treewide: Trace IPIs sent via smp_send_reschedule()

To be able to trace invocations of smp_send_reschedule(), rename the
arch-specific definitions of it to arch_smp_send_reschedule() and wrap it
into an smp_send_reschedule() that contains a tracepoint.

Changes to include the declaration of the tracepoint were driven by the
following coccinelle script:

  @func_use@
  @@
  smp_send_reschedule(...);

  @include@
  @@
  #include <trace/events/ipi.h>

  @no_include depends on func_use && !include@
  @@
    #include <...>
  +
  + #include <trace/events/ipi.h>

[csky bits]
[riscv bits]
Signed-off-by: Valentin Schneider <vschneid@redhat.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Guo Ren <guoren@kernel.org>
Acked-by: Palmer Dabbelt <palmer@rivosinc.com>
Link: https://lore.kernel.org/r/20230307143558.294354-6-vschneid@redhat.com

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

@@ -746,7 +746,7 @@ 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

@@ -976,7 +976,7 @@ 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/mips/kernel/rtlx-cmp.c

@@ -17,6 +17,8 @@
 #include <asm/vpe.h>
 #include <asm/rtlx.h>
 
+#include <trace/events/ipi.h>
+
 static int major;
 
 static void rtlx_interrupt(void)

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

@@ -328,8 +328,8 @@ 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

@@ -98,7 +98,7 @@ static inline void play_dead(void)
 	smp_ops.play_dead();
 }
 
-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

@@ -389,7 +389,7 @@ 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_cpumask(cpumask_of(cpu), _RET_IP_, NULL);  \
+	arch_smp_send_reschedule(cpu);				  \
+})
 
 /*
  * Prepare machine for booting other CPUs.

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