[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <7fe698080904080744y15f781b9lc71d84e705ef6089@mail.gmail.com>
Date: Wed, 8 Apr 2009 23:44:04 +0900
From: Dongjun Shin <djshin90@...il.com>
To: Mark Lord <liml@....ca>
Cc: Matthew Wilcox <willy@...ux.intel.com>, linux-ide@...r.kernel.org,
linux-kernel@...r.kernel.org, jgarzik@...hat.com,
David Woodhouse <David.Woodhouse@...el.com>
Subject: Re: [PATCH 4/5] ide: Add support for TRIM
On Wed, Apr 8, 2009 at 11:33 PM, Mark Lord <liml@....ca> wrote:
>
> Matthew Wilcox wrote:
>>
>> From: David Woodhouse <David.Woodhouse@...el.com>
>>
>> Signed-off-by: David Woodhouse <David.Woodhouse@...el.com>
>> [modified to reduce amount of special casing needed for discard]
>> Signed-off-by: Matthew Wilcox <willy@...ux.intel.com>
>> ---
>
> ..
>>
>> + task->tf.command = ATA_CMD_DSM;
>> + task->tf.feature = ATA_DSM_TRIM;
>> + task->tf.hob_feature = 0x00;
>> + task->tf.nsect = size / 512;
>> + task->tf.hob_nsect = (size / 512) >> 8;
>
> ..
>
> Matthew (or others),
>
> Could you perhaps explain what the purpose of the data portion
> of this command is for? The draft ATA spec I have here has mangled
> text in the description -- like it's missing a crucial sentence there.
>
> So it's not obvious exactly why this command even needs data to
> be transfered.
It's for transfering list of LBA ranges which composed of
LBA offset (48bit) and length of data to be trimmed (16bit).
--
Dongjun
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
Powered by blists - more mailing lists