Received-SPF: pass (google.com: domain of linux-kernel+bounces-142047-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.199.223 as permitted sender) client-ip=147.75.199.223;
Date: Thu, 11 Apr 2024 23:37:42 -0700
From: Pawan Gupta <pawan.kumar.gupta@linux.intel.com>
To: Josh Poimboeuf <jpoimboe@kernel.org>
Cc: x86@kernel.org, linux-kernel@vger.kernel.org,
	Linus Torvalds <torvalds@linux-foundation.org>,
	Daniel Sneddon <daniel.sneddon@linux.intel.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Alexandre Chartre <alexandre.chartre@oracle.com>,
	Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	Sean Christopherson <seanjc@google.com>,
	Andrew Cooper <andrew.cooper3@citrix.com>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	Nikolay Borisov <nik.borisov@suse.com>,
	KP Singh <kpsingh@kernel.org>, Waiman Long <longman@redhat.com>,
	Borislav Petkov <bp@alien8.de>
Subject: Re: [PATCH 5/7] x86/bugs: Only harden syscalls when needed
Message-ID: <20240412063742.bsy7jrpbvqydntre@desk>
References: <cover.1712813475.git.jpoimboe@kernel.org>
 <97befd7c1e008797734dee05181c49056ff6de57.1712813475.git.jpoimboe@kernel.org>
 <20240412062844.p5j33tmqjggladgl@desk>
Precedence: bulk
MIME-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Content-Disposition: inline
In-Reply-To: <20240412062844.p5j33tmqjggladgl@desk>

On Thu, Apr 11, 2024 at 11:28:54PM -0700, Pawan Gupta wrote:
> > +#define __do_syscall(table, func_direct, nr, regs)			\
> > +({									\
> > +	unsigned long __rax, __rdi, __rsi;				\
> > +									\
> > +	asm_inline volatile(						\
> > +		ALTERNATIVE("call " __stringify(func_direct) "\n\t",	\
> > +			    ANNOTATE_RETPOLINE_SAFE			\
> > +			    "call *%[func_ptr]\n\t",			\
> > +			    X86_FEATURE_INDIRECT_SAFE)			\
> > +		: "=D" (__rdi), "=S" (__rsi), "=a" (__rax),		\
> > +		  ASM_CALL_CONSTRAINT					\
> > +		: "0" (regs), "1" (nr), [func_ptr] "r" (table[nr])	\
> > +		: "rdx", "rcx", "r8", "r9", "r10", "r11",		\
> > +		  "cc", "memory");					\
> > +									\
> > +	__rax;								\
> > +})
> 
> This is a nice implementation, but I think we can avoid the complexity
> by using cpu_feature_enabled(). As cpu_feature_enabled() is also runtime
> patched, atleast the likely() path should be comparable to this. Please
> let me know if you have any concerns with this approach.
> 
> ---
> diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c
> index 6de50b80702e..7c5332b83246 100644
> --- a/arch/x86/entry/common.c
> +++ b/arch/x86/entry/common.c
> @@ -49,7 +49,11 @@ static __always_inline bool do_syscall_x64(struct pt_regs *regs, int nr)
>  
>  	if (likely(unr < NR_syscalls)) {
>  		unr = array_index_nospec(unr, NR_syscalls);
> -		regs->ax = x64_sys_call(regs, unr);
> +		if (likely(cpu_feature_enabled(X86_FEATURE_INDIRECT_SAFE)))
> +			regs->ax = sys_call_table[unr](regs);
> +		else
> +			regs->ax = x64_sys_call(regs, unr);

BTW, this also solves the missing lfence case before the indirect call.