diff mbox series

[v6,22/24] x86/resctrl: Add cpu offline callback for resctrl work

Message ID 20230914172138.11977-23-james.morse@arm.com
State New
Headers
Series x86/resctrl: monitored closid+rmid together, separate arch/fs locking |

Commit Message

James Morse Sept. 14, 2023, 5:21 p.m. UTC 
  The resctrl architecture specific code may need to free a domain when
a CPU goes offline, it also needs to reset the CPUs PQR_ASSOC register.
Amongst other things, the resctrl filesystem code needs to clear this
CPU from the cpu_mask of any control and monitor groups.

Currently this is all done in core.c and called from
resctrl_offline_cpu(), making the split between architecture and
filesystem code unclear.

Move the filesystem work to remove the CPU from the control and monitor
groups into a filesystem helper called resctrl_offline_cpu(), and rename
the one in core.c resctrl_arch_offline_cpu().

The rdtgroup_mutex is unlocked and locked again in the call in
preparation for changing the locking rules for the architecture
code.

Reviewed-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
Tested-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
Tested-By: Peter Newman <peternewman@google.com>
Signed-off-by: James Morse <james.morse@arm.com>
---
 arch/x86/kernel/cpu/resctrl/core.c     | 25 +++++--------------------
 arch/x86/kernel/cpu/resctrl/rdtgroup.c | 24 ++++++++++++++++++++++++
 include/linux/resctrl.h                |  1 +
 3 files changed, 30 insertions(+), 20 deletions(-)

Comments

Reinette Chatre Oct. 3, 2023, 9:23 p.m. UTC | #1 
Hi James,

On 9/14/2023 10:21 AM, James Morse wrote:
> The resctrl architecture specific code may need to free a domain when
> a CPU goes offline, it also needs to reset the CPUs PQR_ASSOC register.
> Amongst other things, the resctrl filesystem code needs to clear this
> CPU from the cpu_mask of any control and monitor groups.
> 
> Currently this is all done in core.c and called from
> resctrl_offline_cpu(), making the split between architecture and
> filesystem code unclear.
> 
> Move the filesystem work to remove the CPU from the control and monitor
> groups into a filesystem helper called resctrl_offline_cpu(), and rename
> the one in core.c resctrl_arch_offline_cpu().
> 
> The rdtgroup_mutex is unlocked and locked again in the call in
> preparation for changing the locking rules for the architecture
> code.

This last paragraph may cause some confusion since this refactoring
is not changing any current locking. I'll defer to you if you prefer
to keep it.

> 
> Reviewed-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
> Tested-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
> Tested-By: Peter Newman <peternewman@google.com>
> Signed-off-by: James Morse <james.morse@arm.com>
> ---

Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>

Reinette
James Morse Oct. 25, 2023, 5:57 p.m. UTC | #2 
Hi Reinette,

On 03/10/2023 22:23, Reinette Chatre wrote:
> On 9/14/2023 10:21 AM, James Morse wrote:
>> The resctrl architecture specific code may need to free a domain when
>> a CPU goes offline, it also needs to reset the CPUs PQR_ASSOC register.
>> Amongst other things, the resctrl filesystem code needs to clear this
>> CPU from the cpu_mask of any control and monitor groups.
>>
>> Currently this is all done in core.c and called from
>> resctrl_offline_cpu(), making the split between architecture and
>> filesystem code unclear.
>>
>> Move the filesystem work to remove the CPU from the control and monitor
>> groups into a filesystem helper called resctrl_offline_cpu(), and rename
>> the one in core.c resctrl_arch_offline_cpu().
>>
>> The rdtgroup_mutex is unlocked and locked again in the call in
>> preparation for changing the locking rules for the architecture
>> code.
> 
> This last paragraph may cause some confusion since this refactoring
> is not changing any current locking. I'll defer to you if you prefer
> to keep it.

Hmm, that is referring to an earlier version that looked funny and I felt needed
explanation. I've remove that paragraph.


>> Reviewed-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
>> Tested-by: Shaopeng Tan <tan.shaopeng@fujitsu.com>
>> Tested-By: Peter Newman <peternewman@google.com>
>> Signed-off-by: James Morse <james.morse@arm.com>
>> ---
> 
> Reviewed-by: Reinette Chatre <reinette.chatre@intel.com>


Thanks!

James
diff mbox series

Patch

diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 37aa124f1e4c..00b1592fd059 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -623,31 +623,15 @@  static int resctrl_arch_online_cpu(unsigned int cpu)
 	return 0;
 }
 
-static void clear_childcpus(struct rdtgroup *r, unsigned int cpu)
+static int resctrl_arch_offline_cpu(unsigned int cpu)
 {
-	struct rdtgroup *cr;
-
-	list_for_each_entry(cr, &r->mon.crdtgrp_list, mon.crdtgrp_list) {
-		if (cpumask_test_and_clear_cpu(cpu, &cr->cpu_mask)) {
-			break;
-		}
-	}
-}
-
-static int resctrl_offline_cpu(unsigned int cpu)
-{
-	struct rdtgroup *rdtgrp;
 	struct rdt_resource *r;
 
 	mutex_lock(&rdtgroup_mutex);
+	resctrl_offline_cpu(cpu);
+
 	for_each_capable_rdt_resource(r)
 		domain_remove_cpu(cpu, r);
-	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
-		if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) {
-			clear_childcpus(rdtgrp, cpu);
-			break;
-		}
-	}
 	clear_closid_rmid(cpu);
 	mutex_unlock(&rdtgroup_mutex);
 
@@ -970,7 +954,8 @@  static int __init resctrl_late_init(void)
 
 	state = cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
 				  "x86/resctrl/cat:online:",
-				  resctrl_arch_online_cpu, resctrl_offline_cpu);
+				  resctrl_arch_online_cpu,
+				  resctrl_arch_offline_cpu);
 	if (state < 0)
 		return state;
 
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 49f100c73838..f06a80d8fa3b 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -3878,6 +3878,30 @@  void resctrl_online_cpu(unsigned int cpu)
 	cpumask_set_cpu(cpu, &rdtgroup_default.cpu_mask);
 }
 
+static void clear_childcpus(struct rdtgroup *r, unsigned int cpu)
+{
+	struct rdtgroup *cr;
+
+	list_for_each_entry(cr, &r->mon.crdtgrp_list, mon.crdtgrp_list) {
+		if (cpumask_test_and_clear_cpu(cpu, &cr->cpu_mask))
+			break;
+	}
+}
+
+void resctrl_offline_cpu(unsigned int cpu)
+{
+	struct rdtgroup *rdtgrp;
+
+	lockdep_assert_held(&rdtgroup_mutex);
+
+	list_for_each_entry(rdtgrp, &rdt_all_groups, rdtgroup_list) {
+		if (cpumask_test_and_clear_cpu(cpu, &rdtgrp->cpu_mask)) {
+			clear_childcpus(rdtgrp, cpu);
+			break;
+		}
+	}
+}
+
 /*
  * rdtgroup_init - rdtgroup initialization
  *
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 0888d1975161..74886cda5f66 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -226,6 +226,7 @@  u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d,
 int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d);
 void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d);
 void resctrl_online_cpu(unsigned int cpu);
+void resctrl_offline_cpu(unsigned int cpu);
 
 /**
  * resctrl_arch_rmid_read() - Read the eventid counter corresponding to rmid