x86/intel_rdt: Add scheduler hook

Hook the x86 scheduler code to update closid based on whether the current
task is assigned to a specific closid or running on a CPU assigned to a
specific closid.

Signed-off-by: Fenghua Yu <fenghua.yu@intel.com>
Cc: "Ravi V Shankar" <ravi.v.shankar@intel.com>
Cc: "Tony Luck" <tony.luck@intel.com>
Cc: "Shaohua Li" <shli@fb.com>
Cc: "Sai Prakhya" <sai.praneeth.prakhya@intel.com>
Cc: "Peter Zijlstra" <peterz@infradead.org>
Cc: "Stephane Eranian" <eranian@google.com>
Cc: "Dave Hansen" <dave.hansen@intel.com>
Cc: "David Carrillo-Cisneros" <davidcc@google.com>
Cc: "Nilay Vaish" <nilayvaish@gmail.com>
Cc: "Vikas Shivappa" <vikas.shivappa@linux.intel.com>
Cc: "Ingo Molnar" <mingo@elte.hu>
Cc: "Borislav Petkov" <bp@suse.de>
Cc: "H. Peter Anvin" <h.peter.anvin@intel.com>
Link: http://lkml.kernel.org/r/1477692289-37412-10-git-send-email-fenghua.yu@intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

5 files changed, 53 insertions, 1 deletions

diff --git a/arch/x86/include/asm/intel_rdt.h b/arch/x86/include/asm/intel_rdt.h
index 2e5eab09083e..5bc72a4dbd5e 100644
--- a/arch/x86/include/asm/intel_rdt.h
+++ b/arch/x86/include/asm/intel_rdt.h
@@ -1,8 +1,12 @@
 #ifndef _ASM_X86_INTEL_RDT_H
 #define _ASM_X86_INTEL_RDT_H
 
+#ifdef CONFIG_INTEL_RDT_A
+
 #include <linux/jump_label.h>
 
+#include <asm/intel_rdt_common.h>
+
 #define IA32_L3_QOS_CFG         0xc81
 #define IA32_L3_CBM_BASE        0xc90
 #define IA32_L2_CBM_BASE        0xd10
@@ -176,4 +180,42 @@ ssize_t rdtgroup_schemata_write(struct kernfs_open_file *of,
                                 char *buf, size_t nbytes, loff_t off);
 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.
+ */
+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/kernel/cpu/intel_rdt.c b/arch/x86/kernel/cpu/intel_rdt.c
index 40094aed5f71..5a533fefefa0 100644
--- a/arch/x86/kernel/cpu/intel_rdt.c
+++ b/arch/x86/kernel/cpu/intel_rdt.c
@@ -29,7 +29,6 @@
 #include <linux/cacheinfo.h>
 #include <linux/cpuhotplug.h>
 
-#include <asm/intel_rdt_common.h>
 #include <asm/intel-family.h>
 #include <asm/intel_rdt.h>
 
diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 5c4bab9452b0..a90ad22b9823 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -292,6 +292,9 @@ static void move_myself(struct callback_head *head)
                 kfree(rdtgrp);
         }
 
+        /* update PQR_ASSOC MSR to make resource group go into effect */
+        intel_rdt_sched_in();
+
         kfree(callback);
 }
 
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index bd7be8efdc4c..efe7f9fce44e 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -54,6 +54,7 @@
 #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)
 {
@@ -299,5 +300,8 @@ __switch_to(struct task_struct *prev_p, struct task_struct *next_p)
 
         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 b3760b3c1ca0..acd7d6f507af 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -50,6 +50,7 @@
 #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);
 
@@ -473,6 +474,9 @@ __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;
 }