Re: [PATCH 1/2] arm64/mm: Change THP helpers to comply with generic MM semantics

[Jonathan Cameron]

On Tue, 18 Aug 2020 15:11:58 +0530
Anshuman Khandual <anshuman.khandual@xxxxxxx> wrote:

> On 08/18/2020 02:43 PM, Jonathan Cameron wrote:
> > On Mon, 17 Aug 2020 14:49:43 +0530
> > Anshuman Khandual <anshuman.khandual@xxxxxxx> wrote:
> >   
> >> pmd_present() and pmd_trans_huge() are expected to behave in the following
> >> manner during various phases of a given PMD. It is derived from a previous
> >> detailed discussion on this topic [1] and present THP documentation [2].
> >>
> >> pmd_present(pmd):
> >>
> >> - Returns true if pmd refers to system RAM with a valid pmd_page(pmd)
> >> - Returns false if pmd does not refer to system RAM - Invalid pmd_page(pmd)
> >>
> >> pmd_trans_huge(pmd):
> >>
> >> - Returns true if pmd refers to system RAM and is a trans huge mapping
> >>
> >> -------------------------------------------------------------------------
> >> |	PMD states	|	pmd_present	|	pmd_trans_huge	|
> >> -------------------------------------------------------------------------
> >> |	Mapped		|	Yes		|	Yes		|
> >> -------------------------------------------------------------------------
> >> |	Splitting	|	Yes		|	Yes		|
> >> -------------------------------------------------------------------------
> >> |	Migration/Swap	|	No		|	No		|
> >> -------------------------------------------------------------------------
> >>
> >> The problem:
> >>
> >> PMD is first invalidated with pmdp_invalidate() before it's splitting. This
> >> invalidation clears PMD_SECT_VALID as below.
> >>
> >> PMD Split -> pmdp_invalidate() -> pmd_mkinvalid -> Clears PMD_SECT_VALID
> >>
> >> Once PMD_SECT_VALID gets cleared, it results in pmd_present() return false
> >> on the PMD entry. It will need another bit apart from PMD_SECT_VALID to re-
> >> affirm pmd_present() as true during the THP split process. To comply with
> >> above mentioned semantics, pmd_trans_huge() should also check pmd_present()
> >> first before testing presence of an actual transparent huge mapping.
> >>
> >> The solution:
> >>
> >> Ideally PMD_TYPE_SECT should have been used here instead. But it shares the
> >> bit position with PMD_SECT_VALID which is used for THP invalidation. Hence
> >> it will not be there for pmd_present() check after pmdp_invalidate().
> >>
> >> A new software defined PMD_PRESENT_INVALID (bit 59) can be set on the PMD
> >> entry during invalidation which can help pmd_present() return true and in
> >> recognizing the fact that it still points to memory.
> >>
> >> This bit is transient. During the split process it will be overridden by a
> >> page table page representing normal pages in place of erstwhile huge page.
> >> Other pmdp_invalidate() callers always write a fresh PMD value on the entry
> >> overriding this transient PMD_PRESENT_INVALID bit, which makes it safe.
> >>
> >> [1]: https://lkml.org/lkml/2018/10/17/231
> >> [2]: https://www.kernel.org/doc/Documentation/vm/transhuge.txt  
> > 
> > Hi Anshuman,
> > 
> > One query on this.  From my reading of the ARM ARM, bit 59 is not
> > an ignored bit.  The exact requirements for hardware to be using
> > it are a bit complex though.
> > 
> > It 'might' be safe to use it for this, but if so can we have a comment
> > explaining why.  Also more than possible I'm misunderstanding things!   
> 
> We are using this bit 59 only when the entry is not active from MMU
> perspective i.e PMD_SECT_VALID is clear.
> 

Understood. I guess we ran out of bits that were always ignored so had
to start using ones that are ignored in this particular state.

Jonathan