[PATCH] seccomp: Improve performance by optimizing memory barrier · wanghongzhe <hidden> · 2021-02-01
Re: [PATCH] seccomp: Improve performance by optimizing memory barrier · Andy Lutomirski <luto@amacapital.net> · 2021-02-01
RE: [PATCH] seccomp: Improve performance by optimizing memory barrier · Wanghongzhe (Hongzhe, EulerOS) <hidden> · 2021-02-02
[PATCH v1 1/1] Firstly, as Andy mentioned, this should be smp_rmb() instead of rmb(). considering that TSYNC is a cross-thread situation, and rmb() is a mandatory barrier which should not be used to control SMP effects, since mandatory barriers impose unnecessary overhead on both SMP and UP systems, as kernel Documentation said. · wanghongzhe <hidden> · 2021-02-02
Re: [PATCH v1 1/1] Firstly, as Andy mentioned, this should be smp_rmb() instead of rmb(). considering that TSYNC is a cross-thread situation, and rmb() is a mandatory barrier which should not be used to control SMP effects, since mandatory barriers impose unnecessary overhead on both SMP and UP systems, as kernel Documentation said. · Greg KH <gregkh@linuxfoundation.org> · 2021-02-02
Re: [PATCH v1 1/1] Firstly, as Andy mentioned, this should be smp_rmb() instead of rmb(). considering that TSYNC is a cross-thread situation, and rmb() is a mandatory barrier which should not be used to control SMP effects, since mandatory barriers impose unnecessary overhead on both SMP and UP systems, as kernel Documentation said. · Kees Cook <hidden> · 2021-02-02
RE: [PATCH v1 1/1] Firstly, as Andy mentioned, this should be smp_rmb() instead of rmb(). considering that TSYNC is a cross-thread situation, and rmb() is a mandatory barrier which should not be used to control SMP effects, since mandatory barriers imp... · Wanghongzhe (Hongzhe, EulerOS) <hidden> · 2021-02-04

Re: [PATCH v1 1/1] Firstly, as Andy mentioned, this should be smp_rmb() instead of rmb(). considering that TSYNC is a cross-thread situation, and rmb() is a mandatory barrier which should not be used to control SMP effects, since mandatory barriers impose unnecessary overhead on both SMP and UP systems, as kernel Documentation said.

From: Greg KH <gregkh@linuxfoundation.org>
Date: 2021-02-02 11:54:39
Also in: bpf, lkml

On Tue, Feb 02, 2021 at 06:13:07PM +0800, wanghongzhe wrote:

Secondly, the smp_rmb() should be put between reading SYSCALL_WORK_SECCOMP and reading

<snip>

Your subject line of the patch is a bit odd :)

`h`	back out one level
`j`	next message in thread
`k`	previous message in thread
`l`	drill in
`Esc`	close help / fold thread tree
`?`	toggle this help