Re: [RFC PATCH] powerpc/ftrace: Refactoring and support for -fpatchable-function-entry

2023-06-07 Thread Naveen N Rao
Christophe Leroy wrote: Le 23/05/2023 à 11:31, Naveen N Rao a écrit : Christophe Leroy wrote: Ok, I simplified this further, and this is as close to the previous fast path as we can get (applies atop the original RFC). The only difference left is the ftrace_rec iterator. That's not

Re: [RFC PATCH] powerpc/ftrace: Refactoring and support for -fpatchable-function-entry

2023-05-25 Thread Christophe Leroy
Le 23/05/2023 à 11:31, Naveen N Rao a écrit : > Christophe Leroy wrote: >> >> That's better, but still more time than original implementation: >> >> +20% to activate function tracer (was +40% with your RFC) >> +21% to activate nop tracer (was +24% with your RFC) >> >> perf record (without strict

Re: [RFC PATCH] powerpc/ftrace: Refactoring and support for -fpatchable-function-entry

2023-05-23 Thread Steven Rostedt
On Sat, 20 May 2023 23:58:01 +0530 Naveen N Rao wrote: > > > > At the begining of ftrace_replace_code(), don't you miss: > > > > if (unlikely(ftrace_disabled)) > > return; > > ftrace_disabled is a static, so it can't be tested here. FWIW, x86 also > implements

Re: [RFC PATCH] powerpc/ftrace: Refactoring and support for -fpatchable-function-entry

2023-05-23 Thread Naveen N Rao
Christophe Leroy wrote: That's better, but still more time than original implementation: +20% to activate function tracer (was +40% with your RFC) +21% to activate nop tracer (was +24% with your RFC) perf record (without strict kernel rwx) : 17.75% echo [kernel.kallsyms] [k]

Re: [RFC PATCH] powerpc/ftrace: Refactoring and support for -fpatchable-function-entry

2023-05-21 Thread Christophe Leroy
Le 20/05/2023 à 20:17, Naveen N Rao a écrit : > Christophe Leroy wrote: >> >> >> Le 20/05/2023 à 12:34, Christophe Leroy a écrit : >>> >>> >>> Le 19/05/2023 à 21:26, Naveen N Rao a écrit : [Vous ne recevez pas souvent de courriers de nav...@kernel.org. Découvrez pourquoi ceci est

Re: [RFC PATCH] powerpc/ftrace: Refactoring and support for -fpatchable-function-entry

2023-05-20 Thread Naveen N Rao
Christophe Leroy wrote: Le 19/05/2023 à 21:26, Naveen N Rao a écrit : [Vous ne recevez pas souvent de courriers de nav...@kernel.org. Découvrez pourquoi ceci est important à https://aka.ms/LearnAboutSenderIdentification ] Refactor ftrace code and move to using ftrace_replace_code() to help

Re: [RFC PATCH] powerpc/ftrace: Refactoring and support for -fpatchable-function-entry

2023-05-20 Thread Naveen N Rao
Christophe Leroy wrote: Le 20/05/2023 à 12:34, Christophe Leroy a écrit : Le 19/05/2023 à 21:26, Naveen N Rao a écrit : [Vous ne recevez pas souvent de courriers de nav...@kernel.org. Découvrez pourquoi ceci est important à https://aka.ms/LearnAboutSenderIdentification ] Refactor ftrace

Re: [RFC PATCH] powerpc/ftrace: Refactoring and support for -fpatchable-function-entry

2023-05-20 Thread Christophe Leroy
Le 20/05/2023 à 18:28, Christophe Leroy a écrit : > > > Le 20/05/2023 à 12:34, Christophe Leroy a écrit : >> >> >> Le 19/05/2023 à 21:26, Naveen N Rao a écrit : >>> [Vous ne recevez pas souvent de courriers de nav...@kernel.org. >>> Découvrez pourquoi ceci est important à >>>

Re: [RFC PATCH] powerpc/ftrace: Refactoring and support for -fpatchable-function-entry

2023-05-20 Thread Christophe Leroy
Le 20/05/2023 à 12:34, Christophe Leroy a écrit : > > > Le 19/05/2023 à 21:26, Naveen N Rao a écrit : >> [Vous ne recevez pas souvent de courriers de nav...@kernel.org. >> Découvrez pourquoi ceci est important à >> https://aka.ms/LearnAboutSenderIdentification ] >> >> Refactor ftrace code

Re: [RFC PATCH] powerpc/ftrace: Refactoring and support for -fpatchable-function-entry

2023-05-20 Thread Christophe Leroy
Le 19/05/2023 à 21:26, Naveen N Rao a écrit : > [Vous ne recevez pas souvent de courriers de nav...@kernel.org. Découvrez > pourquoi ceci est important à https://aka.ms/LearnAboutSenderIdentification ] > > Refactor ftrace code and move to using ftrace_replace_code() to help > simplify and make

[RFC PATCH] powerpc/ftrace: Refactoring and support for -fpatchable-function-entry

2023-05-19 Thread Naveen N Rao
Refactor ftrace code and move to using ftrace_replace_code() to help simplify and make the code more maintainable. - The existing ftrace.c code is moved to a separate file so that ppc64 elfv1 and clang -pg only support continue. This makes it possible to converge ppc32 and ppc64 support