From: Ingo Molnar <mingo@kernel.org>
To: Thomas Gleixner <tglx@linutronix.de>
Cc: LKML <linux-kernel@vger.kernel.org>,
x86@kernel.org, Linus Torvalds <torvalds@linuxfoundation.org>,
Andy Lutomirski <luto@kernel.org>,
Stephen Hemminger <stephen@networkplumber.org>,
Willy Tarreau <w@1wt.eu>, Juergen Gross <jgross@suse.com>,
Sean Christopherson <sean.j.christopherson@intel.com>,
"H. Peter Anvin" <hpa@zytor.com>
Subject: Re: [patch V2 11/16] x86/ioperm: Share I/O bitmap if identical
Date: Tue, 12 Nov 2019 08:14:06 +0100 [thread overview]
Message-ID: <20191112071406.GC100264@gmail.com> (raw)
In-Reply-To: <20191111223052.603030685@linutronix.de>
* Thomas Gleixner <tglx@linutronix.de> wrote:
> The I/O bitmap is duplicated on fork. That's wasting memory and slows down
> fork. There is no point to do so. As long as the bitmap is not modified it
> can be shared between threads and processes.
>
> Add a refcount and just share it on fork. If a task modifies the bitmap
> then it has to do the duplication if and only if it is shared.
>
> Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
> ---
> V2: New patch
> ---
> arch/x86/include/asm/iobitmap.h | 5 +++++
> arch/x86/kernel/ioport.c | 38 ++++++++++++++++++++++++++++++++------
> arch/x86/kernel/process.c | 39 ++++++---------------------------------
> 3 files changed, 43 insertions(+), 39 deletions(-)
>
> --- a/arch/x86/include/asm/iobitmap.h
> +++ b/arch/x86/include/asm/iobitmap.h
> @@ -2,10 +2,12 @@
> #ifndef _ASM_X86_IOBITMAP_H
> #define _ASM_X86_IOBITMAP_H
>
> +#include <linux/refcount.h>
> #include <asm/processor.h>
>
> struct io_bitmap {
> u64 sequence;
> + refcount_t refcnt;
> unsigned int io_bitmap_max;
> union {
> unsigned long bits[IO_BITMAP_LONGS];
> +void io_bitmap_share(struct task_struct *tsk)
> + {
> + /*
> + * Take a refcount on current's bitmap. It can be used by
> + * both tasks as long as none of them changes the bitmap.
> + */
> + refcount_inc(¤t->thread.io_bitmap->refcnt);
> + tsk->thread.io_bitmap = current->thread.io_bitmap;
> + set_tsk_thread_flag(tsk, TIF_IO_BITMAP);
> +}
Ok, this is really neat. I suspect there might be some pathological cases
on ancient NUMA systems with a really high NUMA factor and bad caching
where this new sharing might regress performance, but I doubt this
matters, as both the hardware and this software functionality is legacy.
> + /*
> + * If the bitmap is not shared, then nothing can take a refcount as
> + * current can obviously not fork at the same time. If it's shared
> + * duplicate it and drop the refcount on the original one.
> + */
> + if (refcount_read(&iobm->refcnt) > 1) {
> + iobm = kmemdup(iobm, sizeof(*iobm), GFP_KERNEL);
> + if (!iobm)
> + return -ENOMEM;
> + io_bitmap_exit();
> }
>
> + /* Set the tasks io_bitmap pointer (might be the same) */
speling nit:
s/tasks
/task's
Thanks,
Ingo
next prev parent reply other threads:[~2019-11-12 7:14 UTC|newest]
Thread overview: 57+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-11-11 22:03 [patch V2 00/16] x86/iopl: Prevent user space from using CLI/STI with iopl(3) Thomas Gleixner
2019-11-11 22:03 ` [patch V2 01/16] x86/ptrace: Prevent truncation of bitmap size Thomas Gleixner
2019-11-12 15:34 ` Andy Lutomirski
2019-11-11 22:03 ` [patch V2 02/16] x86/process: Unify copy_thread_tls() Thomas Gleixner
2019-11-11 22:03 ` [patch V2 03/16] x86/cpu: Unify cpu_init() Thomas Gleixner
2019-11-11 22:03 ` [patch V2 04/16] x86/tss: Fix and move VMX BUILD_BUG_ON() Thomas Gleixner
2019-11-11 22:44 ` Paolo Bonzini
2019-11-12 15:37 ` Andy Lutomirski
2019-11-11 22:03 ` [patch V2 05/16] x86/iopl: Cleanup include maze Thomas Gleixner
2019-11-12 15:37 ` Andy Lutomirski
2019-11-11 22:03 ` [patch V2 06/16] x86/io: Speedup schedule out of I/O bitmap user Thomas Gleixner
2019-11-12 16:00 ` Andy Lutomirski
2019-11-12 17:08 ` Thomas Gleixner
2019-11-11 22:03 ` [patch V2 07/16] x86/ioperm: Move iobitmap data into a struct Thomas Gleixner
2019-11-12 16:02 ` Andy Lutomirski
2019-11-12 17:08 ` Thomas Gleixner
2019-11-11 22:03 ` [patch V2 08/16] x86/ioperm: Add bitmap sequence number Thomas Gleixner
2019-11-12 9:22 ` Peter Zijlstra
2019-11-12 9:55 ` [patch V2 08/16] x86/ioperm: Add bitmap sequence numberc Thomas Gleixner
2019-11-12 16:08 ` [patch V2 08/16] x86/ioperm: Add bitmap sequence number Andy Lutomirski
2019-11-12 17:10 ` Thomas Gleixner
2019-11-11 22:03 ` [patch V2 09/16] x86/ioperm: Move TSS bitmap update to exit to user work Thomas Gleixner
2019-11-12 16:16 ` Andy Lutomirski
2019-11-12 17:20 ` Thomas Gleixner
2019-11-12 17:41 ` Andy Lutomirski
2019-11-12 17:46 ` Linus Torvalds
2019-11-13 8:30 ` Peter Zijlstra
2019-11-11 22:03 ` [patch V2 10/16] x86/ioperm: Remove bitmap if all permissions dropped Thomas Gleixner
2019-11-12 17:43 ` Andy Lutomirski
2019-11-11 22:03 ` [patch V2 11/16] x86/ioperm: Share I/O bitmap if identical Thomas Gleixner
2019-11-12 7:14 ` Ingo Molnar [this message]
2019-11-12 7:17 ` Thomas Gleixner
2019-11-12 7:52 ` Ingo Molnar
2019-11-12 9:15 ` Peter Zijlstra
2019-11-12 9:51 ` Thomas Gleixner
2019-11-14 11:02 ` David Laight
2019-11-14 12:39 ` Thomas Gleixner
2019-11-14 13:09 ` Peter Zijlstra
2019-11-14 13:22 ` David Laight
2019-11-12 18:12 ` Andy Lutomirski
2019-11-11 22:03 ` [patch V2 12/16] selftests/x86/ioperm: Extend testing so the shared bitmap is exercised Thomas Gleixner
2019-11-11 22:03 ` [patch V2 13/16] x86/iopl: Fixup misleading comment Thomas Gleixner
2019-11-12 18:14 ` Andy Lutomirski
2019-11-11 22:03 ` [patch V2 14/16] x86/iopl: Restrict iopl() permission scope Thomas Gleixner
2019-11-11 23:03 ` Thomas Gleixner
2019-11-12 6:32 ` Ingo Molnar
2019-11-12 8:42 ` Ingo Molnar
2019-11-12 10:07 ` Thomas Gleixner
2019-11-12 18:35 ` Andy Lutomirski
2019-11-11 22:03 ` [patch V2 15/16] x86/iopl: Remove legacy IOPL option Thomas Gleixner
2019-11-12 18:37 ` Andy Lutomirski
2019-11-12 19:40 ` Thomas Gleixner
2019-11-11 22:03 ` [patch V2 16/16] selftests/x86/iopl: Extend test to cover IOPL emulation Thomas Gleixner
2019-11-12 7:40 ` [PATCH] x86/iopl: Factor out IO-bitmap related TSS fields into 'struct x86_io_bitmap' Ingo Molnar
2019-11-12 7:59 ` [PATCH] x86/iopl: Harmonize 'struct io_bitmap' and 'struct x86_io_bitmap' nomenclature Ingo Molnar
2019-11-12 8:11 ` [PATCH] x86/iopl: Clear up the role of the two bitmap copying fields Ingo Molnar
2019-11-12 8:15 ` [PATCH] x86/iopl: Rename <asm/iobitmap.h> to <asm/io_bitmap.h> Ingo Molnar
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=20191112071406.GC100264@gmail.com \
--to=mingo@kernel.org \
--cc=hpa@zytor.com \
--cc=jgross@suse.com \
--cc=linux-kernel@vger.kernel.org \
--cc=luto@kernel.org \
--cc=sean.j.christopherson@intel.com \
--cc=stephen@networkplumber.org \
--cc=tglx@linutronix.de \
--cc=torvalds@linuxfoundation.org \
--cc=w@1wt.eu \
--cc=x86@kernel.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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).