Re: [PATCH v2 19/37] mm/gup: remove record_subpages()

On 06.09.25 03:05, John Hubbard wrote:
> On 9/1/25 8:03 AM, David Hildenbrand wrote:
>> We can just cleanup the code by calculating the #refs earlier,
>> so we can just inline what remains of record_subpages().
>>
>> Calculate the number of references/pages ahead of times, and record them
>> only once all our tests passed.
>>
>> Signed-off-by: David Hildenbrand <[email protected]>
>> ---
>>   mm/gup.c | 25 ++++++++-----------------
>>   1 file changed, 8 insertions(+), 17 deletions(-)
>>
>> diff --git a/mm/gup.c b/mm/gup.c
>> index c10cd969c1a3b..f0f4d1a68e094 100644
>> --- a/mm/gup.c
>> +++ b/mm/gup.c
>> @@ -484,19 +484,6 @@ static inline void mm_set_has_pinned_flag(struct mm_struct *mm)
>>   #ifdef CONFIG_MMU
>>   
>>   #ifdef CONFIG_HAVE_GUP_FAST
>> -static int record_subpages(struct page *page, unsigned long sz,
>> -			   unsigned long addr, unsigned long end,
>> -			   struct page **pages)
>> -{
>> -	int nr;
>> -
>> -	page += (addr & (sz - 1)) >> PAGE_SHIFT;
>> -	for (nr = 0; addr != end; nr++, addr += PAGE_SIZE)
>> -		pages[nr] = page++;
>> -
>> -	return nr;
>> -}
>> -
>>   /**
>>    * try_grab_folio_fast() - Attempt to get or pin a folio in fast path.
>>    * @page:  pointer to page to be grabbed
>> @@ -2967,8 +2954,8 @@ static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
>>   	if (pmd_special(orig))
>>   		return 0;
>>   
>> -	page = pmd_page(orig);
>> -	refs = record_subpages(page, PMD_SIZE, addr, end, pages + *nr);
>> +	refs = (end - addr) >> PAGE_SHIFT;
>> +	page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
>>   
>>   	folio = try_grab_folio_fast(page, refs, flags);
>>   	if (!folio)
>> @@ -2989,6 +2976,8 @@ static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
>>   	}
>>   
>>   	*nr += refs;
>> +	for (; refs; refs--)
>> +		*(pages++) = page++;
>>   	folio_set_referenced(folio);
>>   	return 1;
>>   }
>> @@ -3007,8 +2996,8 @@ static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr,
>>   	if (pud_special(orig))
>>   		return 0;
>>   
>> -	page = pud_page(orig);
>> -	refs = record_subpages(page, PUD_SIZE, addr, end, pages + *nr);
>> +	refs = (end - addr) >> PAGE_SHIFT;
>> +	page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
>>   
>>   	folio = try_grab_folio_fast(page, refs, flags);
>>   	if (!folio)
>> @@ -3030,6 +3019,8 @@ static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr,
>>   	}
>>   
>>   	*nr += refs;
>> +	for (; refs; refs--)
>> +		*(pages++) = page++;
> 
> Hi David,

Hi!

> 
> Probably a similar sentiment as Lorenzo here...the above diffs make the code
> *worse* to read. In fact, I recall adding record_subpages() here long ago,
> specifically to help clarify what was going on.

Well, there is a lot I dislike about record_subpages() to go back there.
Starting with "as Willy keeps explaining, the concept of subpages do
not exist and ending with "why do we fill out the array even on failure".

:)

> 
> Now it's been returned to it's original, cryptic form.
> 

The code in the caller was so uncryptic that both me and Lorenzo missed
that magical addition. :P

> Just my take on it, for whatever that's worth. :)

As always, appreciated.

I could of course keep the simple loop in some "record_folio_pages"
function and clean up what I dislike about record_subpages().

But I much rather want the call chain to be cleaned up instead, if possible.


Roughly, what I am thinking (limiting it to pte+pmd case) about is the following:


 From d6d6d21dbf435d8030782a627175e36e6c7b2dfb Mon Sep 17 00:00:00 2001
From: David Hildenbrand <[email protected]>
Date: Sat, 6 Sep 2025 08:33:42 +0200
Subject: [PATCH] tmp

Signed-off-by: David Hildenbrand <[email protected]>
---
  mm/gup.c | 79 ++++++++++++++++++++++++++------------------------------
  1 file changed, 36 insertions(+), 43 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index 22420f2069ee1..98907ead749c0 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2845,12 +2845,11 @@ static void __maybe_unused gup_fast_undo_dev_pagemap(int *nr, int nr_start,
   * also check pmd here to make sure pmd doesn't change (corresponds to
   * pmdp_collapse_flush() in the THP collapse code path).
   */
-static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
-		unsigned long end, unsigned int flags, struct page **pages,
-		int *nr)
+static unsigned long gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
+		unsigned long end, unsigned int flags, struct page **pages)
  {
  	struct dev_pagemap *pgmap = NULL;
-	int ret = 0;
+	unsigned long nr_pages = 0;
  	pte_t *ptep, *ptem;
  
  	ptem = ptep = pte_offset_map(&pmd, addr);
@@ -2908,24 +2907,20 @@ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
  		 * details.
  		 */
  		if (flags & FOLL_PIN) {
-			ret = arch_make_folio_accessible(folio);
-			if (ret) {
+			if (arch_make_folio_accessible(folio)) {
  				gup_put_folio(folio, 1, flags);
  				goto pte_unmap;
  			}
  		}
  		folio_set_referenced(folio);
-		pages[*nr] = page;
-		(*nr)++;
+		pages[nr_pages++] = page;
  	} while (ptep++, addr += PAGE_SIZE, addr != end);
  
-	ret = 1;
-
  pte_unmap:
  	if (pgmap)
  		put_dev_pagemap(pgmap);
  	pte_unmap(ptem);
-	return ret;
+	return nr_pages;
  }
  #else
  
@@ -2938,21 +2933,24 @@ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
   * get_user_pages_fast_only implementation that can pin pages. Thus it's still
   * useful to have gup_fast_pmd_leaf even if we can't operate on ptes.
   */
-static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
-		unsigned long end, unsigned int flags, struct page **pages,
-		int *nr)
+static unsigned long gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
+		unsigned long end, unsigned int flags, struct page **pages)
  {
  	return 0;
  }
  #endif /* CONFIG_ARCH_HAS_PTE_SPECIAL */
  
-static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
-		unsigned long end, unsigned int flags, struct page **pages,
-		int *nr)
+static unsigned long gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
+		unsigned long end, unsigned int flags, struct page **pages)
  {
+	const unsigned long nr_pages = (end - addr) >> PAGE_SHIFT;
  	struct page *page;
  	struct folio *folio;
-	int refs;
+	unsigned long i;
+
+	/* See gup_fast_pte_range() */
+	if (pmd_protnone(orig))
+		return 0;
  
  	if (!pmd_access_permitted(orig, flags & FOLL_WRITE))
  		return 0;
@@ -2960,33 +2958,30 @@ static int gup_fast_pmd_leaf(pmd_t orig, pmd_t *pmdp, unsigned long addr,
  	if (pmd_special(orig))
  		return 0;
  
-	refs = (end - addr) >> PAGE_SHIFT;
  	page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
  
-	folio = try_grab_folio_fast(page, refs, flags);
+	folio = try_grab_folio_fast(page, nr_pages, flags);
  	if (!folio)
  		return 0;
  
  	if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
-		gup_put_folio(folio, refs, flags);
+		gup_put_folio(folio, nr_pages, flags);
  		return 0;
  	}
  
  	if (!gup_fast_folio_allowed(folio, flags)) {
-		gup_put_folio(folio, refs, flags);
+		gup_put_folio(folio, nr_pages, flags);
  		return 0;
  	}
  	if (!pmd_write(orig) && gup_must_unshare(NULL, flags, &folio->page)) {
-		gup_put_folio(folio, refs, flags);
+		gup_put_folio(folio, nr_pages, flags);
  		return 0;
  	}
  
-	pages += *nr;
-	*nr += refs;
-	for (; refs; refs--)
+	for (i = 0; i < nr_pages; i++)
  		*(pages++) = page++;
  	folio_set_referenced(folio);
-	return 1;
+	return nr_pages;
  }
  
  static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr,
@@ -3033,11 +3028,11 @@ static int gup_fast_pud_leaf(pud_t orig, pud_t *pudp, unsigned long addr,
  	return 1;
  }
  
-static int gup_fast_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr,
-		unsigned long end, unsigned int flags, struct page **pages,
-		int *nr)
+static unsigned long gup_fast_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr,
+		unsigned long end, unsigned int flags, struct page **pages)
  {
-	unsigned long next;
+	unsigned long cur_nr_pages, next;
+	unsigned long nr_pages = 0;
  	pmd_t *pmdp;
  
  	pmdp = pmd_offset_lockless(pudp, pud, addr);
@@ -3046,23 +3041,21 @@ static int gup_fast_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr,
  
  		next = pmd_addr_end(addr, end);
  		if (!pmd_present(pmd))
-			return 0;
+			break;
  
-		if (unlikely(pmd_leaf(pmd))) {
-			/* See gup_fast_pte_range() */
-			if (pmd_protnone(pmd))
-				return 0;
+		if (unlikely(pmd_leaf(pmd)))
+			cur_nr_pages = gup_fast_pmd_leaf(pmd, pmdp, addr, next, flags, pages);
+		else
+			cur_nr_pages = gup_fast_pte_range(pmd, pmdp, addr, next, flags, pages);
  
-			if (!gup_fast_pmd_leaf(pmd, pmdp, addr, next, flags,
-				pages, nr))
-				return 0;
+		nr_pages += cur_nr_pages;
+		pages += cur_nr_pages;
  
-		} else if (!gup_fast_pte_range(pmd, pmdp, addr, next, flags,
-					       pages, nr))
-			return 0;
+		if (nr_pages != (next - addr) >> PAGE_SIZE)
+			break;
  	} while (pmdp++, addr = next, addr != end);
  
-	return 1;
+	return nr_pages;
  }
  
  static int gup_fast_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr,
-- 
2.50.1



Oh, I might even have found a bug moving away from that questionable
"ret==1 means success" handling in gup_fast_pte_range()? Will
have to double-check, but likely the following is the right thing to do.



 From 8f48b25ef93e7ef98611fd58ec89384ad5171782 Mon Sep 17 00:00:00 2001
From: David Hildenbrand <[email protected]>
Date: Sat, 6 Sep 2025 08:46:45 +0200
Subject: [PATCH] mm/gup: fix handling of errors from
  arch_make_folio_accessible() in follow_page_pte()

In case we call arch_make_folio_accessible() and it fails, we would
incorrectly return a value that is "!= 0" to the caller, indicating that
we pinned all requested pages and that the caller can keep going.

follow_page_pte() is not supposed to return error values, but instead
0 on failure and 1 on success.

That is of course wrong, because the caller will just keep going pinning
more pages. If we happen to pin a page afterwards, we're in trouble,
because we essentially skipped some pages.

Fixes: f28d43636d6f ("mm/gup/writeback: add callbacks for inaccessible pages")
Signed-off-by: David Hildenbrand <[email protected]>
---
  mm/gup.c | 3 +--
  1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/mm/gup.c b/mm/gup.c
index 22420f2069ee1..cff226ec0ee7d 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -2908,8 +2908,7 @@ static int gup_fast_pte_range(pmd_t pmd, pmd_t *pmdp, unsigned long addr,
  		 * details.
  		 */
  		if (flags & FOLL_PIN) {
-			ret = arch_make_folio_accessible(folio);
-			if (ret) {
+			if (arch_make_folio_accessible(folio)) {
  				gup_put_folio(folio, 1, flags);
  				goto pte_unmap;
  			}
-- 
2.50.1


-- 
Cheers

David / dhildenb