Date:   Sun, 5 Feb 2023 21:53:53 +0000
From:   Matthew Wilcox <willy@infradead.org>
To:     Hao Lee <haolee.swjtu@gmail.com>
Cc:     akpm@linux-foundation.org, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org
Subject: Re: [PATCH] mm: eliminate function call overhead during
 copy_page_range()
Message-ID: <Y+AlcdA3fH0FiJGO@casper.infradead.org>
References: <20230205150602.GA25866@haolee.io>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20230205150602.GA25866@haolee.io>
Precedence: bulk

On Sun, Feb 05, 2023 at 03:06:02PM +0000, Hao Lee wrote:
> vm_normal_page() is called so many times that its overhead is very high.
> After changing this call site to an inline function, copy_page_range()
> runs 3~5 times faster than before.

So you're saying that your compiler is making bad decisions?  What
architecture, what compiler, what version?  Do you have
CONFIG_ARCH_HAS_PTE_SPECIAL set?

Is there something about inlining it that makes the compiler able to
optimise away code, or is it really the function call overhead?  Can
you share any perf results?