff81003000 <___preempt_schedule>
ffffffff8101f8e2: 5d pop %rbp
ffffffff8101f8e3: c3 retq
ffffffff8101f8e4: 66 66 66 2e 0f 1f 84 data16 data16 nopw %cs:0x0(%rax,%rax,1)
ffffffff8101f8eb: 00 00 00 00 00
And here's the same function with the patch:
ffffffff8101f8c0 <cyc2ns_read_end>:
ffffffff8101f8c0: 83 6f 10 01 subl $0x1,0x10(%rdi)
ffffffff8101f8c4: 75 08 jne ffffffff8101f8ce <cyc2ns_read_end+0xe>
ffffffff8101f8c6: 65 48 89 3d ea 5a ff mov %rdi,%gs:0x7eff5aea(%rip) # 153b8 <cyc2ns+0x38>
ffffffff8101f8cd: 7e
ffffffff8101f8ce: 65 ff 0d 7b c4 fe 7e decl %gs:0x7efec47b(%rip) # bd50 <__preempt_count>
ffffffff8101f8d5: 74 01 je ffffffff8101f8d8 <cyc2ns_read_end+0x18>
ffffffff8101f8d7: c3 retq
ffffffff8101f8d8: 55 push %rbp
ffffffff8101f8d9: 48 89 e5 mov %rsp,%rbp
ffffffff8101f8dc: e8 1f 37 fe ff callq ffffffff81003000 <___preempt_schedule>
ffffffff8101f8e1: 5d pop %rbp
ffffffff8101f8e2: c3 retq
ffffffff8101f8e3: 66 66 66 66 2e 0f 1f data16 data16 data16 nopw %cs:0x0(%rax,%rax,1)
ffffffff8101f8ea: 84 00 00 00 00 00
Notice that it moved the frame pointer setup code to the unlikely
___preempt_schedule() call path. Going through a sampling of the
differences in the asm, that's the most common change I see.
Otherwise it has no real effect on callers which already have stack
frames (though it does result in the reordering of some 'mov's).
Reported-by: Jiri Slaby <jslaby@suse.cz>
Tested-by: Jiri Slaby <jslaby@suse.cz>
Signed-off-by: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: live-patching@vger.kernel.org
Link: http://lkml.kernel.org/r/20160218174158.GA28230@treble.redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
With the introduction of the context switch preempt_count invariant,
and the demise of PREEMPT_ACTIVE, its pointless to save/restore the
per-cpu preemption count, it must always be 2.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Assuming units of PREEMPT_DISABLE_OFFSET for preempt_count() numbers.
Now that TASK_DEAD no longer results in preempt_count() == 3 during
scheduling, we will always call context_switch() with preempt_count()
== 2.
However, we don't always end up with preempt_count() == 2 in
finish_task_switch() because new tasks get created with
preempt_count() == 1.
Create FORK_PREEMPT_COUNT and set it to 2 and use that in the right
places. Note that we cannot use INIT_PREEMPT_COUNT as that serves
another purpose (boot).
After this, preempt_count() is invariant across the context switch,
with exception of PREEMPT_ACTIVE.
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
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>
preempt_schedule_context() is a tracing safe preemption point but it's
only used when CONFIG_CONTEXT_TRACKING=y. Other configs have tracing
recursion issues since commit:
b30f0e3ffe ("sched/preempt: Optimize preemption operations on __schedule() callers")
introduced function based preemp_count_*() ops.
Lets make it available on all configs and give it a more appropriate
name for its new position.
Reported-by: Fengguang Wu <fengguang.wu@intel.com>
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: H. Peter Anvin <hpa@zytor.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1433432349-1021-3-git-send-email-fweisbec@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
task_preempt_count() is pointless if preemption counter is per-cpu,
currently this is x86 only. It is only valid if the task is not
running, and even in this case the only info it can provide is the
state of PREEMPT_ACTIVE bit.
Change its single caller to check p->on_rq instead, this should be
the same if p->state != TASK_RUNNING, and kill this helper.
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Kirill Tkhai <tkhai@yandex.ru>
Cc: Alexander Graf <agraf@suse.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Christoph Lameter <cl@linux.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: linux-arch@vger.kernel.org
Link: http://lkml.kernel.org/r/20141008183348.GC17495@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
preempt_schedule_context() does preempt_enable_notrace() at the end
and this can call the same function again; exception_exit() is heavy
and it is quite possible that need-resched is true again.
1. Change this code to dec preempt_count() and check need_resched()
by hand.
2. As Linus suggested, we can use the PREEMPT_ACTIVE bit and avoid
the enable/disable dance around __schedule(). But in this case
we need to move into sched/core.c.
3. Cosmetic, but x86 forgets to declare this function. This doesn't
really matter because it is only called by asm helpers, still it
make sense to add the declaration into asm/preempt.h to match
preempt_schedule().
Reported-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Oleg Nesterov <oleg@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Alexander Graf <agraf@suse.de>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Anvin <hpa@zytor.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Chuck Ebbert <cebbert.lkml@gmail.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Link: http://lkml.kernel.org/r/20141005202322.GB27962@redhat.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The kernel has never been audited to ensure that this_cpu operations are
consistently used throughout the kernel. The code generated in many
places can be improved through the use of this_cpu operations (which
uses a segment register for relocation of per cpu offsets instead of
performing address calculations).
The patch set also addresses various consistency issues in general with
the per cpu macros.
A. The semantics of __this_cpu_ptr() differs from this_cpu_ptr only
because checks are skipped. This is typically shown through a raw_
prefix. So this patch set changes the places where __this_cpu_ptr()
is used to raw_cpu_ptr().
B. There has been the long term wish by some that __this_cpu operations
would check for preemption. However, there are cases where preemption
checks need to be skipped. This patch set adds raw_cpu operations that
do not check for preemption and then adds preemption checks to the
__this_cpu operations.
C. The use of __get_cpu_var is always a reference to a percpu variable
that can also be handled via a this_cpu operation. This patch set
replaces all uses of __get_cpu_var with this_cpu operations.
D. We can then use this_cpu RMW operations in various places replacing
sequences of instructions by a single one.
E. The use of this_cpu operations throughout will allow other arches than
x86 to implement optimized references and RMV operations to work with
per cpu local data.
F. The use of this_cpu operations opens up the possibility to
further optimize code that relies on synchronization through
per cpu data.
The patch set works in a couple of stages:
I. Patch 1 adds the additional raw_cpu operations and raw_cpu_ptr().
Also converts the existing __this_cpu_xx_# primitive in the x86
code to raw_cpu_xx_#.
II. Patch 2-4 use the raw_cpu operations in places that would give
us false positives once they are enabled.
III. Patch 5 adds preemption checks to __this_cpu operations to allow
checking if preemption is properly disabled when these functions
are used.
IV. Patches 6-20 are patches that simply replace uses of __get_cpu_var
with this_cpu_ptr. They do not depend on any changes to the percpu
code. No preemption tests are skipped if they are applied.
V. Patches 21-46 are conversion patches that use this_cpu operations
in various kernel subsystems/drivers or arch code.
VI. Patches 47/48 (not included in this series) remove no longer used
functions (__this_cpu_ptr and __get_cpu_var). These should only be
applied after all the conversion patches have made it and after we
have done additional passes through the kernel to ensure that none of
the uses of these functions remain.
This patch (of 46):
The patches following this one will add preemption checks to __this_cpu
ops so we need to have an alternative way to use this_cpu operations
without preemption checks.
raw_cpu_ops will be the basis for all other ops since these will be the
operations that do not implement any checks.
Primitive operations are renamed by this patch from __this_cpu_xxx to
raw_cpu_xxxx.
Also change the uses of the x86 percpu primitives in preempt.h.
These depend directly on asm/percpu.h (header #include nesting issue).
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Christoph Lameter <cl@linux.com>
Acked-by: Ingo Molnar <mingo@kernel.org>
Cc: Tejun Heo <tj@kernel.org>
Cc: "James E.J. Bottomley" <jejb@parisc-linux.org>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Alex Shi <alex.shi@intel.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Bryan Wu <cooloney@gmail.com>
Cc: Catalin Marinas <catalin.marinas@arm.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Daniel Lezcano <daniel.lezcano@linaro.org>
Cc: David Daney <david.daney@cavium.com>
Cc: David Miller <davem@davemloft.net>
Cc: David S. Miller <davem@davemloft.net>
Cc: Dimitri Sivanich <sivanich@sgi.com>
Cc: Dipankar Sarma <dipankar@in.ibm.com>
Cc: Eric Dumazet <edumazet@google.com>
Cc: Fenghua Yu <fenghua.yu@intel.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: H. Peter Anvin <hpa@linux.intel.com>
Cc: Haavard Skinnemoen <hskinnemoen@gmail.com>
Cc: Hans-Christian Egtvedt <egtvedt@samfundet.no>
Cc: Hedi Berriche <hedi@sgi.com>
Cc: Heiko Carstens <heiko.carstens@de.ibm.com>
Cc: Helge Deller <deller@gmx.de>
Cc: Ivan Kokshaysky <ink@jurassic.park.msu.ru>
Cc: James Hogan <james.hogan@imgtec.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: John Stultz <john.stultz@linaro.org>
Cc: Martin Schwidefsky <schwidefsky@de.ibm.com>
Cc: Masami Hiramatsu <masami.hiramatsu.pt@hitachi.com>
Cc: Matt Turner <mattst88@gmail.com>
Cc: Mike Frysinger <vapier@gentoo.org>
Cc: Mike Travis <travis@sgi.com>
Cc: Neil Brown <neilb@suse.de>
Cc: Nicolas Pitre <nicolas.pitre@linaro.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Mundt <lethal@linux-sh.org>
Cc: Rafael J. Wysocki <rjw@sisk.pl>
Cc: Ralf Baechle <ralf@linux-mips.org>
Cc: Richard Henderson <rth@twiddle.net>
Cc: Robert Richter <rric@kernel.org>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Russell King <rmk+kernel@arm.linux.org.uk>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Wim Van Sebroeck <wim@iguana.be>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
While hunting a preemption issue with Alexander, Ben noticed that the
currently generic PREEMPT_NEED_RESCHED stuff is horribly broken for
load-store architectures.
We currently rely on the IPI to fold TIF_NEED_RESCHED into
PREEMPT_NEED_RESCHED, but when this IPI lands while we already have
a load for the preempt-count but before the store, the store will erase
the PREEMPT_NEED_RESCHED change.
The current preempt-count only works on load-store archs because
interrupts are assumed to be completely balanced wrt their preempt_count
fiddling; the previous preempt_count load will match the preempt_count
state after the interrupt and therefore nothing gets lost.
This patch removes the PREEMPT_NEED_RESCHED usage from generic code and
pushes it into x86 arch code; the generic code goes back to relying on
TIF_NEED_RESCHED.
Boot tested on x86_64 and compile tested on ppc64.
Reported-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Reported-and-Tested-by: Alexander Graf <agraf@suse.de>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20131128132641.GP10022@twins.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Yuanhan reported a serious throughput regression in his pigz
benchmark. Using the ftrace patch I found that several idle
paths need more TLC before we can switch the generic
need_resched() over to preempt_need_resched.
The preemption paths benefit most from preempt_need_resched and
do indeed use it; all other need_resched() users don't really
care that much so reverting need_resched() back to
tif_need_resched() is the simple and safe solution.
Reported-by: Yuanhan Liu <yuanhan.liu@linux.intel.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Fengguang Wu <fengguang.wu@intel.com>
Cc: Huang Ying <ying.huang@intel.com>
Cc: lkp@linux.intel.com
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Link: http://lkml.kernel.org/r/20130927153003.GF15690@laptop.programming.kicks-ass.net
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Remove the bloat of the C calling convention out of the
preempt_enable() sites by creating an ASM wrapper which allows us to
do an asm("call ___preempt_schedule") instead.
calling.h bits by Andi Kleen
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-tk7xdi1cvvxewixzke8t8le1@git.kernel.org
[ Fixed build error. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Convert x86 to use a per-cpu preemption count. The reason for doing so
is that accessing per-cpu variables is a lot cheaper than accessing
thread_info variables.
We still need to save/restore the actual preemption count due to
PREEMPT_ACTIVE so we place the per-cpu __preempt_count variable in the
same cache-line as the other hot __switch_to() variables such as
current_task.
NOTE: this save/restore is required even for !PREEMPT kernels as
cond_resched() also relies on preempt_count's PREEMPT_ACTIVE to ignore
task_struct::state.
Also rename thread_info::preempt_count to ensure nobody is
'accidentally' still poking at it.
Suggested-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/n/tip-gzn5rfsf8trgjoqx8hyayy3q@git.kernel.org
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Martin Schwidefsky