[RFC PATCH 1/3] powerpc/mm: Introduce temporary mm

[Christophe Leroy]

Le 23/03/2020 à 05:52, Christopher M. Riedl a écrit :
> x86 supports the notion of a temporary mm which restricts access to
> temporary PTEs to a single CPU. A temporary mm is useful for situations
> where a CPU needs to perform sensitive operations (such as patching a
> STRICT_KERNEL_RWX kernel) requiring temporary mappings without exposing
> said mappings to other CPUs. A side benefit is that other CPU TLBs do
> not need to be flushed when the temporary mm is torn down.
> 
> Mappings in the temporary mm can be set in the userspace portion of the
> address-space.
> 
> Interrupts must be disabled while the temporary mm is in use. HW
> breakpoints, which may have been set by userspace as watchpoints on
> addresses now within the temporary mm, are saved and disabled when
> loading the temporary mm. The HW breakpoints are restored when unloading
> the temporary mm. All HW breakpoints are indiscriminately disabled while
> the temporary mm is in use.
> 
> Based on x86 implementation:
> 
> commit cefa929c034e
> ("x86/mm: Introduce temporary mm structs")
> 
> Signed-off-by: Christopher M. Riedl <cmr at informatik.wtf>
> ---
>   arch/powerpc/include/asm/debug.h       |  1 +
>   arch/powerpc/include/asm/mmu_context.h | 56 +++++++++++++++++++++++++-
>   arch/powerpc/kernel/process.c          |  5 +++
>   3 files changed, 61 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/powerpc/include/asm/debug.h b/arch/powerpc/include/asm/debug.h
> index 7756026b95ca..b945bc16c932 100644
> --- a/arch/powerpc/include/asm/debug.h
> +++ b/arch/powerpc/include/asm/debug.h
> @@ -45,6 +45,7 @@ static inline int debugger_break_match(struct pt_regs *regs) { return 0; }
>   static inline int debugger_fault_handler(struct pt_regs *regs) { return 0; }
>   #endif
>   
> +void __get_breakpoint(struct arch_hw_breakpoint *brk);
>   void __set_breakpoint(struct arch_hw_breakpoint *brk);
>   bool ppc_breakpoint_available(void);
>   #ifdef CONFIG_PPC_ADV_DEBUG_REGS
> diff --git a/arch/powerpc/include/asm/mmu_context.h b/arch/powerpc/include/asm/mmu_context.h
> index 360367c579de..3e6381d04c28 100644
> --- a/arch/powerpc/include/asm/mmu_context.h
> +++ b/arch/powerpc/include/asm/mmu_context.h
> @@ -7,9 +7,10 @@
>   #include <linux/mm.h>
>   #include <linux/sched.h>
>   #include <linux/spinlock.h>
> -#include <asm/mmu.h>	
> +#include <asm/mmu.h>
>   #include <asm/cputable.h>
>   #include <asm/cputhreads.h>
> +#include <asm/hw_breakpoint.h>
>   
>   /*
>    * Most if the context management is out of line
> @@ -270,5 +271,58 @@ static inline int arch_dup_mmap(struct mm_struct *oldmm,
>   	return 0;
>   }
>   
> +struct temp_mm {
> +	struct mm_struct *temp;
> +	struct mm_struct *prev;
> +	bool is_kernel_thread;
> +	struct arch_hw_breakpoint brk;
> +};
> +
> +static inline void init_temp_mm(struct temp_mm *temp_mm, struct mm_struct *mm)
> +{
> +	temp_mm->temp = mm;
> +	temp_mm->prev = NULL;
> +	temp_mm->is_kernel_thread = false;
> +	memset(&temp_mm->brk, 0, sizeof(temp_mm->brk));
> +}
> +
> +static inline void use_temporary_mm(struct temp_mm *temp_mm)
> +{
> +	lockdep_assert_irqs_disabled();
> +
> +	temp_mm->is_kernel_thread = current->mm == NULL;
> +	if (temp_mm->is_kernel_thread)
> +		temp_mm->prev = current->active_mm;
> +	else
> +		temp_mm->prev = current->mm;

Could be:
	temp_mm->prev = current->mm ? : current->active_mm;

> +
> +	/*
> +	 * Hash requires a non-NULL current->mm to allocate a userspace address
> +	 * when handling a page fault. Does not appear to hurt in Radix either.
> +	 */
> +	current->mm = temp_mm->temp;
> +	switch_mm_irqs_off(NULL, temp_mm->temp, current);
> +
> +	if (ppc_breakpoint_available()) {
> +		__get_breakpoint(&temp_mm->brk);
> +		if (temp_mm->brk.type != 0)
> +			hw_breakpoint_disable();
> +	}

There is a series for having more than one breakpoint, see 
https://patchwork.ozlabs.org/project/linuxppc-dev/list/?series=170073&state=*

> +}
> +
> +static inline void unuse_temporary_mm(struct temp_mm *temp_mm)
> +{
> +	lockdep_assert_irqs_disabled();
> +
> +	if (temp_mm->is_kernel_thread)
> +		current->mm = NULL;
> +	else
> +		current->mm = temp_mm->prev;

Could be:
	current->mm = !temp_mm->is_kernel_thread ? temp_mm->prev : NULL;

> +	switch_mm_irqs_off(NULL, temp_mm->prev, current);
> +
> +	if (ppc_breakpoint_available() && temp_mm->brk.type != 0)
> +		__set_breakpoint(&temp_mm->brk);
> +}
> +
>   #endif /* __KERNEL__ */
>   #endif /* __ASM_POWERPC_MMU_CONTEXT_H */
> diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
> index fad50db9dcf2..5e5cf33fc358 100644
> --- a/arch/powerpc/kernel/process.c
> +++ b/arch/powerpc/kernel/process.c
> @@ -793,6 +793,11 @@ static inline int set_breakpoint_8xx(struct arch_hw_breakpoint *brk)
>   	return 0;
>   }
>   
> +void __get_breakpoint(struct arch_hw_breakpoint *brk)
> +{
> +	memcpy(brk, this_cpu_ptr(&current_brk), sizeof(*brk));
> +}
> +
>   void __set_breakpoint(struct arch_hw_breakpoint *brk)
>   {
>   	memcpy(this_cpu_ptr(&current_brk), brk, sizeof(*brk));
> 

Christophe