Merge tag 'perf_urgent_for_v6.1_rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf fixes from Borislav Petkov:

 - Fix an intel PT erratum where CPUs do not support single range output
   for more than 4K

 - Fix a NULL ptr dereference which can happen after an NMI interferes
   with the event enabling dance in amd_pmu_enable_all()

 - Free the events array too when freeing uncore contexts on CPU online,
   thereby fixing a memory leak

 - Improve the pending SIGTRAP check

* tag 'perf_urgent_for_v6.1_rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/intel/pt: Fix sampling using single range output
  perf/x86/amd: Fix crash due to race between amd_pmu_enable_all, perf NMI and throttling
  perf/x86/amd/uncore: Fix memory leak for events array
  perf: Improve missing SIGTRAP checking

Author: torvalds

arch/x86/events/amd/core.c

@@ -861,8 +861,7 @@ static int amd_pmu_handle_irq(struct pt_regs *regs)
 	pmu_enabled = cpuc->enabled;
 	cpuc->enabled = 0;
 
-	/* stop everything (includes BRS) */
-	amd_pmu_disable_all();
+	amd_brs_disable_all();
 
 	/* Drain BRS is in use (could be inactive) */
 	if (cpuc->lbr_users)
@@ -873,7 +872,7 @@ static int amd_pmu_handle_irq(struct pt_regs *regs)
 
 	cpuc->enabled = pmu_enabled;
 	if (pmu_enabled)
-		amd_pmu_enable_all(0);
+		amd_brs_enable_all();
 
 	return amd_pmu_adjust_nmi_window(handled);
 }

arch/x86/events/amd/uncore.c

@@ -553,6 +553,7 @@ static void uncore_clean_online(void)
 
 	hlist_for_each_entry_safe(uncore, n, &uncore_unused_list, node) {
 		hlist_del(&uncore->node);
+		kfree(uncore->events);
 		kfree(uncore);
 	}
 }

arch/x86/events/intel/pt.c

@@ -1263,6 +1263,15 @@ static int pt_buffer_try_single(struct pt_buffer *buf, int nr_pages)
 	if (1 << order != nr_pages)
 		goto out;
 
+	/*
+	 * Some processors cannot always support single range for more than
+	 * 4KB - refer errata TGL052, ADL037 and RPL017. Future processors might
+	 * also be affected, so for now rather than trying to keep track of
+	 * which ones, just disable it for all.
+	 */
+	if (nr_pages > 1)
+		goto out;
+
 	buf->single = true;
 	buf->nr_pages = nr_pages;
 	ret = 0;

kernel/events/core.c

@@ -9306,14 +9306,27 @@ static int __perf_event_overflow(struct perf_event *event,
 	}
 
 	if (event->attr.sigtrap) {
-		/*
-		 * Should not be able to return to user space without processing
-		 * pending_sigtrap (kernel events can overflow multiple times).
-		 */
-		WARN_ON_ONCE(event->pending_sigtrap && event->attr.exclude_kernel);
+		unsigned int pending_id = 1;
+
+		if (regs)
+			pending_id = hash32_ptr((void *)instruction_pointer(regs)) ?: 1;
 		if (!event->pending_sigtrap) {
-			event->pending_sigtrap = 1;
+			event->pending_sigtrap = pending_id;
 			local_inc(&event->ctx->nr_pending);
+		} else if (event->attr.exclude_kernel) {
+			/*
+			 * Should not be able to return to user space without
+			 * consuming pending_sigtrap; with exceptions:
+			 *
+			 *  1. Where !exclude_kernel, events can overflow again
+			 *     in the kernel without returning to user space.
+			 *
+			 *  2. Events that can overflow again before the IRQ-
+			 *     work without user space progress (e.g. hrtimer).
+			 *     To approximate progress (with false negatives),
+			 *     check 32-bit hash of the current IP.
+			 */
+			WARN_ON_ONCE(event->pending_sigtrap != pending_id);
 		}
 		event->pending_addr = data->addr;
 		irq_work_queue(&event->pending_irq);