From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from e23smtp02.au.ibm.com (e23smtp02.au.ibm.com [202.81.31.144]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (Client CN "e23smtp02.au.ibm.com", Issuer "Equifax" (verified OK)) by ozlabs.org (Postfix) with ESMTPS id 9E2EFB7CF8 for ; Tue, 30 Mar 2010 21:00:17 +1100 (EST) Received: from d23relay03.au.ibm.com (d23relay03.au.ibm.com [202.81.31.245]) by e23smtp02.au.ibm.com (8.14.3/8.13.1) with ESMTP id o2U9uvkU006389 for ; Tue, 30 Mar 2010 20:56:57 +1100 Received: from d23av02.au.ibm.com (d23av02.au.ibm.com [9.190.235.138]) by d23relay03.au.ibm.com (8.13.8/8.13.8/NCO v10.0) with ESMTP id o2UA0GP01433840 for ; Tue, 30 Mar 2010 21:00:16 +1100 Received: from d23av02.au.ibm.com (loopback [127.0.0.1]) by d23av02.au.ibm.com (8.14.3/8.13.1/NCO v10.0 AVout) with ESMTP id o2UA0FKl028392 for ; Tue, 30 Mar 2010 21:00:16 +1100 Date: Tue, 30 Mar 2010 15:29:25 +0530 From: "K.Prasad" To: "linuxppc-dev@ozlabs.org" Subject: [Patch 1/2] PPC64-HWBKPT: Disable interrupts for data breakpoint exceptions Message-ID: <20100330095925.GB14403@in.ibm.com> References: <20100330095040.565675261@pr> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii Cc: Michael Neuling , Benjamin Herrenschmidt , shaggy@linux.vnet.ibm.com, Frederic Weisbecker , David Gibson , paulus@samba.org, Alan Stern , "K.Prasad" , Roland McGrath List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Data address breakpoint exceptions are currently handled along with page-faults which require interrupts to remain in enabled state. Since exception handling for data breakpoints aren't pre-empt safe, we handle them separately. Signed-off-by: K.Prasad --- arch/powerpc/kernel/exceptions-64s.S | 13 ++++++++++++- arch/powerpc/mm/fault.c | 5 +++-- 2 files changed, 15 insertions(+), 3 deletions(-) Index: linux-2.6.ppc64_test/arch/powerpc/kernel/exceptions-64s.S =================================================================== --- linux-2.6.ppc64_test.orig/arch/powerpc/kernel/exceptions-64s.S +++ linux-2.6.ppc64_test/arch/powerpc/kernel/exceptions-64s.S @@ -735,8 +735,11 @@ _STATIC(do_hash_page) std r3,_DAR(r1) std r4,_DSISR(r1) - andis. r0,r4,0xa450 /* weird error? */ + andis. r0,r4,0xa410 /* weird error? */ bne- handle_page_fault /* if not, try to insert a HPTE */ + andis. r0,r4,DSISR_DABRMATCH@h + bne- handle_dabr_fault + BEGIN_FTR_SECTION andis. r0,r4,0x0020 /* Is it a segment table fault? */ bne- do_ste_alloc /* If so handle it */ @@ -823,6 +826,14 @@ END_FW_FTR_SECTION_IFCLR(FW_FEATURE_ISER bl .raw_local_irq_restore b 11f +/* We have a data breakpoint exception - handle it */ +handle_dabr_fault: + ld r4,_DAR(r1) + ld r5,_DSISR(r1) + addi r3,r1,STACK_FRAME_OVERHEAD + bl .do_dabr + b .ret_from_except_lite + /* Here we have a page fault that hash_page can't handle. */ handle_page_fault: ENABLE_INTS Index: linux-2.6.ppc64_test/arch/powerpc/mm/fault.c =================================================================== --- linux-2.6.ppc64_test.orig/arch/powerpc/mm/fault.c +++ linux-2.6.ppc64_test/arch/powerpc/mm/fault.c @@ -151,13 +151,14 @@ int __kprobes do_page_fault(struct pt_re if (!user_mode(regs) && (address >= TASK_SIZE)) return SIGSEGV; -#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE)) +#if !(defined(CONFIG_4xx) || defined(CONFIG_BOOKE) || \ + defined(CONFIG_PPC_BOOK3S_64)) if (error_code & DSISR_DABRMATCH) { /* DABR match */ do_dabr(regs, address, error_code); return 0; } -#endif /* !(CONFIG_4xx || CONFIG_BOOKE)*/ +#endif if (in_atomic() || mm == NULL) { if (!user_mode(regs))