[PATCH v2 10/33] x86/intel_rdt: Implement scheduling support for Intel RDT

[Fenghua Yu]

From: Vikas Shivappa <vikas.shivappa@xxxxxxxxxxxxxxx>

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 task's capacity bit 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 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 INTEL_RDT
 is enabled.
 - remains a no-op when INTEL_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 starts using one of the capacity bit masks.
 - 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
 don't have to do a rdmsr which actually costs a lot of cycles.

Signed-off-by: Vikas Shivappa <vikas.shivappa@xxxxxxxxxxxxxxx>
Signed-off-by: Fenghua Yu <fenghua.yu@xxxxxxxxx>
Reviewed-by: Tony Luck <tony.luck@xxxxxxxxx>
---
 arch/x86/events/intel/cqm.c       | 24 ++----------------------
 arch/x86/include/asm/intel_rdt.h  | 36 ++++++++++++++++++++++++++++++++++++
 arch/x86/include/asm/pqr_common.h | 27 +++++++++++++++++++++++++++
 arch/x86/kernel/cpu/intel_rdt.c   | 18 ++++++++++++++++++
 arch/x86/kernel/process_64.c      |  6 ++++++
 5 files changed, 89 insertions(+), 22 deletions(-)
 create mode 100644 arch/x86/include/asm/pqr_common.h

diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c
index 783c49d..0ed56ae 100644
--- a/arch/x86/events/intel/cqm.c
+++ b/arch/x86/events/intel/cqm.c
@@ -7,9 +7,9 @@
 #include <linux/perf_event.h>
 #include <linux/slab.h>
 #include <asm/cpu_device_id.h>
+#include <asm/pqr_common.h>
 #include "../perf_event.h"
 
-#define MSR_IA32_PQR_ASSOC	0x0c8f
 #define MSR_IA32_QM_CTR		0x0c8e
 #define MSR_IA32_QM_EVTSEL	0x0c8d
 
@@ -24,32 +24,13 @@ static unsigned int cqm_l3_scale; /* supposedly cacheline size */
 static bool cqm_enabled, mbm_enabled;
 unsigned int mbm_socket_max;
 
-/**
- * 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);
 static struct hrtimer *mbm_timers;
 /**
  * struct sample - mbm event's (local or total) data
@@ -1583,7 +1564,6 @@ static int intel_cqm_cpu_starting(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);
diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h
index 68c9a79..8512174 100644
--- a/arch/x86/include/asm/intel_rdt.h
+++ b/arch/x86/include/asm/intel_rdt.h
@@ -3,14 +3,50 @@
 
 #ifdef CONFIG_INTEL_RDT
 
+#include <linux/jump_label.h>
+
 #define MAX_CBM_LENGTH			32
 #define IA32_L3_CBM_BASE		0xc90
 #define CBM_FROM_INDEX(x)		(IA32_L3_CBM_BASE + x)
 
+extern struct static_key rdt_enable_key;
+void __intel_rdt_sched_in(void *dummy);
+
 struct clos_cbm_table {
 	unsigned long cbm;
 	unsigned int clos_refcnt;
 };
 
+/*
+ * 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 rdtgroup directory and assigns a cache_mask thats
+ * different from the root rdtgroup'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 rdtgroup.
+ * - Closids are allocated so that different rdtgroup 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(NULL);
+}
+
+#else
+
+static inline void intel_rdt_sched_in(void) {}
+
 #endif
 #endif
diff --git a/arch/x86/include/asm/pqr_common.h b/arch/x86/include/asm/pqr_common.h
new file mode 100644
index 0000000..11e985c
--- /dev/null
+++ b/arch/x86/include/asm/pqr_common.h
@@ -0,0 +1,27 @@
+#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;
+};
+
+DECLARE_PER_CPU(struct intel_pqr_state, pqr_state);
+
+#endif
diff --git a/arch/x86/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index 9cf3a7d..9f30492 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -21,6 +21,8 @@
  */
 #include <linux/slab.h>
 #include <linux/err.h>
+#include <linux/sched.h>
+#include <asm/pqr_common.h>
 #include <asm/intel_rdt.h>
 
 /*
@@ -41,12 +43,28 @@ static cpumask_t rdt_cpumask;
  */
 static cpumask_t tmp_cpumask;
 static DEFINE_MUTEX(rdtgroup_mutex);
+struct static_key __read_mostly rdt_enable_key = STATIC_KEY_INIT_FALSE;
 
 struct rdt_remote_data {
 	int msr;
 	u64 val;
 };
 
+void __intel_rdt_sched_in(void *dummy)
+{
+	struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
+
+	/*
+	 * Currently closid is always 0. When  user interface is added,
+	 * closid will come from user interface.
+	 */
+	if (state->closid == 0)
+		return;
+
+	wrmsr(MSR_IA32_PQR_ASSOC, state->rmid, 0);
+	state->closid = 0;
+}
+
 static inline void closid_get(u32 closid)
 {
 	struct clos_cbm_table *cct = &cctable[closid];
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index 63236d8..1c98f80 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -48,6 +48,7 @@
 #include <asm/syscalls.h>
 #include <asm/debugreg.h>
 #include <asm/switch_to.h>
+#include <asm/intel_rdt.h>
 #include <asm/xen/hypervisor.h>
 
 asmlinkage extern void ret_from_fork(void);
@@ -472,6 +473,11 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 			loadsegment(ss, __KERNEL_DS);
 	}
 
+	/*
+	 * Load the Intel cache allocation PQR MSR.
+	 */
+	intel_rdt_sched_in();
+
 	return prev_p;
 }
 
-- 
2.5.0