sched/idle: Fix arch_cpu_idle() vs tracing

We call arch_cpu_idle() with RCU disabled, but then use
local_irq_{en,dis}able(), which invokes tracing, which relies on RCU.

Switch all arch_cpu_idle() implementations to use
raw_local_irq_{en,dis}able() and carefully manage the
lockdep,rcu,tracing state like we do in entry.

(XXX: we really should change arch_cpu_idle() to not return with
interrupts enabled)

Reported-by: Sven Schnelle <svens@linux.ibm.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: Mark Rutland <mark.rutland@arm.com>
Tested-by: Mark Rutland <mark.rutland@arm.com>
Link: https://lkml.kernel.org/r/20201120114925.594122626@infradead.org

diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index 7462a7911002451e5fffb0bd927b08f31e5ccb92..4c7b0414a3ff3b2437ab27ece6bbb9b04f9eb31d 100644 (file)
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -57,7 +57,7 @@ EXPORT_SYMBOL(pm_power_off);
 void arch_cpu_idle(void)
 {
        wtint(0);
-       local_irq_enable();
+       raw_local_irq_enable();
 }
 
 void arch_cpu_idle_dead(void)

diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 8e6ace03e960bef54610ebf653bc6c15d91ef903..9f199b1e838391a71f9018e1763867f597f5ad85 100644 (file)
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -71,7 +71,7 @@ void arch_cpu_idle(void)
                arm_pm_idle();
        else
                cpu_do_idle();
-       local_irq_enable();
+       raw_local_irq_enable();
 }
 
 void arch_cpu_idle_prepare(void)

diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index 4784011cecac976f42725a8a22bfa1c5af678907..9ebe02574127205e5997e704bf6f035b3ea3ef50 100644 (file)
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -126,7 +126,7 @@ void arch_cpu_idle(void)
         * tricks
         */
        cpu_do_idle();
-       local_irq_enable();
+       raw_local_irq_enable();
 }
 
 #ifdef CONFIG_HOTPLUG_CPU

diff --git a/arch/csky/kernel/process.c b/arch/csky/kernel/process.c
index f730869e21eed4829e5f5e90c96f64f1bbc95b68..69af6bc87e6473d2c0c868cf364893e3593f8adf 100644 (file)
--- a/arch/csky/kernel/process.c
+++ b/arch/csky/kernel/process.c
@@ -102,6 +102,6 @@ void arch_cpu_idle(void)
 #ifdef CONFIG_CPU_PM_STOP
        asm volatile("stop\n");
 #endif
-       local_irq_enable();
+       raw_local_irq_enable();
 }
 #endif

diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c
index aea0a40b77a9b4153afbffec789bac2750a4db94..bc1364db58feb01e82c1fd407dea4ee0a8611944 100644 (file)
--- a/arch/h8300/kernel/process.c
+++ b/arch/h8300/kernel/process.c
@@ -57,7 +57,7 @@ asmlinkage void ret_from_kernel_thread(void);
  */
 void arch_cpu_idle(void)
 {
-       local_irq_enable();
+       raw_local_irq_enable();
        __asm__("sleep");
 }
 

diff --git a/arch/hexagon/kernel/process.c b/arch/hexagon/kernel/process.c
index 5a0a95d93ddb7d03cc5d168ded46b3886c37a13d..67767c5ed98c3a14ab4813614416ca3f731fc96a 100644 (file)
--- a/arch/hexagon/kernel/process.c
+++ b/arch/hexagon/kernel/process.c
@@ -44,7 +44,7 @@ void arch_cpu_idle(void)
 {
        __vmwait();
        /*  interrupts wake us up, but irqs are still disabled */
-       local_irq_enable();
+       raw_local_irq_enable();
 }
 
 /*

diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index 6b61a703bcf55b35801d13083cf512db265651e8..c9ff8796b5097e0498256482f10cb96b10b1d802 100644 (file)
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -239,7 +239,7 @@ void arch_cpu_idle(void)
        if (mark_idle)
                (*mark_idle)(1);
 
-       safe_halt();
+       raw_safe_halt();
 
        if (mark_idle)
                (*mark_idle)(0);

diff --git a/arch/microblaze/kernel/process.c b/arch/microblaze/kernel/process.c
index a9e46e525cd0ad4a3c0495da84090911afceb4b3..f99860771ff4854f13b1c3832edb53f1fd61ac1c 100644 (file)
--- a/arch/microblaze/kernel/process.c
+++ b/arch/microblaze/kernel/process.c
@@ -149,5 +149,5 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpregs)
 
 void arch_cpu_idle(void)
 {
-       local_irq_enable();
+       raw_local_irq_enable();
 }

diff --git a/arch/mips/kernel/idle.c b/arch/mips/kernel/idle.c
index 5bc3b04693c7d4446a19a95a498b625f7701da04..18e69ebf5691dd58c2d3a52f8e33525576844404 100644 (file)
--- a/arch/mips/kernel/idle.c
+++ b/arch/mips/kernel/idle.c
@@ -33,19 +33,19 @@ static void __cpuidle r3081_wait(void)
 {
        unsigned long cfg = read_c0_conf();
        write_c0_conf(cfg | R30XX_CONF_HALT);
-       local_irq_enable();
+       raw_local_irq_enable();
 }
 
 static void __cpuidle r39xx_wait(void)
 {
        if (!need_resched())
                write_c0_conf(read_c0_conf() | TX39_CONF_HALT);
-       local_irq_enable();
+       raw_local_irq_enable();
 }
 
 void __cpuidle r4k_wait(void)
 {
-       local_irq_enable();
+       raw_local_irq_enable();
        __r4k_wait();
 }
 
@@ -64,7 +64,7 @@ void __cpuidle r4k_wait_irqoff(void)
                "       .set    arch=r4000      \n"
                "       wait                    \n"
                "       .set    pop             \n");
-       local_irq_enable();
+       raw_local_irq_enable();
 }
 
 /*
@@ -84,7 +84,7 @@ static void __cpuidle rm7k_wait_irqoff(void)
                "       wait                                            \n"
                "       mtc0    $1, $12         # stalls until W stage  \n"
                "       .set    pop                                     \n");
-       local_irq_enable();
+       raw_local_irq_enable();
 }
 
 /*
@@ -257,7 +257,7 @@ void arch_cpu_idle(void)
        if (cpu_wait)
                cpu_wait();
        else
-               local_irq_enable();
+               raw_local_irq_enable();
 }
 
 #ifdef CONFIG_CPU_IDLE

diff --git a/arch/nios2/kernel/process.c b/arch/nios2/kernel/process.c
index 4ffe857e6adad401d1d5a5f2063755af37f43b2e..50b4eb19a6cc9962198ddbe12e1ba02bf2324d4b 100644 (file)
--- a/arch/nios2/kernel/process.c
+++ b/arch/nios2/kernel/process.c
@@ -33,7 +33,7 @@ EXPORT_SYMBOL(pm_power_off);
 
 void arch_cpu_idle(void)
 {
-       local_irq_enable();
+       raw_local_irq_enable();
 }
 
 /*

diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c
index 0ff391f00334c63bef8851b444985cbfa7c1848d..3c98728cce2491c80e586945760b4603e1714c71 100644 (file)
--- a/arch/openrisc/kernel/process.c
+++ b/arch/openrisc/kernel/process.c
@@ -79,7 +79,7 @@ void machine_power_off(void)
  */
 void arch_cpu_idle(void)
 {
-       local_irq_enable();
+       raw_local_irq_enable();
        if (mfspr(SPR_UPR) & SPR_UPR_PMP)
                mtspr(SPR_PMR, mfspr(SPR_PMR) | SPR_PMR_DME);
 }

diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index f196d96e2f9f55f2739b4e518b1daddb24e6d701..a92a23d6acd931c2fb047a898b3c6eef9d488e20 100644 (file)
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -169,7 +169,7 @@ void __cpuidle arch_cpu_idle_dead(void)
 
 void __cpuidle arch_cpu_idle(void)
 {
-       local_irq_enable();
+       raw_local_irq_enable();
 
        /* nop on real hardware, qemu will idle sleep. */
        asm volatile("or %%r10,%%r10,%%r10\n":::);

diff --git a/arch/powerpc/kernel/idle.c b/arch/powerpc/kernel/idle.c
index ae0e2632393d867bf866b1a58627fee691124ad7..1f835539fda420d7f6d0005a7da502da7d42c473 100644 (file)
--- a/arch/powerpc/kernel/idle.c
+++ b/arch/powerpc/kernel/idle.c
@@ -52,9 +52,9 @@ void arch_cpu_idle(void)
                 * interrupts enabled, some don't.
                 */
                if (irqs_disabled())
-                       local_irq_enable();
+                       raw_local_irq_enable();
        } else {
-               local_irq_enable();
+               raw_local_irq_enable();
                /*
                 * Go into low thread priority and possibly
                 * low power mode.

diff --git a/arch/riscv/kernel/process.c b/arch/riscv/kernel/process.c
index 19225ec65db62f608f14493009410711a99b2783..dd5f985b1f40e0418f4bdac872819275a0766cd0 100644 (file)
--- a/arch/riscv/kernel/process.c
+++ b/arch/riscv/kernel/process.c
@@ -36,7 +36,7 @@ extern asmlinkage void ret_from_kernel_thread(void);
 void arch_cpu_idle(void)
 {
        wait_for_interrupt();
-       local_irq_enable();
+       raw_local_irq_enable();
 }
 
 void show_regs(struct pt_regs *regs)

diff --git a/arch/s390/kernel/idle.c b/arch/s390/kernel/idle.c
index f7f1e64e0d980f6e36bd1621d7ed01b2393c1331..2b85096964f8423e232c3fe016a435468d9d9461 100644 (file)
--- a/arch/s390/kernel/idle.c
+++ b/arch/s390/kernel/idle.c
@@ -33,10 +33,10 @@ void enabled_wait(void)
                PSW_MASK_IO | PSW_MASK_EXT | PSW_MASK_MCHECK;
        clear_cpu_flag(CIF_NOHZ_DELAY);
 
-       local_irq_save(flags);
+       raw_local_irq_save(flags);
        /* Call the assembler magic in entry.S */
        psw_idle(idle, psw_mask);
-       local_irq_restore(flags);
+       raw_local_irq_restore(flags);
 
        /* Account time spent with enabled wait psw loaded as idle time. */
        raw_write_seqcount_begin(&idle->seqcount);
@@ -123,7 +123,7 @@ void arch_cpu_idle_enter(void)
 void arch_cpu_idle(void)
 {
        enabled_wait();
-       local_irq_enable();
+       raw_local_irq_enable();
 }
 
 void arch_cpu_idle_exit(void)

diff --git a/arch/sh/kernel/idle.c b/arch/sh/kernel/idle.c
index 0dc0f52f9bb8d3119887dd2fc8b08eaf685ec417..f59814983bd59ffcf5be94d45124f6f5c34399d3 100644 (file)
--- a/arch/sh/kernel/idle.c
+++ b/arch/sh/kernel/idle.c
@@ -22,7 +22,7 @@ static void (*sh_idle)(void);
 void default_idle(void)
 {
        set_bl_bit();
-       local_irq_enable();
+       raw_local_irq_enable();
        /* Isn't this racy ? */
        cpu_sleep();
        clear_bl_bit();

diff --git a/arch/sparc/kernel/leon_pmc.c b/arch/sparc/kernel/leon_pmc.c
index 065e2d4b729084c0d4c50cf0bfdb2b0d51c87df4..396f46bca52eb67a968e02732e2f350a0afd6218 100644 (file)
--- a/arch/sparc/kernel/leon_pmc.c
+++ b/arch/sparc/kernel/leon_pmc.c
@@ -50,7 +50,7 @@ static void pmc_leon_idle_fixup(void)
        register unsigned int address = (unsigned int)leon3_irqctrl_regs;
 
        /* Interrupts need to be enabled to not hang the CPU */
-       local_irq_enable();
+       raw_local_irq_enable();
 
        __asm__ __volatile__ (
                "wr     %%g0, %%asr19\n"
@@ -66,7 +66,7 @@ static void pmc_leon_idle_fixup(void)
 static void pmc_leon_idle(void)
 {
        /* Interrupts need to be enabled to not hang the CPU */
-       local_irq_enable();
+       raw_local_irq_enable();
 
        /* For systems without power-down, this will be no-op */
        __asm__ __volatile__ ("wr       %g0, %asr19\n\t");

diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index adfcaeab3ddc5be0c0869b2b74ac627bba578fbf..a023637359154e9bbd874a574bd9f95ba50c5b10 100644 (file)
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -74,7 +74,7 @@ void arch_cpu_idle(void)
 {
        if (sparc_idle)
                (*sparc_idle)();
-       local_irq_enable();
+       raw_local_irq_enable();
 }
 
 /* XXX cli/sti -> local_irq_xxx here, check this works once SMP is fixed. */

diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index a75093b993f9aed5c2dd77af4e2f74468a315736..6f8c7822fc065d394c0e573aa5eae10851a34542 100644 (file)
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -62,11 +62,11 @@ void arch_cpu_idle(void)
 {
        if (tlb_type != hypervisor) {
                touch_nmi_watchdog();
-               local_irq_enable();
+               raw_local_irq_enable();
        } else {
                unsigned long pstate;
 
-               local_irq_enable();
+               raw_local_irq_enable();
 
                 /* The sun4v sleeping code requires that we have PSTATE.IE cleared over
                  * the cpu sleep hypervisor call.

diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index 3bed09538dd951766fd6bc3219433577cf73fc5b..9505a7e87396a68a1576dc929a9958219f2247cc 100644 (file)
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -217,7 +217,7 @@ void arch_cpu_idle(void)
 {
        cpu_tasks[current_thread_info()->cpu].pid = os_getpid();
        um_idle_sleep();
-       local_irq_enable();
+       raw_local_irq_enable();
 }
 
 int __cant_sleep(void) {

diff --git a/arch/x86/include/asm/mwait.h b/arch/x86/include/asm/mwait.h
index e039a933aca3c38859a395e53f5736573dae9ea0..29dd27b5a339db16cfb1b40aa68004cf7b2bac0c 100644 (file)
--- a/arch/x86/include/asm/mwait.h
+++ b/arch/x86/include/asm/mwait.h
@@ -88,8 +88,6 @@ static inline void __mwaitx(unsigned long eax, unsigned long ebx,
 
 static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
 {
-       trace_hardirqs_on();
-
        mds_idle_clear_cpu_buffers();
        /* "mwait %eax, %ecx;" */
        asm volatile("sti; .byte 0x0f, 0x01, 0xc9;"

diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index ba4593a913fab3dc6f5b136470c07c02699aeefd..145a7ac0c19aa1f9a6e72d47d65a257029ec434a 100644 (file)
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -685,7 +685,7 @@ void arch_cpu_idle(void)
  */
 void __cpuidle default_idle(void)
 {
-       safe_halt();
+       raw_safe_halt();
 }
 #if defined(CONFIG_APM_MODULE) || defined(CONFIG_HALTPOLL_CPUIDLE_MODULE)
 EXPORT_SYMBOL(default_idle);
@@ -736,6 +736,8 @@ void stop_this_cpu(void *dummy)
 /*
  * AMD Erratum 400 aware idle routine. We handle it the same way as C3 power
  * states (local apic timer and TSC stop).
+ *
+ * XXX this function is completely buggered vs RCU and tracing.
  */
 static void amd_e400_idle(void)
 {
@@ -757,9 +759,9 @@ static void amd_e400_idle(void)
         * The switch back from broadcast mode needs to be called with
         * interrupts disabled.
         */
-       local_irq_disable();
+       raw_local_irq_disable();
        tick_broadcast_exit();
-       local_irq_enable();
+       raw_local_irq_enable();
 }
 
 /*
@@ -801,9 +803,9 @@ static __cpuidle void mwait_idle(void)
                if (!need_resched())
                        __sti_mwait(0, 0);
                else
-                       local_irq_enable();
+                       raw_local_irq_enable();
        } else {
-               local_irq_enable();
+               raw_local_irq_enable();
        }
        __current_clr_polling();
 }

diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 24d0ee26377d08269bf095c56e648329a9c82672..c6932b8f4467a5e678c0e1dc6260890b2692369a 100644 (file)
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -78,7 +78,7 @@ void __weak arch_cpu_idle_dead(void) { }
 void __weak arch_cpu_idle(void)
 {
        cpu_idle_force_poll = 1;
-       local_irq_enable();
+       raw_local_irq_enable();
 }
 
 /**
@@ -94,9 +94,35 @@ void __cpuidle default_idle_call(void)
 
                trace_cpu_idle(1, smp_processor_id());
                stop_critical_timings();
+
+               /*
+                * arch_cpu_idle() is supposed to enable IRQs, however
+                * we can't do that because of RCU and tracing.
+                *
+                * Trace IRQs enable here, then switch off RCU, and have
+                * arch_cpu_idle() use raw_local_irq_enable(). Note that
+                * rcu_idle_enter() relies on lockdep IRQ state, so switch that
+                * last -- this is very similar to the entry code.
+                */
+               trace_hardirqs_on_prepare();
+               lockdep_hardirqs_on_prepare(_THIS_IP_);
                rcu_idle_enter();
+               lockdep_hardirqs_on(_THIS_IP_);
+
                arch_cpu_idle();
+
+               /*
+                * OK, so IRQs are enabled here, but RCU needs them disabled to
+                * turn itself back on.. funny thing is that disabling IRQs
+                * will cause tracing, which needs RCU. Jump through hoops to
+                * make it 'work'.
+                */
+               raw_local_irq_disable();
+               lockdep_hardirqs_off(_THIS_IP_);
                rcu_idle_exit();
+               lockdep_hardirqs_on(_THIS_IP_);
+               raw_local_irq_enable();
+
                start_critical_timings();
                trace_cpu_idle(PWR_EVENT_EXIT, smp_processor_id());
        }