From eb52286634f042432ec775077a73334603a1c6e4 Mon Sep 17 00:00:00 2001 From: "Gang Li Subject: padata: dispatch works on" Date: Wed, 6 Mar 2024 13:04:17 -0800 Subject: Author: Gang Li padata: dispatch works on different nodes Date: Thu, 22 Feb 2024 22:04:17 +0800 When a group of tasks that access different nodes are scheduled on the same node, they may encounter bandwidth bottlenecks and access latency. Thus, numa_aware flag is introduced here, allowing tasks to be distributed across different nodes to fully utilize the advantage of multi-node systems. Link: https://lkml.kernel.org/r/20240222140422.393911-5-gang.li@linux.dev Signed-off-by: Gang Li Tested-by: David Rientjes Reviewed-by: Muchun Song Reviewed-by: Tim Chen Cc: Alexey Dobriyan Cc: Daniel Jordan Cc: David Hildenbrand Cc: Jane Chu Cc: Mike Kravetz Cc: Paul E. McKenney Cc: Randy Dunlap Cc: Steffen Klassert Signed-off-by: Andrew Morton --- include/linux/padata.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include/linux/padata.h') diff --git a/include/linux/padata.h b/include/linux/padata.h index 495b16b6b4d7..8f418711351b 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -137,6 +137,7 @@ struct padata_shell { * appropriate for one worker thread to do at once. * @max_threads: Max threads to use for the job, actual number may be less * depending on task size and minimum chunk size. + * @numa_aware: Distribute jobs to different nodes with CPU in a round robin fashion. */ struct padata_mt_job { void (*thread_fn)(unsigned long start, unsigned long end, void *arg); @@ -146,6 +147,7 @@ struct padata_mt_job { unsigned long align; unsigned long min_chunk; int max_threads; + bool numa_aware; }; /** -- cgit v1.2.3 From bd5ed02e23958cb56d0f5a90ebe620c8b47dab47 Mon Sep 17 00:00:00 2001 From: Gang Li Date: Thu, 22 Feb 2024 22:04:18 +0800 Subject: padata: downgrade padata_do_multithreaded to serial execution for non-SMP hugetlb parallelization depends on PADATA, and PADATA depends on SMP. PADATA consists of two distinct functionality: One part is padata_do_multithreaded which disregards order and simply divides tasks into several groups for parallel execution. Hugetlb init parallelization depends on padata_do_multithreaded. The other part is composed of a set of APIs that, while handling data in an out-of-order parallel manner, can eventually return the data with ordered sequence. Currently Only `crypto/pcrypt.c` use them. All users of PADATA of non-SMP case currently only use padata_do_multithreaded. It is easy to implement a serial one in include/linux/padata.h. And it is not necessary to implement another functionality unless the only user of crypto/pcrypt.c does not depend on SMP in the future. Link: https://lkml.kernel.org/r/20240222140422.393911-6-gang.li@linux.dev Signed-off-by: Gang Li Tested-by: Paul E. McKenney Acked-by: Daniel Jordan Cc: David Hildenbrand Cc: David Rientjes Cc: Jane Chu Cc: Muchun Song Cc: Randy Dunlap Cc: Steffen Klassert Cc: Tim Chen Cc: Alexey Dobriyan Cc: Mike Kravetz Signed-off-by: Andrew Morton --- include/linux/padata.h | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) (limited to 'include/linux/padata.h') diff --git a/include/linux/padata.h b/include/linux/padata.h index 8f418711351b..0146daf34430 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -180,10 +180,6 @@ struct padata_instance { #ifdef CONFIG_PADATA extern void __init padata_init(void); -#else -static inline void __init padata_init(void) {} -#endif - extern struct padata_instance *padata_alloc(const char *name); extern void padata_free(struct padata_instance *pinst); extern struct padata_shell *padata_alloc_shell(struct padata_instance *pinst); @@ -194,4 +190,12 @@ extern void padata_do_serial(struct padata_priv *padata); extern void __init padata_do_multithreaded(struct padata_mt_job *job); extern int padata_set_cpumask(struct padata_instance *pinst, int cpumask_type, cpumask_var_t cpumask); +#else +static inline void __init padata_init(void) {} +static inline void __init padata_do_multithreaded(struct padata_mt_job *job) +{ + job->thread_fn(job->start, job->start + job->size, job->fn_arg); +} +#endif + #endif -- cgit v1.2.3