Pull block IO core updates from Jens Axboe:
"This is the pull request for the core changes in the block layer for
3.13. It contains:
- The new blk-mq request interface.
This is a new and more scalable queueing model that marries the
best part of the request based interface we currently have (which
is fully featured, but scales poorly) and the bio based "interface"
which the new drivers for high IOPS devices end up using because
it's much faster than the request based one.
The bio interface has no block layer support, since it taps into
the stack much earlier. This means that drivers end up having to
implement a lot of functionality on their own, like tagging,
timeout handling, requeue, etc. The blk-mq interface provides all
these. Some drivers even provide a switch to select bio or rq and
has code to handle both, since things like merging only works in
the rq model and hence is faster for some workloads. This is a
huge mess. Conversion of these drivers nets us a substantial code
reduction. Initial results on converting SCSI to this model even
shows an 8x improvement on single queue devices. So while the
model was intended to work on the newer multiqueue devices, it has
substantial improvements for "classic" hardware as well. This code
has gone through extensive testing and development, it's now ready
to go. A pull request is coming to convert virtio-blk to this
model will be will be coming as well, with more drivers scheduled
for 3.14 conversion.
- Two blktrace fixes from Jan and Chen Gang.
- A plug merge fix from Alireza Haghdoost.
- Conversion of __get_cpu_var() from Christoph Lameter.
- Fix for sector_div() with 64-bit divider from Geert Uytterhoeven.
- A fix for a race between request completion and the timeout
handling from Jeff Moyer. This is what caused the merge conflict
with blk-mq/core, in case you are looking at that.
- A dm stacking fix from Mike Snitzer.
- A code consolidation fix and duplicated code removal from Kent
Overstreet.
- A handful of block bug fixes from Mikulas Patocka, fixing a loop
crash and memory corruption on blk cg.
- Elevator switch bug fix from Tomoki Sekiyama.
A heads-up that I had to rebase this branch. Initially the immutable
bio_vecs had been queued up for inclusion, but a week later, it became
clear that it wasn't fully cooked yet. So the decision was made to
pull this out and postpone it until 3.14. It was a straight forward
rebase, just pruning out the immutable series and the later fixes of
problems with it. The rest of the patches applied directly and no
further changes were made"
* 'for-3.13/core' of git://git.kernel.dk/linux-block: (31 commits)
block: replace IS_ERR and PTR_ERR with PTR_ERR_OR_ZERO
block: replace IS_ERR and PTR_ERR with PTR_ERR_OR_ZERO
block: Do not call sector_div() with a 64-bit divisor
kernel: trace: blktrace: remove redundent memcpy() in compat_blk_trace_setup()
block: Consolidate duplicated bio_trim() implementations
block: Use rw_copy_check_uvector()
block: Enable sysfs nomerge control for I/O requests in the plug list
block: properly stack underlying max_segment_size to DM device
elevator: acquire q->sysfs_lock in elevator_change()
elevator: Fix a race in elevator switching and md device initialization
block: Replace __get_cpu_var uses
bdi: test bdi_init failure
block: fix a probe argument to blk_register_region
loop: fix crash if blk_alloc_queue fails
blk-core: Fix memory corruption if blkcg_init_queue fails
block: fix race between request completion and timeout handling
blktrace: Send BLK_TN_PROCESS events to all running traces
blk-mq: don't disallow request merges for req->special being set
blk-mq: mq plug list breakage
blk-mq: fix for flush deadlock
...
blk-mq reuses the request potentially immediately, since the most
cache hot is always given out first. This means that rq->csd could
be reused between csd->func() being called and csd_unlock() being
called. This isn't a problem, since we never use wait == 1 for
the smp call function. Add CSD_FLAG_WAIT to be able to tell the
difference, retaining the warning for other cases.
Cc: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
The blk-mq core and the blk-mq null driver uses it.
Reviewed-by: Christoph Hellwig <hch@lst.de>
Acked-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Jens Axboe <axboe@kernel.dk>
As in commit f21afc25f9 ("smp.h: Use local_irq_{save,restore}() in
!SMP version of on_each_cpu()"), we don't want to enable irqs if they
are not already enabled.
I don't know of any bugs currently caused by this unconditional
local_irq_enable(), but I want to use this function in MIPS/OCTEON early
boot (when we have early_boot_irqs_disabled). This also makes this
function have similar semantics to on_each_cpu() which is good in
itself.
Signed-off-by: David Daney <david.daney@cavium.com>
Cc: Gilad Ben-Yossef <gilad@benyossef.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When failure occurs in hotplug_cfd(), need release related resources, or
will cause memory leak.
Signed-off-by: Chen Gang <gang.chen@asianux.com>
Acked-by: Wang YanQing <udknight@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Pull scheduler changes from Ingo Molnar:
"Various optimizations, cleanups and smaller fixes - no major changes
in scheduler behavior"
* 'sched-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
sched/fair: Fix the sd_parent_degenerate() code
sched/fair: Rework and comment the group_imb code
sched/fair: Optimize find_busiest_queue()
sched/fair: Make group power more consistent
sched/fair: Remove duplicate load_per_task computations
sched/fair: Shrink sg_lb_stats and play memset games
sched: Clean-up struct sd_lb_stat
sched: Factor out code to should_we_balance()
sched: Remove one division operation in find_busiest_queue()
sched/cputime: Use this_cpu_add() in task_group_account_field()
cpumask: Fix cpumask leak in partition_sched_domains()
sched/x86: Optimize switch_mm() for multi-threaded workloads
generic-ipi: Kill unnecessary variable - csd_flags
numa: Mark __node_set() as __always_inline
sched/fair: Cleanup: remove duplicate variable declaration
sched/__wake_up_sync_key(): Fix nr_exclusive tasks which lead to WF_SYNC clearing
After commit 8969a5ede0
("generic-ipi: remove kmalloc()"), wait = 0 can be guaranteed,
and all callsites of generic_exec_single() do an unconditional
csd_lock() now.
So csd_flags is unnecessary now. Remove it.
Signed-off-by: Xie XiuQi <xiexiuqi@huawei.com>
Signed-off-by: Peter Zijlstra <peterz@infradead.org>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Link: http://lkml.kernel.org/r/51F72DA1.7010401@huawei.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The __cpuinit type of throwaway sections might have made sense
some time ago when RAM was more constrained, but now the savings
do not offset the cost and complications. For example, the fix in
commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time")
is a good example of the nasty type of bugs that can be created
with improper use of the various __init prefixes.
After a discussion on LKML[1] it was decided that cpuinit should go
the way of devinit and be phased out. Once all the users are gone,
we can then finally remove the macros themselves from linux/init.h.
This removes all the uses of the __cpuinit macros from C files in
the core kernel directories (kernel, init, lib, mm, and include)
that don't really have a specific maintainer.
[1] https://lkml.org/lkml/2013/5/20/589
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
We sometimes use "struct call_single_data *data" and sometimes "struct
call_single_data *csd". Use "csd" consistently.
We sometimes use "struct call_function_data *data" and sometimes "struct
call_function_data *cfd". Use "cfd" consistently.
Also, avoid some 80-col layout tricks.
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Shaohua Li <shli@fusionio.com>
Cc: Shaohua Li <shli@kernel.org>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
csd_lock() uses assignment to data->flags rather than |=. That is not
buggy at present because only one bit (CSD_FLAG_LOCK) is defined in
call_single_data.flags.
But it will become buggy if we later add another flag, so fix it now.
Signed-off-by: liguang <lig.fnst@cn.fujitsu.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
I'm testing swapout workload in a two-socket Xeon machine. The workload
has 10 threads, each thread sequentially accesses separate memory
region. TLB flush overhead is very big in the workload. For each page,
page reclaim need move it from active lru list and then unmap it. Both
need a TLB flush. And this is a multthread workload, TLB flush happens
in 10 CPUs. In X86, TLB flush uses generic smp_call)function. So this
workload stress smp_call_function_many heavily.
Without patch, perf shows:
+ 24.49% [k] generic_smp_call_function_interrupt
- 21.72% [k] _raw_spin_lock
- _raw_spin_lock
+ 79.80% __page_check_address
+ 6.42% generic_smp_call_function_interrupt
+ 3.31% get_swap_page
+ 2.37% free_pcppages_bulk
+ 1.75% handle_pte_fault
+ 1.54% put_super
+ 1.41% grab_super_passive
+ 1.36% __swap_duplicate
+ 0.68% blk_flush_plug_list
+ 0.62% swap_info_get
+ 6.55% [k] flush_tlb_func
+ 6.46% [k] smp_call_function_many
+ 5.09% [k] call_function_interrupt
+ 4.75% [k] default_send_IPI_mask_sequence_phys
+ 2.18% [k] find_next_bit
swapout throughput is around 1300M/s.
With the patch, perf shows:
- 27.23% [k] _raw_spin_lock
- _raw_spin_lock
+ 80.53% __page_check_address
+ 8.39% generic_smp_call_function_single_interrupt
+ 2.44% get_swap_page
+ 1.76% free_pcppages_bulk
+ 1.40% handle_pte_fault
+ 1.15% __swap_duplicate
+ 1.05% put_super
+ 0.98% grab_super_passive
+ 0.86% blk_flush_plug_list
+ 0.57% swap_info_get
+ 8.25% [k] default_send_IPI_mask_sequence_phys
+ 7.55% [k] call_function_interrupt
+ 7.47% [k] smp_call_function_many
+ 7.25% [k] flush_tlb_func
+ 3.81% [k] _raw_spin_lock_irqsave
+ 3.78% [k] generic_smp_call_function_single_interrupt
swapout throughput is around 1400M/s. So there is around a 7%
improvement, and total cpu utilization doesn't change.
Without the patch, cfd_data is shared by all CPUs.
generic_smp_call_function_interrupt does read/write cfd_data several times
which will create a lot of cache ping-pong. With the patch, the data
becomes per-cpu. The ping-pong is avoided. And from the perf data, this
doesn't make call_single_queue lock contend.
Next step is to remove generic_smp_call_function_interrupt() from arch
code.
Signed-off-by: Shaohua Li <shli@fusionio.com>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
I get the following warning every day with v3.7, once or
twice a day:
[ 2235.186027] WARNING: at /mnt/sda7/kernel/linux/arch/x86/kernel/apic/ipi.c:109 default_send_IPI_mask_logical+0x2f/0xb8()
As explained by Linus as well:
|
| Once we've done the "list_add_rcu()" to add it to the
| queue, we can have (another) IPI to the target CPU that can
| now see it and clear the mask.
|
| So by the time we get to actually send the IPI, the mask might
| have been cleared by another IPI.
|
This patch also fixes a system hang problem, if the data->cpumask
gets cleared after passing this point:
if (WARN_ONCE(!mask, "empty IPI mask"))
return;
then the problem in commit 83d349f35e ("x86: don't send an IPI to
the empty set of CPU's") will happen again.
Signed-off-by: Wang YanQing <udknight@gmail.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Acked-by: Jan Beulich <jbeulich@suse.com>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: peterz@infradead.org
Cc: mina86@mina86.org
Cc: srivatsa.bhat@linux.vnet.ibm.com
Cc: <stable@kernel.org>
Link: http://lkml.kernel.org/r/20130126075357.GA3205@udknight
[ Tidied up the changelog and the comment in the code. ]
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Will replace the misnomed cpu_idle_wait() function which is copied a
gazillion times all over arch/*
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Link: http://lkml.kernel.org/r/20120507175652.049316594@linutronix.de
percpu areas are already allocated during boot for each possible cpu.
percpu idle threads can be considered as an extension of the percpu areas,
and allocate them for each possible cpu during boot.
This will eliminate the need for workqueue based idle thread allocation.
In future we can move the idle thread area into the percpu area too.
[ tglx: Moved the loop into smpboot.c and added an error check when
the init code failed to allocate an idle thread for a cpu which
should be onlined ]
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: venki@google.com
Link: http://lkml.kernel.org/r/1334966930.28674.245.camel@sbsiddha-desk.sc.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Add the on_each_cpu_cond() function that wraps on_each_cpu_mask() and
calculates the cpumask of cpus to IPI by calling a function supplied as a
parameter in order to determine whether to IPI each specific cpu.
The function works around allocation failure of cpumask variable in
CONFIG_CPUMASK_OFFSTACK=y by itereating over cpus sending an IPI a time
via smp_call_function_single().
The function is useful since it allows to seperate the specific code that
decided in each case whether to IPI a specific cpu for a specific request
from the common boilerplate code of handling creating the mask, handling
failures etc.
[akpm@linux-foundation.org: s/gfpflags/gfp_flags/]
[akpm@linux-foundation.org: avoid double-evaluation of `info' (per Michal), parenthesise evaluation of `cond_func']
[akpm@linux-foundation.org: s/CPU/CPUs, use all 80 cols in comment]
Signed-off-by: Gilad Ben-Yossef <gilad@benyossef.com>
Cc: Chris Metcalf <cmetcalf@tilera.com>
Cc: Christoph Lameter <cl@linux-foundation.org>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Sasha Levin <levinsasha928@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Avi Kivity <avi@redhat.com>
Acked-by: Michal Nazarewicz <mina86@mina86.org>
Cc: Kosaki Motohiro <kosaki.motohiro@gmail.com>
Cc: Milton Miller <miltonm@bga.com>
Reviewed-by: "Srivatsa S. Bhat" <srivatsa.bhat@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We have lots of infrastructure in place to partition multi-core systems
such that we have a group of CPUs that are dedicated to specific task:
cgroups, scheduler and interrupt affinity, and cpuisol= boot parameter.
Still, kernel code will at times interrupt all CPUs in the system via IPIs
for various needs. These IPIs are useful and cannot be avoided
altogether, but in certain cases it is possible to interrupt only specific
CPUs that have useful work to do and not the entire system.
This patch set, inspired by discussions with Peter Zijlstra and Frederic
Weisbecker when testing the nohz task patch set, is a first stab at trying
to explore doing this by locating the places where such global IPI calls
are being made and turning the global IPI into an IPI for a specific group
of CPUs. The purpose of the patch set is to get feedback if this is the
right way to go for dealing with this issue and indeed, if the issue is
even worth dealing with at all. Based on the feedback from this patch set
I plan to offer further patches that address similar issue in other code
paths.
This patch creates an on_each_cpu_mask() and on_each_cpu_cond()
infrastructure API (the former derived from existing arch specific
versions in Tile and Arm) and uses them to turn several global IPI
invocation to per CPU group invocations.
Core kernel:
on_each_cpu_mask() calls a function on processors specified by cpumask,
which may or may not include the local processor.
You must not call this function with disabled interrupts or from a
hardware interrupt handler or from a bottom half handler.
arch/arm:
Note that the generic version is a little different then the Arm one:
1. It has the mask as first parameter
2. It calls the function on the calling CPU with interrupts disabled,
but this should be OK since the function is called on the other CPUs
with interrupts disabled anyway.
arch/tile:
The API is the same as the tile private one, but the generic version
also calls the function on the with interrupts disabled in UP case
This is OK since the function is called on the other CPUs
with interrupts disabled.
Signed-off-by: Gilad Ben-Yossef <gilad@benyossef.com>
Reviewed-by: Christoph Lameter <cl@linux.com>
Acked-by: Chris Metcalf <cmetcalf@tilera.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Russell King <linux@arm.linux.org.uk>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Matt Mackall <mpm@selenic.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Andi Kleen <andi@firstfloor.org>
Cc: Sasha Levin <levinsasha928@gmail.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Alexander Viro <viro@zeniv.linux.org.uk>
Cc: Avi Kivity <avi@redhat.com>
Acked-by: Michal Nazarewicz <mina86@mina86.org>
Cc: Kosaki Motohiro <kosaki.motohiro@gmail.com>
Cc: Milton Miller <miltonm@bga.com>
Cc: Russell King <linux@arm.linux.org.uk>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The changed files were only including linux/module.h for the
EXPORT_SYMBOL infrastructure, and nothing else. Revector them
onto the isolated export header for faster compile times.
Nothing to see here but a whole lot of instances of:
-#include <linux/module.h>
+#include <linux/export.h>
This commit is only changing the kernel dir; next targets
will probably be mm, fs, the arch dirs, etc.
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
There is a problem that kdump(2nd kernel) sometimes hangs up due
to a pending IPI from 1st kernel. Kernel panic occurs because IPI
comes before call_single_queue is initialized.
To fix the crash, rename init_call_single_data() to call_function_init()
and call it in start_kernel() so that call_single_queue can be
initialized before enabling interrupts.
The details of the crash are:
(1) 2nd kernel boots up
(2) A pending IPI from 1st kernel comes when irqs are first enabled
in start_kernel().
(3) Kernel tries to handle the interrupt, but call_single_queue
is not initialized yet at this point. As a result, in the
generic_smp_call_function_single_interrupt(), NULL pointer
dereference occurs when list_replace_init() tries to access
&q->list.next.
Therefore this patch changes the name of init_call_single_data()
to call_function_init() and calls it before local_irq_enable()
in start_kernel().
Signed-off-by: Takao Indoh <indou.takao@jp.fujitsu.com>
Reviewed-by: WANG Cong <xiyou.wangcong@gmail.com>
Acked-by: Neil Horman <nhorman@tuxdriver.com>
Acked-by: Vivek Goyal <vgoyal@redhat.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Milton Miller <miltonm@bga.com>
Cc: Jens Axboe <axboe@kernel.dk>
Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: kexec@lists.infradead.org
Link: http://lkml.kernel.org/r/D6CBEE2F420741indou.takao@jp.fujitsu.com
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Use the newly added smp_call_func_t in smp_call_function_interrupt for
the func variable, and make the comment above the WARN more assertive
and explicit. Also, func is a function pointer and does not need an
offset, so use %pf not %pS.
Signed-off-by: Milton Miller <miltonm@bga.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Mike Galbraith reported finding a lockup ("perma-spin bug") where the
cpumask passed to smp_call_function_many was cleared by other cpu(s)
while a cpu was preparing its call_data block, resulting in no cpu to
clear the last ref and unlock the block.
Having cpus clear their bit asynchronously could be useful on a mask of
cpus that might have a translation context, or cpus that need a push to
complete an rcu window.
Instead of adding a BUG_ON and requiring yet another cpumask copy, just
detect the race and handle it.
Note: arch_send_call_function_ipi_mask must still handle an empty
cpumask because the data block is globally visible before the that arch
callback is made. And (obviously) there are no guarantees to which cpus
are notified if the mask is changed during the call; only cpus that were
online and had their mask bit set during the whole call are guaranteed
to be called.
Reported-by: Mike Galbraith <efault@gmx.de>
Reported-by: Jan Beulich <JBeulich@novell.com>
Acked-by: Jan Beulich <jbeulich@novell.com>
Cc: stable@kernel.org
Signed-off-by: Milton Miller <miltonm@bga.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Paul McKenney's review pointed out two problems with the barriers in the
2.6.38 update to the smp call function many code.
First, a barrier that would force the func and info members of data to
be visible before their consumption in the interrupt handler was
missing. This can be solved by adding a smp_wmb between setting the
func and info members and setting setting the cpumask; this will pair
with the existing and required smp_rmb ordering the cpumask read before
the read of refs. This placement avoids the need a second smp_rmb in
the interrupt handler which would be executed on each of the N cpus
executing the call request. (I was thinking this barrier was present
but was not).
Second, the previous write to refs (establishing the zero that we the
interrupt handler was testing from all cpus) was performed by a third
party cpu. This would invoke transitivity which, as a recient or
concurrent addition to memory-barriers.txt now explicitly states, would
require a full smp_mb().
However, we know the cpumask will only be set by one cpu (the data
owner) and any preivous iteration of the mask would have cleared by the
reading cpu. By redundantly writing refs to 0 on the owning cpu before
the smp_wmb, the write to refs will follow the same path as the writes
that set the cpumask, which in turn allows us to keep the barrier in the
interrupt handler a smp_rmb instead of promoting it to a smp_mb (which
will be be executed by N cpus for each of the possible M elements on the
list).
I moved and expanded the comment about our (ab)use of the rcu list
primitives for the concurrent walk earlier into this function. I
considered moving the first two paragraphs to the queue list head and
lock, but felt it would have been too disconected from the code.
Cc: Paul McKinney <paulmck@linux.vnet.ibm.com>
Cc: stable@kernel.org (2.6.32 and later)
Signed-off-by: Milton Miller <miltonm@bga.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Peter pointed out there was nothing preventing the list_del_rcu in
smp_call_function_interrupt from running before the list_add_rcu in
smp_call_function_many.
Fix this by not setting refs until we have gotten the lock for the list.
Take advantage of the wmb in list_add_rcu to save an explicit additional
one.
I tried to force this race with a udelay before the lock & list_add and
by mixing all 64 online cpus with just 3 random cpus in the mask, but
was unsuccessful. Still, inspection shows a valid race, and the fix is
a extension of the existing protection window in the current code.
Cc: stable@kernel.org (v2.6.32 and later)
Reported-by: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Milton Miller <miltonm@bga.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'core-fixes-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip:
smp: Allow on_each_cpu() to be called while early_boot_irqs_disabled status to init/main.c
lockdep: Move early boot local IRQ enable/disable status to init/main.c
We have to test the cpu mask in the interrupt handler before checking the
refs, otherwise we can start to follow an entry before its deleted and
find it partially initailzed for the next trip. Presently we also clear
the cpumask bit before executing the called function, which implies
getting write access to the line. After the function is called we then
decrement refs, and if they go to zero we then unlock the structure.
However, this implies getting write access to the call function data
before and after another the function is called. If we can assert that no
smp_call_function execution function is allowed to enable interrupts, then
we can move both writes to after the function is called, hopfully allowing
both writes with one cache line bounce.
On a 256 thread system with a kernel compiled for 1024 threads, the time
to execute testcase in the "smp_call_function_many race" changelog was
reduced by about 30-40ms out of about 545 ms.
I decided to keep this as WARN because its now a buggy function, even
though the stack trace is of no value -- a simple printk would give us the
information needed.
Raw data:
Without patch:
ipi_test startup took 1219366ns complete 539819014ns total 541038380ns
ipi_test startup took 1695754ns complete 543439872ns total 545135626ns
ipi_test startup took 7513568ns complete 539606362ns total 547119930ns
ipi_test startup took 13304064ns complete 533898562ns total 547202626ns
ipi_test startup took 8668192ns complete 544264074ns total 552932266ns
ipi_test startup took 4977626ns complete 548862684ns total 553840310ns
ipi_test startup took 2144486ns complete 541292318ns total 543436804ns
ipi_test startup took 21245824ns complete 530280180ns total 551526004ns
With patch:
ipi_test startup took 5961748ns complete 500859628ns total 506821376ns
ipi_test startup took 8975996ns complete 495098924ns total 504074920ns
ipi_test startup took 19797750ns complete 492204740ns total 512002490ns
ipi_test startup took 14824796ns complete 487495878ns total 502320674ns
ipi_test startup took 11514882ns complete 494439372ns total 505954254ns
ipi_test startup took 8288084ns complete 502570774ns total 510858858ns
ipi_test startup took 6789954ns complete 493388112ns total 500178066ns
#include <linux/module.h>
#include <linux/init.h>
#include <linux/sched.h> /* sched clock */
#define ITERATIONS 100
static void do_nothing_ipi(void *dummy)
{
}
static void do_ipis(struct work_struct *dummy)
{
int i;
for (i = 0; i < ITERATIONS; i++)
smp_call_function(do_nothing_ipi, NULL, 1);
printk(KERN_DEBUG "cpu %d finished\n", smp_processor_id());
}
static struct work_struct work[NR_CPUS];
static int __init testcase_init(void)
{
int cpu;
u64 start, started, done;
start = local_clock();
for_each_online_cpu(cpu) {
INIT_WORK(&work[cpu], do_ipis);
schedule_work_on(cpu, &work[cpu]);
}
started = local_clock();
for_each_online_cpu(cpu)
flush_work(&work[cpu]);
done = local_clock();
pr_info("ipi_test startup took %lldns complete %lldns total %lldns\n",
started-start, done-started, done-start);
return 0;
}
static void __exit testcase_exit(void)
{
}
module_init(testcase_init)
module_exit(testcase_exit)
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Anton Blanchard");
Signed-off-by: Milton Miller <miltonm@bga.com>
Cc: Anton Blanchard <anton@samba.org>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
I noticed a failure where we hit the following WARN_ON in
generic_smp_call_function_interrupt:
if (!cpumask_test_and_clear_cpu(cpu, data->cpumask))
continue;
data->csd.func(data->csd.info);
refs = atomic_dec_return(&data->refs);
WARN_ON(refs < 0); <-------------------------
We atomically tested and cleared our bit in the cpumask, and yet the
number of cpus left (ie refs) was 0. How can this be?
It turns out commit 54fdade1c3
("generic-ipi: make struct call_function_data lockless") is at fault. It
removes locking from smp_call_function_many and in doing so creates a
rather complicated race.
The problem comes about because:
- The smp_call_function_many interrupt handler walks call_function.queue
without any locking.
- We reuse a percpu data structure in smp_call_function_many.
- We do not wait for any RCU grace period before starting the next
smp_call_function_many.
Imagine a scenario where CPU A does two smp_call_functions back to back,
and CPU B does an smp_call_function in between. We concentrate on how CPU
C handles the calls:
CPU A CPU B CPU C CPU D
smp_call_function
smp_call_function_interrupt
walks
call_function.queue sees
data from CPU A on list
smp_call_function
smp_call_function_interrupt
walks
call_function.queue sees
(stale) CPU A on list
smp_call_function int
clears last ref on A
list_del_rcu, unlock
smp_call_function reuses
percpu *data A
data->cpumask sees and
clears bit in cpumask
might be using old or new fn!
decrements refs below 0
set data->refs (too late!)
The important thing to note is since the interrupt handler walks a
potentially stale call_function.queue without any locking, then another
cpu can view the percpu *data structure at any time, even when the owner
is in the process of initialising it.
The following test case hits the WARN_ON 100% of the time on my PowerPC
box (having 128 threads does help :)
#include <linux/module.h>
#include <linux/init.h>
#define ITERATIONS 100
static void do_nothing_ipi(void *dummy)
{
}
static void do_ipis(struct work_struct *dummy)
{
int i;
for (i = 0; i < ITERATIONS; i++)
smp_call_function(do_nothing_ipi, NULL, 1);
printk(KERN_DEBUG "cpu %d finished\n", smp_processor_id());
}
static struct work_struct work[NR_CPUS];
static int __init testcase_init(void)
{
int cpu;
for_each_online_cpu(cpu) {
INIT_WORK(&work[cpu], do_ipis);
schedule_work_on(cpu, &work[cpu]);
}
return 0;
}
static void __exit testcase_exit(void)
{
}
module_init(testcase_init)
module_exit(testcase_exit)
MODULE_LICENSE("GPL");
MODULE_AUTHOR("Anton Blanchard");
I tried to fix it by ordering the read and the write of ->cpumask and
->refs. In doing so I missed a critical case but Paul McKenney was able
to spot my bug thankfully :) To ensure we arent viewing previous
iterations the interrupt handler needs to read ->refs then ->cpumask then
->refs _again_.
Thanks to Milton Miller and Paul McKenney for helping to debug this issue.
[miltonm@bga.com: add WARN_ON and BUG_ON, remove extra read of refs before initial read of mask that doesn't help (also noted by Peter Zijlstra), adjust comments, hopefully clarify scenario ]
[miltonm@bga.com: remove excess tests]
Signed-off-by: Anton Blanchard <anton@samba.org>
Signed-off-by: Milton Miller <miltonm@bga.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: <stable@kernel.org> [2.6.32+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
percpu may end up calling vfree() during early boot which in
turn may call on_each_cpu() for TLB flushes. The function of
on_each_cpu() can be done safely while IRQ is disabled during
early boot but it assumed that the function is always called
with local IRQ enabled which ended up enabling local IRQ
prematurely during boot and triggering a couple of warnings.
This patch updates on_each_cpu() and smp_call_function_many()
such on_each_cpu() can be used safely while
early_boot_irqs_disabled is set.
Signed-off-by: Tejun Heo <tj@kernel.org>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Pekka Enberg <penberg@kernel.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
LKML-Reference: <20110120110713.GC6036@htj.dyndns.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Reported-by: Ingo Molnar <mingo@elte.hu>
For arch which needs USE_GENERIC_SMP_HELPERS, it has to select
USE_GENERIC_SMP_HELPERS, rather than leaving a choice to user, since they
don't provide their own implementions.
Also, move on_each_cpu() to kernel/smp.c, it is strange to put it in
kernel/softirq.c.
For arch which doesn't use USE_GENERIC_SMP_HELPERS, e.g. blackfin, only
on_each_cpu() is compiled.
Signed-off-by: Amerigo Wang <amwang@redhat.com>
Cc: David Howells <dhowells@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Randy Dunlap <randy.dunlap@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Typedef the pointer to the function to be called by smp_call_function() and
friends:
typedef void (*smp_call_func_t)(void *info);
as it is used in a fair number of places.
Signed-off-by: David Howells <dhowells@redhat.com>
cc: linux-arch@vger.kernel.org
Just got my 6 way machine to a state where cpu 0 is in an
endless loop within __smp_call_function_single.
All other cpus are idle.
The call trace on cpu 0 looks like this:
__smp_call_function_single
scheduler_tick
update_process_times
tick_sched_timer
__run_hrtimer
hrtimer_interrupt
clock_comparator_work
do_extint
ext_int_handler
----> timer irq
cpu_idle
__smp_call_function_single() got called from nohz_balancer_kick()
(inlined) with the remote cpu being 1, wait being 0 and the per
cpu variable remote_sched_softirq_cb (call_single_data) of the
current cpu (0).
Then it loops forever when it tries to grab the lock of the
call_single_data, since it is already locked and enqueued on cpu 0.
My theory how this could have happened: for some reason the
scheduler decided to call __smp_call_function_single() on it's own
cpu, and sends an IPI to itself. The interrupt stays pending
since IRQs are disabled. If then the hypervisor schedules the
cpu away it might happen that upon rescheduling both the IPI and
the timer IRQ are pending. If then interrupts are enabled again
it depends which one gets scheduled first.
If the timer interrupt gets delivered first we end up with the
local deadlock as seen in the calltrace above.
Let's make __smp_call_function_single() check if the target cpu is
the current cpu and execute the function immediately just like
smp_call_function_single does. That should prevent at least the
scenario described here.
It might also be that the scheduler is not supposed to call
__smp_call_function_single with the remote cpu being the current
cpu, but that is a different issue.
Signed-off-by: Heiko Carstens <heiko.carstens@de.ibm.com>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Jens Axboe <jaxboe@fusionio.com>
Cc: Venkatesh Pallipadi <venki@google.com>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
LKML-Reference: <20100910114729.GB2827@osiris.boeblingen.de.ibm.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
By the previous modification, the cpu notifier can return encapsulate
errno value. This converts the cpu notifiers for kernel/*.c
Signed-off-by: Akinobu Mita <akinobu.mita@gmail.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
percpu.h is included by sched.h and module.h and thus ends up being
included when building most .c files. percpu.h includes slab.h which
in turn includes gfp.h making everything defined by the two files
universally available and complicating inclusion dependencies.
percpu.h -> slab.h dependency is about to be removed. Prepare for
this change by updating users of gfp and slab facilities include those
headers directly instead of assuming availability. As this conversion
needs to touch large number of source files, the following script is
used as the basis of conversion.
http://userweb.kernel.org/~tj/misc/slabh-sweep.py
The script does the followings.
* Scan files for gfp and slab usages and update includes such that
only the necessary includes are there. ie. if only gfp is used,
gfp.h, if slab is used, slab.h.
* When the script inserts a new include, it looks at the include
blocks and try to put the new include such that its order conforms
to its surrounding. It's put in the include block which contains
core kernel includes, in the same order that the rest are ordered -
alphabetical, Christmas tree, rev-Xmas-tree or at the end if there
doesn't seem to be any matching order.
* If the script can't find a place to put a new include (mostly
because the file doesn't have fitting include block), it prints out
an error message indicating which .h file needs to be added to the
file.
The conversion was done in the following steps.
1. The initial automatic conversion of all .c files updated slightly
over 4000 files, deleting around 700 includes and adding ~480 gfp.h
and ~3000 slab.h inclusions. The script emitted errors for ~400
files.
2. Each error was manually checked. Some didn't need the inclusion,
some needed manual addition while adding it to implementation .h or
embedding .c file was more appropriate for others. This step added
inclusions to around 150 files.
3. The script was run again and the output was compared to the edits
from #2 to make sure no file was left behind.
4. Several build tests were done and a couple of problems were fixed.
e.g. lib/decompress_*.c used malloc/free() wrappers around slab
APIs requiring slab.h to be added manually.
5. The script was run on all .h files but without automatically
editing them as sprinkling gfp.h and slab.h inclusions around .h
files could easily lead to inclusion dependency hell. Most gfp.h
inclusion directives were ignored as stuff from gfp.h was usually
wildly available and often used in preprocessor macros. Each
slab.h inclusion directive was examined and added manually as
necessary.
6. percpu.h was updated not to include slab.h.
7. Build test were done on the following configurations and failures
were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my
distributed build env didn't work with gcov compiles) and a few
more options had to be turned off depending on archs to make things
build (like ipr on powerpc/64 which failed due to missing writeq).
* x86 and x86_64 UP and SMP allmodconfig and a custom test config.
* powerpc and powerpc64 SMP allmodconfig
* sparc and sparc64 SMP allmodconfig
* ia64 SMP allmodconfig
* s390 SMP allmodconfig
* alpha SMP allmodconfig
* um on x86_64 SMP allmodconfig
8. percpu.h modifications were reverted so that it could be applied as
a separate patch and serve as bisection point.
Given the fact that I had only a couple of failures from tests on step
6, I'm fairly confident about the coverage of this conversion patch.
If there is a breakage, it's likely to be something in one of the arch
headers which should be easily discoverable easily on most builds of
the specific arch.
Signed-off-by: Tejun Heo <tj@kernel.org>
Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
The smp ipi data is passed around and given write access by
other cpus and should be separated from per-cpu data consumed by
this cpu.
Looking for hot lines, I saw call_function_data shared with
tick_cpu_sched.
Signed-off-by: Milton Miller <miltonm@bga.com>
Acked-by: Anton Blanchard <anton@samba.org>
Acked-by: Jens Axboe <jens.axboe@oracle.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: : Nick Piggin <npiggin@suse.de>
LKML-Reference: <20100118020051.GR12666@kryten>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The change in acpi_cpufreq to use smp_call_function_any causes a warning
when it is called since the function erroneously passes the cpu id to
cpumask_of_node rather than the node that the cpu is on. Fix this.
cpumask_of_node(3): node > nr_node_ids(1)
Pid: 1, comm: swapper Not tainted 2.6.33-rc3-00097-g2c1f189 #223
Call Trace:
[<ffffffff81028bb3>] cpumask_of_node+0x23/0x58
[<ffffffff81061f51>] smp_call_function_any+0x65/0xfa
[<ffffffff810160d1>] ? do_drv_read+0x0/0x2f
[<ffffffff81015fba>] get_cur_val+0xb0/0x102
[<ffffffff81016080>] get_cur_freq_on_cpu+0x74/0xc5
[<ffffffff810168a7>] acpi_cpufreq_cpu_init+0x417/0x515
[<ffffffff81562ce9>] ? __down_write+0xb/0xd
[<ffffffff8148055e>] cpufreq_add_dev+0x278/0x922
Signed-off-by: David John <davidjon@xenontk.org>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'core-locking-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (26 commits)
clockevents: Convert to raw_spinlock
clockevents: Make tick_device_lock static
debugobjects: Convert to raw_spinlocks
perf_event: Convert to raw_spinlock
hrtimers: Convert to raw_spinlocks
genirq: Convert irq_desc.lock to raw_spinlock
smp: Convert smplocks to raw_spinlocks
rtmutes: Convert rtmutex.lock to raw_spinlock
sched: Convert pi_lock to raw_spinlock
sched: Convert cpupri lock to raw_spinlock
sched: Convert rt_runtime_lock to raw_spinlock
sched: Convert rq->lock to raw_spinlock
plist: Make plist debugging raw_spinlock aware
bkl: Fixup core_lock fallout
locking: Cleanup the name space completely
locking: Further name space cleanups
alpha: Fix fallout from locking changes
locking: Implement new raw_spinlock
locking: Convert raw_rwlock functions to arch_rwlock
locking: Convert raw_rwlock to arch_rwlock
...
Use smp_processor_id() instead of get_cpu() and put_cpu() in
generic_smp_call_function_interrupt(), It's no need to disable preempt,
because we must call generic_smp_call_function_interrupt() with interrupts
disabled.
Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Convert locks which cannot be sleeping locks in preempt-rt to
raw_spinlocks.
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Acked-by: Peter Zijlstra <peterz@infradead.org>
Acked-by: Ingo Molnar <mingo@elte.hu>
Andrew points out that acpi-cpufreq uses cpumask_any, when it really
would prefer to use the same CPU if possible (to avoid an IPI). In
general, this seems a good idea to offer.
[ tglx: Documented selection preference and Inlined the UP case to
avoid the copy of smp_call_function_single() and the extra
EXPORT ]
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Venkatesh Pallipadi <venkatesh.pallipadi@intel.com>
Cc: Len Brown <len.brown@intel.com>
Cc: Zhao Yakui <yakui.zhao@intel.com>
Cc: Dave Jones <davej@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Mike Galbraith <efault@gmx.de>
Cc: "Zhang, Yanmin" <yanmin_zhang@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
This patch can remove spinlock from struct call_function_data, the
reasons are below:
1: add a new interface for cpumask named cpumask_test_and_clear_cpu(),
it can atomically test and clear specific cpu, we can use it instead
of cpumask_test_cpu() and cpumask_clear_cpu() and no need data->lock
to protect those in generic_smp_call_function_interrupt().
2: in smp_call_function_many(), after csd_lock() return, the current's
cfd_data is deleted from call_function list, so it not have race
between other cpus, then cfs_data is only used in
smp_call_function_many() that must disable preemption and not from
a hardware interrupthandler or from a bottom half handler to call,
only the correspond cpu can use it, so it not have race in current
cpu, no need cfs_data->lock to protect it.
3: after 1 and 2, cfs_data->lock is only use to protect cfs_data->refs in
generic_smp_call_function_interrupt(), so we can define cfs_data->refs
to atomic_t, and no need cfs_data->lock any more.
Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Peter Zijlstra <peterz@infradead.org>
Acked-by: Rusty Russell <rusty@rustcorp.com.au>
[akpm@linux-foundation.org: use atomic_dec_return()]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Reason: Change to is_new_memtype_allowed() in x86/urgent
Resolved semantic conflicts in:
arch/x86/mm/pat.c
arch/x86/mm/ioremap.c
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Because of deadlock possiblities smp_call_function() is not allowed to
be called with interrupts disabled. Add an exception for the cpu not
yet online, as no one else can send smp call function interrupt to this
cpu that is not yet online and as such deadlock condition is not possible.
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Acked-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Use CONFIG_HOTPLUG_CPU, not CONFIG_CPU_HOTPLUG
When hot-unpluging a cpu, it will leak memory allocated at cpu hotplug,
but only if CPUMASK_OFFSTACK=y, which is default to n.
The bug was introduced by 8969a5ede0
("generic-ipi: remove kmalloc()").
Signed-off-by: Xiao Guangrong <xiaoguangrong@cn.fujitsu.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
These are defined as static cpumask_var_t so if MAXSMP is not used,
they are cleared already. Avoid surprises when MAXSMP is enabled.
Signed-off-by: Yinghai Lu <yinghai.lu@kernel.org>
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Do not output smp-call related warnings in the oops/panic codepath.
Reported-by: Jan Beulich <jbeulich@novell.com>
Acked-by: Peter Zijlstra <peterz@infradead.org>
LKML-Reference: <49B91A7E.76E4.0078.0@novell.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Andrew pointed out that there's some small amount of
style rot in kernel/smp.c.
Clean it up.
Reported-by: Andrew Morton <akpm@linux-foundation.org>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Oleg noticed that we don't strictly need CSD_FLAG_WAIT, rework
the code so that we can use CSD_FLAG_LOCK for both purposes.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Remove the use of kmalloc() from the smp_call_function_*()
calls.
Steven's generic-ipi patch (d7240b98: generic-ipi: use per cpu
data for single cpu ipi calls) started the discussion on the use
of kmalloc() in this code and fixed the
smp_call_function_single(.wait=0) fallback case.
In this patch we complete this by also providing means for the
_many() call, which fully removes the need for kmalloc() in this
code.
The problem with the _many() call is that other cpus might still
be observing our entry when we're done with it. It solved this
by dynamically allocating data elements and RCU-freeing it.
We solve it by using a single per-cpu entry which provides
static storage and solves one half of the problem (avoiding
referencing freed data).
The other half, ensuring the queue iteration it still possible,
is done by placing re-used entries at the head of the list. This
means that if someone was still iterating that entry when it got
moved, he will now re-visit the entries on the list he had
already seen, but avoids skipping over entries like would have
happened had we placed the new entry at the end.
Furthermore, visiting entries twice is not a problem, since we
remove our cpu from the entry's cpumask once its called.
Many thanks to Oleg for his suggestions and him poking holes in
my earlier attempts.
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Nick Piggin <npiggin@suse.de>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Simplify the barriers in generic remote function call interrupt
code.
Firstly, just unconditionally take the lock and check the list
in the generic_call_function_single_interrupt IPI handler. As
we've just taken an IPI here, the chances are fairly high that
there will be work on the list for us, so do the locking
unconditionally. This removes the tricky lockless list_empty
check and dubious barriers. The change looks bigger than it is
because it is just removing an outer loop.
Secondly, clarify architecture specific IPI locking rules.
Generic code has no tools to impose any sane ordering on IPIs if
they go outside normal cache coherency, ergo the arch code must
make them appear to obey cache coherency as a "memory operation"
to initiate an IPI, and a "memory operation" to receive one.
This way at least they can be reasoned about in generic code,
and smp_mb used to provide ordering.
The combination of these two changes means that explict barriers
can be taken out of queue handling for the single case -- shared
data is explicitly locked, and ipi ordering must conform to
that, so no barriers needed. An extra barrier is needed in the
many handler, so as to ensure we load the list element after the
IPI is received.
Does any architecture actually *need* these barriers? For the
initiator I could see it, but for the handler I would be
surprised. So the other thing we could do for simplicity is just
to require that, rather than just matching with cache coherency,
we just require a full barrier before generating an IPI, and
after receiving an IPI. In which case, the smp_mb()s can go
away. But just for now, we'll be on the safe side and use the
barriers (they're in the slow case anyway).
Signed-off-by: Nick Piggin <npiggin@suse.de>
Acked-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: linux-arch@vger.kernel.org
Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Jens Axboe <jens.axboe@oracle.com>
Cc: Oleg Nesterov <oleg@redhat.com>
Cc: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
The smp_call_function can be passed a wait parameter telling it to
wait for all the functions running on other CPUs to complete before
returning, or to return without waiting. Unfortunately, this is
currently just a suggestion and not manditory. That is, the
smp_call_function can decide not to return and wait instead.
The reason for this is because it uses kmalloc to allocate storage
to send to the called CPU and that CPU will free it when it is done.
But if we fail to allocate the storage, the stack is used instead.
This means we must wait for the called CPU to finish before
continuing.
Unfortunatly, some callers do no abide by this hint and act as if
the non-wait option is mandatory. The MTRR code for instance will
deadlock if the smp_call_function is set to wait. This is because
the smp_call_function will wait for the other CPUs to finish their
called functions, but those functions are waiting on the caller to
continue.
This patch changes the generic smp_call_function code to use per cpu
variables if the allocation of the data fails for a single CPU call. The
smp_call_function_many will fall back to the smp_call_function_single
if it fails its alloc. The smp_call_function_single is modified
to not force the wait state.
Since we now are using a single data per cpu we must synchronize the
callers to prevent a second caller modifying the data before the
first called IPI functions complete. To do so, I added a flag to
the call_single_data called CSD_FLAG_LOCK. When the single CPU is
called (which can be called when a many call fails an alloc), we
set the LOCK bit on this per cpu data. When the caller finishes
it clears the LOCK bit.
The caller must wait till the LOCK bit is cleared before setting
it. When it is cleared, there is no IPI function using it.
Signed-off-by: Steven Rostedt <srostedt@redhat.com>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Acked-by: Jens Axboe <jens.axboe@oracle.com>
Acked-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Impact: cleanup
In future, all cpumask ops will only be valid (in general) for bit
numbers < nr_cpu_ids. So use that instead of NR_CPUS in iterators
and other comparisons.
This is always safe: no cpu number can be >= nr_cpu_ids, and
nr_cpu_ids is initialized to NR_CPUS at boot.
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Mike Travis <travis@sgi.com>
Acked-by: Ingo Molnar <mingo@elte.hu>
Acked-by: James Morris <jmorris@namei.org>
Cc: Eric Biederman <ebiederm@xmission.com>
Impact: new API to reduce stack usage
We're weaning the core code off handing cpumask's around on-stack.
This introduces arch_send_call_function_ipi_mask().
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Impact: Implementation change to remove cpumask_t from stack.
Actually change smp_call_function_mask() to smp_call_function_many().
We avoid cpumasks on the stack in this version.
(S390 has its own version, but that's going away apparently).
We have to do some dancing to figure out if 0 or 1 other cpus are in
the mask supplied and the online mask without allocating a tmp
cpumask. It's still fairly cheap.
We allocate the cpumask at the end of the call_function_data
structure: if allocation fails we fallback to smp_call_function_single
rather than using the baroque quiescing code (which needs a cpumask on
stack).
(Thanks to Hiroshi Shimamoto for spotting several bugs in previous versions!)
Signed-off-by: Rusty Russell <rusty@rustcorp.com.au>
Signed-off-by: Mike Travis <travis@sgi.com>
Cc: Hiroshi Shimamoto <h-shimamoto@ct.jp.nec.com>
Cc: npiggin@suse.de
Cc: axboe@kernel.dk
smp_mb() is needed (to make the memory operations visible globally) before
sending the ipi on the sender and the receiver (on Alpha atleast) needs
smp_read_barrier_depends() in the handler before reading the call_single_queue
list in a lock-free fashion.
On x86, x2apic mode register accesses for sending IPI's don't have serializing
semantics. So the need for smp_mb() before sending the IPI becomes more
critical in x2apic mode.
Remove the unnecessary smp_mb() in csd_flag_wait(), as the presence of that
smp_mb() doesn't mean anything on the sender, when the ipi receiver is not
doing any thing special (like memory fence) after clearing the CSD_FLAG_WAIT.
Signed-off-by: Suresh Siddha <suresh.b.siddha@intel.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Have smp_call_function_single() return invalid CPU indicies and return
-ENXIO. This function is already executed inside a
get_cpu()..put_cpu() which locks out CPU removal, so rather than
having the higher layers doing another layer of locking to guard
against unplugged CPUs do the test here.
Signed-off-by: H. Peter Anvin <hpa@zytor.com>
> > Nick Piggin (1):
> > generic-ipi: fix stack and rcu interaction bug in
> > smp_call_function_mask()
>
> I'm still not 100% sure that I have this patch right... I might have seen
> a lockup trace implicating the smp call function path... which may have
> been due to some other problem or a different bug in the new call function
> code, but if some more people can take a look at it before merging?
OK indeed it did have a couple of bugs. Firstly, I wasn't freeing the
data properly in the alloc && wait case. Secondly, I wasn't resetting
CSD_FLAG_WAIT in the for each cpu loop (so only the first CPU would
wait).
After those fixes, the patch boots and runs with the kmalloc commented
out (so it always executes the slowpath).
Signed-off-by: Ingo Molnar <mingo@elte.hu>
* Venki Pallipadi <venkatesh.pallipadi@intel.com> wrote:
> Found a OOPS on a big SMP box during an overnight reboot test with
> upstream git.
>
> Suresh and I looked at the oops and looks like the root cause is in
> generic_smp_call_function_interrupt() and smp_call_function_mask() with
> wait parameter.
>
> The actual oops looked like
>
> [ 11.277260] BUG: unable to handle kernel paging request at ffff8802ffffffff
> [ 11.277815] IP: [<ffff8802ffffffff>] 0xffff8802ffffffff
> [ 11.278155] PGD 202063 PUD 0
> [ 11.278576] Oops: 0010 [1] SMP
> [ 11.279006] CPU 5
> [ 11.279336] Modules linked in:
> [ 11.279752] Pid: 0, comm: swapper Not tainted 2.6.27-rc2-00020-g685d87f #290
> [ 11.280039] RIP: 0010:[<ffff8802ffffffff>] [<ffff8802ffffffff>] 0xffff8802ffffffff
> [ 11.280692] RSP: 0018:ffff88027f1f7f70 EFLAGS: 00010086
> [ 11.280976] RAX: 00000000ffffffff RBX: 0000000000000000 RCX: 0000000000000000
> [ 11.281264] RDX: 0000000000004f4e RSI: 0000000000000001 RDI: 0000000000000000
> [ 11.281624] RBP: ffff88027f1f7f98 R08: 0000000000000001 R09: ffffffff802509af
> [ 11.281925] R10: ffff8800280c2780 R11: 0000000000000000 R12: ffff88027f097d48
> [ 11.282214] R13: ffff88027f097d70 R14: 0000000000000005 R15: ffff88027e571000
> [ 11.282502] FS: 0000000000000000(0000) GS:ffff88027f1c3340(0000) knlGS:0000000000000000
> [ 11.283096] CS: 0010 DS: 0018 ES: 0018 CR0: 000000008005003b
> [ 11.283382] CR2: ffff8802ffffffff CR3: 0000000000201000 CR4: 00000000000006e0
> [ 11.283760] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
> [ 11.284048] DR3: 0000000000000000 DR6: 00000000ffff0ff0 DR7: 0000000000000400
> [ 11.284337] Process swapper (pid: 0, threadinfo ffff88027f1f2000, task ffff88027f1f0640)
> [ 11.284936] Stack: ffffffff80250963 0000000000000212 0000000000ee8c78 0000000000ee8a66
> [ 11.285802] ffff88027e571550 ffff88027f1f7fa8 ffffffff8021adb5 ffff88027f1f3e40
> [ 11.286599] ffffffff8020bdd6 ffff88027f1f3e40 <EOI> ffff88027f1f3ef8 0000000000000000
> [ 11.287120] Call Trace:
> [ 11.287768] <IRQ> [<ffffffff80250963>] ? generic_smp_call_function_interrupt+0x61/0x12c
> [ 11.288354] [<ffffffff8021adb5>] smp_call_function_interrupt+0x17/0x27
> [ 11.288744] [<ffffffff8020bdd6>] call_function_interrupt+0x66/0x70
> [ 11.289030] <EOI> [<ffffffff8024ab3b>] ? clockevents_notify+0x19/0x73
> [ 11.289380] [<ffffffff803b9b75>] ? acpi_idle_enter_simple+0x18b/0x1fa
> [ 11.289760] [<ffffffff803b9b6b>] ? acpi_idle_enter_simple+0x181/0x1fa
> [ 11.290051] [<ffffffff8053aeca>] ? cpuidle_idle_call+0x70/0xa2
> [ 11.290338] [<ffffffff80209f61>] ? cpu_idle+0x5f/0x7d
> [ 11.290723] [<ffffffff8060224a>] ? start_secondary+0x14d/0x152
> [ 11.291010]
> [ 11.291287]
> [ 11.291654] Code: Bad RIP value.
> [ 11.292041] RIP [<ffff8802ffffffff>] 0xffff8802ffffffff
> [ 11.292380] RSP <ffff88027f1f7f70>
> [ 11.292741] CR2: ffff8802ffffffff
> [ 11.310951] ---[ end trace 137c54d525305f1c ]---
>
> The problem is with the following sequence of events:
>
> - CPU A calls smp_call_function_mask() for CPU B with wait parameter
> - CPU A sets up the call_function_data on the stack and does an rcu add to
> call_function_queue
> - CPU A waits until the WAIT flag is cleared
> - CPU B gets the call function interrupt and starts going through the
> call_function_queue
> - CPU C also gets some other call function interrupt and starts going through
> the call_function_queue
> - CPU C, which is also going through the call_function_queue, starts referencing
> CPU A's stack, as that element is still in call_function_queue
> - CPU B finishes the function call that CPU A set up and as there are no other
> references to it, rcu deletes the call_function_data (which was from CPU A
> stack)
> - CPU B sees the wait flag and just clears the flag (no call_rcu to free)
> - CPU A which was waiting on the flag continues executing and the stack
> contents change
>
> - CPU C is still in rcu_read section accessing the CPU A's stack sees
> inconsistent call_funation_data and can try to execute
> function with some random pointer, causing stack corruption for A
> (by clearing the bits in mask field) and oops.
Nice debugging work.
I'd suggest something like the attached (boot tested) patch as the simple
fix for now.
I expect the benefits from the less synchronized, multiple-in-flight-data
global queue will still outweigh the costs of dynamic allocations. But
if worst comes to worst then we just go back to a globally synchronous
one-at-a-time implementation, but that would be pretty sad!
Signed-off-by: Ingo Molnar <mingo@elte.hu>
A previous patch added the early_initcall(), to allow a cleaner hooking of
pre-SMP initcalls. Now we remove the older interface, converting all
existing users to the new one.
[akpm@linux-foundation.org: cleanups]
[akpm@linux-foundation.org: build fix]
[kosaki.motohiro@jp.fujitsu.com: warning fix]
[kosaki.motohiro@jp.fujitsu.com: warning fix]
Signed-off-by: Eduard - Gabriel Munteanu <eduard.munteanu@linux360.ro>
Cc: Tom Zanussi <tzanussi@gmail.com>
Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When a GFP_ATOMIC allocation fails, it falls back to allocating the
data on the stack and converting it to a waiting call.
Make sure we actually wait in this case.
Signed-off-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'generic-ipi-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (22 commits)
generic-ipi: more merge fallout
generic-ipi: merge fix
x86, visws: use mach-default/entry_arch.h
x86, visws: fix generic-ipi build
generic-ipi: fixlet
generic-ipi: fix s390 build bug
generic-ipi: fix linux-next tree build failure
fix: "smp_call_function: get rid of the unused nonatomic/retry argument"
fix: "smp_call_function: get rid of the unused nonatomic/retry argument"
fix "smp_call_function: get rid of the unused nonatomic/retry argument"
on_each_cpu(): kill unused 'retry' parameter
smp_call_function: get rid of the unused nonatomic/retry argument
sh: convert to generic helpers for IPI function calls
parisc: convert to generic helpers for IPI function calls
mips: convert to generic helpers for IPI function calls
m32r: convert to generic helpers for IPI function calls
arm: convert to generic helpers for IPI function calls
alpha: convert to generic helpers for IPI function calls
ia64: convert to generic helpers for IPI function calls
powerpc: convert to generic helpers for IPI function calls
...
Fix trivial conflicts due to rcu updates in kernel/rcupdate.c manually
fix:
kernel/smp.c: In function 'smp_call_function_mask':
kernel/smp.c:303: error: too many arguments to function 'smp_call_function_single'
Signed-off-by: Ingo Molnar <mingo@elte.hu>
It's never used and the comments refer to nonatomic and retry
interchangably. So get rid of it.
Acked-by: Jeremy Fitzhardinge <jeremy.fitzhardinge@citrix.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
This adds kernel/smp.c which contains helpers for IPI function calls. In
addition to supporting the existing smp_call_function() in a more efficient
manner, it also adds a more scalable variant called smp_call_function_single()
for calling a given function on a single CPU only.
The core of this is based on the x86-64 patch from Nick Piggin, lots of
changes since then. "Alan D. Brunelle" <Alan.Brunelle@hp.com> has
contributed lots of fixes and suggestions as well. Also thanks to
Paul E. McKenney <paulmck@linux.vnet.ibm.com> for reviewing RCU usage
and getting rid of the data allocation fallback deadlock.
Acked-by: Ingo Molnar <mingo@elte.hu>
Reviewed-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Jens Axboe <jens.axboe@oracle.com>
Linus Torvalds