Hi Paul Another Issue with the 34xx clock patch. >Sent: Thursday, December 20, 2007 11:05 PM >> The cause is the following check: >> The GPT2 registers lie PER and the check is a hard coded value of CORE_MOD >> The correct check for GPT2 should be OMAP_CM_REGADDR(OMAP3430_PER_MOD, CM_FCLKEN) >> So the function returns in the following check. > >Thanks. There's a temporary patch that was posted on December 3 to the >list about this issue. A better long-term fix is coming (for git >consumption). Let me know if you'd like me to resend... I have put the temporary patch and it works and image does not crash on boot up. However I have seen another problem on enable of 120m_fck ENABLE[usbhost_120m_fck] <3>clock.c: Enable for dpll5_ck without enable code clock.c: Enable for dpll5_ck without enable code <3>clock.c: Enable for dpll5_m2_ck without enable code clock.c: Enable for dpll5_m2_ck without enable code <3>clock.c: Enable for omap_120m_fck without enable code clock.c: Enable for omap_120m_fck without enable code <7>cm_write_reg: writing 0x2 to 0xd8005400 Could you check the logic you are using to enable the DPLL5? > > >- Paul - To unsubscribe from this list: send the line "unsubscribe linux-omap" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
