From: Jan Beulich <jbeulich@suse.com>
To: Carlo Nonato <carlo.nonato@minervasys.tech>
Cc: andrea.bastoni@minervasys.tech,
Andrew Cooper <andrew.cooper3@citrix.com>,
George Dunlap <george.dunlap@citrix.com>,
Julien Grall <julien@xen.org>,
Stefano Stabellini <sstabellini@kernel.org>,
Marco Solieri <marco.solieri@minervasys.tech>,
xen-devel@lists.xenproject.org
Subject: Re: [PATCH v8 01/13] xen/common: add cache coloring common code
Date: Mon, 6 May 2024 13:54:42 +0200 [thread overview]
Message-ID: <bcfc0da1-5d8a-4e14-be34-89876d668b86@suse.com> (raw)
In-Reply-To: <20240502165533.319988-2-carlo.nonato@minervasys.tech>
On 02.05.2024 18:55, Carlo Nonato wrote:
> --- a/xen/common/Kconfig
> +++ b/xen/common/Kconfig
> @@ -71,6 +71,9 @@ config HAS_IOPORTS
> config HAS_KEXEC
> bool
>
> +config HAS_LLC_COLORING
> + bool
> +
> config HAS_PIRQ
> bool
>
> @@ -513,4 +516,23 @@ config TRACEBUFFER
> to be collected at run time for debugging or performance analysis.
> Memory and execution overhead when not active is minimal.
>
> +config LLC_COLORING
> + bool "Last Level Cache (LLC) coloring" if EXPERT
> + depends on HAS_LLC_COLORING
> + depends on !NUMA
> +
> +config MAX_LLC_COLORS_ORDER
May I ask that you consider dropping MAX_ from here (but keeping "maximum"
in prompt and text), thus ...
> --- /dev/null
> +++ b/xen/common/llc-coloring.c
> @@ -0,0 +1,111 @@
> +/* SPDX-License-Identifier: GPL-2.0-only */
> +/*
> + * Last Level Cache (LLC) coloring common code
> + *
> + * Copyright (C) 2022 Xilinx Inc.
> + */
> +#include <xen/keyhandler.h>
> +#include <xen/llc-coloring.h>
> +#include <xen/param.h>
> +
> +#define NR_LLC_COLORS (1 << CONFIG_MAX_LLC_COLORS_ORDER)
... making this look less strange?
To match up with e.g. max_nr_colors you may also want to use 1U here.
> +void __init llc_coloring_init(void)
> +{
> + unsigned int way_size;
> +
> + if ( llc_size && llc_nr_ways )
> + {
> + llc_coloring_enabled = true;
> + way_size = llc_size / llc_nr_ways;
> + }
> + else if ( !llc_coloring_enabled )
> + return;
> + else
> + {
> + way_size = get_llc_way_size();
> + if ( !way_size )
> + panic("LLC probing failed and 'llc-size' or 'llc-nr-ways' missing\n");
Since you won't accept way_size == 0 here, how about it ending up zero in
the initial if()'s body? Even more, don't you want to demand
llc_size % llc_nr_ways == 0 there (thus, together with the enclosing
condition, guaranteeing way_size != 0)?
> + }
> +
> + /*
> + * The maximum number of colors must be a power of 2 in order to correctly
> + * map them to bits of an address.
> + */
> + max_nr_colors = way_size >> PAGE_SHIFT;
> +
> + if ( max_nr_colors & (max_nr_colors - 1) )
> + panic("Number of LLC colors (%u) isn't a power of 2\n", max_nr_colors);
> +
> + if ( max_nr_colors > NR_LLC_COLORS )
> + {
> + printk(XENLOG_WARNING
> + "Number of LLC colors (%u) too big. Using configured max %u\n",
> + max_nr_colors, NR_LLC_COLORS);
> + max_nr_colors = NR_LLC_COLORS;
> + } else if ( max_nr_colors < 2 )
> + panic("Number of LLC colors %u < 2\n", max_nr_colors);
Ah, here's a check guaranteeing at least the first of the two things asked
about above.
Jan
next prev parent reply other threads:[~2024-05-06 11:55 UTC|newest]
Thread overview: 26+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-05-02 16:55 [PATCH v8 00/13] Arm cache coloring Carlo Nonato
2024-05-02 16:55 ` [PATCH v8 01/13] xen/common: add cache coloring common code Carlo Nonato
2024-05-06 11:54 ` Jan Beulich [this message]
2024-05-06 15:53 ` Carlo Nonato
2024-05-02 16:55 ` [PATCH v8 02/13] xen/arm: add initial support for LLC coloring on arm64 Carlo Nonato
2024-05-02 16:55 ` [PATCH v8 03/13] xen/arm: permit non direct-mapped Dom0 construction Carlo Nonato
2024-05-02 16:55 ` [PATCH v8 04/13] xen/arm: add Dom0 cache coloring support Carlo Nonato
2024-05-06 12:01 ` Jan Beulich
2024-05-06 15:53 ` Carlo Nonato
2024-05-14 7:02 ` Jan Beulich
2024-05-02 16:55 ` [PATCH v8 05/13] xen: extend domctl interface for cache coloring Carlo Nonato
2024-05-06 12:05 ` Jan Beulich
2024-05-02 16:55 ` [PATCH v8 06/13] tools: add support for cache coloring configuration Carlo Nonato
2024-07-01 12:29 ` Anthony PERARD
2024-05-02 16:55 ` [PATCH v8 07/13] xen/arm: add support for cache coloring configuration via device-tree Carlo Nonato
2024-05-06 12:11 ` Jan Beulich
2024-05-02 16:55 ` [PATCH v8 08/13] xen/page_alloc: introduce preserved page flags macro Carlo Nonato
2024-05-06 12:22 ` Jan Beulich
2024-05-06 15:54 ` Carlo Nonato
2024-05-02 16:55 ` [PATCH v8 09/13] xen: add cache coloring allocator for domains Carlo Nonato
2024-05-06 12:46 ` Jan Beulich
2024-05-02 16:55 ` [PATCH v8 10/13] xen/arm: use domain memory to allocate p2m page tables Carlo Nonato
2024-05-02 16:55 ` [PATCH v8 11/13] xen/arm: add Xen cache colors command line parameter Carlo Nonato
2024-05-06 13:24 ` Jan Beulich
2024-05-02 16:55 ` [PATCH v8 12/13] xen/arm: make consider_modules() available for xen relocation Carlo Nonato
2024-05-02 16:55 ` [PATCH v8 13/13] xen/arm: add cache coloring support for Xen Carlo Nonato
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=bcfc0da1-5d8a-4e14-be34-89876d668b86@suse.com \
--to=jbeulich@suse.com \
--cc=andrea.bastoni@minervasys.tech \
--cc=andrew.cooper3@citrix.com \
--cc=carlo.nonato@minervasys.tech \
--cc=george.dunlap@citrix.com \
--cc=julien@xen.org \
--cc=marco.solieri@minervasys.tech \
--cc=sstabellini@kernel.org \
--cc=xen-devel@lists.xenproject.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.