1
0
Fork 0
alistair23-linux/include/linux/padata.h

171 lines
5.4 KiB
C
Raw Normal View History

/* SPDX-License-Identifier: GPL-2.0-only */
/*
* padata.h - header for the padata parallelization interface
*
* Copyright (C) 2008, 2009 secunet Security Networks AG
* Copyright (C) 2008, 2009 Steffen Klassert <steffen.klassert@secunet.com>
*/
#ifndef PADATA_H
#define PADATA_H
#include <linux/workqueue.h>
#include <linux/spinlock.h>
#include <linux/list.h>
#include <linux/notifier.h>
#include <linux/kobject.h>
#define PADATA_CPU_SERIAL 0x01
#define PADATA_CPU_PARALLEL 0x02
/**
* struct padata_priv - Embedded to the users data structure.
*
* @list: List entry, to attach to the padata lists.
* @pd: Pointer to the internal control structure.
* @cb_cpu: Callback cpu for serializatioon.
* @cpu: Cpu for parallelization.
* @seq_nr: Sequence number of the parallelized data object.
* @info: Used to pass information from the parallel to the serial function.
* @parallel: Parallel execution function.
* @serial: Serial complete function.
*/
struct padata_priv {
struct list_head list;
struct parallel_data *pd;
int cb_cpu;
int cpu;
padata: unbind parallel jobs from specific CPUs Padata binds the parallel part of a job to a single CPU and round-robins over all CPUs in the system for each successive job. Though the serial parts rely on per-CPU queues for correct ordering, they're not necessary for parallel work, and it improves performance to run the job locally on NUMA machines and let the scheduler pick the CPU within a node on a busy system. So, make the parallel workqueue unbound. Update the parallel workqueue's cpumask when the instance's parallel cpumask changes. Now that parallel jobs no longer run on max_active=1 workqueues, two or more parallel works that hash to the same CPU may run simultaneously, finish out of order, and so be serialized out of order. Prevent this by keeping the works sorted on the reorder list by sequence number and checking that in the reordering logic. padata_get_next becomes padata_find_next so it can be reused for the end of padata_reorder, where it's used to avoid uselessly queueing work when the next job by sequence number isn't finished yet but a later job that hashed to the same CPU has. The ENODATA case in padata_find_next no longer makes sense because parallel jobs aren't bound to specific CPUs. The EINPROGRESS case takes care of the scenario where a parallel job is potentially running on the same CPU as padata_find_next, and with only one error code left, just use NULL instead. Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: Lai Jiangshan <jiangshanlai@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: Tejun Heo <tj@kernel.org> Cc: linux-crypto@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2019-09-05 19:40:28 -06:00
unsigned int seq_nr;
int info;
void (*parallel)(struct padata_priv *padata);
void (*serial)(struct padata_priv *padata);
};
/**
* struct padata_list
*
* @list: List head.
* @lock: List lock.
*/
struct padata_list {
struct list_head list;
spinlock_t lock;
};
/**
* struct padata_serial_queue - The percpu padata serial queue
*
* @serial: List to wait for serialization after reordering.
* @work: work struct for serialization.
* @pd: Backpointer to the internal control structure.
*/
struct padata_serial_queue {
struct padata_list serial;
struct work_struct work;
struct parallel_data *pd;
};
/**
* struct padata_parallel_queue - The percpu padata parallel queue
*
* @parallel: List to wait for parallelization.
* @reorder: List to wait for reordering after parallel processing.
* @serial: List to wait for serialization after reordering.
* @pwork: work struct for parallelization.
* @swork: work struct for serialization.
* @work: work struct for parallelization.
* @num_obj: Number of objects that are processed by this cpu.
*/
struct padata_parallel_queue {
struct padata_list parallel;
struct padata_list reorder;
struct work_struct work;
atomic_t num_obj;
};
/**
* struct padata_cpumask - The cpumasks for the parallel/serial workers
*
* @pcpu: cpumask for the parallel workers.
* @cbcpu: cpumask for the serial (callback) workers.
*/
struct padata_cpumask {
cpumask_var_t pcpu;
cpumask_var_t cbcpu;
};
/**
* struct parallel_data - Internal control structure, covers everything
* that depends on the cpumask in use.
*
* @pinst: padata instance.
* @pqueue: percpu padata queues used for parallelization.
* @squeue: percpu padata queues used for serialuzation.
* @reorder_objects: Number of objects waiting in the reorder queues.
* @refcnt: Number of objects holding a reference on this parallel_data.
* @max_seq_nr: Maximal used sequence number.
padata: unbind parallel jobs from specific CPUs Padata binds the parallel part of a job to a single CPU and round-robins over all CPUs in the system for each successive job. Though the serial parts rely on per-CPU queues for correct ordering, they're not necessary for parallel work, and it improves performance to run the job locally on NUMA machines and let the scheduler pick the CPU within a node on a busy system. So, make the parallel workqueue unbound. Update the parallel workqueue's cpumask when the instance's parallel cpumask changes. Now that parallel jobs no longer run on max_active=1 workqueues, two or more parallel works that hash to the same CPU may run simultaneously, finish out of order, and so be serialized out of order. Prevent this by keeping the works sorted on the reorder list by sequence number and checking that in the reordering logic. padata_get_next becomes padata_find_next so it can be reused for the end of padata_reorder, where it's used to avoid uselessly queueing work when the next job by sequence number isn't finished yet but a later job that hashed to the same CPU has. The ENODATA case in padata_find_next no longer makes sense because parallel jobs aren't bound to specific CPUs. The EINPROGRESS case takes care of the scenario where a parallel job is potentially running on the same CPU as padata_find_next, and with only one error code left, just use NULL instead. Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: Lai Jiangshan <jiangshanlai@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: Tejun Heo <tj@kernel.org> Cc: linux-crypto@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2019-09-05 19:40:28 -06:00
* @processed: Number of already processed objects.
* @cpu: Next CPU to be processed.
* @cpumask: The cpumasks in use for parallel and serial workers.
* @reorder_work: work struct for reordering.
* @lock: Reorder lock.
*/
struct parallel_data {
struct padata_instance *pinst;
struct padata_parallel_queue __percpu *pqueue;
struct padata_serial_queue __percpu *squeue;
atomic_t reorder_objects;
atomic_t refcnt;
atomic_t seq_nr;
padata: unbind parallel jobs from specific CPUs Padata binds the parallel part of a job to a single CPU and round-robins over all CPUs in the system for each successive job. Though the serial parts rely on per-CPU queues for correct ordering, they're not necessary for parallel work, and it improves performance to run the job locally on NUMA machines and let the scheduler pick the CPU within a node on a busy system. So, make the parallel workqueue unbound. Update the parallel workqueue's cpumask when the instance's parallel cpumask changes. Now that parallel jobs no longer run on max_active=1 workqueues, two or more parallel works that hash to the same CPU may run simultaneously, finish out of order, and so be serialized out of order. Prevent this by keeping the works sorted on the reorder list by sequence number and checking that in the reordering logic. padata_get_next becomes padata_find_next so it can be reused for the end of padata_reorder, where it's used to avoid uselessly queueing work when the next job by sequence number isn't finished yet but a later job that hashed to the same CPU has. The ENODATA case in padata_find_next no longer makes sense because parallel jobs aren't bound to specific CPUs. The EINPROGRESS case takes care of the scenario where a parallel job is potentially running on the same CPU as padata_find_next, and with only one error code left, just use NULL instead. Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com> Cc: Herbert Xu <herbert@gondor.apana.org.au> Cc: Lai Jiangshan <jiangshanlai@gmail.com> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Steffen Klassert <steffen.klassert@secunet.com> Cc: Tejun Heo <tj@kernel.org> Cc: linux-crypto@vger.kernel.org Cc: linux-kernel@vger.kernel.org Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2019-09-05 19:40:28 -06:00
unsigned int processed;
int cpu;
struct padata_cpumask cpumask;
struct work_struct reorder_work;
spinlock_t lock ____cacheline_aligned;
};
/**
* struct padata_instance - The overall control structure.
*
* @cpu_notifier: cpu hotplug notifier.
* @parallel_wq: The workqueue used for parallel work.
* @serial_wq: The workqueue used for serial work.
* @pd: The internal control structure.
* @cpumask: User supplied cpumasks for parallel and serial works.
* @cpumask_change_notifier: Notifiers chain for user-defined notify
* callbacks that will be called when either @pcpu or @cbcpu
* or both cpumasks change.
* @kobj: padata instance kernel object.
* @lock: padata instance lock.
* @flags: padata flags.
*/
struct padata_instance {
struct hlist_node node;
struct workqueue_struct *parallel_wq;
struct workqueue_struct *serial_wq;
struct parallel_data *pd;
struct padata_cpumask cpumask;
struct blocking_notifier_head cpumask_change_notifier;
struct kobject kobj;
struct mutex lock;
u8 flags;
#define PADATA_INIT 1
#define PADATA_RESET 2
#define PADATA_INVALID 4
};
extern struct padata_instance *padata_alloc_possible(const char *name);
extern void padata_free(struct padata_instance *pinst);
extern int padata_do_parallel(struct padata_instance *pinst,
struct padata_priv *padata, int *cb_cpu);
extern void padata_do_serial(struct padata_priv *padata);
extern int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type,
cpumask_var_t cpumask);
extern int padata_start(struct padata_instance *pinst);
extern void padata_stop(struct padata_instance *pinst);
extern int padata_register_cpumask_notifier(struct padata_instance *pinst,
struct notifier_block *nblock);
extern int padata_unregister_cpumask_notifier(struct padata_instance *pinst,
struct notifier_block *nblock);
#endif