kernel-fxtec-pro1x/arch/x86/kernel/irq.c

366 lines
9.3 KiB
C
Raw Normal View History

/*
* Common interrupt code for 32 and 64 bit
*/
#include <linux/cpu.h>
#include <linux/interrupt.h>
#include <linux/kernel_stat.h>
#include <linux/of.h>
#include <linux/seq_file.h>
#include <linux/smp.h>
#include <linux/ftrace.h>
#include <linux/delay.h>
#include <linux/export.h>
#include <asm/apic.h>
#include <asm/io_apic.h>
#include <asm/irq.h>
#include <asm/idle.h>
#include <asm/mce.h>
#include <asm/hw_irq.h>
trace,x86: Move creation of irq tracepoints from apic.c to irq.c Compiling without CONFIG_X86_LOCAL_APIC set, apic.c will not be compiled, and the irq tracepoints will not be created via the CREATE_TRACE_POINTS macro. When CONFIG_X86_LOCAL_APIC is not set, we get the following build error: LD init/built-in.o arch/x86/built-in.o: In function `trace_x86_platform_ipi_entry': linux-test.git/arch/x86/include/asm/trace/irq_vectors.h:66: undefined reference to `__tracepoint_x86_platform_ipi_entry' arch/x86/built-in.o: In function `trace_x86_platform_ipi_exit': linux-test.git/arch/x86/include/asm/trace/irq_vectors.h:66: undefined reference to `__tracepoint_x86_platform_ipi_exit' arch/x86/built-in.o: In function `trace_irq_work_entry': linux-test.git/arch/x86/include/asm/trace/irq_vectors.h:72: undefined reference to `__tracepoint_irq_work_entry' arch/x86/built-in.o: In function `trace_irq_work_exit': linux-test.git/arch/x86/include/asm/trace/irq_vectors.h:72: undefined reference to `__tracepoint_irq_work_exit' arch/x86/built-in.o:(__jump_table+0x8): undefined reference to `__tracepoint_x86_platform_ipi_entry' arch/x86/built-in.o:(__jump_table+0x14): undefined reference to `__tracepoint_x86_platform_ipi_exit' arch/x86/built-in.o:(__jump_table+0x20): undefined reference to `__tracepoint_irq_work_entry' arch/x86/built-in.o:(__jump_table+0x2c): undefined reference to `__tracepoint_irq_work_exit' make[1]: *** [vmlinux] Error 1 make: *** [sub-make] Error 2 As irq.c is always compiled for x86, it is a more appropriate location to create the irq tracepoints. Cc: Seiji Aguchi <seiji.aguchi@hds.com> Signed-off-by: Steven Rostedt <rostedt@goodmis.org>
2013-06-21 08:29:05 -06:00
#define CREATE_TRACE_POINTS
x86, trace: Add irq vector tracepoints [Purpose of this patch] As Vaibhav explained in the thread below, tracepoints for irq vectors are useful. http://www.spinics.net/lists/mm-commits/msg85707.html <snip> The current interrupt traces from irq_handler_entry and irq_handler_exit provide when an interrupt is handled. They provide good data about when the system has switched to kernel space and how it affects the currently running processes. There are some IRQ vectors which trigger the system into kernel space, which are not handled in generic IRQ handlers. Tracing such events gives us the information about IRQ interaction with other system events. The trace also tells where the system is spending its time. We want to know which cores are handling interrupts and how they are affecting other processes in the system. Also, the trace provides information about when the cores are idle and which interrupts are changing that state. <snip> On the other hand, my usecase is tracing just local timer event and getting a value of instruction pointer. I suggested to add an argument local timer event to get instruction pointer before. But there is another way to get it with external module like systemtap. So, I don't need to add any argument to irq vector tracepoints now. [Patch Description] Vaibhav's patch shared a trace point ,irq_vector_entry/irq_vector_exit, in all events. But there is an above use case to trace specific irq_vector rather than tracing all events. In this case, we are concerned about overhead due to unwanted events. So, add following tracepoints instead of introducing irq_vector_entry/exit. so that we can enable them independently. - local_timer_vector - reschedule_vector - call_function_vector - call_function_single_vector - irq_work_entry_vector - error_apic_vector - thermal_apic_vector - threshold_apic_vector - spurious_apic_vector - x86_platform_ipi_vector Also, introduce a logic switching IDT at enabling/disabling time so that a time penalty makes a zero when tracepoints are disabled. Detailed explanations are as follows. - Create trace irq handlers with entering_irq()/exiting_irq(). - Create a new IDT, trace_idt_table, at boot time by adding a logic to _set_gate(). It is just a copy of original idt table. - Register the new handlers for tracpoints to the new IDT by introducing macros to alloc_intr_gate() called at registering time of irq_vector handlers. - Add checking, whether irq vector tracing is on/off, into load_current_idt(). This has to be done below debug checking for these reasons. - Switching to debug IDT may be kicked while tracing is enabled. - On the other hands, switching to trace IDT is kicked only when debugging is disabled. In addition, the new IDT is created only when CONFIG_TRACING is enabled to avoid being used for other purposes. Signed-off-by: Seiji Aguchi <seiji.aguchi@hds.com> Link: http://lkml.kernel.org/r/51C323ED.5050708@hds.com Signed-off-by: H. Peter Anvin <hpa@linux.intel.com> Cc: Steven Rostedt <rostedt@goodmis.org>
2013-06-20 09:46:53 -06:00
#include <asm/trace/irq_vectors.h>
atomic_t irq_err_count;
/* Function pointer for generic interrupt vector handling */
void (*x86_platform_ipi_callback)(void) = NULL;
/*
* 'what should we do if we get a hw irq event on an illegal vector'.
* each architecture has to answer this themselves.
*/
void ack_bad_irq(unsigned int irq)
{
if (printk_ratelimit())
pr_err("unexpected IRQ trap at vector %02x\n", irq);
/*
* Currently unexpected vectors happen only on SMP and APIC.
* We _must_ ack these because every local APIC has only N
* irq slots per priority level, and a 'hanging, unacked' IRQ
* holds up an irq slot - in excessive cases (when multiple
* unexpected vectors occur) that might lock up the APIC
* completely.
* But only ack when the APIC is enabled -AK
*/
ack_APIC_irq();
}
#define irq_stats(x) (&per_cpu(irq_stat, x))
/*
* /proc/interrupts printing for arch specific interrupts
*/
int arch_show_interrupts(struct seq_file *p, int prec)
{
int j;
seq_printf(p, "%*s: ", prec, "NMI");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->__nmi_count);
seq_printf(p, " Non-maskable interrupts\n");
#ifdef CONFIG_X86_LOCAL_APIC
seq_printf(p, "%*s: ", prec, "LOC");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->apic_timer_irqs);
seq_printf(p, " Local timer interrupts\n");
seq_printf(p, "%*s: ", prec, "SPU");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_spurious_count);
seq_printf(p, " Spurious interrupts\n");
seq_printf(p, "%*s: ", prec, "PMI");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->apic_perf_irqs);
seq_printf(p, " Performance monitoring interrupts\n");
seq_printf(p, "%*s: ", prec, "IWI");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->apic_irq_work_irqs);
seq_printf(p, " IRQ work interrupts\n");
seq_printf(p, "%*s: ", prec, "RTR");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->icr_read_retry_count);
seq_printf(p, " APIC ICR read retries\n");
#endif
if (x86_platform_ipi_callback) {
seq_printf(p, "%*s: ", prec, "PLT");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->x86_platform_ipis);
seq_printf(p, " Platform interrupts\n");
}
#ifdef CONFIG_SMP
seq_printf(p, "%*s: ", prec, "RES");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_resched_count);
seq_printf(p, " Rescheduling interrupts\n");
seq_printf(p, "%*s: ", prec, "CAL");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_call_count -
irq_stats(j)->irq_tlb_count);
seq_printf(p, " Function call interrupts\n");
seq_printf(p, "%*s: ", prec, "TLB");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_tlb_count);
seq_printf(p, " TLB shootdowns\n");
#endif
#ifdef CONFIG_X86_THERMAL_VECTOR
seq_printf(p, "%*s: ", prec, "TRM");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_thermal_count);
seq_printf(p, " Thermal event interrupts\n");
#endif
#ifdef CONFIG_X86_MCE_THRESHOLD
seq_printf(p, "%*s: ", prec, "THR");
for_each_online_cpu(j)
seq_printf(p, "%10u ", irq_stats(j)->irq_threshold_count);
seq_printf(p, " Threshold APIC interrupts\n");
#endif
#ifdef CONFIG_X86_MCE
seq_printf(p, "%*s: ", prec, "MCE");
for_each_online_cpu(j)
seq_printf(p, "%10u ", per_cpu(mce_exception_count, j));
seq_printf(p, " Machine check exceptions\n");
seq_printf(p, "%*s: ", prec, "MCP");
for_each_online_cpu(j)
seq_printf(p, "%10u ", per_cpu(mce_poll_count, j));
seq_printf(p, " Machine check polls\n");
#endif
seq_printf(p, "%*s: %10u\n", prec, "ERR", atomic_read(&irq_err_count));
#if defined(CONFIG_X86_IO_APIC)
seq_printf(p, "%*s: %10u\n", prec, "MIS", atomic_read(&irq_mis_count));
#endif
return 0;
}
/*
* /proc/stat helpers
*/
u64 arch_irq_stat_cpu(unsigned int cpu)
{
u64 sum = irq_stats(cpu)->__nmi_count;
#ifdef CONFIG_X86_LOCAL_APIC
sum += irq_stats(cpu)->apic_timer_irqs;
sum += irq_stats(cpu)->irq_spurious_count;
sum += irq_stats(cpu)->apic_perf_irqs;
sum += irq_stats(cpu)->apic_irq_work_irqs;
sum += irq_stats(cpu)->icr_read_retry_count;
#endif
if (x86_platform_ipi_callback)
sum += irq_stats(cpu)->x86_platform_ipis;
#ifdef CONFIG_SMP
sum += irq_stats(cpu)->irq_resched_count;
sum += irq_stats(cpu)->irq_call_count;
#endif
#ifdef CONFIG_X86_THERMAL_VECTOR
sum += irq_stats(cpu)->irq_thermal_count;
#endif
#ifdef CONFIG_X86_MCE_THRESHOLD
sum += irq_stats(cpu)->irq_threshold_count;
#endif
#ifdef CONFIG_X86_MCE
sum += per_cpu(mce_exception_count, cpu);
sum += per_cpu(mce_poll_count, cpu);
#endif
return sum;
}
u64 arch_irq_stat(void)
{
u64 sum = atomic_read(&irq_err_count);
return sum;
}
/*
* do_IRQ handles all normal device IRQ's (the special
* SMP cross-CPU interrupts have their own specific
* handlers).
*/
unsigned int __irq_entry do_IRQ(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
/* high bit used in ret_from_ code */
unsigned vector = ~regs->orig_ax;
unsigned irq;
irq_enter();
x86: Call idle notifier after irq_enter() Interrupts notify the idle exit state before calling irq_enter(). But the notifier code calls rcu_read_lock() and this is not allowed while rcu is in an extended quiescent state. We need to wait for irq_enter() -> rcu_idle_exit() to be called before doing so otherwise this results in a grumpy RCU: [ 0.099991] WARNING: at include/linux/rcupdate.h:194 __atomic_notifier_call_chain+0xd2/0x110() [ 0.099991] Hardware name: AMD690VM-FMH [ 0.099991] Modules linked in: [ 0.099991] Pid: 0, comm: swapper Not tainted 3.0.0-rc6+ #255 [ 0.099991] Call Trace: [ 0.099991] <IRQ> [<ffffffff81051c8a>] warn_slowpath_common+0x7a/0xb0 [ 0.099991] [<ffffffff81051cd5>] warn_slowpath_null+0x15/0x20 [ 0.099991] [<ffffffff817d6fa2>] __atomic_notifier_call_chain+0xd2/0x110 [ 0.099991] [<ffffffff817d6ff1>] atomic_notifier_call_chain+0x11/0x20 [ 0.099991] [<ffffffff81001873>] exit_idle+0x43/0x50 [ 0.099991] [<ffffffff81020439>] smp_apic_timer_interrupt+0x39/0xa0 [ 0.099991] [<ffffffff817da253>] apic_timer_interrupt+0x13/0x20 [ 0.099991] <EOI> [<ffffffff8100ae67>] ? default_idle+0xa7/0x350 [ 0.099991] [<ffffffff8100ae65>] ? default_idle+0xa5/0x350 [ 0.099991] [<ffffffff8100b19b>] amd_e400_idle+0x8b/0x110 [ 0.099991] [<ffffffff810cb01f>] ? rcu_enter_nohz+0x8f/0x160 [ 0.099991] [<ffffffff810019a0>] cpu_idle+0xb0/0x110 [ 0.099991] [<ffffffff817a7505>] rest_init+0xe5/0x140 [ 0.099991] [<ffffffff817a7468>] ? rest_init+0x48/0x140 [ 0.099991] [<ffffffff81cc5ca3>] start_kernel+0x3d1/0x3dc [ 0.099991] [<ffffffff81cc5321>] x86_64_start_reservations+0x131/0x135 [ 0.099991] [<ffffffff81cc5412>] x86_64_start_kernel+0xed/0xf4 Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com> Cc: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: H. Peter Anvin <hpa@zytor.com> Cc: Andy Henroid <andrew.d.henroid@intel.com> Signed-off-by: Paul E. McKenney <paulmck@linux.vnet.ibm.com> Reviewed-by: Josh Triplett <josh@joshtriplett.org>
2011-10-07 10:22:09 -06:00
exit_idle();
irq = __this_cpu_read(vector_irq[vector]);
if (!handle_irq(irq, regs)) {
ack_APIC_irq();
if (printk_ratelimit())
pr_emerg("%s: %d.%d No irq handler for vector (irq %d)\n",
__func__, smp_processor_id(), vector, irq);
}
irq_exit();
set_irq_regs(old_regs);
return 1;
}
/*
* Handler for X86_PLATFORM_IPI_VECTOR.
*/
x86, trace: Introduce entering/exiting_irq() When implementing tracepoints in interrupt handers, if the tracepoints are simply added in the performance sensitive path of interrupt handers, it may cause potential performance problem due to the time penalty. To solve the problem, an idea is to prepare non-trace/trace irq handers and switch their IDTs at the enabling/disabling time. So, let's introduce entering_irq()/exiting_irq() for pre/post- processing of each irq handler. A way to use them is as follows. Non-trace irq handler: smp_irq_handler() { entering_irq(); /* pre-processing of this handler */ __smp_irq_handler(); /* * common logic between non-trace and trace handlers * in a vector. */ exiting_irq(); /* post-processing of this handler */ } Trace irq_handler: smp_trace_irq_handler() { entering_irq(); /* pre-processing of this handler */ trace_irq_entry(); /* tracepoint for irq entry */ __smp_irq_handler(); /* * common logic between non-trace and trace handlers * in a vector. */ trace_irq_exit(); /* tracepoint for irq exit */ exiting_irq(); /* post-processing of this handler */ } If tracepoints can place outside entering_irq()/exiting_irq() as follows, it looks cleaner. smp_trace_irq_handler() { trace_irq_entry(); smp_irq_handler(); trace_irq_exit(); } But it doesn't work. The problem is with irq_enter/exit() being called. They must be called before trace_irq_enter/exit(), because of the rcu_irq_enter() must be called before any tracepoints are used, as tracepoints use rcu to synchronize. As a possible alternative, we may be able to call irq_enter() first as follows if irq_enter() can nest. smp_trace_irq_hander() { irq_entry(); trace_irq_entry(); smp_irq_handler(); trace_irq_exit(); irq_exit(); } But it doesn't work, either. If irq_enter() is nested, it may have a time penalty because it has to check if it was already called or not. The time penalty is not desired in performance sensitive paths even if it is tiny. Signed-off-by: Seiji Aguchi <seiji.aguchi@hds.com> Link: http://lkml.kernel.org/r/51C3238D.9040706@hds.com Signed-off-by: H. Peter Anvin <hpa@linux.intel.com> Cc: Steven Rostedt <rostedt@goodmis.org>
2013-06-20 09:45:17 -06:00
void __smp_x86_platform_ipi(void)
{
inc_irq_stat(x86_platform_ipis);
if (x86_platform_ipi_callback)
x86_platform_ipi_callback();
x86, trace: Introduce entering/exiting_irq() When implementing tracepoints in interrupt handers, if the tracepoints are simply added in the performance sensitive path of interrupt handers, it may cause potential performance problem due to the time penalty. To solve the problem, an idea is to prepare non-trace/trace irq handers and switch their IDTs at the enabling/disabling time. So, let's introduce entering_irq()/exiting_irq() for pre/post- processing of each irq handler. A way to use them is as follows. Non-trace irq handler: smp_irq_handler() { entering_irq(); /* pre-processing of this handler */ __smp_irq_handler(); /* * common logic between non-trace and trace handlers * in a vector. */ exiting_irq(); /* post-processing of this handler */ } Trace irq_handler: smp_trace_irq_handler() { entering_irq(); /* pre-processing of this handler */ trace_irq_entry(); /* tracepoint for irq entry */ __smp_irq_handler(); /* * common logic between non-trace and trace handlers * in a vector. */ trace_irq_exit(); /* tracepoint for irq exit */ exiting_irq(); /* post-processing of this handler */ } If tracepoints can place outside entering_irq()/exiting_irq() as follows, it looks cleaner. smp_trace_irq_handler() { trace_irq_entry(); smp_irq_handler(); trace_irq_exit(); } But it doesn't work. The problem is with irq_enter/exit() being called. They must be called before trace_irq_enter/exit(), because of the rcu_irq_enter() must be called before any tracepoints are used, as tracepoints use rcu to synchronize. As a possible alternative, we may be able to call irq_enter() first as follows if irq_enter() can nest. smp_trace_irq_hander() { irq_entry(); trace_irq_entry(); smp_irq_handler(); trace_irq_exit(); irq_exit(); } But it doesn't work, either. If irq_enter() is nested, it may have a time penalty because it has to check if it was already called or not. The time penalty is not desired in performance sensitive paths even if it is tiny. Signed-off-by: Seiji Aguchi <seiji.aguchi@hds.com> Link: http://lkml.kernel.org/r/51C3238D.9040706@hds.com Signed-off-by: H. Peter Anvin <hpa@linux.intel.com> Cc: Steven Rostedt <rostedt@goodmis.org>
2013-06-20 09:45:17 -06:00
}
x86, trace: Introduce entering/exiting_irq() When implementing tracepoints in interrupt handers, if the tracepoints are simply added in the performance sensitive path of interrupt handers, it may cause potential performance problem due to the time penalty. To solve the problem, an idea is to prepare non-trace/trace irq handers and switch their IDTs at the enabling/disabling time. So, let's introduce entering_irq()/exiting_irq() for pre/post- processing of each irq handler. A way to use them is as follows. Non-trace irq handler: smp_irq_handler() { entering_irq(); /* pre-processing of this handler */ __smp_irq_handler(); /* * common logic between non-trace and trace handlers * in a vector. */ exiting_irq(); /* post-processing of this handler */ } Trace irq_handler: smp_trace_irq_handler() { entering_irq(); /* pre-processing of this handler */ trace_irq_entry(); /* tracepoint for irq entry */ __smp_irq_handler(); /* * common logic between non-trace and trace handlers * in a vector. */ trace_irq_exit(); /* tracepoint for irq exit */ exiting_irq(); /* post-processing of this handler */ } If tracepoints can place outside entering_irq()/exiting_irq() as follows, it looks cleaner. smp_trace_irq_handler() { trace_irq_entry(); smp_irq_handler(); trace_irq_exit(); } But it doesn't work. The problem is with irq_enter/exit() being called. They must be called before trace_irq_enter/exit(), because of the rcu_irq_enter() must be called before any tracepoints are used, as tracepoints use rcu to synchronize. As a possible alternative, we may be able to call irq_enter() first as follows if irq_enter() can nest. smp_trace_irq_hander() { irq_entry(); trace_irq_entry(); smp_irq_handler(); trace_irq_exit(); irq_exit(); } But it doesn't work, either. If irq_enter() is nested, it may have a time penalty because it has to check if it was already called or not. The time penalty is not desired in performance sensitive paths even if it is tiny. Signed-off-by: Seiji Aguchi <seiji.aguchi@hds.com> Link: http://lkml.kernel.org/r/51C3238D.9040706@hds.com Signed-off-by: H. Peter Anvin <hpa@linux.intel.com> Cc: Steven Rostedt <rostedt@goodmis.org>
2013-06-20 09:45:17 -06:00
void smp_x86_platform_ipi(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
x86, trace: Introduce entering/exiting_irq() When implementing tracepoints in interrupt handers, if the tracepoints are simply added in the performance sensitive path of interrupt handers, it may cause potential performance problem due to the time penalty. To solve the problem, an idea is to prepare non-trace/trace irq handers and switch their IDTs at the enabling/disabling time. So, let's introduce entering_irq()/exiting_irq() for pre/post- processing of each irq handler. A way to use them is as follows. Non-trace irq handler: smp_irq_handler() { entering_irq(); /* pre-processing of this handler */ __smp_irq_handler(); /* * common logic between non-trace and trace handlers * in a vector. */ exiting_irq(); /* post-processing of this handler */ } Trace irq_handler: smp_trace_irq_handler() { entering_irq(); /* pre-processing of this handler */ trace_irq_entry(); /* tracepoint for irq entry */ __smp_irq_handler(); /* * common logic between non-trace and trace handlers * in a vector. */ trace_irq_exit(); /* tracepoint for irq exit */ exiting_irq(); /* post-processing of this handler */ } If tracepoints can place outside entering_irq()/exiting_irq() as follows, it looks cleaner. smp_trace_irq_handler() { trace_irq_entry(); smp_irq_handler(); trace_irq_exit(); } But it doesn't work. The problem is with irq_enter/exit() being called. They must be called before trace_irq_enter/exit(), because of the rcu_irq_enter() must be called before any tracepoints are used, as tracepoints use rcu to synchronize. As a possible alternative, we may be able to call irq_enter() first as follows if irq_enter() can nest. smp_trace_irq_hander() { irq_entry(); trace_irq_entry(); smp_irq_handler(); trace_irq_exit(); irq_exit(); } But it doesn't work, either. If irq_enter() is nested, it may have a time penalty because it has to check if it was already called or not. The time penalty is not desired in performance sensitive paths even if it is tiny. Signed-off-by: Seiji Aguchi <seiji.aguchi@hds.com> Link: http://lkml.kernel.org/r/51C3238D.9040706@hds.com Signed-off-by: H. Peter Anvin <hpa@linux.intel.com> Cc: Steven Rostedt <rostedt@goodmis.org>
2013-06-20 09:45:17 -06:00
entering_ack_irq();
__smp_x86_platform_ipi();
exiting_irq();
set_irq_regs(old_regs);
}
#ifdef CONFIG_HAVE_KVM
/*
* Handler for POSTED_INTERRUPT_VECTOR.
*/
void smp_kvm_posted_intr_ipi(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
ack_APIC_irq();
irq_enter();
exit_idle();
inc_irq_stat(kvm_posted_intr_ipis);
irq_exit();
set_irq_regs(old_regs);
}
#endif
x86, trace: Add irq vector tracepoints [Purpose of this patch] As Vaibhav explained in the thread below, tracepoints for irq vectors are useful. http://www.spinics.net/lists/mm-commits/msg85707.html <snip> The current interrupt traces from irq_handler_entry and irq_handler_exit provide when an interrupt is handled. They provide good data about when the system has switched to kernel space and how it affects the currently running processes. There are some IRQ vectors which trigger the system into kernel space, which are not handled in generic IRQ handlers. Tracing such events gives us the information about IRQ interaction with other system events. The trace also tells where the system is spending its time. We want to know which cores are handling interrupts and how they are affecting other processes in the system. Also, the trace provides information about when the cores are idle and which interrupts are changing that state. <snip> On the other hand, my usecase is tracing just local timer event and getting a value of instruction pointer. I suggested to add an argument local timer event to get instruction pointer before. But there is another way to get it with external module like systemtap. So, I don't need to add any argument to irq vector tracepoints now. [Patch Description] Vaibhav's patch shared a trace point ,irq_vector_entry/irq_vector_exit, in all events. But there is an above use case to trace specific irq_vector rather than tracing all events. In this case, we are concerned about overhead due to unwanted events. So, add following tracepoints instead of introducing irq_vector_entry/exit. so that we can enable them independently. - local_timer_vector - reschedule_vector - call_function_vector - call_function_single_vector - irq_work_entry_vector - error_apic_vector - thermal_apic_vector - threshold_apic_vector - spurious_apic_vector - x86_platform_ipi_vector Also, introduce a logic switching IDT at enabling/disabling time so that a time penalty makes a zero when tracepoints are disabled. Detailed explanations are as follows. - Create trace irq handlers with entering_irq()/exiting_irq(). - Create a new IDT, trace_idt_table, at boot time by adding a logic to _set_gate(). It is just a copy of original idt table. - Register the new handlers for tracpoints to the new IDT by introducing macros to alloc_intr_gate() called at registering time of irq_vector handlers. - Add checking, whether irq vector tracing is on/off, into load_current_idt(). This has to be done below debug checking for these reasons. - Switching to debug IDT may be kicked while tracing is enabled. - On the other hands, switching to trace IDT is kicked only when debugging is disabled. In addition, the new IDT is created only when CONFIG_TRACING is enabled to avoid being used for other purposes. Signed-off-by: Seiji Aguchi <seiji.aguchi@hds.com> Link: http://lkml.kernel.org/r/51C323ED.5050708@hds.com Signed-off-by: H. Peter Anvin <hpa@linux.intel.com> Cc: Steven Rostedt <rostedt@goodmis.org>
2013-06-20 09:46:53 -06:00
void smp_trace_x86_platform_ipi(struct pt_regs *regs)
{
struct pt_regs *old_regs = set_irq_regs(regs);
entering_ack_irq();
trace_x86_platform_ipi_entry(X86_PLATFORM_IPI_VECTOR);
__smp_x86_platform_ipi();
trace_x86_platform_ipi_exit(X86_PLATFORM_IPI_VECTOR);
exiting_irq();
set_irq_regs(old_regs);
}
EXPORT_SYMBOL_GPL(vector_used_by_percpu_irq);
#ifdef CONFIG_HOTPLUG_CPU
/* A cpu has been removed from cpu_online_mask. Reset irq affinities. */
void fixup_irqs(void)
{
unsigned int irq, vector;
static int warned;
struct irq_desc *desc;
struct irq_data *data;
struct irq_chip *chip;
for_each_irq_desc(irq, desc) {
int break_affinity = 0;
int set_affinity = 1;
const struct cpumask *affinity;
if (!desc)
continue;
if (irq == 2)
continue;
/* interrupt's are disabled at this point */
raw_spin_lock(&desc->lock);
data = irq_desc_get_irq_data(desc);
affinity = data->affinity;
if (!irq_has_action(irq) || irqd_is_per_cpu(data) ||
cpumask_subset(affinity, cpu_online_mask)) {
raw_spin_unlock(&desc->lock);
continue;
}
/*
* Complete the irq move. This cpu is going down and for
* non intr-remapping case, we can't wait till this interrupt
* arrives at this cpu before completing the irq move.
*/
irq_force_complete_move(irq);
if (cpumask_any_and(affinity, cpu_online_mask) >= nr_cpu_ids) {
break_affinity = 1;
affinity = cpu_online_mask;
}
chip = irq_data_get_irq_chip(data);
if (!irqd_can_move_in_process_context(data) && chip->irq_mask)
chip->irq_mask(data);
if (chip->irq_set_affinity)
chip->irq_set_affinity(data, affinity, true);
else if (!(warned++))
set_affinity = 0;
/*
* We unmask if the irq was not marked masked by the
* core code. That respects the lazy irq disable
* behaviour.
*/
if (!irqd_can_move_in_process_context(data) &&
!irqd_irq_masked(data) && chip->irq_unmask)
chip->irq_unmask(data);
raw_spin_unlock(&desc->lock);
if (break_affinity && set_affinity)
pr_notice("Broke affinity for irq %i\n", irq);
else if (!set_affinity)
pr_notice("Cannot set affinity for irq %i\n", irq);
}
/*
* We can remove mdelay() and then send spuriuous interrupts to
* new cpu targets for all the irqs that were handled previously by
* this cpu. While it works, I have seen spurious interrupt messages
* (nothing wrong but still...).
*
* So for now, retain mdelay(1) and check the IRR and then send those
* interrupts to new targets as this cpu is already offlined...
*/
mdelay(1);
for (vector = FIRST_EXTERNAL_VECTOR; vector < NR_VECTORS; vector++) {
unsigned int irr;
if (__this_cpu_read(vector_irq[vector]) < 0)
continue;
irr = apic_read(APIC_IRR + (vector / 32 * 0x10));
if (irr & (1 << (vector % 32))) {
irq = __this_cpu_read(vector_irq[vector]);
desc = irq_to_desc(irq);
data = irq_desc_get_irq_data(desc);
chip = irq_data_get_irq_chip(data);
raw_spin_lock(&desc->lock);
if (chip->irq_retrigger)
chip->irq_retrigger(data);
raw_spin_unlock(&desc->lock);
}
__this_cpu_write(vector_irq[vector], -1);
}
}
#endif