exporting TCQ functionality to the kernel in SYMBIOS/NCR 53C8XX driver
Hi Matthew,
Does this patch makes sense to you ?
Could you consider this for inclusion into mainline ?
best regards,
Philipp
Signature · 3 lines
: Dipl-Ing Philipp Reisner Tel +43-1-8178292-50 : : LINBIT Information Technologies GmbH Fax +43-1-8178292-82 : : Schönbrunnerstr 244, 1120 Vienna, Austria http://www.linbit.com :
drivers/scsi/sym53c8xx_2/sym_glue.c +9 -1
@@ -494,7 +494,14 @@* Select tagged/untagged. */ lp =sym_lp (tp, sdev->lun); - order = (lp && lp->s.reqtags) ?M_SIMPLE_TAG :0 ; +if (lp && lp->s.reqtags) { +if (cmd->request->flags &REQ_HARDBARRIER ) + order =M_ORDERED_TAG ; +else + order =M_SIMPLE_TAG ; + }else { + order =0 ; + }/* * Queue the SCSI IO.
@@ -1926,6 +1933,7 @@ .proc_info = sym53c8xx_proc_info, .proc_name = NAME53C8XX, #endif + .ordered_tag = 1, };static int attach_count;
Quoted 4 lines · Philipp Reisner
Hi Matthew,
Does this patch makes sense to you ?
Could you consider this for inclusion into mainline ?
Does it actually do anything? The sym2 driver doesn't use the generic midlayer queue tagging code at all yet, so could this flag ever get set?
I must admit, I was hoping you'd done the work to make that happen, but I guess I'll have to do it myself (which will make this patch irrelevant).
Signature · 6 lines
"Next the statesmen will invent cheap lies, putting the blame upon the nation that is attacked, and every man will be glad of those conscience-soothing falsities, and will diligently study them, and refuse to examine any refutations of them; and thus he will by and by convince himself that the war is just, and will thank God for the better sleep he enjoys after this process of grotesque self-deception." -- Mark Twain