For multithreaded jobs the computed chunk size is rounded up by the
caller-specified alignment. However, the number of worker threads to
use is computed using the minimum chunk size without taking alignment
into account. A sufficiently large alignment value can result in too
many worker threads being allocated for the job.
Signed-off-by: Anthony Yznaga <[email protected]>
---
kernel/padata.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/kernel/padata.c b/kernel/padata.c
index e007b8a4b738..4abc536ecdb1 100644
--- a/kernel/padata.c
+++ b/kernel/padata.c
@@ -491,7 +491,7 @@ void __init padata_do_multithreaded(struct padata_mt_job *job)
return;
/* Ensure at least one thread when size < min_chunk. */
- nworks = max(job->size / job->min_chunk, 1ul);
+ nworks = max(job->size / max(job->min_chunk, job->align), 1ul);
nworks = min(nworks, job->max_threads);
if (nworks == 1) {
--
1.8.3.1
On Wed, Feb 22, 2023 at 04:33:12PM -0800, Anthony Yznaga wrote:
> For multithreaded jobs the computed chunk size is rounded up by the
> caller-specified alignment. However, the number of worker threads to
> use is computed using the minimum chunk size without taking alignment
> into account. A sufficiently large alignment value can result in too
> many worker threads being allocated for the job.
>
> Signed-off-by: Anthony Yznaga <[email protected]>
No effect for now since the page init code uses the same align and
min_chunk, but it protects future users from this problem so
Acked-by: Daniel Jordan <[email protected]>
Thanks.
> ---
> kernel/padata.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
>
> diff --git a/kernel/padata.c b/kernel/padata.c
> index e007b8a4b738..4abc536ecdb1 100644
> --- a/kernel/padata.c
> +++ b/kernel/padata.c
> @@ -491,7 +491,7 @@ void __init padata_do_multithreaded(struct padata_mt_job *job)
> return;
>
> /* Ensure at least one thread when size < min_chunk. */
> - nworks = max(job->size / job->min_chunk, 1ul);
> + nworks = max(job->size / max(job->min_chunk, job->align), 1ul);
> nworks = min(nworks, job->max_threads);
>
> if (nworks == 1) {
> --
> 1.8.3.1
>
Anthony Yznaga <[email protected]> wrote:
> For multithreaded jobs the computed chunk size is rounded up by the
> caller-specified alignment. However, the number of worker threads to
> use is computed using the minimum chunk size without taking alignment
> into account. A sufficiently large alignment value can result in too
> many worker threads being allocated for the job.
>
> Signed-off-by: Anthony Yznaga <[email protected]>
> ---
> kernel/padata.c | 2 +-
> 1 file changed, 1 insertion(+), 1 deletion(-)
Patch applied. Thanks.
--
Email: Herbert Xu <[email protected]>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt