Return-Path: Received: from mail.lixom.net (lixom.net [66.141.50.11]) by ozlabs.org (Postfix) with ESMTP id BD2D7DDEDE for ; Mon, 26 Feb 2007 17:24:37 +1100 (EST) Date: Mon, 26 Feb 2007 00:35:14 -0600 To: paulus@samba.org Subject: [PATCH] No DEEPNAP on 970MP 1.0 Message-ID: <20070226063514.GA16700@lixom.net> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii From: olof@lixom.net (Olof Johansson) Cc: linuxppc-dev@ozlabs.org List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , 970MP rev 1.0 is reported to have nonworking DEEPNAP support, we've had bug reports of lockups on those machines. Appearantly Apple used them on some dual-core dual-cpu systems. Rev 1.1 is OK, and that's the one that all 4-way systems seem to use. Signed-off-by: Olof Johansson --- Paul, please consider for 2.6.21 and 2.6.20-stable, we've seen bugreports on this from users. diff --git a/arch/powerpc/kernel/cputable.c b/arch/powerpc/kernel/cputable.c index 7ec4ac7..e4006dc 100644 --- a/arch/powerpc/kernel/cputable.c +++ b/arch/powerpc/kernel/cputable.c @@ -225,6 +225,22 @@ #ifdef CONFIG_PPC64 .oprofile_type = PPC_OPROFILE_POWER4, .platform = "ppc970", }, + { /* PPC970MP DD1.0 - no DEEPNAP, use regular 970 init */ + .pvr_mask = 0xffffffff, + .pvr_value = 0x00440100, + .cpu_name = "PPC970MP", + .cpu_features = CPU_FTRS_PPC970, + .cpu_user_features = COMMON_USER_POWER4 | + PPC_FEATURE_HAS_ALTIVEC_COMP, + .icache_bsize = 128, + .dcache_bsize = 128, + .num_pmcs = 8, + .cpu_setup = __setup_cpu_ppc970, + .cpu_restore = __restore_cpu_ppc970, + .oprofile_cpu_type = "ppc64/970MP", + .oprofile_type = PPC_OPROFILE_POWER4, + .platform = "ppc970", + }, { /* PPC970MP */ .pvr_mask = 0xffff0000, .pvr_value = 0x00440000,