diff options
author | Daniel Jordan <daniel.m.jordan@oracle.com> | 2020-06-03 15:59:39 -0700 |
---|---|---|
committer | Linus Torvalds <torvalds@linux-foundation.org> | 2020-06-03 20:09:45 -0700 |
commit | 4611ce22468895acd61fee9ac1da810d60617d9a (patch) | |
tree | e5f71eeb19df9a835455734e6ec059433bf5854e /include | |
parent | f1b192b117cd418bacf42a9583d7a01855a18fe5 (diff) | |
download | linux-4611ce22468895acd61fee9ac1da810d60617d9a.tar.bz2 |
padata: allocate work structures for parallel jobs from a pool
padata allocates per-CPU, per-instance work structs for parallel jobs. A
do_parallel call assigns a job to a sequence number and hashes the number
to a CPU, where the job will eventually run using the corresponding work.
This approach fit with how padata used to bind a job to each CPU
round-robin, makes less sense after commit bfde23ce200e6 ("padata: unbind
parallel jobs from specific CPUs") because a work isn't bound to a
particular CPU anymore, and isn't needed at all for multithreaded jobs
because they don't have sequence numbers.
Replace the per-CPU works with a preallocated pool, which allows sharing
them between existing padata users and the upcoming multithreaded user.
The pool will also facilitate setting NUMA-aware concurrency limits with
later users.
The pool is sized according to the number of possible CPUs. With this
limit, MAX_OBJ_NUM no longer makes sense, so remove it.
If the global pool is exhausted, a parallel job is run in the current task
instead to throttle a system trying to do too much in parallel.
Signed-off-by: Daniel Jordan <daniel.m.jordan@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Tested-by: Josh Triplett <josh@joshtriplett.org>
Cc: Alexander Duyck <alexander.h.duyck@linux.intel.com>
Cc: Alex Williamson <alex.williamson@redhat.com>
Cc: Dan Williams <dan.j.williams@intel.com>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Herbert Xu <herbert@gondor.apana.org.au>
Cc: Jason Gunthorpe <jgg@ziepe.ca>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Pavel Machek <pavel@ucw.cz>
Cc: Pavel Tatashin <pasha.tatashin@soleen.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Robert Elliott <elliott@hpe.com>
Cc: Shile Zhang <shile.zhang@linux.alibaba.com>
Cc: Steffen Klassert <steffen.klassert@secunet.com>
Cc: Steven Sistare <steven.sistare@oracle.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Zi Yan <ziy@nvidia.com>
Link: http://lkml.kernel.org/r/20200527173608.2885243-4-daniel.m.jordan@oracle.com
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'include')
-rw-r--r-- | include/linux/padata.h | 8 |
1 files changed, 1 insertions, 7 deletions
diff --git a/include/linux/padata.h b/include/linux/padata.h index d50bd1a7756f..b4da88f8588c 100644 --- a/include/linux/padata.h +++ b/include/linux/padata.h @@ -24,7 +24,6 @@ * @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. @@ -34,7 +33,6 @@ struct padata_priv { struct list_head list; struct parallel_data *pd; int cb_cpu; - int cpu; unsigned int seq_nr; int info; void (*parallel)(struct padata_priv *padata); @@ -68,15 +66,11 @@ struct padata_serial_queue { /** * struct padata_parallel_queue - The percpu padata parallel queue * - * @parallel: List to wait for parallelization. * @reorder: List to wait for reordering after parallel processing. - * @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; }; @@ -111,7 +105,7 @@ struct parallel_data { struct padata_parallel_queue __percpu *pqueue; struct padata_serial_queue __percpu *squeue; atomic_t refcnt; - atomic_t seq_nr; + unsigned int seq_nr; unsigned int processed; int cpu; struct padata_cpumask cpumask; |