linux/kernel/irq/handle.c

243 lines
6.1 KiB
C
Raw Normal View History

// SPDX-License-Identifier: GPL-2.0
/*
* Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar
* Copyright (C) 2005-2006, Thomas Gleixner, Russell King
*
* This file contains the core interrupt handling code. Detailed
* information is available in Documentation/core-api/genericirq.rst
*
*/
#include <linux/irq.h>
#include <linux/random.h>
#include <linux/sched.h>
#include <linux/interrupt.h>
#include <linux/kernel_stat.h>
#include <asm/irq_regs.h>
#include <trace/events/irq.h>
#include "internals.h"
#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER
void (*handle_arch_irq)(struct pt_regs *) __ro_after_init;
#endif
/**
* handle_bad_irq - handle spurious and unhandled irqs
* @desc: description of the interrupt
*
* Handles spurious and unhandled IRQ's. It also prints a debugmessage.
*/
void handle_bad_irq(struct irq_desc *desc)
{
unsigned int irq = irq_desc_get_irq(desc);
print_irq_desc(irq, desc);
kstat_incr_irqs_this_cpu(desc);
ack_bad_irq(irq);
}
EXPORT_SYMBOL_GPL(handle_bad_irq);
/*
* Special, empty irq handler:
*/
IRQ: Maintain regs pointer globally rather than passing to IRQ handlers Maintain a per-CPU global "struct pt_regs *" variable which can be used instead of passing regs around manually through all ~1800 interrupt handlers in the Linux kernel. The regs pointer is used in few places, but it potentially costs both stack space and code to pass it around. On the FRV arch, removing the regs parameter from all the genirq function results in a 20% speed up of the IRQ exit path (ie: from leaving timer_interrupt() to leaving do_IRQ()). Where appropriate, an arch may override the generic storage facility and do something different with the variable. On FRV, for instance, the address is maintained in GR28 at all times inside the kernel as part of general exception handling. Having looked over the code, it appears that the parameter may be handed down through up to twenty or so layers of functions. Consider a USB character device attached to a USB hub, attached to a USB controller that posts its interrupts through a cascaded auxiliary interrupt controller. A character device driver may want to pass regs to the sysrq handler through the input layer which adds another few layers of parameter passing. I've build this code with allyesconfig for x86_64 and i386. I've runtested the main part of the code on FRV and i386, though I can't test most of the drivers. I've also done partial conversion for powerpc and MIPS - these at least compile with minimal configurations. This will affect all archs. Mostly the changes should be relatively easy. Take do_IRQ(), store the regs pointer at the beginning, saving the old one: struct pt_regs *old_regs = set_irq_regs(regs); And put the old one back at the end: set_irq_regs(old_regs); Don't pass regs through to generic_handle_irq() or __do_IRQ(). In timer_interrupt(), this sort of change will be necessary: - update_process_times(user_mode(regs)); - profile_tick(CPU_PROFILING, regs); + update_process_times(user_mode(get_irq_regs())); + profile_tick(CPU_PROFILING); I'd like to move update_process_times()'s use of get_irq_regs() into itself, except that i386, alone of the archs, uses something other than user_mode(). Some notes on the interrupt handling in the drivers: (*) input_dev() is now gone entirely. The regs pointer is no longer stored in the input_dev struct. (*) finish_unlinks() in drivers/usb/host/ohci-q.c needs checking. It does something different depending on whether it's been supplied with a regs pointer or not. (*) Various IRQ handler function pointers have been moved to type irq_handler_t. Signed-Off-By: David Howells <dhowells@redhat.com> (cherry picked from 1b16e7ac850969f38b375e511e3fa2f474a33867 commit)
2006-10-05 21:55:46 +08:00
irqreturn_t no_action(int cpl, void *dev_id)
{
return IRQ_NONE;
}
EXPORT_SYMBOL_GPL(no_action);
static void warn_no_thread(unsigned int irq, struct irqaction *action)
{
if (test_and_set_bit(IRQTF_WARNED, &action->thread_flags))
return;
printk(KERN_WARNING "IRQ %d device %s returned IRQ_WAKE_THREAD "
"but no thread function available.", irq, action->name);
}
void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action)
{
/*
* In case the thread crashed and was killed we just pretend that
* we handled the interrupt. The hardirq handler has disabled the
* device interrupt, so no irq storm is lurking.
*/
if (action->thread->flags & PF_EXITING)
return;
/*
* Wake up the handler thread for this action. If the
* RUNTHREAD bit is already set, nothing to do.
*/
if (test_and_set_bit(IRQTF_RUNTHREAD, &action->thread_flags))
return;
/*
* It's safe to OR the mask lockless here. We have only two
* places which write to threads_oneshot: This code and the
* irq thread.
*
* This code is the hard irq context and can never run on two
* cpus in parallel. If it ever does we have more serious
* problems than this bitmask.
*
* The irq threads of this irq which clear their "running" bit
* in threads_oneshot are serialized via desc->lock against
* each other and they are serialized against this code by
* IRQS_INPROGRESS.
*
* Hard irq handler:
*
* spin_lock(desc->lock);
* desc->state |= IRQS_INPROGRESS;
* spin_unlock(desc->lock);
* set_bit(IRQTF_RUNTHREAD, &action->thread_flags);
* desc->threads_oneshot |= mask;
* spin_lock(desc->lock);
* desc->state &= ~IRQS_INPROGRESS;
* spin_unlock(desc->lock);
*
* irq thread:
*
* again:
* spin_lock(desc->lock);
* if (desc->state & IRQS_INPROGRESS) {
* spin_unlock(desc->lock);
* while(desc->state & IRQS_INPROGRESS)
* cpu_relax();
* goto again;
* }
* if (!test_bit(IRQTF_RUNTHREAD, &action->thread_flags))
* desc->threads_oneshot &= ~mask;
* spin_unlock(desc->lock);
*
* So either the thread waits for us to clear IRQS_INPROGRESS
* or we are waiting in the flow handler for desc->lock to be
* released before we reach this point. The thread also checks
* IRQTF_RUNTHREAD under desc->lock. If set it leaves
* threads_oneshot untouched and runs the thread another time.
*/
desc->threads_oneshot |= action->thread_mask;
/*
* We increment the threads_active counter in case we wake up
* the irq thread. The irq thread decrements the counter when
* it returns from the handler or in the exit path and wakes
* up waiters which are stuck in synchronize_irq() when the
* active count becomes zero. synchronize_irq() is serialized
* against this code (hard irq handler) via IRQS_INPROGRESS
* like the finalize_oneshot() code. See comment above.
*/
atomic_inc(&desc->threads_active);
wake_up_process(action->thread);
}
irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc)
{
irqreturn_t retval = IRQ_NONE;
unsigned int irq = desc->irq_data.irq;
struct irqaction *action;
genirq/timings: Add infrastructure to track the interrupt timings The interrupt framework gives a lot of information about each interrupt. It does not keep track of when those interrupts occur though, which is a prerequisite for estimating the next interrupt arrival for power management purposes. Add a mechanism to record the timestamp for each interrupt occurrences in a per-CPU circular buffer to help with the prediction of the next occurrence using a statistical model. Each CPU can store up to IRQ_TIMINGS_SIZE events <irq, timestamp>, the current value of IRQ_TIMINGS_SIZE is 32. Each event is encoded into a single u64, where the high 48 bits are used for the timestamp and the low 16 bits are for the irq number. A static key is introduced so when the irq prediction is switched off at runtime, the overhead is near to zero. It results in most of the code in internals.h for inline reasons and a very few in the new file timings.c. The latter will contain more in the next patch which will provide the statistical model for the next event prediction. Signed-off-by: Daniel Lezcano <daniel.lezcano@linaro.org> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Acked-by: Nicolas Pitre <nicolas.pitre@linaro.org> Cc: Jens Axboe <axboe@kernel.dk> Cc: Hannes Reinecke <hare@suse.com> Cc: Vincent Guittot <vincent.guittot@linaro.org> Cc: "Rafael J . Wysocki" <rafael@kernel.org> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Bjorn Helgaas <bhelgaas@google.com> Link: http://lkml.kernel.org/r/1498227072-5980-1-git-send-email-daniel.lezcano@linaro.org
2017-06-23 22:11:07 +08:00
record_irq_time(desc);
for_each_action_of_desc(desc, action) {
irqreturn_t res;
lockdep: Introduce wait-type checks Extend lockdep to validate lock wait-type context. The current wait-types are: LD_WAIT_FREE, /* wait free, rcu etc.. */ LD_WAIT_SPIN, /* spin loops, raw_spinlock_t etc.. */ LD_WAIT_CONFIG, /* CONFIG_PREEMPT_LOCK, spinlock_t etc.. */ LD_WAIT_SLEEP, /* sleeping locks, mutex_t etc.. */ Where lockdep validates that the current lock (the one being acquired) fits in the current wait-context (as generated by the held stack). This ensures that there is no attempt to acquire mutexes while holding spinlocks, to acquire spinlocks while holding raw_spinlocks and so on. In other words, its a more fancy might_sleep(). Obviously RCU made the entire ordeal more complex than a simple single value test because RCU can be acquired in (pretty much) any context and while it presents a context to nested locks it is not the same as it got acquired in. Therefore its necessary to split the wait_type into two values, one representing the acquire (outer) and one representing the nested context (inner). For most 'normal' locks these two are the same. [ To make static initialization easier we have the rule that: .outer == INV means .outer == .inner; because INV == 0. ] It further means that its required to find the minimal .inner of the held stack to compare against the outer of the new lock; because while 'normal' RCU presents a CONFIG type to nested locks, if it is taken while already holding a SPIN type it obviously doesn't relax the rules. Below is an example output generated by the trivial test code: raw_spin_lock(&foo); spin_lock(&bar); spin_unlock(&bar); raw_spin_unlock(&foo); [ BUG: Invalid wait context ] ----------------------------- swapper/0/1 is trying to lock: ffffc90000013f20 (&bar){....}-{3:3}, at: kernel_init+0xdb/0x187 other info that might help us debug this: 1 lock held by swapper/0/1: #0: ffffc90000013ee0 (&foo){+.+.}-{2:2}, at: kernel_init+0xd1/0x187 The way to read it is to look at the new -{n,m} part in the lock description; -{3:3} for the attempted lock, and try and match that up to the held locks, which in this case is the one: -{2,2}. This tells that the acquiring lock requires a more relaxed environment than presented by the lock stack. Currently only the normal locks and RCU are converted, the rest of the lockdep users defaults to .inner = INV which is ignored. More conversions can be done when desired. The check for spinlock_t nesting is not enabled by default. It's a separate config option for now as there are known problems which are currently addressed. The config option allows to identify these problems and to verify that the solutions found are indeed solving them. The config switch will be removed and the checks will permanently enabled once the vast majority of issues has been addressed. [ bigeasy: Move LD_WAIT_FREE,… out of CONFIG_LOCKDEP to avoid compile failure with CONFIG_DEBUG_SPINLOCK + !CONFIG_LOCKDEP] [ tglx: Add the config option ] Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20200321113242.427089655@linutronix.de
2020-03-21 19:26:01 +08:00
/*
* If this IRQ would be threaded under force_irqthreads, mark it so.
*/
if (irq_settings_can_thread(desc) &&
!(action->flags & (IRQF_NO_THREAD | IRQF_PERCPU | IRQF_ONESHOT)))
x86 entry code updates: - Convert the 32bit syscalls to be pt_regs based which removes the requirement to push all 6 potential arguments onto the stack and consolidates the interface with the 64bit variant - The first small portion of the exception and syscall related entry code consolidation which aims to address the recently discovered issues vs. RCU, int3, NMI and some other exceptions which can interrupt any context. The bulk of the changes is still work in progress and aimed for 5.8. - A few lockdep namespace cleanups which have been applied into this branch to keep the prerequisites for the ongoing work confined. -----BEGIN PGP SIGNATURE----- iQJHBAABCgAxFiEEQp8+kY+LLUocC4bMphj1TA10mKEFAl6B/TMTHHRnbHhAbGlu dXRyb25peC5kZQAKCRCmGPVMDXSYoYA6EAC7r/bCMxBelljT3b7LkBbiJcocJ+zK OSzWU9miJGTAvYqn4/ciLKg4dA424b/1rBFlF1hBTCQ0HL5Cv4lajxdKEZCO5WCC WWTCz+MC60aWFaH3VNoywiLGb39H2IbqWbS9yNPd/wBkLHiMAD6NPQntOvcPaD4j 1lyrMtLzfrWlrHxvxdI3kt5ZpFLYNXr2xk61xQjTz0ROFQBhf2sDsuhHhiYVLPj7 JwYktpbBiPeaw2+I18NPymNPY+VfY8LCTgLl5M+rbKyCqebKaedZQJ7QXFhAEqKC Y2f+gJsKWtTDzGP2mk/5kF0uP7cd0vJK35ZCXtLZ9BbcNtFZU6w+ADqRo4pJBHRY QRzo/AWrdkuTJF0CrP6mcneNC7NwWLSdKrE1z77RQCHUPVvhHhRDZsgdLcZ/KKwx y1ji22trwNB+7LmI2fUOU5RRHZBIuNvQT+mPt24febJuHpZKul62dd3cqTGeSTC+ MYVknYDSg/+jk+83DhuZnTyb9lWTbq/0Q1HRDu6l2LrMIH7YMPpY5Ea64ZFYzWXy s0+iHEM4mUzltwNauHIntjbwXi3C0l2k1WQyG0gun2eS6SXfu0lb93V4msFj/N1+ oHavH2n2A4XrRr+Ob87fsl7nfXJibWP7R9xPblrWP2sNdqfjSyGd49rnsvpWqWMK Fj0d7tQ78+/SwA== =tWXS -----END PGP SIGNATURE----- Merge tag 'x86-entry-2020-03-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip Pull x86 entry code updates from Thomas Gleixner: - Convert the 32bit syscalls to be pt_regs based which removes the requirement to push all 6 potential arguments onto the stack and consolidates the interface with the 64bit variant - The first small portion of the exception and syscall related entry code consolidation which aims to address the recently discovered issues vs. RCU, int3, NMI and some other exceptions which can interrupt any context. The bulk of the changes is still work in progress and aimed for 5.8. - A few lockdep namespace cleanups which have been applied into this branch to keep the prerequisites for the ongoing work confined. * tag 'x86-entry-2020-03-30' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (35 commits) x86/entry: Fix build error x86 with !CONFIG_POSIX_TIMERS lockdep: Rename trace_{hard,soft}{irq_context,irqs_enabled}() lockdep: Rename trace_softirqs_{on,off}() lockdep: Rename trace_hardirq_{enter,exit}() x86/entry: Rename ___preempt_schedule x86: Remove unneeded includes x86/entry: Drop asmlinkage from syscalls x86/entry/32: Enable pt_regs based syscalls x86/entry/32: Use IA32-specific wrappers for syscalls taking 64-bit arguments x86/entry/32: Rename 32-bit specific syscalls x86/entry/32: Clean up syscall_32.tbl x86/entry: Remove ABI prefixes from functions in syscall tables x86/entry/64: Add __SYSCALL_COMMON() x86/entry: Remove syscall qualifier support x86/entry/64: Remove ptregs qualifier from syscall table x86/entry: Move max syscall number calculation to syscallhdr.sh x86/entry/64: Split X32 syscall table into its own file x86/entry/64: Move sys_ni_syscall stub to common.c x86/entry/64: Use syscall wrappers for x32_rt_sigreturn x86/entry: Refactor SYS_NI macros ...
2020-03-31 10:14:28 +08:00
lockdep_hardirq_threaded();
lockdep: Introduce wait-type checks Extend lockdep to validate lock wait-type context. The current wait-types are: LD_WAIT_FREE, /* wait free, rcu etc.. */ LD_WAIT_SPIN, /* spin loops, raw_spinlock_t etc.. */ LD_WAIT_CONFIG, /* CONFIG_PREEMPT_LOCK, spinlock_t etc.. */ LD_WAIT_SLEEP, /* sleeping locks, mutex_t etc.. */ Where lockdep validates that the current lock (the one being acquired) fits in the current wait-context (as generated by the held stack). This ensures that there is no attempt to acquire mutexes while holding spinlocks, to acquire spinlocks while holding raw_spinlocks and so on. In other words, its a more fancy might_sleep(). Obviously RCU made the entire ordeal more complex than a simple single value test because RCU can be acquired in (pretty much) any context and while it presents a context to nested locks it is not the same as it got acquired in. Therefore its necessary to split the wait_type into two values, one representing the acquire (outer) and one representing the nested context (inner). For most 'normal' locks these two are the same. [ To make static initialization easier we have the rule that: .outer == INV means .outer == .inner; because INV == 0. ] It further means that its required to find the minimal .inner of the held stack to compare against the outer of the new lock; because while 'normal' RCU presents a CONFIG type to nested locks, if it is taken while already holding a SPIN type it obviously doesn't relax the rules. Below is an example output generated by the trivial test code: raw_spin_lock(&foo); spin_lock(&bar); spin_unlock(&bar); raw_spin_unlock(&foo); [ BUG: Invalid wait context ] ----------------------------- swapper/0/1 is trying to lock: ffffc90000013f20 (&bar){....}-{3:3}, at: kernel_init+0xdb/0x187 other info that might help us debug this: 1 lock held by swapper/0/1: #0: ffffc90000013ee0 (&foo){+.+.}-{2:2}, at: kernel_init+0xd1/0x187 The way to read it is to look at the new -{n,m} part in the lock description; -{3:3} for the attempted lock, and try and match that up to the held locks, which in this case is the one: -{2,2}. This tells that the acquiring lock requires a more relaxed environment than presented by the lock stack. Currently only the normal locks and RCU are converted, the rest of the lockdep users defaults to .inner = INV which is ignored. More conversions can be done when desired. The check for spinlock_t nesting is not enabled by default. It's a separate config option for now as there are known problems which are currently addressed. The config option allows to identify these problems and to verify that the solutions found are indeed solving them. The config switch will be removed and the checks will permanently enabled once the vast majority of issues has been addressed. [ bigeasy: Move LD_WAIT_FREE,… out of CONFIG_LOCKDEP to avoid compile failure with CONFIG_DEBUG_SPINLOCK + !CONFIG_LOCKDEP] [ tglx: Add the config option ] Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Link: https://lkml.kernel.org/r/20200321113242.427089655@linutronix.de
2020-03-21 19:26:01 +08:00
trace_irq_handler_entry(irq, action);
res = action->handler(irq, action->dev_id);
trace_irq_handler_exit(irq, action, res);
2019-03-26 03:32:28 +08:00
if (WARN_ONCE(!irqs_disabled(),"irq %u handler %pS enabled interrupts\n",
irq, action->handler))
local_irq_disable();
switch (res) {
case IRQ_WAKE_THREAD:
/*
* Catch drivers which return WAKE_THREAD but
* did not set up a thread function
*/
if (unlikely(!action->thread_fn)) {
warn_no_thread(irq, action);
break;
}
__irq_wake_thread(desc, action);
break;
default:
break;
}
retval |= res;
genirq: Validate action before dereferencing it in handle_irq_event_percpu() commit 71f64340fc0e changed the handling of irq_desc->action from CPU 0 CPU 1 free_irq() lock(desc) lock(desc) handle_edge_irq() if (desc->action) { handle_irq_event() action = desc->action unlock(desc) desc->action = NULL handle_irq_event_percpu(desc, action) action->xxx to CPU 0 CPU 1 free_irq() lock(desc) lock(desc) handle_edge_irq() if (desc->action) { handle_irq_event() unlock(desc) desc->action = NULL handle_irq_event_percpu(desc, action) action = desc->action action->xxx So if free_irq manages to set the action to NULL between the unlock and before the readout, we happily dereference a null pointer. We could simply revert 71f64340fc0e, but we want to preserve the better code generation. A simple solution is to change the action loop from a do {} while to a while {} loop. This is safe because we either see a valid desc->action or NULL. If the action is about to be removed it is still valid as free_irq() is blocked on synchronize_irq(). CPU 0 CPU 1 free_irq() lock(desc) lock(desc) handle_edge_irq() handle_irq_event(desc) set(INPROGRESS) unlock(desc) handle_irq_event_percpu(desc) action = desc->action desc->action = NULL while (action) { action->xxx ... action = action->next; sychronize_irq() while(INPROGRESS); lock(desc) clr(INPROGRESS) free(action) That's basically the same mechanism as we have for shared interrupts. action->next can become NULL while handle_irq_event_percpu() runs. Either it sees the action or NULL. It does not matter, because action itself cannot go away before the interrupt in progress flag has been cleared. Fixes: commit 71f64340fc0e "genirq: Remove the second parameter from handle_irq_event_percpu()" Reported-by: zyjzyj2000@gmail.com Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Huang Shijie <shijie.huang@arm.com> Cc: Jiang Liu <jiang.liu@linux.intel.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: stable@vger.kernel.org Link: http://lkml.kernel.org/r/alpine.DEB.2.11.1601131224190.3575@nanos
2016-01-13 21:07:25 +08:00
}
return retval;
}
irqreturn_t handle_irq_event_percpu(struct irq_desc *desc)
{
irqreturn_t retval;
retval = __handle_irq_event_percpu(desc);
add_interrupt_randomness(desc->irq_data.irq);
if (!irq_settings_no_debug(desc))
note_interrupt(desc, retval);
return retval;
}
irqreturn_t handle_irq_event(struct irq_desc *desc)
{
irqreturn_t ret;
desc->istate &= ~IRQS_PENDING;
irqd_set(&desc->irq_data, IRQD_IRQ_INPROGRESS);
raw_spin_unlock(&desc->lock);
ret = handle_irq_event_percpu(desc);
raw_spin_lock(&desc->lock);
irqd_clear(&desc->irq_data, IRQD_IRQ_INPROGRESS);
return ret;
}
#ifdef CONFIG_GENERIC_IRQ_MULTI_HANDLER
int __init set_handle_irq(void (*handle_irq)(struct pt_regs *))
{
if (handle_arch_irq)
return -EBUSY;
handle_arch_irq = handle_irq;
return 0;
}
/**
* generic_handle_arch_irq - root irq handler for architectures which do no
* entry accounting themselves
* @regs: Register file coming from the low-level handling code
*/
asmlinkage void noinstr generic_handle_arch_irq(struct pt_regs *regs)
{
struct pt_regs *old_regs;
irq_enter();
old_regs = set_irq_regs(regs);
handle_arch_irq(regs);
set_irq_regs(old_regs);
irq_exit();
}
#endif