Re: Bart's efforts?

Re: Bart's efforts?

[Mikael Pettersson]

On Sat, 3 Nov 2007 14:10:22 +0000, Alan Cox wrote:
> > My question is if the drivers/ide infrastructure is slowly moving in
> > the direction of being leverageable by libata when/if it moves out of
> > scsi.  Or does the drivers/ide code simply have the wrong kind of
> > plumbing for libata to ever use.
> 
> I don't think there is anything useful in old IDE that isn't in the new.

For semi-modern machines that might be true. However:

1) there's no libata replacement for the IDE pmac driver
2) pata_pdc202xx_old can't do UDMA on my 440BX PIII box
3) pata_legacy doesn't release io/irq combinations for failed
   probes, causing conflicts with drivers loaded later on

(Not a complaint, just a reminder that rm -rf drivers/ide/
isn't an option yet.)

Re: Bart's efforts?

[Alan Cox]

> 1) there's no libata replacement for the IDE pmac driver

This is true currently. David Woodhouse loaned me a Pmac to fix that but
it died so thats waiting for the PPC people to do something about it.

> 2) pata_pdc202xx_old can't do UDMA on my 440BX PIII box

Bug # ?

> 3) pata_legacy doesn't release io/irq combinations for failed
>    probes, causing conflicts with drivers loaded later on

In my tree it does but I'm still testing some bits. I've been rewriting
the legacy driver to make it a lot cleaner and easy to plug other ISA/VLB
device handlers into it.

Re: Bart's efforts?

[Mark Lord]

delkin_cb is also missing from libata.

I was going to port it over once, but no longer have a cardbus slot
in either of my notebooks here.

Cheers

Re: Bart's efforts?

[Alan Cox]

On Wed, 07 Nov 2007 17:37:07 -0500
Mark Lord <liml@rtr.ca> wrote:

> delkin_cb is also missing from libata.
> 
> I was going to port it over once, but no longer have a cardbus slot
> in either of my notebooks here.

Yes I looked at it but it didn't have any proper speed setting, so I
decided it wasn't actually worth doing.

Alan

Re: Bart's efforts?

[Mark Lord]

Alan Cox wrote:
> On Wed, 07 Nov 2007 17:37:07 -0500
> Mark Lord <liml@rtr.ca> wrote:
> 
>> delkin_cb is also missing from libata.
>>
>> I was going to port it over once, but no longer have a cardbus slot
>> in either of my notebooks here.
> 
> Yes I looked at it but it didn't have any proper speed setting, so I
> decided it wasn't actually worth doing.
..

Yeah.  No docs whatsoever, but there's more than a few users
of it out there.

Cheers

Re: Bart's efforts?

[Alan Cox]

> Yeah.  No docs whatsoever, but there's more than a few users
> of it out there.

So how do we handle devices that don't support PIO4 ?

Other than the speed handling mystery the port is trivial.

Alan

Re: Bart's efforts?

[Mark Lord]

Alan Cox wrote:
>> Yeah.  No docs whatsoever, but there's more than a few users
>> of it out there.
> 
> So how do we handle devices that don't support PIO4 ?
..

I'm not actually sure that it's even running that fast (PIO4), 
as the performance is still only half of what Windoze gets.

I have a logic analyzer here, but no Cardbus extender to hook it onto.

Re: Bart's efforts?

[Mikael Pettersson]

Mikael Pettersson writes:
 > On Sat, 3 Nov 2007 14:10:22 +0000, Alan Cox wrote:
 > > > My question is if the drivers/ide infrastructure is slowly moving in
 > > > the direction of being leverageable by libata when/if it moves out of
 > > > scsi.  Or does the drivers/ide code simply have the wrong kind of
 > > > plumbing for libata to ever use.
 > > 
 > > I don't think there is anything useful in old IDE that isn't in the new.
 > 
 > For semi-modern machines that might be true. However:
 > 
...
 > 2) pata_pdc202xx_old can't do UDMA on my 440BX PIII box

See <http://bugzilla.kernel.org/show_bug.cgi?id=9337> for details.

Delkin Cardbus IDE, a.k.a. ASKA "Ninja" chipset

[Mark Lord]

Mark Lord wrote:
> Alan Cox wrote:
>> On Wed, 07 Nov 2007 17:37:07 -0500
>> Mark Lord <liml@rtr.ca> wrote:
>>
>>> delkin_cb is also missing from libata.
>>>
>>> I was going to port it over once, but no longer have a cardbus slot
>>> in either of my notebooks here.
>>
>> Yes I looked at it but it didn't have any proper speed setting, so I
>> decided it wasn't actually worth doing.
> ..
> 
> Yeah.  No docs whatsoever, but there's more than a few users
> of it out there.
...

Mmmm.. the NetBSD people seem to have detailed information on these chips!
There seems to be more than enough information in the NetBSD sources
to implement full timings support and full bus-master DMA support:

http://cvsweb.netbsd.org/bsdweb.cgi/src/sys/dev/ic/ninjaata32var.h?rev=1.3&content-type=text/x-cvsweb-markup
http://cvsweb.netbsd.org/bsdweb.cgi/src/sys/dev/ic/ninjaata32reg.h?rev=1.3&content-type=text/x-cvsweb-markup
http://cvsweb.netbsd.org/bsdweb.cgi/src/sys/dev/ic/ninjaata32.c?rev=1.9&content-type=text/x-cvsweb-markup


Anyone want to take this on?

Cheers

Re: Delkin Cardbus IDE, a.k.a. ASKA "Ninja" chipset

[Mark Lord]

Mark Lord wrote:
> Mark Lord wrote:
>> Alan Cox wrote:
>>> On Wed, 07 Nov 2007 17:37:07 -0500
>>> Mark Lord <liml@rtr.ca> wrote:
>>>
>>>> delkin_cb is also missing from libata.
>>>>
>>>> I was going to port it over once, but no longer have a cardbus slot
>>>> in either of my notebooks here.
>>>
>>> Yes I looked at it but it didn't have any proper speed setting, so I
>>> decided it wasn't actually worth doing.
>> ..
>>
>> Yeah.  No docs whatsoever, but there's more than a few users
>> of it out there.
> ...
> 
> Mmmm.. the NetBSD people seem to have detailed information on these chips!
> There seems to be more than enough information in the NetBSD sources
> to implement full timings support and full bus-master DMA support:
> 
> http://cvsweb.netbsd.org/bsdweb.cgi/src/sys/dev/ic/ninjaata32var.h?rev=1.3&content-type=text/x-cvsweb-markup 
> 
> http://cvsweb.netbsd.org/bsdweb.cgi/src/sys/dev/ic/ninjaata32reg.h?rev=1.3&content-type=text/x-cvsweb-markup 
> 
> http://cvsweb.netbsd.org/bsdweb.cgi/src/sys/dev/ic/ninjaata32.c?rev=1.9&content-type=text/x-cvsweb-markup 
..

Plus the man page (which looks slightly out of date):

http://netbsd.gw.com/cgi-bin/man-cgi/man?njata+4+NetBSD-current

Re: Delkin Cardbus IDE, a.k.a. ASKA "Ninja" chipset

[Mark Lord]

Mark Lord wrote:
> Mark Lord wrote:
>> Mark Lord wrote:
>>> Alan Cox wrote:
>>>> On Wed, 07 Nov 2007 17:37:07 -0500
>>>> Mark Lord <liml@rtr.ca> wrote:
>>>>
>>>>> delkin_cb is also missing from libata.
>>>>>
>>>>> I was going to port it over once, but no longer have a cardbus slot
>>>>> in either of my notebooks here.
>>>>
>>>> Yes I looked at it but it didn't have any proper speed setting, so I
>>>> decided it wasn't actually worth doing.
>>> ..
>>>
>>> Yeah.  No docs whatsoever, but there's more than a few users
>>> of it out there.
>> ...
>>
>> Mmmm.. the NetBSD people seem to have detailed information on these 
>> chips!
>> There seems to be more than enough information in the NetBSD sources
>> to implement full timings support and full bus-master DMA support:
>>
>> http://cvsweb.netbsd.org/bsdweb.cgi/src/sys/dev/ic/ninjaata32var.h?rev=1.3&content-type=text/x-cvsweb-markup 
>>
>> http://cvsweb.netbsd.org/bsdweb.cgi/src/sys/dev/ic/ninjaata32reg.h?rev=1.3&content-type=text/x-cvsweb-markup 
>>
>> http://cvsweb.netbsd.org/bsdweb.cgi/src/sys/dev/ic/ninjaata32.c?rev=1.9&content-type=text/x-cvsweb-markup 
> 
> Plus the man page (which looks slightly out of date):
> 
> http://netbsd.gw.com/cgi-bin/man-cgi/man?njata+4+NetBSD-current
..

One more link, with many PCI IDs for these chips:

http://cvsweb.netbsd.org/bsdweb.cgi/src/sys/dev/cardbus/njata_cardbus.c?rev=1.5&content-type=text/x-cvsweb-markup

Re: Delkin Cardbus IDE, a.k.a. ASKA "Ninja" chipset

[Alan Cox]

On Mon, 12 Nov 2007 15:11:16 -0500
Mark Lord <liml@rtr.ca> wrote:

> Mark Lord wrote:
> > Alan Cox wrote:
> >> On Wed, 07 Nov 2007 17:37:07 -0500
> >> Mark Lord <liml@rtr.ca> wrote:
> >>
> >>> delkin_cb is also missing from libata.
> >>>
> >>> I was going to port it over once, but no longer have a cardbus slot
> >>> in either of my notebooks here.
> >>
> >> Yes I looked at it but it didn't have any proper speed setting, so I
> >> decided it wasn't actually worth doing.
> > ..
> > 
> > Yeah.  No docs whatsoever, but there's more than a few users
> > of it out there.
> ...
> 
> Mmmm.. the NetBSD people seem to have detailed information on these chips!
> There seems to be more than enough information in the NetBSD sources
> to implement full timings support and full bus-master DMA support:
> 
> http://cvsweb.netbsd.org/bsdweb.cgi/src/sys/dev/ic/ninjaata32var.h?rev=1.3&content-type=text/x-cvsweb-markup
> http://cvsweb.netbsd.org/bsdweb.cgi/src/sys/dev/ic/ninjaata32reg.h?rev=1.3&content-type=text/x-cvsweb-markup
> http://cvsweb.netbsd.org/bsdweb.cgi/src/sys/dev/ic/ninjaata32.c?rev=1.9&content-type=text/x-cvsweb-markup
> 
> 
> Anyone want to take this on?

I'll knock a driver out next week providing someone with hardware is
willing to be test monkey.

Alan

Re: Delkin Cardbus IDE, a.k.a. ASKA "Ninja" chipset

[Mark Lord]

Alan Cox wrote:
> On Mon, 12 Nov 2007 15:11:16 -0500
> Mark Lord <liml@rtr.ca> wrote:
> 
>> Mark Lord wrote:
>>> Alan Cox wrote:
>>>> On Wed, 07 Nov 2007 17:37:07 -0500
>>>> Mark Lord <liml@rtr.ca> wrote:
>>>>
>>>>> delkin_cb is also missing from libata.
>>>>>
>>>>> I was going to port it over once, but no longer have a cardbus slot
>>>>> in either of my notebooks here.
>>>> Yes I looked at it but it didn't have any proper speed setting, so I
>>>> decided it wasn't actually worth doing.
>>> ..
>>>
>>> Yeah.  No docs whatsoever, but there's more than a few users
>>> of it out there.
>> ...
>>
>> Mmmm.. the NetBSD people seem to have detailed information on these chips!
>> There seems to be more than enough information in the NetBSD sources
>> to implement full timings support and full bus-master DMA support:
>>
>> http://cvsweb.netbsd.org/bsdweb.cgi/src/sys/dev/ic/ninjaata32var.h?rev=1.3&content-type=text/x-cvsweb-markup
>> http://cvsweb.netbsd.org/bsdweb.cgi/src/sys/dev/ic/ninjaata32reg.h?rev=1.3&content-type=text/x-cvsweb-markup
>> http://cvsweb.netbsd.org/bsdweb.cgi/src/sys/dev/ic/ninjaata32.c?rev=1.9&content-type=text/x-cvsweb-markup
>>
>>
>> Anyone want to take this on?
> 
> I'll knock a driver out next week providing someone with hardware is
> willing to be test monkey.

I've got hardware here that you can have, if you want it.
It's just a cardbus CF adapter, and neither of my own notebooks have slots.

Email me privately with mailing address if you want it.

Cheers

Re: Delkin Cardbus IDE, a.k.a. ASKA "Ninja" chipset

[Alan Cox]

First guess

/*
 * pata_ninja32.c 	- Ninja32 PATA for new ATA layer
 *			  (C) 2007 Red Hat Inc
 *			  Alan Cox <alan@redhat.com>
 *
 * Note: The controller like many controllers has shared timings for
 * PIO and DMA. We thus flip to the DMA timings in dma_start and flip back
 * in the dma_stop function. Thus we actually don't need a set_dmamode
 * method as the PIO method is always called and will set the right PIO
 * timing parameters.
 *
 * The Ninja32 Cardbus is not a generic SFF controller. Instead it is
 * laid out as follows off BAR 0. This is based upon Mark Lord's delkin
 * driver and the extensive analysis done by the BSD developers, notably
 * ITOH Yasufumi.
 *
 *	Base + 0x00 IRQ Status
 *	Base + 0x01 IRQ control
 *	Base + 0x02 Chipset control
 *	Base + 0x04 VDMA and reset control + wait bits
 *	Base + 0x08 BMIMBA
 *	Base + 0x0C DMA Length
 *	Base + 0x10 Taskfile
 *	Base + 0x18 BMDMA Status ?
 *	Base + 0x1C
 *	Base + 0x1D Bus master control
 *		bit 0 = enable
 *		bit 1 = 0 write/1 read
 *		bit 2 = 1 sgtable
 *		bit 3 = go
 *		bit 4-6 wait bits
 *		bit 7 = done
 *	Base + 0x1E AltStatus
 *	Base + 0x1F timing register
 */

#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/pci.h>
#include <linux/init.h>
#include <linux/blkdev.h>
#include <linux/delay.h>
#include <scsi/scsi_host.h>
#include <linux/libata.h>

#define DRV_NAME "pata_ninja32"
#define DRV_VERSION "0.0.1"

/**
 *	ninja32_configure_piomode	-	set chip PIO timing
 *	@ap: ATA interface
 *	@adev: ATA device
 *	@pio: PIO mode
 *
 *	Called to do the PIO mode setup. Our timing registers are shared
 *	so a configure_dmamode call will undo any work we do here and vice
 *	versa
 */

static void ninja32_configure_piomode(struct ata_port *ap, struct ata_device *adev, int pio)
{
	static u16 pio_timing[5] = {
		0xd6, 0x85, 0x44, 0x33, 0x13
	};
	iowrite8(pio_timing[pio], ap->ioaddr.bmdma_addr + 0x1f);
}

/**
 *	ninja32_set_piomode	-	set initial PIO mode data
 *	@ap: ATA interface
 *	@adev: ATA device
 *
 *	Called to do the PIO mode setup. Our timing registers are shared
 *	but we want to set the PIO timing by default.
 */

static void ninja32_set_piomode(struct ata_port *ap, struct ata_device *adev)
{
	ninja32_configure_piomode(ap, adev, adev->pio_mode - XFER_PIO_0);
}

static struct scsi_host_template ninja32_sht = {
	.module			= THIS_MODULE,
	.name			= DRV_NAME,
	.ioctl			= ata_scsi_ioctl,
	.queuecommand		= ata_scsi_queuecmd,
	.can_queue		= ATA_DEF_QUEUE,
	.this_id		= ATA_SHT_THIS_ID,
	.sg_tablesize		= LIBATA_MAX_PRD,
	.cmd_per_lun		= ATA_SHT_CMD_PER_LUN,
	.emulated		= ATA_SHT_EMULATED,
	.use_clustering		= ATA_SHT_USE_CLUSTERING,
	.proc_name		= DRV_NAME,
	.dma_boundary		= ATA_DMA_BOUNDARY,
	.slave_configure	= ata_scsi_slave_config,
	.slave_destroy		= ata_scsi_slave_destroy,
	.bios_param		= ata_std_bios_param,
};

static struct ata_port_operations ninja32_port_ops = {
	.set_piomode	= ninja32_set_piomode,
	.mode_filter	= ata_pci_default_filter,

	.tf_load	= ata_tf_load,
	.tf_read	= ata_tf_read,
	.check_status 	= ata_check_status,
	.exec_command	= ata_exec_command,
	.dev_select 	= ata_std_dev_select,

	.freeze		= ata_bmdma_freeze,
	.thaw		= ata_bmdma_thaw,
	.error_handler	= ata_bmdma_error_handler,
	.post_internal_cmd = ata_bmdma_post_internal_cmd,
	.cable_detect	= ata_cable_40wire,

	.bmdma_setup 	= ata_bmdma_setup,
	.bmdma_start 	= ata_bmdma_start,
	.bmdma_stop	= ata_bmdma_stop,
	.bmdma_status 	= ata_bmdma_status,

	.qc_prep 	= ata_qc_prep,
	.qc_issue	= ata_qc_issue_prot,

	.data_xfer	= ata_data_xfer,

	.irq_handler	= ata_interrupt,
	.irq_clear	= ata_bmdma_irq_clear,
	.irq_on		= ata_irq_on,

	.port_start	= ata_sff_port_start,
};

static int ninja32_init_one(struct pci_dev *dev, const struct pci_device_id *id)
{
	struct ata_host *host;
	struct ata_port *ap;
	void __iomem *base;
	int rc;
	
	host = ata_host_alloc(&dev->dev, 1);
	if (!host)
		return -ENOMEM;
	ap = host->ports[0];

	/* Set up the PCI device */
	rc = pcim_enable_device(dev);
	if (rc)
		return rc;
	rc = pcim_iomap_regions(dev, 1 << 0, DRV_NAME);
	if (rc == -EBUSY)
		pcim_pin_device(dev);
	if (rc)
		return rc;

	host->iomap = pcim_iomap_table(dev);
	rc = pci_set_dma_mask(dev, ATA_DMA_MASK);
	if (rc)
		return rc;
	rc = pci_set_consistent_dma_mask(dev, ATA_DMA_MASK);
	if (rc)
		return rc;
	pci_set_master(dev);
		
	/* Set up the register mappings */
	base = host->iomap[0];
	if (!base)
		return -ENOMEM;
	ap->ops = &ninja32_port_ops;
	ap->pio_mask = 0x1F;
	ap->flags |= ATA_FLAG_SLAVE_POSS;
	
	ap->ioaddr.cmd_addr = base + 0x10;
	ap->ioaddr.ctl_addr = base + 0x1E;
	ap->ioaddr.altstatus_addr = base + 0x1E;
	ap->ioaddr.bmdma_addr = base;
	ata_std_ports(&ap->ioaddr);
	
	return ata_host_activate(host, dev->irq, ata_interrupt, IRQF_SHARED, &ninja32_sht);
}

static const struct pci_device_id ninja32[] = {
	{ 0x1145, 0xf021, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0},
	{ 0x1145, 0xf024, PCI_ANY_ID, PCI_ANY_ID, 0, 0, 0},
	{ },
};

static struct pci_driver ninja32_pci_driver = {
	.name 		= DRV_NAME,
	.id_table	= ninja32,
	.probe 		= ninja32_init_one,
	.remove		= ata_pci_remove_one
};

static int __init ninja32_init(void)
{
	return pci_register_driver(&ninja32_pci_driver);
}

static void __exit ninja32_exit(void)
{
	pci_unregister_driver(&ninja32_pci_driver);
}

MODULE_AUTHOR("Alan Cox");
MODULE_DESCRIPTION("low-level driver for Ninja32 ATA");
MODULE_LICENSE("GPL");
MODULE_DEVICE_TABLE(pci, ninja32);
MODULE_VERSION(DRV_VERSION);

module_init(ninja32_init);
module_exit(ninja32_exit);

Re: Delkin Cardbus IDE, a.k.a. ASKA "Ninja" chipset

[Mark Lord]

Alan wrote:
> First guess
> 
> /*
>  * pata_ninja32.c 	- Ninja32 PATA for new ATA layer
..

Okay, I tried it on the wife's notebook.
It needs the patch below to enable chip interrupts,
and it is *very* slow on I/O (1MB/sec), slower even
than delkin_cb at present.

But it does work, with this patch:

Signed-off-by: Mark Lord <mlord@pobox.com>
---
(I still have hardware here to send you..)

--- old/pata_ninja32.c	2007-11-13 23:06:21.000000000 -0500
+++ new/pata_ninja32.c	2007-11-13 23:49:24.000000000 -0500
@@ -169,6 +169,7 @@
 	ap->pio_mask = 0x1F;
 	ap->flags |= ATA_FLAG_SLAVE_POSS;
 	
+	iowrite8(0x05, base + 1);
 	ap->ioaddr.cmd_addr = base + 0x10;
 	ap->ioaddr.ctl_addr = base + 0x1E;
 	ap->ioaddr.altstatus_addr = base + 0x1E;

RE: Delkin Cardbus IDE, a.k.a. ASKA "Ninja" chipset

[Iain Barker]

Alan, Mark,

FYI, I had a chance to test the Ninja driver today using two manufacturers CardBus32 CF card adpaters (a Viking and a Lexar).

I can confirm Mark's observation that the access speeds are slower - around half the speed of the earlier Linux PIO driver, and a quarter the performance of WinXP. Test CF card was a SanDisk UltraII as the target, with CB1410 (Yenta compatible TI clone) as the host CB32 controller.

The driver works, but appears to use PIO only (PIO 4 is reported, actual performance is nearer PIO 0)
Should the UDMA modes of the CF be usable?

Linux throughput of 'dd bs=100MD' writing to FAT16 (Dell 3GHz P4 x86 32bit, kernel 2.6.23):

 3.1MB/sec for Linux PCMCIA     (legacy delkin_cb.c )
 1.8MB/sec for Linux CardBus 32 (libata pata_ninja32.c)

For comparison:

 1.4MB/sec for WinXP PCMCIA     (generic driver)
 7.8MB/sec for WinXP CardBus 32 (Lexmark driver)


Note: As a reference I used a SanDisk CF->USB2 adapter connected via an NEC USB2->CardBus32 in this same slot.
It gets >10MB/s to the same card so this is not a limitation with host DMA or the PCI/Yenta socket driver.


The following is the dmesg trace and hdparm in case it's of any use in locating the cause of the slowdown.

pccard: CardBus card inserted into slot 0
PCI: Found 0000:01:00.0 [1145/f021] 000180 00
PCI: Calling quirk c0022948 for 0000:01:00.0
PCI: Succeeded allocate mem resource #1:1000@34000000 for 0000:01:00.0
  got res [34000000:34000fff] bus [34000000:34000fff] flags 200 for BAR 1 of 0000:01:00.0
PCI: moved device 0000:01:00.0 resource 1 (200) to 34000000
PCI: Succeeded allocate I/O resource #0:20@2400 for 0000:01:00.0
  got res [2400:241f] bus [2400:241f] flags 101 for BAR 0 of 0000:01:00.0
PCI: moved device 0000:01:00.0 resource 0 (101) to 2400
PCI: enabling device 0000:01:00.0 (0000 -> 0003)
PCI: Enabling bus mastering for device 0000:01:00.0
PCI: Setting latency timer of device 0000:01:00.0 to 64
scsi0 : pata_ninja32
ata1: PATA max PIO4 cmd 0x00012410 ctl 0x0001241e bmdma 0x00012400 irq 39
ata1.00: CFA: SanDisk SDCFH-2048, HDX 4.04, max MWDMA2
ata1.00: 4001760 sectors, multi 0: LBA
ata1.00: configured for PIO4
scsi 0:0:0:0: Direct-Access     ATA      SanDisk SDCFH-20 HDX  PQ: 0 ANSI: 5
sd 0:0:0:0: [sda] 4001760 512-byte hardware sectors (2049 MB)
sd 0:0:0:0: [sda] Write Protect is off
sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00
sd 0:0:0:0: [sda] Write cache: disabled, read cache: enabled, doesn't support DPO or FUA
sd 0:0:0:0: [sda] 4001760 512-byte hardware sectors (2049 MB)
sd 0:0:0:0: [sda] Write Protect is off
sd 0:0:0:0: [sda] Mode Sense: 00 3a 00 00
sd 0:0:0:0: [sda] Write cache: disabled, read cache: enabled, doesn't support DPO or FUA
 sda: sda1
sd 0:0:0:0: [sda] Attached SCSI removable disk


# hdparm /dev/sda

/dev/sda:
 IO_support    =  0 (default 16-bit)
 readonly      =  0 (off)
 readahead     = 256 (on)
 geometry      = 249/255/63, sectors = 4001760, start = 0

# hdparm -I /dev/sda

/dev/sda:

CompactFlash ATA device, with removable media
        Model Number:       SanDisk SDCFH-2048
        Serial Number:      011908D1907Q3145
        Firmware Revision:  HDX 4.04
Standards:
        Supported: 4
        Likely used: 4
Configuration:
        Logical         max     current
        cylinders       3970    3970
        heads           16      16
        sectors/track   63      63
        --
        CHS current addressable sectors:    4001760
        LBA    user addressable sectors:    4001760
        device size with M = 1024*1024:        1953 MBytes
        device size with M = 1000*1000:        2048 MBytes (2 GB)
Capabilities:
        LBA, IORDY(may be)(cannot be disabled)
        Standby timer values: spec'd by Vendor
        R/W multiple sector transfer: Max = 4   Current = 0
        DMA: mdma0 mdma1 mdma2 (?)
             Cycle time: min=120ns recommended=120ns
        PIO: pio0 pio1 pio2 pio3 pio4
             Cycle time: no flow control=120ns  IORDY flow control=120ns
Commands/features:
        Enabled Supported:
           *    CFA feature set

# hdparm -d1 /dev/sda

/dev/sda:
 setting using_dma to 1 (on)
 HDIO_SET_DMA failed: Inappropriate ioctl for device


Let me know if there's any more useful info I could provide.


regards,

Iain Barker


----


To: Alan Cox <alan@xxxxxxxxxxxxxxxxxxx> 
Subject: Re: Delkin Cardbus IDE, a.k.a. ASKA "Ninja" chipset 
From: Mark Lord <liml@xxxxxx> 
Date: Tue, 13 Nov 2007 23:50:47 -0500 
Cc: Mikael Pettersson <mikpe@xxxxxxxx>, greg.freemyer@xxxxxxxxx, linux-ide@xxxxxxxxxxxxxxx 
In-reply-to: <20071114005718.7b151b37@xxxxxxxxxxxxxxxxx> 
References: <200711031541.lA3FfJ6h006120@xxxxxxxxxxxxxx> <20071103162203.5388a37f@xxxxxxxxxxxxxxxxx> <47323E13.3030205@xxxxxx> <20071107232132.238fdf04@xxxxxxxxxxxxxxxxx> <47324A16.5010205@xxxxxx> <4738B364.5030806@xxxxxx> <20071114005718.7b151b37@xxxxxxxxxxxxxxxxx> 
User-agent: Thunderbird 2.0.0.6 (X11/20070728) 

--------------------------------------------------------------------------------

Alan wrote:

First guess

/*
 * pata_ninja32.c 	- Ninja32 PATA for new ATA layer

..

Okay, I tried it on the wife's notebook.
It needs the patch below to enable chip interrupts,
and it is *very* slow on I/O (1MB/sec), slower even
than delkin_cb at present.

But it does work, with this patch:

Signed-off-by: Mark Lord <mlord@xxxxxxxxx>
---
(I still have hardware here to send you..)

--- old/pata_ninja32.c	2007-11-13 23:06:21.000000000 -0500
+++ new/pata_ninja32.c	2007-11-13 23:49:24.000000000 -0500
@@ -169,6 +169,7 @@
	ap->pio_mask = 0x1F;
	ap->flags |= ATA_FLAG_SLAVE_POSS;
	
+	iowrite8(0x05, base + 1);
	ap->ioaddr.cmd_addr = base + 0x10;
	ap->ioaddr.ctl_addr = base + 0x1E;
	ap->ioaddr.altstatus_addr = base + 0x1E;
-
To unsubscribe from this list: send the line "unsubscribe linux-ide" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Re: Delkin Cardbus IDE, a.k.a. ASKA "Ninja" chipset

[Alan Cox]

> I can confirm Mark's observation that the access speeds are slower - around half the speed of the earlier Linux PIO driver, and a quarter the performance of WinXP. Test CF card was a SanDisk UltraII as the target, with CB1410 (Yenta compatible TI clone) as the host CB32 controller.
> 
> The driver works, but appears to use PIO only (PIO 4 is reported, actual performance is nearer PIO 0)
> Should the UDMA modes of the CF be usable?

Due to lack of documentation - not at the moment. Even the BSD folks
haven't managed to get that bit going. Pulling the card registers for the
device in Windows PIO4 would be most useful.

> Linux throughput of 'dd bs=100MD' writing to FAT16 (Dell 3GHz P4 x86 32bit, kernel 2.6.23):
> 
>  3.1MB/sec for Linux PCMCIA     (legacy delkin_cb.c )
>  1.8MB/sec for Linux CardBus 32 (libata pata_ninja32.c)

Yes. I've not had time to go back and do more investigating.

Alan