diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
index a97cd029db36..1b460cf27a10 100644
--- a/arch/x86/events/intel/uncore_snbep.c
+++ b/arch/x86/events/intel/uncore_snbep.c
@@ -474,6 +474,9 @@
 /* DMR */
 #define DMR_IMH1_HIOP_MMIO_BASE			0x1ffff6ae7000
 #define DMR_HIOP_MMIO_SIZE			0x8000
+#define DMR_CXLCM_PMON_CTL_INVERT		BIT(21)
+#define DMR_CXLCM_PMON_RAW_EVENT_MASK		(GENERIC_PMON_RAW_EVENT_MASK | \
+						 DMR_CXLCM_PMON_CTL_INVERT)
 #define DMR_CXLCM_EVENT_MASK_EXT		0xf
 #define DMR_HAMVF_EVENT_MASK_EXT		0xffffffff
 #define DMR_PCIE4_EVENT_MASK_EXT		0xffffff
@@ -6696,7 +6699,7 @@ static struct event_constraint dmr_uncore_cxlcm_constraints[] = {
 
 static struct intel_uncore_type dmr_uncore_cxlcm = {
 	.name			= "cxlcm",
-	.event_mask		= GENERIC_PMON_RAW_EVENT_MASK,
+	.event_mask		= DMR_CXLCM_PMON_RAW_EVENT_MASK,
 	.event_mask_ext		= DMR_CXLCM_EVENT_MASK_EXT,
 	.constraints		= dmr_uncore_cxlcm_constraints,
 	.format_group		= &dmr_cxlcm_uncore_format_group,
diff --git a/include/linux/sched/user.h b/include/linux/sched/user.h
index 8d7e5521f7cd..ec262b605437 100644
--- a/include/linux/sched/user.h
+++ b/include/linux/sched/user.h
@@ -23,11 +23,13 @@ struct user_struct {
 	struct hlist_node uidhash_node;
 	kuid_t uid;
 
-#if defined(CONFIG_PERF_EVENTS) || defined(CONFIG_BPF_SYSCALL) || \
-	defined(CONFIG_NET) || defined(CONFIG_IO_URING) || \
+#if defined(CONFIG_NET) || defined(CONFIG_IO_URING) || \
 	defined(CONFIG_VFIO_PCI_ZDEV_KVM) || IS_ENABLED(CONFIG_IOMMUFD) || \
 	defined(CONFIG_SECRETMEM)
-	atomic_long_t locked_vm;
+	atomic_long_t locked_vm;	/* pinned pages charged to RLIMIT_MEMLOCK */
+#endif
+#ifdef CONFIG_PERF_EVENTS
+	atomic_long_t perf_mlock;	/* perf buffer pages within perf_event_mlock_kb */
 #endif
 #ifdef CONFIG_WATCH_QUEUE
 	atomic_t nr_watches;	/* The number of watches this user currently has */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 7846d70be57f..c4217c996f5a 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -4639,6 +4639,7 @@ static bool perf_rotate_context(struct perf_cpu_pmu_context *cpc)
 
 	if (cpu_event) {
 		update_context_time(&cpuctx->ctx);
+		update_cgrp_time_from_cpuctx(cpuctx, false);
 		__pmu_ctx_sched_out(cpu_epc, EVENT_FLEXIBLE);
 		rotate_ctx(&cpuctx->ctx, cpu_event);
 		__pmu_ctx_sched_in(cpu_epc, EVENT_FLEXIBLE);
@@ -7059,7 +7060,7 @@ static void perf_mmap_close(struct vm_area_struct *vma)
 		perf_pmu_output_stop(event);
 
 		/* now it's safe to free the pages */
-		atomic_long_sub(rb->aux_nr_pages - rb->aux_mmap_locked, &mmap_user->locked_vm);
+		atomic_long_sub(rb->aux_nr_pages - rb->aux_mmap_locked, &mmap_user->perf_mlock);
 		atomic64_sub(rb->aux_mmap_locked, &vma->vm_mm->pinned_vm);
 
 		/* this has to be the last one */
@@ -7242,11 +7243,11 @@ static bool perf_mmap_calc_limits(struct vm_area_struct *vma, long *user_extra,
 	/* Increase the limit linearly with more CPUs */
 	user_lock_limit *= num_online_cpus();
 
-	user_locked = atomic_long_read(&user->locked_vm);
+	user_locked = atomic_long_read(&user->perf_mlock);
 
 	/*
 	 * sysctl_perf_event_mlock may have changed, so that
-	 *     user->locked_vm > user_lock_limit
+	 *     user->perf_mlock > user_lock_limit
 	 */
 	if (user_locked > user_lock_limit)
 		user_locked = user_lock_limit;
@@ -7254,7 +7255,7 @@ static bool perf_mmap_calc_limits(struct vm_area_struct *vma, long *user_extra,
 
 	if (user_locked > user_lock_limit) {
 		/*
-		 * charge locked_vm until it hits user_lock_limit;
+		 * charge perf_mlock until it hits user_lock_limit;
 		 * charge the rest from pinned_vm
 		 */
 		*extra = user_locked - user_lock_limit;
@@ -7272,7 +7273,7 @@ static void perf_mmap_account(struct vm_area_struct *vma, long user_extra, long
 {
 	struct user_struct *user = current_user();
 
-	atomic_long_add(user_extra, &user->locked_vm);
+	atomic_long_add(user_extra, &user->perf_mlock);
 	atomic64_add(extra, &vma->vm_mm->pinned_vm);
 }
 
@@ -7281,7 +7282,7 @@ static void perf_mmap_unaccount(struct vm_area_struct *vma, struct perf_buffer *
 	struct user_struct *user = rb->mmap_user;
 
 	atomic_long_sub((perf_data_size(rb) >> PAGE_SHIFT) + 1 - rb->mmap_locked,
-			&user->locked_vm);
+			&user->perf_mlock);
 	atomic64_sub(rb->mmap_locked, &vma->vm_mm->pinned_vm);
 }
 
@@ -14394,23 +14395,18 @@ err:
 }
 EXPORT_SYMBOL_GPL(perf_event_create_kernel_counter);
 
-static void __perf_pmu_remove(struct perf_event_context *ctx,
-			      int cpu, struct pmu *pmu,
-			      struct perf_event_groups *groups,
+static void __perf_pmu_remove(struct perf_event_context *ctx, struct pmu *pmu,
 			      struct list_head *events)
 {
-	struct perf_event *event, *sibling;
+	struct perf_event *event, *tmp;
+
+	list_for_each_entry_safe(event, tmp, &ctx->event_list, event_entry) {
+		if (event->pmu_ctx->pmu != pmu)
+			continue;
 
-	perf_event_groups_for_cpu_pmu(event, groups, cpu, pmu) {
 		perf_remove_from_context(event, 0);
 		put_pmu_ctx(event->pmu_ctx);
 		list_add(&event->migrate_entry, events);
-
-		for_each_sibling_event(sibling, event) {
-			perf_remove_from_context(sibling, 0);
-			put_pmu_ctx(sibling->pmu_ctx);
-			list_add(&sibling->migrate_entry, events);
-		}
 	}
 }
 
@@ -14486,8 +14482,7 @@ void perf_pmu_migrate_context(struct pmu *pmu, int src_cpu, int dst_cpu)
 	 */
 	mutex_lock_double(&src_ctx->mutex, &dst_ctx->mutex);
 
-	__perf_pmu_remove(src_ctx, src_cpu, pmu, &src_ctx->pinned_groups, &events);
-	__perf_pmu_remove(src_ctx, src_cpu, pmu, &src_ctx->flexible_groups, &events);
+	__perf_pmu_remove(src_ctx, pmu, &events);
 
 	if (!list_empty(&events)) {
 		/*