[PATCH 7/9] x86/intel_rdt: Implement scheduling support for Intel RDT

From: Vikas Shivappa
Date: Thu Jun 25 2015 - 15:29:31 EST


Adds support for IA32_PQR_ASSOC MSR writes during task scheduling. For
Cache Allocation, MSR write would let the task fill in the cache
'subset' represented by the cgroup's cache_mask.

The high 32 bits in the per processor MSR IA32_PQR_ASSOC represents the
CLOSid. During context switch kernel implements this by writing the
CLOSid of the cgroup to which the task belongs to the CPU's
IA32_PQR_ASSOC MSR.

This patch also implements a common software cache for IA32_PQR_MSR(RMID
0:9, CLOSId 32:63) to be used by both Cache monitoring(CMT) and
Cache allocation. CMT updates the RMID where as cache_alloc updates the
CLOSid in the software cache. During scheduling when the new
RMID/CLOSid value is different from the cached values, IA32_PQR_MSR is
updated. Since the measured rdmsr latency for IA32_PQR_MSR is very
high(~250 cycles) this software cache is necessary to avoid reading the
MSR to compare the current CLOSid value.

The following considerations are done for the PQR MSR write so that it
minimally impacts scheduler hot path:
- This path does not exist on any non-intel platforms.
- On Intel platforms, this would not exist by default unless CGROUP_RDT
is enabled.
- remains a no-op when CGROUP_RDT is enabled and intel SKU does not
support the feature.
- When feature is available and enabled, never does MSR write till the
user manually creates a cgroup directory *and* assigns a cache_mask
different from root cgroup directory. Since the child node inherits
the parents cache mask , by cgroup creation there is no scheduling hot
path impact from the new cgroup.
- MSR write is only done when there is a task with different Closid is
scheduled on the CPU. Typically if the task groups are bound to be
scheduled on a set of CPUs , the number of MSR writes is greatly
reduced.
- A per CPU cache of CLOSids is maintained to do the check so that we
dont have to do a rdmsr which actually costs a lot of cycles.
- For cgroup directories having same cache_mask the CLOSids are reused.
This minimizes the number of CLOSids used and hence reduces the MSR
write frequency.

Signed-off-by: Vikas Shivappa <vikas.shivappa@xxxxxxxxxxxxxxx>
---
arch/x86/include/asm/intel_rdt.h | 45 ++++++++++++++++++++++++++++++
arch/x86/include/asm/rdt_common.h | 25 +++++++++++++++++
arch/x86/include/asm/switch_to.h | 3 ++
arch/x86/kernel/cpu/intel_rdt.c | 17 +++++++++++
arch/x86/kernel/cpu/perf_event_intel_cqm.c | 26 ++---------------
5 files changed, 93 insertions(+), 23 deletions(-)
create mode 100644 arch/x86/include/asm/rdt_common.h

diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h
index 3ad426c..78df3d7 100644
--- a/arch/x86/include/asm/intel_rdt.h
+++ b/arch/x86/include/asm/intel_rdt.h
@@ -4,10 +4,16 @@
#ifdef CONFIG_CGROUP_RDT

#include <linux/cgroup.h>
+#include <asm/rdt_common.h>
+
#define MAX_CBM_LENGTH 32
#define IA32_L3_CBM_BASE 0xc90
#define CBM_FROM_INDEX(x) (IA32_L3_CBM_BASE + x)

+DECLARE_PER_CPU(struct intel_pqr_state, pqr_state);
+extern struct static_key rdt_enable_key;
+extern void __intel_rdt_sched_in(void);
+
struct rdt_subsys_info {
unsigned long *closmap;
};
@@ -35,5 +41,44 @@ static inline struct intel_rdt *parent_rdt(struct intel_rdt *ir)
return css_rdt(ir->css.parent);
}

+/*
+ * Return rdt group to which this task belongs.
+ */
+static inline struct intel_rdt *task_rdt(struct task_struct *task)
+{
+ return css_rdt(task_css(task, intel_rdt_cgrp_id));
+}
+
+/*
+ * intel_rdt_sched_in() - Writes the task's CLOSid to IA32_PQR_MSR
+ *
+ * Following considerations are made so that this has minimal impact
+ * on scheduler hot path:
+ * - This will stay as no-op unless we are running on an Intel SKU
+ * which supports L3 cache allocation.
+ * - When support is present and enabled, does not do any
+ * IA32_PQR_MSR writes until the user starts really using the feature
+ * ie creates a rdt cgroup directory and assigns a cache_mask thats
+ * different from the root cgroup's cache_mask.
+ * - Caches the per cpu CLOSid values and does the MSR write only
+ * when a task with a different CLOSid is scheduled in. That
+ * means the task belongs to a different cgroup.
+ * - Closids are allocated so that different cgroup directories
+ * with same cache_mask gets the same CLOSid. This minimizes CLOSids
+ * used and reduces MSR write frequency.
+ */
+static inline void intel_rdt_sched_in(void)
+{
+ /*
+ * Call the schedule in code only when RDT is enabled.
+ */
+ if (static_key_false(&rdt_enable_key))
+ __intel_rdt_sched_in();
+}
+
+#else
+
+static inline void intel_rdt_sched_in(void) {}
+
#endif
#endif
diff --git a/arch/x86/include/asm/rdt_common.h b/arch/x86/include/asm/rdt_common.h
new file mode 100644
index 0000000..01502c5
--- /dev/null
+++ b/arch/x86/include/asm/rdt_common.h
@@ -0,0 +1,25 @@
+#ifndef _X86_RDT_H_
+#define _X86_RDT_H_
+
+#define MSR_IA32_PQR_ASSOC 0x0c8f
+
+/**
+ * struct intel_pqr_state - State cache for the PQR MSR
+ * @rmid: The cached Resource Monitoring ID
+ * @closid: The cached Class Of Service ID
+ * @rmid_usecnt: The usage counter for rmid
+ *
+ * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the
+ * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always
+ * contains both parts, so we need to cache them.
+ *
+ * The cache also helps to avoid pointless updates if the value does
+ * not change.
+ */
+struct intel_pqr_state {
+ u32 rmid;
+ u32 closid;
+ int rmid_usecnt;
+};
+
+#endif
diff --git a/arch/x86/include/asm/switch_to.h b/arch/x86/include/asm/switch_to.h
index 751bf4b..9149577 100644
--- a/arch/x86/include/asm/switch_to.h
+++ b/arch/x86/include/asm/switch_to.h
@@ -8,6 +8,9 @@ struct tss_struct;
void __switch_to_xtra(struct task_struct *prev_p, struct task_struct *next_p,
struct tss_struct *tss);

+#include <asm/intel_rdt.h>
+#define finish_arch_switch(prev) intel_rdt_sched_in()
+
#ifdef CONFIG_X86_32

#ifdef CONFIG_CC_STACKPROTECTOR
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index 750b02a..c8bb134 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -34,6 +34,8 @@ static struct clos_cbm_map *ccmap;
static struct rdt_subsys_info rdtss_info;
static DEFINE_MUTEX(rdt_group_mutex);
struct intel_rdt rdt_root_group;
+struct static_key __read_mostly rdt_enable_key = STATIC_KEY_INIT_FALSE;
+
/*
* Mask of CPUs for writing CBM values. We only need one CPU per-socket.
*/
@@ -88,6 +90,20 @@ static inline void closid_put(u32 closid)
closid_free(closid);
}

+void __intel_rdt_sched_in(void)
+{
+ struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
+ struct task_struct *task = current;
+ struct intel_rdt *ir;
+
+ ir = task_rdt(task);
+ if (ir->closid == state->closid)
+ return;
+
+ wrmsr(MSR_IA32_PQR_ASSOC, state->rmid, ir->closid);
+ state->closid = ir->closid;
+}
+
static struct cgroup_subsys_state *
intel_rdt_css_alloc(struct cgroup_subsys_state *parent_css)
{
@@ -345,6 +361,7 @@ static int __init intel_rdt_late_init(void)
for_each_online_cpu(i)
rdt_cpumask_update(i);

+ static_key_slow_inc(&rdt_enable_key);
pr_info("Intel cache allocation enabled\n");
out_err:

diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index 9f4ee29..1ce76b4 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -7,41 +7,22 @@
#include <linux/perf_event.h>
#include <linux/slab.h>
#include <asm/cpu_device_id.h>
+#include <asm/rdt_common.h>
#include "perf_event.h"

-#define MSR_IA32_PQR_ASSOC 0x0c8f
#define MSR_IA32_QM_CTR 0x0c8e
#define MSR_IA32_QM_EVTSEL 0x0c8d

static u32 cqm_max_rmid = -1;
static unsigned int cqm_l3_scale; /* supposedly cacheline size */

-/**
- * struct intel_pqr_state - State cache for the PQR MSR
- * @rmid: The cached Resource Monitoring ID
- * @closid: The cached Class Of Service ID
- * @rmid_usecnt: The usage counter for rmid
- *
- * The upper 32 bits of MSR_IA32_PQR_ASSOC contain closid and the
- * lower 10 bits rmid. The update to MSR_IA32_PQR_ASSOC always
- * contains both parts, so we need to cache them.
- *
- * The cache also helps to avoid pointless updates if the value does
- * not change.
- */
-struct intel_pqr_state {
- u32 rmid;
- u32 closid;
- int rmid_usecnt;
-};
-
/*
* The cached intel_pqr_state is strictly per CPU and can never be
* updated from a remote CPU. Both functions which modify the state
* (intel_cqm_event_start and intel_cqm_event_stop) are called with
* interrupts disabled, which is sufficient for the protection.
*/
-static DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);
+DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);

/*
* Protects cache_cgroups and cqm_rmid_free_lru and cqm_rmid_limbo_lru.
@@ -402,9 +383,9 @@ static void __intel_cqm_event_count(void *info);
*/
static u32 intel_cqm_xchg_rmid(struct perf_event *group, u32 rmid)
{
- struct perf_event *event;
struct list_head *head = &group->hw.cqm_group_entry;
u32 old_rmid = group->hw.cqm_rmid;
+ struct perf_event *event;

lockdep_assert_held(&cache_mutex);

@@ -1253,7 +1234,6 @@ static void intel_cqm_cpu_prepare(unsigned int cpu)
struct cpuinfo_x86 *c = &cpu_data(cpu);

state->rmid = 0;
- state->closid = 0;
state->rmid_usecnt = 0;

WARN_ON(c->x86_cache_max_rmid != cqm_max_rmid);
--
1.9.1

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/