** Resending in TEXT/PLAIN, earlier sent email bounce back ** Adding linux-scsi group to this email... I would like to check with you if anyone had encountered similar issues with upper layers older libsas/libata drivers. It would be of great help if anyone can shed some light on this issue. Please advise! Sincerely, Mahesh From: Tony Ruiz Sent: Tuesday, February 05, 2013 6:15 AM To: 'James Bottomley' Cc: Mahesh Rajashekhara Subject: Linux Libsas/Libata updates/releases Hi James, I am the manager for the PMC-Sierra driver team working on the arcsas and pmc8001 drivers. We are in the Beta testing phase of the pmc8001 Linux driver with newer ASIC support. When we use the updated libsas/libata libraries like those in RHEL 6.3 or SuSe SP3 Beta, medium error handling works fine. When we use kernels with older libsas/libata libraries with medium error (details below) the system crashes. We worked with SuSe and they provided the updated libraries which work well and asked us to opened a bug with SLES to make sure they include the latest into their kernel: "798738 - SLES 11 SP2 does not contain several libsas/libata backport commits for handling ATA errors." My question is: - Is there a recommend way to release our driver with these updated libraries? - If there are none, is there an easy solution for customers' to update only these components instead of the entire kernel? Thanks in advanced. Tony Ruiz Manager of Host Software PMC-Sierra, Inc. ==================================================== Details of the issue: 1. If a target/drive has medium error and IO has been aborted, during this phase LibATA has some issues in this Error Handling Path and system eventually crashes. a. This is very consistent with SUSE11SP2 (3.0.13) Kernel, but the private branch of SLES11SP3 (3.0.57) which is still in BETA has all the LibATA Error Handling back ported, this resolved all these error handling issues. b. This very same issue with Debian 6.0.3 till 6.0.6 c. With RHEL6.3 everything is working fine, since the Libsas/LibATA changes are back-ported from 3.4 kernels to their RHEL6.3 Kernel (2.6.32-279). Sequence: - Medium Error Reported by drive for an IO either Read/Write_FPDMA (NCQ Command) - Firmware Raise NCQ Event - Holds the IO expects RLE and puts the drive into Error State - Internally driver is issuing RLE because we don't have the IO Context - FW/Drive processes RLE - Driver Receives RLE Response - Issues Abort ALL (as per SATA Spec) - FW releases all IO's by completing as IO Aborted - Driver Completes these to Midlayer In the Successful case the sequence follows: - Receives RLE, but driver is faking it now - then receives Hard-Resetting Link - Domain Revalidation - Rediscover - IO's Successfully restarted. In the Failure case the sequence follows: - System hangs -- To unsubscribe from this list: send the line "unsubscribe linux-scsi" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
