Merge tag 'smp-core-2023-04-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull SMP cross-CPU function-call updates from Ingo Molnar:

 - Remove diagnostics and adjust config for CSD lock diagnostics

 - Add a generic IPI-sending tracepoint, as currently there's no easy
   way to instrument IPI origins: it's arch dependent and for some major
   architectures it's not even consistently available.

* tag 'smp-core-2023-04-27' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  trace,smp: Trace all smp_function_call*() invocations
  trace: Add trace_ipi_send_cpu()
  sched, smp: Trace smp callback causing an IPI
  smp: reword smp call IPI comment
  treewide: Trace IPIs sent via smp_send_reschedule()
  irq_work: Trace self-IPIs sent via arch_irq_work_raise()
  smp: Trace IPIs sent via arch_send_call_function_ipi_mask()
  sched, smp: Trace IPIs sent via send_call_function_single_ipi()
  trace: Add trace_ipi_send_cpumask()
  kernel/smp: Make csdlock_debug= resettable
  locking/csd_lock: Remove per-CPU data indirection from CSD lock debugging
  locking/csd_lock: Remove added data from CSD lock debugging
  locking/csd_lock: Add Kconfig option for csd_debug default

Documentation/admin-guide/kernel-parameters.txt

@@ -912,15 +912,14 @@
 	cs89x0_media=	[HW,NET]
 			Format: { rj45 | aui | bnc }
 
-	csdlock_debug=	[KNL] Enable debug add-ons of cross-CPU function call
-			handling. When switched on, additional debug data is
-			printed to the console in case a hanging CPU is
-			detected, and that CPU is pinged again in order to try
-			to resolve the hang situation.
-			0: disable csdlock debugging (default)
-			1: enable basic csdlock debugging (minor impact)
-			ext: enable extended csdlock debugging (more impact,
-			     but more data)
+	csdlock_debug=	[KNL] Enable or disable debug add-ons of cross-CPU
+			function call handling. When switched on,
+			additional debug data is printed to the console
+			in case a hanging CPU is detected, and that
+			CPU is pinged again in order to try to resolve
+			the hang situation.  The default value of this
+			option depends on the CSD_LOCK_WAIT_DEBUG_DEFAULT
+			Kconfig option.
 
 	dasd=		[HW,NET]
 			See header of drivers/s390/block/dasd_devmap.c.

arch/alpha/kernel/smp.c

@@ -562,7 +562,7 @@ handle_ipi(struct pt_regs *regs)
 }
 
 void
-smp_send_reschedule(int cpu)
+arch_smp_send_reschedule(int cpu)
 {
 #ifdef DEBUG_IPI_MSG
 	if (cpu == hard_smp_processor_id())

arch/arc/kernel/smp.c

@@ -292,7 +292,7 @@ static void ipi_send_msg(const struct cpumask *callmap, enum ipi_msg_type msg)
 		ipi_send_msg_one(cpu, msg);
 }
 
-void smp_send_reschedule(int cpu)
+void arch_smp_send_reschedule(int cpu)
 {
 	ipi_send_msg_one(cpu, IPI_RESCHEDULE);
 }

arch/arm/kernel/smp.c

@@ -48,7 +48,6 @@
 #include <asm/mach/arch.h>
 #include <asm/mpu.h>
 
-#define CREATE_TRACE_POINTS
 #include <trace/events/ipi.h>
 
 /*
@@ -749,7 +748,7 @@ void __init set_smp_ipi_range(int ipi_base, int n)
 	ipi_setup(smp_processor_id());
 }
 
-void smp_send_reschedule(int cpu)
+void arch_smp_send_reschedule(int cpu)
 {
 	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
 }

arch/arm/mach-actions/platsmp.c

@@ -20,6 +20,8 @@
 #include <asm/smp_plat.h>
 #include <asm/smp_scu.h>
 
+#include <trace/events/ipi.h>
+
 #define OWL_CPU1_ADDR	0x50
 #define OWL_CPU1_FLAG	0x5c
 

arch/arm64/kernel/smp.c

@@ -51,7 +51,6 @@
 #include <asm/ptrace.h>
 #include <asm/virt.h>
 
-#define CREATE_TRACE_POINTS
 #include <trace/events/ipi.h>
 
 DEFINE_PER_CPU_READ_MOSTLY(int, cpu_number);
@@ -979,7 +978,7 @@ void __init set_smp_ipi_range(int ipi_base, int n)
 	ipi_setup(smp_processor_id());
 }
 
-void smp_send_reschedule(int cpu)
+void arch_smp_send_reschedule(int cpu)
 {
 	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
 }

arch/csky/kernel/smp.c

@@ -140,7 +140,7 @@ void smp_send_stop(void)
 	on_each_cpu(ipi_stop, NULL, 1);
 }
 
-void smp_send_reschedule(int cpu)
+void arch_smp_send_reschedule(int cpu)
 {
 	send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE);
 }

arch/hexagon/kernel/smp.c

@@ -217,7 +217,7 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
 	}
 }
 
-void smp_send_reschedule(int cpu)
+void arch_smp_send_reschedule(int cpu)
 {
 	send_ipi(cpumask_of(cpu), IPI_RESCHEDULE);
 }

arch/ia64/kernel/smp.c

@@ -220,11 +220,11 @@ kdump_smp_send_init(void)
  * Called with preemption disabled.
  */
 void
-smp_send_reschedule (int cpu)
+arch_smp_send_reschedule (int cpu)
 {
 	ia64_send_ipi(cpu, IA64_IPI_RESCHEDULE, IA64_IPI_DM_INT, 0);
 }
-EXPORT_SYMBOL_GPL(smp_send_reschedule);
+EXPORT_SYMBOL_GPL(arch_smp_send_reschedule);
 
 /*
  * Called with preemption disabled.

arch/loongarch/kernel/smp.c

@@ -155,11 +155,11 @@ void loongson_send_ipi_mask(const struct cpumask *mask, unsigned int action)
  * it goes straight through and wastes no time serializing
  * anything. Worst case is that we lose a reschedule ...
  */
-void smp_send_reschedule(int cpu)
+void arch_smp_send_reschedule(int cpu)
 {
 	loongson_send_ipi_single(cpu, SMP_RESCHEDULE);
 }
-EXPORT_SYMBOL_GPL(smp_send_reschedule);
+EXPORT_SYMBOL_GPL(arch_smp_send_reschedule);
 
 irqreturn_t loongson_ipi_interrupt(int irq, void *dev)
 {

arch/mips/include/asm/smp.h

@@ -66,7 +66,7 @@ extern void calculate_cpu_foreign_map(void);
  * it goes straight through and wastes no time serializing
  * anything. Worst case is that we lose a reschedule ...
  */
-static inline void smp_send_reschedule(int cpu)
+static inline void arch_smp_send_reschedule(int cpu)
 {
 	extern const struct plat_smp_ops *mp_ops;	/* private */
 

arch/openrisc/kernel/smp.c

@@ -173,7 +173,7 @@ void handle_IPI(unsigned int ipi_msg)
 	}
 }
 
-void smp_send_reschedule(int cpu)
+void arch_smp_send_reschedule(int cpu)
 {
 	smp_cross_call(cpumask_of(cpu), IPI_RESCHEDULE);
 }

arch/parisc/kernel/smp.c

@@ -246,8 +246,8 @@ void kgdb_roundup_cpus(void)
 inline void 
 smp_send_stop(void)	{ send_IPI_allbutself(IPI_CPU_STOP); }
 
-void 
-smp_send_reschedule(int cpu) { send_IPI_single(cpu, IPI_RESCHEDULE); }
+void
+arch_smp_send_reschedule(int cpu) { send_IPI_single(cpu, IPI_RESCHEDULE); }
 
 void
 smp_send_all_nop(void)

arch/powerpc/kernel/smp.c

@@ -61,6 +61,8 @@
 #include <asm/kup.h>
 #include <asm/fadump.h>
 
+#include <trace/events/ipi.h>
+
 #ifdef DEBUG
 #include <asm/udbg.h>
 #define DBG(fmt...) udbg_printf(fmt)
@@ -364,12 +366,12 @@ static inline void do_message_pass(int cpu, int msg)
 #endif
 }
 
-void smp_send_reschedule(int cpu)
+void arch_smp_send_reschedule(int cpu)
 {
 	if (likely(smp_ops))
 		do_message_pass(cpu, PPC_MSG_RESCHEDULE);
 }
-EXPORT_SYMBOL_GPL(smp_send_reschedule);
+EXPORT_SYMBOL_GPL(arch_smp_send_reschedule);
 
 void arch_send_call_function_single_ipi(int cpu)
 {

arch/powerpc/kvm/book3s_hv.c

@@ -43,6 +43,7 @@
 #include <linux/compiler.h>
 #include <linux/of.h>
 #include <linux/irqdomain.h>
+#include <linux/smp.h>
 
 #include <asm/ftrace.h>
 #include <asm/reg.h>
@@ -80,6 +81,8 @@
 #include <asm/dtl.h>
 #include <asm/plpar_wrappers.h>
 
+#include <trace/events/ipi.h>
+
 #include "book3s.h"
 #include "book3s_hv.h"
 

arch/powerpc/platforms/powernv/subcore.c

@@ -20,6 +20,8 @@
 #include <asm/opal.h>
 #include <asm/smp.h>
 
+#include <trace/events/ipi.h>
+
 #include "subcore.h"
 #include "powernv.h"
 

arch/riscv/kernel/smp.c

@@ -333,8 +333,8 @@ bool smp_crash_stop_failed(void)
 }
 #endif
 
-void smp_send_reschedule(int cpu)
+void arch_smp_send_reschedule(int cpu)
 {
 	send_ipi_single(cpu, IPI_RESCHEDULE);
 }
-EXPORT_SYMBOL_GPL(smp_send_reschedule);
+EXPORT_SYMBOL_GPL(arch_smp_send_reschedule);

arch/s390/kernel/smp.c

@@ -553,7 +553,7 @@ void arch_send_call_function_single_ipi(int cpu)
  * it goes straight through and wastes no time serializing
  * anything. Worst case is that we lose a reschedule ...
  */
-void smp_send_reschedule(int cpu)
+void arch_smp_send_reschedule(int cpu)
 {
 	pcpu_ec_call(pcpu_devices + cpu, ec_schedule);
 }

arch/sh/kernel/smp.c

@@ -256,7 +256,7 @@ void __init smp_cpus_done(unsigned int max_cpus)
 	       (bogosum / (5000/HZ)) % 100);
 }
 
-void smp_send_reschedule(int cpu)
+void arch_smp_send_reschedule(int cpu)
 {
 	mp_ops->send_ipi(cpu, SMP_MSG_RESCHEDULE);
 }

arch/sparc/kernel/smp_32.c

@@ -120,7 +120,7 @@ void cpu_panic(void)
 
 struct linux_prom_registers smp_penguin_ctable = { 0 };
 
-void smp_send_reschedule(int cpu)
+void arch_smp_send_reschedule(int cpu)
 {
 	/*
 	 * CPU model dependent way of implementing IPI generation targeting

arch/sparc/kernel/smp_64.c

@@ -1430,7 +1430,7 @@ static unsigned long send_cpu_poke(int cpu)
 	return hv_err;
 }
 
-void smp_send_reschedule(int cpu)
+void arch_smp_send_reschedule(int cpu)
 {
 	if (cpu == smp_processor_id()) {
 		WARN_ON_ONCE(preemptible());

arch/x86/include/asm/smp.h

@@ -99,7 +99,7 @@ static inline void __noreturn play_dead(void)
 	BUG();
 }
 
-static inline void smp_send_reschedule(int cpu)
+static inline void arch_smp_send_reschedule(int cpu)
 {
 	smp_ops.smp_send_reschedule(cpu);
 }

arch/x86/kvm/svm/svm.c

@@ -27,6 +27,7 @@
 #include <linux/swap.h>
 #include <linux/rwsem.h>
 #include <linux/cc_platform.h>
+#include <linux/smp.h>
 
 #include <asm/apic.h>
 #include <asm/perf_event.h>
@@ -41,6 +42,9 @@
 #include <asm/fpu/api.h>
 
 #include <asm/virtext.h>
+
+#include <trace/events/ipi.h>
+
 #include "trace.h"
 
 #include "svm.h"

arch/x86/kvm/x86.c

@@ -60,7 +60,9 @@
 #include <linux/mem_encrypt.h>
 #include <linux/entry-kvm.h>
 #include <linux/suspend.h>
+#include <linux/smp.h>
 
+#include <trace/events/ipi.h>
 #include <trace/events/kvm.h>
 
 #include <asm/debugreg.h>

arch/xtensa/kernel/smp.c

@@ -391,7 +391,7 @@ void arch_send_call_function_single_ipi(int cpu)
 	send_ipi_message(cpumask_of(cpu), IPI_CALL_FUNC);
 }
 
-void smp_send_reschedule(int cpu)
+void arch_smp_send_reschedule(int cpu)
 {
 	send_ipi_message(cpumask_of(cpu), IPI_RESCHEDULE);
 }

include/linux/smp.h

@@ -125,8 +125,15 @@ extern void smp_send_stop(void);
 /*
  * sends a 'reschedule' event to another CPU:
  */
-extern void smp_send_reschedule(int cpu);
-
+extern void arch_smp_send_reschedule(int cpu);
+/*
+ * scheduler_ipi() is inline so can't be passed as callback reason, but the
+ * callsite IP should be sufficient for root-causing IPIs sent from here.
+ */
+#define smp_send_reschedule(cpu) ({		  \
+	trace_ipi_send_cpu(cpu, _RET_IP_, NULL);  \
+	arch_smp_send_reschedule(cpu);		  \
+})
 
 /*
  * Prepare machine for booting other CPUs.

include/trace/events/ipi.h

@@ -35,6 +35,50 @@ TRACE_EVENT(ipi_raise,
 	TP_printk("target_mask=%s (%s)", __get_bitmask(target_cpus), __entry->reason)
 );
 
+TRACE_EVENT(ipi_send_cpu,
+
+	TP_PROTO(const unsigned int cpu, unsigned long callsite, void *callback),
+
+	TP_ARGS(cpu, callsite, callback),
+
+	TP_STRUCT__entry(
+		__field(unsigned int, cpu)
+		__field(void *, callsite)
+		__field(void *, callback)
+	),
+
+	TP_fast_assign(
+		__entry->cpu = cpu;
+		__entry->callsite = (void *)callsite;
+		__entry->callback = callback;
+	),
+
+	TP_printk("cpu=%u callsite=%pS callback=%pS",
+		  __entry->cpu, __entry->callsite, __entry->callback)
+);
+
+TRACE_EVENT(ipi_send_cpumask,
+
+	TP_PROTO(const struct cpumask *cpumask, unsigned long callsite, void *callback),
+
+	TP_ARGS(cpumask, callsite, callback),
+
+	TP_STRUCT__entry(
+		__cpumask(cpumask)
+		__field(void *, callsite)
+		__field(void *, callback)
+	),
+
+	TP_fast_assign(
+		__assign_cpumask(cpumask, cpumask_bits(cpumask));
+		__entry->callsite = (void *)callsite;
+		__entry->callback = callback;
+	),
+
+	TP_printk("cpumask=%s callsite=%pS callback=%pS",
+		  __get_cpumask(cpumask), __entry->callsite, __entry->callback)
+);
+
 DECLARE_EVENT_CLASS(ipi_handler,
 
 	TP_PROTO(const char *reason),

kernel/irq_work.c

@@ -22,6 +22,8 @@
 #include <asm/processor.h>
 #include <linux/kasan.h>
 
+#include <trace/events/ipi.h>
+
 static DEFINE_PER_CPU(struct llist_head, raised_list);
 static DEFINE_PER_CPU(struct llist_head, lazy_list);
 static DEFINE_PER_CPU(struct task_struct *, irq_workd);
@@ -74,6 +76,14 @@ void __weak arch_irq_work_raise(void)
 	 */
 }
 
+static __always_inline void irq_work_raise(struct irq_work *work)
+{
+	if (trace_ipi_send_cpu_enabled() && arch_irq_work_has_interrupt())
+		trace_ipi_send_cpu(smp_processor_id(), _RET_IP_, work->func);
+
+	arch_irq_work_raise();
+}
+
 /* Enqueue on current CPU, work must already be claimed and preempt disabled */
 static void __irq_work_queue_local(struct irq_work *work)
 {
@@ -99,7 +109,7 @@ static void __irq_work_queue_local(struct irq_work *work)
 
 	/* If the work is "lazy", handle it from next tick if any */
 	if (!lazy_work || tick_nohz_tick_stopped())
-		arch_irq_work_raise();
+		irq_work_raise(work);
 }
 
 /* Enqueue the irq work @work on the current CPU */

kernel/sched/core.c

@@ -80,6 +80,7 @@
 #define CREATE_TRACE_POINTS
 #include <linux/sched/rseq_api.h>
 #include <trace/events/sched.h>
+#include <trace/events/ipi.h>
 #undef CREATE_TRACE_POINTS
 
 #include "sched.h"
@@ -95,6 +96,9 @@
 #include "../../io_uring/io-wq.h"
 #include "../smpboot.h"
 
+EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpu);
+EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpumask);
+
 /*
  * Export tracepoints that act as a bare tracehook (ie: have no trace event
  * associated with them) to allow external modules to probe them.
@@ -3848,14 +3852,20 @@ void sched_ttwu_pending(void *arg)
 	rq_unlock_irqrestore(rq, &rf);
 }
 
-void send_call_function_single_ipi(int cpu)
+/*
+ * Prepare the scene for sending an IPI for a remote smp_call
+ *
+ * Returns true if the caller can proceed with sending the IPI.
+ * Returns false otherwise.
+ */
+bool call_function_single_prep_ipi(int cpu)
 {
-	struct rq *rq = cpu_rq(cpu);
-
-	if (!set_nr_if_polling(rq->idle))
-		arch_send_call_function_single_ipi(cpu);
-	else
+	if (set_nr_if_polling(cpu_rq(cpu)->idle)) {
 		trace_sched_wake_idle_without_ipi(cpu);
+		return false;
+	}
+
+	return true;
 }
 
 /*

kernel/sched/smp.h

@@ -6,7 +6,7 @@
 
 extern void sched_ttwu_pending(void *arg);
 
-extern void send_call_function_single_ipi(int cpu);
+extern bool call_function_single_prep_ipi(int cpu);
 
 #ifdef CONFIG_SMP
 extern void flush_smp_call_function_queue(void);

lib/Kconfig.debug

@@ -1490,6 +1490,15 @@ config CSD_LOCK_WAIT_DEBUG
 	  include the IPI handler function currently executing (if any)
 	  and relevant stack traces.
 
+config CSD_LOCK_WAIT_DEBUG_DEFAULT
+	bool "Default csd_lock_wait() debugging on at boot time"
+	depends on CSD_LOCK_WAIT_DEBUG
+	depends on 64BIT
+	default n
+	help
+	  This option causes the csdlock_debug= kernel boot parameter to
+	  default to 1 (basic debugging) instead of 0 (no debugging).
+
 endmenu # lock debugging
 
 config TRACE_IRQFLAGS

virt/kvm/kvm_main.c

@@ -62,11 +62,14 @@
 #include "kvm_mm.h"
 #include "vfio.h"
 
+#include <trace/events/ipi.h>
+
 #define CREATE_TRACE_POINTS
 #include <trace/events/kvm.h>
 
 #include <linux/kvm_dirty_ring.h>
 
+
 /* Worst case buffer size needed for holding an integer. */
 #define ITOA_MAX_LEN 12