All of lore.kernel.org
 help / color / mirror / Atom feed
From: Al Viro <viro@zeniv.linux.org.uk>
To: afzal mohammed <afzal.mohd.ma@gmail.com>
Cc: Arnd Bergmann <arnd@arndb.de>, Nicolas Pitre <nico@fluxnic.net>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Linus Walleij <linus.walleij@linaro.org>,
	Russell King - ARM Linux admin <linux@armlinux.org.uk>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	Linux-MM <linux-mm@kvack.org>, Will Deacon <will@kernel.org>,
	Linux ARM <linux-arm-kernel@lists.infradead.org>
Subject: Re: [RFC 1/3] lib: copy_{from,to}_user using gup & kmap_atomic()
Date: Sat, 13 Jun 2020 13:51:26 +0100	[thread overview]
Message-ID: <20200613125126.GE23230@ZenIV.linux.org.uk> (raw)
In-Reply-To: <20200613120432.GA5319@afzalpc>

On Sat, Jun 13, 2020 at 05:34:32PM +0530, afzal mohammed wrote:

> Observation is that max. pages reaching copy_{from,to}_user() is 2,
> observed maximum of n (number of bytes) being 1 page size. i think C
> library cuts any size read, write to page size (if it exceeds) &
> invokes the system call. Max. pages reaching 2, happens when 'n'
> crosses page boundary, this has been observed w/ small size request
> as well w/ ones of exact page size (but not page aligned).
> 
> Even w/ dd of various size >4K, never is the number of pages required
> to be mapped going greater than 2 (even w/ 'dd' 'bs=1M')
> 
> i have a worry (don't know whether it is an unnecessary one): even
> if we improve performance w/ large copy sizes, it might end up in a
> sluggishness w.r.t user experience due to most (hence a high amount)
> of user copy calls being few bytes & there the penalty being higher.
> And benchmark would not be able to detect anything abnormal since
> usercopy are being tested on large sizes.
> 
> Quickly comparing boot-time on Beagle Bone White, boot time increases
> by only 4%, perhaps this worry is irrelevant, but just thought will
> put it across.

Do stat(2) of the same tmpfs file in a loop (on tmpfs, to eliminate
the filesystem playing silly buggers).  And I wouldn't expect anything
good there...

_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel

WARNING: multiple messages have this Message-ID (diff)
From: Al Viro <viro@zeniv.linux.org.uk>
To: afzal mohammed <afzal.mohd.ma@gmail.com>
Cc: Arnd Bergmann <arnd@arndb.de>,
	Russell King - ARM Linux admin <linux@armlinux.org.uk>,
	Linus Walleij <linus.walleij@linaro.org>,
	"linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
	Linux-MM <linux-mm@kvack.org>,
	Linux ARM <linux-arm-kernel@lists.infradead.org>,
	Nicolas Pitre <nico@fluxnic.net>,
	Catalin Marinas <catalin.marinas@arm.com>,
	Will Deacon <will@kernel.org>
Subject: Re: [RFC 1/3] lib: copy_{from,to}_user using gup & kmap_atomic()
Date: Sat, 13 Jun 2020 13:51:26 +0100	[thread overview]
Message-ID: <20200613125126.GE23230@ZenIV.linux.org.uk> (raw)
In-Reply-To: <20200613120432.GA5319@afzalpc>

On Sat, Jun 13, 2020 at 05:34:32PM +0530, afzal mohammed wrote:

> Observation is that max. pages reaching copy_{from,to}_user() is 2,
> observed maximum of n (number of bytes) being 1 page size. i think C
> library cuts any size read, write to page size (if it exceeds) &
> invokes the system call. Max. pages reaching 2, happens when 'n'
> crosses page boundary, this has been observed w/ small size request
> as well w/ ones of exact page size (but not page aligned).
> 
> Even w/ dd of various size >4K, never is the number of pages required
> to be mapped going greater than 2 (even w/ 'dd' 'bs=1M')
> 
> i have a worry (don't know whether it is an unnecessary one): even
> if we improve performance w/ large copy sizes, it might end up in a
> sluggishness w.r.t user experience due to most (hence a high amount)
> of user copy calls being few bytes & there the penalty being higher.
> And benchmark would not be able to detect anything abnormal since
> usercopy are being tested on large sizes.
> 
> Quickly comparing boot-time on Beagle Bone White, boot time increases
> by only 4%, perhaps this worry is irrelevant, but just thought will
> put it across.

Do stat(2) of the same tmpfs file in a loop (on tmpfs, to eliminate
the filesystem playing silly buggers).  And I wouldn't expect anything
good there...


  reply	other threads:[~2020-06-13 12:52 UTC|newest]

Thread overview: 54+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-12 10:17 [RFC 0/3] ARM: copy_{from,to}_user() for vmsplit 4g/4g afzal mohammed
2020-06-12 10:17 ` afzal mohammed
2020-06-12 10:17 ` [RFC 1/3] lib: copy_{from,to}_user using gup & kmap_atomic() afzal mohammed
2020-06-12 10:35   ` [RFC PATCH " afzal mohammed
2020-06-12 12:02   ` [RFC " Arnd Bergmann
2020-06-12 12:02     ` Arnd Bergmann
2020-06-12 13:55     ` afzal mohammed
2020-06-12 13:55       ` afzal mohammed
2020-06-12 20:07       ` Arnd Bergmann
2020-06-12 20:07         ` Arnd Bergmann
2020-06-13 12:04         ` afzal mohammed
2020-06-13 12:04           ` afzal mohammed
2020-06-13 12:51           ` Al Viro [this message]
2020-06-13 12:51             ` Al Viro
2020-06-13 12:56             ` Al Viro
2020-06-13 12:56               ` Al Viro
2020-06-13 13:42               ` afzal mohammed
2020-06-13 13:42                 ` afzal mohammed
2020-06-13 15:31                 ` Al Viro
2020-06-13 15:31                   ` Al Viro
2020-06-13 15:41                   ` Al Viro
2020-06-13 15:41                     ` Al Viro
2020-06-13 16:00                     ` Al Viro
2020-06-13 16:00                       ` Al Viro
2020-06-13 18:55                       ` Arnd Bergmann
2020-06-13 18:55                         ` Arnd Bergmann
2020-06-15 11:22                   ` David Laight
2020-06-15 11:22                     ` David Laight
2020-06-13 13:15           ` Russell King - ARM Linux admin
2020-06-13 13:15             ` Russell King - ARM Linux admin
2020-06-14 13:06             ` afzal mohammed
2020-06-14 13:06               ` afzal mohammed
2020-06-13 20:45           ` Arnd Bergmann
2020-06-13 20:45             ` Arnd Bergmann
2020-06-13 22:16             ` Matthew Wilcox
2020-06-13 22:16               ` Matthew Wilcox
2020-06-14 13:21             ` afzal mohammed
2020-06-14 13:21               ` afzal mohammed
2020-06-14 14:55               ` afzal mohammed
2020-06-14 14:55                 ` afzal mohammed
2020-06-13 11:08   ` Andy Shevchenko
2020-06-13 11:08     ` Andy Shevchenko
2020-06-13 13:29     ` afzal mohammed
2020-06-13 13:29       ` afzal mohammed
2020-06-12 10:18 ` [RFC 2/3] ARM: uaccess: let UACCESS_GUP_KMAP_MEMCPY enabling afzal mohammed
2020-06-12 10:40   ` [RFC PATCH " afzal mohammed
2020-06-12 10:18 ` [RFC 3/3] ARM: provide CONFIG_VMSPLIT_4G_DEV for development afzal mohammed
2020-06-12 10:38   ` [RFC PATCH " afzal mohammed
2020-06-12 15:19 ` [RFC 0/3] ARM: copy_{from,to}_user() for vmsplit 4g/4g Nicolas Pitre
2020-06-12 15:19   ` Nicolas Pitre
2020-06-12 16:01   ` afzal mohammed
2020-06-12 16:01     ` afzal mohammed
2020-06-12 16:03     ` afzal mohammed
2020-06-12 16:03       ` afzal mohammed

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=20200613125126.GE23230@ZenIV.linux.org.uk \
    --to=viro@zeniv.linux.org.uk \
    --cc=afzal.mohd.ma@gmail.com \
    --cc=arnd@arndb.de \
    --cc=catalin.marinas@arm.com \
    --cc=linus.walleij@linaro.org \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=linux@armlinux.org.uk \
    --cc=nico@fluxnic.net \
    --cc=will@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 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.