(cc'ing Marvell ppl and Mark and quoting whole body for them)
On Sun, Jun 26, 2011 at 12:08:20AM -0700, Marc MERLIN wrote:
> Howdy
>
> I have a dual sil PMP which has been working well enough, and recently moved
> to a new Motherboard.
>
> I had to switch my sil3128 to a sil3132 (PCI-X to PCIe) and it seems to work
> ok.
> I was however trying to switch to a Marvell card that's supposed to be
> faster, but I get errors like these on it:
>
> I think my cables are ok since they work with the sil3132.
> I also notice that the real error seems to be with the PMP itself
> (ata9.15 SError: { BadCRC Handshk } ) and that the rest is just noise.
>
> Is my Marvell card somewhat bad or incompatible with my PMP?
>
> I have 2.6.39.1
>
> gargamel kernel: sata_mv 0000:02:00.0: version 1.28
> gargamel kernel: sata_mv 0000:02:00.0: PCI INT A -> GSI 16 (level, low) -> IRQ 16
> gargamel kernel: sata_mv 0000:02:00.0: Gen-IIE 32 slots 4 ports SCSI mode IRQ via INTx
> gargamel kernel: sata_mv 0000:02:00.0: setting latency timer to 64
> gargamel kernel: scsi8 : sata_mv
> gargamel kernel: scsi9 : sata_mv
> gargamel kernel: scsi10 : sata_mv
> gargamel kernel: scsi11 : sata_mv
> gargamel kernel: ata9: SATA max UDMA/133 mmio m1048576@0xfb800000 port 0xfb822000 irq 16
> gargamel kernel: ata10: SATA max UDMA/133 mmio m1048576@0xfb800000 port 0xfb824000 irq 16
> gargamel kernel: ata11: SATA max UDMA/133 mmio m1048576@0xfb800000 port 0xfb826000 irq 16
> gargamel kernel: ata12: SATA max UDMA/133 mmio m1048576@0xfb800000 port 0xfb828000 irq 16
>
> gargamel kernel: ata10: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
> gargamel kernel: ata10.15: Port Multiplier 1.1, 0x1095:0x3726 r23, 6 ports, feat 0x1/0x9
>
> Mmmh, dmesg also shows this (9.15 is my other PMP plugged into the same card):
>
> Is the card bad, is it possibly a driver issue, or could it still be a sata cable issue?
>
> kernel: ata9.00: qc timeout (cmd 0xec)
> kernel: ata9.00: failed to IDENTIFY (I/O error, err_mask=0x4)
> kernel: ata9.15: hard resetting link
> kernel: ata9.15: SATA link up 3.0 Gbps (SStatus 123 SControl 300)
> kernel: ------------[ cut here ]------------
> kernel: WARNING: at drivers/ata/libata-sff.c:1322 ata_sff_queue_pio_task+0x26/0x44()
> kernel: Hardware name: System Product Name
> kernel: Modules linked in: usbserial pci_hotplug processor thermal_sys wmi parport_pc hwmon button parport r8169 rtc_core snd rtc_lib i2c_i801 xhci_hcd ehci_hcd soundcore sata_mv snd_page_alloc evdev pcspkr iTCO_wdt iTCO_vendor_support intel_agp intel_gtt tpm_tis agpgart usbcore
> kernel: Pid: 1642, comm: scsi_eh_8 Not tainted 2.6.39.1-core2-volpreempt-noide-hm64-20110620 #2
> kernel: Call Trace:
> kernel: [<c0133599>] warn_slowpath_common+0x60/0x75
> kernel: [<c01335bd>] warn_slowpath_null+0xf/0x13
> kernel: [<c0370812>] ata_sff_queue_pio_task+0x26/0x44
> kernel: [<c0370946>] ata_sff_qc_issue+0x116/0x14d
> kernel: [<c03709d6>] ata_bmdma_qc_issue+0x59/0x156
> kernel: [<f84b150b>] mv_qc_issue+0x441/0x44d [sata_mv]
> kernel: [<c028ea13>] ? vsnprintf+0x80/0x2d7
> kernel: [<c014b5bb>] ? up+0x2b/0x2f
> kernel: [<c036309d>] ata_qc_issue+0x30b/0x329
> kernel: [<c03638c2>] ata_exec_internal_sg+0x27f/0x4a0
> kernel: [<c036f84b>] ? ata_sff_tf_read+0x53/0xde
> kernel: [<c0363b41>] ata_exec_internal+0x5e/0x66
> kernel: [<c036a0a3>] ? ata_eh_done+0x12/0x18
> kernel: [<c037213a>] sata_pmp_read+0x66/0x9d
> kernel: [<c0372197>] sata_pmp_read_gscr+0x26/0x65
> kernel: [<c0371e77>] ? ata_sff_softreset+0x150/0x150
> kernel: [<c03727b8>] sata_pmp_error_handler+0x2ff/0xa42
> kernel: [<c01289e3>] ? dequeue_task_fair+0x1fc/0x204
> kernel: [<c03704f9>] ? ata_sff_drain_fifo+0x5a/0x5a
> kernel: [<f84b0f41>] ? mv_port_start+0x19f/0x19f [sata_mv]
> kernel: [<f84b0c50>] ? mv_pmp_hardreset+0x8c/0x8c [sata_mv]
> kernel: [<c0371e77>] ? ata_sff_softreset+0x150/0x150
> kernel: [<c044194d>] ? __mutex_lock_slowpath+0x1f2/0x1fa
> kernel: [<c013cadd>] ? lock_timer_base+0x1f/0x3e
> kernel: [<f84b0bbf>] mv_pmp_error_handler+0x60/0x65 [sata_mv]
> kernel: [<c036e283>] ata_scsi_port_error_handler+0x206/0x522
> kernel: [<c01448f6>] ? cancel_delayed_work_sync+0xb/0xd
> kernel: [<c036e60c>] ata_scsi_error+0x6d/0x8f
> kernel: [<c032ad17>] ? scsi_eh_get_sense+0x16d/0x16d
> kernel: [<c032ae1a>] scsi_error_handler+0x103/0x507
> kernel: [<c012750b>] ? complete+0x34/0x3e
> kernel: [<c032ad17>] ? scsi_eh_get_sense+0x16d/0x16d
> kernel: [<c01476c0>] kthread+0x64/0x69
> kernel: [<c014765c>] ? kthread_worker_fn+0x119/0x119
> kernel: [<c0443bbe>] kernel_thread_helper+0x6/0xd
>
> This is the error that happens a lot with the sata_mv card, but not the sil24 one:
>
> ata9.15: exception Emask 0x100 SAct 0x0 SErr 0x600000 action 0x6 frozen
> ata9.15: edma_err_cause=02320080 pp_flags=00000007, EDMA self-disable
> ata9.15: SError: { BadCRC Handshk }
> ata9.00: exception Emask 0x100 SAct 0x2 SErr 0x0 action 0x6 frozen
> ata9.00: failed command: READ FPDMA QUEUED
> ata9.00: cmd 60/78:08:e7:0f:b8/02:00:01:00:00/40 tag 1 ncq 323584 in
> res 40/00:2c:c7:0f:b8/00:00:01:00:00/40 Emask 0x100 (unknown error)
> ata9.00: status: { DRDY }
> ata9.01: exception Emask 0x100 SAct 0x8 SErr 0x0 action 0x6 frozen
> ata9.01: failed command: READ FPDMA QUEUED
> ata9.01: cmd 60/80:18:df:0f:b8/02:00:01:00:00/40 tag 3 ncq 327680 in
> res 40/00:2c:c7:0f:b8/00:00:01:00:00/40 Emask 0x100 (unknown error)
> ata9.01: status: { DRDY }
> ata9.02: exception Emask 0x100 SAct 0x1 SErr 0x0 action 0x6 frozen
> ata9.02: failed command: READ FPDMA QUEUED
> ata9.02: cmd 60/80:00:df:0f:b8/02:00:01:00:00/40 tag 0 ncq 327680 in
> res 40/00:2c:c7:0f:b8/00:00:01:00:00/40 Emask 0x100 (unknown error)
> ata9.02: status: { DRDY }
> ata9.03: exception Emask 0x100 SAct 0x74 SErr 0x0 action 0x6 frozen
> ata9.03: failed command: WRITE FPDMA QUEUED
> ata9.03: cmd 61/08:10:d7:0f:b8/00:00:01:00:00/40 tag 2 ncq 4096 out
> res 40/00:2c:c7:0f:b8/00:00:01:00:00/40 Emask 0x100 (unknown error)
> ata9.03: status: { DRDY }
> ata9.03: failed command: WRITE FPDMA QUEUED
> ata9.03: cmd 61/88:20:3f:0c:b8/03:00:01:00:00/40 tag 4 ncq 462848 out
> res 40/00:2c:c7:0f:b8/00:00:01:00:00/40 Emask 0x100 (unknown error)
> ata9.03: status: { DRDY }
> ata9.03: failed command: WRITE FPDMA QUEUED
> ata9.03: cmd 61/08:28:c7:0f:b8/00:00:01:00:00/40 tag 5 ncq 4096 out
> res 40/00:2c:c7:0f:b8/00:00:01:00:00/40 Emask 0x100 (unknown error)
> ata9.03: status: { DRDY }
> ata9.03: failed command: WRITE FPDMA QUEUED
> ata9.03: cmd 61/08:30:cf:0f:b8/00:00:01:00:00/40 tag 6 ncq 4096 out
> res 40/00:2c:c7:0f:b8/00:00:01:00:00/40 Emask 0x100 (unknown error)
> ata9.03: status: { DRDY }
> ata9.04: exception Emask 0x100 SAct 0x80 SErr 0x0 action 0x6 frozen
> ata9.04: failed command: READ FPDMA QUEUED
> ata9.04: cmd 60/80:38:df:0f:b8/02:00:01:00:00/40 tag 7 ncq 327680 in
> res 40/00:2c:c7:0f:b8/00:00:01:00:00/40 Emask 0x100 (unknown error)
> ata9.04: status: { DRDY }
> ata9.05: exception Emask 0x100 SAct 0x0 SErr 0x0 action 0x6 frozen
> ata9.15: exception Emask 0x100 SAct 0x0 SErr 0x600000 action 0x6 frozen
> ata9.15: edma_err_cause=02320080 pp_flags=00000007, EDMA self-disable
> ata9.15: SError: { BadCRC Handshk }
> ata9.00: exception Emask 0x100 SAct 0x11110611 SErr 0x0 action 0x6 frozen
> ata9.00: failed command: READ FPDMA QUEUED
> ata9.00: cmd 60/08:00:17:de:b8/00:00:01:00:00/40 tag 0 ncq 4096 in
> res 40/00:1c:6f:da:b8/00:00:01:00:00/40 Emask 0x100 (unknown error)
> ata9.00: status: { DRDY }
> ata9.00: failed command: READ FPDMA QUEUED
> ata9.00: cmd 60/08:20:1f:de:b8/00:00:01:00:00/40 tag 4 ncq 4096 in
> res 40/00:1c:6f:da:b8/00:00:01:00:00/40 Emask 0x100 (unknown error)
> ata9.00: status: { DRDY }
> ata9.00: failed command: READ FPDMA QUEUED
> ata9.00: cmd 60/98:48:7f:da:b8/03:00:01:00:00/40 tag 9 ncq 471040 in
> res 40/00:1c:6f:da:b8/00:00:01:00:00/40 Emask 0x100 (unknown error)
> ata9.00: status: { DRDY }
> ata9.00: failed command: READ FPDMA QUEUED
> ata9.00: cmd 60/08:50:27:de:b8/00:00:01:00:00/40 tag 10 ncq 4096 in
> res 40/00:1c:6f:da:b8/00:00:01:00:00/40 Emask 0x100 (unknown error)
> ata9.00: status: { DRDY }
This sounds a lot like another recent PMP problem we had with marvell.
It could be that FIS-based switching doesn't work quite as well for
some reason.
Thanks.
--
tejun
--
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
