Re: [PATCH v4 06/29] arm64: context switch POR_EL0 register

[Joey Gouly <joey.gouly@arm.com>]

On Mon, Jul 15, 2024 at 01:57:10PM +0530, Anshuman Khandual wrote:
> 
> 
> On 5/3/24 18:31, Joey Gouly wrote:
> > POR_EL0 is a register that can be modified by userspace directly,
> > so it must be context switched.
> > 
> > Signed-off-by: Joey Gouly <joey.gouly@arm.com>
> > Cc: Catalin Marinas <catalin.marinas@arm.com>
> > Cc: Will Deacon <will@kernel.org>
> > ---
> >  arch/arm64/include/asm/cpufeature.h |  6 ++++++
> >  arch/arm64/include/asm/processor.h  |  1 +
> >  arch/arm64/include/asm/sysreg.h     |  3 +++
> >  arch/arm64/kernel/process.c         | 28 ++++++++++++++++++++++++++++
> >  4 files changed, 38 insertions(+)
> > 
> > diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
> > index 8b904a757bd3..d46aab23e06e 100644
> > --- a/arch/arm64/include/asm/cpufeature.h
> > +++ b/arch/arm64/include/asm/cpufeature.h
> > @@ -832,6 +832,12 @@ static inline bool system_supports_lpa2(void)
> >  	return cpus_have_final_cap(ARM64_HAS_LPA2);
> >  }
> >  
> > +static inline bool system_supports_poe(void)
> > +{
> > +	return IS_ENABLED(CONFIG_ARM64_POE) &&
> 
> CONFIG_ARM64_POE has not been defined/added until now ?
> 
> > +		alternative_has_cap_unlikely(ARM64_HAS_S1POE);
> > +}
> > +
> >  int do_emulate_mrs(struct pt_regs *regs, u32 sys_reg, u32 rt);
> >  bool try_emulate_mrs(struct pt_regs *regs, u32 isn);
> >  
> > diff --git a/arch/arm64/include/asm/processor.h b/arch/arm64/include/asm/processor.h
> > index f77371232d8c..e6376f979273 100644
> > --- a/arch/arm64/include/asm/processor.h
> > +++ b/arch/arm64/include/asm/processor.h
> > @@ -184,6 +184,7 @@ struct thread_struct {
> >  	u64			sctlr_user;
> >  	u64			svcr;
> >  	u64			tpidr2_el0;
> > +	u64			por_el0;
> >  };
> 
> As there going to be a new config i.e CONFIG_ARM64_POE, should not this
> register be wrapped up with #ifdef CONFIG_ARM64_POE as well ? Similarly
> access into p->thread.por_el0 should also be conditional on that config.

It seems like we're a bit inconsistent here, for example tpidr2_el0 from
FEAT_SME is not guarded.  Not guarding means that we can have left #ifdef's in
the C files and since system_supports_poe() checks if CONFIG_ARM64_POE is
enabled, most of the code should be optimised away anyway. So unless there's a
good reason I think it makes sense to stay this way.

> 
> >  
> >  static inline unsigned int thread_get_vl(struct thread_struct *thread,
> > diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h
> > index 9e8999592f3a..62c399811dbf 100644
> > --- a/arch/arm64/include/asm/sysreg.h
> > +++ b/arch/arm64/include/asm/sysreg.h
> > @@ -1064,6 +1064,9 @@
> >  #define POE_RXW		UL(0x7)
> >  #define POE_MASK	UL(0xf)
> >  
> > +/* Initial value for Permission Overlay Extension for EL0 */
> > +#define POR_EL0_INIT	POE_RXW
> 
> The idea behind POE_RXW as the init value is to be all permissive ?

Yup, the default index 0, needs to allow everything.

> 
> > +
> >  #define ARM64_FEATURE_FIELD_BITS	4
> >  
> >  /* Defined for compatibility only, do not add new users. */
> > diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
> > index 4ae31b7af6c3..0ffaca98bed6 100644
> > --- a/arch/arm64/kernel/process.c
> > +++ b/arch/arm64/kernel/process.c
> > @@ -271,12 +271,23 @@ static void flush_tagged_addr_state(void)
> >  		clear_thread_flag(TIF_TAGGED_ADDR);
> >  }
> >  
> > +static void flush_poe(void)
> > +{
> > +	if (!system_supports_poe())
> > +		return;
> > +
> > +	write_sysreg_s(POR_EL0_INIT, SYS_POR_EL0);
> > +	/* ISB required for kernel uaccess routines when chaning POR_EL0 */
> > +	isb();
> > +}
> > +
> >  void flush_thread(void)
> >  {
> >  	fpsimd_flush_thread();
> >  	tls_thread_flush();
> >  	flush_ptrace_hw_breakpoint(current);
> >  	flush_tagged_addr_state();
> > +	flush_poe();
> >  }
> >  
> >  void arch_release_task_struct(struct task_struct *tsk)
> > @@ -371,6 +382,9 @@ int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
> >  		if (system_supports_tpidr2())
> >  			p->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);
> >  
> > +		if (system_supports_poe())
> > +			p->thread.por_el0 = read_sysreg_s(SYS_POR_EL0);
> > +
> >  		if (stack_start) {
> >  			if (is_compat_thread(task_thread_info(p)))
> >  				childregs->compat_sp = stack_start;
> > @@ -495,6 +509,19 @@ static void erratum_1418040_new_exec(void)
> >  	preempt_enable();
> >  }
> >  
> > +static void permission_overlay_switch(struct task_struct *next)
> > +{
> > +	if (!system_supports_poe())
> > +		return;
> > +
> > +	current->thread.por_el0 = read_sysreg_s(SYS_POR_EL0);
> > +	if (current->thread.por_el0 != next->thread.por_el0) {
> > +		write_sysreg_s(next->thread.por_el0, SYS_POR_EL0);
> > +		/* ISB required for kernel uaccess routines when chaning POR_EL0 */
> > +		isb();
> > +	}
> > +}
> > +
> >  /*
> >   * __switch_to() checks current->thread.sctlr_user as an optimisation. Therefore
> >   * this function must be called with preemption disabled and the update to
> > @@ -530,6 +557,7 @@ struct task_struct *__switch_to(struct task_struct *prev,
> >  	ssbs_thread_switch(next);
> >  	erratum_1418040_thread_switch(next);
> >  	ptrauth_thread_switch_user(next);
> > +	permission_overlay_switch(next);
> >  
> >  	/*
> >  	 * Complete any pending TLB or cache maintenance on this CPU in case
>