Message ID | 20201208212841.694b3022@orivej.orivej.org |
---|---|
State | New |
Headers | show |
Series | sched: exporting linux-rt migrate_disable for ZFS | expand |
On 2020-12-08 23:58:27 [+0000], Orivej Desh wrote: > Greetings! Hi, > With sched-Add-migrate_disable.patch first released in v5.9-rc8-rt14 [1] > linux-rt defines functions migrate_disable and migrate_enable. > They are used in linux headers in various macros and static inline > functions, and in particular in kmap_atomic and kunmap_atomic. > The latter are needed by ZFS which currently fails to build against > 5.9-rt [2] because these functions are exported with EXPORT_SYMBOL_GPL. > Could you export them with EXPORT_SYMBOL instead? This is out of my jurisdiction, so just a few notes: - v5.9 is out of maintenance. Be careful. - We don't export symbols for out-of-tree modules. Sebastian
* Sebastian Andrzej Siewior <bigeasy@linutronix.de> [2020-12-14] > On 2020-12-08 23:58:27 [+0000], Orivej Desh wrote: > > With sched-Add-migrate_disable.patch first released in v5.9-rc8-rt14 [1] > > linux-rt defines functions migrate_disable and migrate_enable. > > They are used in linux headers in various macros and static inline > > functions, and in particular in kmap_atomic and kunmap_atomic. > > The latter are needed by ZFS which currently fails to build against > > 5.9-rt [2] because these functions are exported with EXPORT_SYMBOL_GPL. > > Could you export them with EXPORT_SYMBOL instead? > > This is out of my jurisdiction, so just a few notes: > - v5.9 is out of maintenance. Be careful. Thanks! I have noticed a bug with usb-storage (using smp_processor_id in preemptible code) in 5.9.1-rt20 thas has been fixed in 5.10-rt17. > - We don't export symbols for out-of-tree modules. The issue is that in the vanilla kernel these two functions are available as macros that expand into EXPORT_SYMBOL function calls (kunmap_atomic_high, etc.). If I am not mistaken the kernel is generally supposed to keep the API made available to non-GPL modules still available, for example here https://lwn.net/Articles/171838/ : "When GPL-only exports were first added to the kernel, they went in with the understanding that only new symbols would be tagged GPL-only. The current module interface - while always subject to change - was not to have symbols withdrawn arbitrarily." The current rt patch has this effect: it makes non-GPL API of the vanilla kernel GPL-only.
On Mon, 2020-12-14 at 13:33 +0100, Sebastian Andrzej Siewior wrote: > On 2020-12-08 23:58:27 [+0000], Orivej Desh wrote: > > Greetings! > Hi, > > > With sched-Add-migrate_disable.patch first released in v5.9-rc8-rt14 [1] > > linux-rt defines functions migrate_disable and migrate_enable. > > They are used in linux headers in various macros and static inline > > functions, and in particular in kmap_atomic and kunmap_atomic. > > The latter are needed by ZFS which currently fails to build against > > 5.9-rt [2] because these functions are exported with EXPORT_SYMBOL_GPL. > > Could you export them with EXPORT_SYMBOL instead? > > This is out of my jurisdiction, so just a few notes: > - v5.9 is out of maintenance. Be careful. > - We don't export symbols for out-of-tree modules. Hm, dejavu all over again. I recall this issue long ago having been resolved in favor of exporting via plain EXPORT_SYMBOL. https://lore.kernel.org/linux-rt-users/1321359802.4181.1.camel@frodo/ From 859a31c5ec958326dd046f4e41f6fa0db0ce98c3 Mon Sep 17 00:00:00 2001 From: Steven Rostedt <srostedt@redhat.com> Date: Mon, 16 Apr 2012 21:51:54 -0400 Subject: rt: Make migrate_disable/enable() and __rt_mutex_init non-GPL only Modules that load on the normal vanilla kernel should also load on an -rt kernel as well. This does not mean we condone non-GPL modules, we are only being consistent. Signed-off-by: Steven Rostedt <rostedt@goodmis.org> --- kernel/rtmutex.c | 2 +- kernel/sched.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) diff --git a/kernel/rtmutex.c b/kernel/rtmutex.c index a02fbd9f9583..d58db993f5cd 100644 --- a/kernel/rtmutex.c +++ b/kernel/rtmutex.c @@ -1282,7 +1282,7 @@ void __rt_mutex_init(struct rt_mutex *lock, const char *name) debug_rt_mutex_init(lock, name); } -EXPORT_SYMBOL_GPL(__rt_mutex_init); +EXPORT_SYMBOL(__rt_mutex_init); /** * rt_mutex_init_proxy_locked - initialize and lock a rt_mutex on behalf of a diff --git a/kernel/sched.c b/kernel/sched.c index df3048139d1b..ed3433573641 100644 --- a/kernel/sched.c +++ b/kernel/sched.c @@ -4255,7 +4255,7 @@ void migrate_disable(void) p->migrate_disable = 1; preempt_enable(); } -EXPORT_SYMBOL_GPL(migrate_disable); +EXPORT_SYMBOL(migrate_disable); void migrate_enable(void) { @@ -4307,7 +4307,7 @@ void migrate_enable(void) unpin_current_cpu(); preempt_enable(); } -EXPORT_SYMBOL_GPL(migrate_enable); +EXPORT_SYMBOL(migrate_enable); #else static inline void update_migrate_disable(struct task_struct *p) { } #define migrate_disabled_updated(p) 0 -- 2.29.2
On Tue, 15 Dec 2020 04:19:23 +0100 Mike Galbraith <efault@gmx.de> wrote: > From 859a31c5ec958326dd046f4e41f6fa0db0ce98c3 Mon Sep 17 00:00:00 2001 > From: Steven Rostedt <srostedt@redhat.com> > Date: Mon, 16 Apr 2012 21:51:54 -0400 > Subject: rt: Make migrate_disable/enable() and __rt_mutex_init non-GPL only > > Modules that load on the normal vanilla kernel should also load on > an -rt kernel as well. This does not mean we condone non-GPL modules, > we are only being consistent. > > Signed-off-by: Steven Rostedt <rostedt@goodmis.org> Yep, Back in the day (like in 2005), we said that -rt should strive to work wherever vanilla Linux works. Thus, if we add a symbol that replaces a non GPL symbol, we need to keep that symbol non GPL. -- Steve
--- a/kernel/sched/core.c +++ b/kernel/sched/core.c @@ -1812 +1812 @@ void migrate_disable(void) -EXPORT_SYMBOL_GPL(migrate_disable); +EXPORT_SYMBOL(migrate_disable); @@ -1843 +1843 @@ void migrate_enable(void) -EXPORT_SYMBOL_GPL(migrate_enable); +EXPORT_SYMBOL(migrate_enable);