lkml.org 
[lkml]   [2015]   [Jan]   [27]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH 5/6] x86/intel_rdt: Software Cache for IA32_PQR_MSR
Date
This patch implements a common software cache for IA32_PQR_MSR(RMID 0:9,
CLOSId 32:63) to be used by both CMT and CAT. CMT updates the RMID
where as CAT updates the CLOSid in the software cache. 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.

Signed-off-by: Vikas Shivappa <vikas.shivappa@linux.intel.com>
---
arch/x86/include/asm/intel_cat.h | 36 ++++++++++++++++--------------
arch/x86/include/asm/rdt.h | 13 +++++++++++
arch/x86/kernel/cpu/perf_event_intel_cqm.c | 20 ++++++-----------
3 files changed, 39 insertions(+), 30 deletions(-)
create mode 100644 arch/x86/include/asm/rdt.h

diff --git a/arch/x86/include/asm/intel_cat.h b/arch/x86/include/asm/intel_cat.h
index eda86b1..a534e94 100644
--- a/arch/x86/include/asm/intel_cat.h
+++ b/arch/x86/include/asm/intel_cat.h
@@ -4,11 +4,13 @@
#ifdef CONFIG_CGROUP_CAT

#include <linux/cgroup.h>
-#define MSR_IA32_PQR_ASSOC 0xc8f
-#define MAX_CBM_LENGTH 32
-#define IA32_L3_CBM_BASE 0xc90
+#include <asm/rdt.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(unsigned int, x86_cpu_clos);
+
+DECLARE_PER_CPU(struct intel_pqr_state, pqr_state);
extern struct static_key cat_enable_key;

struct cat_subsys_info {
@@ -63,30 +65,30 @@ static inline struct cache_alloc *task_cat(struct task_struct *task)
static inline void cat_sched_in(struct task_struct *task)
{
struct cache_alloc *cq;
- unsigned int clos;
+ struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
+ unsigned long flags;

if (!cat_enabled())
return;

- /*
- * This needs to be fixed after CQM code stabilizes
- * to cache the whole PQR instead of just CLOSid.
- * PQR has closid in high 32 bits and CQM-RMID in low 10 bits.
- * Should not write a 0 to the low 10 bits of PQR
- * and corrupt RMID.
- */
- clos = this_cpu_read(x86_cpu_clos);
-
+ raw_spin_lock_irqsave(&state->lock, flags);
rcu_read_lock();
cq = task_cat(task);
- if (cq->clos == clos) {
+ if (cq->clos == state->clos) {
rcu_read_unlock();
+ raw_spin_unlock_irqrestore(&state->lock, flags);
return;
}

- wrmsr(MSR_IA32_PQR_ASSOC, 0, cq->clos);
- this_cpu_write(x86_cpu_clos, cq->clos);
+ /*
+ * PQR has closid in high 32 bits and CQM-RMID
+ * in low 10 bits. Rewrite the exsting rmid from
+ * software cache.
+ */
+ wrmsr(MSR_IA32_PQR_ASSOC, state->rmid, cq->clos);
+ state->clos = cq->clos;
rcu_read_unlock();
+ raw_spin_unlock_irqrestore(&state->lock, flags);
}

#else
diff --git a/arch/x86/include/asm/rdt.h b/arch/x86/include/asm/rdt.h
new file mode 100644
index 0000000..c87f908
--- /dev/null
+++ b/arch/x86/include/asm/rdt.h
@@ -0,0 +1,13 @@
+#ifndef _X86_RDT_H_
+#define _X86_RDT_H_
+
+#define MSR_IA32_PQR_ASSOC 0x0c8f
+
+struct intel_pqr_state {
+ raw_spinlock_t lock;
+ int rmid;
+ int clos;
+ int cnt;
+};
+
+#endif
diff --git a/arch/x86/kernel/cpu/perf_event_intel_cqm.c b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
index 596d1ec..15564e2 100644
--- a/arch/x86/kernel/cpu/perf_event_intel_cqm.c
+++ b/arch/x86/kernel/cpu/perf_event_intel_cqm.c
@@ -7,22 +7,16 @@
#include <linux/perf_event.h>
#include <linux/slab.h>
#include <asm/cpu_device_id.h>
+#include <asm/rdt.h>
#include "perf_event.h"

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

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

-struct intel_cqm_state {
- raw_spinlock_t lock;
- int rmid;
- int cnt;
-};
-
-static DEFINE_PER_CPU(struct intel_cqm_state, cqm_state);
+DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);

/*
* Protects cache_cgroups and cqm_rmid_free_lru and cqm_rmid_limbo_lru.
@@ -931,7 +925,7 @@ out:

static void intel_cqm_event_start(struct perf_event *event, int mode)
{
- struct intel_cqm_state *state = this_cpu_ptr(&cqm_state);
+ struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
unsigned int rmid = event->hw.cqm_rmid;
unsigned long flags;

@@ -948,14 +942,14 @@ static void intel_cqm_event_start(struct perf_event *event, int mode)
WARN_ON_ONCE(state->rmid);

state->rmid = rmid;
- wrmsrl(MSR_IA32_PQR_ASSOC, state->rmid);
+ wrmsr(MSR_IA32_PQR_ASSOC, state->rmid, state->clos);

raw_spin_unlock_irqrestore(&state->lock, flags);
}

static void intel_cqm_event_stop(struct perf_event *event, int mode)
{
- struct intel_cqm_state *state = this_cpu_ptr(&cqm_state);
+ struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
unsigned long flags;

if (event->hw.cqm_state & PERF_HES_STOPPED)
@@ -968,7 +962,7 @@ static void intel_cqm_event_stop(struct perf_event *event, int mode)

if (!--state->cnt) {
state->rmid = 0;
- wrmsrl(MSR_IA32_PQR_ASSOC, 0);
+ wrmsr(MSR_IA32_PQR_ASSOC, 0, state->clos);
} else {
WARN_ON_ONCE(!state->rmid);
}
@@ -1213,7 +1207,7 @@ static inline void cqm_pick_event_reader(int cpu)

static void intel_cqm_cpu_prepare(unsigned int cpu)
{
- struct intel_cqm_state *state = &per_cpu(cqm_state, cpu);
+ struct intel_pqr_state *state = &per_cpu(pqr_state, cpu);
struct cpuinfo_x86 *c = &cpu_data(cpu);

raw_spin_lock_init(&state->lock);
--
1.9.1


\
 
 \ /
  Last update: 2015-01-28 01:21    [W:0.111 / U:0.432 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site