From: David Howells <dhowells@redhat.com>
To: Stefan Metzmacher <metze@samba.org>
Cc: dhowells@redhat.com, linux-cifs@vger.kernel.org,
Steve French <sfrench@samba.org>, Tom Talpey <tom@talpey.com>
Subject: Re: [PATCH 2/2] smb: client: let smbd_post_send_iter() respect the peers max_send_size and transmit all data
Date: Thu, 19 Jun 2025 12:49:00 +0100 [thread overview]
Message-ID: <850317.1750333740@warthog.procyon.org.uk> (raw)
In-Reply-To: <8ecf5dc585af7abb37f3fabac6eb0f9f3273da85.1750264849.git.metze@samba.org>
Stefan Metzmacher <metze@samba.org> wrote:
> diff --git a/fs/smb/client/smbdirect.c b/fs/smb/client/smbdirect.c
> index cbc85bca006f..3a41dcbbff81 100644
> --- a/fs/smb/client/smbdirect.c
> +++ b/fs/smb/client/smbdirect.c
> @@ -842,7 +842,7 @@ static int smbd_post_send(struct smbd_connection *info,
>
> static int smbd_post_send_iter(struct smbd_connection *info,
> struct iov_iter *iter,
> - int *_remaining_data_length)
> + unsigned int *_remaining_data_length)
I would recommend size_t...
> {
> struct smbdirect_socket *sc = &info->socket;
> struct smbdirect_socket_parameters *sp = &sc->parameters;
> @@ -907,8 +907,10 @@ static int smbd_post_send_iter(struct smbd_connection *info,
> .local_dma_lkey = sc->ib.pd->local_dma_lkey,
> .direction = DMA_TO_DEVICE,
> };
> + size_t payload_len = min_t(size_t, *_remaining_data_length,
> + sp->max_send_size - sizeof(*packet));
... and umin().
>
> - rc = smb_extract_iter_to_rdma(iter, *_remaining_data_length,
> + rc = smb_extract_iter_to_rdma(iter, payload_len,
> &extract);
> if (rc < 0)
> goto err_dma;
> @@ -970,8 +972,16 @@ static int smbd_post_send_iter(struct smbd_connection *info,
> request->sge[0].lkey = sc->ib.pd->local_dma_lkey;
>
> rc = smbd_post_send(info, request);
> - if (!rc)
> + if (!rc) {
> + if (iter && iov_iter_count(iter) > 0) {
> + /*
> + * There is more data to send
> + */
> + goto wait_credit;
> + }
> +
This fix isn't mentioned in the patch description.
> return 0;
> + }
>
> err_dma:
> for (i = 0; i < request->num_sge; i++)
> @@ -1007,7 +1017,7 @@ static int smbd_post_send_iter(struct smbd_connection *info,
> */
> static int smbd_post_send_empty(struct smbd_connection *info)
> {
> - int remaining_data_length = 0;
> + unsigned int remaining_data_length = 0;
size_t?
>
> info->count_send_empty++;
> return smbd_post_send_iter(info, NULL, &remaining_data_length);
Apart from the above:
Reviewed-by: David Howells <dhowells@redhat.com>
next prev parent reply other threads:[~2025-06-19 11:49 UTC|newest]
Thread overview: 15+ messages / expand[flat|nested] mbox.gz Atom feed top
2025-06-18 16:51 [PATCH 0/2] smb: client: fix problems with smbdirect/rdma mounts Stefan Metzmacher
2025-06-18 16:51 ` [PATCH 1/2] smb: client: fix max_sge overflow in smb_extract_folioq_to_rdma() Stefan Metzmacher
2025-06-19 11:41 ` David Howells
2025-06-19 19:07 ` Tom Talpey
2025-06-18 16:51 ` [PATCH 2/2] smb: client: let smbd_post_send_iter() respect the peers max_send_size and transmit all data Stefan Metzmacher
2025-06-19 11:49 ` David Howells [this message]
2025-06-19 19:22 ` Tom Talpey
2025-06-20 12:29 ` David Howells
2025-06-20 13:33 ` Tom Talpey
2025-06-20 14:56 ` David Howells
2025-06-25 7:59 ` David Howells
2025-06-23 15:46 ` Stefan Metzmacher
2025-06-23 17:28 ` Steve French
2025-06-23 19:48 ` Sasha Levin
2025-06-25 8:00 ` David Howells
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=850317.1750333740@warthog.procyon.org.uk \
--to=dhowells@redhat.com \
--cc=linux-cifs@vger.kernel.org \
--cc=metze@samba.org \
--cc=sfrench@samba.org \
--cc=tom@talpey.com \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox