Merge tag 'perf-core-2024-07-16' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull performance events updates from Ingo Molnar:

 - Intel PT support enhancements & fixes

 - Fix leaked SIGTRAP events

 - Improve and fix the Intel uncore driver

 - Add support for Intel HBM and CXL uncore counters

 - Add Intel Lake and Arrow Lake support

 - AMD uncore driver fixes

 - Make SIGTRAP and __perf_pending_irq() work on RT

 - Micro-optimizations

 - Misc cleanups and fixes

* tag 'perf-core-2024-07-16' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (44 commits)
  perf/x86/intel: Add a distinct name for Granite Rapids
  perf/x86/intel/ds: Fix non 0 retire latency on Raptorlake
  perf/x86/intel: Hide Topdown metrics events if the feature is not enumerated
  perf/x86/intel/uncore: Fix the bits of the CHA extended umask for SPR
  perf: Split __perf_pending_irq() out of perf_pending_irq()
  perf: Don't disable preemption in perf_pending_task().
  perf: Move swevent_htable::recursion into task_struct.
  perf: Shrink the size of the recursion counter.
  perf: Enqueue SIGTRAP always via task_work.
  task_work: Add TWA_NMI_CURRENT as an additional notify mode.
  perf: Move irq_work_queue() where the event is prepared.
  perf: Fix event leak upon exec and file release
  perf: Fix event leak upon exit
  task_work: Introduce task_work_cancel() again
  task_work: s/task_work_cancel()/task_work_cancel_func()/
  perf/x86/amd/uncore: Fix DF and UMC domain identification
  perf/x86/amd/uncore: Avoid PMU registration if counters are unavailable
  perf/x86/intel: Support Perfmon MSRs aliasing
  perf/x86/intel: Support PERFEVTSEL extension
  perf/x86: Add config_mask to represent EVENTSEL bitmask
  ...

4 files changed, 17 insertions, 11 deletions

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index a5304ae8c654..65ece0d5b4b6 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -781,11 +781,12 @@ struct perf_event {
 	unsigned int			pending_wakeup;
 	unsigned int			pending_kill;
 	unsigned int			pending_disable;
-	unsigned int			pending_sigtrap;
 	unsigned long			pending_addr;	/* SIGTRAP */
 	struct irq_work			pending_irq;
+	struct irq_work			pending_disable_irq;
 	struct callback_head		pending_task;
 	unsigned int			pending_work;
+	struct rcuwait			pending_work_wait;
 
 	atomic_t			event_limit;
 
@@ -962,7 +963,7 @@ struct perf_event_context {
 	struct rcu_head			rcu_head;
 
 	/*
-	 * Sum (event->pending_sigtrap + event->pending_work)
+	 * Sum (event->pending_work + event->pending_work)
 	 *
 	 * The SIGTRAP is targeted at ctx->task, as such it won't do changing
 	 * that until the signal is delivered.
@@ -970,12 +971,6 @@ struct perf_event_context {
 	local_t				nr_pending;
 };
 
-/*
- * Number of contexts where an event can trigger:
- *	task, softirq, hardirq, nmi.
- */
-#define PERF_NR_CONTEXTS	4
-
 struct perf_cpu_pmu_context {
 	struct perf_event_pmu_context	epc;
 	struct perf_event_pmu_context	*task_epc;
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 76214d7c819d..3e1329e4bf1f 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -734,6 +734,12 @@ enum perf_event_task_context {
 	perf_nr_task_contexts,
 };
 
+/*
+ * Number of contexts where an event can trigger:
+ *      task, softirq, hardirq, nmi.
+ */
+#define PERF_NR_CONTEXTS	4
+
 struct wake_q_node {
 	struct wake_q_node *next;
 };
@@ -1256,6 +1262,7 @@ struct task_struct {
 	unsigned int			futex_state;
 #endif
 #ifdef CONFIG_PERF_EVENTS
+	u8				perf_recursion[PERF_NR_CONTEXTS];
 	struct perf_event_context	*perf_event_ctxp;
 	struct mutex			perf_event_mutex;
 	struct list_head		perf_event_list;
diff --git a/include/linux/task_work.h b/include/linux/task_work.h
index 795ef5a68429..cf5e7e891a77 100644
--- a/include/linux/task_work.h
+++ b/include/linux/task_work.h
@@ -18,6 +18,7 @@ enum task_work_notify_mode {
 	TWA_RESUME,
 	TWA_SIGNAL,
 	TWA_SIGNAL_NO_IPI,
+	TWA_NMI_CURRENT,
 };
 
 static inline bool task_work_pending(struct task_struct *task)
@@ -30,7 +31,8 @@ int task_work_add(struct task_struct *task, struct callback_head *twork,
 
 struct callback_head *task_work_cancel_match(struct task_struct *task,
 	bool (*match)(struct callback_head *, void *data), void *data);
-struct callback_head *task_work_cancel(struct task_struct *, task_work_func_t);
+struct callback_head *task_work_cancel_func(struct task_struct *, task_work_func_t);
+bool task_work_cancel(struct task_struct *task, struct callback_head *cb);
 void task_work_run(void);
 
 static inline void exit_task_work(struct task_struct *task)
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 3a64499b0f5d..4842c36fdf80 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -1349,12 +1349,14 @@ union perf_mem_data_src {
 #define PERF_MEM_LVLNUM_L2	0x02 /* L2 */
 #define PERF_MEM_LVLNUM_L3	0x03 /* L3 */
 #define PERF_MEM_LVLNUM_L4	0x04 /* L4 */
-/* 5-0x7 available */
+#define PERF_MEM_LVLNUM_L2_MHB	0x05 /* L2 Miss Handling Buffer */
+#define PERF_MEM_LVLNUM_MSC	0x06 /* Memory-side Cache */
+/* 0x7 available */
 #define PERF_MEM_LVLNUM_UNC	0x08 /* Uncached */
 #define PERF_MEM_LVLNUM_CXL	0x09 /* CXL */
 #define PERF_MEM_LVLNUM_IO	0x0a /* I/O */
 #define PERF_MEM_LVLNUM_ANY_CACHE 0x0b /* Any cache */
-#define PERF_MEM_LVLNUM_LFB	0x0c /* LFB */
+#define PERF_MEM_LVLNUM_LFB	0x0c /* LFB / L1 Miss Handling Buffer */
 #define PERF_MEM_LVLNUM_RAM	0x0d /* RAM */
 #define PERF_MEM_LVLNUM_PMEM	0x0e /* PMEM */
 #define PERF_MEM_LVLNUM_NA	0x0f /* N/A */