When a CPU is taken offline resctrl may need to move the overflow or
limbo handlers to run on a different CPU.
Once the offline callbacks have been split, cqm_setup_limbo_handler()
will be called while the CPU that is going offline is still present
in the cpu_mask.
Pass the CPU to exclude to cqm_setup_limbo_handler() and
mbm_setup_overflow_handler(). These functions can use a variant of
cpumask_any_but() when selecting the CPU. -1 is used to indicate no CPUs
need excluding.
Signed-off-by: James Morse <[email protected]>
Tested-by: Shaopeng Tan <[email protected]>
Tested-by: Peter Newman <[email protected]>
Tested-by: Babu Moger <[email protected]>
Tested-by: Carl Worth <[email protected]> # arm64
Reviewed-by: Shaopeng Tan <[email protected]>
Reviewed-by: Babu Moger <[email protected]>
Reviewed-by: Reinette Chatre <[email protected]>
---
Changes since v2:
* Rephrased a comment to avoid a two letter bad-word. (we)
* Avoid assigning mbm_work_cpu if the domain is going to be free()d
* Added cpumask_any_housekeeping_but(), I dislike the name
Changes since v3:
* Marked an explanatory comment as temporary as the subsequent patch is
no longer adjacent.
Changes since v4:
* Check against RESCTRL_PICK_ANY_CPU instead of -1.
* Leave cqm_work_cpu as nr_cpu_ids when no CPU is available.
* Made cpumask_any_housekeeping_but() more readable.
Changes since v5:
* Changes in captialisation, and a typo.
* Merged cpumask helpers.
Changes since v6:
* Added the missing dom parameter to some kernel doc.
* Re-added use of cpumask_any_but(),
* Expanded comment above cpumask_any_housekeeping(),
* Added some more comments for good measure.
* Added explicit IS_ENABLED() check as gcc-12 doesn't seem to work this out.
Changes since v7:
* Removed the paragraph with the badword 'subsequent'.
* Reworded a comment with the badword 'we'.
* Fixed a bounds checking bug in cpumask_any_housekeeping().
---
arch/x86/kernel/cpu/resctrl/core.c | 8 +++--
arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 2 +-
arch/x86/kernel/cpu/resctrl/internal.h | 33 ++++++++++++++----
arch/x86/kernel/cpu/resctrl/monitor.c | 42 ++++++++++++++++++-----
arch/x86/kernel/cpu/resctrl/rdtgroup.c | 6 ++--
include/linux/resctrl.h | 2 ++
6 files changed, 72 insertions(+), 21 deletions(-)
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 4627d447bc3d..55322ba629da 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -584,12 +584,16 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
if (r == &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl) {
if (is_mbm_enabled() && cpu == d->mbm_work_cpu) {
cancel_delayed_work(&d->mbm_over);
- mbm_setup_overflow_handler(d, 0);
+ /*
+ * temporary: exclude_cpu=-1 as this CPU has already
+ * been removed by cpumask_clear_cpu()d
+ */
+ mbm_setup_overflow_handler(d, 0, RESCTRL_PICK_ANY_CPU);
}
if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu &&
has_busy_rmid(d)) {
cancel_delayed_work(&d->cqm_limbo);
- cqm_setup_limbo_handler(d, 0);
+ cqm_setup_limbo_handler(d, 0, RESCTRL_PICK_ANY_CPU);
}
}
}
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index a033e8e32108..64db51455df3 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -552,7 +552,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
return;
}
- cpu = cpumask_any_housekeeping(&d->cpu_mask);
+ cpu = cpumask_any_housekeeping(&d->cpu_mask, RESCTRL_PICK_ANY_CPU);
/*
* cpumask_any_housekeeping() prefers housekeeping CPUs, but
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 3ee855c37447..c99f26ebe7a6 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -60,19 +60,36 @@
* cpumask_any_housekeeping() - Choose any CPU in @mask, preferring those that
* aren't marked nohz_full
* @mask: The mask to pick a CPU from.
+ * @exclude_cpu:The CPU to avoid picking.
*
- * Returns a CPU in @mask. If there are housekeeping CPUs that don't use
- * nohz_full, these are preferred.
+ * Returns a CPU from @mask, but not @exclude_cpu. If there are housekeeping
+ * CPUs that don't use nohz_full, these are preferred. Pass
+ * RESCTRL_PICK_ANY_CPU to avoid excluding any CPUs.
+ *
+ * When a CPU is excluded, returns >= nr_cpu_ids if no CPUs are available.
*/
-static inline unsigned int cpumask_any_housekeeping(const struct cpumask *mask)
+static inline unsigned int
+cpumask_any_housekeeping(const struct cpumask *mask, int exclude_cpu)
{
unsigned int cpu, hk_cpu;
- cpu = cpumask_any(mask);
- if (!tick_nohz_full_cpu(cpu))
+ if (exclude_cpu == RESCTRL_PICK_ANY_CPU)
+ cpu = cpumask_any(mask);
+ else
+ cpu = cpumask_any_but(mask, exclude_cpu);
+
+ if (!IS_ENABLED(CONFIG_NO_HZ_FULL))
+ return cpu;
+
+ /* If the CPU picked isn't marked nohz_full nothing more needs doing. */
+ if (cpu < nr_cpu_ids && !tick_nohz_full_cpu(cpu))
return cpu;
+ /* Try to find a CPU that isn't nohz_full to use in preference */
hk_cpu = cpumask_nth_andnot(0, mask, tick_nohz_full_mask);
+ if (hk_cpu == exclude_cpu)
+ hk_cpu = cpumask_nth_andnot(1, mask, tick_nohz_full_mask);
+
if (hk_cpu < nr_cpu_ids)
cpu = hk_cpu;
@@ -573,11 +590,13 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
struct rdt_domain *d, struct rdtgroup *rdtgrp,
int evtid, int first);
void mbm_setup_overflow_handler(struct rdt_domain *dom,
- unsigned long delay_ms);
+ unsigned long delay_ms,
+ int exclude_cpu);
void mbm_handle_overflow(struct work_struct *work);
void __init intel_rdt_mbm_apply_quirk(void);
bool is_mba_sc(struct rdt_resource *r);
-void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms);
+void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms,
+ int exclude_cpu);
void cqm_handle_limbo(struct work_struct *work);
bool has_busy_rmid(struct rdt_domain *d);
void __check_limbo(struct rdt_domain *d, bool force_free);
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 92d7ba674003..67edd4c440f0 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -481,7 +481,8 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
* setup up the limbo worker.
*/
if (!has_busy_rmid(d))
- cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL);
+ cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL,
+ RESCTRL_PICK_ANY_CPU);
set_bit(idx, d->rmid_busy_llc);
entry->busy++;
}
@@ -784,7 +785,8 @@ void cqm_handle_limbo(struct work_struct *work)
__check_limbo(d, false);
if (has_busy_rmid(d)) {
- d->cqm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask);
+ d->cqm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask,
+ RESCTRL_PICK_ANY_CPU);
schedule_delayed_work_on(d->cqm_work_cpu, &d->cqm_limbo,
delay);
}
@@ -792,15 +794,25 @@ void cqm_handle_limbo(struct work_struct *work)
mutex_unlock(&rdtgroup_mutex);
}
-void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
+/**
+ * cqm_setup_limbo_handler() - Schedule the limbo handler to run for this
+ * domain.
+ * @dom: The domain the limbo handler should run for.
+ * @delay_ms: How far in the future the handler should run.
+ * @exclude_cpu: Which CPU the handler should not run on,
+ * RESCTRL_PICK_ANY_CPU to pick any CPU.
+ */
+void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms,
+ int exclude_cpu)
{
unsigned long delay = msecs_to_jiffies(delay_ms);
int cpu;
- cpu = cpumask_any_housekeeping(&dom->cpu_mask);
+ cpu = cpumask_any_housekeeping(&dom->cpu_mask, exclude_cpu);
dom->cqm_work_cpu = cpu;
- schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
+ if (cpu < nr_cpu_ids)
+ schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
}
void mbm_handle_overflow(struct work_struct *work)
@@ -838,14 +850,24 @@ void mbm_handle_overflow(struct work_struct *work)
* Re-check for housekeeping CPUs. This allows the overflow handler to
* move off a nohz_full CPU quickly.
*/
- d->mbm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask);
+ d->mbm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask,
+ RESCTRL_PICK_ANY_CPU);
schedule_delayed_work_on(d->mbm_work_cpu, &d->mbm_over, delay);
out_unlock:
mutex_unlock(&rdtgroup_mutex);
}
-void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
+/**
+ * mbm_setup_overflow_handler() - Schedule the overflow handler to run for this
+ * domain.
+ * @dom: The domain the overflow handler should run for.
+ * @delay_ms: How far in the future the handler should run.
+ * @exclude_cpu: Which CPU the handler should not run on,
+ * RESCTRL_PICK_ANY_CPU to pick any CPU.
+ */
+void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms,
+ int exclude_cpu)
{
unsigned long delay = msecs_to_jiffies(delay_ms);
int cpu;
@@ -856,9 +878,11 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
*/
if (!resctrl_mounted || !resctrl_arch_mon_capable())
return;
- cpu = cpumask_any_housekeeping(&dom->cpu_mask);
+ cpu = cpumask_any_housekeeping(&dom->cpu_mask, exclude_cpu);
dom->mbm_work_cpu = cpu;
- schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
+
+ if (cpu < nr_cpu_ids)
+ schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
}
static int dom_data_init(struct rdt_resource *r)
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 38d3b19a3aca..f5688c79d94f 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2678,7 +2678,8 @@ static int rdt_get_tree(struct fs_context *fc)
if (is_mbm_enabled()) {
r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
list_for_each_entry(dom, &r->domains, list)
- mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL);
+ mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL,
+ RESCTRL_PICK_ANY_CPU);
}
goto out;
@@ -3989,7 +3990,8 @@ int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d)
if (is_mbm_enabled()) {
INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow);
- mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL);
+ mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL,
+ RESCTRL_PICK_ANY_CPU);
}
if (is_llc_occupancy_enabled())
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 4c4bad3c34e4..ccbbbe5d18d3 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -10,6 +10,8 @@
#define RESCTRL_RESERVED_CLOSID 0
#define RESCTRL_RESERVED_RMID 0
+#define RESCTRL_PICK_ANY_CPU -1
+
#ifdef CONFIG_PROC_CPU_RESCTRL
int proc_resctrl_show(struct seq_file *m,
--
2.39.2
The following commit has been merged into the x86/cache branch of tip:
Commit-ID: 978fcca954cb52249babbc14e53de53c88dd6433
Gitweb: https://git.kernel.org/tip/978fcca954cb52249babbc14e53de53c88dd6433
Author: James Morse <[email protected]>
AuthorDate: Tue, 13 Feb 2024 18:44:35
Committer: Borislav Petkov (AMD) <[email protected]>
CommitterDate: Fri, 16 Feb 2024 19:18:33 +01:00
x86/resctrl: Allow overflow/limbo handlers to be scheduled on any-but CPU
When a CPU is taken offline resctrl may need to move the overflow or limbo
handlers to run on a different CPU.
Once the offline callbacks have been split, cqm_setup_limbo_handler() will be
called while the CPU that is going offline is still present in the CPU mask.
Pass the CPU to exclude to cqm_setup_limbo_handler() and
mbm_setup_overflow_handler(). These functions can use a variant of
cpumask_any_but() when selecting the CPU. -1 is used to indicate no CPUs need
excluding.
Signed-off-by: James Morse <[email protected]>
Signed-off-by: Borislav Petkov (AMD) <[email protected]>
Reviewed-by: Shaopeng Tan <[email protected]>
Reviewed-by: Babu Moger <[email protected]>
Reviewed-by: Reinette Chatre <[email protected]>
Tested-by: Shaopeng Tan <[email protected]>
Tested-by: Peter Newman <[email protected]>
Tested-by: Babu Moger <[email protected]>
Tested-by: Carl Worth <[email protected]> # arm64
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Borislav Petkov (AMD) <[email protected]>
---
arch/x86/kernel/cpu/resctrl/core.c | 8 +++-
arch/x86/kernel/cpu/resctrl/ctrlmondata.c | 2 +-
arch/x86/kernel/cpu/resctrl/internal.h | 33 +++++++++++++----
arch/x86/kernel/cpu/resctrl/monitor.c | 42 +++++++++++++++++-----
arch/x86/kernel/cpu/resctrl/rdtgroup.c | 6 ++-
include/linux/resctrl.h | 2 +-
6 files changed, 72 insertions(+), 21 deletions(-)
diff --git a/arch/x86/kernel/cpu/resctrl/core.c b/arch/x86/kernel/cpu/resctrl/core.c
index 4627d44..55322ba 100644
--- a/arch/x86/kernel/cpu/resctrl/core.c
+++ b/arch/x86/kernel/cpu/resctrl/core.c
@@ -584,12 +584,16 @@ static void domain_remove_cpu(int cpu, struct rdt_resource *r)
if (r == &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl) {
if (is_mbm_enabled() && cpu == d->mbm_work_cpu) {
cancel_delayed_work(&d->mbm_over);
- mbm_setup_overflow_handler(d, 0);
+ /*
+ * temporary: exclude_cpu=-1 as this CPU has already
+ * been removed by cpumask_clear_cpu()d
+ */
+ mbm_setup_overflow_handler(d, 0, RESCTRL_PICK_ANY_CPU);
}
if (is_llc_occupancy_enabled() && cpu == d->cqm_work_cpu &&
has_busy_rmid(d)) {
cancel_delayed_work(&d->cqm_limbo);
- cqm_setup_limbo_handler(d, 0);
+ cqm_setup_limbo_handler(d, 0, RESCTRL_PICK_ANY_CPU);
}
}
}
diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index 52fa0e1..20b02d6 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -552,7 +552,7 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
return;
}
- cpu = cpumask_any_housekeeping(&d->cpu_mask);
+ cpu = cpumask_any_housekeeping(&d->cpu_mask, RESCTRL_PICK_ANY_CPU);
/*
* cpumask_any_housekeeping() prefers housekeeping CPUs, but
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 3ee855c..c99f26e 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -60,19 +60,36 @@
* cpumask_any_housekeeping() - Choose any CPU in @mask, preferring those that
* aren't marked nohz_full
* @mask: The mask to pick a CPU from.
+ * @exclude_cpu:The CPU to avoid picking.
*
- * Returns a CPU in @mask. If there are housekeeping CPUs that don't use
- * nohz_full, these are preferred.
+ * Returns a CPU from @mask, but not @exclude_cpu. If there are housekeeping
+ * CPUs that don't use nohz_full, these are preferred. Pass
+ * RESCTRL_PICK_ANY_CPU to avoid excluding any CPUs.
+ *
+ * When a CPU is excluded, returns >= nr_cpu_ids if no CPUs are available.
*/
-static inline unsigned int cpumask_any_housekeeping(const struct cpumask *mask)
+static inline unsigned int
+cpumask_any_housekeeping(const struct cpumask *mask, int exclude_cpu)
{
unsigned int cpu, hk_cpu;
- cpu = cpumask_any(mask);
- if (!tick_nohz_full_cpu(cpu))
+ if (exclude_cpu == RESCTRL_PICK_ANY_CPU)
+ cpu = cpumask_any(mask);
+ else
+ cpu = cpumask_any_but(mask, exclude_cpu);
+
+ if (!IS_ENABLED(CONFIG_NO_HZ_FULL))
return cpu;
+ /* If the CPU picked isn't marked nohz_full nothing more needs doing. */
+ if (cpu < nr_cpu_ids && !tick_nohz_full_cpu(cpu))
+ return cpu;
+
+ /* Try to find a CPU that isn't nohz_full to use in preference */
hk_cpu = cpumask_nth_andnot(0, mask, tick_nohz_full_mask);
+ if (hk_cpu == exclude_cpu)
+ hk_cpu = cpumask_nth_andnot(1, mask, tick_nohz_full_mask);
+
if (hk_cpu < nr_cpu_ids)
cpu = hk_cpu;
@@ -573,11 +590,13 @@ void mon_event_read(struct rmid_read *rr, struct rdt_resource *r,
struct rdt_domain *d, struct rdtgroup *rdtgrp,
int evtid, int first);
void mbm_setup_overflow_handler(struct rdt_domain *dom,
- unsigned long delay_ms);
+ unsigned long delay_ms,
+ int exclude_cpu);
void mbm_handle_overflow(struct work_struct *work);
void __init intel_rdt_mbm_apply_quirk(void);
bool is_mba_sc(struct rdt_resource *r);
-void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms);
+void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms,
+ int exclude_cpu);
void cqm_handle_limbo(struct work_struct *work);
bool has_busy_rmid(struct rdt_domain *d);
void __check_limbo(struct rdt_domain *d, bool force_free);
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 92d7ba6..67edd4c 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -481,7 +481,8 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
* setup up the limbo worker.
*/
if (!has_busy_rmid(d))
- cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL);
+ cqm_setup_limbo_handler(d, CQM_LIMBOCHECK_INTERVAL,
+ RESCTRL_PICK_ANY_CPU);
set_bit(idx, d->rmid_busy_llc);
entry->busy++;
}
@@ -784,7 +785,8 @@ void cqm_handle_limbo(struct work_struct *work)
__check_limbo(d, false);
if (has_busy_rmid(d)) {
- d->cqm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask);
+ d->cqm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask,
+ RESCTRL_PICK_ANY_CPU);
schedule_delayed_work_on(d->cqm_work_cpu, &d->cqm_limbo,
delay);
}
@@ -792,15 +794,25 @@ void cqm_handle_limbo(struct work_struct *work)
mutex_unlock(&rdtgroup_mutex);
}
-void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms)
+/**
+ * cqm_setup_limbo_handler() - Schedule the limbo handler to run for this
+ * domain.
+ * @dom: The domain the limbo handler should run for.
+ * @delay_ms: How far in the future the handler should run.
+ * @exclude_cpu: Which CPU the handler should not run on,
+ * RESCTRL_PICK_ANY_CPU to pick any CPU.
+ */
+void cqm_setup_limbo_handler(struct rdt_domain *dom, unsigned long delay_ms,
+ int exclude_cpu)
{
unsigned long delay = msecs_to_jiffies(delay_ms);
int cpu;
- cpu = cpumask_any_housekeeping(&dom->cpu_mask);
+ cpu = cpumask_any_housekeeping(&dom->cpu_mask, exclude_cpu);
dom->cqm_work_cpu = cpu;
- schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
+ if (cpu < nr_cpu_ids)
+ schedule_delayed_work_on(cpu, &dom->cqm_limbo, delay);
}
void mbm_handle_overflow(struct work_struct *work)
@@ -838,14 +850,24 @@ void mbm_handle_overflow(struct work_struct *work)
* Re-check for housekeeping CPUs. This allows the overflow handler to
* move off a nohz_full CPU quickly.
*/
- d->mbm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask);
+ d->mbm_work_cpu = cpumask_any_housekeeping(&d->cpu_mask,
+ RESCTRL_PICK_ANY_CPU);
schedule_delayed_work_on(d->mbm_work_cpu, &d->mbm_over, delay);
out_unlock:
mutex_unlock(&rdtgroup_mutex);
}
-void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
+/**
+ * mbm_setup_overflow_handler() - Schedule the overflow handler to run for this
+ * domain.
+ * @dom: The domain the overflow handler should run for.
+ * @delay_ms: How far in the future the handler should run.
+ * @exclude_cpu: Which CPU the handler should not run on,
+ * RESCTRL_PICK_ANY_CPU to pick any CPU.
+ */
+void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms,
+ int exclude_cpu)
{
unsigned long delay = msecs_to_jiffies(delay_ms);
int cpu;
@@ -856,9 +878,11 @@ void mbm_setup_overflow_handler(struct rdt_domain *dom, unsigned long delay_ms)
*/
if (!resctrl_mounted || !resctrl_arch_mon_capable())
return;
- cpu = cpumask_any_housekeeping(&dom->cpu_mask);
+ cpu = cpumask_any_housekeeping(&dom->cpu_mask, exclude_cpu);
dom->mbm_work_cpu = cpu;
- schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
+
+ if (cpu < nr_cpu_ids)
+ schedule_delayed_work_on(cpu, &dom->mbm_over, delay);
}
static int dom_data_init(struct rdt_resource *r)
diff --git a/arch/x86/kernel/cpu/resctrl/rdtgroup.c b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
index 38d3b19..f5688c7 100644
--- a/arch/x86/kernel/cpu/resctrl/rdtgroup.c
+++ b/arch/x86/kernel/cpu/resctrl/rdtgroup.c
@@ -2678,7 +2678,8 @@ static int rdt_get_tree(struct fs_context *fc)
if (is_mbm_enabled()) {
r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
list_for_each_entry(dom, &r->domains, list)
- mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL);
+ mbm_setup_overflow_handler(dom, MBM_OVERFLOW_INTERVAL,
+ RESCTRL_PICK_ANY_CPU);
}
goto out;
@@ -3989,7 +3990,8 @@ int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d)
if (is_mbm_enabled()) {
INIT_DELAYED_WORK(&d->mbm_over, mbm_handle_overflow);
- mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL);
+ mbm_setup_overflow_handler(d, MBM_OVERFLOW_INTERVAL,
+ RESCTRL_PICK_ANY_CPU);
}
if (is_llc_occupancy_enabled())
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 4c4bad3..ccbbbe5 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -10,6 +10,8 @@
#define RESCTRL_RESERVED_CLOSID 0
#define RESCTRL_RESERVED_RMID 0
+#define RESCTRL_PICK_ANY_CPU -1
+
#ifdef CONFIG_PROC_CPU_RESCTRL
int proc_resctrl_show(struct seq_file *m,
> -static inline unsigned int cpumask_any_housekeeping(const struct cpumask *mask)
> +static inline unsigned int
> +cpumask_any_housekeeping(const struct cpumask *mask, int exclude_cpu)
> {
> unsigned int cpu, hk_cpu;
>
> - cpu = cpumask_any(mask);
> - if (!tick_nohz_full_cpu(cpu))
> + if (exclude_cpu == RESCTRL_PICK_ANY_CPU)
> + cpu = cpumask_any(mask);
> + else
> + cpu = cpumask_any_but(mask, exclude_cpu);
> +
> + if (!IS_ENABLED(CONFIG_NO_HZ_FULL))
> + return cpu;
> +
> + /* If the CPU picked isn't marked nohz_full nothing more needs doing. */
> + if (cpu < nr_cpu_ids && !tick_nohz_full_cpu(cpu))
> return cpu;
>
> + /* Try to find a CPU that isn't nohz_full to use in preference */
> hk_cpu = cpumask_nth_andnot(0, mask, tick_nohz_full_mask);
> + if (hk_cpu == exclude_cpu)
> + hk_cpu = cpumask_nth_andnot(1, mask, tick_nohz_full_mask);
OOPS HERE ^^^^^^^^^^^^^^^^^^
> +
> if (hk_cpu < nr_cpu_ids)
> cpu = hk_cpu;
James,
I'm playing around with v6.9-rc1. When I take all the CPUs in a domain
offline, resctrl wants to stop the mbm overflow handler. While doing
so it crashes with a NULL dereference in the code above.
At this point the cpu_mask for the domain still has the bit for
the last CPU standing in this domain. So cpumask_any_housekeeping()
is called with a mask that just has CPU 36 set, but request to find
a CPU other than 36.
-Tony
Heres the OOPs:
[ 97.107355] smpboot: CPU 37 is now offline
[ 97.166136] BUG: kernel NULL pointer dereference, address: 0000000000000000
[ 97.173118] #PF: supervisor read access in kernel mode
[ 97.178263] #PF: error_code(0x0000) - not-present page
[ 97.183410] PGD 0
[ 97.185438] Oops: 0000 [#1] PREEMPT SMP NOPTI
[ 97.189805] CPU: 36 PID: 235 Comm: cpuhp/36 Tainted: G T 6.9.0-rc1 #356
[ 97.197810] Hardware name: Intel Corporation WilsonCity/WilsonCity, BIOS WLYDCRB1.SYS.0021.P06.2104260458 04/26/2021
[ 97.208322] RIP: 0010:__find_nth_andnot_bit+0x66/0x110
[ 97.213472] Code: d2 eb 20 48 29 c6 48 8d 41 c0 48 39 ca 0f 82 8b 00 00 00 48 01 f0 48 83 c1 40 48 39 d0 0f 83 9e 00 00 00 4d 89 d3 49 83 c2 01 <4b> 8b 3c d8 48 f7 d7 4b 23 3c d9 f3 48 0f b8 c7 48 39 c6 73 c4 4c
[ 97.232214] RSP: 0018:ff462f11872bbd98 EFLAGS: 00010202
[ 97.237440] RAX: 0000000000000000 RBX: 0000000000000024 RCX: 0000000000000080
[ 97.244574] RDX: 0000000000000090 RSI: 0000000000000000 RDI: 0000000000000000
[ 97.251705] RBP: ff43a0b049599018 R08: 0000000000000000 R09: ff43a0b049599018
[ 97.258835] R10: 0000000000000001 R11: 0000000000000000 R12: 0000000000000025
[ 97.265970] R13: 0000000000000090 R14: 0000000000000000 R15: ffffffffaa068fb0
[ 97.273100] FS: 0000000000000000(0000) GS:ff43a0b81d800000(0000) knlGS:0000000000000000
[ 97.281187] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 97.286932] CR2: 0000000000000000 CR3: 0000000a50e3a004 CR4: 0000000000771ef0
[ 97.294065] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 97.301197] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 97.308328] PKRU: 55555554
[ 97.311039] Call Trace:
[ 97.313492] <TASK>
[ 97.315600] ? __die+0x1f/0x60
[ 97.318665] ? page_fault_oops+0x176/0x5a0
[ 97.322777] ? exc_page_fault+0x7f/0x260
[ 97.326708] ? asm_exc_page_fault+0x22/0x30
[ 97.330903] ? __pfx_resctrl_arch_offline_cpu+0x10/0x10
[ 97.336140] ? __find_nth_andnot_bit+0x66/0x110
[ 97.340680] ? __cancel_work+0x7d/0xc0
[ 97.344438] cpumask_any_housekeeping+0x55/0x110
[ 97.349060] mbm_setup_overflow_handler+0x40/0x70
[ 97.353774] resctrl_offline_cpu+0x101/0x110
[ 97.358054] resctrl_arch_offline_cpu+0x19/0x260
[ 97.362673] cpuhp_invoke_callback+0x156/0x6b0
[ 97.367127] ? cpuhp_thread_fun+0x5f/0x250
[ 97.371234] cpuhp_thread_fun+0x1ca/0x250
[ 97.375247] ? __pfx_smpboot_thread_fn+0x10/0x10
[ 97.379874] smpboot_thread_fn+0x184/0x220
[ 97.383974] kthread+0xe0/0x110
[ 97.387129] ? __pfx_kthread+0x10/0x10
[ 97.390888] ret_from_fork+0x2d/0x50
[ 97.394467] ? __pfx_kthread+0x10/0x10
[ 97.398220] ret_from_fork_asm+0x1a/0x30
[ 97.402149] </TASK>