netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: <sameehj@amazon.com>
To: <davem@davemloft.net>, <netdev@vger.kernel.org>
Cc: Sameeh Jubran <sameehj@amazon.com>, <dwmw@amazon.com>,
	<zorik@amazon.com>, <matua@amazon.com>, <saeedb@amazon.com>,
	<msw@amazon.com>, <aliguori@amazon.com>, <nafea@amazon.com>,
	<gtzalik@amazon.com>, <netanel@amazon.com>, <alisaidi@amazon.com>,
	<benh@amazon.com>, <akiyano@amazon.com>,
	Igor Chauskin <igorch@amazon.com>
Subject: [PATCH V2 net 07/11] net: ena: allow automatic fallback to polling mode
Date: Mon, 3 Jun 2019 17:43:25 +0300	[thread overview]
Message-ID: <20190603144329.16366-8-sameehj@amazon.com> (raw)
In-Reply-To: <20190603144329.16366-1-sameehj@amazon.com>

From: Sameeh Jubran <sameehj@amazon.com>

Enable fallback to polling mode for Admin queue
when identified a command response arrival
without an accompanying MSI-X interrupt

Signed-off-by: Igor Chauskin <igorch@amazon.com>
Signed-off-by: Sameeh Jubran <sameehj@amazon.com>
---
 drivers/net/ethernet/amazon/ena/ena_com.c | 34 +++++++++++++++++------
 drivers/net/ethernet/amazon/ena/ena_com.h | 14 ++++++++++
 2 files changed, 39 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/amazon/ena/ena_com.c b/drivers/net/ethernet/amazon/ena/ena_com.c
index 139b31549..5e2abdda7 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.c
+++ b/drivers/net/ethernet/amazon/ena/ena_com.c
@@ -762,16 +762,26 @@ static int ena_com_wait_and_process_admin_cq_interrupts(struct ena_comp_ctx *com
 		admin_queue->stats.no_completion++;
 		spin_unlock_irqrestore(&admin_queue->q_lock, flags);
 
-		if (comp_ctx->status == ENA_CMD_COMPLETED)
-			pr_err("The ena device have completion but the driver didn't receive any MSI-X interrupt (cmd %d)\n",
-			       comp_ctx->cmd_opcode);
-		else
-			pr_err("The ena device doesn't send any completion for the admin cmd %d status %d\n",
+		if (comp_ctx->status == ENA_CMD_COMPLETED) {
+			pr_err("The ena device sent a completion but the driver didn't receive a MSI-X interrupt (cmd %d), autopolling mode is %s\n",
+			       comp_ctx->cmd_opcode,
+			       admin_queue->auto_polling ? "ON" : "OFF");
+			/* Check if fallback to polling is enabled */
+			if (admin_queue->auto_polling)
+				admin_queue->polling = true;
+		} else {
+			pr_err("The ena device doesn't send a completion for the admin cmd %d status %d\n",
 			       comp_ctx->cmd_opcode, comp_ctx->status);
-
-		admin_queue->running_state = false;
-		ret = -ETIME;
-		goto err;
+		}
+		/* Check if shifted to polling mode.
+		 * This will happen if there is a completion without an interrupt
+		 * and autopolling mode is enabled. Continuing normal execution in such case
+		 */
+		if (!admin_queue->polling) {
+			admin_queue->running_state = false;
+			ret = -ETIME;
+			goto err;
+		}
 	}
 
 	ret = ena_com_comp_status_to_errno(comp_ctx->comp_status);
@@ -1650,6 +1660,12 @@ void ena_com_set_admin_polling_mode(struct ena_com_dev *ena_dev, bool polling)
 	ena_dev->admin_queue.polling = polling;
 }
 
+void ena_com_set_admin_auto_polling_mode(struct ena_com_dev *ena_dev,
+					 bool polling)
+{
+	ena_dev->admin_queue.auto_polling = polling;
+}
+
 int ena_com_mmio_reg_read_request_init(struct ena_com_dev *ena_dev)
 {
 	struct ena_com_mmio_read *mmio_read = &ena_dev->mmio_read;
diff --git a/drivers/net/ethernet/amazon/ena/ena_com.h b/drivers/net/ethernet/amazon/ena/ena_com.h
index ce36444c3..6d356cb05 100644
--- a/drivers/net/ethernet/amazon/ena/ena_com.h
+++ b/drivers/net/ethernet/amazon/ena/ena_com.h
@@ -283,6 +283,9 @@ struct ena_com_admin_queue {
 	/* Indicate if the admin queue should poll for completion */
 	bool polling;
 
+	/* Define if fallback to polling mode should occur */
+	bool auto_polling;
+
 	u16 curr_cmd_id;
 
 	/* Indicate that the ena was initialized and can
@@ -545,6 +548,17 @@ void ena_com_set_admin_polling_mode(struct ena_com_dev *ena_dev, bool polling);
  */
 bool ena_com_get_ena_admin_polling_mode(struct ena_com_dev *ena_dev);
 
+/* ena_com_set_admin_auto_polling_mode - Enable autoswitch to polling mode
+ * @ena_dev: ENA communication layer struct
+ * @polling: Enable/Disable polling mode
+ *
+ * Set the autopolling mode.
+ * If autopolling is on:
+ * In case of missing interrupt when data is available switch to polling.
+ */
+void ena_com_set_admin_auto_polling_mode(struct ena_com_dev *ena_dev,
+					 bool polling);
+
 /* ena_com_admin_q_comp_intr_handler - admin queue interrupt handler
  * @ena_dev: ENA communication layer struct
  *
-- 
2.17.1


  parent reply	other threads:[~2019-06-03 14:44 UTC|newest]

Thread overview: 32+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-06-03 14:43 [PATCH V2 net 00/11] Extending the ena driver to support new features and enhance performance sameehj
2019-06-03 14:43 ` [PATCH V2 net 01/11] net: ena: add handling of llq max tx burst size sameehj
2019-06-03 14:43 ` [PATCH V2 net 02/11] net: ena: ethtool: add extra properties retrieval via get_priv_flags sameehj
2019-06-03 14:43 ` [PATCH V2 net 03/11] net: ena: replace free_tx/rx_ids union with single free_ids field in ena_ring sameehj
2019-06-03 14:43 ` [PATCH V2 net 04/11] net: ena: arrange ena_probe() function variables in reverse christmas tree sameehj
2019-06-03 14:43 ` [PATCH V2 net 05/11] net: ena: add newline at the end of pr_err prints sameehj
2019-06-03 14:43 ` [PATCH V2 net 06/11] net: ena: documentation: update ena.txt sameehj
2019-06-03 14:43 ` sameehj [this message]
2019-06-03 14:43 ` [PATCH V2 net 08/11] net: ena: add support for changing max_header_size in LLQ mode sameehj
2019-06-03 14:43 ` [PATCH V2 net 09/11] net: ena: optimise calculations for CQ doorbell sameehj
2019-06-03 14:43 ` [PATCH V2 net 10/11] net: ena: add good checksum counter sameehj
2019-06-03 14:43 ` [PATCH V2 net 11/11] net: ena: use dev_info_once instead of static variable sameehj
2019-06-03 20:30 ` [PATCH V2 net 00/11] Extending the ena driver to support new features and enhance performance David Miller
2019-06-03 21:32 ` Jakub Kicinski
     [not found]   ` <9da931e72debc868efaac144082f40d379c50f3c.camel@amazon.co.uk>
2019-06-03 23:03     ` Jakub Kicinski
2019-06-04  1:50       ` Andrew Lunn
2019-06-04  2:15         ` Bshara, Nafea
2019-06-04  6:57           ` David Woodhouse
2019-06-04 17:24             ` Jakub Kicinski
2019-06-06 10:23               ` Jubran, Samih
2019-06-06 17:16                 ` Jakub Kicinski
2019-06-06 21:40                   ` Bshara, Nafea
2019-06-06 22:04                     ` Jakub Kicinski
2019-06-06 22:57                       ` Bshara, Nafea
2019-06-06 23:07                         ` Jakub Kicinski
2019-06-06 23:21                           ` Bshara, Nafea
2019-06-06 23:42                             ` Jakub Kicinski
2019-06-07  1:04                               ` Bshara, Nafea
2019-06-07  1:14                                 ` Jakub Kicinski
2019-06-07 21:27                                   ` Jakub Kicinski
2019-06-07 21:34                                     ` Bshara, Nafea
2019-06-07 21:54                                       ` Jakub Kicinski

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=20190603144329.16366-8-sameehj@amazon.com \
    --to=sameehj@amazon.com \
    --cc=akiyano@amazon.com \
    --cc=aliguori@amazon.com \
    --cc=alisaidi@amazon.com \
    --cc=benh@amazon.com \
    --cc=davem@davemloft.net \
    --cc=dwmw@amazon.com \
    --cc=gtzalik@amazon.com \
    --cc=igorch@amazon.com \
    --cc=matua@amazon.com \
    --cc=msw@amazon.com \
    --cc=nafea@amazon.com \
    --cc=netanel@amazon.com \
    --cc=netdev@vger.kernel.org \
    --cc=saeedb@amazon.com \
    --cc=zorik@amazon.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).