Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
Subject: Re: [PATCH 09/15] lightnvm: implement get log report chunk helpers
To:     Javier Gonzalez <javier@cnexlabs.com>
Cc:     "linux-block@vger.kernel.org" <linux-block@vger.kernel.org>,
        "linux-kernel@vger.kernel.org" <linux-kernel@vger.kernel.org>,
        "linux-nvme@lists.infradead.org" <linux-nvme@lists.infradead.org>
References: <1519832975-25432-1-git-send-email-javier@cnexlabs.com>
 <1519832975-25432-10-git-send-email-javier@cnexlabs.com>
 <4c82d581-d8bf-25fb-26ea-48b26e6de899@lightnvm.io>
 <B6B4086D-DA0B-41FF-AFB4-5E752F18CD01@cnexlabs.com>
From:   =?UTF-8?Q?Matias_Bj=c3=b8rling?= <mb@lightnvm.io>
Message-ID: <3713fd85-5050-b498-ce32-e699444337ba@lightnvm.io>
Date:   Thu, 1 Mar 2018 12:51:40 +0100
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:52.0) Gecko/20100101
 Thunderbird/52.5.0
MIME-Version: 1.0
In-Reply-To: <B6B4086D-DA0B-41FF-AFB4-5E752F18CD01@cnexlabs.com>
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Language: en-GB
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

On 03/01/2018 12:02 PM, Javier Gonzalez wrote:
>> On 1 Mar 2018, at 11.40, Matias Bjørling <mb@lightnvm.io> wrote:
>>
>> On 02/28/2018 04:49 PM, Javier González wrote:
>>> The 2.0 spec provides a report chunk log page that can be retrieved
>>> using the stangard nvme get log page. This replaces the dedicated
>>> get/put bad block table in 1.2.
>>> This patch implements the helper functions to allow targets retrieve the
>>> chunk metadata using get log page. It makes nvme_get_log_ext available
>>> outside of nvme core so that we can use it form lightnvm.
>>> Signed-off-by: Javier González <javier@cnexlabs.com>
>>> ---
>>>   drivers/lightnvm/core.c      | 11 +++++++
>>>   drivers/nvme/host/core.c     |  6 ++--
>>>   drivers/nvme/host/lightnvm.c | 74 ++++++++++++++++++++++++++++++++++++++++++++
>>>   drivers/nvme/host/nvme.h     |  3 ++
>>>   include/linux/lightnvm.h     | 24 ++++++++++++++
>>>   5 files changed, 115 insertions(+), 3 deletions(-)
>>> diff --git a/drivers/lightnvm/core.c b/drivers/lightnvm/core.c
>>> index ed33e0b11788..4141871f460d 100644
>>> --- a/drivers/lightnvm/core.c
>>> +++ b/drivers/lightnvm/core.c
>>> @@ -712,6 +712,17 @@ static void nvm_free_rqd_ppalist(struct nvm_tgt_dev *tgt_dev,
>>>   	nvm_dev_dma_free(tgt_dev->parent, rqd->ppa_list, rqd->dma_ppa_list);
>>>   }
>>>   +int nvm_get_chunk_meta(struct nvm_tgt_dev *tgt_dev, struct nvm_chk_meta *meta,
>>> +		struct ppa_addr ppa, int nchks)
>>> +{
>>> +	struct nvm_dev *dev = tgt_dev->parent;
>>> +
>>> +	nvm_ppa_tgt_to_dev(tgt_dev, &ppa, 1);
>>> +
>>> +	return dev->ops->get_chk_meta(tgt_dev->parent, meta,
>>> +						(sector_t)ppa.ppa, nchks);
>>> +}
>>> +EXPORT_SYMBOL(nvm_get_chunk_meta);
>>>     int nvm_set_tgt_bb_tbl(struct nvm_tgt_dev *tgt_dev, struct ppa_addr *ppas,
>>>   		       int nr_ppas, int type)
>>> diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
>>> index 2e9e9f973a75..af642ce6ba69 100644
>>> --- a/drivers/nvme/host/core.c
>>> +++ b/drivers/nvme/host/core.c
>>> @@ -2127,9 +2127,9 @@ static int nvme_init_subsystem(struct nvme_ctrl *ctrl, struct nvme_id_ctrl *id)
>>>   	return ret;
>>>   }
>>>   -static int nvme_get_log_ext(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
>>> -			    u8 log_page, void *log,
>>> -			    size_t size, size_t offset)
>>> +int nvme_get_log_ext(struct nvme_ctrl *ctrl, struct nvme_ns *ns,
>>> +		     u8 log_page, void *log,
>>> +		     size_t size, size_t offset)
>>>   {
>>>   	struct nvme_command c = { };
>>>   	unsigned long dwlen = size / 4 - 1;
>>> diff --git a/drivers/nvme/host/lightnvm.c b/drivers/nvme/host/lightnvm.c
>>> index f7135659f918..a1796241040f 100644
>>> --- a/drivers/nvme/host/lightnvm.c
>>> +++ b/drivers/nvme/host/lightnvm.c
>>> @@ -35,6 +35,10 @@ enum nvme_nvm_admin_opcode {
>>>   	nvme_nvm_admin_set_bb_tbl	= 0xf1,
>>>   };
>>>   +enum nvme_nvm_log_page {
>>> +	NVME_NVM_LOG_REPORT_CHUNK	= 0xca,
>>> +};
>>> +
>>>   struct nvme_nvm_ph_rw {
>>>   	__u8			opcode;
>>>   	__u8			flags;
>>> @@ -236,6 +240,16 @@ struct nvme_nvm_id20 {
>>>   	__u8			vs[1024];
>>>   };
>>>   +struct nvme_nvm_chk_meta {
>>> +	__u8	state;
>>> +	__u8	type;
>>> +	__u8	wi;
>>> +	__u8	rsvd[5];
>>> +	__le64	slba;
>>> +	__le64	cnlb;
>>> +	__le64	wp;
>>> +};
>>> +
>>>   /*
>>>    * Check we didn't inadvertently grow the command struct
>>>    */
>>> @@ -252,6 +266,9 @@ static inline void _nvme_nvm_check_size(void)
>>>   	BUILD_BUG_ON(sizeof(struct nvme_nvm_bb_tbl) != 64);
>>>   	BUILD_BUG_ON(sizeof(struct nvme_nvm_id20_addrf) != 8);
>>>   	BUILD_BUG_ON(sizeof(struct nvme_nvm_id20) != NVME_IDENTIFY_DATA_SIZE);
>>> +	BUILD_BUG_ON(sizeof(struct nvme_nvm_chk_meta) != 32);
>>> +	BUILD_BUG_ON(sizeof(struct nvme_nvm_chk_meta) !=
>>> +						sizeof(struct nvm_chk_meta));
>>>   }
>>>     static void nvme_nvm_set_addr_12(struct nvm_addr_format_12 *dst,
>>> @@ -555,6 +572,61 @@ static int nvme_nvm_set_bb_tbl(struct nvm_dev *nvmdev, struct ppa_addr *ppas,
>>>   	return ret;
>>>   }
>>>   +/*
>>> + * Expect the lba in device format
>>> + */
>>> +static int nvme_nvm_get_chk_meta(struct nvm_dev *ndev,
>>> +				 struct nvm_chk_meta *meta,
>>> +				 sector_t slba, int nchks)
>>> +{
>>> +	struct nvm_geo *geo = &ndev->geo;
>>> +	struct nvme_ns *ns = ndev->q->queuedata;
>>> +	struct nvme_ctrl *ctrl = ns->ctrl;
>>> +	struct nvme_nvm_chk_meta *dev_meta = (struct nvme_nvm_chk_meta *)meta;
>>> +	struct ppa_addr ppa;
>>> +	size_t left = nchks * sizeof(struct nvme_nvm_chk_meta);
>>> +	size_t log_pos, offset, len;
>>> +	int ret, i;
>>> +
>>> +	/* Normalize lba address space to obtain log offset */
>>> +	ppa.ppa = slba;
>>> +	ppa = dev_to_generic_addr(ndev, ppa);
>>> +
>>> +	log_pos = ppa.m.chk;
>>> +	log_pos += ppa.m.pu * geo->num_chk;
>>> +	log_pos += ppa.m.grp * geo->num_lun * geo->num_chk;
>>
>> Why is this done?
> 
> The log page does not map to the lba space. You need to convert it to
> get one chunk at a time in the format.
> 
>     GRP:PU:CHK
> 
> I can see why taking a lba as argument is better than a ppa, since users
> might use the lbas directly, but the conversion needs to be done
> somewhere.
> 

Good point. I guess this is clash between the two APIs. Chunk metadata 
being laid out sequentially, while the address space is sparse. I'm good 
with the conversion being in the fn.