Re: [PATCH v2 04/11] md/raid5: use mempool to allocate stripe_request_ctx

[Li Nan]

在 2025/11/24 14:31, Yu Kuai 写道:
> On the one hand, stripe_request_ctx is 72 bytes, and it's a bit huge for
> a stack variable.
>
> On the other hand, the bitmap sectors_to_do is a fixed size, result in
> max_hw_sector_kb of raid5 array is at most 256 * 4k = 1Mb, and this will
> make full stripe IO impossible for the array that chunk_size * data_disks
> is bigger. Allocate ctx during runtime will make it possible to get rid
> of this limit.
>
> Signed-off-by: Yu Kuai <yukuai@xxxxxxxxx>
> ---
>   drivers/md/md.h       |  4 +++
>   drivers/md/raid1-10.c |  5 ----
>   drivers/md/raid5.c    | 61 +++++++++++++++++++++++++++----------------
>   drivers/md/raid5.h    |  2 ++
>   4 files changed, 45 insertions(+), 27 deletions(-)
>
> diff --git a/drivers/md/md.h b/drivers/md/md.h
> index 6ee18045f41c..b8c5dec12b62 100644
> --- a/drivers/md/md.h
> +++ b/drivers/md/md.h
> @@ -22,6 +22,10 @@
>   #include <trace/events/block.h>
>   
>   #define MaxSector (~(sector_t)0)
> +/*
> + * Number of guaranteed raid bios in case of extreme VM load:
> + */
> +#define	NR_RAID_BIOS 256
>   
>   enum md_submodule_type {
>   	MD_PERSONALITY = 0,
> diff --git a/drivers/md/raid1-10.c b/drivers/md/raid1-10.c
> index 521625756128..c33099925f23 100644
> --- a/drivers/md/raid1-10.c
> +++ b/drivers/md/raid1-10.c
> @@ -3,11 +3,6 @@
>   #define RESYNC_BLOCK_SIZE (64*1024)
>   #define RESYNC_PAGES ((RESYNC_BLOCK_SIZE + PAGE_SIZE-1) / PAGE_SIZE)
>   
> -/*
> - * Number of guaranteed raid bios in case of extreme VM load:
> - */
> -#define	NR_RAID_BIOS 256
> -
>   /* when we get a read error on a read-only array, we redirect to another
>    * device without failing the first device, or trying to over-write to
>    * correct the read error.  To keep track of bad blocks on a per-bio
> diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
> index f405ba7b99a7..0080dec4a6ef 100644
> --- a/drivers/md/raid5.c
> +++ b/drivers/md/raid5.c
> @@ -6083,13 +6083,13 @@ static sector_t raid5_bio_lowest_chunk_sector(struct r5conf *conf,
>   static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
>   {
>   	DEFINE_WAIT_FUNC(wait, woken_wake_function);
> -	bool on_wq;
>   	struct r5conf *conf = mddev->private;
> -	sector_t logical_sector;
> -	struct stripe_request_ctx ctx = {};
>   	const int rw = bio_data_dir(bi);
> +	struct stripe_request_ctx *ctx;
> +	sector_t logical_sector;
>   	enum stripe_result res;
>   	int s, stripe_cnt;
> +	bool on_wq;
>   
>   	if (unlikely(bi->bi_opf & REQ_PREFLUSH)) {
>   		int ret = log_handle_flush_request(conf, bi);
> @@ -6101,11 +6101,6 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
>   				return true;
>   		}
>   		/* ret == -EAGAIN, fallback */
> -		/*
> -		 * if r5l_handle_flush_request() didn't clear REQ_PREFLUSH,
> -		 * we need to flush journal device
> -		 */
> -		ctx.do_flush = bi->bi_opf & REQ_PREFLUSH;
>   	}
>   
>   	md_write_start(mddev, bi);
> @@ -6128,16 +6123,24 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
>   	}
>   
>   	logical_sector = bi->bi_iter.bi_sector & ~((sector_t)RAID5_STRIPE_SECTORS(conf)-1);
> -	ctx.first_sector = logical_sector;
> -	ctx.last_sector = bio_end_sector(bi);
>   	bi->bi_next = NULL;
>   
> -	stripe_cnt = DIV_ROUND_UP_SECTOR_T(ctx.last_sector - logical_sector,
> +	ctx = mempool_alloc(conf->ctx_pool, GFP_NOIO | __GFP_ZERO);

In mempool_alloc_noprof():
	VM_WARN_ON_ONCE(gfp_mask & __GFP_ZERO);

__GFP_ZERO should be removed and ensure init before accessing the members.

--
Thanks,
Nan