Re: [PATCH v1 5/6] mm: tlb: Provide flush_*_tlb_range wrappers

From: Zhenyu Ye
Date: Tue Apr 21 2020 - 10:19:13 EST


Hi Peter,

On 2020/4/20 20:09, Peter Zijlstra wrote:
> On Fri, Apr 03, 2020 at 05:00:47PM +0800, Zhenyu Ye wrote:
>> This patch provides flush_{pte|pmd|pud|p4d}_tlb_range() in generic
>> code, which are expressed through the mmu_gather APIs. These
>> interface set tlb->cleared_* and finally call tlb_flush(), so we
>> can do the tlb invalidation according to the information in
>> struct mmu_gather.
>>
>> Signed-off-by: Zhenyu Ye <yezhenyu2@xxxxxxxxxx>
>> ---
>> include/asm-generic/pgtable.h | 12 +++++++--
>> mm/pgtable-generic.c | 50 +++++++++++++++++++++++++++++++++++
>> 2 files changed, 60 insertions(+), 2 deletions(-)
>>
>> diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
>> index e2e2bef07dd2..2bedeee94131 100644
>> --- a/include/asm-generic/pgtable.h
>> +++ b/include/asm-generic/pgtable.h
>> @@ -1160,11 +1160,19 @@ static inline int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
>> * invalidate the entire TLB which is not desitable.
>> * e.g. see arch/arc: flush_pmd_tlb_range
>> */
>> -#define flush_pmd_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end)
>> -#define flush_pud_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end)
>> +extern void flush_pte_tlb_range(struct vm_area_struct *vma,
>> + unsigned long addr, unsigned long end);
>> +extern void flush_pmd_tlb_range(struct vm_area_struct *vma,
>> + unsigned long addr, unsigned long end);
>> +extern void flush_pud_tlb_range(struct vm_area_struct *vma,
>> + unsigned long addr, unsigned long end);
>> +extern void flush_p4d_tlb_range(struct vm_area_struct *vma,
>> + unsigned long addr, unsigned long end);
>> #else
>> +#define flush_pte_tlb_range(vma, addr, end) BUILD_BUG()
>> #define flush_pmd_tlb_range(vma, addr, end) BUILD_BUG()
>> #define flush_pud_tlb_range(vma, addr, end) BUILD_BUG()
>> +#define flush_p4d_tlb_range(vma, addr, end) BUILD_BUG()
>> #endif
>> #endif
>
> Ideally you'd make __HAVE_ARCH_FLUSH_PMD_TLB_RANGE go away. Power
> certainly doesnt need it with the below.
>

However, arch `arc` also uses __HAVE_ARCH_FLUSH_PMD_TLB_RANGE :

grep -nr __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
mm/pgtable-generic.c:104:#ifndef __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
mm/pgtable-generic.c:152:#endif /* __HAVE_ARCH_FLUSH_PMD_TLB_RANGE */
include/asm-generic/pgtable.h:1153:#ifndef __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
arch/powerpc/include/asm/book3s/64/tlbflush.h:49:#define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
arch/arc/include/asm/hugepage.h:69:#define __HAVE_ARCH_FLUSH_PMD_TLB_RANGE

So I am not sure if we can remove it.

And if we remove the __HAVE_ARCH_FLUSH_PMD_TLB_RANGE, how to ensure not
redefine flush_pXX_tlb_range() ?

>> diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c
>> index 3d7c01e76efc..0f5414a4a2ec 100644
>> --- a/mm/pgtable-generic.c
>> +++ b/mm/pgtable-generic.c
>> @@ -101,6 +101,56 @@ pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address,
>>
>> #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>>
>> +#ifndef __HAVE_ARCH_FLUSH_PMD_TLB_RANGE
>> +void flush_pte_tlb_range(struct vm_area_struct *vma,
>> + unsigned long addr, unsigned long end)
>> +{
>> + struct mmu_gather tlb;
>> +
>> + tlb_gather_mmu(&tlb, vma->vm_mm, addr, end);
>> + tlb_start_vma(&tlb, vma);
>> + tlb_set_pte_range(&tlb, addr, end - addr);
>> + tlb_end_vma(&tlb, vma);
>> + tlb_finish_mmu(&tlb, addr, end);
>> +}
>> +
>> +void flush_pmd_tlb_range(struct vm_area_struct *vma,
>> + unsigned long addr, unsigned long end)
>> +{
>> + struct mmu_gather tlb;
>> +
>> + tlb_gather_mmu(&tlb, vma->vm_mm, addr, end);
>> + tlb_start_vma(&tlb, vma);
>> + tlb_set_pmd_range(&tlb, addr, end - addr);
>> + tlb_end_vma(&tlb, vma);
>> + tlb_finish_mmu(&tlb, addr, end);
>> +}
>> +
>> +void flush_pud_tlb_range(struct vm_area_struct *vma,
>> + unsigned long addr, unsigned long end)
>> +{
>> + struct mmu_gather tlb;
>> +
>> + tlb_gather_mmu(&tlb, vma->vm_mm, addr, end);
>> + tlb_start_vma(&tlb, vma);
>> + tlb_set_pud_range(&tlb, addr, end - addr);
>> + tlb_end_vma(&tlb, vma);
>> + tlb_finish_mmu(&tlb, addr, end);
>> +}
>> +
>> +void flush_p4d_tlb_range(struct vm_area_struct *vma,
>> + unsigned long addr, unsigned long end)
>> +{
>> + struct mmu_gather tlb;
>> +
>> + tlb_gather_mmu(&tlb, vma->vm_mm, addr, end);
>> + tlb_start_vma(&tlb, vma);
>> + tlb_set_p4d_range(&tlb, addr, end - addr);
>> + tlb_end_vma(&tlb, vma);
>> + tlb_finish_mmu(&tlb, addr, end);
>> +}
>> +#endif /* __HAVE_ARCH_FLUSH_PMD_TLB_RANGE */
>
> You're nowhere near lazy enough:
>
> #define FLUSH_Pxx_TLB_RANGE(_pxx) \
> void flush_##_pxx##_tlb_range(struct vm_area_struct *vma, \
> unsigned long addr, unsigned long end) \
> { \
> struct mmu_gather tlb; \
> \
> tlb_gather_mmu(&tlb, vma->vm_mm, addr, end); \
> tlb_start_vma(&tlb, vma); \
> tlb_flush_##_pxx##_range(&tlb, addr, end-addr); \
> tlb_end_vma(&tlb, vma); \
> tlb_finish_mmu(&tlb, addr, end); \
> }
>
> FLUSH_Pxx_TLB_RANGE(pte)
> FLUSH_Pxx_TLB_RANGE(pmd)
> FLUSH_Pxx_TLB_RANGE(pud)
> FLUSH_Pxx_TLB_RANGE(p4d)
>
>
> .
>