Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1658331

Re: [PATCH v2] arch/sparc: support NR_CPUS = 4096

From David Miller <davem@davemloft.net>
Newsgroups linux.kernel
Subject Re: [PATCH v2] arch/sparc: support NR_CPUS = 4096
Date 2017-06-06 05:30 +0200
Message-ID <tPdlT-3jW-3@gated-at.bofh.it> (permalink)
References <tP98C-rI-21@gated-at.bofh.it> <tPb0M-1BU-83@gated-at.bofh.it> <tPd2y-3dl-7@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw

From: jane.chu@oracle.com
Date: Mon, 5 Jun 2017 20:03:28 -0700

> On sun4v sparc, it looks like kzalloc(64, GFP_KERNEL) ends up
> allocating from kmalloc_caches[6] - a 64-byte kmem-cache allocated
> by kmem_cache_init() with SLAB_HWCACHE_ALIGN flag set, so it's in
> l3-cache-line-size alignment, i.e. 64byte.  I printed out the
> 'mondo' pa and verified that.

Please check this, because that is an implementation detail.  We have
three SLAB allocators.

For example, if the user enables SLOB, I bet you don't get that
alignment.

The only thing we are universally guaranteed is ARCH_KMALLOC_MINALIGN.

Please implement this properly, rather than relying upon things like
the above.

Thank you.

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[PATCH v2] arch/sparc: support NR_CPUS = 4096 Jane Chu <jane.chu@oracle.com> - 2017-06-06 01:00 +0200
  Re: [PATCH v2] arch/sparc: support NR_CPUS = 4096 David Miller <davem@davemloft.net> - 2017-06-06 03:00 +0200
    Re: [PATCH v2] arch/sparc: support NR_CPUS = 4096 jane.chu@oracle.com - 2017-06-06 05:10 +0200
      Re: [PATCH v2] arch/sparc: support NR_CPUS = 4096 David Miller <davem@davemloft.net> - 2017-06-06 05:30 +0200
        Re: [PATCH v2] arch/sparc: support NR_CPUS = 4096 jane.chu@oracle.com - 2017-06-06 19:10 +0200

csiph-web