From: Julian Wiedmann <jwi@linux.ibm.com>
To: David Miller <davem@davemloft.net>
Cc: netdev <netdev@vger.kernel.org>,
linux-s390 <linux-s390@vger.kernel.org>,
Heiko Carstens <heiko.carstens@de.ibm.com>,
Ursula Braun <ubraun@linux.ibm.com>,
Julian Wiedmann <jwi@linux.ibm.com>
Subject: [PATCH v2 net-next 01/11] s390/qeth: simplify RX buffer tracking
Date: Wed, 25 Mar 2020 10:34:57 +0100 [thread overview]
Message-ID: <20200325093507.20831-2-jwi@linux.ibm.com> (raw)
In-Reply-To: <20200325093507.20831-1-jwi@linux.ibm.com>
Since RX buffers may contain multiple packets, qeth's NAPI poll code can
exhaust its budget in the middle of an RX buffer. Thus we keep track of
our current position within the active RX buffer, so we can resume
processing here in the next NAPI poll period.
Clean up that code by tracking the index of the active buffer element,
instead of a pointer to it.
Also simplify the code that advances to the next RX buffer when the
current buffer has been fully processed.
v2: - remove QDIO_ELEMENT_NO() macro (davem)
Signed-off-by: Julian Wiedmann <jwi@linux.ibm.com>
---
drivers/s390/net/qeth_core.h | 2 +-
drivers/s390/net/qeth_core_main.c | 30 ++++++++++++------------------
2 files changed, 13 insertions(+), 19 deletions(-)
diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h
index 6eb431c194bd..9840d4fab010 100644
--- a/drivers/s390/net/qeth_core.h
+++ b/drivers/s390/net/qeth_core.h
@@ -752,7 +752,7 @@ enum qeth_addr_disposition {
struct qeth_rx {
int b_count;
int b_index;
- struct qdio_buffer_element *b_element;
+ u8 buf_element;
int e_offset;
int qdio_err;
};
diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c
index bd3adbb6ad50..4f33e4ee49d7 100644
--- a/drivers/s390/net/qeth_core_main.c
+++ b/drivers/s390/net/qeth_core_main.c
@@ -5332,14 +5332,13 @@ static inline int qeth_is_last_sbale(struct qdio_buffer_element *sbale)
}
static int qeth_extract_skb(struct qeth_card *card,
- struct qeth_qdio_buffer *qethbuffer,
- struct qdio_buffer_element **__element,
+ struct qeth_qdio_buffer *qethbuffer, u8 *element_no,
int *__offset)
{
- struct qdio_buffer_element *element = *__element;
struct qeth_priv *priv = netdev_priv(card->dev);
struct qdio_buffer *buffer = qethbuffer->buffer;
struct napi_struct *napi = &card->napi;
+ struct qdio_buffer_element *element;
unsigned int linear_len = 0;
bool uses_frags = false;
int offset = *__offset;
@@ -5349,6 +5348,8 @@ static int qeth_extract_skb(struct qeth_card *card,
struct sk_buff *skb;
int skb_len = 0;
+ element = &buffer->element[*element_no];
+
next_packet:
/* qeth_hdr must not cross element boundaries */
while (element->length < offset + sizeof(struct qeth_hdr)) {
@@ -5504,7 +5505,7 @@ static int qeth_extract_skb(struct qeth_card *card,
if (!skb)
goto next_packet;
- *__element = element;
+ *element_no = element - &buffer->element[0];
*__offset = offset;
qeth_receive_skb(card, skb, hdr, uses_frags);
@@ -5519,7 +5520,7 @@ static int qeth_extract_skbs(struct qeth_card *card, int budget,
*done = false;
while (budget) {
- if (qeth_extract_skb(card, buf, &card->rx.b_element,
+ if (qeth_extract_skb(card, buf, &card->rx.buf_element,
&card->rx.e_offset)) {
*done = true;
break;
@@ -5550,10 +5551,6 @@ int qeth_poll(struct napi_struct *napi, int budget)
card->rx.b_count = 0;
break;
}
- card->rx.b_element =
- &card->qdio.in_q->bufs[card->rx.b_index]
- .buffer->element[0];
- card->rx.e_offset = 0;
}
while (card->rx.b_count) {
@@ -5572,15 +5569,12 @@ int qeth_poll(struct napi_struct *napi, int budget)
buffer->pool_entry);
qeth_queue_input_buffer(card, card->rx.b_index);
card->rx.b_count--;
- if (card->rx.b_count) {
- card->rx.b_index =
- QDIO_BUFNR(card->rx.b_index + 1);
- card->rx.b_element =
- &card->qdio.in_q
- ->bufs[card->rx.b_index]
- .buffer->element[0];
- card->rx.e_offset = 0;
- }
+
+ /* Step forward to next buffer: */
+ card->rx.b_index =
+ QDIO_BUFNR(card->rx.b_index + 1);
+ card->rx.buf_element = 0;
+ card->rx.e_offset = 0;
}
if (work_done >= budget)
--
2.17.1
next prev parent reply other threads:[~2020-03-25 9:35 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-03-25 9:34 [PATCH v2 net-next 00/11] s390/qeth: updates 2020-03-25 Julian Wiedmann
2020-03-25 9:34 ` Julian Wiedmann [this message]
2020-03-25 9:34 ` [PATCH v2 net-next 02/11] s390/qeth: split out RX poll code Julian Wiedmann
2020-03-25 9:34 ` [PATCH v2 net-next 03/11] s390/qeth: remove redundant if-clause in " Julian Wiedmann
2020-03-25 9:35 ` [PATCH v2 net-next 04/11] s390/qdio: extend polling support to multiple queues Julian Wiedmann
2020-03-25 9:35 ` [PATCH v2 net-next 05/11] s390/qeth: simplify L3 dev_id logic Julian Wiedmann
2020-03-25 9:35 ` [PATCH v2 net-next 06/11] s390/qeth: clean up the mac_bits Julian Wiedmann
2020-03-25 9:35 ` [PATCH v2 net-next 07/11] s390/qeth: collect more TX statistics Julian Wiedmann
2020-03-25 9:35 ` [PATCH v2 net-next 08/11] s390/qeth: add TX IRQ coalescing support for IQD devices Julian Wiedmann
2020-03-25 9:35 ` [PATCH v2 net-next 09/11] s390/qeth: fine-tune MAC Address-related errnos Julian Wiedmann
2020-03-25 9:35 ` [PATCH v2 net-next 10/11] s390/qeth: keep track of fixed prio-queue configuration Julian Wiedmann
2020-03-25 9:35 ` [PATCH v2 net-next 11/11] s390/qeth: modernize two list helpers Julian Wiedmann
2020-03-25 19:07 ` [PATCH v2 net-next 00/11] s390/qeth: updates 2020-03-25 David Miller
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=20200325093507.20831-2-jwi@linux.ibm.com \
--to=jwi@linux.ibm.com \
--cc=davem@davemloft.net \
--cc=heiko.carstens@de.ibm.com \
--cc=linux-s390@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=ubraun@linux.ibm.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;
as well as URLs for NNTP newsgroup(s).