All of lore.kernel.org
 help / color / mirror / Atom feed
From: Alexander Steffen <Alexander.Steffen@infineon.com>
To: <jarkko.sakkinen@linux.intel.com>, <nayna@linux.vnet.ibm.com>,
	<kgold@linux.vnet.ibm.com>, <linux-integrity@vger.kernel.org>
Subject: [RFC][PATCH 9/9] tpm: ignore burstcount to improve tpm_tis send() performance
Date: Fri, 8 Dec 2017 19:46:58 +0100	[thread overview]
Message-ID: <20171208184658.9588-10-Alexander.Steffen@infineon.com> (raw)
In-Reply-To: <20171208184658.9588-1-Alexander.Steffen@infineon.com>

From: Nayna Jain <nayna@linux.vnet.ibm.com>

The TPM burstcount status indicates the number of bytes that can
be sent to the TPM without causing bus wait states.  Effectively,
it is the number of empty bytes in the command FIFO.

This patch optimizes the tpm_tis_send_data() function by checking
the burstcount only once. And if the burstcount is valid, it writes
all the bytes at once, permitting wait state.

After this change, performance on a TPM 1.2 with an 8 byte
burstcount for 1000 extends improved from ~41sec to ~14sec.

Suggested-by: Ken Goldman <kgold@linux.vnet.ibm.com> in
conjunction with the TPM Device Driver work group.
Signed-off-by: Nayna Jain <nayna@linux.vnet.ibm.com>
Acked-by: Mimi Zohar <zohar@linux.vnet.ibm.com>
Reviewed-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Tested-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
Signed-off-by: Jarkko Sakkinen <jarkko.sakkinen@linux.intel.com>
---
 drivers/char/tpm/tpm_tis_core.c | 31 +++++++++++++++----------------
 1 file changed, 15 insertions(+), 16 deletions(-)

diff --git a/drivers/char/tpm/tpm_tis_core.c b/drivers/char/tpm/tpm_tis_core.c
index 7240ee4..7979b06 100644
--- a/drivers/char/tpm/tpm_tis_core.c
+++ b/drivers/char/tpm/tpm_tis_core.c
@@ -320,7 +320,6 @@ static int tpm_tis_send_data(struct tpm_chip *chip, const u8 *buf, size_t len)
 {
 	struct tpm_tis_data *priv = dev_get_drvdata(&chip->dev);
 	int rc, status, burstcnt;
-	size_t count = 0;
 
 	status = tpm_tis_status(chip);
 	if ((status & TPM_STS_COMMAND_READY) == 0) {
@@ -333,23 +332,23 @@ static int tpm_tis_send_data(struct tpm_chip *chip, const u8 *buf, size_t len)
 		}
 	}
 
-	while (count < len) {
-		burstcnt = get_burstcount(chip);
-		if (burstcnt < 0) {
-			dev_err(&chip->dev, "Unable to read burstcount\n");
-			rc = burstcnt;
-			goto out_err;
-		}
-		burstcnt = min_t(int, burstcnt, len - count);
-		rc = tpm_tis_write_bytes(priv, ADD_LOCALITY(priv->fifo_address,
-							    priv->locality),
-					 burstcnt, buf + count);
-		if (rc < 0)
-			goto out_err;
-
-		count += burstcnt;
+	/*
+	 * Get the initial burstcount to ensure TPM is ready to
+	 * accept data.
+	 */
+	burstcnt = get_burstcount(chip);
+	if (burstcnt < 0) {
+		dev_err(&chip->dev, "Unable to read burstcount\n");
+		rc = burstcnt;
+		goto out_err;
 	}
 
+	rc = tpm_tis_write_bytes(priv, ADD_LOCALITY(priv->fifo_address,
+						    priv->locality),
+				 len, buf);
+	if (rc < 0)
+		goto out_err;
+
 	if (!(priv->flags & TPM_TIS_ITPM_WORKAROUND) &&
 	    wait_for_tpm_stat(chip, TPM_STS_DATA_EXPECT | TPM_STS_VALID,
 			      TPM_STS_VALID, chip->timeout_c, &priv->int_queue,
-- 
2.7.4

  parent reply	other threads:[~2017-12-08 18:54 UTC|newest]

Thread overview: 35+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-12-08 18:46 [RFC][PATCH 0/9] tpm: fix driver so that burstcount can be safely ignored Alexander Steffen
2017-12-08 18:46 ` [RFC][PATCH 1/9] tpm_tis_core: clean up whitespace Alexander Steffen
2018-01-18 17:11   ` Jarkko Sakkinen
2017-12-08 18:46 ` [RFC][PATCH 2/9] tpm_tis_core: access single TIS registers before doing complex transfers Alexander Steffen
2018-01-18 17:16   ` Jarkko Sakkinen
2017-12-08 18:46 ` [RFC][PATCH 3/9] tpm_tis_core: correctly wait for flags to become zero Alexander Steffen
2018-01-18 17:49   ` Jarkko Sakkinen
2018-01-18 17:58   ` Jarkko Sakkinen
2018-01-18 17:59     ` Jarkko Sakkinen
2017-12-08 18:46 ` [RFC][PATCH 4/9] tpm_tis_core: send all data in single operation Alexander Steffen
2017-12-19  9:01   ` Nayna Jain
2018-01-18 18:04   ` Jarkko Sakkinen
2017-12-08 18:46 ` [RFC][PATCH 5/9] tpm_tis_core: use XDATA_FIFO for transfers if available Alexander Steffen
2018-01-18 18:20   ` Jarkko Sakkinen
2017-12-08 18:46 ` [RFC][PATCH 6/9] tpm_tis_spi: fix sending wrong data during wait state handling Alexander Steffen
2018-01-18 18:26   ` Jarkko Sakkinen
2017-12-08 18:46 ` [RFC][PATCH 7/9] tpm_tis_spi: release CS line when wait state handling fails Alexander Steffen
2018-01-18 18:30   ` Jarkko Sakkinen
2017-12-08 18:46 ` [RFC][PATCH 8/9] tpm_tis_spi: add delay between wait state retries Alexander Steffen
2018-01-11 19:46   ` Mimi Zohar
2018-01-12  8:28     ` Alexander Steffen
2018-01-12 14:53       ` Mimi Zohar
2018-01-15 22:30       ` Mimi Zohar
2018-01-17 17:15         ` Mimi Zohar
2018-01-17 18:58           ` Alexander Steffen
2018-01-18 18:32   ` Jarkko Sakkinen
2017-12-08 18:46 ` Alexander Steffen [this message]
2017-12-15 12:04 ` [RFC][PATCH 0/9] tpm: fix driver so that burstcount can be safely ignored Jarkko Sakkinen
2017-12-24 20:41   ` Jarkko Sakkinen
2018-01-04 13:11     ` Alexander.Steffen
2018-01-05  6:46       ` Nayna Jain
2018-01-05  7:38         ` Alexander Steffen
2018-01-08 10:50           ` Jarkko Sakkinen
2018-01-08 10:49       ` Jarkko Sakkinen
2017-12-19  8:53 ` Nayna Jain

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=20171208184658.9588-10-Alexander.Steffen@infineon.com \
    --to=alexander.steffen@infineon.com \
    --cc=jarkko.sakkinen@linux.intel.com \
    --cc=kgold@linux.vnet.ibm.com \
    --cc=linux-integrity@vger.kernel.org \
    --cc=nayna@linux.vnet.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.