Files
linux/kernel/irq/internals.h
Linus Torvalds 764e77d868 Merge tag 'locking-core-2026-06-14' of gitolite.kernel.org:pub/scm/linux/kernel/git/tip/tip
Pull locking updates from Ingo Molnar:
 "Futex updates:

   - Optimize futex hash bucket access patterns (Peter Zijlstra)

   - Large series to address the robust futex unlock race for real, by
     Thomas Gleixner:

      "The robust futex unlock mechanism is racy in respect to the
       clearing of the robust_list_head::list_op_pending pointer because
       unlock and clearing the pointer are not atomic.

       The race window is between the unlock and clearing the pending op
       pointer. If the task is forced to exit in this window, exit will
       access a potentially invalid pending op pointer when cleaning up
       the robust list.

       That happens if another task manages to unmap the object
       containing the lock before the cleanup, which results in an UAF.

       In the worst case this UAF can lead to memory corruption when
       unrelated content has been mapped to the same address by the time
       the access happens.

       User space can't solve this problem without help from the kernel.
       This series provides the kernel side infrastructure to help it
       along:

        1) Combined unlock, pointer clearing, wake-up for the
           contended case

        2) VDSO based unlock and pointer clearing helpers with a
           fix-up function in the kernel when user space was interrupted
           within the critical section.

      ... with help by André Almeida:

        - Add a note about robust list race condition (André Almeida)
        - Add self-tests for robust release operations (André Almeida)

  Context analysis updates:

   - Implement context analysis for 'struct rt_mutex'. (Bart Van Assche)
   - Bump required Clang version to 23 (Marco Elver)

  Guard infrastructure updates:

   - Series to remove NULL check from unconditional guards (Dmitry
     Ilvokhin)

  Lockdep updates:

   - Restore self-test migrate_disable() and sched_rt_mutex state on
     PREEMPT_RT (Karl Mehltretter)

  Membarriers updates:

   - Use per-CPU mutexes for targeted commands (Aniket Gattani)
   - Modernize membarrier_global_expedited with cleanup guards (Aniket
     Gattani)
   - Add rseq stress test for CFS throttle interactions (Aniket Gattani)

  percpu-rwsems updates:

   - Extract __percpu_up_read() to optimize inlining overhead (Dmitry
     Ilvokhin)

  Seqlocks updates:

   - Allow UBSAN_ALIGNMENT to fail optimizing (Heiko Carstens)

  Lock tracing:

   - Add contended_release tracepoint to sleepable locks such as
     mutexes, percpu-rwsems, rtmutexes, rwsems and semaphores (Dmitry
     Ilvokhin)

  MAINTAINERS updates:

   - MAINTAINERS: Add RUST [SYNC] entry (Boqun Feng)

  Misc updates and fixes by Randy Dunlap, YE WEI-HONG, Fabricio Parra,
  Dmitry Ilvokhin and Peter Zijlstra"

* tag 'locking-core-2026-06-14' of gitolite.kernel.org:pub/scm/linux/kernel/git/tip/tip: (36 commits)
  locking: Add contended_release tracepoint to sleepable locks
  locking/percpu-rwsem: Extract __percpu_up_read()
  tracing/lock: Remove unnecessary linux/sched.h include
  futex: Optimize futex hash bucket access patterns
  rust: sync: completion: Mark inline complete_all and wait_for_completion
  MAINTAINERS: Add RUST [SYNC] entry
  cleanup: Specify nonnull argument index
  selftests: futex: Add tests for robust release operations
  Documentation: futex: Add a note about robust list race condition
  x86/vdso: Implement __vdso_futex_robust_try_unlock()
  x86/vdso: Prepare for robust futex unlock support
  futex: Provide infrastructure to plug the non contended robust futex unlock race
  futex: Add robust futex unlock IP range
  futex: Add support for unlocking robust futexes
  futex: Cleanup UAPI defines
  x86: Select ARCH_MEMORY_ORDER_TSO
  uaccess: Provide unsafe_atomic_store_release_user()
  futex: Provide UABI defines for robust list entry modifiers
  futex: Move futex related mm_struct data into a struct
  futex: Make futex_mm_init() void
  ...
2026-06-15 14:21:14 +05:30

398 lines
12 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* IRQ subsystem internal functions and variables:
*
* Do not ever include this file from anything else than
* kernel/irq/. Do not even think about using any information outside
* of this file for your non core code.
*/
#include <linux/irqdesc.h>
#include <linux/kernel_stat.h>
#include <linux/pm_runtime.h>
#include <linux/rcuref.h>
#include <linux/sched/clock.h>
#include "debugfs.h"
#include "proc.h"
#ifdef CONFIG_SPARSE_IRQ
# define MAX_SPARSE_IRQS INT_MAX
#else
# define MAX_SPARSE_IRQS NR_IRQS
#endif
#define istate core_internal_state__do_not_mess_with_it
extern bool noirqdebug;
extern int irq_poll_cpu;
extern unsigned int total_nr_irqs;
extern struct irqaction chained_action;
/*
* Bits used by threaded handlers:
* IRQTF_RUNTHREAD - signals that the interrupt handler thread should run
* IRQTF_WARNED - warning "IRQ_WAKE_THREAD w/o thread_fn" has been printed
* IRQTF_AFFINITY - irq thread is requested to adjust affinity
* IRQTF_FORCED_THREAD - irq action is force threaded
* IRQTF_READY - signals that irq thread is ready
*/
enum {
IRQTF_RUNTHREAD,
IRQTF_WARNED,
IRQTF_AFFINITY,
IRQTF_FORCED_THREAD,
IRQTF_READY,
};
/*
* Bit masks for desc->core_internal_state__do_not_mess_with_it
*
* IRQS_AUTODETECT - autodetection in progress
* IRQS_SPURIOUS_DISABLED - was disabled due to spurious interrupt
* detection
* IRQS_POLL_INPROGRESS - polling in progress
* IRQS_ONESHOT - irq is not unmasked in primary handler
* IRQS_REPLAY - irq has been resent and will not be resent
* again until the handler has run and cleared
* this flag.
* IRQS_WAITING - irq is waiting
* IRQS_PENDING - irq needs to be resent and should be resent
* at the next available opportunity.
* IRQS_SUSPENDED - irq is suspended
* IRQS_NMI - irq line is used to deliver NMIs
* IRQS_SYSFS - descriptor has been added to sysfs
*/
enum {
IRQS_AUTODETECT = 0x00000001,
IRQS_SPURIOUS_DISABLED = 0x00000002,
IRQS_POLL_INPROGRESS = 0x00000008,
IRQS_ONESHOT = 0x00000020,
IRQS_REPLAY = 0x00000040,
IRQS_WAITING = 0x00000080,
IRQS_PENDING = 0x00000200,
IRQS_SUSPENDED = 0x00000800,
IRQS_TIMINGS = 0x00001000,
IRQS_NMI = 0x00002000,
IRQS_SYSFS = 0x00004000,
};
#include "debug.h"
#include "settings.h"
extern int __irq_set_trigger(struct irq_desc *desc, unsigned long flags);
extern void __disable_irq(struct irq_desc *desc);
extern void __enable_irq(struct irq_desc *desc);
#define IRQ_RESEND true
#define IRQ_NORESEND false
#define IRQ_START_FORCE true
#define IRQ_START_COND false
extern int irq_activate(struct irq_desc *desc);
extern int irq_activate_and_startup(struct irq_desc *desc, bool resend);
extern int irq_startup(struct irq_desc *desc, bool resend, bool force);
extern void irq_startup_managed(struct irq_desc *desc);
extern void irq_shutdown(struct irq_desc *desc);
extern void irq_shutdown_and_deactivate(struct irq_desc *desc);
extern void irq_disable(struct irq_desc *desc);
extern void irq_percpu_enable(struct irq_desc *desc, unsigned int cpu);
extern void irq_percpu_disable(struct irq_desc *desc, unsigned int cpu);
extern void mask_irq(struct irq_desc *desc);
extern void unmask_irq(struct irq_desc *desc);
extern void unmask_threaded_irq(struct irq_desc *desc);
#ifdef CONFIG_SPARSE_IRQ
static __always_inline void irq_mark_irq(unsigned int irq) { }
void irq_desc_free_rcu(struct irq_desc *desc);
static __always_inline bool irq_desc_get_ref(struct irq_desc *desc)
{
return rcuref_get(&desc->refcnt);
}
static __always_inline void irq_desc_put_ref(struct irq_desc *desc)
{
if (rcuref_put(&desc->refcnt))
irq_desc_free_rcu(desc);
}
#else
extern void irq_mark_irq(unsigned int irq);
static __always_inline bool irq_desc_get_ref(struct irq_desc *desc) { return true; }
static __always_inline void irq_desc_put_ref(struct irq_desc *desc) { }
#endif
irqreturn_t __handle_irq_event_percpu(struct irq_desc *desc);
irqreturn_t handle_irq_event_percpu(struct irq_desc *desc);
irqreturn_t handle_irq_event(struct irq_desc *desc);
/* Resending of interrupts :*/
int check_irq_resend(struct irq_desc *desc, bool inject);
void clear_irq_resend(struct irq_desc *desc);
void irq_resend_init(struct irq_desc *desc);
void __irq_wake_thread(struct irq_desc *desc, struct irqaction *action);
void wake_threads_waitq(struct irq_desc *desc);
#ifdef CONFIG_PROC_FS
extern void register_irq_proc(unsigned int irq, struct irq_desc *desc);
extern void unregister_irq_proc(unsigned int irq, struct irq_desc *desc);
extern void register_handler_proc(unsigned int irq, struct irqaction *action);
extern void unregister_handler_proc(unsigned int irq, struct irqaction *action);
void irq_proc_update_valid(struct irq_desc *desc);
#else
static inline void register_irq_proc(unsigned int irq, struct irq_desc *desc) { }
static inline void unregister_irq_proc(unsigned int irq, struct irq_desc *desc) { }
static inline void register_handler_proc(unsigned int irq,
struct irqaction *action) { }
static inline void unregister_handler_proc(unsigned int irq,
struct irqaction *action) { }
static inline void irq_proc_update_valid(struct irq_desc *desc) { }
#endif
struct irq_desc *irq_find_desc_at_or_after(unsigned int offset);
extern bool irq_can_set_affinity_usr(unsigned int irq);
extern int irq_do_set_affinity(struct irq_data *data,
const struct cpumask *dest, bool force);
extern void irq_affinity_schedule_notify_work(struct irq_desc *desc);
#ifdef CONFIG_SMP
extern int irq_setup_affinity(struct irq_desc *desc);
#else
static inline int irq_setup_affinity(struct irq_desc *desc) { return 0; }
#endif
#define for_each_action_of_desc(desc, act) \
for (act = desc->action; act; act = act->next)
/* Inline functions for support of irq chips on slow busses */
static inline void chip_bus_lock(struct irq_desc *desc)
{
if (unlikely(desc->irq_data.chip->irq_bus_lock))
desc->irq_data.chip->irq_bus_lock(&desc->irq_data);
}
static inline void chip_bus_sync_unlock(struct irq_desc *desc)
{
if (unlikely(desc->irq_data.chip->irq_bus_sync_unlock))
desc->irq_data.chip->irq_bus_sync_unlock(&desc->irq_data);
}
#define _IRQ_DESC_CHECK (1 << 0)
#define _IRQ_DESC_PERCPU (1 << 1)
#define IRQ_GET_DESC_CHECK_GLOBAL (_IRQ_DESC_CHECK)
#define IRQ_GET_DESC_CHECK_PERCPU (_IRQ_DESC_CHECK | _IRQ_DESC_PERCPU)
struct irq_desc *__irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus,
unsigned int check);
void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus);
__DEFINE_CLASS_IS_CONDITIONAL(irqdesc_lock, true);
__DEFINE_UNLOCK_GUARD(irqdesc_lock, struct irq_desc,
if (_T->lock) __irq_put_desc_unlock(_T->lock, _T->flags, _T->bus),
unsigned long flags; bool bus);
static inline class_irqdesc_lock_t class_irqdesc_lock_constructor(unsigned int irq, bool bus,
unsigned int check)
{
class_irqdesc_lock_t _t = { .bus = bus, };
_t.lock = __irq_get_desc_lock(irq, &_t.flags, bus, check);
return _t;
}
#define scoped_irqdesc_get_and_lock(_irq, _check) \
scoped_guard(irqdesc_lock, _irq, false, _check)
#define scoped_irqdesc_get_and_buslock(_irq, _check) \
scoped_guard(irqdesc_lock, _irq, true, _check)
#define scoped_irqdesc ((struct irq_desc *)(__guard_ptr(irqdesc_lock)(&scope)))
#define __irqd_to_state(d) ACCESS_PRIVATE((d)->common, state_use_accessors)
static inline unsigned int irqd_get(struct irq_data *d)
{
return __irqd_to_state(d);
}
/*
* Manipulation functions for irq_data.state
*/
static inline void irqd_set_move_pending(struct irq_data *d)
{
__irqd_to_state(d) |= IRQD_SETAFFINITY_PENDING;
}
static inline void irqd_clr_move_pending(struct irq_data *d)
{
__irqd_to_state(d) &= ~IRQD_SETAFFINITY_PENDING;
}
static inline void irqd_set_managed_shutdown(struct irq_data *d)
{
__irqd_to_state(d) |= IRQD_MANAGED_SHUTDOWN;
}
static inline void irqd_clr_managed_shutdown(struct irq_data *d)
{
__irqd_to_state(d) &= ~IRQD_MANAGED_SHUTDOWN;
}
static inline void irqd_clear(struct irq_data *d, unsigned int mask)
{
__irqd_to_state(d) &= ~mask;
}
static inline void irqd_set(struct irq_data *d, unsigned int mask)
{
__irqd_to_state(d) |= mask;
}
static inline bool irqd_has_set(struct irq_data *d, unsigned int mask)
{
return __irqd_to_state(d) & mask;
}
static inline void irq_state_set_disabled(struct irq_desc *desc)
{
irqd_set(&desc->irq_data, IRQD_IRQ_DISABLED);
}
static inline void irq_state_set_masked(struct irq_desc *desc)
{
irqd_set(&desc->irq_data, IRQD_IRQ_MASKED);
}
#undef __irqd_to_state
static inline void __kstat_incr_irqs_this_cpu(struct irq_desc *desc)
{
__this_cpu_inc(desc->kstat_irqs->cnt);
__this_cpu_inc(kstat.irqs_sum);
}
static inline void kstat_incr_irqs_this_cpu(struct irq_desc *desc)
{
__kstat_incr_irqs_this_cpu(desc);
desc->tot_count++;
}
static inline int irq_desc_get_node(struct irq_desc *desc)
{
return irq_common_data_get_node(&desc->irq_common_data);
}
static inline int irq_desc_is_chained(struct irq_desc *desc)
{
return (desc->action && desc->action == &chained_action);
}
static inline bool irq_is_nmi(struct irq_desc *desc)
{
return desc->istate & IRQS_NMI;
}
#ifdef CONFIG_PM_SLEEP
void irq_pm_handle_wakeup(struct irq_desc *desc);
void irq_pm_install_action(struct irq_desc *desc, struct irqaction *action);
void irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action);
#else
static inline void irq_pm_handle_wakeup(struct irq_desc *desc) { }
static inline void
irq_pm_install_action(struct irq_desc *desc, struct irqaction *action) { }
static inline void
irq_pm_remove_action(struct irq_desc *desc, struct irqaction *action) { }
#endif
#ifdef CONFIG_GENERIC_IRQ_CHIP
void irq_init_generic_chip(struct irq_chip_generic *gc, const char *name,
int num_ct, unsigned int irq_base,
void __iomem *reg_base, irq_flow_handler_t handler);
#else
static inline void
irq_init_generic_chip(struct irq_chip_generic *gc, const char *name,
int num_ct, unsigned int irq_base,
void __iomem *reg_base, irq_flow_handler_t handler) { }
#endif /* CONFIG_GENERIC_IRQ_CHIP */
#ifdef CONFIG_GENERIC_PENDING_IRQ
static inline bool irq_can_move_pcntxt(struct irq_data *data)
{
return !(data->chip->flags & IRQCHIP_MOVE_DEFERRED);
}
static inline bool irq_move_pending(struct irq_data *data)
{
return irqd_is_setaffinity_pending(data);
}
static inline void
irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask)
{
cpumask_copy(desc->pending_mask, mask);
}
static inline void
irq_get_pending(struct cpumask *mask, struct irq_desc *desc)
{
cpumask_copy(mask, desc->pending_mask);
}
static inline struct cpumask *irq_desc_get_pending_mask(struct irq_desc *desc)
{
return desc->pending_mask;
}
bool irq_fixup_move_pending(struct irq_desc *desc, bool force_clear);
void irq_force_complete_move(struct irq_desc *desc);
#else /* CONFIG_GENERIC_PENDING_IRQ */
static inline bool irq_can_move_pcntxt(struct irq_data *data)
{
return true;
}
static inline bool irq_move_pending(struct irq_data *data)
{
return false;
}
static inline void
irq_copy_pending(struct irq_desc *desc, const struct cpumask *mask)
{
}
static inline void
irq_get_pending(struct cpumask *mask, struct irq_desc *desc)
{
}
static inline struct cpumask *irq_desc_get_pending_mask(struct irq_desc *desc)
{
return NULL;
}
static inline bool irq_fixup_move_pending(struct irq_desc *desc, bool fclear)
{
return false;
}
static inline void irq_force_complete_move(struct irq_desc *desc) { }
#endif /* !CONFIG_GENERIC_PENDING_IRQ */
#if !defined(CONFIG_IRQ_DOMAIN) || !defined(CONFIG_IRQ_DOMAIN_HIERARCHY)
static inline int irq_domain_activate_irq(struct irq_data *data, bool reserve)
{
irqd_set_activated(data);
return 0;
}
static inline void irq_domain_deactivate_irq(struct irq_data *data)
{
irqd_clr_activated(data);
}
#endif
static inline struct irq_data *irqd_get_parent_data(struct irq_data *irqd)
{
#ifdef CONFIG_IRQ_DOMAIN_HIERARCHY
return irqd->parent_data;
#else
return NULL;
#endif
}