Re: [PATCH] mmc: core: Allow to avoid REQ_FUA if the eMMC supports an internal cache

From: Christoph Hellwig <hch@infradead.org>
To: Ulf Hansson <ulf.hansson@linaro.org>
Cc: linux-mmc@vger.kernel.org,
	Wenchao Chen <wenchao.chen666@gmail.com>,
	Adrian Hunter <adrian.hunter@intel.com>,
	Avri Altman <avri.altman@wdc.com>,
	Christian Lohle <cloehle@hyperstone.com>,
	linux-block@vger.kernel.org, linux-kernel@vger.kernel.org,
	Bean Huo <beanhuo@micron.com>
Subject: Re: [PATCH] mmc: core: Allow to avoid REQ_FUA if the eMMC supports an internal cache
Date: Thu, 16 Mar 2023 09:49:07 -0700	[thread overview]
Message-ID: <ZBNIg8+rOdFKcsS8@infradead.org> (raw)
In-Reply-To: <20230316164514.1615169-1-ulf.hansson@linaro.org>

On Thu, Mar 16, 2023 at 05:45:14PM +0100, Ulf Hansson wrote:
> File systems typically uses REQ_FUA for writing their meta-data and other
> important information. Ideally it should provide an increased protection
> against data-corruption, during sudden power-failures. This said, file
> systems have other ways to handle sudden power-failures too, like using
> checksums to detect partly-written data, for example.

Sorry, but this is completely wrong and dangerous, if not intentionally
misleading bullshit.

The only way to provide data integrity is to ensure data is written to
the media and not a cache.  That can be done by a full blown cache
flush, or with a FUA-like optimization.