* Re: Linux Plumbers MD BOF discussion notes
From: NeilBrown @ 2017-10-04 21:41 UTC (permalink / raw)
To: Artur Paszkiewicz, Mikael Abrahamsson; +Cc: linux-raid
In-Reply-To: <619758c0-9ca4-c25d-c61b-f411b095041d@intel.com>
[-- Attachment #1: Type: text/plain, Size: 8435 bytes --]
On Wed, Oct 04 2017, Artur Paszkiewicz wrote:
>
> Also, our customers are asking specifically for an option to "hide" the
> member drives. Making it impossible to write to the devices is ok, but
> they would like to see only the md device, "like hardware raid". One of
> the reasons is that some monitoring or inventory scan applications treat
> md arrays and their components as separate storage devices. They should
> probably modify their software but maybe that's not possible.
What exactly is meant by "hide". How, exactly, does this software scan
all devices? /proc/partitions? /sys/block? /sys/class/block?
/dev/disks? All of the above.
Modifying their application *must* be on the table, else modify the
kernel is *not* on the table. I'm certainly open to enhancing the
kernel so that it is easy to skip a particular class of devices, but if
their application chooses to ignore the information the kernel provides,
then the fact that the application doesn't work is their problem, not
ours.
>
> I've been experimenting with different solutions and here is a patch
> that allows to "hide" disk devices and their partitions by writing to a
> sysfs attribute. It removes the device nodes (on devtmpfs), links in
> /sys/block/ and removes the devices from the block class list, so they
> won't be included in places like /proc/partitions, /sys/class/block/,
> lsblk and so on. The device's "real" sysfs directory under /sys/devices/
> is still available, also the links in /sys/dev/block/ are preserved.
> Applications like mdadm can use this to hide/unhide their component
> devices.
Can you confirm that this addresses the customer problem? Do you know
which of these lists their code looks at?
Thanks,
NeilBrown
>
> Thanks,
> Artur
>
> diff --git a/block/genhd.c b/block/genhd.c
> index 7f520fa25d16..58b8e3eb14af 100644
> --- a/block/genhd.c
> +++ b/block/genhd.c
> @@ -685,6 +685,55 @@ void del_gendisk(struct gendisk *disk)
> }
> EXPORT_SYMBOL(del_gendisk);
>
> +static int hide_disk(struct gendisk *disk)
> +{
> + struct device *ddev = disk_to_dev(disk);
> + struct disk_part_iter piter;
> + struct hd_struct *part;
> + int ret;
> +
> + ret = device_hide(ddev);
> + if (ret)
> + return ret;
> +
> + disk_part_iter_init(&piter, disk,
> + DISK_PITER_INCL_EMPTY | DISK_PITER_REVERSE);
> + while ((part = disk_part_iter_next(&piter)))
> + device_hide(part_to_dev(part));
> + disk_part_iter_exit(&piter);
> +
> + if (!sysfs_deprecated)
> + sysfs_remove_link(block_depr, dev_name(ddev));
> +
> + return ret;
> +}
> +
> +static int unhide_disk(struct gendisk *disk)
> +{
> + struct device *ddev = disk_to_dev(disk);
> + struct disk_part_iter piter;
> + struct hd_struct *part;
> + int ret;
> +
> + ret = device_unhide(ddev);
> + if (ret)
> + return ret;
> +
> + disk_part_iter_init(&piter, disk, DISK_PITER_INCL_EMPTY);
> + while ((part = disk_part_iter_next(&piter)))
> + device_unhide(part_to_dev(part));
> + disk_part_iter_exit(&piter);
> +
> + if (!sysfs_deprecated) {
> + if (sysfs_create_link(block_depr, &ddev->kobj,
> + kobject_name(&ddev->kobj)))
> + pr_warn("%s: failed to restore /sys/block link\n",
> + disk->disk_name);
> + }
> +
> + return ret;
> +}
> +
> /* sysfs access to bad-blocks list. */
> static ssize_t disk_badblocks_show(struct device *dev,
> struct device_attribute *attr,
> @@ -1017,6 +1066,31 @@ static ssize_t disk_discard_alignment_show(struct device *dev,
> return sprintf(buf, "%d\n", queue_discard_alignment(disk->queue));
> }
>
> +static ssize_t disk_hidden_show(struct device *dev,
> + struct device_attribute *attr,
> + char *buf)
> +{
> + return sprintf(buf, "%d\n", device_is_hidden(dev));
> +}
> +
> +static ssize_t disk_hidden_store(struct device *dev,
> + struct device_attribute *attr,
> + const char *buf, size_t len)
> +{
> + struct gendisk *disk = dev_to_disk(dev);
> + bool hide;
> + int ret;
> +
> + ret = kstrtobool(buf, &hide);
> + if (ret)
> + return ret;
> +
> + if (hide != device_is_hidden(dev))
> + ret = hide ? hide_disk(disk) : unhide_disk(disk);
> +
> + return ret ?: len;
> +}
> +
> static DEVICE_ATTR(range, S_IRUGO, disk_range_show, NULL);
> static DEVICE_ATTR(ext_range, S_IRUGO, disk_ext_range_show, NULL);
> static DEVICE_ATTR(removable, S_IRUGO, disk_removable_show, NULL);
> @@ -1030,6 +1104,8 @@ static DEVICE_ATTR(stat, S_IRUGO, part_stat_show, NULL);
> static DEVICE_ATTR(inflight, S_IRUGO, part_inflight_show, NULL);
> static DEVICE_ATTR(badblocks, S_IRUGO | S_IWUSR, disk_badblocks_show,
> disk_badblocks_store);
> +static DEVICE_ATTR(hidden, S_IRUGO | S_IWUSR, disk_hidden_show,
> + disk_hidden_store);
> #ifdef CONFIG_FAIL_MAKE_REQUEST
> static struct device_attribute dev_attr_fail =
> __ATTR(make-it-fail, S_IRUGO|S_IWUSR, part_fail_show, part_fail_store);
> @@ -1058,6 +1134,7 @@ static struct attribute *disk_attrs[] = {
> #ifdef CONFIG_FAIL_IO_TIMEOUT
> &dev_attr_fail_timeout.attr,
> #endif
> + &dev_attr_hidden.attr,
> NULL
> };
>
> diff --git a/block/partition-generic.c b/block/partition-generic.c
> index c5ec8246e25e..0223a37c7a8c 100644
> --- a/block/partition-generic.c
> +++ b/block/partition-generic.c
> @@ -350,6 +350,9 @@ struct hd_struct *add_partition(struct gendisk *disk, int partno,
> if (err)
> goto out_put;
>
> + if (device_is_hidden(ddev))
> + device_hide(pdev);
> +
> err = -ENOMEM;
> p->holder_dir = kobject_create_and_add("holders", &pdev->kobj);
> if (!p->holder_dir)
> diff --git a/drivers/base/core.c b/drivers/base/core.c
> index 755451f684bc..0804a45b8fbf 100644
> --- a/drivers/base/core.c
> +++ b/drivers/base/core.c
> @@ -1871,6 +1871,71 @@ void device_del(struct device *dev)
> }
> EXPORT_SYMBOL_GPL(device_del);
>
> +DEFINE_KLIST(klist_hidden_devices, NULL, NULL);
> +
> +bool device_is_hidden(struct device *dev)
> +{
> + bool ret = false;
> +
> + if (dev->class) {
> + mutex_lock(&dev->class->p->mutex);
> + ret = (dev->knode_class.n_klist == &klist_hidden_devices);
> + mutex_unlock(&dev->class->p->mutex);
> + }
> + return ret;
> +}
> +
> +int device_hide(struct device *dev)
> +{
> + char *envp[] = { "EVENT=hide", NULL };
> +
> + if (!dev->class)
> + return -EINVAL;
> +
> + if (MAJOR(dev->devt))
> + devtmpfs_delete_node(dev);
> +
> + device_remove_class_symlinks(dev);
> +
> + mutex_lock(&dev->class->p->mutex);
> + /* remove the device from the class list */
> + klist_remove(&dev->knode_class);
> + /* add to the hidden devices list */
> + klist_add_tail(&dev->knode_class, &klist_hidden_devices);
> + mutex_unlock(&dev->class->p->mutex);
> +
> + kobject_uevent_env(&dev->kobj, KOBJ_CHANGE, envp);
> +
> + return 0;
> +}
> +
> +int device_unhide(struct device *dev)
> +{
> + char *envp[] = { "EVENT=unhide", NULL };
> + int err;
> +
> + if (!dev->class)
> + return -EINVAL;
> +
> + err = device_add_class_symlinks(dev);
> + if (err)
> + return err;
> +
> + if (MAJOR(dev->devt))
> + devtmpfs_create_node(dev);
> +
> + mutex_lock(&dev->class->p->mutex);
> + /* remove the device from the hidden devices list */
> + klist_remove(&dev->knode_class);
> + /* tie the class to the device */
> + klist_add_tail(&dev->knode_class, &dev->class->p->klist_devices);
> + mutex_unlock(&dev->class->p->mutex);
> +
> + kobject_uevent_env(&dev->kobj, KOBJ_CHANGE, envp);
> +
> + return err;
> +}
> +
> /**
> * device_unregister - unregister device from system.
> * @dev: device going away.
> diff --git a/include/linux/device.h b/include/linux/device.h
> index beabdbc08420..90ab1e6b63c6 100644
> --- a/include/linux/device.h
> +++ b/include/linux/device.h
> @@ -1118,6 +1118,9 @@ extern void device_unregister(struct device *dev);
> extern void device_initialize(struct device *dev);
> extern int __must_check device_add(struct device *dev);
> extern void device_del(struct device *dev);
> +extern bool device_is_hidden(struct device *dev);
> +extern int device_hide(struct device *dev);
> +extern int device_unhide(struct device *dev);
> extern int device_for_each_child(struct device *dev, void *data,
> int (*fn)(struct device *dev, void *data));
> extern int device_for_each_child_reverse(struct device *dev, void *data,
[-- Attachment #2: signature.asc --]
[-- Type: application/pgp-signature, Size: 832 bytes --]
^ permalink raw reply
* [nft PATCH] netlink: Use nftnl_expr_fprintf() in netlink_dump_expr()
From: Phil Sutter @ 2017-10-04 21:41 UTC (permalink / raw)
To: Pablo Neira Ayuso; +Cc: netfilter-devel
This gets rid of the temporary buffer.
Signed-off-by: Phil Sutter <phil@nwl.cc>
---
Please note that this patch depends on the previously submitted libnftnl
patch "expr: Introduce nftnl_expr_fprintf()". Since that patch is
obviously not contained in libnftnl-1.0.8, this one should not be
applied until nftables-v0.8 has been released.
---
src/netlink.c | 6 ++----
1 file changed, 2 insertions(+), 4 deletions(-)
diff --git a/src/netlink.c b/src/netlink.c
index d5d410a847624..c9859ef151213 100644
--- a/src/netlink.c
+++ b/src/netlink.c
@@ -520,13 +520,11 @@ void netlink_dump_rule(const struct nftnl_rule *nlr, struct netlink_ctx *ctx)
void netlink_dump_expr(const struct nftnl_expr *nle,
FILE *fp, unsigned int debug_mask)
{
- char buf[4096];
-
if (!(debug_mask & DEBUG_NETLINK))
return;
- nftnl_expr_snprintf(buf, sizeof(buf), nle, 0, 0);
- fprintf(fp, "%s\n", buf);
+ nftnl_expr_fprintf(fp, nle, 0, 0);
+ fprintf(fp, "\n");
}
static int list_rule_cb(struct nftnl_rule *nlr, void *arg)
--
2.13.1
^ permalink raw reply related
* Re: [Qemu-devel] [PATCH v1 3/5] xlnx-zcu102: Specify the valid CPUs
From: Alistair Francis @ 2017-10-04 21:39 UTC (permalink / raw)
To: Eduardo Habkost
Cc: Igor Mammedov, Marcel Apfelbaum, qemu-devel@nongnu.org Developers,
Philippe Mathieu-Daudé, Alistair Francis
In-Reply-To: <20171004163434.GN4760@localhost.localdomain>
On Wed, Oct 4, 2017 at 9:34 AM, Eduardo Habkost <ehabkost@redhat.com> wrote:
> On Wed, Oct 04, 2017 at 03:08:16PM +0200, Igor Mammedov wrote:
>> On Wed, 4 Oct 2017 09:28:51 -0300
>> Eduardo Habkost <ehabkost@redhat.com> wrote:
>>
>> > On Wed, Oct 04, 2017 at 01:12:32PM +0200, Igor Mammedov wrote:
>> > > On Tue, 3 Oct 2017 14:41:17 -0700
>> > > Alistair Francis <alistair.francis@xilinx.com> wrote:
>> > >
>> > > > On Tue, Oct 3, 2017 at 1:36 PM, Eduardo Habkost <ehabkost@redhat.com> wrote:
>> > > > > On Tue, Oct 03, 2017 at 01:05:13PM -0700, Alistair Francis wrote:
>> > > > >> List all possible valid CPU options.
>> > > > >>
>> > > > >> Signed-off-by: Alistair Francis <alistair.francis@xilinx.com>
>> > > > >> ---
>> > > > >>
>> > > > >> hw/arm/xlnx-zcu102.c | 10 ++++++++++
>> > > > >> hw/arm/xlnx-zynqmp.c | 16 +++++++++-------
>> > > > >> include/hw/arm/xlnx-zynqmp.h | 1 +
>> > > > >> 3 files changed, 20 insertions(+), 7 deletions(-)
>> > > > >>
>> > > > >> diff --git a/hw/arm/xlnx-zcu102.c b/hw/arm/xlnx-zcu102.c
>> > > > >> index 519a16ed98..039649e522 100644
>> > > > >> --- a/hw/arm/xlnx-zcu102.c
>> > > > >> +++ b/hw/arm/xlnx-zcu102.c
>> > > > >> @@ -98,6 +98,8 @@ static void xlnx_zynqmp_init(XlnxZCU102 *s, MachineState *machine)
>> > > > >> object_property_add_child(OBJECT(machine), "soc", OBJECT(&s->soc),
>> > > > >> &error_abort);
>> > > > >>
>> > > > >> + object_property_set_str(OBJECT(&s->soc), machine->cpu_type, "cpu-type",
>> > > > >> + &error_fatal);
>> > > > >
>> > > > > Do you have plans to support other CPU types to xlnx_zynqmp in
>> > > > > the future? If not, I wouldn't bother adding the cpu-type
>> > > > > property and the extra boilerplate code if it's always going to
>> > > > > be set to cortex-a53.
>> > > >
>> > > > No, it'll always be A53.
>> > > >
>> > > > I did think of that, but I also wanted to use the new option! I also
>> > > > think there is an advantage in sanely handling users '-cpu' option,
>> > > > before now we just ignored it, so I think it still does give a
>> > > > benefit. That'll be especially important on the Xilinx tree (sometimes
>> > > > people use our machines with a different CPU to 'benchmark' or test
>> > > > other CPUs with our CoSimulation setup). So I think it does make sense
>> > > > to keep in.
>> > > if cpu isn't user settable, one could just outright die if cpu_type
>> > > is not NULL and say that user's CLI is wrong.
>> > > (i.e. don't give users illusion that they allowed to use '-cpu')
>> >
>> > Isn't it exactly what this patch does, by setting:
>> > mc->default_cpu_type = ARM_CPU_TYPE_NAME("cortex-a53");
>> > mc->valid_cpu_types = xlnx_zynqmp_valid_cpus;
>> > ?
>> >
>> > Except that "-cpu cortex-a53" won't die, which is a good thing.
>> allowing "-cpu cortex-a53" here, would allow to use feature parsing
>> which weren't allowed or were ignored before if user supplied '-cpu'.
>> so I'd more strict and refuse any -cpu and break CLI that tries to use it
>> if board has non configurable cpu type. It would be easier to relax
>> restriction later if necessary.
>>
>> using validate_cpus here just to have users for the new code,
>> doesn't seem like valid justification and at that it makes board
>> code more complex where it's not necessary and build in cpu type
>> works just fine.
>
> It's up to the board maintainer to decide what's the best option.
> Both features are independent from each other and can be
> implemented by machine core.
Noooo!
My hope with this series is that eventually we could hit a state where
every single machine acts the same way with the -cpu option.
I really don't like what we do now where some boards use it, some
boards error and some boars just ignore the option. I think we should
agree on something and every machine should follow the same flow so
that users know what to expect when they use the -cpu option.
If this means we allow machines to specify they don't support the
option or only have a single element in the list of supported options
doesn't really matter, but all machines should do the same thing.
>
> In either case, the valid_cpu_types feature will be still very
> useful for boards like pxa270 and sa1110, which support -cpu but
> only with specific families of CPU types (grep for
> "strncmp(cpu_type").
>
>>
>> wrt centralized way to refuse -cpu if board doesn't support it,
>> (which is not really related to this series) following could be done:
>>
>> when cpu_model removal is completely done I plan to replace
>> vl.c
>> cpu_parse_cpu_model(machine_class->default_cpu_type, cpu_model)
>> with
>> cpu_parse_cpu_model(DEFAULT_TARGET_CPU_TYPE, cpu_model)
>>
>> so that we could drop temporary guard
>>
>> if (machine_class->default_cpu_type) {
>
> This sounds good to me, even if we don't reject -cpu on any
> board.
>
>
>>
>> with that it would be possible to tell from machine_run_board_init()
>> that board doesn't provide cpu but user provided '-cpu'
>> so we would be able to:
>> if ((machine_class->default_cpu_type == NULL) &&
>> (machine->cpu_type != NULL))
>> error_fatal("machine doesn't support -cpu option");
>
> I won't complain too much if a board maintainer really wants to
> make the board reject -cpu completely, but it's up to them.
I disagree. I think a standard way of doing it is better. At least for
each architecture. The ARM -cpu option is very confusing at the moment
and it really doesn't need to be that bad.
>
> Personally, I'd prefer to have all boards setting
> default_cpu_type even if they support only one CPU model, so
> clients don't need a special case for boards that don't support
> -cpu.
I agree, I think having one CPU makes more sense. It makes it easier
to add support for more cpus in the future and allows the users to use
the -cpu option without killing QEMU.
Thanks,
Alistair
>
> --
> Eduardo
>
^ permalink raw reply
* [Bug 75985] [NVC1] HDMI audio device only visible after rescan
From: bugzilla-daemon-CC+yJ3UmIYqDUpFQwHEjaQ @ 2017-10-04 21:39 UTC (permalink / raw)
To: nouveau-PD4FTy7X32lNgt0PjOBp9y5qC8QIuHrW
In-Reply-To: <bug-75985-8800-V0hAGp6uBxMKqLRl/0Ahz6D7qz1kEfGD2LY78lusg7I@public.gmane.org/>
[-- Attachment #1.1: Type: text/plain, Size: 507 bytes --]
https://bugs.freedesktop.org/show_bug.cgi?id=75985
--- Comment #15 from Peter Wu <peter-VTkQYDcBqhK7DlmcbJSQ7g@public.gmane.org> ---
The AER capability was the closest one I could see just before the magic value
of 0x488, it likely has nothing to do with 0x488. I haven't tried
writing/reading it yet.
You might also be interested in this document:
https://github.com/envytools/envytools/blob/master/rnndb/bus/pci.xml
--
You are receiving this mail because:
You are the assignee for the bug.
[-- Attachment #1.2: Type: text/html, Size: 1344 bytes --]
[-- Attachment #2: Type: text/plain, Size: 154 bytes --]
_______________________________________________
Nouveau mailing list
Nouveau@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/nouveau
^ permalink raw reply
* Re: [PATCH v2] doc: add shared library versions for missing PMDs
From: Thomas Monjalon @ 2017-10-04 21:38 UTC (permalink / raw)
To: Yigit, Ferruh; +Cc: dev, Yang, Zhiyong, Mcnamara, John
In-Reply-To: <E182254E98A5DA4EB1E657AC7CB9BD2A8AF1BA09@BGSMSX101.gar.corp.intel.com>
Added comment:
These PMDs must be versioned because they have an API.
> > Signed-off-by: Ferruh Yigit <ferruh.yigit@intel.com>
> > Acked-by: John McNamara <john.mcnamara@intel.com>
>
> Acked-by: Zhiyong Yang <zhiyong.yang@intel.com>
Applied, thanks
^ permalink raw reply
* [PATCH tip/core/rcu 3/3] membarrier: Document scheduler barrier requirements
From: Paul E. McKenney @ 2017-10-04 21:37 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, fweisbec, oleg,
Paul E. McKenney, Boqun Feng, Andrew Hunter, Maged Michael,
gromer, Avi Kivity, Benjamin Herrenschmidt, Paul Mackerras,
Michael Ellerman, Dave Watson, Ingo Molnar, H. Peter Anvin,
Andrea Parri, x86
In-Reply-To: <20171004213734.GA11463@linux.vnet.ibm.com>
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Document the membarrier requirement on having a full memory barrier in
__schedule() after coming from user-space, before storing to rq->curr.
It is provided by smp_mb__after_spinlock() in __schedule().
Document that membarrier requires a full barrier on transition from
kernel thread to userspace thread. We currently have an implicit barrier
from atomic_dec_and_test() in mmdrop() that ensures this.
The x86 switch_mm_irqs_off() full barrier is currently provided by many
cpumask update operations as well as write_cr3(). Document that
write_cr3() provides this barrier.
Changes since v1:
- Update comments to match reality for code paths which are after
storing to rq->curr, before returning to user-space, based on feedback
from Andrea Parri.
Changes since v2:
- Update changelog (smp_mb__before_spinlock -> smp_mb__after_spinlock).
Based on feedback from Andrea Parri.
Changes since v3:
- Clarify comments following feeback from Peter Zijlstra.
Changes since v4:
- Update comment regarding powerpc barrier.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
CC: Boqun Feng <boqun.feng@gmail.com>
CC: Andrew Hunter <ahh@google.com>
CC: Maged Michael <maged.michael@gmail.com>
CC: gromer@google.com
CC: Avi Kivity <avi@scylladb.com>
CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
CC: Michael Ellerman <mpe@ellerman.id.au>
CC: Dave Watson <davejwatson@fb.com>
CC: Thomas Gleixner <tglx@linutronix.de>
CC: Ingo Molnar <mingo@redhat.com>
CC: "H. Peter Anvin" <hpa@zytor.com>
CC: Andrea Parri <parri.andrea@gmail.com>
CC: x86@kernel.org
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
arch/x86/mm/tlb.c | 5 +++++
include/linux/sched/mm.h | 5 +++++
kernel/sched/core.c | 37 ++++++++++++++++++++++++++-----------
3 files changed, 36 insertions(+), 11 deletions(-)
diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
index 49d9778376d7..38f6cbd8cd80 100644
--- a/arch/x86/mm/tlb.c
+++ b/arch/x86/mm/tlb.c
@@ -143,6 +143,11 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
}
#endif
+ /*
+ * The membarrier system call requires a full memory barrier
+ * before returning to user-space, after storing to rq->curr.
+ * Writing to CR3 provides that full memory barrier.
+ */
if (real_prev == next) {
VM_BUG_ON(this_cpu_read(cpu_tlbstate.ctxs[prev_asid].ctx_id) !=
next->context.ctx_id);
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 4af1b719c65f..d5a9ab8f3836 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -38,6 +38,11 @@ static inline void mmgrab(struct mm_struct *mm)
extern void __mmdrop(struct mm_struct *);
static inline void mmdrop(struct mm_struct *mm)
{
+ /*
+ * The implicit full barrier implied by atomic_dec_and_test is
+ * required by the membarrier system call before returning to
+ * user-space, after storing to rq->curr.
+ */
if (unlikely(atomic_dec_and_test(&mm->mm_count)))
__mmdrop(mm);
}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index f29525e453c4..8a176892b4f0 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2648,6 +2648,12 @@ static struct rq *finish_task_switch(struct task_struct *prev)
finish_arch_post_lock_switch();
fire_sched_in_preempt_notifiers(current);
+ /*
+ * When transitioning from a kernel thread to a userspace
+ * thread, mmdrop()'s implicit full barrier is required by the
+ * membarrier system call, because the current active_mm can
+ * become the current mm without going through switch_mm().
+ */
if (mm)
mmdrop(mm);
if (unlikely(prev_state == TASK_DEAD)) {
@@ -2753,6 +2759,13 @@ context_switch(struct rq *rq, struct task_struct *prev,
*/
arch_start_context_switch(prev);
+ /*
+ * If mm is non-NULL, we pass through switch_mm(). If mm is
+ * NULL, we will pass through mmdrop() in finish_task_switch().
+ * Both of these contain the full memory barrier required by
+ * membarrier after storing to rq->curr, before returning to
+ * user-space.
+ */
if (!mm) {
next->active_mm = oldmm;
mmgrab(oldmm);
@@ -3289,6 +3302,9 @@ static void __sched notrace __schedule(bool preempt)
* Make sure that signal_pending_state()->signal_pending() below
* can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
* done by the caller to avoid the race with signal_wake_up().
+ *
+ * The membarrier system call requires a full memory barrier
+ * after coming from user-space, before storing to rq->curr.
*/
rq_lock(rq, &rf);
smp_mb__after_spinlock();
@@ -3336,17 +3352,16 @@ static void __sched notrace __schedule(bool preempt)
/*
* The membarrier system call requires each architecture
* to have a full memory barrier after updating
- * rq->curr, before returning to user-space. For TSO
- * (e.g. x86), the architecture must provide its own
- * barrier in switch_mm(). For weakly ordered machines
- * for which spin_unlock() acts as a full memory
- * barrier, finish_lock_switch() in common code takes
- * care of this barrier. For weakly ordered machines for
- * which spin_unlock() acts as a RELEASE barrier (only
- * arm64 and PowerPC), arm64 has a full barrier in
- * switch_to(), and PowerPC has
- * smp_mb__after_unlock_lock() before
- * finish_lock_switch().
+ * rq->curr, before returning to user-space.
+ *
+ * Here are the schemes providing that barrier on the
+ * various architectures:
+ * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC.
+ * switch_mm() rely on membarrier_arch_switch_mm() on PowerPC.
+ * - finish_lock_switch() for weakly-ordered
+ * architectures where spin_unlock is a full barrier,
+ * - switch_to() for arm64 (weakly-ordered, spin_unlock
+ * is a RELEASE barrier),
*/
++*switch_count;
--
2.5.2
^ permalink raw reply related
* [PATCH tip/core/rcu 2/3] membarrier: selftest: Test private expedited cmd
From: Paul E. McKenney @ 2017-10-04 21:37 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, fweisbec, oleg,
Paul E. McKenney, Boqun Feng, Andrew Hunter, Maged Michael,
gromer, Avi Kivity, Benjamin Herrenschmidt, Paul Mackerras,
Michael Ellerman, Dave Watson, Alan Stern, Will Deacon,
Andy Lutomirski, Alice Ferrazzi, Paul Elder, linux-kselftest,
linux-arch
In-Reply-To: <20171004213734.GA11463@linux.vnet.ibm.com>
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Test the new MEMBARRIER_CMD_PRIVATE_EXPEDITED and
MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED commands.
Add checks expecting specific error values on system calls expected to
fail.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Shuah Khan <shuahkh@osg.samsung.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
CC: Boqun Feng <boqun.feng@gmail.com>
CC: Andrew Hunter <ahh@google.com>
CC: Maged Michael <maged.michael@gmail.com>
CC: gromer@google.com
CC: Avi Kivity <avi@scylladb.com>
CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
CC: Michael Ellerman <mpe@ellerman.id.au>
CC: Dave Watson <davejwatson@fb.com>
CC: Alan Stern <stern@rowland.harvard.edu>
CC: Will Deacon <will.deacon@arm.com>
CC: Andy Lutomirski <luto@kernel.org>
CC: Alice Ferrazzi <alice.ferrazzi@gmail.com>
CC: Paul Elder <paul.elder@pitt.edu>
CC: linux-kselftest@vger.kernel.org
CC: linux-arch@vger.kernel.org
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
.../testing/selftests/membarrier/membarrier_test.c | 109 ++++++++++++++++++---
1 file changed, 94 insertions(+), 15 deletions(-)
diff --git a/tools/testing/selftests/membarrier/membarrier_test.c b/tools/testing/selftests/membarrier/membarrier_test.c
index 21399fcf1a59..f85657374b59 100644
--- a/tools/testing/selftests/membarrier/membarrier_test.c
+++ b/tools/testing/selftests/membarrier/membarrier_test.c
@@ -15,49 +15,119 @@ static int sys_membarrier(int cmd, int flags)
static int test_membarrier_cmd_fail(void)
{
int cmd = -1, flags = 0;
+ const char *test_name = "sys membarrier invalid command";
if (sys_membarrier(cmd, flags) != -1) {
ksft_exit_fail_msg(
- "sys membarrier invalid command test: command = %d, flags = %d. Should fail, but passed\n",
- cmd, flags);
+ "%s test: command = %d, flags = %d. Should fail, but passed\n",
+ test_name, cmd, flags);
+ }
+ if (errno != EINVAL) {
+ ksft_exit_fail_msg(
+ "%s test: flags = %d. Should return (%d: \"%s\"), but returned (%d: \"%s\").\n",
+ test_name, flags, EINVAL, strerror(EINVAL),
+ errno, strerror(errno));
}
ksft_test_result_pass(
- "sys membarrier invalid command test: command = %d, flags = %d. Failed as expected\n",
- cmd, flags);
+ "%s test: command = %d, flags = %d, errno = %d. Failed as expected\n",
+ test_name, cmd, flags, errno);
return 0;
}
static int test_membarrier_flags_fail(void)
{
int cmd = MEMBARRIER_CMD_QUERY, flags = 1;
+ const char *test_name = "sys membarrier MEMBARRIER_CMD_QUERY invalid flags";
if (sys_membarrier(cmd, flags) != -1) {
ksft_exit_fail_msg(
- "sys membarrier MEMBARRIER_CMD_QUERY invalid flags test: flags = %d. Should fail, but passed\n",
- flags);
+ "%s test: flags = %d. Should fail, but passed\n",
+ test_name, flags);
+ }
+ if (errno != EINVAL) {
+ ksft_exit_fail_msg(
+ "%s test: flags = %d. Should return (%d: \"%s\"), but returned (%d: \"%s\").\n",
+ test_name, flags, EINVAL, strerror(EINVAL),
+ errno, strerror(errno));
}
ksft_test_result_pass(
- "sys membarrier MEMBARRIER_CMD_QUERY invalid flags test: flags = %d. Failed as expected\n",
- flags);
+ "%s test: flags = %d, errno = %d. Failed as expected\n",
+ test_name, flags, errno);
return 0;
}
-static int test_membarrier_success(void)
+static int test_membarrier_shared_success(void)
{
int cmd = MEMBARRIER_CMD_SHARED, flags = 0;
- const char *test_name = "sys membarrier MEMBARRIER_CMD_SHARED\n";
+ const char *test_name = "sys membarrier MEMBARRIER_CMD_SHARED";
+
+ if (sys_membarrier(cmd, flags) != 0) {
+ ksft_exit_fail_msg(
+ "%s test: flags = %d, errno = %d\n",
+ test_name, flags, errno);
+ }
+
+ ksft_test_result_pass(
+ "%s test: flags = %d\n", test_name, flags);
+ return 0;
+}
+
+static int test_membarrier_private_expedited_fail(void)
+{
+ int cmd = MEMBARRIER_CMD_PRIVATE_EXPEDITED, flags = 0;
+ const char *test_name = "sys membarrier MEMBARRIER_CMD_PRIVATE_EXPEDITED not registered failure";
+
+ if (sys_membarrier(cmd, flags) != -1) {
+ ksft_exit_fail_msg(
+ "%s test: flags = %d. Should fail, but passed\n",
+ test_name, flags);
+ }
+ if (errno != EPERM) {
+ ksft_exit_fail_msg(
+ "%s test: flags = %d. Should return (%d: \"%s\"), but returned (%d: \"%s\").\n",
+ test_name, flags, EPERM, strerror(EPERM),
+ errno, strerror(errno));
+ }
+
+ ksft_test_result_pass(
+ "%s test: flags = %d, errno = %d\n",
+ test_name, flags, errno);
+ return 0;
+}
+
+static int test_membarrier_register_private_expedited_success(void)
+{
+ int cmd = MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED, flags = 0;
+ const char *test_name = "sys membarrier MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED";
if (sys_membarrier(cmd, flags) != 0) {
ksft_exit_fail_msg(
- "sys membarrier MEMBARRIER_CMD_SHARED test: flags = %d\n",
- flags);
+ "%s test: flags = %d, errno = %d\n",
+ test_name, flags, errno);
}
ksft_test_result_pass(
- "sys membarrier MEMBARRIER_CMD_SHARED test: flags = %d\n",
- flags);
+ "%s test: flags = %d\n",
+ test_name, flags);
+ return 0;
+}
+
+static int test_membarrier_private_expedited_success(void)
+{
+ int cmd = MEMBARRIER_CMD_PRIVATE_EXPEDITED, flags = 0;
+ const char *test_name = "sys membarrier MEMBARRIER_CMD_PRIVATE_EXPEDITED";
+
+ if (sys_membarrier(cmd, flags) != 0) {
+ ksft_exit_fail_msg(
+ "%s test: flags = %d, errno = %d\n",
+ test_name, flags, errno);
+ }
+
+ ksft_test_result_pass(
+ "%s test: flags = %d\n",
+ test_name, flags);
return 0;
}
@@ -71,7 +141,16 @@ static int test_membarrier(void)
status = test_membarrier_flags_fail();
if (status)
return status;
- status = test_membarrier_success();
+ status = test_membarrier_shared_success();
+ if (status)
+ return status;
+ status = test_membarrier_private_expedited_fail();
+ if (status)
+ return status;
+ status = test_membarrier_register_private_expedited_success();
+ if (status)
+ return status;
+ status = test_membarrier_private_expedited_success();
if (status)
return status;
return 0;
--
2.5.2
^ permalink raw reply related
* [PATCH tip/core/rcu 1/3] membarrier: Provide register expedited private command
From: Paul E. McKenney @ 2017-10-04 21:37 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, fweisbec, oleg,
Paul E. McKenney, Boqun Feng, Andrew Hunter, Maged Michael,
gromer, Avi Kivity, Benjamin Herrenschmidt, Paul Mackerras,
Michael Ellerman, Dave Watson, Alan Stern, Will Deacon,
Andy Lutomirski, Ingo Molnar, Alexander Viro, Nicholas Piggin,
linuxppc-dev, linux-arch
In-Reply-To: <20171004213734.GA11463@linux.vnet.ibm.com>
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Provide a new command allowing processes to register their intent to use
the private expedited command.
This allows PowerPC to skip the full memory barrier in switch_mm(), and
only issue the barrier when scheduling into a task belonging to a
process that has registered to use expedited private.
Processes are now required to register before using
MEMBARRIER_CMD_PRIVATE_EXPEDITED, otherwise that command returns EPERM.
Changes since v1:
- Use test_ti_thread_flag(next, ...) instead of test_thread_flag() in
powerpc membarrier_arch_sched_in(), given that we want to specifically
check the next thread state.
- Add missing ARCH_HAS_MEMBARRIER_HOOKS in Kconfig.
- Use task_thread_info() to pass thread_info from task to
*_ti_thread_flag().
Changes since v2:
- Move membarrier_arch_sched_in() call to finish_task_switch().
- Check for NULL t->mm in membarrier_arch_fork().
- Use membarrier_sched_in() in generic code, which invokes the
arch-specific membarrier_arch_sched_in(). This fixes allnoconfig
build on PowerPC.
- Move asm/membarrier.h include under CONFIG_MEMBARRIER, fixing
allnoconfig build on PowerPC.
- Build and runtime tested on PowerPC.
Changes since v3:
- Simply rely on copy_mm() to copy the membarrier_private_expedited mm
field on fork.
- powerpc: test thread flag instead of reading
membarrier_private_expedited in membarrier_arch_fork().
- powerpc: skip memory barrier in membarrier_arch_sched_in() if coming
from kernel thread, since mmdrop() implies a full barrier.
- Set membarrier_private_expedited to 1 only after arch registration
code, thus eliminating a race where concurrent commands could succeed
when they should fail if issued concurrently with process
registration.
- Use READ_ONCE() for membarrier_private_expedited field access in
membarrier_private_expedited. Matches WRITE_ONCE() performed in
process registration.
Changes since v4:
- Move powerpc hook from sched_in() to switch_mm(), based on feedback
from Nicholas Piggin.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
CC: Boqun Feng <boqun.feng@gmail.com>
CC: Andrew Hunter <ahh@google.com>
CC: Maged Michael <maged.michael@gmail.com>
CC: gromer@google.com
CC: Avi Kivity <avi@scylladb.com>
CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
CC: Michael Ellerman <mpe@ellerman.id.au>
CC: Dave Watson <davejwatson@fb.com>
CC: Alan Stern <stern@rowland.harvard.edu>
CC: Will Deacon <will.deacon@arm.com>
CC: Andy Lutomirski <luto@kernel.org>
CC: Ingo Molnar <mingo@redhat.com>
CC: Alexander Viro <viro@zeniv.linux.org.uk>
CC: Nicholas Piggin <npiggin@gmail.com>
CC: linuxppc-dev@lists.ozlabs.org
CC: linux-arch@vger.kernel.org
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
MAINTAINERS | 2 ++
arch/powerpc/Kconfig | 1 +
arch/powerpc/include/asm/membarrier.h | 43 +++++++++++++++++++++++++++++
arch/powerpc/include/asm/thread_info.h | 3 ++
arch/powerpc/kernel/Makefile | 2 ++
arch/powerpc/kernel/membarrier.c | 45 ++++++++++++++++++++++++++++++
arch/powerpc/mm/mmu_context.c | 7 +++++
fs/exec.c | 1 +
include/linux/mm_types.h | 3 ++
include/linux/sched/mm.h | 50 ++++++++++++++++++++++++++++++++++
include/uapi/linux/membarrier.h | 23 +++++++++++-----
init/Kconfig | 3 ++
kernel/fork.c | 2 ++
kernel/sched/core.c | 10 -------
kernel/sched/membarrier.c | 25 ++++++++++++++---
15 files changed, 199 insertions(+), 21 deletions(-)
create mode 100644 arch/powerpc/include/asm/membarrier.h
create mode 100644 arch/powerpc/kernel/membarrier.c
diff --git a/MAINTAINERS b/MAINTAINERS
index 65b0c88d5ee0..c5296d7f447b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8822,6 +8822,8 @@ L: linux-kernel@vger.kernel.org
S: Supported
F: kernel/sched/membarrier.c
F: include/uapi/linux/membarrier.h
+F: arch/powerpc/kernel/membarrier.c
+F: arch/powerpc/include/asm/membarrier.h
MEMORY MANAGEMENT
L: linux-mm@kvack.org
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 809c468edab1..6f44c5f74f71 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -138,6 +138,7 @@ config PPC
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
+ select ARCH_HAS_MEMBARRIER_HOOKS
select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE
select ARCH_HAS_SG_CHAIN
select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
diff --git a/arch/powerpc/include/asm/membarrier.h b/arch/powerpc/include/asm/membarrier.h
new file mode 100644
index 000000000000..61152a7a3cf9
--- /dev/null
+++ b/arch/powerpc/include/asm/membarrier.h
@@ -0,0 +1,43 @@
+#ifndef _ASM_POWERPC_MEMBARRIER_H
+#define _ASM_POWERPC_MEMBARRIER_H
+
+static inline void membarrier_arch_switch_mm(struct mm_struct *prev,
+ struct mm_struct *next, struct task_struct *tsk)
+{
+ /*
+ * Only need the full barrier when switching between processes.
+ * Barrier when switching from kernel to userspace is not
+ * required here, given that it is implied by mmdrop(). Barrier
+ * when switching from userspace to kernel is not needed after
+ * store to rq->curr.
+ */
+ if (likely(!test_ti_thread_flag(task_thread_info(tsk),
+ TIF_MEMBARRIER_PRIVATE_EXPEDITED) || !prev))
+ return;
+
+ /*
+ * The membarrier system call requires a full memory barrier
+ * after storing to rq->curr, before going back to user-space.
+ */
+ smp_mb();
+}
+static inline void membarrier_arch_fork(struct task_struct *t,
+ unsigned long clone_flags)
+{
+ /*
+ * Coherence of TIF_MEMBARRIER_PRIVATE_EXPEDITED against thread
+ * fork is protected by siglock. membarrier_arch_fork is called
+ * with siglock held.
+ */
+ if (test_thread_flag(TIF_MEMBARRIER_PRIVATE_EXPEDITED))
+ set_ti_thread_flag(task_thread_info(t),
+ TIF_MEMBARRIER_PRIVATE_EXPEDITED);
+}
+static inline void membarrier_arch_execve(struct task_struct *t)
+{
+ clear_ti_thread_flag(task_thread_info(t),
+ TIF_MEMBARRIER_PRIVATE_EXPEDITED);
+}
+void membarrier_arch_register_private_expedited(struct task_struct *t);
+
+#endif /* _ASM_POWERPC_MEMBARRIER_H */
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index a941cc6fc3e9..2a208487724b 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -100,6 +100,7 @@ static inline struct thread_info *current_thread_info(void)
#if defined(CONFIG_PPC64)
#define TIF_ELF2ABI 18 /* function descriptors must die! */
#endif
+#define TIF_MEMBARRIER_PRIVATE_EXPEDITED 19 /* membarrier */
/* as above, but as bit values */
#define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE)
@@ -119,6 +120,8 @@ static inline struct thread_info *current_thread_info(void)
#define _TIF_SYSCALL_TRACEPOINT (1<<TIF_SYSCALL_TRACEPOINT)
#define _TIF_EMULATE_STACK_STORE (1<<TIF_EMULATE_STACK_STORE)
#define _TIF_NOHZ (1<<TIF_NOHZ)
+#define _TIF_MEMBARRIER_PRIVATE_EXPEDITED \
+ (1<<TIF_MEMBARRIER_PRIVATE_EXPEDITED)
#define _TIF_SYSCALL_DOTRACE (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
_TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \
_TIF_NOHZ)
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 91960f83039c..2dd4b9e3313a 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -135,6 +135,8 @@ endif
obj-$(CONFIG_EPAPR_PARAVIRT) += epapr_paravirt.o epapr_hcalls.o
obj-$(CONFIG_KVM_GUEST) += kvm.o kvm_emul.o
+obj-$(CONFIG_MEMBARRIER) += membarrier.o
+
# Disable GCOV & sanitizers in odd or sensitive code
GCOV_PROFILE_prom_init.o := n
UBSAN_SANITIZE_prom_init.o := n
diff --git a/arch/powerpc/kernel/membarrier.c b/arch/powerpc/kernel/membarrier.c
new file mode 100644
index 000000000000..b0d79a5f5981
--- /dev/null
+++ b/arch/powerpc/kernel/membarrier.c
@@ -0,0 +1,45 @@
+/*
+ * Copyright (C) 2010-2017 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ *
+ * membarrier system call - PowerPC architecture code
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/sched/mm.h>
+#include <linux/sched/signal.h>
+#include <linux/thread_info.h>
+#include <linux/spinlock.h>
+#include <linux/rcupdate.h>
+
+void membarrier_arch_register_private_expedited(struct task_struct *p)
+{
+ struct task_struct *t;
+
+ if (get_nr_threads(p) == 1) {
+ set_thread_flag(TIF_MEMBARRIER_PRIVATE_EXPEDITED);
+ return;
+ }
+ /*
+ * Coherence of TIF_MEMBARRIER_PRIVATE_EXPEDITED against thread
+ * fork is protected by siglock.
+ */
+ spin_lock(&p->sighand->siglock);
+ for_each_thread(p, t)
+ set_ti_thread_flag(task_thread_info(t),
+ TIF_MEMBARRIER_PRIVATE_EXPEDITED);
+ spin_unlock(&p->sighand->siglock);
+ /*
+ * Ensure all future scheduler executions will observe the new
+ * thread flag state for this process.
+ */
+ synchronize_sched();
+}
diff --git a/arch/powerpc/mm/mmu_context.c b/arch/powerpc/mm/mmu_context.c
index 0f613bc63c50..22f5c91cdc38 100644
--- a/arch/powerpc/mm/mmu_context.c
+++ b/arch/powerpc/mm/mmu_context.c
@@ -12,6 +12,7 @@
#include <linux/mm.h>
#include <linux/cpu.h>
+#include <linux/sched/mm.h>
#include <asm/mmu_context.h>
@@ -67,6 +68,10 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
*
* On the read side the barrier is in pte_xchg(), which orders
* the store to the PTE vs the load of mm_cpumask.
+ *
+ * This full barrier is needed by membarrier when switching
+ * between processes after store to rq->curr, before user-space
+ * memory accesses.
*/
smp_mb();
@@ -89,6 +94,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
if (new_on_cpu)
radix_kvm_prefetch_workaround(next);
+ else
+ membarrier_arch_switch_mm(prev, next, tsk);
/*
* The actual HW switching method differs between the various
diff --git a/fs/exec.c b/fs/exec.c
index ac34d9724684..b2448f2731b3 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1802,6 +1802,7 @@ static int do_execveat_common(int fd, struct filename *filename,
/* execve succeeded */
current->fs->in_exec = 0;
current->in_execve = 0;
+ membarrier_execve(current);
acct_update_integrals(current);
task_numa_free(current);
free_bprm(bprm);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 46f4ecf5479a..5e0fe8ce053b 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -445,6 +445,9 @@ struct mm_struct {
unsigned long flags; /* Must use atomic bitops to access the bits */
struct core_state *core_state; /* coredumping support */
+#ifdef CONFIG_MEMBARRIER
+ int membarrier_private_expedited;
+#endif
#ifdef CONFIG_AIO
spinlock_t ioctx_lock;
struct kioctx_table __rcu *ioctx_table;
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 3a19c253bdb1..4af1b719c65f 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -205,4 +205,54 @@ static inline void memalloc_noreclaim_restore(unsigned int flags)
current->flags = (current->flags & ~PF_MEMALLOC) | flags;
}
+#ifdef CONFIG_MEMBARRIER
+
+#ifdef CONFIG_ARCH_HAS_MEMBARRIER_HOOKS
+#include <asm/membarrier.h>
+#else
+static inline void membarrier_arch_switch_mm(struct mm_struct *prev,
+ struct mm_struct *next, struct task_struct *tsk)
+{
+}
+static inline void membarrier_arch_fork(struct task_struct *t,
+ unsigned long clone_flags)
+{
+}
+static inline void membarrier_arch_execve(struct task_struct *t)
+{
+}
+static inline void membarrier_arch_register_private_expedited(
+ struct task_struct *p)
+{
+}
+#endif
+
+static inline void membarrier_fork(struct task_struct *t,
+ unsigned long clone_flags)
+{
+ /*
+ * Prior copy_mm() copies the membarrier_private_expedited field
+ * from current->mm to t->mm.
+ */
+ membarrier_arch_fork(t, clone_flags);
+}
+static inline void membarrier_execve(struct task_struct *t)
+{
+ t->mm->membarrier_private_expedited = 0;
+ membarrier_arch_execve(t);
+}
+#else
+static inline void membarrier_arch_switch_mm(struct mm_struct *prev,
+ struct mm_struct *next, struct task_struct *tsk)
+{
+}
+static inline void membarrier_fork(struct task_struct *t,
+ unsigned long clone_flags)
+{
+}
+static inline void membarrier_execve(struct task_struct *t)
+{
+}
+#endif
+
#endif /* _LINUX_SCHED_MM_H */
diff --git a/include/uapi/linux/membarrier.h b/include/uapi/linux/membarrier.h
index 6d47b3249d8a..4e01ad7ffe98 100644
--- a/include/uapi/linux/membarrier.h
+++ b/include/uapi/linux/membarrier.h
@@ -52,21 +52,30 @@
* (non-running threads are de facto in such a
* state). This only covers threads from the
* same processes as the caller thread. This
- * command returns 0. The "expedited" commands
- * complete faster than the non-expedited ones,
- * they never block, but have the downside of
- * causing extra overhead.
+ * command returns 0 on success. The
+ * "expedited" commands complete faster than
+ * the non-expedited ones, they never block,
+ * but have the downside of causing extra
+ * overhead. A process needs to register its
+ * intent to use the private expedited command
+ * prior to using it, otherwise this command
+ * returns -EPERM.
+ * @MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED:
+ * Register the process intent to use
+ * MEMBARRIER_CMD_PRIVATE_EXPEDITED. Always
+ * returns 0.
*
* Command to be passed to the membarrier system call. The commands need to
* be a single bit each, except for MEMBARRIER_CMD_QUERY which is assigned to
* the value 0.
*/
enum membarrier_cmd {
- MEMBARRIER_CMD_QUERY = 0,
- MEMBARRIER_CMD_SHARED = (1 << 0),
+ MEMBARRIER_CMD_QUERY = 0,
+ MEMBARRIER_CMD_SHARED = (1 << 0),
/* reserved for MEMBARRIER_CMD_SHARED_EXPEDITED (1 << 1) */
/* reserved for MEMBARRIER_CMD_PRIVATE (1 << 2) */
- MEMBARRIER_CMD_PRIVATE_EXPEDITED = (1 << 3),
+ MEMBARRIER_CMD_PRIVATE_EXPEDITED = (1 << 3),
+ MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED = (1 << 4),
};
#endif /* _UAPI_LINUX_MEMBARRIER_H */
diff --git a/init/Kconfig b/init/Kconfig
index 78cb2461012e..a3dc6a66f0d1 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1400,6 +1400,9 @@ config MEMBARRIER
If unsure, say Y.
+config ARCH_HAS_MEMBARRIER_HOOKS
+ bool
+
config EMBEDDED
bool "Embedded system"
option allnoconfig_y
diff --git a/kernel/fork.c b/kernel/fork.c
index 10646182440f..bd4a93915e08 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1840,6 +1840,8 @@ static __latent_entropy struct task_struct *copy_process(
*/
copy_seccomp(p);
+ membarrier_fork(p, clone_flags);
+
/*
* Process group and session signals need to be delivered to just the
* parent before the fork or both the parent and the child after the
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d17c5da523a0..f29525e453c4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2644,16 +2644,6 @@ static struct rq *finish_task_switch(struct task_struct *prev)
prev_state = prev->state;
vtime_task_switch(prev);
perf_event_task_sched_in(prev, current);
- /*
- * The membarrier system call requires a full memory barrier
- * after storing to rq->curr, before going back to user-space.
- *
- * TODO: This smp_mb__after_unlock_lock can go away if PPC end
- * up adding a full barrier to switch_mm(), or we should figure
- * out if a smp_mb__after_unlock_lock is really the proper API
- * to use.
- */
- smp_mb__after_unlock_lock();
finish_lock_switch(rq, prev);
finish_arch_post_lock_switch();
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index a92fddc22747..f06949a279ca 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -26,21 +26,25 @@
* except MEMBARRIER_CMD_QUERY.
*/
#define MEMBARRIER_CMD_BITMASK \
- (MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED)
+ (MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED \
+ | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED)
static void ipi_mb(void *info)
{
smp_mb(); /* IPIs should be serializing but paranoid. */
}
-static void membarrier_private_expedited(void)
+static int membarrier_private_expedited(void)
{
int cpu;
bool fallback = false;
cpumask_var_t tmpmask;
+ if (!READ_ONCE(current->mm->membarrier_private_expedited))
+ return -EPERM;
+
if (num_online_cpus() == 1)
- return;
+ return 0;
/*
* Matches memory barriers around rq->curr modification in
@@ -94,6 +98,17 @@ static void membarrier_private_expedited(void)
* rq->curr modification in scheduler.
*/
smp_mb(); /* exit from system call is not a mb */
+ return 0;
+}
+
+static void membarrier_register_private_expedited(void)
+{
+ struct task_struct *p = current;
+
+ if (READ_ONCE(p->mm->membarrier_private_expedited))
+ return;
+ membarrier_arch_register_private_expedited(p);
+ WRITE_ONCE(p->mm->membarrier_private_expedited, 1);
}
/**
@@ -144,7 +159,9 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
synchronize_sched();
return 0;
case MEMBARRIER_CMD_PRIVATE_EXPEDITED:
- membarrier_private_expedited();
+ return membarrier_private_expedited();
+ case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED:
+ membarrier_register_private_expedited();
return 0;
default:
return -EINVAL;
--
2.5.2
^ permalink raw reply related
* [PATCH tip/core/rcu 1/3] membarrier: Provide register expedited private command
From: Paul E. McKenney @ 2017-10-04 21:37 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, fweisbec, oleg,
Paul E. McKenney, Boqun Feng, Andrew Hunter, Maged Michael,
gromer, Avi Kivity, Benjamin Herrenschmidt, Paul Mackerras,
Michael Ellerman, Dave Watson, Alan Stern, Will Deacon,
Andy Lutomirski
In-Reply-To: <20171004213734.GA11463@linux.vnet.ibm.com>
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Provide a new command allowing processes to register their intent to use
the private expedited command.
This allows PowerPC to skip the full memory barrier in switch_mm(), and
only issue the barrier when scheduling into a task belonging to a
process that has registered to use expedited private.
Processes are now required to register before using
MEMBARRIER_CMD_PRIVATE_EXPEDITED, otherwise that command returns EPERM.
Changes since v1:
- Use test_ti_thread_flag(next, ...) instead of test_thread_flag() in
powerpc membarrier_arch_sched_in(), given that we want to specifically
check the next thread state.
- Add missing ARCH_HAS_MEMBARRIER_HOOKS in Kconfig.
- Use task_thread_info() to pass thread_info from task to
*_ti_thread_flag().
Changes since v2:
- Move membarrier_arch_sched_in() call to finish_task_switch().
- Check for NULL t->mm in membarrier_arch_fork().
- Use membarrier_sched_in() in generic code, which invokes the
arch-specific membarrier_arch_sched_in(). This fixes allnoconfig
build on PowerPC.
- Move asm/membarrier.h include under CONFIG_MEMBARRIER, fixing
allnoconfig build on PowerPC.
- Build and runtime tested on PowerPC.
Changes since v3:
- Simply rely on copy_mm() to copy the membarrier_private_expedited mm
field on fork.
- powerpc: test thread flag instead of reading
membarrier_private_expedited in membarrier_arch_fork().
- powerpc: skip memory barrier in membarrier_arch_sched_in() if coming
from kernel thread, since mmdrop() implies a full barrier.
- Set membarrier_private_expedited to 1 only after arch registration
code, thus eliminating a race where concurrent commands could succeed
when they should fail if issued concurrently with process
registration.
- Use READ_ONCE() for membarrier_private_expedited field access in
membarrier_private_expedited. Matches WRITE_ONCE() performed in
process registration.
Changes since v4:
- Move powerpc hook from sched_in() to switch_mm(), based on feedback
from Nicholas Piggin.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
CC: Boqun Feng <boqun.feng@gmail.com>
CC: Andrew Hunter <ahh@google.com>
CC: Maged Michael <maged.michael@gmail.com>
CC: gromer@google.com
CC: Avi Kivity <avi@scylladb.com>
CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
CC: Michael Ellerman <mpe@ellerman.id.au>
CC: Dave Watson <davejwatson@fb.com>
CC: Alan Stern <stern@rowland.harvard.edu>
CC: Will Deacon <will.deacon@arm.com>
CC: Andy Lutomirski <luto@kernel.org>
CC: Ingo Molnar <mingo@redhat.com>
CC: Alexander Viro <viro@zeniv.linux.org.uk>
CC: Nicholas Piggin <npiggin@gmail.com>
CC: linuxppc-dev@lists.ozlabs.org
CC: linux-arch@vger.kernel.org
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
MAINTAINERS | 2 ++
arch/powerpc/Kconfig | 1 +
arch/powerpc/include/asm/membarrier.h | 43 +++++++++++++++++++++++++++++
arch/powerpc/include/asm/thread_info.h | 3 ++
arch/powerpc/kernel/Makefile | 2 ++
arch/powerpc/kernel/membarrier.c | 45 ++++++++++++++++++++++++++++++
arch/powerpc/mm/mmu_context.c | 7 +++++
fs/exec.c | 1 +
include/linux/mm_types.h | 3 ++
include/linux/sched/mm.h | 50 ++++++++++++++++++++++++++++++++++
include/uapi/linux/membarrier.h | 23 +++++++++++-----
init/Kconfig | 3 ++
kernel/fork.c | 2 ++
kernel/sched/core.c | 10 -------
kernel/sched/membarrier.c | 25 ++++++++++++++---
15 files changed, 199 insertions(+), 21 deletions(-)
create mode 100644 arch/powerpc/include/asm/membarrier.h
create mode 100644 arch/powerpc/kernel/membarrier.c
diff --git a/MAINTAINERS b/MAINTAINERS
index 65b0c88d5ee0..c5296d7f447b 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -8822,6 +8822,8 @@ L: linux-kernel@vger.kernel.org
S: Supported
F: kernel/sched/membarrier.c
F: include/uapi/linux/membarrier.h
+F: arch/powerpc/kernel/membarrier.c
+F: arch/powerpc/include/asm/membarrier.h
MEMORY MANAGEMENT
L: linux-mm@kvack.org
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 809c468edab1..6f44c5f74f71 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -138,6 +138,7 @@ config PPC
select ARCH_HAS_ELF_RANDOMIZE
select ARCH_HAS_FORTIFY_SOURCE
select ARCH_HAS_GCOV_PROFILE_ALL
+ select ARCH_HAS_MEMBARRIER_HOOKS
select ARCH_HAS_SCALED_CPUTIME if VIRT_CPU_ACCOUNTING_NATIVE
select ARCH_HAS_SG_CHAIN
select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
diff --git a/arch/powerpc/include/asm/membarrier.h b/arch/powerpc/include/asm/membarrier.h
new file mode 100644
index 000000000000..61152a7a3cf9
--- /dev/null
+++ b/arch/powerpc/include/asm/membarrier.h
@@ -0,0 +1,43 @@
+#ifndef _ASM_POWERPC_MEMBARRIER_H
+#define _ASM_POWERPC_MEMBARRIER_H
+
+static inline void membarrier_arch_switch_mm(struct mm_struct *prev,
+ struct mm_struct *next, struct task_struct *tsk)
+{
+ /*
+ * Only need the full barrier when switching between processes.
+ * Barrier when switching from kernel to userspace is not
+ * required here, given that it is implied by mmdrop(). Barrier
+ * when switching from userspace to kernel is not needed after
+ * store to rq->curr.
+ */
+ if (likely(!test_ti_thread_flag(task_thread_info(tsk),
+ TIF_MEMBARRIER_PRIVATE_EXPEDITED) || !prev))
+ return;
+
+ /*
+ * The membarrier system call requires a full memory barrier
+ * after storing to rq->curr, before going back to user-space.
+ */
+ smp_mb();
+}
+static inline void membarrier_arch_fork(struct task_struct *t,
+ unsigned long clone_flags)
+{
+ /*
+ * Coherence of TIF_MEMBARRIER_PRIVATE_EXPEDITED against thread
+ * fork is protected by siglock. membarrier_arch_fork is called
+ * with siglock held.
+ */
+ if (test_thread_flag(TIF_MEMBARRIER_PRIVATE_EXPEDITED))
+ set_ti_thread_flag(task_thread_info(t),
+ TIF_MEMBARRIER_PRIVATE_EXPEDITED);
+}
+static inline void membarrier_arch_execve(struct task_struct *t)
+{
+ clear_ti_thread_flag(task_thread_info(t),
+ TIF_MEMBARRIER_PRIVATE_EXPEDITED);
+}
+void membarrier_arch_register_private_expedited(struct task_struct *t);
+
+#endif /* _ASM_POWERPC_MEMBARRIER_H */
diff --git a/arch/powerpc/include/asm/thread_info.h b/arch/powerpc/include/asm/thread_info.h
index a941cc6fc3e9..2a208487724b 100644
--- a/arch/powerpc/include/asm/thread_info.h
+++ b/arch/powerpc/include/asm/thread_info.h
@@ -100,6 +100,7 @@ static inline struct thread_info *current_thread_info(void)
#if defined(CONFIG_PPC64)
#define TIF_ELF2ABI 18 /* function descriptors must die! */
#endif
+#define TIF_MEMBARRIER_PRIVATE_EXPEDITED 19 /* membarrier */
/* as above, but as bit values */
#define _TIF_SYSCALL_TRACE (1<<TIF_SYSCALL_TRACE)
@@ -119,6 +120,8 @@ static inline struct thread_info *current_thread_info(void)
#define _TIF_SYSCALL_TRACEPOINT (1<<TIF_SYSCALL_TRACEPOINT)
#define _TIF_EMULATE_STACK_STORE (1<<TIF_EMULATE_STACK_STORE)
#define _TIF_NOHZ (1<<TIF_NOHZ)
+#define _TIF_MEMBARRIER_PRIVATE_EXPEDITED \
+ (1<<TIF_MEMBARRIER_PRIVATE_EXPEDITED)
#define _TIF_SYSCALL_DOTRACE (_TIF_SYSCALL_TRACE | _TIF_SYSCALL_AUDIT | \
_TIF_SECCOMP | _TIF_SYSCALL_TRACEPOINT | \
_TIF_NOHZ)
diff --git a/arch/powerpc/kernel/Makefile b/arch/powerpc/kernel/Makefile
index 91960f83039c..2dd4b9e3313a 100644
--- a/arch/powerpc/kernel/Makefile
+++ b/arch/powerpc/kernel/Makefile
@@ -135,6 +135,8 @@ endif
obj-$(CONFIG_EPAPR_PARAVIRT) += epapr_paravirt.o epapr_hcalls.o
obj-$(CONFIG_KVM_GUEST) += kvm.o kvm_emul.o
+obj-$(CONFIG_MEMBARRIER) += membarrier.o
+
# Disable GCOV & sanitizers in odd or sensitive code
GCOV_PROFILE_prom_init.o := n
UBSAN_SANITIZE_prom_init.o := n
diff --git a/arch/powerpc/kernel/membarrier.c b/arch/powerpc/kernel/membarrier.c
new file mode 100644
index 000000000000..b0d79a5f5981
--- /dev/null
+++ b/arch/powerpc/kernel/membarrier.c
@@ -0,0 +1,45 @@
+/*
+ * Copyright (C) 2010-2017 Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
+ *
+ * membarrier system call - PowerPC architecture code
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+ * GNU General Public License for more details.
+ */
+
+#include <linux/sched/mm.h>
+#include <linux/sched/signal.h>
+#include <linux/thread_info.h>
+#include <linux/spinlock.h>
+#include <linux/rcupdate.h>
+
+void membarrier_arch_register_private_expedited(struct task_struct *p)
+{
+ struct task_struct *t;
+
+ if (get_nr_threads(p) == 1) {
+ set_thread_flag(TIF_MEMBARRIER_PRIVATE_EXPEDITED);
+ return;
+ }
+ /*
+ * Coherence of TIF_MEMBARRIER_PRIVATE_EXPEDITED against thread
+ * fork is protected by siglock.
+ */
+ spin_lock(&p->sighand->siglock);
+ for_each_thread(p, t)
+ set_ti_thread_flag(task_thread_info(t),
+ TIF_MEMBARRIER_PRIVATE_EXPEDITED);
+ spin_unlock(&p->sighand->siglock);
+ /*
+ * Ensure all future scheduler executions will observe the new
+ * thread flag state for this process.
+ */
+ synchronize_sched();
+}
diff --git a/arch/powerpc/mm/mmu_context.c b/arch/powerpc/mm/mmu_context.c
index 0f613bc63c50..22f5c91cdc38 100644
--- a/arch/powerpc/mm/mmu_context.c
+++ b/arch/powerpc/mm/mmu_context.c
@@ -12,6 +12,7 @@
#include <linux/mm.h>
#include <linux/cpu.h>
+#include <linux/sched/mm.h>
#include <asm/mmu_context.h>
@@ -67,6 +68,10 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
*
* On the read side the barrier is in pte_xchg(), which orders
* the store to the PTE vs the load of mm_cpumask.
+ *
+ * This full barrier is needed by membarrier when switching
+ * between processes after store to rq->curr, before user-space
+ * memory accesses.
*/
smp_mb();
@@ -89,6 +94,8 @@ void switch_mm_irqs_off(struct mm_struct *prev, struct mm_struct *next,
if (new_on_cpu)
radix_kvm_prefetch_workaround(next);
+ else
+ membarrier_arch_switch_mm(prev, next, tsk);
/*
* The actual HW switching method differs between the various
diff --git a/fs/exec.c b/fs/exec.c
index ac34d9724684..b2448f2731b3 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -1802,6 +1802,7 @@ static int do_execveat_common(int fd, struct filename *filename,
/* execve succeeded */
current->fs->in_exec = 0;
current->in_execve = 0;
+ membarrier_execve(current);
acct_update_integrals(current);
task_numa_free(current);
free_bprm(bprm);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 46f4ecf5479a..5e0fe8ce053b 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -445,6 +445,9 @@ struct mm_struct {
unsigned long flags; /* Must use atomic bitops to access the bits */
struct core_state *core_state; /* coredumping support */
+#ifdef CONFIG_MEMBARRIER
+ int membarrier_private_expedited;
+#endif
#ifdef CONFIG_AIO
spinlock_t ioctx_lock;
struct kioctx_table __rcu *ioctx_table;
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 3a19c253bdb1..4af1b719c65f 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -205,4 +205,54 @@ static inline void memalloc_noreclaim_restore(unsigned int flags)
current->flags = (current->flags & ~PF_MEMALLOC) | flags;
}
+#ifdef CONFIG_MEMBARRIER
+
+#ifdef CONFIG_ARCH_HAS_MEMBARRIER_HOOKS
+#include <asm/membarrier.h>
+#else
+static inline void membarrier_arch_switch_mm(struct mm_struct *prev,
+ struct mm_struct *next, struct task_struct *tsk)
+{
+}
+static inline void membarrier_arch_fork(struct task_struct *t,
+ unsigned long clone_flags)
+{
+}
+static inline void membarrier_arch_execve(struct task_struct *t)
+{
+}
+static inline void membarrier_arch_register_private_expedited(
+ struct task_struct *p)
+{
+}
+#endif
+
+static inline void membarrier_fork(struct task_struct *t,
+ unsigned long clone_flags)
+{
+ /*
+ * Prior copy_mm() copies the membarrier_private_expedited field
+ * from current->mm to t->mm.
+ */
+ membarrier_arch_fork(t, clone_flags);
+}
+static inline void membarrier_execve(struct task_struct *t)
+{
+ t->mm->membarrier_private_expedited = 0;
+ membarrier_arch_execve(t);
+}
+#else
+static inline void membarrier_arch_switch_mm(struct mm_struct *prev,
+ struct mm_struct *next, struct task_struct *tsk)
+{
+}
+static inline void membarrier_fork(struct task_struct *t,
+ unsigned long clone_flags)
+{
+}
+static inline void membarrier_execve(struct task_struct *t)
+{
+}
+#endif
+
#endif /* _LINUX_SCHED_MM_H */
diff --git a/include/uapi/linux/membarrier.h b/include/uapi/linux/membarrier.h
index 6d47b3249d8a..4e01ad7ffe98 100644
--- a/include/uapi/linux/membarrier.h
+++ b/include/uapi/linux/membarrier.h
@@ -52,21 +52,30 @@
* (non-running threads are de facto in such a
* state). This only covers threads from the
* same processes as the caller thread. This
- * command returns 0. The "expedited" commands
- * complete faster than the non-expedited ones,
- * they never block, but have the downside of
- * causing extra overhead.
+ * command returns 0 on success. The
+ * "expedited" commands complete faster than
+ * the non-expedited ones, they never block,
+ * but have the downside of causing extra
+ * overhead. A process needs to register its
+ * intent to use the private expedited command
+ * prior to using it, otherwise this command
+ * returns -EPERM.
+ * @MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED:
+ * Register the process intent to use
+ * MEMBARRIER_CMD_PRIVATE_EXPEDITED. Always
+ * returns 0.
*
* Command to be passed to the membarrier system call. The commands need to
* be a single bit each, except for MEMBARRIER_CMD_QUERY which is assigned to
* the value 0.
*/
enum membarrier_cmd {
- MEMBARRIER_CMD_QUERY = 0,
- MEMBARRIER_CMD_SHARED = (1 << 0),
+ MEMBARRIER_CMD_QUERY = 0,
+ MEMBARRIER_CMD_SHARED = (1 << 0),
/* reserved for MEMBARRIER_CMD_SHARED_EXPEDITED (1 << 1) */
/* reserved for MEMBARRIER_CMD_PRIVATE (1 << 2) */
- MEMBARRIER_CMD_PRIVATE_EXPEDITED = (1 << 3),
+ MEMBARRIER_CMD_PRIVATE_EXPEDITED = (1 << 3),
+ MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED = (1 << 4),
};
#endif /* _UAPI_LINUX_MEMBARRIER_H */
diff --git a/init/Kconfig b/init/Kconfig
index 78cb2461012e..a3dc6a66f0d1 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -1400,6 +1400,9 @@ config MEMBARRIER
If unsure, say Y.
+config ARCH_HAS_MEMBARRIER_HOOKS
+ bool
+
config EMBEDDED
bool "Embedded system"
option allnoconfig_y
diff --git a/kernel/fork.c b/kernel/fork.c
index 10646182440f..bd4a93915e08 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -1840,6 +1840,8 @@ static __latent_entropy struct task_struct *copy_process(
*/
copy_seccomp(p);
+ membarrier_fork(p, clone_flags);
+
/*
* Process group and session signals need to be delivered to just the
* parent before the fork or both the parent and the child after the
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d17c5da523a0..f29525e453c4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2644,16 +2644,6 @@ static struct rq *finish_task_switch(struct task_struct *prev)
prev_state = prev->state;
vtime_task_switch(prev);
perf_event_task_sched_in(prev, current);
- /*
- * The membarrier system call requires a full memory barrier
- * after storing to rq->curr, before going back to user-space.
- *
- * TODO: This smp_mb__after_unlock_lock can go away if PPC end
- * up adding a full barrier to switch_mm(), or we should figure
- * out if a smp_mb__after_unlock_lock is really the proper API
- * to use.
- */
- smp_mb__after_unlock_lock();
finish_lock_switch(rq, prev);
finish_arch_post_lock_switch();
diff --git a/kernel/sched/membarrier.c b/kernel/sched/membarrier.c
index a92fddc22747..f06949a279ca 100644
--- a/kernel/sched/membarrier.c
+++ b/kernel/sched/membarrier.c
@@ -26,21 +26,25 @@
* except MEMBARRIER_CMD_QUERY.
*/
#define MEMBARRIER_CMD_BITMASK \
- (MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED)
+ (MEMBARRIER_CMD_SHARED | MEMBARRIER_CMD_PRIVATE_EXPEDITED \
+ | MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED)
static void ipi_mb(void *info)
{
smp_mb(); /* IPIs should be serializing but paranoid. */
}
-static void membarrier_private_expedited(void)
+static int membarrier_private_expedited(void)
{
int cpu;
bool fallback = false;
cpumask_var_t tmpmask;
+ if (!READ_ONCE(current->mm->membarrier_private_expedited))
+ return -EPERM;
+
if (num_online_cpus() == 1)
- return;
+ return 0;
/*
* Matches memory barriers around rq->curr modification in
@@ -94,6 +98,17 @@ static void membarrier_private_expedited(void)
* rq->curr modification in scheduler.
*/
smp_mb(); /* exit from system call is not a mb */
+ return 0;
+}
+
+static void membarrier_register_private_expedited(void)
+{
+ struct task_struct *p = current;
+
+ if (READ_ONCE(p->mm->membarrier_private_expedited))
+ return;
+ membarrier_arch_register_private_expedited(p);
+ WRITE_ONCE(p->mm->membarrier_private_expedited, 1);
}
/**
@@ -144,7 +159,9 @@ SYSCALL_DEFINE2(membarrier, int, cmd, int, flags)
synchronize_sched();
return 0;
case MEMBARRIER_CMD_PRIVATE_EXPEDITED:
- membarrier_private_expedited();
+ return membarrier_private_expedited();
+ case MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED:
+ membarrier_register_private_expedited();
return 0;
default:
return -EINVAL;
--
2.5.2
^ permalink raw reply related
* [PATCH tip/core/rcu 2/3] membarrier: selftest: Test private expedited cmd
From: Paul E. McKenney @ 2017-10-04 21:37 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, fweisbec, oleg,
Paul E. McKenney, Boqun Feng, Andrew Hunter, Maged Michael,
gromer, Avi Kivity, Benjamin Herrenschmidt, Paul Mackerras,
Michael Ellerman, Dave Watson, Alan Stern, Will Deacon,
Andy Lutomirski
In-Reply-To: <20171004213734.GA11463@linux.vnet.ibm.com>
From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Test the new MEMBARRIER_CMD_PRIVATE_EXPEDITED and
MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED commands.
Add checks expecting specific error values on system calls expected to
fail.
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Acked-by: Shuah Khan <shuahkh@osg.samsung.com>
Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
CC: Peter Zijlstra <peterz@infradead.org>
CC: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
CC: Boqun Feng <boqun.feng@gmail.com>
CC: Andrew Hunter <ahh@google.com>
CC: Maged Michael <maged.michael@gmail.com>
CC: gromer@google.com
CC: Avi Kivity <avi@scylladb.com>
CC: Benjamin Herrenschmidt <benh@kernel.crashing.org>
CC: Paul Mackerras <paulus@samba.org>
CC: Michael Ellerman <mpe@ellerman.id.au>
CC: Dave Watson <davejwatson@fb.com>
CC: Alan Stern <stern@rowland.harvard.edu>
CC: Will Deacon <will.deacon@arm.com>
CC: Andy Lutomirski <luto@kernel.org>
CC: Alice Ferrazzi <alice.ferrazzi@gmail.com>
CC: Paul Elder <paul.elder@pitt.edu>
CC: linux-kselftest@vger.kernel.org
CC: linux-arch@vger.kernel.org
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
.../testing/selftests/membarrier/membarrier_test.c | 109 ++++++++++++++++++---
1 file changed, 94 insertions(+), 15 deletions(-)
diff --git a/tools/testing/selftests/membarrier/membarrier_test.c b/tools/testing/selftests/membarrier/membarrier_test.c
index 21399fcf1a59..f85657374b59 100644
--- a/tools/testing/selftests/membarrier/membarrier_test.c
+++ b/tools/testing/selftests/membarrier/membarrier_test.c
@@ -15,49 +15,119 @@ static int sys_membarrier(int cmd, int flags)
static int test_membarrier_cmd_fail(void)
{
int cmd = -1, flags = 0;
+ const char *test_name = "sys membarrier invalid command";
if (sys_membarrier(cmd, flags) != -1) {
ksft_exit_fail_msg(
- "sys membarrier invalid command test: command = %d, flags = %d. Should fail, but passed\n",
- cmd, flags);
+ "%s test: command = %d, flags = %d. Should fail, but passed\n",
+ test_name, cmd, flags);
+ }
+ if (errno != EINVAL) {
+ ksft_exit_fail_msg(
+ "%s test: flags = %d. Should return (%d: \"%s\"), but returned (%d: \"%s\").\n",
+ test_name, flags, EINVAL, strerror(EINVAL),
+ errno, strerror(errno));
}
ksft_test_result_pass(
- "sys membarrier invalid command test: command = %d, flags = %d. Failed as expected\n",
- cmd, flags);
+ "%s test: command = %d, flags = %d, errno = %d. Failed as expected\n",
+ test_name, cmd, flags, errno);
return 0;
}
static int test_membarrier_flags_fail(void)
{
int cmd = MEMBARRIER_CMD_QUERY, flags = 1;
+ const char *test_name = "sys membarrier MEMBARRIER_CMD_QUERY invalid flags";
if (sys_membarrier(cmd, flags) != -1) {
ksft_exit_fail_msg(
- "sys membarrier MEMBARRIER_CMD_QUERY invalid flags test: flags = %d. Should fail, but passed\n",
- flags);
+ "%s test: flags = %d. Should fail, but passed\n",
+ test_name, flags);
+ }
+ if (errno != EINVAL) {
+ ksft_exit_fail_msg(
+ "%s test: flags = %d. Should return (%d: \"%s\"), but returned (%d: \"%s\").\n",
+ test_name, flags, EINVAL, strerror(EINVAL),
+ errno, strerror(errno));
}
ksft_test_result_pass(
- "sys membarrier MEMBARRIER_CMD_QUERY invalid flags test: flags = %d. Failed as expected\n",
- flags);
+ "%s test: flags = %d, errno = %d. Failed as expected\n",
+ test_name, flags, errno);
return 0;
}
-static int test_membarrier_success(void)
+static int test_membarrier_shared_success(void)
{
int cmd = MEMBARRIER_CMD_SHARED, flags = 0;
- const char *test_name = "sys membarrier MEMBARRIER_CMD_SHARED\n";
+ const char *test_name = "sys membarrier MEMBARRIER_CMD_SHARED";
+
+ if (sys_membarrier(cmd, flags) != 0) {
+ ksft_exit_fail_msg(
+ "%s test: flags = %d, errno = %d\n",
+ test_name, flags, errno);
+ }
+
+ ksft_test_result_pass(
+ "%s test: flags = %d\n", test_name, flags);
+ return 0;
+}
+
+static int test_membarrier_private_expedited_fail(void)
+{
+ int cmd = MEMBARRIER_CMD_PRIVATE_EXPEDITED, flags = 0;
+ const char *test_name = "sys membarrier MEMBARRIER_CMD_PRIVATE_EXPEDITED not registered failure";
+
+ if (sys_membarrier(cmd, flags) != -1) {
+ ksft_exit_fail_msg(
+ "%s test: flags = %d. Should fail, but passed\n",
+ test_name, flags);
+ }
+ if (errno != EPERM) {
+ ksft_exit_fail_msg(
+ "%s test: flags = %d. Should return (%d: \"%s\"), but returned (%d: \"%s\").\n",
+ test_name, flags, EPERM, strerror(EPERM),
+ errno, strerror(errno));
+ }
+
+ ksft_test_result_pass(
+ "%s test: flags = %d, errno = %d\n",
+ test_name, flags, errno);
+ return 0;
+}
+
+static int test_membarrier_register_private_expedited_success(void)
+{
+ int cmd = MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED, flags = 0;
+ const char *test_name = "sys membarrier MEMBARRIER_CMD_REGISTER_PRIVATE_EXPEDITED";
if (sys_membarrier(cmd, flags) != 0) {
ksft_exit_fail_msg(
- "sys membarrier MEMBARRIER_CMD_SHARED test: flags = %d\n",
- flags);
+ "%s test: flags = %d, errno = %d\n",
+ test_name, flags, errno);
}
ksft_test_result_pass(
- "sys membarrier MEMBARRIER_CMD_SHARED test: flags = %d\n",
- flags);
+ "%s test: flags = %d\n",
+ test_name, flags);
+ return 0;
+}
+
+static int test_membarrier_private_expedited_success(void)
+{
+ int cmd = MEMBARRIER_CMD_PRIVATE_EXPEDITED, flags = 0;
+ const char *test_name = "sys membarrier MEMBARRIER_CMD_PRIVATE_EXPEDITED";
+
+ if (sys_membarrier(cmd, flags) != 0) {
+ ksft_exit_fail_msg(
+ "%s test: flags = %d, errno = %d\n",
+ test_name, flags, errno);
+ }
+
+ ksft_test_result_pass(
+ "%s test: flags = %d\n",
+ test_name, flags);
return 0;
}
@@ -71,7 +141,16 @@ static int test_membarrier(void)
status = test_membarrier_flags_fail();
if (status)
return status;
- status = test_membarrier_success();
+ status = test_membarrier_shared_success();
+ if (status)
+ return status;
+ status = test_membarrier_private_expedited_fail();
+ if (status)
+ return status;
+ status = test_membarrier_register_private_expedited_success();
+ if (status)
+ return status;
+ status = test_membarrier_private_expedited_success();
if (status)
return status;
return 0;
--
2.5.2
^ permalink raw reply related
* [PATCH tip/core/rcu 0/3] Updates to sys_membarrier for v4.14 to add registration
From: Paul E. McKenney @ 2017-10-04 21:37 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, fweisbec, oleg
Hello!
This post-merge-window series fixes a problem that arose when designing
requested extensions to sys_membarrier() to allow JITs to efficiently
flush old code from instruction caches. Several potential algorithms are
much less painful if the user register intent to use this functionality
early on, for example, before the process spawns the second thread.
Registering at this time removes the need to interrupt each and every
thread in that process at the first expedited sys_membarrier() system
call.
However, if we let the current function out, then user programs might
be written without registration, which would make it more difficult to
add required registration after the fact. Hence the late-in-merge-window
request. (Ingo, pull request on its way as well.)
1. Provide register expedited private command.
2. Test private expedited cmd.
3. Document scheduler barrier requirements.
All courtesy of Mathieu Desnoyers.
Thanx, Paul
------------------------------------------------------------------------
MAINTAINERS | 2
arch/powerpc/Kconfig | 1
arch/powerpc/include/asm/membarrier.h | 43 +++++++
arch/powerpc/include/asm/thread_info.h | 3
arch/powerpc/kernel/Makefile | 2
arch/powerpc/kernel/membarrier.c | 45 +++++++
arch/powerpc/mm/mmu_context.c | 7 +
arch/x86/mm/tlb.c | 5
fs/exec.c | 1
include/linux/mm_types.h | 3
include/linux/sched/mm.h | 55 +++++++++
include/uapi/linux/membarrier.h | 23 ++--
init/Kconfig | 3
kernel/fork.c | 2
kernel/sched/core.c | 47 ++++----
kernel/sched/membarrier.c | 25 +++-
tools/testing/selftests/membarrier/membarrier_test.c | 109 ++++++++++++++++---
17 files changed, 329 insertions(+), 47 deletions(-)
^ permalink raw reply
* [libnftnl PATCH] expr: Introduce nftnl_expr_fprintf()
From: Phil Sutter @ 2017-10-04 21:36 UTC (permalink / raw)
To: Pablo Neira Ayuso; +Cc: netfilter-devel
Implement expression printing into a FILE pointer analogous to
nftnl_rule_fprintf().
Signed-off-by: Phil Sutter <phil@nwl.cc>
---
include/libnftnl/expr.h | 1 +
src/expr.c | 14 ++++++++++++++
2 files changed, 15 insertions(+)
diff --git a/include/libnftnl/expr.h b/include/libnftnl/expr.h
index 76f28fee7b5f7..f37f50963d6c3 100644
--- a/include/libnftnl/expr.h
+++ b/include/libnftnl/expr.h
@@ -39,6 +39,7 @@ const char *nftnl_expr_get_str(const struct nftnl_expr *expr, uint16_t type);
bool nftnl_expr_cmp(const struct nftnl_expr *e1, const struct nftnl_expr *e2);
int nftnl_expr_snprintf(char *buf, size_t buflen, const struct nftnl_expr *expr, uint32_t type, uint32_t flags);
+int nftnl_expr_fprintf(FILE *fp, const struct nftnl_expr *expr, uint32_t type, uint32_t flags);
enum {
NFTNL_EXPR_PAYLOAD_DREG = NFTNL_EXPR_BASE,
diff --git a/src/expr.c b/src/expr.c
index c5fcf06492ae2..1eae70787209d 100644
--- a/src/expr.c
+++ b/src/expr.c
@@ -293,3 +293,17 @@ int nftnl_expr_snprintf(char *buf, size_t size, const struct nftnl_expr *expr,
return offset;
}
EXPORT_SYMBOL(nftnl_expr_snprintf);
+
+static int nftnl_expr_do_snprintf(char *buf, size_t size, const void *e,
+ uint32_t cmd, uint32_t type, uint32_t flags)
+{
+ return nftnl_expr_snprintf(buf, size, e, type, flags);
+}
+
+int nftnl_expr_fprintf(FILE *fp, const struct nftnl_expr *expr, uint32_t type,
+ uint32_t flags)
+{
+ return nftnl_fprintf(fp, expr, NFTNL_CMD_UNSPEC, type, flags,
+ nftnl_expr_do_snprintf);
+}
+EXPORT_SYMBOL(nftnl_expr_fprintf);
--
2.13.1
^ permalink raw reply related
* [Buildroot] [PATCH v4] HOST_DIR/lib: symlink respectively to lib32/64
From: Matt Weber @ 2017-10-04 21:33 UTC (permalink / raw)
To: buildroot
Discovered the issue on a RHEL7.4 machine where
the cmake build dynamically selected HOST_DIR/lib64
as the installation path for the lzo2 library.
Fixes failures like the following:
host-mtd
http://autobuild.buildroot.net/results/d31/d31581d2e60f35cf70312683df99c768e2ea8516/
host-squashfs
http://autobuild.buildroot.net/results/d9c/d9c95231ac774ed71580754a15ebb3b121764310/
Signed-off-by: Matthew Weber <matthew.weber@rockwellcollins.com>
---
Changes:
[Arnout
v3 -> v4
- Added @ infront of case statement
- Handled case of HOST_DIR ends up being newer and ln -s
would create a link inside of the lib folder. Add -nf
to the args of ln (ie. ln -snf)
[Yann
v2 -> v3
- Updated hostarch logic to check for 64bit in the name
and if present create link. This supports all archs
vs just x86.
v1 -> v2
- Correct the condition used to determine host arch.
(Previously used the target arch check)
---
Makefile | 9 ++++++++-
1 file changed, 8 insertions(+), 1 deletion(-)
diff --git a/Makefile b/Makefile
index 9b09589..02f7cda 100644
--- a/Makefile
+++ b/Makefile
@@ -542,7 +542,7 @@ endif
.PHONY: dirs
dirs: $(BUILD_DIR) $(STAGING_DIR) $(TARGET_DIR) \
- $(HOST_DIR) $(HOST_DIR)/usr $(BINARIES_DIR)
+ $(HOST_DIR) $(HOST_DIR)/usr $(HOST_DIR)/lib $(BINARIES_DIR)
$(BUILD_DIR)/buildroot-config/auto.conf: $(BR2_CONFIG)
$(MAKE1) $(EXTRAMAKEARGS) HOSTCC="$(HOSTCC_NOCCACHE)" HOSTCXX="$(HOSTCXX_NOCCACHE)" silentoldconfig
@@ -565,6 +565,13 @@ sdk: world
$(HOST_DIR)/usr: $(HOST_DIR)
@ln -snf . $@
+$(HOST_DIR)/lib: $(HOST_DIR)
+ @mkdir -p $@
+ @case $(HOSTARCH) in \
+ (*64) ln -snf lib $(@D)/lib64;; \
+ (*) ln -snf lib $(@D)/lib32;; \
+ esac
+
# Populating the staging with the base directories is handled by the skeleton package
$(STAGING_DIR):
@mkdir -p $(STAGING_DIR)
--
1.9.1
^ permalink raw reply related
* [PATCH tip/core/rcu 3/9] rcu: Create call_rcu_tasks() kthread at boot time
From: Paul E. McKenney @ 2017-10-04 21:29 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, fweisbec, oleg,
Paul E. McKenney
In-Reply-To: <20171004212915.GA10089@linux.vnet.ibm.com>
Currently the call_rcu_tasks() kthread is created upon first
invocation of call_rcu_tasks(). This has the advantage of avoiding
creation if there are never any invocations of call_rcu_tasks() and of
synchronize_rcu_tasks(), but it requires an unreliable heuristic to
determine when it is safe to create the kthread. For example, it is
not safe to create the kthread when call_rcu_tasks() is invoked with
a spinlock held, but there is no good way to detect this in !PREEMPT
kernels.
This commit therefore creates this kthread unconditionally at
core_initcall() time. If you don't want this kthread created, then
build with CONFIG_TASKS_RCU=n.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
kernel/rcu/update.c | 24 +++++-------------------
1 file changed, 5 insertions(+), 19 deletions(-)
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 9e599fcdd7bf..ed5922857384 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -585,7 +585,6 @@ DEFINE_STATIC_SRCU(tasks_rcu_exit_srcu);
static int rcu_task_stall_timeout __read_mostly = RCU_TASK_STALL_TIMEOUT;
module_param(rcu_task_stall_timeout, int, 0644);
-static void rcu_spawn_tasks_kthread(void);
static struct task_struct *rcu_tasks_kthread_ptr;
/**
@@ -610,7 +609,6 @@ void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func)
{
unsigned long flags;
bool needwake;
- bool havetask = READ_ONCE(rcu_tasks_kthread_ptr);
rhp->next = NULL;
rhp->func = func;
@@ -620,11 +618,8 @@ void call_rcu_tasks(struct rcu_head *rhp, rcu_callback_t func)
rcu_tasks_cbs_tail = &rhp->next;
raw_spin_unlock_irqrestore(&rcu_tasks_cbs_lock, flags);
/* We can't create the thread unless interrupts are enabled. */
- if ((needwake && havetask) ||
- (!havetask && !irqs_disabled_flags(flags))) {
- rcu_spawn_tasks_kthread();
+ if (needwake && READ_ONCE(rcu_tasks_kthread_ptr))
wake_up(&rcu_tasks_cbs_wq);
- }
}
EXPORT_SYMBOL_GPL(call_rcu_tasks);
@@ -863,27 +858,18 @@ static int __noreturn rcu_tasks_kthread(void *arg)
}
}
-/* Spawn rcu_tasks_kthread() at first call to call_rcu_tasks(). */
-static void rcu_spawn_tasks_kthread(void)
+/* Spawn rcu_tasks_kthread() at core_initcall() time. */
+static int __init rcu_spawn_tasks_kthread(void)
{
- static DEFINE_MUTEX(rcu_tasks_kthread_mutex);
struct task_struct *t;
- if (READ_ONCE(rcu_tasks_kthread_ptr)) {
- smp_mb(); /* Ensure caller sees full kthread. */
- return;
- }
- mutex_lock(&rcu_tasks_kthread_mutex);
- if (rcu_tasks_kthread_ptr) {
- mutex_unlock(&rcu_tasks_kthread_mutex);
- return;
- }
t = kthread_run(rcu_tasks_kthread, NULL, "rcu_tasks_kthread");
BUG_ON(IS_ERR(t));
smp_mb(); /* Ensure others see full kthread. */
WRITE_ONCE(rcu_tasks_kthread_ptr, t);
- mutex_unlock(&rcu_tasks_kthread_mutex);
+ return 0;
}
+core_initcall(rcu_spawn_tasks_kthread);
/* Do the srcu_read_lock() for the above synchronize_srcu(). */
void exit_tasks_rcu_start(void)
--
2.5.2
^ permalink raw reply related
* [PATCH tip/core/rcu 1/9] rcu: Provide GP ordering in face of migrations and delays
From: Paul E. McKenney @ 2017-10-04 21:29 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, fweisbec, oleg,
Paul E. McKenney
In-Reply-To: <20171004212915.GA10089@linux.vnet.ibm.com>
Consider the following admittedly improbable sequence of events:
o RCU is initially idle.
o Task A on CPU 0 executes rcu_read_lock().
o Task B on CPU 1 executes synchronize_rcu(), which must
wait on Task A:
o Task B registers the callback, which starts a new
grace period, awakening the grace-period kthread
on CPU 3, which immediately starts a new grace period.
o Task B migrates to CPU 2, which provides a quiescent
state for both CPUs 1 and 2.
o Both CPUs 1 and 2 take scheduling-clock interrupts,
and both invoke RCU_SOFTIRQ, both thus learning of the
new grace period.
o Task B is delayed, perhaps by vCPU preemption on CPU 2.
o CPUs 2 and 3 pass through quiescent states, which are reported
to core RCU.
o Task B is resumed just long enough to be migrated to CPU 3,
and then is once again delayed.
o Task A executes rcu_read_unlock(), exiting its RCU read-side
critical section.
o CPU 0 passes through a quiescent sate, which is reported to
core RCU. Only CPU 1 continues to block the grace period.
o CPU 1 passes through a quiescent state, which is reported to
core RCU. This ends the grace period, and CPU 1 therefore
invokes its callbacks, one of which awakens Task B via
complete().
o Task B resumes (still on CPU 3) and starts executing
wait_for_completion(), which sees that the completion has
already completed, and thus does not block. It returns from
the synchronize_rcu() without any ordering against the
end of Task A's RCU read-side critical section.
It can therefore mess up Task A's RCU read-side critical section,
in theory, anyway.
However, if CPU hotplug ever gets rid of stop_machine(), there will be
more straightforward ways for this sort of thing to happen, so this
commit adds a memory barrier in order to enforce the needed ordering.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
kernel/rcu/update.c | 10 ++++++++++
1 file changed, 10 insertions(+)
diff --git a/kernel/rcu/update.c b/kernel/rcu/update.c
index 5033b66d2753..9e599fcdd7bf 100644
--- a/kernel/rcu/update.c
+++ b/kernel/rcu/update.c
@@ -413,6 +413,16 @@ void __wait_rcu_gp(bool checktiny, int n, call_rcu_func_t *crcu_array,
wait_for_completion(&rs_array[i].completion);
destroy_rcu_head_on_stack(&rs_array[i].head);
}
+
+ /*
+ * If we migrated after we registered a callback, but before the
+ * corresponding wait_for_completion(), we might now be running
+ * on a CPU that has not yet noticed that the corresponding grace
+ * period has ended. That CPU might not yet be fully ordered
+ * against the completion of the grace period, so the full memory
+ * barrier below enforces that ordering via the completion's state.
+ */
+ smp_mb(); /* ^^^ */
}
EXPORT_SYMBOL_GPL(__wait_rcu_gp);
--
2.5.2
^ permalink raw reply related
* [PATCH tip/core/rcu 5/9] srcu: Add parameters to SRCU docbook comments
From: Paul E. McKenney @ 2017-10-04 21:29 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, fweisbec, oleg,
Paul E. McKenney
In-Reply-To: <20171004212915.GA10089@linux.vnet.ibm.com>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
include/linux/srcu.h | 1 +
kernel/rcu/srcutree.c | 2 +-
2 files changed, 2 insertions(+), 1 deletion(-)
diff --git a/include/linux/srcu.h b/include/linux/srcu.h
index 39af9bc0f653..62be8966e837 100644
--- a/include/linux/srcu.h
+++ b/include/linux/srcu.h
@@ -78,6 +78,7 @@ void synchronize_srcu(struct srcu_struct *sp);
/**
* srcu_read_lock_held - might we be in SRCU read-side critical section?
+ * @sp: The srcu_struct structure to check
*
* If CONFIG_DEBUG_LOCK_ALLOC is selected, returns nonzero iff in an SRCU
* read-side critical section. In absence of CONFIG_DEBUG_LOCK_ALLOC,
diff --git a/kernel/rcu/srcutree.c b/kernel/rcu/srcutree.c
index 729a8706751d..6d5880089ff6 100644
--- a/kernel/rcu/srcutree.c
+++ b/kernel/rcu/srcutree.c
@@ -854,7 +854,7 @@ void __call_srcu(struct srcu_struct *sp, struct rcu_head *rhp,
/**
* call_srcu() - Queue a callback for invocation after an SRCU grace period
* @sp: srcu_struct in queue the callback
- * @head: structure to be used for queueing the SRCU callback.
+ * @rhp: structure to be used for queueing the SRCU callback.
* @func: function to be invoked after the SRCU grace period
*
* The callback function will be invoked some time after a full SRCU
--
2.5.2
^ permalink raw reply related
* Re: [PATCH net-next] openvswitch: Add erspan tunnel support.
From: Pravin Shelar @ 2017-10-04 21:31 UTC (permalink / raw)
To: William Tu; +Cc: Linux Kernel Network Developers
In-Reply-To: <1507118559-13774-1-git-send-email-u9012063@gmail.com>
On Wed, Oct 4, 2017 at 5:02 AM, William Tu <u9012063@gmail.com> wrote:
> Add type II erspan vport implementation. Since erspan protocol is
> on top of the GRE header, the implementation is extended from the
> existing gre implementation.
>
> Signed-off-by: William Tu <u9012063@gmail.com>
> Cc: Pravin B Shelar <pshelar@ovn.org>
Why are you adding ERSPAN support to compat code. Isn't this supported
over OVS netlink-rtnl (dpif-netlink-rtnl)?
^ permalink raw reply
* Re: [lockdep] b09be676e0 BUG: unable to handle kernel NULL pointer dereference at 000001f2
From: Linus Torvalds @ 2017-10-04 21:30 UTC (permalink / raw)
To: Josh Poimboeuf
Cc: Tetsuo Handa, Wu Fengguang, Byungchul Park, Ingo Molnar,
Peter Zijlstra, Linux Kernel Mailing List, LKP, Borislav Petkov,
the arch/x86 maintainers, Peter Anvin, Thomas Gleixner
In-Reply-To: <20171004210624.yyi64y2o5cvbr3d3@treble>
On Wed, Oct 4, 2017 at 2:06 PM, Josh Poimboeuf <jpoimboe@redhat.com> wrote:
>
> I compiled the same kernel with a similar version of GCC. It turns out
> that GCC *does* create unaligned stacks with frame pointers enabled:
Christ. What a piece of crap.
It doesn't even seem to make any sense. Spill room for the "u16
item_count" and "u8 move_type"?
That function is disgusting anyway (the switch really should be
outside the loop, not inside it), but whatever. No excuse for that
kind of garbage code generation.
> This was a leaf function. For no apparent reason, GCC 4.8 decided to
> subtract 3 from the stack pointer in the prologue.
Can you make objtool warn about unaligned stack pointer additions like that?
Maybe it only happens in very limited cases, and we can find a pattern
to why gcc generates garbage code like that? And perhaps even how to
just avoid it?
Linus
^ permalink raw reply
* Re: [PATCH] cma: Take __GFP_NOWARN into account in cma_alloc()
From: Laura Abbott @ 2017-10-04 21:30 UTC (permalink / raw)
To: Boris Brezillon, linux-mm, Andrew Morton
Cc: Jaewon Kim, David Airlie, Daniel Vetter, dri-devel, Eric Anholt
In-Reply-To: <20171004125447.15195-1-boris.brezillon@free-electrons.com>
On 10/04/2017 05:54 AM, Boris Brezillon wrote:
> cma_alloc() unconditionally prints an INFO message when the CMA
> allocation fails. Make this message conditional on the non-presence of
> __GFP_NOWARN in gfp_mask.
>
> Signed-off-by: Boris Brezillon <boris.brezillon@free-electrons.com>
Acked-by: Laura Abbott <labbott@redhat.com>
> ---
> Hello,
>
> This patch aims at removing INFO messages that are displayed when the
> VC4 driver tries to allocate buffer objects. From the driver perspective
> an allocation failure is acceptable, and the driver can possibly do
> something to make following allocation succeed (like flushing the VC4
> internal cache).
>
> Also, I don't understand why this message is only an INFO message, and
> not a WARN (pr_warn()). Please let me know if you have good reasons to
> keep it as an unconditional pr_info().
>
> Thanks,
>
> Boris
> ---
> mm/cma.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/mm/cma.c b/mm/cma.c
> index c0da318c020e..022e52bd8370 100644
> --- a/mm/cma.c
> +++ b/mm/cma.c
> @@ -460,7 +460,7 @@ struct page *cma_alloc(struct cma *cma, size_t count, unsigned int align,
>
> trace_cma_alloc(pfn, page, count, align);
>
> - if (ret) {
> + if (ret && !(gfp_mask & __GFP_NOWARN)) {
> pr_info("%s: alloc failed, req-size: %zu pages, ret: %d\n",
> __func__, count, ret);
> cma_debug_show_areas(cma);
>
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>
^ permalink raw reply
* Re: [lockdep] b09be676e0 BUG: unable to handle kernel NULL pointer dereference at 000001f2
From: Linus Torvalds @ 2017-10-04 21:30 UTC (permalink / raw)
To: lkp
In-Reply-To: <20171004210624.yyi64y2o5cvbr3d3@treble>
[-- Attachment #1: Type: text/plain, Size: 927 bytes --]
On Wed, Oct 4, 2017 at 2:06 PM, Josh Poimboeuf <jpoimboe@redhat.com> wrote:
>
> I compiled the same kernel with a similar version of GCC. It turns out
> that GCC *does* create unaligned stacks with frame pointers enabled:
Christ. What a piece of crap.
It doesn't even seem to make any sense. Spill room for the "u16
item_count" and "u8 move_type"?
That function is disgusting anyway (the switch really should be
outside the loop, not inside it), but whatever. No excuse for that
kind of garbage code generation.
> This was a leaf function. For no apparent reason, GCC 4.8 decided to
> subtract 3 from the stack pointer in the prologue.
Can you make objtool warn about unaligned stack pointer additions like that?
Maybe it only happens in very limited cases, and we can find a pattern
to why gcc generates garbage code like that? And perhaps even how to
just avoid it?
Linus
^ permalink raw reply
* [PATCH tip/core/rcu 7/9] rcu: Pretend ->boost_mtx acquired legitimately
From: Paul E. McKenney @ 2017-10-04 21:29 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, fweisbec, oleg,
Paul E. McKenney
In-Reply-To: <20171004212915.GA10089@linux.vnet.ibm.com>
RCU priority boosting uses rt_mutex_init_proxy_locked() to initialize an
rt_mutex structure in locked state held by some other task. When that
other task releases it, lockdep complains (quite accurately, but a bit
uselessly) that the other task never acquired it. This complaint can
suppress other, more helpful, lockdep complaints, and in any case it is
a false positive.
This commit therefore uses the mutex_acquire() macro to make it look
like that other process legitimately acquired the lock, thus suppressing
this lockdep false-positive complaint.
Of course, if lockdep ever learns about rt_mutex_init_proxy_locked(),
this commit will need to be reverted.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
kernel/rcu/tree_plugin.h | 5 ++++-
1 file changed, 4 insertions(+), 1 deletion(-)
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index fed95fa941e6..60bfb16c9a1a 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -529,8 +529,11 @@ void rcu_read_unlock_special(struct task_struct *t)
}
/* Unboost if we were boosted. */
- if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex)
+ if (IS_ENABLED(CONFIG_RCU_BOOST) && drop_boost_mutex) {
+ /* For lockdep, pretend we acquired lock honestly. */
+ mutex_acquire(&rnp->boost_mtx.dep_map, 0, 0, _RET_IP_);
rt_mutex_unlock(&rnp->boost_mtx);
+ }
/*
* If this was the last task on the expedited lists,
--
2.5.2
^ permalink raw reply related
* [PATCH tip/core/rcu 9/9] rcu/segcblist: Include rcupdate.h
From: Paul E. McKenney @ 2017-10-04 21:29 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, fweisbec, oleg,
Sebastian Andrzej Siewior, Paul E. McKenney
In-Reply-To: <20171004212915.GA10089@linux.vnet.ibm.com>
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
The RT build on ARM complains about non-existing ULONG_CMP_LT.
This commit therefore includes rcupdate.h into rcu_segcblist.c.
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
kernel/rcu/rcu_segcblist.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/kernel/rcu/rcu_segcblist.c b/kernel/rcu/rcu_segcblist.c
index 7649fcd2c4c7..88cba7c2956c 100644
--- a/kernel/rcu/rcu_segcblist.c
+++ b/kernel/rcu/rcu_segcblist.c
@@ -23,6 +23,7 @@
#include <linux/types.h>
#include <linux/kernel.h>
#include <linux/interrupt.h>
+#include <linux/rcupdate.h>
#include "rcu_segcblist.h"
--
2.5.2
^ permalink raw reply related
* [PATCH tip/core/rcu 4/9] irq_work: Map irq_work_on_queue() to irq_work_on() in !SMP
From: Paul E. McKenney @ 2017-10-04 21:29 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, fweisbec, oleg,
Paul E. McKenney
In-Reply-To: <20171004212915.GA10089@linux.vnet.ibm.com>
Commit 478850160636 ("irq_work: Implement remote queueing") provides
irq_work_on_queue() only for SMP builds. However, providing it simplifies
code that submits irq_work to lists of CPUs, eliminating the !SMP special
cases. This commit therefore maps irq_work_on_queue() to irq_work_on()
in !SMP builds, but validating the specified CPU.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
include/linux/irq_work.h | 3 ---
kernel/irq_work.c | 9 ++++++---
2 files changed, 6 insertions(+), 6 deletions(-)
diff --git a/include/linux/irq_work.h b/include/linux/irq_work.h
index 47b9ebd4a74f..d8c9876d5da4 100644
--- a/include/linux/irq_work.h
+++ b/include/linux/irq_work.h
@@ -33,10 +33,7 @@ void init_irq_work(struct irq_work *work, void (*func)(struct irq_work *))
#define DEFINE_IRQ_WORK(name, _f) struct irq_work name = { .func = (_f), }
bool irq_work_queue(struct irq_work *work);
-
-#ifdef CONFIG_SMP
bool irq_work_queue_on(struct irq_work *work, int cpu);
-#endif
void irq_work_tick(void);
void irq_work_sync(struct irq_work *work);
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index bcf107ce0854..9f20f6c72579 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -56,7 +56,6 @@ void __weak arch_irq_work_raise(void)
*/
}
-#ifdef CONFIG_SMP
/*
* Enqueue the irq_work @work on @cpu unless it's already pending
* somewhere.
@@ -68,6 +67,8 @@ bool irq_work_queue_on(struct irq_work *work, int cpu)
/* All work should have been flushed before going offline */
WARN_ON_ONCE(cpu_is_offline(cpu));
+#ifdef CONFIG_SMP
+
/* Arch remote IPI send/receive backend aren't NMI safe */
WARN_ON_ONCE(in_nmi());
@@ -78,10 +79,12 @@ bool irq_work_queue_on(struct irq_work *work, int cpu)
if (llist_add(&work->llnode, &per_cpu(raised_list, cpu)))
arch_send_call_function_single_ipi(cpu);
+#else /* #ifdef CONFIG_SMP */
+ irq_work_queue(work);
+#endif /* #else #ifdef CONFIG_SMP */
+
return true;
}
-EXPORT_SYMBOL_GPL(irq_work_queue_on);
-#endif
/* Enqueue the irq work @work on the current CPU */
bool irq_work_queue(struct irq_work *work)
--
2.5.2
^ permalink raw reply related
* [PATCH tip/core/rcu 2/9] rcu: Fix up pending cbs check in rcu_prepare_for_idle
From: Paul E. McKenney @ 2017-10-04 21:29 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, fweisbec, oleg,
Neeraj Upadhyay, Paul E. McKenney, stable
In-Reply-To: <20171004212915.GA10089@linux.vnet.ibm.com>
From: Neeraj Upadhyay <neeraju@codeaurora.org>
The pending-callbacks check in rcu_prepare_for_idle() is backwards.
It should accelerate if there are pending callbacks, but the check
rather uselessly accelerates only if there are no callbacks. This commit
therefore inverts this check.
Fixes: 15fecf89e46a ("srcu: Abstract multi-tail callback list handling")
Signed-off-by: Neeraj Upadhyay <neeraju@codeaurora.org>
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
Cc: <stable@vger.kernel.org> # 4.12.x
---
kernel/rcu/tree_plugin.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/rcu/tree_plugin.h b/kernel/rcu/tree_plugin.h
index e012b9be777e..fed95fa941e6 100644
--- a/kernel/rcu/tree_plugin.h
+++ b/kernel/rcu/tree_plugin.h
@@ -1507,7 +1507,7 @@ static void rcu_prepare_for_idle(void)
rdtp->last_accelerate = jiffies;
for_each_rcu_flavor(rsp) {
rdp = this_cpu_ptr(rsp->rda);
- if (rcu_segcblist_pend_cbs(&rdp->cblist))
+ if (!rcu_segcblist_pend_cbs(&rdp->cblist))
continue;
rnp = rdp->mynode;
raw_spin_lock_rcu_node(rnp); /* irqs already disabled. */
--
2.5.2
^ permalink raw reply related
* [PATCH tip/core/rcu 8/9] rcu: Add extended-quiescent-state testing advice
From: Paul E. McKenney @ 2017-10-04 21:29 UTC (permalink / raw)
To: linux-kernel
Cc: mingo, jiangshanlai, dipankar, akpm, mathieu.desnoyers, josh,
tglx, peterz, rostedt, dhowells, edumazet, fweisbec, oleg,
Paul E. McKenney
In-Reply-To: <20171004212915.GA10089@linux.vnet.ibm.com>
If you add or remove calls to rcu_idle_enter(), rcu_user_enter(),
rcu_irq_exit(), rcu_irq_exit_irqson(), rcu_idle_exit(), rcu_user_exit(),
rcu_irq_enter(), rcu_irq_enter_irqson(), rcu_nmi_enter(), or
rcu_nmi_exit(), you should run a full set of tests on a kernel built
with CONFIG_RCU_EQS_DEBUG=y.
Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com>
---
kernel/rcu/tree.c | 30 ++++++++++++++++++++++++++++++
1 file changed, 30 insertions(+)
diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
index 0c44c7b42e6d..5186fcea8ba3 100644
--- a/kernel/rcu/tree.c
+++ b/kernel/rcu/tree.c
@@ -837,6 +837,9 @@ static void rcu_eqs_enter(bool user)
* We crowbar the ->dynticks_nesting field to zero to allow for
* the possibility of usermode upcalls having messed up our count
* of interrupt nesting level during the prior busy period.
+ *
+ * If you add or remove a call to rcu_idle_enter(), be sure to test with
+ * CONFIG_RCU_EQS_DEBUG=y.
*/
void rcu_idle_enter(void)
{
@@ -852,6 +855,9 @@ void rcu_idle_enter(void)
* is permitted between this call and rcu_user_exit(). This way the
* CPU doesn't need to maintain the tick for RCU maintenance purposes
* when the CPU runs in userspace.
+ *
+ * If you add or remove a call to rcu_user_enter(), be sure to test with
+ * CONFIG_RCU_EQS_DEBUG=y.
*/
void rcu_user_enter(void)
{
@@ -875,6 +881,9 @@ void rcu_user_enter(void)
* Use things like work queues to work around this limitation.
*
* You have been warned.
+ *
+ * If you add or remove a call to rcu_irq_exit(), be sure to test with
+ * CONFIG_RCU_EQS_DEBUG=y.
*/
void rcu_irq_exit(void)
{
@@ -899,6 +908,9 @@ void rcu_irq_exit(void)
/*
* Wrapper for rcu_irq_exit() where interrupts are enabled.
+ *
+ * If you add or remove a call to rcu_irq_exit_irqson(), be sure to test
+ * with CONFIG_RCU_EQS_DEBUG=y.
*/
void rcu_irq_exit_irqson(void)
{
@@ -971,6 +983,9 @@ static void rcu_eqs_exit(bool user)
* allow for the possibility of usermode upcalls messing up our count
* of interrupt nesting level during the busy period that is just
* now starting.
+ *
+ * If you add or remove a call to rcu_idle_exit(), be sure to test with
+ * CONFIG_RCU_EQS_DEBUG=y.
*/
void rcu_idle_exit(void)
{
@@ -987,6 +1002,9 @@ void rcu_idle_exit(void)
*
* Exit RCU idle mode while entering the kernel because it can
* run a RCU read side critical section anytime.
+ *
+ * If you add or remove a call to rcu_user_exit(), be sure to test with
+ * CONFIG_RCU_EQS_DEBUG=y.
*/
void rcu_user_exit(void)
{
@@ -1012,6 +1030,9 @@ void rcu_user_exit(void)
* Use things like work queues to work around this limitation.
*
* You have been warned.
+ *
+ * If you add or remove a call to rcu_irq_enter(), be sure to test with
+ * CONFIG_RCU_EQS_DEBUG=y.
*/
void rcu_irq_enter(void)
{
@@ -1037,6 +1058,9 @@ void rcu_irq_enter(void)
/*
* Wrapper for rcu_irq_enter() where interrupts are enabled.
+ *
+ * If you add or remove a call to rcu_irq_enter_irqson(), be sure to test
+ * with CONFIG_RCU_EQS_DEBUG=y.
*/
void rcu_irq_enter_irqson(void)
{
@@ -1055,6 +1079,9 @@ void rcu_irq_enter_irqson(void)
* that the CPU is active. This implementation permits nested NMIs, as
* long as the nesting level does not overflow an int. (You will probably
* run out of stack space first.)
+ *
+ * If you add or remove a call to rcu_nmi_enter(), be sure to test
+ * with CONFIG_RCU_EQS_DEBUG=y.
*/
void rcu_nmi_enter(void)
{
@@ -1087,6 +1114,9 @@ void rcu_nmi_enter(void)
* RCU-idle period, update rdtp->dynticks and rdtp->dynticks_nmi_nesting
* to let the RCU grace-period handling know that the CPU is back to
* being RCU-idle.
+ *
+ * If you add or remove a call to rcu_nmi_exit(), be sure to test
+ * with CONFIG_RCU_EQS_DEBUG=y.
*/
void rcu_nmi_exit(void)
{
--
2.5.2
^ permalink raw reply related
page: next (older) | prev (newer) | latest
- recent:[subjects (threaded)|topics (new)|topics (active)]
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.