flush_tlb_range() uses a fixed stride of PAGE_SIZE and in its current form,
when a hugetlb mapping needs to be flushed, flush_tlb_range() flushes the
whole tlb: so set a stride of the size of the hugetlb mapping in order to
only flush the hugetlb mapping. However, if the hugepage is a NAPOT region,
all PTEs that constitute this mapping must be invalidated, so the stride
size must actually be the size of the PTE.

Note that THPs are directly handled by flush_pmd_tlb_range().

Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
---
 arch/riscv/mm/tlbflush.c | 31 ++++++++++++++++++++++++++++++-
 1 file changed, 30 insertions(+), 1 deletion(-)

diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
index fa03289853d8..5933744df91a 100644
--- a/arch/riscv/mm/tlbflush.c
+++ b/arch/riscv/mm/tlbflush.c
@@ -3,6 +3,7 @@
 #include <linux/mm.h>
 #include <linux/smp.h>
 #include <linux/sched.h>
+#include <linux/hugetlb.h>
 #include <asm/sbi.h>
 #include <asm/mmu_context.h>
 
@@ -147,7 +148,35 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
 void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
 		     unsigned long end)
 {
-	__flush_tlb_range(vma->vm_mm, start, end - start, PAGE_SIZE);
+	unsigned long stride_size;
+
+	if (!is_vm_hugetlb_page(vma)) {
+		stride_size = PAGE_SIZE;
+	} else {
+		stride_size = huge_page_size(hstate_vma(vma));
+
+#ifdef CONFIG_RISCV_ISA_SVNAPOT
+		/*
+		 * As stated in the privileged specification, every PTE in a
+		 * NAPOT region must be invalidated, so reset the stride in that
+		 * case.
+		 */
+		if (has_svnapot()) {
+			if (stride_size >= PGDIR_SIZE)
+				stride_size = PGDIR_SIZE;
+			else if (stride_size >= P4D_SIZE)
+				stride_size = P4D_SIZE;
+			else if (stride_size >= PUD_SIZE)
+				stride_size = PUD_SIZE;
+			else if (stride_size >= PMD_SIZE)
+				stride_size = PMD_SIZE;
+			else
+				stride_size = PAGE_SIZE;
+		}
+#endif
+	}
+
+	__flush_tlb_range(vma->vm_mm, start, end - start, stride_size);
 }
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
-- 
2.39.2

On Thu, Oct 19, 2023 at 3:04 PM Alexandre Ghiti <alexghiti@rivosinc.com> wrote:
>
> flush_tlb_range() uses a fixed stride of PAGE_SIZE and in its current form,
> when a hugetlb mapping needs to be flushed, flush_tlb_range() flushes the
> whole tlb: so set a stride of the size of the hugetlb mapping in order to
> only flush the hugetlb mapping. However, if the hugepage is a NAPOT region,
> all PTEs that constitute this mapping must be invalidated, so the stride
> size must actually be the size of the PTE.
>
> Note that THPs are directly handled by flush_pmd_tlb_range().
>
> Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
> ---
>  arch/riscv/mm/tlbflush.c | 31 ++++++++++++++++++++++++++++++-
>  1 file changed, 30 insertions(+), 1 deletion(-)
>
Tested-by: Lad Prabhakar <prabhakar.mahadev-lad.rj@bp.renesas.com> #
On RZ/Five SMARC

Cheers,
Prabhakar

> diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
> index fa03289853d8..5933744df91a 100644
> --- a/arch/riscv/mm/tlbflush.c
> +++ b/arch/riscv/mm/tlbflush.c
> @@ -3,6 +3,7 @@
>  #include <linux/mm.h>
>  #include <linux/smp.h>
>  #include <linux/sched.h>
> +#include <linux/hugetlb.h>
>  #include <asm/sbi.h>
>  #include <asm/mmu_context.h>
>
> @@ -147,7 +148,35 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
>  void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
>                      unsigned long end)
>  {
> -       __flush_tlb_range(vma->vm_mm, start, end - start, PAGE_SIZE);
> +       unsigned long stride_size;
> +
> +       if (!is_vm_hugetlb_page(vma)) {
> +               stride_size = PAGE_SIZE;
> +       } else {
> +               stride_size = huge_page_size(hstate_vma(vma));
> +
> +#ifdef CONFIG_RISCV_ISA_SVNAPOT
> +               /*
> +                * As stated in the privileged specification, every PTE in a
> +                * NAPOT region must be invalidated, so reset the stride in that
> +                * case.
> +                */
> +               if (has_svnapot()) {
> +                       if (stride_size >= PGDIR_SIZE)
> +                               stride_size = PGDIR_SIZE;
> +                       else if (stride_size >= P4D_SIZE)
> +                               stride_size = P4D_SIZE;
> +                       else if (stride_size >= PUD_SIZE)
> +                               stride_size = PUD_SIZE;
> +                       else if (stride_size >= PMD_SIZE)
> +                               stride_size = PMD_SIZE;
> +                       else
> +                               stride_size = PAGE_SIZE;
> +               }
> +#endif
> +       }
> +
> +       __flush_tlb_range(vma->vm_mm, start, end - start, stride_size);
>  }
>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>  void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,
> --
> 2.39.2
>

On 2023-10-19 9:01 AM, Alexandre Ghiti wrote:
> flush_tlb_range() uses a fixed stride of PAGE_SIZE and in its current form,
> when a hugetlb mapping needs to be flushed, flush_tlb_range() flushes the
> whole tlb: so set a stride of the size of the hugetlb mapping in order to
> only flush the hugetlb mapping. However, if the hugepage is a NAPOT region,
> all PTEs that constitute this mapping must be invalidated, so the stride
> size must actually be the size of the PTE.
> 
> Note that THPs are directly handled by flush_pmd_tlb_range().
> 
> Signed-off-by: Alexandre Ghiti <alexghiti@rivosinc.com>
> ---
>  arch/riscv/mm/tlbflush.c | 31 ++++++++++++++++++++++++++++++-
>  1 file changed, 30 insertions(+), 1 deletion(-)
> 
> diff --git a/arch/riscv/mm/tlbflush.c b/arch/riscv/mm/tlbflush.c
> index fa03289853d8..5933744df91a 100644
> --- a/arch/riscv/mm/tlbflush.c
> +++ b/arch/riscv/mm/tlbflush.c
> @@ -3,6 +3,7 @@
>  #include <linux/mm.h>
>  #include <linux/smp.h>
>  #include <linux/sched.h>
> +#include <linux/hugetlb.h>
>  #include <asm/sbi.h>
>  #include <asm/mmu_context.h>
>  
> @@ -147,7 +148,35 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
>  void flush_tlb_range(struct vm_area_struct *vma, unsigned long start,
>  		     unsigned long end)
>  {
> -	__flush_tlb_range(vma->vm_mm, start, end - start, PAGE_SIZE);
> +	unsigned long stride_size;
> +
> +	if (!is_vm_hugetlb_page(vma)) {
> +		stride_size = PAGE_SIZE;
> +	} else {
> +		stride_size = huge_page_size(hstate_vma(vma));
> +
> +#ifdef CONFIG_RISCV_ISA_SVNAPOT

There is a fallback implementation of has_svnapot(), so you do not need this
preprocessor check. With that removed:

Reviewed-by: Samuel Holland <samuel.holland@sifive.com>

> +		/*
> +		 * As stated in the privileged specification, every PTE in a
> +		 * NAPOT region must be invalidated, so reset the stride in that
> +		 * case.
> +		 */
> +		if (has_svnapot()) {
> +			if (stride_size >= PGDIR_SIZE)
> +				stride_size = PGDIR_SIZE;
> +			else if (stride_size >= P4D_SIZE)
> +				stride_size = P4D_SIZE;

As a side note, and this is probably premature optimization... PGDIR_SIZE and
P4D_SIZE check pgtable_l{4,5}_enabled. That's not really necessary here, since
we are just trying to round down, and there won't be any higher-order hugepages
if those paging levels are disabled.

> +			else if (stride_size >= PUD_SIZE)
> +				stride_size = PUD_SIZE;
> +			else if (stride_size >= PMD_SIZE)
> +				stride_size = PMD_SIZE;
> +			else
> +				stride_size = PAGE_SIZE;
> +		}
> +#endif
> +	}
> +
> +	__flush_tlb_range(vma->vm_mm, start, end - start, stride_size);
>  }
>  #ifdef CONFIG_TRANSPARENT_HUGEPAGE
>  void flush_pmd_tlb_range(struct vm_area_struct *vma, unsigned long start,