[PATCH 07/12] x86/rdt,cqm: Scheduling support update

From: Vikas Shivappa
Date: Fri Jan 06 2017 - 17:40:31 EST

Next message: RafaÅ MiÅecki: "Re: [PATCH] ssb: main.c: This patch removes unnecessary return statement using spatch tool"
Previous message: Greg Kroah-Hartman: "[PATCH 4.9 066/116] s390/kexec: use node 0 when re-adding crash kernel memory"
In reply to: Vikas Shivappa: "[PATCH 08/12] x86/cqm: Add support for monitoring task and cgroup together"
Next in thread: Vikas Shivappa: "[PATCH 06/12] x86/cqm: Add cgroup hierarchical monitoring support"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]

Introduce a scheduling hook finish_arch_pre_lock_switch which is
called just after the perf sched_in during context switch. This method
handles both cat and cqm sched in scenarios.
The IA32_PQR_ASSOC MSR is used by cat(cache allocation) and cqm and this
patch integrates the two msr writes to one. The common sched_in patch
checks if the per cpu cache has a different RMID or CLOSid than the task
and does the MSR write.

During sched_in the task uses the task RMID if the task is monitored or
else uses the task's cgroup rmid.

Patch is based on David Carrillo-Cisneros <davidcc@xxxxxxxxxx> patches
in cqm2 series.

Signed-off-by: Vikas Shivappa <vikas.shivappa@xxxxxxxxxxxxxxx>
---
arch/x86/events/intel/cqm.c | 45 ++++++++++-----
arch/x86/include/asm/intel_pqr_common.h | 38 +++++++++++++
arch/x86/include/asm/intel_rdt.h | 39 -------------
arch/x86/include/asm/intel_rdt_common.h | 11 ++++
arch/x86/include/asm/processor.h | 4 ++
arch/x86/kernel/cpu/Makefile | 1 +
arch/x86/kernel/cpu/intel_rdt_common.c | 98 ++++++++++++++++++++++++++++++++
arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 4 +-
arch/x86/kernel/process_32.c | 4 --
arch/x86/kernel/process_64.c | 4 --
kernel/sched/core.c | 1 +
kernel/sched/sched.h | 3 +
12 files changed, 188 insertions(+), 64 deletions(-)
create mode 100644 arch/x86/include/asm/intel_pqr_common.h
create mode 100644 arch/x86/kernel/cpu/intel_rdt_common.c

diff --git a/arch/x86/events/intel/cqm.c b/arch/x86/events/intel/cqm.c
index c6479ae..597a184 100644
--- a/arch/x86/events/intel/cqm.c
+++ b/arch/x86/events/intel/cqm.c
@@ -28,13 +28,6 @@
static bool cqm_enabled, mbm_enabled;
unsigned int cqm_socket_max;

-/*
- * 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.
- */
-DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);
static struct hrtimer *mbm_timers;
/**
* struct sample - mbm event's (local or total) data
@@ -74,6 +67,8 @@ struct sample {
static DEFINE_MUTEX(cache_mutex);
static DEFINE_RAW_SPINLOCK(cache_lock);

+DEFINE_STATIC_KEY_FALSE(cqm_enable_key);
+
/*
* Groups of events that have the same target(s), one RMID per group.
*/
@@ -108,7 +103,7 @@ struct sample {
* Likewise, an rmid value of -1 is used to indicate "no rmid currently
* assigned" and is used as part of the rotation code.
*/
-static inline bool __rmid_valid(u32 rmid)
+bool __rmid_valid(u32 rmid)
{
if (!rmid || rmid > cqm_max_rmid)
return false;
@@ -161,7 +156,7 @@ static inline struct cqm_rmid_entry *__rmid_entry(u32 rmid, int domain)
*
* We expect to be called with cache_mutex held.
*/
-static u32 __get_rmid(int domain)
+u32 __get_rmid(int domain)
{
struct list_head *cqm_flist;
struct cqm_rmid_entry *entry;
@@ -368,6 +363,23 @@ static void init_mbm_sample(u32 *rmid, u32 evt_type)
on_each_cpu_mask(&cqm_cpumask, __intel_mbm_event_init, &rr, 1);
}

+#ifdef CONFIG_CGROUP_PERF
+struct cgrp_cqm_info *cqminfo_from_tsk(struct task_struct *tsk)
+{
+ struct cgrp_cqm_info *ccinfo = NULL;
+ struct perf_cgroup *pcgrp;
+
+ pcgrp = perf_cgroup_from_task(tsk, NULL);
+
+ if (!pcgrp)
+ return NULL;
+ else
+ ccinfo = cgrp_to_cqm_info(pcgrp);
+
+ return ccinfo;
+}
+#endif
+
static inline void cqm_enable_mon(struct cgrp_cqm_info *cqm_info, u32 *rmid)
{
if (rmid != NULL) {
@@ -713,26 +725,27 @@ void alloc_needed_pkg_rmid(u32 *cqm_rmid)
static void intel_cqm_event_start(struct perf_event *event, int mode)
{
struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
- u32 rmid;

if (!(event->hw.cqm_state & PERF_HES_STOPPED))
return;

event->hw.cqm_state &= ~PERF_HES_STOPPED;

- alloc_needed_pkg_rmid(event->hw.cqm_rmid);
-
- rmid = event->hw.cqm_rmid[pkg_id];
- state->rmid = rmid;
- wrmsr(MSR_IA32_PQR_ASSOC, rmid, state->closid);
+ if (is_task_event(event)) {
+ alloc_needed_pkg_rmid(event->hw.cqm_rmid);
+ state->next_task_rmid = event->hw.cqm_rmid[pkg_id];
+ }
}

static void intel_cqm_event_stop(struct perf_event *event, int mode)
{
+ struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
+
if (event->hw.cqm_state & PERF_HES_STOPPED)
return;

event->hw.cqm_state |= PERF_HES_STOPPED;
+ state->next_task_rmid = 0;
}

static int intel_cqm_event_add(struct perf_event *event, int mode)
@@ -1366,6 +1379,8 @@ static int __init intel_cqm_init(void)
if (mbm_enabled)
pr_info("Intel MBM enabled\n");

+ static_branch_enable(&cqm_enable_key);
+
/*
* Setup the hot cpu notifier once we are sure cqm
* is enabled to avoid notifier leak.
diff --git a/arch/x86/include/asm/intel_pqr_common.h b/arch/x86/include/asm/intel_pqr_common.h
new file mode 100644
index 0000000..8fe9d8e
--- /dev/null
+++ b/arch/x86/include/asm/intel_pqr_common.h
@@ -0,0 +1,38 @@
+#ifndef _ASM_X86_INTEL_PQR_COMMON_H
+#define _ASM_X86_INTEL_PQR_COMMON_H
+
+#ifdef CONFIG_INTEL_RDT
+
+#include <linux/jump_label.h>
+#include <linux/types.h>
+#include <asm/percpu.h>
+#include <asm/msr.h>
+#include <asm/intel_rdt_common.h>
+
+void __intel_rdt_sched_in(void);
+
+/*
+ * 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 resource control and we enable by mounting the
+ * resctrl file system.
+ * - Caches the per cpu CLOSid values and does the MSR write only
+ * when a task with a different CLOSid is scheduled in.
+ */
+static inline void intel_rdt_sched_in(void)
+{
+ if (static_branch_likely(&rdt_enable_key) ||
+ static_branch_unlikely(&cqm_enable_key)) {
+ __intel_rdt_sched_in();
+ }
+}
+
+#else
+
+static inline void intel_rdt_sched_in(void) {}
+
+#endif
+#endif
diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h
index 95ce5c8..3b4a099 100644
--- a/arch/x86/include/asm/intel_rdt.h
+++ b/arch/x86/include/asm/intel_rdt.h
@@ -5,7 +5,6 @@

#include <linux/kernfs.h>
#include <linux/jump_label.h>
-
#include <asm/intel_rdt_common.h>

#define IA32_L3_QOS_CFG 0xc81
@@ -182,43 +181,5 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
int rdtgroup_schemata_show(struct kernfs_open_file *of,
struct seq_file *s, void *v);

-/*
- * 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 resource control and we enable by mounting the
- * resctrl file system.
- * - Caches the per cpu CLOSid values and does the MSR write only
- * when a task with a different CLOSid is scheduled in.
- *
- * Must be called with preemption disabled.
- */
-static inline void intel_rdt_sched_in(void)
-{
- if (static_branch_likely(&rdt_enable_key)) {
- struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
- int closid;
-
- /*
- * If this task has a closid assigned, use it.
- * Else use the closid assigned to this cpu.
- */
- closid = current->closid;
- if (closid == 0)
- closid = this_cpu_read(cpu_closid);
-
- if (closid != state->closid) {
- state->closid = closid;
- wrmsr(MSR_IA32_PQR_ASSOC, state->rmid, closid);
- }
- }
-}
-
-#else
-
-static inline void intel_rdt_sched_in(void) {}
-
#endif /* CONFIG_INTEL_RDT_A */
#endif /* _ASM_X86_INTEL_RDT_H */
diff --git a/arch/x86/include/asm/intel_rdt_common.h b/arch/x86/include/asm/intel_rdt_common.h
index e11ed5e..544acaa 100644
--- a/arch/x86/include/asm/intel_rdt_common.h
+++ b/arch/x86/include/asm/intel_rdt_common.h
@@ -18,12 +18,23 @@
*/
struct intel_pqr_state {
u32 rmid;
+ u32 next_task_rmid;
u32 closid;
int rmid_usecnt;
};

DECLARE_PER_CPU(struct intel_pqr_state, pqr_state);

+u32 __get_rmid(int domain);
+bool __rmid_valid(u32 rmid);
+void alloc_needed_pkg_rmid(u32 *cqm_rmid);
+struct cgrp_cqm_info *cqminfo_from_tsk(struct task_struct *tsk);
+
+extern struct cgrp_cqm_info cqm_rootcginfo;
+
+DECLARE_STATIC_KEY_FALSE(cqm_enable_key);
+DECLARE_STATIC_KEY_FALSE(rdt_enable_key);
+
/**
* struct cgrp_cqm_info - perf_event cgroup metadata for cqm
* @cont_mon Continuous monitoring flag
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index eaf1005..ec4beed 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -22,6 +22,7 @@
#include <asm/nops.h>
#include <asm/special_insns.h>
#include <asm/fpu/types.h>
+#include <asm/intel_pqr_common.h>

#include <linux/personality.h>
#include <linux/cache.h>
@@ -903,4 +904,7 @@ static inline uint32_t hypervisor_cpuid_base(const char *sig, uint32_t leaves)

void stop_this_cpu(void *dummy);
void df_debug(struct pt_regs *regs, long error_code);
+
+#define finish_arch_pre_lock_switch intel_rdt_sched_in
+
#endif /* _ASM_X86_PROCESSOR_H */
diff --git a/arch/x86/kernel/cpu/Makefile b/arch/x86/kernel/cpu/Makefile
index 5200001..d354e84 100644
--- a/arch/x86/kernel/cpu/Makefile
+++ b/arch/x86/kernel/cpu/Makefile
@@ -32,6 +32,7 @@ obj-$(CONFIG_CPU_SUP_CENTAUR) += centaur.o
obj-$(CONFIG_CPU_SUP_TRANSMETA_32) += transmeta.o
obj-$(CONFIG_CPU_SUP_UMC_32) += umc.o

+obj-$(CONFIG_INTEL_RDT) += intel_rdt_common.o
obj-$(CONFIG_INTEL_RDT_A) += intel_rdt.o intel_rdt_rdtgroup.o intel_rdt_schemata.o

obj-$(CONFIG_X86_MCE) += mcheck/
diff --git a/arch/x86/kernel/cpu/intel_rdt_common.c b/arch/x86/kernel/cpu/intel_rdt_common.c
new file mode 100644
index 0000000..c3c50cd
--- /dev/null
+++ b/arch/x86/kernel/cpu/intel_rdt_common.c
@@ -0,0 +1,98 @@
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/slab.h>
+#include <linux/err.h>
+#include <linux/cacheinfo.h>
+#include <linux/cpuhotplug.h>
+#include <asm/intel-family.h>
+#include <asm/intel_rdt.h>
+
+/*
+ * 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.
+ */
+DEFINE_PER_CPU(struct intel_pqr_state, pqr_state);
+
+#define pkg_id topology_physical_package_id(smp_processor_id())
+
+#ifdef CONFIG_INTEL_RDT_M
+static inline int get_cgroup_sched_rmid(void)
+{
+#ifdef CONFIG_CGROUP_PERF
+ struct cgrp_cqm_info *ccinfo = NULL;
+
+ ccinfo = cqminfo_from_tsk(current);
+
+ if (!ccinfo)
+ return 0;
+
+ /*
+ * A cgroup is always monitoring for itself or
+ * for an ancestor(default is root).
+ */
+ if (ccinfo->mon_enabled) {
+ alloc_needed_pkg_rmid(ccinfo->rmid);
+ return ccinfo->rmid[pkg_id];
+ } else {
+ alloc_needed_pkg_rmid(ccinfo->mfa->rmid);
+ return ccinfo->mfa->rmid[pkg_id];
+ }
+#endif
+
+ return 0;
+}
+
+static inline int get_sched_in_rmid(void)
+{
+ struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
+ u32 rmid = 0;
+
+ rmid = state->next_task_rmid;
+
+ return rmid ? rmid : get_cgroup_sched_rmid();
+}
+#endif
+
+/*
+ * 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 resource control and we enable by mounting the
+ * resctrl file system or it supports resource monitoring.
+ * - Caches the per cpu CLOSid/RMID values and does the MSR write only
+ * when a task with a different CLOSid/RMID is scheduled in.
+ */
+void __intel_rdt_sched_in(void)
+{
+ struct intel_pqr_state *state = this_cpu_ptr(&pqr_state);
+ int closid = 0;
+ u32 rmid = 0;
+
+#ifdef CONFIG_INTEL_RDT_A
+ if (static_branch_likely(&rdt_enable_key)) {
+ /*
+ * If this task has a closid assigned, use it.
+ * Else use the closid assigned to this cpu.
+ */
+ closid = current->closid;
+ if (closid == 0)
+ closid = this_cpu_read(cpu_closid);
+ }
+#endif
+
+#ifdef CONFIG_INTEL_RDT_M
+ if (static_branch_unlikely(&cqm_enable_key))
+ rmid = get_sched_in_rmid();
+#endif
+
+ if (closid != state->closid || rmid != state->rmid) {
+
+ state->closid = closid;
+ state->rmid = rmid;
+ wrmsr(MSR_IA32_PQR_ASSOC, rmid, closid);
+ }
+}
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 8af04af..8b6b429 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -206,7 +206,7 @@ static void rdt_update_cpu_closid(void *closid)
* executing task might have its own closid selected. Just reuse
* the context switch code.
*/
- intel_rdt_sched_in();
+ __intel_rdt_sched_in();
}

/*
@@ -328,7 +328,7 @@ static void move_myself(struct callback_head *head)

preempt_disable();
/* update PQR_ASSOC MSR to make resource group go into effect */
- intel_rdt_sched_in();
+ __intel_rdt_sched_in();
preempt_enable();

kfree(callback);
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index a0ac3e8..d0d7441 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -53,7 +53,6 @@
#include <asm/debugreg.h>
#include <asm/switch_to.h>
#include <asm/vm86.h>
-#include <asm/intel_rdt.h>

void __show_regs(struct pt_regs *regs, int all)
{
@@ -297,8 +296,5 @@ int copy_thread_tls(unsigned long clone_flags, unsigned long sp,

this_cpu_write(current_task, next_p);

- /* Load the Intel cache allocation PQR MSR. */
- intel_rdt_sched_in();
-
return prev_p;
}
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index a61e141..a76b65e 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -49,7 +49,6 @@
#include <asm/switch_to.h>
#include <asm/xen/hypervisor.h>
#include <asm/vdso.h>
-#include <asm/intel_rdt.h>

__visible DEFINE_PER_CPU(unsigned long, rsp_scratch);

@@ -477,9 +476,6 @@ void compat_start_thread(struct pt_regs *regs, u32 new_ip, u32 new_sp)
loadsegment(ss, __KERNEL_DS);
}

- /* Load the Intel cache allocation PQR MSR. */
- intel_rdt_sched_in();
-
return prev_p;
}

diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index c56fb57..bf970ab 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -2767,6 +2767,7 @@ static struct rq *finish_task_switch(struct task_struct *prev)
prev_state = prev->state;
vtime_task_switch(prev);
perf_event_task_sched_in(prev, current);
+ finish_arch_pre_lock_switch();
finish_lock_switch(rq, prev);
finish_arch_post_lock_switch();

diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 7b34c78..61b47a5 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1121,6 +1121,9 @@ static inline int task_on_rq_migrating(struct task_struct *p)
#ifndef prepare_arch_switch
# define prepare_arch_switch(next) do { } while (0)
#endif
+#ifndef finish_arch_pre_lock_switch
+# define finish_arch_pre_lock_switch() do { } while (0)
+#endif
#ifndef finish_arch_post_lock_switch
# define finish_arch_post_lock_switch() do { } while (0)
#endif
--
1.9.1

Next message: RafaÅ MiÅecki: "Re: [PATCH] ssb: main.c: This patch removes unnecessary return statement using spatch tool"
Previous message: Greg Kroah-Hartman: "[PATCH 4.9 066/116] s390/kexec: use node 0 when re-adding crash kernel memory"
In reply to: Vikas Shivappa: "[PATCH 08/12] x86/cqm: Add support for monitoring task and cgroup together"
Next in thread: Vikas Shivappa: "[PATCH 06/12] x86/cqm: Add cgroup hierarchical monitoring support"
Messages sorted by: [ date ] [ thread ] [ subject ] [ author ]