Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Date:   Fri, 18 Nov 2022 12:31:50 +0000
From:   Will Deacon <will@kernel.org>
To:     Mark Rutland <mark.rutland@arm.com>
Cc:     linux-kernel@vger.kernel.org, catalin.marinas@arm.com,
        linux-arm-kernel@lists.infradead.org, mhiramat@kernel.org,
        revest@chromium.org, rostedt@goodmis.org
Subject: Re: [PATCH v2 4/4] ftrace: arm64: move from REGS to ARGS
Message-ID: <20221118123149.GB3697@willie-the-truck>
References: <20221103170520.931305-1-mark.rutland@arm.com>
 <20221103170520.931305-5-mark.rutland@arm.com>
 <20221115112701.GB32523@willie-the-truck>
 <Y3YRqvfYOP+RBk8r@FVFF77S0Q05N>
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <Y3YRqvfYOP+RBk8r@FVFF77S0Q05N>
User-Agent: Mutt/1.10.1 (2018-07-13)
Precedence: bulk

On Thu, Nov 17, 2022 at 10:52:15AM +0000, Mark Rutland wrote:
> On Tue, Nov 15, 2022 at 11:27:03AM +0000, Will Deacon wrote:
> > On Thu, Nov 03, 2022 at 05:05:20PM +0000, Mark Rutland wrote:
> > > This commit replaces arm64's support for FTRACE_WITH_REGS with support
> > > for FTRACE_WITH_ARGS. This removes some overhead and complexity, and
> > > removes some latent issues with inconsistent presentation of struct
> > > pt_regs (which can only be reliably saved/restored at exception
> > > boundaries).
> > 
> > [...]
> > 
> > > @@ -78,10 +77,71 @@ static inline unsigned long ftrace_call_adjust(unsigned long addr)
> > >  	return addr;
> > >  }
> > >  
> > > -#ifdef CONFIG_DYNAMIC_FTRACE_WITH_REGS
> > > +#ifdef CONFIG_DYNAMIC_FTRACE_WITH_ARGS
> > >  struct dyn_ftrace;
> > >  struct ftrace_ops;
> > > -struct ftrace_regs;
> > > +
> > > +#define arch_ftrace_get_regs(regs) NULL
> > > +
> > > +struct ftrace_regs {
> > > +	/* x0 - x8 */
> > > +	unsigned long regs[9];
> > > +	unsigned long __unused;
> > > +
> > > +	unsigned long fp;
> > > +	unsigned long lr;
> > > +
> > > +	unsigned long sp;
> > > +	unsigned long pc;
> > > +};
> > > +
> > > +static __always_inline unsigned long
> > > +ftrace_regs_get_instruction_pointer(const struct ftrace_regs *fregs)
> > > +{
> > > +	return fregs->pc;
> > > +}
> > > +
> > > +static __always_inline void
> > > +ftrace_regs_set_instruction_pointer(struct ftrace_regs *fregs,
> > > +				    unsigned long pc)
> > > +{
> > > +	fregs->pc = pc;
> > > +}
> > > +
> > > +static __always_inline unsigned long
> > > +ftrace_regs_get_stack_pointer(const struct ftrace_regs *fregs)
> > > +{
> > > +	return fregs->sp;
> > > +}
> > > +
> > > +static __always_inline unsigned long
> > > +ftrace_regs_get_argument(struct ftrace_regs *fregs, unsigned int n)
> > > +{
> > > +	if (n < 8)
> > > +		return fregs->regs[n];
> > 
> > Where does this '8' come from?
> 
> Because in AAPCS64 the arguments are in x0 to x7, as mentioned in the commit
> message:
> 
> | Per AAPCS64, all function call argument and return values are held in
> | the following GPRs:
> | 
> | * X0 - X7 : parameter / result registers
> | * X8      : indirect result location register
> | * SP      : stack pointer (AKA SP)
> 
> The 'indirect result location register' would be used when returning large
> structures, and isn't a function argument as such.

Ah gotcha, I was mainly wondering about the role of x8 in 'struct
ftrace_regs', but now I see that the FETCH_OP_REG might want to get at that.

Will