From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S933483AbcBCHXZ (ORCPT ); Wed, 3 Feb 2016 02:23:25 -0500 Received: from mail-pa0-f44.google.com ([209.85.220.44]:36132 "EHLO mail-pa0-f44.google.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S933155AbcBCHXY (ORCPT ); Wed, 3 Feb 2016 02:23:24 -0500 Subject: Re: [PATCH v6 1/9] ppc64 (le): prepare for -mprofile-kernel To: Torsten Duwe , Steven Rostedt , Michael Ellerman References: <20160125170459.14DB7692CE@newverein.lst.de> <20160125170723.D2CCE692CE@newverein.lst.de> Cc: Jiri Kosina , linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org, live-patching@vger.kernel.org From: AKASHI Takahiro Message-ID: <56B1AAE5.10500@linaro.org> Date: Wed, 3 Feb 2016 16:23:17 +0900 User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:38.0) Gecko/20100101 Thunderbird/38.2.0 MIME-Version: 1.0 In-Reply-To: <20160125170723.D2CCE692CE@newverein.lst.de> Content-Type: text/plain; charset=windows-1252; format=flowed Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Hi, On 01/26/2016 12:26 AM, Torsten Duwe wrote: > The gcc switch -mprofile-kernel, available for ppc64 on gcc > 4.8.5, > allows to call _mcount very early in the function, which low-level > ASM code and code patching functions need to consider. > Especially the link register and the parameter registers are still > alive and not yet saved into a new stack frame. I'm thinking of implementing live patch support *for arm64*, and as part of those efforts, we are proposing[1] a new *generic* gcc option, -fprolog-add=N. This option will insert N nop instructions at the beginning of each function. So we have to initialize those codes at the boot time to later utilize them for FTRACE_WITH_REGS. Other than that, it will work similarly with -mfentry on x86 (and -mprofile-kernel?). I'm totally unfamiliar with ppc architecture, but just wondering whether this option will also be useful for other architectures. I will really appreciate you if you share your thoughts with me, please? [1] https://gcc.gnu.org/ml/gcc/2015-05/msg00267.html, and https://gcc.gnu.org/ml/gcc/2015-10/msg00090.html Thanks, -Takahiro AKASHI > Signed-off-by: Torsten Duwe > --- > arch/powerpc/kernel/entry_64.S | 45 +++++++++++++++++++++++++++++++++++++++-- > arch/powerpc/kernel/ftrace.c | 12 +++++++++-- > arch/powerpc/kernel/module_64.c | 14 +++++++++++++ > 3 files changed, 67 insertions(+), 4 deletions(-) > > diff --git a/arch/powerpc/kernel/entry_64.S b/arch/powerpc/kernel/entry_64.S > index a94f155..e7cd043 100644 > --- a/arch/powerpc/kernel/entry_64.S > +++ b/arch/powerpc/kernel/entry_64.S > @@ -1206,7 +1206,12 @@ _GLOBAL(enter_prom) > #ifdef CONFIG_DYNAMIC_FTRACE > _GLOBAL(mcount) > _GLOBAL(_mcount) > - blr > + std r0,LRSAVE(r1) /* gcc6 does this _after_ this call _only_ */ > + mflr r0 > + mtctr r0 > + ld r0,LRSAVE(r1) > + mtlr r0 > + bctr > > _GLOBAL_TOC(ftrace_caller) > /* Taken from output of objdump from lib64/glibc */ > @@ -1262,13 +1267,28 @@ _GLOBAL(ftrace_stub) > > #ifdef CONFIG_FUNCTION_GRAPH_TRACER > _GLOBAL(ftrace_graph_caller) > +#ifdef CC_USING_MPROFILE_KERNEL > + /* with -mprofile-kernel, parameter regs are still alive at _mcount */ > + std r10, 104(r1) > + std r9, 96(r1) > + std r8, 88(r1) > + std r7, 80(r1) > + std r6, 72(r1) > + std r5, 64(r1) > + std r4, 56(r1) > + std r3, 48(r1) > + mfctr r4 /* ftrace_caller has moved local addr here */ > + std r4, 40(r1) > + mflr r3 /* ftrace_caller has restored LR from stack */ > +#else > /* load r4 with local address */ > ld r4, 128(r1) > - subi r4, r4, MCOUNT_INSN_SIZE > > /* Grab the LR out of the caller stack frame */ > ld r11, 112(r1) > ld r3, 16(r11) > +#endif > + subi r4, r4, MCOUNT_INSN_SIZE > > bl prepare_ftrace_return > nop > @@ -1277,6 +1297,26 @@ _GLOBAL(ftrace_graph_caller) > * prepare_ftrace_return gives us the address we divert to. > * Change the LR in the callers stack frame to this. > */ > + > +#ifdef CC_USING_MPROFILE_KERNEL > + mtlr r3 > + > + ld r0, 40(r1) > + mtctr r0 > + ld r10, 104(r1) > + ld r9, 96(r1) > + ld r8, 88(r1) > + ld r7, 80(r1) > + ld r6, 72(r1) > + ld r5, 64(r1) > + ld r4, 56(r1) > + ld r3, 48(r1) > + > + addi r1, r1, 112 > + mflr r0 > + std r0, LRSAVE(r1) > + bctr > +#else > ld r11, 112(r1) > std r3, 16(r11) > > @@ -1284,6 +1324,7 @@ _GLOBAL(ftrace_graph_caller) > mtlr r0 > addi r1, r1, 112 > blr > +#endif > > _GLOBAL(return_to_handler) > /* need to save return values */ > diff --git a/arch/powerpc/kernel/ftrace.c b/arch/powerpc/kernel/ftrace.c > index 44d4d8e..080c525 100644 > --- a/arch/powerpc/kernel/ftrace.c > +++ b/arch/powerpc/kernel/ftrace.c > @@ -306,11 +306,19 @@ __ftrace_make_call(struct dyn_ftrace *rec, unsigned long addr) > * The load offset is different depending on the ABI. For simplicity > * just mask it out when doing the compare. > */ > +#ifndef CC_USING_MPROFILE_KERNEL > if ((op[0] != 0x48000008) || ((op[1] & 0xffff0000) != 0xe8410000)) { > - pr_err("Unexpected call sequence: %x %x\n", op[0], op[1]); > + pr_err("Unexpected call sequence at %p: %x %x\n", > + ip, op[0], op[1]); > return -EINVAL; > } > - > +#else > + /* look for patched "NOP" on ppc64 with -mprofile-kernel */ > + if (op[0] != 0x60000000) { > + pr_err("Unexpected call at %p: %x\n", ip, op[0]); > + return -EINVAL; > + } > +#endif > /* If we never set up a trampoline to ftrace_caller, then bail */ > if (!rec->arch.mod->arch.tramp) { > pr_err("No ftrace trampoline\n"); > diff --git a/arch/powerpc/kernel/module_64.c b/arch/powerpc/kernel/module_64.c > index 6838451..30f6be1 100644 > --- a/arch/powerpc/kernel/module_64.c > +++ b/arch/powerpc/kernel/module_64.c > @@ -475,6 +475,20 @@ static unsigned long stub_for_addr(Elf64_Shdr *sechdrs, > static int restore_r2(u32 *instruction, struct module *me) > { > if (*instruction != PPC_INST_NOP) { > +#ifdef CC_USING_MPROFILE_KERNEL > + /* -mprofile_kernel sequence starting with > + * mflr r0 and maybe std r0, LRSAVE(r1) > + */ > + if ((instruction[-3] == 0x7c0802a6 && > + instruction[-2] == 0xf8010010) || > + instruction[-2] == 0x7c0802a6) { > + /* Nothing to be done here, it's an _mcount > + * call location and r2 will have to be > + * restored in the _mcount function. > + */ > + return 1; > + }; > +#endif > pr_err("%s: Expect noop after relocate, got %08x\n", > me->name, *instruction); > return 0; >