From: Dave Hansen <dave.hansen@linux.intel.com>
There are a billion ways to refer to a physical memory address.
One of the x86 PMD freeing code location chooses to use a 'pte_t *' to
point to a PMD page and then call a PTE-specific freeing function for
it. That's a bit wonky.
Just use a 'struct ptdesc *' instead. Its entire purpose is to refer
to page table pages. It also means being able to remove an explicit
cast.
Right now, pte_free_kernel() is a one-liner that calls
pagetable_dtor_free(). Effectively, all this patch does is
remove one superfluous __pa(__va(paddr)) conversion and then
call pagetable_dtor_free() directly instead of through a helper.
Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
---
arch/x86/mm/pgtable.c | 12 ++++++------
1 file changed, 6 insertions(+), 6 deletions(-)
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index ddf248c3ee7d..2e5ecfdce73c 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -729,7 +729,7 @@ int pmd_clear_huge(pmd_t *pmd)
int pud_free_pmd_page(pud_t *pud, unsigned long addr)
{
pmd_t *pmd, *pmd_sv;
- pte_t *pte;
+ struct ptdesc *pt;
int i;
pmd = pud_pgtable(*pud);
@@ -750,8 +750,8 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr)
for (i = 0; i < PTRS_PER_PMD; i++) {
if (!pmd_none(pmd_sv[i])) {
- pte = (pte_t *)pmd_page_vaddr(pmd_sv[i]);
- pte_free_kernel(&init_mm, pte);
+ pt = page_ptdesc(pmd_page(pmd_sv[i]));
+ pagetable_dtor_free(pt);
}
}
@@ -772,15 +772,15 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr)
*/
int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
{
- pte_t *pte;
+ struct ptdesc *pt;
- pte = (pte_t *)pmd_page_vaddr(*pmd);
+ pt = page_ptdesc(pmd_page(*pmd));
pmd_clear(pmd);
/* INVLPG to clear all paging-structure caches */
flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1);
- pte_free_kernel(&init_mm, pte);
+ pagetable_dtor_free(pt);
return 1;
}
--
2.43.0On 19.09.25 07:40, Lu Baolu wrote:
> From: Dave Hansen <dave.hansen@linux.intel.com>
>
> There are a billion ways to refer to a physical memory address.
> One of the x86 PMD freeing code location chooses to use a 'pte_t *' to
> point to a PMD page and then call a PTE-specific freeing function for
> it. That's a bit wonky.
>
> Just use a 'struct ptdesc *' instead. Its entire purpose is to refer
> to page table pages. It also means being able to remove an explicit
> cast.
>
> Right now, pte_free_kernel() is a one-liner that calls
> pagetable_dtor_free(). Effectively, all this patch does is
> remove one superfluous __pa(__va(paddr)) conversion and then
> call pagetable_dtor_free() directly instead of through a helper.
>
> Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
> Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
> Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
> Reviewed-by: Kevin Tian <kevin.tian@intel.com>
> ---
> arch/x86/mm/pgtable.c | 12 ++++++------
> 1 file changed, 6 insertions(+), 6 deletions(-)
>
> diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
> index ddf248c3ee7d..2e5ecfdce73c 100644
> --- a/arch/x86/mm/pgtable.c
> +++ b/arch/x86/mm/pgtable.c
> @@ -729,7 +729,7 @@ int pmd_clear_huge(pmd_t *pmd)
> int pud_free_pmd_page(pud_t *pud, unsigned long addr)
> {
> pmd_t *pmd, *pmd_sv;
> - pte_t *pte;
> + struct ptdesc *pt;
> int i;
>
> pmd = pud_pgtable(*pud);
> @@ -750,8 +750,8 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr)
>
> for (i = 0; i < PTRS_PER_PMD; i++) {
> if (!pmd_none(pmd_sv[i])) {
> - pte = (pte_t *)pmd_page_vaddr(pmd_sv[i]);
> - pte_free_kernel(&init_mm, pte);
> + pt = page_ptdesc(pmd_page(pmd_sv[i]));
> + pagetable_dtor_free(pt);
There is pmd_ptdesc() which does
page_ptdesc(pmd_pgtable_page(pmd));
It's buried in a
#if defined(CONFIG_SPLIT_PMD_PTLOCKS)
Can't we just make that always available so we can use it here?
--
Cheers
David / dhildenb
On 10/9/25 12:25, David Hildenbrand wrote:
>>
>> @@ -750,8 +750,8 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr)
>> for (i = 0; i < PTRS_PER_PMD; i++) {
>> if (!pmd_none(pmd_sv[i])) {
>> - pte = (pte_t *)pmd_page_vaddr(pmd_sv[i]);
>> - pte_free_kernel(&init_mm, pte);
>> + pt = page_ptdesc(pmd_page(pmd_sv[i]));
>> + pagetable_dtor_free(pt);
>
> There is pmd_ptdesc() which does
>
> page_ptdesc(pmd_pgtable_page(pmd));
>
> It's buried in a
>
> #if defined(CONFIG_SPLIT_PMD_PTLOCKS)
>
> Can't we just make that always available so we can use it here?
Yes, that looks like a good idea. I never noticed pmd_ptdesc() when I
was writing this for sure.
On 10/10/25 03:31, Dave Hansen wrote:
> On 10/9/25 12:25, David Hildenbrand wrote:
>>>
>>> @@ -750,8 +750,8 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr)
>>> for (i = 0; i < PTRS_PER_PMD; i++) {
>>> if (!pmd_none(pmd_sv[i])) {
>>> - pte = (pte_t *)pmd_page_vaddr(pmd_sv[i]);
>>> - pte_free_kernel(&init_mm, pte);
>>> + pt = page_ptdesc(pmd_page(pmd_sv[i]));
>>> + pagetable_dtor_free(pt);
>>
>> There is pmd_ptdesc() which does
>>
>> page_ptdesc(pmd_pgtable_page(pmd));
>>
>> It's buried in a
>>
>> #if defined(CONFIG_SPLIT_PMD_PTLOCKS)
>>
>> Can't we just make that always available so we can use it here?
>
> Yes, that looks like a good idea. I never noticed pmd_ptdesc() when I
> was writing this for sure.
I updated the patch like this,
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 6a0bb7fc3148..a0850dc6878e 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3203,8 +3203,6 @@ pte_t *pte_offset_map_rw_nolock(struct mm_struct
*mm, pmd_t *pmd,
((unlikely(pmd_none(*(pmd))) && __pte_alloc_kernel(pmd))? \
NULL: pte_offset_kernel(pmd, address))
-#if defined(CONFIG_SPLIT_PMD_PTLOCKS)
-
static inline struct page *pmd_pgtable_page(pmd_t *pmd)
{
unsigned long mask = ~(PTRS_PER_PMD * sizeof(pmd_t) - 1);
@@ -3216,6 +3214,8 @@ static inline struct ptdesc *pmd_ptdesc(pmd_t *pmd)
return page_ptdesc(pmd_pgtable_page(pmd));
}
+#if defined(CONFIG_SPLIT_PMD_PTLOCKS)
+
static inline spinlock_t *pmd_lockptr(struct mm_struct *mm, pmd_t *pmd)
{
return ptlock_ptr(pmd_ptdesc(pmd));
diff --git a/arch/x86/mm/pgtable.c b/arch/x86/mm/pgtable.c
index ddf248c3ee7d..c830ccbc2fd8 100644
--- a/arch/x86/mm/pgtable.c
+++ b/arch/x86/mm/pgtable.c
@@ -729,7 +729,7 @@ int pmd_clear_huge(pmd_t *pmd)
int pud_free_pmd_page(pud_t *pud, unsigned long addr)
{
pmd_t *pmd, *pmd_sv;
- pte_t *pte;
+ struct ptdesc *pt;
int i;
pmd = pud_pgtable(*pud);
@@ -750,8 +750,8 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr)
for (i = 0; i < PTRS_PER_PMD; i++) {
if (!pmd_none(pmd_sv[i])) {
- pte = (pte_t *)pmd_page_vaddr(pmd_sv[i]);
- pte_free_kernel(&init_mm, pte);
+ pt = pmd_ptdesc(&pmd_sv[i]);
+ pagetable_dtor_free(pt);
}
}
@@ -772,15 +772,15 @@ int pud_free_pmd_page(pud_t *pud, unsigned long addr)
*/
int pmd_free_pte_page(pmd_t *pmd, unsigned long addr)
{
- pte_t *pte;
+ struct ptdesc *pt;
- pte = (pte_t *)pmd_page_vaddr(*pmd);
+ pt = pmd_ptdesc(pmd);
pmd_clear(pmd);
/* INVLPG to clear all paging-structure caches */
flush_tlb_kernel_range(addr, addr + PAGE_SIZE-1);
- pte_free_kernel(&init_mm, pte);
+ pagetable_dtor_free(pt);
return 1;
}
Thanks,
baolu
© 2016 - 2026 Red Hat, Inc.