diff mbox series

[v11,01/25] mm/gup: factor out duplicate code from four routines

Message ID 20191216222537.491123-2-jhubbard@nvidia.com
State New
Headers show
Series mm/gup: track dma-pinned pages: FOLL_PIN | expand

Commit Message

John Hubbard Dec. 16, 2019, 10:25 p.m. UTC
There are four locations in gup.c that have a fair amount of code
duplication. This means that changing one requires making the same
changes in four places, not to mention reading the same code four
times, and wondering if there are subtle differences.

Factor out the common code into static functions, thus reducing the
overall line count and the code's complexity.

Also, take the opportunity to slightly improve the efficiency of the
error cases, by doing a mass subtraction of the refcount, surrounded
by get_page()/put_page().

Also, further simplify (slightly), by waiting until the the successful
end of each routine, to increment *nr.

Reviewed-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Jérôme Glisse <jglisse@redhat.com>
Reviewed-by: Jan Kara <jack@suse.cz>
Cc: Ira Weiny <ira.weiny@intel.com>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Aneesh Kumar K.V <aneesh.kumar@linux.ibm.com>
Signed-off-by: John Hubbard <jhubbard@nvidia.com>
---
 mm/gup.c | 91 ++++++++++++++++++++++----------------------------------
 1 file changed, 36 insertions(+), 55 deletions(-)

Comments

Kirill A. Shutemov Dec. 18, 2019, 3:52 p.m. UTC | #1
On Mon, Dec 16, 2019 at 02:25:13PM -0800, John Hubbard wrote:
> +static void put_compound_head(struct page *page, int refs)
> +{
> +	/* Do a get_page() first, in case refs == page->_refcount */
> +	get_page(page);
> +	page_ref_sub(page, refs);
> +	put_page(page);
> +}

It's not terribly efficient. Maybe something like:

	VM_BUG_ON_PAGE(page_ref_count(page) < ref, page);
	if (refs > 2)
		page_ref_sub(page, refs - 1);
	put_page(page);

?
John Hubbard Dec. 18, 2019, 10:15 p.m. UTC | #2
On 12/18/19 7:52 AM, Kirill A. Shutemov wrote:
> On Mon, Dec 16, 2019 at 02:25:13PM -0800, John Hubbard wrote:
>> +static void put_compound_head(struct page *page, int refs)
>> +{
>> +	/* Do a get_page() first, in case refs == page->_refcount */
>> +	get_page(page);
>> +	page_ref_sub(page, refs);
>> +	put_page(page);
>> +}
> 
> It's not terribly efficient. Maybe something like:
> 
> 	VM_BUG_ON_PAGE(page_ref_count(page) < ref, page);
> 	if (refs > 2)
> 		page_ref_sub(page, refs - 1);
> 	put_page(page);
> 
> ?

OK, but how about this instead? I don't see the need for a "2", as that
is a magic number that requires explanation. Whereas "1" is not a magic
number--here it means: either there are "many" (>1) refs, or not.

And the routine won't be called with refs less than about 32 (2MB huge
page, 64KB base page == 32 subpages) anyway.

	VM_BUG_ON_PAGE(page_ref_count(page) < refs, page);
	/*
	 * Calling put_page() for each ref is unnecessarily slow. Only the last
	 * ref needs a put_page().
	 */
	if (refs > 1)
		page_ref_sub(page, refs - 1);
	put_page(page);


thanks,
Kirill A. Shutemov Dec. 18, 2019, 10:45 p.m. UTC | #3
On Wed, Dec 18, 2019 at 02:15:53PM -0800, John Hubbard wrote:
> On 12/18/19 7:52 AM, Kirill A. Shutemov wrote:
> > On Mon, Dec 16, 2019 at 02:25:13PM -0800, John Hubbard wrote:
> > > +static void put_compound_head(struct page *page, int refs)
> > > +{
> > > +	/* Do a get_page() first, in case refs == page->_refcount */
> > > +	get_page(page);
> > > +	page_ref_sub(page, refs);
> > > +	put_page(page);
> > > +}
> > 
> > It's not terribly efficient. Maybe something like:
> > 
> > 	VM_BUG_ON_PAGE(page_ref_count(page) < ref, page);
> > 	if (refs > 2)
> > 		page_ref_sub(page, refs - 1);
> > 	put_page(page);
> > 
> > ?
> 
> OK, but how about this instead? I don't see the need for a "2", as that
> is a magic number that requires explanation. Whereas "1" is not a magic
> number--here it means: either there are "many" (>1) refs, or not.

Yeah, it's my thinko. Sure, it has to be '1' (or >= 2, which is less readable).

> And the routine won't be called with refs less than about 32 (2MB huge
> page, 64KB base page == 32 subpages) anyway.

It's hard to make predictions about future :P

> 	VM_BUG_ON_PAGE(page_ref_count(page) < refs, page);
> 	/*
> 	 * Calling put_page() for each ref is unnecessarily slow. Only the last
> 	 * ref needs a put_page().
> 	 */
> 	if (refs > 1)
> 		page_ref_sub(page, refs - 1);
> 	put_page(page);

Looks good to me.
diff mbox series

Patch

diff --git a/mm/gup.c b/mm/gup.c
index 7646bf993b25..f764432914c4 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1978,6 +1978,25 @@  static int __gup_device_huge_pud(pud_t pud, pud_t *pudp, unsigned long addr,
 }
 #endif
 
+static int record_subpages(struct page *page, unsigned long addr,
+			   unsigned long end, struct page **pages)
+{
+	int nr;
+
+	for (nr = 0; addr != end; addr += PAGE_SIZE)
+		pages[nr++] = page++;
+
+	return nr;
+}
+
+static void put_compound_head(struct page *page, int refs)
+{
+	/* Do a get_page() first, in case refs == page->_refcount */
+	get_page(page);
+	page_ref_sub(page, refs);
+	put_page(page);
+}
+
 #ifdef CONFIG_ARCH_HAS_HUGEPD
 static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end,
 				      unsigned long sz)
@@ -2007,32 +2026,20 @@  static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr,
 	/* hugepages are never "special" */
 	VM_BUG_ON(!pfn_valid(pte_pfn(pte)));
 
-	refs = 0;
 	head = pte_page(pte);
-
 	page = head + ((addr & (sz-1)) >> PAGE_SHIFT);
-	do {
-		VM_BUG_ON(compound_head(page) != head);
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
 	head = try_get_compound_head(head, refs);
-	if (!head) {
-		*nr -= refs;
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pte_val(pte) != pte_val(*ptep))) {
-		/* Could be optimized better */
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }
@@ -2079,28 +2086,19 @@  static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr,
 		return __gup_device_huge_pmd(orig, pmdp, addr, end, pages, nr);
 	}
 
-	refs = 0;
 	page = pmd_page(orig) + ((addr & ~PMD_MASK) >> PAGE_SHIFT);
-	do {
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
 	head = try_get_compound_head(pmd_page(orig), refs);
-	if (!head) {
-		*nr -= refs;
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pmd_val(orig) != pmd_val(*pmdp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }
@@ -2120,28 +2118,19 @@  static int gup_huge_pud(pud_t orig, pud_t *pudp, unsigned long addr,
 		return __gup_device_huge_pud(orig, pudp, addr, end, pages, nr);
 	}
 
-	refs = 0;
 	page = pud_page(orig) + ((addr & ~PUD_MASK) >> PAGE_SHIFT);
-	do {
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
 	head = try_get_compound_head(pud_page(orig), refs);
-	if (!head) {
-		*nr -= refs;
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pud_val(orig) != pud_val(*pudp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }
@@ -2157,28 +2146,20 @@  static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr,
 		return 0;
 
 	BUILD_BUG_ON(pgd_devmap(orig));
-	refs = 0;
+
 	page = pgd_page(orig) + ((addr & ~PGDIR_MASK) >> PAGE_SHIFT);
-	do {
-		pages[*nr] = page;
-		(*nr)++;
-		page++;
-		refs++;
-	} while (addr += PAGE_SIZE, addr != end);
+	refs = record_subpages(page, addr, end, pages + *nr);
 
 	head = try_get_compound_head(pgd_page(orig), refs);
-	if (!head) {
-		*nr -= refs;
+	if (!head)
 		return 0;
-	}
 
 	if (unlikely(pgd_val(orig) != pgd_val(*pgdp))) {
-		*nr -= refs;
-		while (refs--)
-			put_page(head);
+		put_compound_head(head, refs);
 		return 0;
 	}
 
+	*nr += refs;
 	SetPageReferenced(head);
 	return 1;
 }