linux-next/include/linux/smp.h
Linus Torvalds 067610ebaa RCU pull request for v6.12
This pull request contains the following branches:
 
 context_tracking.15.08.24a: Rename context tracking state related
         symbols and remove references to "dynticks" in various context
         tracking state variables and related helpers; force
         context_tracking_enabled_this_cpu() to be inlined to avoid
         leaving a noinstr section.
 
 csd.lock.15.08.24a: Enhance CSD-lock diagnostic reports; add an API
         to provide an indication of ongoing CSD-lock stall.
 
 nocb.09.09.24a: Update and simplify RCU nocb code to handle
         (de-)offloading of callbacks only for offline CPUs; fix RT
         throttling hrtimer being armed from offline CPU.
 
 rcutorture.14.08.24a: Remove redundant rcu_torture_ops get_gp_completed
         fields; add SRCU ->same_gp_state and ->get_comp_state
         functions; add generic test for NUM_ACTIVE_*RCU_POLL* for
         testing RCU and SRCU polled grace periods; add CFcommon.arch
         for arch-specific Kconfig options; print number of update types
         in rcu_torture_write_types();
         add rcutree.nohz_full_patience_delay testing to the TREE07
         scenario; add a stall_cpu_repeat module parameter to test
         repeated CPU stalls; add argument to limit number of CPUs a
         guest OS can use in torture.sh;
 
 rcustall.09.09.24a: Abbreviate RCU CPU stall warnings during CSD-lock
         stalls; Allow dump_cpu_task() to be called without disabling
         preemption; defer printing stall-warning backtrace when holding
         rcu_node lock.
 
 srcu.12.08.24a: Make SRCU gp seq wrap-around faster; add KCSAN checks
         for concurrent updates to ->srcu_n_exp_nodelay and
         ->reschedule_count which are used in heuristics governing
         auto-expediting of normal SRCU grace periods and
         grace-period-state-machine delays; mark idle SRCU-barrier
         callbacks to help identify stuck SRCU-barrier callback.
 
 rcu.tasks.14.08.24a: Remove RCU Tasks Rude asynchronous APIs as they
         are no longer used; stop testing RCU Tasks Rude asynchronous
         APIs; fix access to non-existent percpu regions; check
         processor-ID assumptions during chosen CPU calculation for
         callback enqueuing; update description of rtp->tasks_gp_seq
         grace-period sequence number; add rcu_barrier_cb_is_done()
         to identify whether a given rcu_barrier callback is stuck;
         mark idle Tasks-RCU-barrier callbacks; add
         *torture_stats_print() functions to print detailed
         diagnostics for Tasks-RCU variants; capture start time of
         rcu_barrier_tasks*() operation to help distinguish a hung
         barrier operation from a long series of barrier operations.
 
 rcu_scaling_tests.15.08.24a:
         refscale: Add a TINY scenario to support tests of Tiny RCU
         and Tiny SRCU; Optimize process_durations() operation;
 
         rcuscale: Dump stacks of stalled rcu_scale_writer() instances;
         dump grace-period statistics when rcu_scale_writer() stalls;
         mark idle RCU-barrier callbacks to identify stuck RCU-barrier
         callbacks; print detailed grace-period and barrier diagnostics
         on rcu_scale_writer() hangs for Tasks-RCU variants; warn if
         async module parameter is specified for RCU implementations
         that do not have async primitives such as RCU Tasks Rude;
         make all writer tasks report upon hang; tolerate repeated
         GFP_KERNEL failure in rcu_scale_writer(); use special allocator
         for rcu_scale_writer(); NULL out top-level pointers to heap
         memory to avoid double-free bugs on modprobe failures; maintain
         per-task instead of per-CPU callbacks count to avoid any issues
         with migration of either tasks or callbacks; constify struct
         ref_scale_ops.
 
 fixes.12.08.24a: Use system_unbound_wq for kfree_rcu work to avoid
         disturbing isolated CPUs.
 
 misc.11.08.24a: Warn on unexpected rcu_state.srs_done_tail state;
         Better define "atomic" for list_replace_rcu() and
         hlist_replace_rcu() routines; annotate struct
         kvfree_rcu_bulk_data with __counted_by().
 -----BEGIN PGP SIGNATURE-----
 
 iHUEABYIAB0WIQSi2tPIQIc2VEtjarIAHS7/6Z0wpQUCZt8+8wAKCRAAHS7/6Z0w
 pTqoAPwPN//tlEoJx2PRs6t0q+nD1YNvnZawPaRmdzgdM8zJogD+PiSN+XhqRr80
 jzyvMDU4Aa0wjUNP3XsCoaCxo7L/lQk=
 =bZ9z
 -----END PGP SIGNATURE-----

Merge tag 'rcu.release.v6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/rcu/linux

Pull RCU updates from Neeraj Upadhyay:
 "Context tracking:
   - rename context tracking state related symbols and remove references
     to "dynticks" in various context tracking state variables and
     related helpers
   - force context_tracking_enabled_this_cpu() to be inlined to avoid
     leaving a noinstr section

  CSD lock:
   - enhance CSD-lock diagnostic reports
   - add an API to provide an indication of ongoing CSD-lock stall

  nocb:
   - update and simplify RCU nocb code to handle (de-)offloading of
     callbacks only for offline CPUs
   - fix RT throttling hrtimer being armed from offline CPU

  rcutorture:
   - remove redundant rcu_torture_ops get_gp_completed fields
   - add SRCU ->same_gp_state and ->get_comp_state functions
   - add generic test for NUM_ACTIVE_*RCU_POLL* for testing RCU and SRCU
     polled grace periods
   - add CFcommon.arch for arch-specific Kconfig options
   - print number of update types in rcu_torture_write_types()
   - add rcutree.nohz_full_patience_delay testing to the TREE07 scenario
   - add a stall_cpu_repeat module parameter to test repeated CPU stalls
   - add argument to limit number of CPUs a guest OS can use in
     torture.sh

  rcustall:
   - abbreviate RCU CPU stall warnings during CSD-lock stalls
   - Allow dump_cpu_task() to be called without disabling preemption
   - defer printing stall-warning backtrace when holding rcu_node lock

  srcu:
   - make SRCU gp seq wrap-around faster
   - add KCSAN checks for concurrent updates to ->srcu_n_exp_nodelay and
     ->reschedule_count which are used in heuristics governing
     auto-expediting of normal SRCU grace periods and
     grace-period-state-machine delays
   - mark idle SRCU-barrier callbacks to help identify stuck
     SRCU-barrier callback

  rcu tasks:
   - remove RCU Tasks Rude asynchronous APIs as they are no longer used
   - stop testing RCU Tasks Rude asynchronous APIs
   - fix access to non-existent percpu regions
   - check processor-ID assumptions during chosen CPU calculation for
     callback enqueuing
   - update description of rtp->tasks_gp_seq grace-period sequence
     number
   - add rcu_barrier_cb_is_done() to identify whether a given
     rcu_barrier callback is stuck
   - mark idle Tasks-RCU-barrier callbacks
   - add *torture_stats_print() functions to print detailed diagnostics
     for Tasks-RCU variants
   - capture start time of rcu_barrier_tasks*() operation to help
     distinguish a hung barrier operation from a long series of barrier
     operations

  refscale:
   - add a TINY scenario to support tests of Tiny RCU and Tiny
     SRCU
   - optimize process_durations() operation

  rcuscale:
   - dump stacks of stalled rcu_scale_writer() instances and
     grace-period statistics when rcu_scale_writer() stalls
   - mark idle RCU-barrier callbacks to identify stuck RCU-barrier
     callbacks
   - print detailed grace-period and barrier diagnostics on
     rcu_scale_writer() hangs for Tasks-RCU variants
   - warn if async module parameter is specified for RCU implementations
     that do not have async primitives such as RCU Tasks Rude
   - make all writer tasks report upon hang
   - tolerate repeated GFP_KERNEL failure in rcu_scale_writer()
   - use special allocator for rcu_scale_writer()
   - NULL out top-level pointers to heap memory to avoid double-free
     bugs on modprobe failures
   - maintain per-task instead of per-CPU callbacks count to avoid any
     issues with migration of either tasks or callbacks
   - constify struct ref_scale_ops

  Fixes:
   - use system_unbound_wq for kfree_rcu work to avoid disturbing
     isolated CPUs

  Misc:
   - warn on unexpected rcu_state.srs_done_tail state
   - better define "atomic" for list_replace_rcu() and
     hlist_replace_rcu() routines
   - annotate struct kvfree_rcu_bulk_data with __counted_by()"

* tag 'rcu.release.v6.12' of git://git.kernel.org/pub/scm/linux/kernel/git/rcu/linux: (90 commits)
  rcu: Defer printing stall-warning backtrace when holding rcu_node lock
  rcu/nocb: Remove superfluous memory barrier after bypass enqueue
  rcu/nocb: Conditionally wake up rcuo if not already waiting on GP
  rcu/nocb: Fix RT throttling hrtimer armed from offline CPU
  rcu/nocb: Simplify (de-)offloading state machine
  context_tracking: Tag context_tracking_enabled_this_cpu() __always_inline
  context_tracking, rcu: Rename rcu_dyntick trace event into rcu_watching
  rcu: Update stray documentation references to rcu_dynticks_eqs_{enter, exit}()
  rcu: Rename rcu_momentary_dyntick_idle() into rcu_momentary_eqs()
  rcu: Rename rcu_implicit_dynticks_qs() into rcu_watching_snap_recheck()
  rcu: Rename dyntick_save_progress_counter() into rcu_watching_snap_save()
  rcu: Rename struct rcu_data .exp_dynticks_snap into .exp_watching_snap
  rcu: Rename struct rcu_data .dynticks_snap into .watching_snap
  rcu: Rename rcu_dynticks_zero_in_eqs() into rcu_watching_zero_in_eqs()
  rcu: Rename rcu_dynticks_in_eqs_since() into rcu_watching_snap_stopped_since()
  rcu: Rename rcu_dynticks_in_eqs() into rcu_watching_snap_in_eqs()
  rcu: Rename rcu_dynticks_eqs_online() into rcu_watching_online()
  context_tracking, rcu: Rename rcu_dynticks_curr_cpu_in_eqs() into rcu_is_watching_curr_cpu()
  context_tracking, rcu: Rename rcu_dynticks_task*() into rcu_task*()
  refscale: Constify struct ref_scale_ops
  ...
2024-09-18 07:52:24 +02:00

304 lines
8.0 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __LINUX_SMP_H
#define __LINUX_SMP_H
/*
* Generic SMP support
* Alan Cox. <alan@redhat.com>
*/
#include <linux/errno.h>
#include <linux/types.h>
#include <linux/list.h>
#include <linux/cpumask.h>
#include <linux/init.h>
#include <linux/smp_types.h>
typedef void (*smp_call_func_t)(void *info);
typedef bool (*smp_cond_func_t)(int cpu, void *info);
/*
* structure shares (partial) layout with struct irq_work
*/
struct __call_single_data {
struct __call_single_node node;
smp_call_func_t func;
void *info;
};
#define CSD_INIT(_func, _info) \
(struct __call_single_data){ .func = (_func), .info = (_info), }
/* Use __aligned() to avoid to use 2 cache lines for 1 csd */
typedef struct __call_single_data call_single_data_t
__aligned(sizeof(struct __call_single_data));
#define INIT_CSD(_csd, _func, _info) \
do { \
*(_csd) = CSD_INIT((_func), (_info)); \
} while (0)
/*
* Enqueue a llist_node on the call_single_queue; be very careful, read
* flush_smp_call_function_queue() in detail.
*/
extern void __smp_call_single_queue(int cpu, struct llist_node *node);
/* total number of cpus in this system (may exceed NR_CPUS) */
extern unsigned int total_cpus;
int smp_call_function_single(int cpuid, smp_call_func_t func, void *info,
int wait);
void on_each_cpu_cond_mask(smp_cond_func_t cond_func, smp_call_func_t func,
void *info, bool wait, const struct cpumask *mask);
int smp_call_function_single_async(int cpu, call_single_data_t *csd);
/*
* Cpus stopping functions in panic. All have default weak definitions.
* Architecture-dependent code may override them.
*/
void __noreturn panic_smp_self_stop(void);
void __noreturn nmi_panic_self_stop(struct pt_regs *regs);
void crash_smp_send_stop(void);
/*
* Call a function on all processors
*/
static inline void on_each_cpu(smp_call_func_t func, void *info, int wait)
{
on_each_cpu_cond_mask(NULL, func, info, wait, cpu_online_mask);
}
/**
* on_each_cpu_mask(): Run a function on processors specified by
* cpumask, which may include the local processor.
* @mask: The set of cpus to run on (only runs on online subset).
* @func: The function to run. This must be fast and non-blocking.
* @info: An arbitrary pointer to pass to the function.
* @wait: If true, wait (atomically) until function has completed
* on other CPUs.
*
* If @wait is true, then returns once @func has returned.
*
* You must not call this function with disabled interrupts or from a
* hardware interrupt handler or from a bottom half handler. The
* exception is that it may be used during early boot while
* early_boot_irqs_disabled is set.
*/
static inline void on_each_cpu_mask(const struct cpumask *mask,
smp_call_func_t func, void *info, bool wait)
{
on_each_cpu_cond_mask(NULL, func, info, wait, mask);
}
/*
* Call a function on each processor for which the supplied function
* cond_func returns a positive value. This may include the local
* processor. May be used during early boot while early_boot_irqs_disabled is
* set. Use local_irq_save/restore() instead of local_irq_disable/enable().
*/
static inline void on_each_cpu_cond(smp_cond_func_t cond_func,
smp_call_func_t func, void *info, bool wait)
{
on_each_cpu_cond_mask(cond_func, func, info, wait, cpu_online_mask);
}
/*
* Architecture specific boot CPU setup. Defined as empty weak function in
* init/main.c. Architectures can override it.
*/
void __init smp_prepare_boot_cpu(void);
#ifdef CONFIG_SMP
#include <linux/preempt.h>
#include <linux/compiler.h>
#include <linux/thread_info.h>
#include <asm/smp.h>
/*
* main cross-CPU interfaces, handles INIT, TLB flush, STOP, etc.
* (defined in asm header):
*/
/*
* stops all CPUs but the current one:
*/
extern void smp_send_stop(void);
/*
* sends a 'reschedule' event to another 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_cpu(cpu, _RET_IP_, NULL); \
arch_smp_send_reschedule(cpu); \
})
/*
* Prepare machine for booting other CPUs.
*/
extern void smp_prepare_cpus(unsigned int max_cpus);
/*
* Bring a CPU up
*/
extern int __cpu_up(unsigned int cpunum, struct task_struct *tidle);
/*
* Final polishing of CPUs
*/
extern void smp_cpus_done(unsigned int max_cpus);
/*
* Call a function on all other processors
*/
void smp_call_function(smp_call_func_t func, void *info, int wait);
void smp_call_function_many(const struct cpumask *mask,
smp_call_func_t func, void *info, bool wait);
int smp_call_function_any(const struct cpumask *mask,
smp_call_func_t func, void *info, int wait);
void kick_all_cpus_sync(void);
void wake_up_all_idle_cpus(void);
/*
* Generic and arch helpers
*/
void __init call_function_init(void);
void generic_smp_call_function_single_interrupt(void);
#define generic_smp_call_function_interrupt \
generic_smp_call_function_single_interrupt
extern unsigned int setup_max_cpus;
extern void __init setup_nr_cpu_ids(void);
extern void __init smp_init(void);
extern int __boot_cpu_id;
static inline int get_boot_cpu_id(void)
{
return __boot_cpu_id;
}
#else /* !SMP */
static inline void smp_send_stop(void) { }
/*
* These macros fold the SMP functionality into a single CPU system
*/
#define raw_smp_processor_id() 0
static inline void up_smp_call_function(smp_call_func_t func, void *info)
{
}
#define smp_call_function(func, info, wait) \
(up_smp_call_function(func, info))
static inline void smp_send_reschedule(int cpu) { }
#define smp_call_function_many(mask, func, info, wait) \
(up_smp_call_function(func, info))
static inline void call_function_init(void) { }
static inline int
smp_call_function_any(const struct cpumask *mask, smp_call_func_t func,
void *info, int wait)
{
return smp_call_function_single(0, func, info, wait);
}
static inline void kick_all_cpus_sync(void) { }
static inline void wake_up_all_idle_cpus(void) { }
#define setup_max_cpus 0
#ifdef CONFIG_UP_LATE_INIT
extern void __init up_late_init(void);
static inline void smp_init(void) { up_late_init(); }
#else
static inline void smp_init(void) { }
#endif
static inline int get_boot_cpu_id(void)
{
return 0;
}
#endif /* !SMP */
/**
* raw_processor_id() - get the current (unstable) CPU id
*
* For then you know what you are doing and need an unstable
* CPU id.
*/
/**
* smp_processor_id() - get the current (stable) CPU id
*
* This is the normal accessor to the CPU id and should be used
* whenever possible.
*
* The CPU id is stable when:
*
* - IRQs are disabled;
* - preemption is disabled;
* - the task is CPU affine.
*
* When CONFIG_DEBUG_PREEMPT; we verify these assumption and WARN
* when smp_processor_id() is used when the CPU id is not stable.
*/
/*
* Allow the architecture to differentiate between a stable and unstable read.
* For example, x86 uses an IRQ-safe asm-volatile read for the unstable but a
* regular asm read for the stable.
*/
#ifndef __smp_processor_id
#define __smp_processor_id() raw_smp_processor_id()
#endif
#ifdef CONFIG_DEBUG_PREEMPT
extern unsigned int debug_smp_processor_id(void);
# define smp_processor_id() debug_smp_processor_id()
#else
# define smp_processor_id() __smp_processor_id()
#endif
#define get_cpu() ({ preempt_disable(); __smp_processor_id(); })
#define put_cpu() preempt_enable()
/*
* Callback to arch code if there's nosmp or maxcpus=0 on the
* boot command line:
*/
extern void arch_disable_smp_support(void);
extern void arch_thaw_secondary_cpus_begin(void);
extern void arch_thaw_secondary_cpus_end(void);
void smp_setup_processor_id(void);
int smp_call_on_cpu(unsigned int cpu, int (*func)(void *), void *par,
bool phys);
/* SMP core functions */
int smpcfd_prepare_cpu(unsigned int cpu);
int smpcfd_dead_cpu(unsigned int cpu);
int smpcfd_dying_cpu(unsigned int cpu);
#ifdef CONFIG_CSD_LOCK_WAIT_DEBUG
bool csd_lock_is_stuck(void);
#else
static inline bool csd_lock_is_stuck(void) { return false; }
#endif
#endif /* __LINUX_SMP_H */