Skip to contentSkip to conversation

sdhci-stm performance issues

PATCH RESEND In review Peppe CAVALLARO 2 participants 5 messages Aug 24, 2010 – Sep 21, 2010

Subsystems (2)
lore
Share & tools
lore
#0 lore raw

Hello,
testing the sdhci-stm.c driver, I sent some weeks ago to the mailing list, I'm facing some performance issues.
For example, when copy a file (e.g. ~10MiB) to the card, I've noticed that, in the sdhci_prepare_data, the maximum value for data->blocks is 248.

The sdhci-stm driver uses the ADMA and:
max_seg_size = 65536,
max_hw_segs = 128,
max_phys_segs = 128,
max_req_size = 524288,
max_blk_size = 2048,
max_blk_count = 65535.

Using my arasan.c code, I've also sent to this mailing list in July,
I could see that the data->blocks was bigger than 248 and the performances were better. Note that this driver used the same mmc_host parameters (max_blk_size etc.) reported above for the sdhci-stm.

What am I missing?

Welcome advice.

Best Regards,
Giuseppe

#1 lore raw

Hello
The problem was due to the missing both 8BIT and MMC_SPEED supports in my sdhci driver (comes from the 2.6.32 Kernel series).
I've also added the patch in attachment.

Best Regards
Peppe

Quoted 25 lines · Peppe CAVALLARO

Hello,
testing the sdhci-stm.c driver, I sent some weeks ago to the mailing list, I'm facing some performance issues.
For example, when copy a file (e.g. ~10MiB) to the card, I've noticed that,
in the sdhci_prepare_data, the maximum value for data->blocks is 248.

The sdhci-stm driver uses the ADMA and:
max_seg_size = 65536,
max_hw_segs = 128,
max_phys_segs = 128,
max_req_size = 524288,
max_blk_size = 2048,
max_blk_count = 65535.

Using my arasan.c code, I've also sent to this mailing list in July, I could see that the data->blocks was bigger than 248 and the performances were better.
Note that this driver used the same mmc_host parameters (max_blk_size etc.) reported
above for the sdhci-stm.

What am I missing?

Quoted 9 lines

Welcome advice.

Best Regards,
Giuseppe
--
To unsubscribe from this list: send the line "unsubscribe linux-mmc" in the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html

From b3427a938ed04febdaa729ca500f266274e06bd2 Mon Sep 17 00:00:00 2001
From: Giuseppe Cavallaro <[email protected]>
Date: Tue, 31 Aug 2010 05:43:45 +0200
Subject: [PATCH (sh-2.6.32.y)] sdhci: add MMC_CAP_8_BIT_DATA in the Host capabilities

---
 drivers/mmc/host/sdhci.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)
drivers/mmc/host/sdhci.c +1 -1
index 955cad9..1c49326 100644
@@ -1799,7 +1799,7 @@ int sdhci_add_host(struct sdhci_host *host)
 	mmc->caps = MMC_CAP_SDIO_IRQ;
 
 	if (!(host->quirks & SDHCI_QUIRK_FORCE_1_BIT_DATA))
-		mmc->caps |= MMC_CAP_4_BIT_DATA;
+		mmc->caps |= MMC_CAP_4_BIT_DATA | MMC_CAP_8_BIT_DATA;
 
 	if (caps & SDHCI_CAN_DO_HISPD)
 		mmc->caps |= MMC_CAP_SD_HIGHSPEED;
Signature · 1 line
1.5.5.6
#2 lore raw

PATCH RESEND 1/1 sdhci: add MMC_CAP_8_BIT_DATA in the Host capabilities

From: Giuseppe Cavallaro <[email protected]>
Date: Tue, 31 Aug 2010 05:43:45 +0200
Subject: [PATCH (sh-2.6.32.y)] sdhci: add MMC_CAP_8_BIT_DATA in the Host capabilities

---
 drivers/mmc/host/sdhci.c |    2 +-
 1 files changed, 1 insertions(+), 1 deletions(-)
drivers/mmc/host/sdhci.c +1 -1
index 955cad9..1c49326 100644
@@ -1799,7 +1799,7 @@ int sdhci_add_host(struct sdhci_host *host)
 	mmc->caps = MMC_CAP_SDIO_IRQ;
 
 	if (!(host->quirks & SDHCI_QUIRK_FORCE_1_BIT_DATA))
-		mmc->caps |= MMC_CAP_4_BIT_DATA;
+		mmc->caps |= MMC_CAP_4_BIT_DATA | MMC_CAP_8_BIT_DATA;
 
 	if (caps & SDHCI_CAN_DO_HISPD)
 		mmc->caps |= MMC_CAP_SD_HIGHSPEED;
Signature · 2 lines
Chris Ball   <[email protected]>   <http://printf.net/>
One Laptop Per Child
#3 lore raw

Re: [PATCH RESEND] sdhci: add MMC_CAP_8_BIT_DATA in the Host capabilities

-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

Thanks Chris to have resent the patch again.

I'm going to resend it just today ;-).

I'm using 8BIT_DATA mode on my HC without any problems and with good performances.

Regards
Peppe

Quoted 24 lines · Chris Ball

From: Giuseppe Cavallaro <[email protected]>
Date: Tue, 31 Aug 2010 05:43:45 +0200
Subject: [PATCH (sh-2.6.32.y)] sdhci: add MMC_CAP_8_BIT_DATA in the Host capabilities

---
drivers/mmc/host/sdhci.c | 2 +-

1 files changed, 1 insertions(+), 1 deletions(-)
drivers/mmc/host/sdhci.c +1 -2
index 955cad9..1c49326 100644
@@ -1799,7 +1799,7 @@ int sdhci_add_host(struct sdhci_host *host)
 mmc->caps = MMC_CAP_SDIO_IRQ;
 
 if (!(host->quirks & SDHCI_QUIRK_FORCE_1_BIT_DATA))
- mmc->caps |= MMC_CAP_4_BIT_DATA;
+ mmc->caps |= MMC_CAP_4_BIT_DATA | MMC_CAP_8_BIT_DATA;
 
 if (caps & SDHCI_CAN_DO_HISPD)
 mmc->caps |= MMC_CAP_SD_HIGHSPEED;
--
Quoted 3 lines

Chris Ball <[email protected]> <http://printf.net/>
One Laptop Per Child

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.10 (GNU/Linux)
Comment: Using GnuPG with Mozilla - http://enigmail.mozdev.org/

iQEcBAEBAgAGBQJMlwSGAAoJEAm9vY9TshdvbJAH+wZXUrPEOIGr/4i/uAGKW+jN 6yYukjyyCHerXLmI9vmmV8NekDU/DOi5jMHlUaFHkCUZcSVFfK+68xfOuH4Sz2Cu 7L3wTPXrQabIeM6cV31DOu15wLpgmTZhXECBxlZOAjMnnE2UyzszMbep4v5ZMZM4 Tj8lbCkdnINjBZc/lNUUwgIdOGvoIdxt5KIMy0k84BZY01ggsurTzMwtnXQEK6J4 YkOT4Ut57TIR/9ZxEzii/QbJjVNvm4hrZOwbooTu8cYcy2di66dJ7TwrOa5rKcev z5QkmH7UZqVja7WAhgK1f9TlBSMiTmhRnJeOoQvELpq8lHV0tOajIBsK7EmJiwI= =W0a6
-----END PGP SIGNATURE-----

#4 lore raw

Re: [PATCH RESEND] sdhci: add MMC_CAP_8_BIT_DATA in the Host capabilities

Hi Peppe,

Quoted 6 lines · Peppe CAVALLARO

Thanks Chris to have resent the patch again.

I'm going to resend it just today ;-).

I'm using 8BIT_DATA mode on my HC without any problems and with good performances.

Thanks, I've applied this to mmc-next now.

Signature · 2 lines
Chris Ball   <[email protected]>   <http://printf.net/>
One Laptop Per Child