On 09.09.19 16:35, Jan Beulich wrote:
On 09.08.2019 16:58, Juergen Gross wrote:
--- a/xen/common/schedule.c
+++ b/xen/common/schedule.c
@@ -248,6 +248,20 @@ static inline void vcpu_runstate_change(
v->runstate.state = new_state;
}
+static inline void sched_unit_runstate_change(str
On 09.09.19 17:14, Jan Beulich wrote:
On 09.08.2019 16:58, Juergen Gross wrote:
@@ -504,22 +511,21 @@ int sched_move_domain(struct domain *d, struct cpupool *c)
if ( IS_ERR(domdata) )
return PTR_ERR(domdata);
-vcpu_priv = xzalloc_array(void *, d->max_vcpus);
-
On 12.09.19 16:05, Paul Durrant wrote:
Since commit 0629adfd80e "Actually set a HVM domain's time offset when it
sets the RTC", the comment in the public header has been misleading, since
it claims that wallclock time is only updated by control software.
Moreover, the comments stating that wc_sec
On 12.09.19 16:40, Jan Beulich wrote:
On 12.09.2019 16:02, Juergen Gross wrote:
On 09.09.19 17:14, Jan Beulich wrote:
On 09.08.2019 16:58, Juergen Gross wrote:
@@ -1002,17 +1032,17 @@ int cpu_disable_scheduler(unsigned int cpu)
* * the scheduler will always find a suitable
Add missing #includes.
Signed-off-by: Juergen Gross
---
xen/common/debugtrace.c | 2 ++
1 file changed, 2 insertions(+)
diff --git a/xen/common/debugtrace.c b/xen/common/debugtrace.c
index 5d22d431ad..7313e89389 100644
--- a/xen/common/debugtrace.c
+++ b/xen/common/debugtrace.c
@@ -11,7 +11,9
On 10.09.19 16:06, Jan Beulich wrote:
On 09.08.2019 16:58, Juergen Gross wrote:
vcpu_force_reschedule() is only used for modifying the periodic timer
of a vcpu.
I don't think this is true prior to this patch, or else ...
@@ -419,8 +419,6 @@ int pv_shim_shutdown(uint8_t r
On 13.09.19 11:53, Jan Beulich wrote:
On 12.09.2019 15:28, Juergen Gross wrote:
--- a/xen/common/spinlock.c
+++ b/xen/common/spinlock.c
@@ -348,6 +348,7 @@ static s_time_t lock_profile_start;
static struct lock_profile_anc *lock_profile_ancs;
static struct lock_profile_qhead
concurrent
timer activation via a per-vcpu lock it is even no longer required to
bother the target vcpu at all for updating its timer.
Rename the function to vcpu_set_periodic_timer() as this now reflects
the functionality.
Signed-off-by: Juergen Gross
---
- Carved out from my core scheduling series
On 10.09.19 17:11, Jan Beulich wrote:
On 09.08.2019 16:58, Juergen Gross wrote:
--- a/xen/common/schedule.c
+++ b/xen/common/schedule.c
@@ -733,35 +733,40 @@ void vcpu_unblock(struct vcpu *v)
}
/*
- * Do the actual movement of a vcpu from old to new CPU. Locks for *both*
+ * Do the
On 10.09.19 17:18, Jan Beulich wrote:
On 09.08.2019 16:58, Juergen Gross wrote:
In order to prepare for multiple vcpus per schedule unit move struct
task_slice in schedule() from the local stack into struct sched_unit
of the currently running unit.
The change looks mechanical enough to be
On 10.09.19 17:36, Jan Beulich wrote:
On 09.08.2019 16:58, Juergen Gross wrote:
+static bool sched_tasklet_check(unsigned int cpu)
+{
+bool tasklet_work_scheduled = false;
+const cpumask_t *mask = get_sched_res(cpu)->cpus;
+int cpu_iter;
unsigned int ?
Yes.
+static v
On 11.09.19 12:30, Jan Beulich wrote:
On 09.08.2019 16:58, Juergen Gross wrote:
--- a/xen/common/schedule.c
+++ b/xen/common/schedule.c
@@ -266,7 +266,7 @@ static inline void sched_unit_runstate_change(struct
sched_unit *unit,
struct vcpu *v = unit->vcpu_list;
if ( runn
On 12.09.19 12:24, Dario Faggioli wrote:
On Fri, 2019-08-09 at 16:58 +0200, Juergen Gross wrote:
Today the vcpu runstate of a new scheduled vcpu is always set to
"running" even if at that time vcpu_runnable() is already returning
false due to a race (e.g. with pausing the vcpu).
On 13.09.19 16:42, Jan Beulich wrote:
On 13.09.2019 14:14, Juergen Gross wrote:
---
- Carved out from my core scheduling series
- Reworked to avoid deadlock when 2 vcpus are trying to modify each
others periodic timers, leading to address all comments by Jan
Beulich.
Oh, indeed - a
On 11.09.19 12:43, Jan Beulich wrote:
On 09.08.2019 16:58, Juergen Gross wrote:
V1:
- add special handling for idle unit in unit_runnable() and
unit_runnable_state()
Why was this done? Isn't vcpu_runnable() going to always return
true for idle vCPU-s?
The problem i
On 13.09.19 16:44, Jan Beulich wrote:
On 13.09.2019 16:07, Juergen Gross wrote:
On 11.09.19 12:30, Jan Beulich wrote:
On 09.08.2019 16:58, Juergen Gross wrote:
--- a/xen/include/xen/sched.h
+++ b/xen/include/xen/sched.h
@@ -174,6 +174,7 @@ struct vcpu
XEN_GUEST_HANDLE
On 13.09.19 19:27, Dario Faggioli wrote:
On Mon, 2019-09-09 at 11:33 +0200, Juergen Gross wrote:
Today a cpu which is removed from the system is taken directly from
Pool0 to the offline state. This will conflict with the new idle
scheduler, so remove it from Pool0 first. Additionally accept
don't register it as an
official scheduler, but just include it in schedule.c.
Signed-off-by: Juergen Gross
Acked-by: Dario Faggioli
---
V3:
- use ZERO_BLOCK_PTR instead of (void *)1 (Jan Beulich, Andrew Cooper)
---
xen/common/sched_credit.c | 9 ---
xen/common/sched_null.c | 7 ---
x
longer happen, as parking the not
to be started threads is done before.
Changes in V4:
- fix a bug when unassigning a cpu not in a cpupool (patch 2)
Changes in V3:
- use ZERO_BLOCK_PTR (Patch 3)
- add patch 4
Changes in V2:
- commit messages updated
- renamed functions (Patch 2)
Juergen Gross (4
Instead of having a cpupool_dprintk() define just use debugtrace.
Signed-off-by: Juergen Gross
Acked-by: Dario Faggioli
---
xen/common/cpupool.c | 48 +++-
1 file changed, 23 insertions(+), 25 deletions(-)
diff --git a/xen/common/cpupool.c b/xen
so we need to switch from spinlock_irq to spinlock_irqsave.
Signed-off-by: Juergen Gross
---
V2: rename cpupool_unassign_cpu_[epi|pro]logue() (Dario Faggioli)
V4: fix bug when unassigning cpu not in pool
---
xen/common/cpupool.c | 182 +++--
xen/common
online cpus at that time in order to be able to add the cpu notifier
late, too.
Signed-off-by: Juergen Gross
Reviewed-by: Dario Faggioli
---
V1: new patch
---
xen/common/cpupool.c | 18 ++
1 file changed, 14 insertions(+), 4 deletions(-)
diff --git a/xen/common/cpupool.c b/xen
concurrent
timer activation via a per-vcpu lock it is even no longer required to
bother the target vcpu at all for updating its timer.
Rename the function to vcpu_set_periodic_timer() as this now reflects
the functionality.
Signed-off-by: Juergen Gross
---
- Carved out from my core scheduling series
flag must be kept per vcpu as it is related to
guest actions on specific vcpus. When support of multiple vcpus per
sched_unit is being added, a unit is regarded as being subject to
"broken affinity" when any of its vcpus has the affinity_broken flag
set.
Signed-off-by: Juergen Gross
---
re working now
- idling will always be done with idle_vcpu active
- other small changes see individual patches
Juergen Gross (47):
xen/sched: use new sched_unit instead of vcpu in scheduler interfaces
xen/sched: move per-vcpu scheduler private data pointer to sched_unit
xen/sched: build a link
rename local functions switched to sched_unit, too.
For now this new struct will contain a domain, a vcpu pointer and a
unit_id only and is allocated at vcpu creation time.
Signed-off-by: Juergen Gross
Reviewed-by: Dario Faggioli
---
RFC V2:
- move definition of struct sched_unit to sched.h
Where appropriate switch from for_each_vcpu() to for_each_sched_unit()
in order to prepare core scheduling.
As it is beneficial once here and for sure in future add a
unit_scheduler() helper and let vcpu_scheduler() use it.
Signed-off-by: Juergen Gross
---
V2:
- handle affinity_broken correctly
core or socket only.
Signed-off-by: Juergen Gross
Reviewed-by: Dario Faggioli
---
V1:
- add accessor functions
- use DEFINE_PER_CPU_READ_MOSTLY (Dario Faggioli)
V3:
- don't pre-define struct sched_resource in sched.h (Jan Beulich)
- rename res->processor to res->master_cpu (Jan Beulic
affinity before calling XEN_DOMCTL_max_vcpus.
To be able to use const struct domain * make cpupool_domain_cpumask()
take a const domain pointer, too.
Signed-off-by: Juergen Gross
Acked-by: Andrew Cooper
Acked-by: Julien Grall
---
RFC V2:
- add ASSERT(), modify error message (Andrew Cooper)
V1:
- co
Instead of returning a physical cpu number let pick_cpu() return a
scheduler resource instead. Rename pick_cpu() to pick_resource() to
reflect that change.
Signed-off-by: Juergen Gross
Reviewed-by: Dario Faggioli
---
V3:
- style fix (Jan Beulich)
---
xen/common/sched_arinc653.c | 13
Rename vcpu_schedule_[un]lock[_irq]() to unit_schedule_[un]lock[_irq]()
and let it take a sched_unit pointer instead of a vcpu pointer as
parameter.
Signed-off-by: Juergen Gross
---
xen/common/sched_credit.c | 17 +
xen/common/sched_credit2.c | 40
vcpu_sync_execstate() for each
vcpu of the unit when changing processors.
vcpu_move_locked() is switched to schedule unit, too.
Signed-off-by: Juergen Gross
---
V3:
- move tested invariant condition out of loop (Jan Beulich)
- add comment regarding call of vcpu_sync_execstate() (Jan Beulich
pause_flags of all vcpus of the
unit)
- sched_idle_unit() to get the sched_unit pointer of the idle vcpu of a
specific physical cpu
Signed-off-by: Juergen Gross
---
V3:
- make unit parameter of sched_unit_cpu() const
---
xen/common/sched_credit.c | 3 +--
xen/common/schedule.c | 21
The credit scheduler calls vcpu_pause_nosync() and vcpu_unpause()
today. Add sched_unit_pause_nosync() and sched_unit_unpause() to
perform the same operations on scheduler units instead.
Signed-off-by: Juergen Gross
---
xen/common/sched_credit.c | 6 +++---
xen/include/xen/sched-if.h | 10
This prepares making the different schedulers vcpu agnostic.
Note that some scheduler specific accessor function are misnamed after
this patch. This will be corrected in later patches.
Signed-off-by: Juergen Gross
Reviewed-by: Dario Faggioli
---
xen/common/sched_arinc653.c | 4 ++--
xen
instead.
Add a helper to get that sched_resource master_cpu and modify the
schedulers to use it in a correct way.
Signed-off-by: Juergen Gross
---
V3:
- style correction (Jan Beulich)
- rename cpu to cur_cpu when introducing sched_cpu in same function
(Jan Beulich)
- undo change in
Let the schedulers put a sched_unit pointer into struct task_slice
instead of a vcpu pointer.
Signed-off-by: Juergen Gross
---
xen/common/sched_arinc653.c | 8
xen/common/sched_credit.c | 4 ++--
xen/common/sched_credit2.c | 4 ++--
xen/common/sched_null.c | 12
make it a plain percpu variable.
Signed-off-by: Juergen Gross
---
V1:
- move sched_has_urgent_vcpu()
V2:
- make sched_has_urgent_vcpu() return bool (Jan Beulich)
V3:
- split out removing sched-if.h include in some C files (Jan Beulich)
- make urgent_count a plain percpu variable (Jan Beulich
for_each_sched_unit_vcpu() which
will iterate over all vcpus of a sched_unit (right now only one). This
will be needed later for larger scheduling granularity (e.g. cores).
Signed-off-by: Juergen Gross
Reviewed-by: Dario Faggioli
---
V2:
- add comment (Dario Faggioli)
---
xen/common/schedule.c
.
Signed-off-by: Juergen Gross
---
V3:
- readd accidentally dropped call of continue_running() (Dario Faggioli)
---
xen/common/sched_arinc653.c | 20 +++-
xen/common/sched_credit.c | 25 +++--
xen/common/sched_credit2.c | 21 +
xen/common
Having a pointer to struct cpupool in struct sched_resource instead
of per cpu is enough.
Signed-off-by: Juergen Gross
---
V1: new patch
---
xen/common/cpupool.c | 4 +---
xen/common/sched_credit.c | 2 +-
xen/common/sched_rt.c | 2 +-
xen/common/schedule.c | 8
xen
pdated whenever the is_running indicator is changed.
Use that new field in the schedulers instead of the similar vcpu field.
Signed-off-by: Juergen Gross
---
RFC V2:
- fix arm build, don't drop v->is_running
V3:
- avoid holes in structures (Jan Beulich)
---
xen/common/sched_credit.c | 12 +++
Switch arinc653 scheduler completely from vcpu to sched_unit usage.
Signed-off-by: Juergen Gross
---
xen/common/sched_arinc653.c | 208 +---
1 file changed, 101 insertions(+), 107 deletions(-)
diff --git a/xen/common/sched_arinc653.c b/xen/common
Switch rt scheduler completely from vcpu to sched_unit usage.
Signed-off-by: Juergen Gross
---
xen/common/sched_rt.c | 356 --
1 file changed, 174 insertions(+), 182 deletions(-)
diff --git a/xen/common/sched_rt.c b/xen/common/sched_rt.c
index
cpupool_domain_cpumask() is used by scheduling to select cpus or to
iterate over cpus. In order to support scheduling units spanning
multiple cpus let cpupool_domain_cpumask() return a cpumask with only
one bit set per scheduling resource.
Signed-off-by: Juergen Gross
---
xen/common/cpupool.c
In preparation of core scheduling let the percpu pointer
schedule_data.curr point to a strct sched_unit instead of the related
vcpu. At the same time rename the per-vcpu scheduler specific structs
to per-unit ones.
Signed-off-by: Juergen Gross
Reviewed-by: Dario Faggioli
---
V3:
- remove no
In several places there is support for multiple vcpus per sched unit
missing. Add that missing support (with the exception of initial
allocation) and missing helpers for that.
Signed-off-by: Juergen Gross
---
RFC V2:
- fix vcpu_runstate_helper()
V1:
- add special handling for idle unit in
priority than a normal schedule
event.
Use the same mechanism when waking up a vcpu of a currently active
unit.
While at it make vcpu_sleep_nosync_locked() static as it is used in
schedule.c only.
Signed-off-by: Juergen Gross
---
RFC V2: add vcpu_sleep() handling and force_context_switch flag
V2: fix
selecting the vcpu to switch to, as we already know which vcpu we
want to run. This has the other advantage not to loose any other
concurrent SCHEDULE_SOFTIRQ events.
Signed-off-by: Juergen Gross
---
RFC V2:
- move syncing after context_switch() to schedule.c
V2:
- don't run tasklets directly
Prepare supporting multiple cpus per scheduling resource by allocating
the cpumask per resource dynamically.
Modify sched_res_mask to have only one bit per scheduling resource set.
Signed-off-by: Juergen Gross
---
V1: new patch (carved out from other patch)
---
xen/common/schedule.c | 16
pu struct.
Signed-off-by: Juergen Gross
---
RFC V2:
- new patch
V3:
- add vcpu loop to unit_runnable_state() right now instead of doing
so in next patch (Jan Beulich, Dario Faggioli)
- make new_state unsigned int (Jan Beulich)
---
xen/common/domain.c | 1 +
xen/common/sched_arinc
sched_move_irqs() should work on a sched_unit as that is the unit
moved between cpus.
Rename the current function to vcpu_move_irqs() as it is still needed
in schedule().
Signed-off-by: Juergen Gross
---
xen/common/schedule.c | 18 +-
1 file changed, 13 insertions(+), 5
Having a pointer to struct scheduler in struct sched_resource instead
of per cpu is enough.
Signed-off-by: Juergen Gross
---
V1: new patch
---
xen/common/sched_credit.c | 18 +++---
xen/common/sched_credit2.c | 3 ++-
xen/common/schedule.c | 15 +++
xen/include
Use sched_units instead of vcpus in schedule(). This includes the
introduction of sched_unit_runstate_change() as a replacement of
vcpu_runstate_change() in schedule().
Signed-off-by: Juergen Gross
---
Note that sched_unit_runstate_change() will be subsumed by another
rework in a later patch
Switch credit scheduler completely from vcpu to sched_unit usage.
Signed-off-by: Juergen Gross
---
xen/common/sched_credit.c | 503 +++---
1 file changed, 250 insertions(+), 253 deletions(-)
diff --git a/xen/common/sched_credit.c b/xen/common
Add counters to struct sched_unit summing up runstates of associated
vcpus. This allows doing quick checks whether a unit has any vcpu
running or whether only a single vcpu of a unit is running.
Signed-off-by: Juergen Gross
---
RFC V2: add counters for each possible runstate
---
xen/common
When core or socket scheduling are active enabling or disabling smt is
not possible as that would require a major host reconfiguration.
Add a bool sched_disable_smt_switching which will be set for core or
socket scheduling.
Signed-off-by: Juergen Gross
Acked-by: Jan Beulich
---
V1:
- new patch
softirq handler
with a dummy scheduling routine only enabling tasklets to run.
Signed-off-by: Juergen Gross
---
V2: new patch
---
xen/arch/x86/acpi/power.c | 4
xen/common/schedule.c | 31 +--
xen/include/xen/sched.h | 2 ++
3 files changed, 35 insertions
We'll need a way to free a sched_unit structure without side effects
in a later patch.
Signed-off-by: Juergen Gross
---
RFC V2: new patch, carved out from RFC V1 patch 49
---
xen/common/schedule.c | 38 +-
1 file changed, 21 insertions(+), 17 dele
Switch null scheduler completely from vcpu to sched_unit usage.
Signed-off-by: Juergen Gross
---
xen/common/sched_null.c | 333
1 file changed, 165 insertions(+), 168 deletions(-)
diff --git a/xen/common/sched_null.c b/xen/common/sched_null.c
-off-by: Juergen Gross
---
RFC V2: new patch (carved out from RFC V1 patch 49)
---
xen/common/schedule.c | 11 +--
1 file changed, 9 insertions(+), 2 deletions(-)
diff --git a/xen/common/schedule.c b/xen/common/schedule.c
index 5e34008ca8..246ad38c7d 100644
--- a/xen/common/schedule.c
Instead of letting schedule_cpu_switch() handle moving cpus from and
to cpupools, split it into schedule_cpu_add() and schedule_cpu_rm().
This will allow us to drop allocating/freeing scheduler data for free
cpus as the idle scheduler doesn't need such data.
Signed-off-by: Juergen Gross
-
is needed.
Signed-off-by: Juergen Gross
Acked-by: Julien Grall
---
RFC V2:
- new patch (Andrew Cooper)
V1:
- use urgent_count to select correct idle routine (Jan Beulich)
V2:
- set vcpu->is_running in context_saved()
- introduce reset_stack_and_jump_nolp() (Jan Beulich)
- readd scrubbing
duling resource relation. In order to be able to free
unused resources protect struct sched_resource via RCU. This ensures
there are no users left when freeing such a resource.
Signed-off-by: Juergen Gross
---
V1: new patch
---
xen/common/cpupool.c | 4 +
xen/common/schedule.c
populating the cpupool with cpus.
This will make on- and offlining of cpus much easier and avoids
writing code which would needed to be thrown away later.
Signed-off-by: Juergen Gross
---
V1: new patch
---
xen/common/cpupool.c | 2 ++
xen/common/schedule.c | 27
larity sched_granularity is set after
all cpus are online.
A test is added for all sched resources holding the same number of
cpus. Fall back to core- or cpu-scheduling in that case.
Signed-off-by: Juergen Gross
---
RFC V2:
- fixed freeing of sched_res when merging cpus
- rename parameter to "s
Rename the scheduler related perf counters from vcpu* to unit* where
appropriate.
Signed-off-by: Juergen Gross
---
xen/common/sched_credit.c| 32
xen/common/sched_credit2.c | 18 +-
xen/common/sched_null.c | 18 +-
xen
f the domain's vcpu linked
list, which isn't the case.
Signed-off-by: Juergen Gross
---
xen/common/schedule.c | 86 ++-
1 file changed, 65 insertions(+), 21 deletions(-)
diff --git a/xen/common/schedule.c b/xen/common/schedule.c
index 87660c6
With core scheduling active it is necessary to move multiple cpus at
the same time to or from a cpupool in order to avoid split scheduling
resources in between.
Signed-off-by: Juergen Gross
---
V1: new patch
---
xen/common/cpupool.c | 100 +
xen
pdata and vdata and loop over
those where appropriate.
Additionally the scheduling resource(s) must either be merged or
split.
Signed-off-by: Juergen Gross
---
xen/common/cpupool.c | 18 ++--
xen/common/schedule.c | 226 +++---
2 files changed, 204
Switch credit2 scheduler completely from vcpu to sched_unit usage.
As we are touching lots of lines remove some white space at the end of
the line, too.
Signed-off-by: Juergen Gross
---
xen/common/sched_credit2.c | 820 ++---
1 file changed, 403
On 16.09.19 11:20, Jan Beulich wrote:
On 14.09.2019 08:42, Juergen Gross wrote:
vcpu_force_reschedule() is only used for modifying the periodic timer
of a vcpu. Forcing a vcpu to give up the physical cpu for that purpose
is kind of brutal.
So instead of doing the reschedule dance just operate
On 16.09.19 16:39, Jan Beulich wrote:
On 16.09.2019 14:49, Juergen Gross wrote:
On 16.09.19 11:20, Jan Beulich wrote:
On 14.09.2019 08:42, Juergen Gross wrote:
vcpu_force_reschedule() is only used for modifying the periodic timer
of a vcpu. Forcing a vcpu to give up the physical cpu for that
On 17.09.19 14:31, Julien Grall wrote:
(+ Juergen)
Hi,
On 9/16/19 9:51 AM, Jan Beulich wrote:
On 15.09.2019 19:51, Julien Grall wrote:
Hi,
On 9/15/19 3:09 PM, osstest service owner wrote:
flight 141333 xen-unstable-smoke real [real]
http://logs.test-lab.xenproject.org/osstest/logs/141333/
tively mis-emulating
MOVSXD on modern Intel hardware for quite some time, so it getting
delayed until after 4.13 (and then possible be backported) wouldn't
be overly bad.
1: treat Hygon guests like AMD ones
2: adjust MOVSXD source operand handling
For the series:
Release-acked-by: Juergen G
vcpu_runstate_get() should never return a state entry time with
XEN_RUNSTATE_UPDATE set. To avoid this let update_runstate_area()
operate on a local runstate copy.
This problem was introduced with commit 2529c850ea48f036 ("add update
indicator to vcpu_runstate_info").
Signed-off-b
rew Cooper
Signed-off-by: Juergen Gross
---
V2: add handling on ARM, too (Jan Beulich)
---
xen/arch/arm/domain.c | 13 -
xen/arch/x86/domain.c | 17 ++---
2 files changed, 18 insertions(+), 12 deletions(-)
diff --git a/xen/arch/arm/domain.c b/xen/arch/arm/domain.c
index
Fix two latent bugs discovered in review of my core scheduling series.
For the series:
Release-acked-by: Juergen Gross
Juergen Gross (2):
xen/sched: fix locking in a653sched_free_vdata()
xen/sched: fix freeing per-vcpu data in sched_move_domain()
xen/common/sched_arinc653.c | 6
the sched_free_vdata() hook.
Signed-off-by: Juergen Gross
---
xen/common/schedule.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/xen/common/schedule.c b/xen/common/schedule.c
index 13b5ffc7cf..13c17fe944 100644
--- a/xen/common/schedule.c
+++ b/xen/common/schedule.c
The arinc653 scheduler's free_vdata() function is missing proper
locking: as it is modifying the scheduler's private vcpu list it needs
to take the scheduler lock during that operation.
Signed-off-by: Juergen Gross
---
xen/common/sched_arinc653.c | 6 ++
1 file changed, 6
Linus,
Please git pull the following tag:
git://git.kernel.org/pub/scm/linux/kernel/git/xen/tip.git for-linus-5.4-rc1-tag
xen: features for 5.4-rc1
It contains only two small patches this time:
- a small cleanup for swiotlb-xen
- a fix for PCI initialization for some platforms
Thanks.
Juerg
Signed-off-by: Juergen Gross
---
V2: add handling on ARM, too (Jan Beulich)
---
xen/arch/arm/domain.c | 13 -
xen/arch/x86/domain.c | 17 ++---
2 files changed, 18 insertions(+), 12 deletions(-)
diff --git a/xen/arch/arm/domain.c b/xen/arch/arm/domain.c
index 61d35cd120..
is always shown as empty as those entries are printed in the global
buffer's dump already.
Fix that.
Signed-off-by: Juergen Gross
---
xen/common/debugtrace.c | 1 -
1 file changed, 1 deletion(-)
diff --git a/xen/common/debugtrace.c b/xen/common/debugtrace.c
index 7313e89389..a788e55b4c 100
Let the schedulers put a sched_unit pointer into struct task_slice
instead of a vcpu pointer.
Signed-off-by: Juergen Gross
Reviewed-by: Dario Faggioli
---
xen/common/sched_arinc653.c | 8
xen/common/sched_credit.c | 4 ++--
xen/common/sched_credit2.c | 4 ++--
xen/common
Instead of returning a physical cpu number let pick_cpu() return a
scheduler resource instead. Rename pick_cpu() to pick_resource() to
reflect that change.
Signed-off-by: Juergen Gross
Reviewed-by: Dario Faggioli
---
V3:
- style fix (Jan Beulich)
---
xen/common/sched_arinc653.c | 13
-/offlining support)
- all review comments addressed
- some minor changes (see individual patches)
Changes in RFC V2:
- ARM is building now
- HVM domains are working now
- idling will always be done with idle_vcpu active
- other small changes see individual patches
Juergen Gross (46):
xen/sched: use
make it a plain percpu variable.
Signed-off-by: Juergen Gross
Reviewed-by: Jan Beulich
Reviewed-by: Dario Faggioli
---
V1:
- move sched_has_urgent_vcpu()
V2:
- make sched_has_urgent_vcpu() return bool (Jan Beulich)
V3:
- split out removing sched-if.h include in some C files (Jan Beulich)
- make
Rename vcpu_schedule_[un]lock[_irq]() to unit_schedule_[un]lock[_irq]()
and let it take a sched_unit pointer instead of a vcpu pointer as
parameter.
Signed-off-by: Juergen Gross
Reviewed-by: Dario Faggioli
---
xen/common/sched_credit.c | 17 +
xen/common/sched_credit2.c | 40
Rename the scheduler related perf counters from vcpu* to unit* where
appropriate.
Signed-off-by: Juergen Gross
Reviewed-by: Dario Faggioli
---
xen/common/sched_credit.c| 32
xen/common/sched_credit2.c | 18 +-
xen/common/sched_null.c
Switch credit scheduler completely from vcpu to sched_unit usage.
Signed-off-by: Juergen Gross
Reviewed-by: Dario Faggioli
---
xen/common/sched_credit.c | 503 +++---
1 file changed, 250 insertions(+), 253 deletions(-)
diff --git a/xen/common
for_each_sched_unit_vcpu() which
will iterate over all vcpus of a sched_unit (right now only one). This
will be needed later for larger scheduling granularity (e.g. cores).
Signed-off-by: Juergen Gross
Reviewed-by: Dario Faggioli
---
V2:
- add comment (Dario Faggioli)
V4:
- rename iterator macro
Switch null scheduler completely from vcpu to sched_unit usage.
Signed-off-by: Juergen Gross
Reviewed-by: Dario Faggioli
---
V4:
- Item -> unit (Dario Faggioli)
---
xen/common/sched_null.c | 333
1 file changed, 165 insertions(+), 168 deleti
This prepares making the different schedulers vcpu agnostic.
Note that some scheduler specific accessor function are misnamed after
this patch. This will be corrected in later patches.
Signed-off-by: Juergen Gross
Reviewed-by: Dario Faggioli
---
xen/common/sched_arinc653.c | 4 ++--
xen
core or socket only.
Signed-off-by: Juergen Gross
Reviewed-by: Dario Faggioli
---
V1:
- add accessor functions
- use DEFINE_PER_CPU_READ_MOSTLY (Dario Faggioli)
V3:
- don't pre-define struct sched_resource in sched.h (Jan Beulich)
- rename res->processor to res->master_cpu (Jan Beulic
sched_move_irqs() should work on a sched_unit as that is the unit
moved between cpus.
Rename the current function to vcpu_move_irqs() as it is still needed
in schedule().
Signed-off-by: Juergen Gross
Reviewed-by: Dario Faggioli
---
V4:
- make parameter const (Jan Beulich)
---
xen/common
flag must be kept per vcpu as it is related to
guest actions on specific vcpus. When support of multiple vcpus per
sched_unit is being added, a unit is regarded as being subject to
"broken affinity" when any of its vcpus has the affinity_broken flag
set.
Signed-off-by: Juergen Gross
Ack
In preparation of core scheduling let the percpu pointer
schedule_data.curr point to a strct sched_unit instead of the related
vcpu. At the same time rename the per-vcpu scheduler specific structs
to per-unit ones.
Signed-off-by: Juergen Gross
Reviewed-by: Dario Faggioli
---
V3:
- remove no
pdated whenever the is_running indicator is changed.
Use that new field in the schedulers instead of the similar vcpu field.
Signed-off-by: Juergen Gross
Reviewed-by: Dario Faggioli
---
RFC V2:
- fix arm build, don't drop v->is_running
V3:
- avoid holes in structures (Jan Beulich)
V4:
- assign
In several places there is support for multiple vcpus per sched unit
missing. Add that missing support (with the exception of initial
allocation) and missing helpers for that.
Signed-off-by: Juergen Gross
---
RFC V2:
- fix vcpu_runstate_helper()
V1:
- add special handling for idle unit in
pause_flags of all vcpus of the
unit)
- sched_idle_unit() to get the sched_unit pointer of the idle vcpu of a
specific physical cpu
Signed-off-by: Juergen Gross
---
V3:
- make unit parameter of sched_unit_cpu() const
V4:
- loop over vcpus in helpers where appropriate (Jan Beulich)
- add some
201 - 300 of 7454 matches
Mail list logo
