zfs/module/spl/spl-thread.c

164 lines
4.3 KiB
C
Raw Normal View History

/*
* Copyright (C) 2007-2010 Lawrence Livermore National Security, LLC.
* Copyright (C) 2007 The Regents of the University of California.
* Produced at Lawrence Livermore National Laboratory (cf, DISCLAIMER).
* Written by Brian Behlendorf <behlendorf1@llnl.gov>.
* UCRL-CODE-235197
*
* This file is part of the SPL, Solaris Porting Layer.
* For details, see <http://zfsonlinux.org/>.
*
* The SPL is free software; you can redistribute it and/or modify it
* under the terms of the GNU General Public License as published by the
* Free Software Foundation; either version 2 of the License, or (at your
* option) any later version.
*
* The SPL is distributed in the hope that it will be useful, but WITHOUT
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
* for more details.
*
* You should have received a copy of the GNU General Public License along
* with the SPL. If not, see <http://www.gnu.org/licenses/>.
*
* Solaris Porting Layer (SPL) Thread Implementation.
*/
#include <sys/thread.h>
#include <sys/kmem.h>
Add Thread Specific Data (TSD) Implementation Thread specific data has implemented using a hash table, this avoids the need to add a member to the task structure and allows maximum portability between kernels. This implementation has been optimized to keep the tsd_set() and tsd_get() times as small as possible. The majority of the entries in the hash table are for specific tsd entries. These entries are hashed by the product of their key and pid because by design the key and pid are guaranteed to be unique. Their product also has the desirable properly that it will be uniformly distributed over the hash bins providing neither the pid nor key is zero. Under linux the zero pid is always the init process and thus won't be used, and this implementation is careful to never to assign a zero key. By default the hash table is sized to 512 bins which is expected to be sufficient for light to moderate usage of thread specific data. The hash table contains two additional type of entries. They first type is entry is called a 'key' entry and it is added to the hash during tsd_create(). It is used to store the address of the destructor function and it is used as an anchor point. All tsd entries which use the same key will be linked to this entry. This is used during tsd_destory() to quickly call the destructor function for all tsd associated with the key. The 'key' entry may be looked up with tsd_hash_search() by passing the key you wish to lookup and DTOR_PID constant as the pid. The second type of entry is called a 'pid' entry and it is added to the hash the first time a process set a key. The 'pid' entry is also used as an anchor and all tsd for the process will be linked to it. This list is using during tsd_exit() to ensure all registered destructors are run for the process. The 'pid' entry may be looked up with tsd_hash_search() by passing the PID_KEY constant as the key, and the process pid. Note that tsd_exit() is called by thread_exit() so if your using the Solaris thread API you should not need to call tsd_exit() directly.
2010-11-30 17:51:46 +00:00
#include <sys/tsd.h>
#include <sys/simd.h>
/*
* Thread interfaces
*/
typedef struct thread_priv_s {
unsigned long tp_magic; /* Magic */
int tp_name_size; /* Name size */
char *tp_name; /* Name (without _thread suffix) */
void (*tp_func)(void *); /* Registered function */
void *tp_args; /* Args to be passed to function */
size_t tp_len; /* Len to be passed to function */
int tp_state; /* State to start thread at */
pri_t tp_pri; /* Priority to start threat at */
} thread_priv_t;
static int
thread_generic_wrapper(void *arg)
{
thread_priv_t *tp = (thread_priv_t *)arg;
void (*func)(void *);
void *args;
ASSERT(tp->tp_magic == TP_MAGIC);
func = tp->tp_func;
args = tp->tp_args;
set_current_state(tp->tp_state);
set_user_nice((kthread_t *)current, PRIO_TO_NICE(tp->tp_pri));
Linux 5.0 compat: SIMD compatibility Restore the SIMD optimization for 4.19.38 LTS, 4.14.120 LTS, and 5.0 and newer kernels. This is accomplished by leveraging the fact that by definition dedicated kernel threads never need to concern themselves with saving and restoring the user FPU state. Therefore, they may use the FPU as long as we can guarantee user tasks always restore their FPU state before context switching back to user space. For the 5.0 and 5.1 kernels disabling preemption and local interrupts is sufficient to allow the FPU to be used. All non-kernel threads will restore the preserved user FPU state. For 5.2 and latter kernels the user FPU state restoration will be skipped if the kernel determines the registers have not changed. Therefore, for these kernels we need to perform the additional step of saving and restoring the FPU registers. Invalidating the per-cpu global tracking the FPU state would force a restore but that functionality is private to the core x86 FPU implementation and unavailable. In practice, restricting SIMD to kernel threads is not a major restriction for ZFS. The vast majority of SIMD operations are already performed by the IO pipeline. The remaining cases are relatively infrequent and can be handled by the generic code without significant impact. The two most noteworthy cases are: 1) Decrypting the wrapping key for an encrypted dataset, i.e. `zfs load-key`. All other encryption and decryption operations will use the SIMD optimized implementations. 2) Generating the payload checksums for a `zfs send` stream. In order to avoid making any changes to the higher layers of ZFS all of the `*_get_ops()` functions were updated to take in to consideration the calling context. This allows for the fastest implementation to be used as appropriate (see kfpu_allowed()). The only other notable instance of SIMD operations being used outside a kernel thread was at module load time. This code was moved in to a taskq in order to accommodate the new kernel thread restriction. Finally, a few other modifications were made in order to further harden this code and facilitate testing. They include updating each implementations operations structure to be declared as a constant. And allowing "cycle" to be set when selecting the preferred ops in the kernel as well as user space. Reviewed-by: Tony Hutter <hutter2@llnl.gov> Signed-off-by: Brian Behlendorf <behlendorf1@llnl.gov> Closes #8754 Closes #8793 Closes #8965
2019-07-12 16:31:20 +00:00
kfpu_initialize();
kmem_free(tp->tp_name, tp->tp_name_size);
kmem_free(tp, sizeof (thread_priv_t));
if (func)
func(args);
return (0);
}
void
__thread_exit(void)
{
Add Thread Specific Data (TSD) Implementation Thread specific data has implemented using a hash table, this avoids the need to add a member to the task structure and allows maximum portability between kernels. This implementation has been optimized to keep the tsd_set() and tsd_get() times as small as possible. The majority of the entries in the hash table are for specific tsd entries. These entries are hashed by the product of their key and pid because by design the key and pid are guaranteed to be unique. Their product also has the desirable properly that it will be uniformly distributed over the hash bins providing neither the pid nor key is zero. Under linux the zero pid is always the init process and thus won't be used, and this implementation is careful to never to assign a zero key. By default the hash table is sized to 512 bins which is expected to be sufficient for light to moderate usage of thread specific data. The hash table contains two additional type of entries. They first type is entry is called a 'key' entry and it is added to the hash during tsd_create(). It is used to store the address of the destructor function and it is used as an anchor point. All tsd entries which use the same key will be linked to this entry. This is used during tsd_destory() to quickly call the destructor function for all tsd associated with the key. The 'key' entry may be looked up with tsd_hash_search() by passing the key you wish to lookup and DTOR_PID constant as the pid. The second type of entry is called a 'pid' entry and it is added to the hash the first time a process set a key. The 'pid' entry is also used as an anchor and all tsd for the process will be linked to it. This list is using during tsd_exit() to ensure all registered destructors are run for the process. The 'pid' entry may be looked up with tsd_hash_search() by passing the PID_KEY constant as the key, and the process pid. Note that tsd_exit() is called by thread_exit() so if your using the Solaris thread API you should not need to call tsd_exit() directly.
2010-11-30 17:51:46 +00:00
tsd_exit();
complete_and_exit(NULL, 0);
/* Unreachable */
}
EXPORT_SYMBOL(__thread_exit);
/*
* thread_create() may block forever if it cannot create a thread or
* allocate memory. This is preferable to returning a NULL which Solaris
* style callers likely never check for... since it can't fail.
*/
kthread_t *
__thread_create(caddr_t stk, size_t stksize, thread_func_t func,
const char *name, void *args, size_t len, proc_t *pp, int state, pri_t pri)
{
thread_priv_t *tp;
struct task_struct *tsk;
char *p;
/* Option pp is simply ignored */
/* Variable stack size unsupported */
ASSERT(stk == NULL);
tp = kmem_alloc(sizeof (thread_priv_t), KM_PUSHPAGE);
if (tp == NULL)
return (NULL);
tp->tp_magic = TP_MAGIC;
tp->tp_name_size = strlen(name) + 1;
tp->tp_name = kmem_alloc(tp->tp_name_size, KM_PUSHPAGE);
if (tp->tp_name == NULL) {
kmem_free(tp, sizeof (thread_priv_t));
return (NULL);
}
strncpy(tp->tp_name, name, tp->tp_name_size);
/*
* Strip trailing "_thread" from passed name which will be the func
* name since the exposed API has no parameter for passing a name.
*/
p = strstr(tp->tp_name, "_thread");
if (p)
p[0] = '\0';
tp->tp_func = func;
tp->tp_args = args;
tp->tp_len = len;
tp->tp_state = state;
tp->tp_pri = pri;
tsk = spl_kthread_create(thread_generic_wrapper, (void *)tp,
"%s", tp->tp_name);
if (IS_ERR(tsk))
return (NULL);
wake_up_process(tsk);
return ((kthread_t *)tsk);
}
EXPORT_SYMBOL(__thread_create);
/*
* spl_kthread_create - Wrapper providing pre-3.13 semantics for
* kthread_create() in which it is not killable and less likely
* to return -ENOMEM.
*/
struct task_struct *
spl_kthread_create(int (*func)(void *), void *data, const char namefmt[], ...)
{
struct task_struct *tsk;
va_list args;
char name[TASK_COMM_LEN];
va_start(args, namefmt);
vsnprintf(name, sizeof (name), namefmt, args);
va_end(args);
do {
tsk = kthread_create(func, data, "%s", name);
if (IS_ERR(tsk)) {
if (signal_pending(current)) {
clear_thread_flag(TIF_SIGPENDING);
continue;
}
if (PTR_ERR(tsk) == -ENOMEM)
continue;
return (NULL);
} else {
return (tsk);
}
} while (1);
}
EXPORT_SYMBOL(spl_kthread_create);