[PATCH 11/11] nvmet: add an FDP write translation tracepoint

[Guixin Liu]

在 2026/10/19 11:48, sashiko-bot at kernel.org 写道:
> Thank you for your contribution! Sashiko AI review found 2 potential issue(s) to consider:
> - [Medium] nvmet: trace_nvmet_fdp_write_translate() called on non-directive writes
> - [Medium] nvmet: missing bi_write_stream copy on chained bios in nvmet_bdev_execute_rw()
> --
>
> commit 910a51c080606805fab754e08158c76023d49e00
> Author: Guixin Liu <kanie at linux.alibaba.com>
>
> nvmet: add an FDP write translation tracepoint
>
> This commit adds the nvmet_fdp_write_translate tracepoint to the bdev write
> path to report the placement identifier from a write command and the backing
> write stream it is translated to.
>
>> diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
>> index ff480f9ab9906..139be9edad969 100644
>> --- a/drivers/nvme/target/io-cmd-bdev.c
>> +++ b/drivers/nvme/target/io-cmd-bdev.c
> [ ... ]
>
>> @@ -302,7 +303,10 @@ static void nvmet_bdev_execute_rw(struct nvmet_req *req)
>>  	bio->bi_end_io = nvmet_bio_done;
>>  	if (req->cmd->rw.opcode == nvme_cmd_write &&
>>  	    nvmet_fdp_enabled(req->ns)) {
>> +		u16 pid = le32_to_cpu(req->cmd->rw.dsmgmt) >> 16;
>> +
>>  		bio->bi_write_stream = nvmet_fdp_write_stream(req);
>> +		trace_nvmet_fdp_write_translate(req, pid, bio->bi_write_stream);
>>  	}
> [Severity: Medium]
> Should trace_nvmet_fdp_write_translate() only be called when the write
> command actually carries the Data Placement Directive?
>
> The commit message notes that the tracepoint "reports the placement
> identifier carried by a write command with the Data Placement Directive
> and the backing write stream it is translated to."
>
> In drivers/nvme/target/nvmet.h, nvmet_fdp_write_stream() checks the
> directive type before treating the upper 16 bits of req->cmd->rw.dsmgmt
> as a placement identifier:
>
> static inline u8 nvmet_fdp_write_stream(struct nvmet_req *req)
> {
> 	u16 control = le16_to_cpu(req->cmd->rw.control);
> 	u16 pid;
>
> 	if ((control & 0xf0) != (NVME_RW_DTYPE_DPLCMT & 0xf0))
> 		return 0;
>
> 	pid = le32_to_cpu(req->cmd->rw.dsmgmt) >> 16;
>
> In nvmet_bdev_execute_rw(), however, trace_nvmet_fdp_write_translate() is
> invoked for every nvme_cmd_write to an FDP-enabled namespace without
> checking whether req->cmd->rw.control specifies NVME_RW_DTYPE_DPLCMT.
>
> When a host issues an ordinary non-directive write (or a write with a
> different directive type) to an FDP-enabled namespace, won't this still
> fire the tracepoint and report the upper 16 bits of req->cmd->rw.dsmgmt
> as pid alongside write_stream=0, making non-directive writes
> indistinguishable from directive writes whose placement identifier failed
> translation?
Well, yes, fixed in v2.
>
> [Severity: Medium]
> Also in nvmet_bdev_execute_rw(), what happens when a write with the Data
> Placement Directive spans more than BIO_MAX_VECS (256) scatterlist
> segments and has to be split across chained bios?
>
> Later in nvmet_bdev_execute_rw(), if bio_add_page() cannot fit all
> segments into the initial bio, a continuation bio is allocated and
> chained:
>
> 	for_each_sg(req->sg, sg, req->sg_cnt, i) {
> 		while (bio_add_page(bio, sg_page(sg), sg->length, sg->offset)
> 				!= sg->length) {
> 			struct bio *prev = bio;
> 			...
> 			bio = bio_alloc(req->ns->bdev, bio_max_segs(sg_cnt),
> 					opf, GFP_KERNEL);
> 			bio->bi_iter.bi_sector = sector;
>
> 			bio_chain(bio, prev);
> 			submit_bio(prev);
> 		}
>
> Because bio_alloc() initializes bi_write_stream to 0 and bio_chain() does
> not copy prev->bi_write_stream, the continuation bios keep
> bi_write_stream == 0 while trace_nvmet_fdp_write_translate() reports that
> the request was translated to the initial bio's stream.
>
> As a result, blk_rq_merge_ok() will reject merging the continuation bios
> with the initial bio due to the mismatched bi_write_stream, and
> nvme_setup_rw() will submit the remainder of the write to the backing
> device without NVME_RW_DTYPE_DPLCMT (placing it into default stream 0).
> Should prev->bi_write_stream be copied to each chained bio in
> nvmet_bdev_execute_rw()?
Same as before, fixed in v2.
>>  
>>  	blk_start_plug(&plug);
> [ ... ]
>
>>
>>
> []
>