mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-26 05:30:53 +07:00
46c498c2cd
commit 14e568e78 (stop_machine: Use smpboot threads) introduced the
following regression:
Before this commit the stopper enabled bit was set in the online
notifier.
CPU0 CPU1
cpu_up
cpu online
hotplug_notifier(ONLINE)
stopper(CPU1)->enabled = true;
...
stop_machine()
The conversion to smpboot threads moved the enablement to the wakeup
path of the parked thread. The majority of users seem to have the
following working order:
CPU0 CPU1
cpu_up
cpu online
unpark_threads()
wakeup(stopper[CPU1])
....
stopper thread runs
stopper(CPU1)->enabled = true;
stop_machine()
But Konrad and Sander have observed:
CPU0 CPU1
cpu_up
cpu online
unpark_threads()
wakeup(stopper[CPU1])
....
stop_machine()
stopper thread runs
stopper(CPU1)->enabled = true;
Now the stop machinery kicks CPU0 into the stop loop, where it gets
stuck forever because the queue code saw stopper(CPU1)->enabled ==
false, so CPU0 waits for CPU1 to enter stomp_machine, but the CPU1
stopper work got discarded due to enabled == false.
Add a pre_unpark function to the smpboot thread descriptor and call it
before waking the thread.
This fixes the problem at hand, but the stop_machine code should be
more robust. The stopper->enabled flag smells fishy at best.
Thanks to Konrad for going through a loop of debug patches and
providing the information to decode this issue.
Reported-and-tested-by: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Reported-and-tested-by: Sander Eikelenboom <linux@eikelenboom.it>
Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Cc: Rusty Russell <rusty@rustcorp.com.au>
Link: http://lkml.kernel.org/r/alpine.LFD.2.02.1302261843240.22263@ionos
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
53 lines
1.9 KiB
C
53 lines
1.9 KiB
C
#ifndef _LINUX_SMPBOOT_H
|
|
#define _LINUX_SMPBOOT_H
|
|
|
|
#include <linux/types.h>
|
|
|
|
struct task_struct;
|
|
/* Cookie handed to the thread_fn*/
|
|
struct smpboot_thread_data;
|
|
|
|
/**
|
|
* struct smp_hotplug_thread - CPU hotplug related thread descriptor
|
|
* @store: Pointer to per cpu storage for the task pointers
|
|
* @list: List head for core management
|
|
* @thread_should_run: Check whether the thread should run or not. Called with
|
|
* preemption disabled.
|
|
* @thread_fn: The associated thread function
|
|
* @create: Optional setup function, called when the thread gets
|
|
* created (Not called from the thread context)
|
|
* @setup: Optional setup function, called when the thread gets
|
|
* operational the first time
|
|
* @cleanup: Optional cleanup function, called when the thread
|
|
* should stop (module exit)
|
|
* @park: Optional park function, called when the thread is
|
|
* parked (cpu offline)
|
|
* @unpark: Optional unpark function, called when the thread is
|
|
* unparked (cpu online)
|
|
* @pre_unpark: Optional unpark function, called before the thread is
|
|
* unparked (cpu online). This is not guaranteed to be
|
|
* called on the target cpu of the thread. Careful!
|
|
* @selfparking: Thread is not parked by the park function.
|
|
* @thread_comm: The base name of the thread
|
|
*/
|
|
struct smp_hotplug_thread {
|
|
struct task_struct __percpu **store;
|
|
struct list_head list;
|
|
int (*thread_should_run)(unsigned int cpu);
|
|
void (*thread_fn)(unsigned int cpu);
|
|
void (*create)(unsigned int cpu);
|
|
void (*setup)(unsigned int cpu);
|
|
void (*cleanup)(unsigned int cpu, bool online);
|
|
void (*park)(unsigned int cpu);
|
|
void (*unpark)(unsigned int cpu);
|
|
void (*pre_unpark)(unsigned int cpu);
|
|
bool selfparking;
|
|
const char *thread_comm;
|
|
};
|
|
|
|
int smpboot_register_percpu_thread(struct smp_hotplug_thread *plug_thread);
|
|
void smpboot_unregister_percpu_thread(struct smp_hotplug_thread *plug_thread);
|
|
int smpboot_thread_schedule(void);
|
|
|
|
#endif
|