x86/resctrl: Fix to restore to original value when re-enabling hardware prefetch register

The current pseudo_lock.c code overwrites the value of the
MSR_MISC_FEATURE_CONTROL to 0 even if the original value is not 0.
Therefore, modify it to save and restore the original values.

Fixes: 018961ae ("x86/intel_rdt: Pseudo-lock region creation/removal core")
Fixes: 443810fe ("x86/intel_rdt: Create debugfs files for pseudo-locking testing")
Fixes: 8a2fc0e1 ("x86/intel_rdt: More precise L2 hit/miss measurements")
Signed-off-by: Kohei Tarumizu <tarumizu.kohei@fujitsu.com>
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Acked-by: Reinette Chatre <reinette.chatre@intel.com>
Link: https://lkml.kernel.org/r/eb660f3c2010b79a792c573c02d01e8e841206ad.1661358182.git.reinette.chatre@intel.com

arch/x86/kernel/cpu/resctrl/pseudo_lock.c

@@ -420,6 +420,7 @@ static int pseudo_lock_fn(void *_rdtgrp)
 	struct pseudo_lock_region *plr = rdtgrp->plr;
 	u32 rmid_p, closid_p;
 	unsigned long i;
+	u64 saved_msr;
 #ifdef CONFIG_KASAN
 	/*
 	 * The registers used for local register variables are also used
@@ -463,6 +464,7 @@ static int pseudo_lock_fn(void *_rdtgrp)
 	 * the buffer and evict pseudo-locked memory read earlier from the
 	 * cache.
 	 */
+	saved_msr = __rdmsr(MSR_MISC_FEATURE_CONTROL);
 	__wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
 	closid_p = this_cpu_read(pqr_state.cur_closid);
 	rmid_p = this_cpu_read(pqr_state.cur_rmid);
@@ -514,7 +516,7 @@ static int pseudo_lock_fn(void *_rdtgrp)
 	__wrmsr(IA32_PQR_ASSOC, rmid_p, closid_p);
 
 	/* Re-enable the hardware prefetcher(s) */
-	wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
+	wrmsrl(MSR_MISC_FEATURE_CONTROL, saved_msr);
 	local_irq_enable();
 
 	plr->thread_done = 1;
@@ -871,6 +873,7 @@ bool rdtgroup_pseudo_locked_in_hierarchy(struct rdt_domain *d)
 static int measure_cycles_lat_fn(void *_plr)
 {
 	struct pseudo_lock_region *plr = _plr;
+	u32 saved_low, saved_high;
 	unsigned long i;
 	u64 start, end;
 	void *mem_r;
@@ -879,6 +882,7 @@ static int measure_cycles_lat_fn(void *_plr)
 	/*
 	 * Disable hardware prefetchers.
 	 */
+	rdmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high);
 	wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
 	mem_r = READ_ONCE(plr->kmem);
 	/*
@@ -895,7 +899,7 @@ static int measure_cycles_lat_fn(void *_plr)
 		end = rdtsc_ordered();
 		trace_pseudo_lock_mem_latency((u32)(end - start));
 	}
-	wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
+	wrmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high);
 	local_irq_enable();
 	plr->thread_done = 1;
 	wake_up_interruptible(&plr->lock_thread_wq);
@@ -940,6 +944,7 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr,
 	u64 hits_before = 0, hits_after = 0, miss_before = 0, miss_after = 0;
 	struct perf_event *miss_event, *hit_event;
 	int hit_pmcnum, miss_pmcnum;
+	u32 saved_low, saved_high;
 	unsigned int line_size;
 	unsigned int size;
 	unsigned long i;
@@ -973,6 +978,7 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr,
 	/*
 	 * Disable hardware prefetchers.
 	 */
+	rdmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high);
 	wrmsr(MSR_MISC_FEATURE_CONTROL, prefetch_disable_bits, 0x0);
 
 	/* Initialize rest of local variables */
@@ -1031,7 +1037,7 @@ static int measure_residency_fn(struct perf_event_attr *miss_attr,
 	 */
 	rmb();
 	/* Re-enable hardware prefetchers */
-	wrmsr(MSR_MISC_FEATURE_CONTROL, 0x0, 0x0);
+	wrmsr(MSR_MISC_FEATURE_CONTROL, saved_low, saved_high);
 	local_irq_enable();
 out_hit:
 	perf_event_release_kernel(hit_event);