[PATCH v4 01/12] arm64/mm: Update non-range tlb invalidation routines for FEAT_LPA2

Ryan Roberts ryan.roberts at arm.com
Fri Oct 20 05:39:47 PDT 2023


On 20/10/2023 09:05, Marc Zyngier wrote:
> On Thu, 19 Oct 2023 10:22:37 +0100,
> Ryan Roberts <ryan.roberts at arm.com> wrote:
>>
>> On 19/10/2023 09:03, Marc Zyngier wrote:
>>> On Mon, 09 Oct 2023 19:49:57 +0100,
>>> Ryan Roberts <ryan.roberts at arm.com> wrote:
>>>>
>>>> FEAT_LPA2 impacts tlb invalidation in 2 ways; Firstly, the TTL field in
>>>> the non-range tlbi instructions can now validly take a 0 value for the
>>>> 4KB granule (this is due to the extra level of translation). Secondly,
>>>
>>> nit: 0 was always valid. It just didn't indicate any level.
>>
>> True. I'll change to "can now validly take a 0 value as a TTL hint".
>>
>>>
>>>> the BADDR field in the range tlbi instructions must be aligned to 64KB
>>>> when LPA2 is in use (TCR.DS=1). Changes are required for tlbi to
>>>> continue to operate correctly when LPA2 is in use.
>>>>
>>>> KVM only uses the non-range (__tlbi_level()) routines. Therefore we only
>>>> solve the first problem with this patch.
>>>
>>> Is this still true? This patch changes __TLBI_VADDR_RANGE() and co.
>>
>> It is no longer true that KVM only uses the non-range routines. v6.6 adds a
>> series where KVM will now use the range-based routines too. So that text is out
>> of date and I should have spotted it when doing the rebase - I'll fix. KVM now
>> using range-based ops is the reason I added patch 2 to this series.
>>
>> However, this patch doesn't really change __TLBI_VADDR_RANGE()'s behavior, it
>> just makes it robust to the presence of TLBI_TTL_UNKNOWN, instead of 0 which was
>> previously used as the "don't know" value.
>>
>>>
>>>>
>>>> It is solved by always adding the level hint if the level is between [0,
>>>> 3] (previously anything other than 0 was hinted, which breaks in the new
>>>> level -1 case from kvm). When running on non-LPA2 HW, 0 is still safe to
>>>> hint as the HW will fall back to non-hinted. While we are at it, we
>>>> replace the notion of 0 being the non-hinted seninel with a macro,
>>>> TLBI_TTL_UNKNOWN. This means callers won't need updating if/when
>>>> translation depth increases in future.
>>>>
>>>> Signed-off-by: Ryan Roberts <ryan.roberts at arm.com>
>>>> Reviewed-by: Catalin Marinas <catalin.marinas at arm.com>
>>>> ---
>>>>  arch/arm64/include/asm/tlb.h      |  9 ++++---
>>>>  arch/arm64/include/asm/tlbflush.h | 43 +++++++++++++++++++------------
>>>>  2 files changed, 31 insertions(+), 21 deletions(-)
>>>>
>>>> diff --git a/arch/arm64/include/asm/tlb.h b/arch/arm64/include/asm/tlb.h
>>>> index 2c29239d05c3..93c537635dbb 100644
>>>> --- a/arch/arm64/include/asm/tlb.h
>>>> +++ b/arch/arm64/include/asm/tlb.h
>>>> @@ -22,15 +22,16 @@ static void tlb_flush(struct mmu_gather *tlb);
>>>>  #include <asm-generic/tlb.h>
>>>>  
>>>>  /*
>>>> - * get the tlbi levels in arm64.  Default value is 0 if more than one
>>>> - * of cleared_* is set or neither is set.
>>>> + * get the tlbi levels in arm64.  Default value is TLBI_TTL_UNKNOWN if more than
>>>> + * one of cleared_* is set or neither is set - this elides the level hinting to
>>>> + * the hardware.
>>>>   * Arm64 doesn't support p4ds now.
>>>>   */
>>>>  static inline int tlb_get_level(struct mmu_gather *tlb)
>>>>  {
>>>>  	/* The TTL field is only valid for the leaf entry. */
>>>>  	if (tlb->freed_tables)
>>>> -		return 0;
>>>> +		return TLBI_TTL_UNKNOWN;
>>>>  
>>>>  	if (tlb->cleared_ptes && !(tlb->cleared_pmds ||
>>>>  				   tlb->cleared_puds ||
>>>> @@ -47,7 +48,7 @@ static inline int tlb_get_level(struct mmu_gather *tlb)
>>>>  				   tlb->cleared_p4ds))
>>>>  		return 1;
>>>>  
>>>> -	return 0;
>>>> +	return TLBI_TTL_UNKNOWN;
>>>>  }
>>>>  
>>>>  static inline void tlb_flush(struct mmu_gather *tlb)
>>>> diff --git a/arch/arm64/include/asm/tlbflush.h b/arch/arm64/include/asm/tlbflush.h
>>>> index b149cf9f91bc..e688246b3b13 100644
>>>> --- a/arch/arm64/include/asm/tlbflush.h
>>>> +++ b/arch/arm64/include/asm/tlbflush.h
>>>> @@ -94,19 +94,22 @@ static inline unsigned long get_trans_granule(void)
>>>>   * When ARMv8.4-TTL exists, TLBI operations take an additional hint for
>>>>   * the level at which the invalidation must take place. If the level is
>>>>   * wrong, no invalidation may take place. In the case where the level
>>>> - * cannot be easily determined, a 0 value for the level parameter will
>>>> - * perform a non-hinted invalidation.
>>>> + * cannot be easily determined, the value TLBI_TTL_UNKNOWN will perform
>>>> + * a non-hinted invalidation. Any provided level outside the hint range
>>>> + * will also cause fall-back to non-hinted invalidation.
>>>>   *
>>>>   * For Stage-2 invalidation, use the level values provided to that effect
>>>>   * in asm/stage2_pgtable.h.
>>>>   */
>>>>  #define TLBI_TTL_MASK		GENMASK_ULL(47, 44)
>>>>  
>>>> +#define TLBI_TTL_UNKNOWN	(-1)
>>>
>>> I find this value somehow confusing, as it represent an actual level
>>> number. It just happen to be one that cannot be provided as a TTL. So
>>> having that as a return value from tlb_get_level() isn't great, and
>>> I'd rather have something that cannot be mistaken for a valid level.
>>
>> OK, how about INT_MAX?
> 
> Works for me.
> 
>>
>>>
>>>> +
>>>>  #define __tlbi_level(op, addr, level) do {				\
>>>>  	u64 arg = addr;							\
>>>>  									\
>>>>  	if (cpus_have_const_cap(ARM64_HAS_ARMv8_4_TTL) &&		\
>>>> -	    level) {							\
>>>> +	    level >= 0 && level <= 3) {					\
>>>>  		u64 ttl = level & 3;					\
>>>>  		ttl |= get_trans_granule() << 2;			\
>>>>  		arg &= ~TLBI_TTL_MASK;					\
>>>> @@ -134,16 +137,17 @@ static inline unsigned long get_trans_granule(void)
>>>>   * [BADDR, BADDR + (NUM + 1) * 2^(5*SCALE + 1) * PAGESIZE)
>>>>   *
>>>>   */
>>>> -#define __TLBI_VADDR_RANGE(addr, asid, scale, num, ttl)		\
>>>> -	({							\
>>>> -		unsigned long __ta = (addr) >> PAGE_SHIFT;	\
>>>> -		__ta &= GENMASK_ULL(36, 0);			\
>>>> -		__ta |= (unsigned long)(ttl) << 37;		\
>>>> -		__ta |= (unsigned long)(num) << 39;		\
>>>> -		__ta |= (unsigned long)(scale) << 44;		\
>>>> -		__ta |= get_trans_granule() << 46;		\
>>>> -		__ta |= (unsigned long)(asid) << 48;		\
>>>> -		__ta;						\
>>>> +#define __TLBI_VADDR_RANGE(addr, asid, scale, num, ttl)				\
>>>> +	({									\
>>>> +		unsigned long __ta = (addr) >> PAGE_SHIFT;			\
>>>> +		unsigned long __ttl = (ttl >= 1 && ttl <= 3) ? ttl : 0;		\
>>>> +		__ta &= GENMASK_ULL(36, 0);					\
>>>> +		__ta |= __ttl << 37;						\
>>>> +		__ta |= (unsigned long)(num) << 39;				\
>>>> +		__ta |= (unsigned long)(scale) << 44;				\
>>>> +		__ta |= get_trans_granule() << 46;				\
>>>> +		__ta |= (unsigned long)(asid) << 48;				\
>>>> +		__ta;								\
>>>>  	})
>>>>  
>>>>  /* These macros are used by the TLBI RANGE feature. */
>>>> @@ -216,12 +220,16 @@ static inline unsigned long get_trans_granule(void)
>>>>   *		CPUs, ensuring that any walk-cache entries associated with the
>>>>   *		translation are also invalidated.
>>>>   *
>>>> - *	__flush_tlb_range(vma, start, end, stride, last_level)
>>>> + *	__flush_tlb_range(vma, start, end, stride, last_level, tlb_level)
>>>>   *		Invalidate the virtual-address range '[start, end)' on all
>>>>   *		CPUs for the user address space corresponding to 'vma->mm'.
>>>>   *		The invalidation operations are issued at a granularity
>>>>   *		determined by 'stride' and only affect any walk-cache entries
>>>> - *		if 'last_level' is equal to false.
>>>> + *		if 'last_level' is equal to false. tlb_level is the level at
>>>> + *		which the invalidation must take place. If the level is wrong,
>>>> + *		no invalidation may take place. In the case where the level
>>>> + *		cannot be easily determined, the value TLBI_TTL_UNKNOWN will
>>>> + *		perform a non-hinted invalidation.
>>>>   *
>>>>   *
>>>>   *	Finally, take a look at asm/tlb.h to see how tlb_flush() is implemented
>>>> @@ -442,9 +450,10 @@ static inline void flush_tlb_range(struct vm_area_struct *vma,
>>>>  	/*
>>>>  	 * We cannot use leaf-only invalidation here, since we may be invalidating
>>>>  	 * table entries as part of collapsing hugepages or moving page tables.
>>>> -	 * Set the tlb_level to 0 because we can not get enough information here.
>>>> +	 * Set the tlb_level to TLBI_TTL_UNKNOWN because we can not get enough
>>>> +	 * information here.
>>>>  	 */
>>>> -	__flush_tlb_range(vma, start, end, PAGE_SIZE, false, 0);
>>>> +	__flush_tlb_range(vma, start, end, PAGE_SIZE, false, TLBI_TTL_UNKNOWN);
>>>>  }
>>>>  
>>>>  static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
>>>
>>> It feels like this range stuff would be better located in the second
>>> patch. Not a huge deal though.
>>
>> As I said, this is the minimal change to the range-based side of things to
>> robustly deal with the introduction of TLBI_TTL_UNKNOWN.
>>
>> But I wonder if I'm actually better of squashing both of the 2 patches into one.
>> The only reason I split it previously was because KVM was only using the
>> level-based ops.
> 
> Maybe. There is something to be said about making the range rework
> (decreasing scale) an independent patch, as it is a significant change
> on its own. But maybe the rest of the plumbing can be grouped
> together.

But that's effectively the split I have now, isn't it? The first patch
introduces TLBI_TTL_UNKNOWN to enable use of 0 as a ttl hint. Then the second
patch reworks the range stuff. I don't quite follow what you are suggesting.

> 
> Thanks,
> 
> 	M.
> 




More information about the linux-arm-kernel mailing list