diff mbox series

[mm,v5,7/7] mm: Use common iterator for deferred_init_pages and deferred_free_pages

Message ID 154145280115.30046.13334106887516645119.stgit@ahduyck-desk1.jf.intel.com (mailing list archive)
State Superseded
Headers show
Series Deferred page init improvements | expand

Commit Message

Alexander Duyck Nov. 5, 2018, 9:20 p.m. UTC
This patch creates a common iterator to be used by both deferred_init_pages
and deferred_free_pages. By doing this we can cut down a bit on code
overhead as they will likely both be inlined into the same function anyway.

This new approach allows deferred_init_pages to make use of
__init_pageblock. By doing this we can cut down on the code size by sharing
code between both the hotplug and deferred memory init code paths.

An additional benefit to this approach is that we improve in cache locality
of the memory init as we can focus on the memory areas related to
identifying if a given PFN is valid and keep that warm in the cache until
we transition to a region of a different type. So we will stream through a
chunk of valid blocks before we turn to initializing page structs.

On my x86_64 test system with 384GB of memory per node I saw a reduction in
initialization time from 1.38s to 1.06s as a result of this patch.

Signed-off-by: Alexander Duyck <alexander.h.duyck@linux.intel.com>
---
 mm/page_alloc.c |  134 +++++++++++++++++++++++++++----------------------------
 1 file changed, 65 insertions(+), 69 deletions(-)

Comments

Pasha Tatashin Nov. 10, 2018, 4:13 a.m. UTC | #1
On 18-11-05 13:20:01, Alexander Duyck wrote:
> +static unsigned long __next_pfn_valid_range(unsigned long *i,
> +					    unsigned long end_pfn)
>  {
> -	if (!pfn_valid_within(pfn))
> -		return false;
> -	if (!(pfn & (pageblock_nr_pages - 1)) && !pfn_valid(pfn))
> -		return false;
> -	return true;
> +	unsigned long pfn = *i;
> +	unsigned long count;
> +
> +	while (pfn < end_pfn) {
> +		unsigned long t = ALIGN(pfn + 1, pageblock_nr_pages);
> +		unsigned long pageblock_pfn = min(t, end_pfn);
> +
> +#ifndef CONFIG_HOLES_IN_ZONE
> +		count = pageblock_pfn - pfn;
> +		pfn = pageblock_pfn;
> +		if (!pfn_valid(pfn))
> +			continue;
> +#else
> +		for (count = 0; pfn < pageblock_pfn; pfn++) {
> +			if (pfn_valid_within(pfn)) {
> +				count++;
> +				continue;
> +			}
> +
> +			if (count)
> +				break;
> +		}
> +
> +		if (!count)
> +			continue;
> +#endif
> +		*i = pfn;
> +		return count;
> +	}
> +
> +	return 0;
>  }
>  
> +#define for_each_deferred_pfn_valid_range(i, start_pfn, end_pfn, pfn, count) \
> +	for (i = (start_pfn),						     \
> +	     count = __next_pfn_valid_range(&i, (end_pfn));		     \
> +	     count && ({ pfn = i - count; 1; });			     \
> +	     count = __next_pfn_valid_range(&i, (end_pfn)))

Can this be improved somehow? It took me a while to understand this
piece of code. i is actually end of block, and not an index by PFN, ({pfn = i - count; 1;}) is
simply hard to parse. Why can't we make __next_pfn_valid_range() to
return both end and a start of a block?

The rest is good:

Reviewed-by: Pavel Tatashin <pasha.tatashin@soleen.com>

Thank you,
Pasha
Alexander Duyck Nov. 12, 2018, 3:12 p.m. UTC | #2
On 11/9/2018 8:13 PM, Pavel Tatashin wrote:
> On 18-11-05 13:20:01, Alexander Duyck wrote:
>> +static unsigned long __next_pfn_valid_range(unsigned long *i,
>> +					    unsigned long end_pfn)
>>   {
>> -	if (!pfn_valid_within(pfn))
>> -		return false;
>> -	if (!(pfn & (pageblock_nr_pages - 1)) && !pfn_valid(pfn))
>> -		return false;
>> -	return true;
>> +	unsigned long pfn = *i;
>> +	unsigned long count;
>> +
>> +	while (pfn < end_pfn) {
>> +		unsigned long t = ALIGN(pfn + 1, pageblock_nr_pages);
>> +		unsigned long pageblock_pfn = min(t, end_pfn);
>> +
>> +#ifndef CONFIG_HOLES_IN_ZONE
>> +		count = pageblock_pfn - pfn;
>> +		pfn = pageblock_pfn;
>> +		if (!pfn_valid(pfn))
>> +			continue;
>> +#else
>> +		for (count = 0; pfn < pageblock_pfn; pfn++) {
>> +			if (pfn_valid_within(pfn)) {
>> +				count++;
>> +				continue;
>> +			}
>> +
>> +			if (count)
>> +				break;
>> +		}
>> +
>> +		if (!count)
>> +			continue;
>> +#endif
>> +		*i = pfn;
>> +		return count;
>> +	}
>> +
>> +	return 0;
>>   }
>>   
>> +#define for_each_deferred_pfn_valid_range(i, start_pfn, end_pfn, pfn, count) \
>> +	for (i = (start_pfn),						     \
>> +	     count = __next_pfn_valid_range(&i, (end_pfn));		     \
>> +	     count && ({ pfn = i - count; 1; });			     \
>> +	     count = __next_pfn_valid_range(&i, (end_pfn)))
> 
> Can this be improved somehow? It took me a while to understand this
> piece of code. i is actually end of block, and not an index by PFN, ({pfn = i - count; 1;}) is
> simply hard to parse. Why can't we make __next_pfn_valid_range() to
> return both end and a start of a block?

One thing I could do is flip the direction and work from the end to the 
start. If I did that then 'i' and 'pfn' would be the same value and I 
wouldn't have to do the subtraction. If that works for you I could 
probably do that and it may actually be more efficient.

Otherwise I could probably pass pfn as a reference, and compute it in 
the case where count is non-zero.

> The rest is good:
> 
> Reviewed-by: Pavel Tatashin <pasha.tatashin@soleen.com>
> 
> Thank you,
> Pasha
>
diff mbox series

Patch

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 9eb993a9be99..521b94eb02a0 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1484,32 +1484,6 @@  void clear_zone_contiguous(struct zone *zone)
 }
 
 #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
-static void __init deferred_free_range(unsigned long pfn,
-				       unsigned long nr_pages)
-{
-	struct page *page;
-	unsigned long i;
-
-	if (!nr_pages)
-		return;
-
-	page = pfn_to_page(pfn);
-
-	/* Free a large naturally-aligned chunk if possible */
-	if (nr_pages == pageblock_nr_pages &&
-	    (pfn & (pageblock_nr_pages - 1)) == 0) {
-		set_pageblock_migratetype(page, MIGRATE_MOVABLE);
-		__free_pages_core(page, pageblock_order);
-		return;
-	}
-
-	for (i = 0; i < nr_pages; i++, page++, pfn++) {
-		if ((pfn & (pageblock_nr_pages - 1)) == 0)
-			set_pageblock_migratetype(page, MIGRATE_MOVABLE);
-		__free_pages_core(page, 0);
-	}
-}
-
 /* Completion tracking for deferred_init_memmap() threads */
 static atomic_t pgdat_init_n_undone __initdata;
 static __initdata DECLARE_COMPLETION(pgdat_init_all_done_comp);
@@ -1521,48 +1495,77 @@  static inline void __init pgdat_init_report_one_done(void)
 }
 
 /*
- * Returns true if page needs to be initialized or freed to buddy allocator.
+ * Returns count if page range needs to be initialized or freed
  *
- * First we check if pfn is valid on architectures where it is possible to have
- * holes within pageblock_nr_pages. On systems where it is not possible, this
- * function is optimized out.
+ * First, we check if a current large page is valid by only checking the
+ * validity of the head pfn.
  *
- * Then, we check if a current large page is valid by only checking the validity
- * of the head pfn.
+ * Then we check if the contiguous pfns are valid on architectures where it
+ * is possible to have holes within pageblock_nr_pages. On systems where it
+ * is not possible, this function is optimized out.
  */
-static inline bool __init deferred_pfn_valid(unsigned long pfn)
+static unsigned long __next_pfn_valid_range(unsigned long *i,
+					    unsigned long end_pfn)
 {
-	if (!pfn_valid_within(pfn))
-		return false;
-	if (!(pfn & (pageblock_nr_pages - 1)) && !pfn_valid(pfn))
-		return false;
-	return true;
+	unsigned long pfn = *i;
+	unsigned long count;
+
+	while (pfn < end_pfn) {
+		unsigned long t = ALIGN(pfn + 1, pageblock_nr_pages);
+		unsigned long pageblock_pfn = min(t, end_pfn);
+
+#ifndef CONFIG_HOLES_IN_ZONE
+		count = pageblock_pfn - pfn;
+		pfn = pageblock_pfn;
+		if (!pfn_valid(pfn))
+			continue;
+#else
+		for (count = 0; pfn < pageblock_pfn; pfn++) {
+			if (pfn_valid_within(pfn)) {
+				count++;
+				continue;
+			}
+
+			if (count)
+				break;
+		}
+
+		if (!count)
+			continue;
+#endif
+		*i = pfn;
+		return count;
+	}
+
+	return 0;
 }
 
+#define for_each_deferred_pfn_valid_range(i, start_pfn, end_pfn, pfn, count) \
+	for (i = (start_pfn),						     \
+	     count = __next_pfn_valid_range(&i, (end_pfn));		     \
+	     count && ({ pfn = i - count; 1; });			     \
+	     count = __next_pfn_valid_range(&i, (end_pfn)))
 /*
  * Free pages to buddy allocator. Try to free aligned pages in
  * pageblock_nr_pages sizes.
  */
-static void __init deferred_free_pages(unsigned long pfn,
+static void __init deferred_free_pages(unsigned long start_pfn,
 				       unsigned long end_pfn)
 {
-	unsigned long nr_pgmask = pageblock_nr_pages - 1;
-	unsigned long nr_free = 0;
-
-	for (; pfn < end_pfn; pfn++) {
-		if (!deferred_pfn_valid(pfn)) {
-			deferred_free_range(pfn - nr_free, nr_free);
-			nr_free = 0;
-		} else if (!(pfn & nr_pgmask)) {
-			deferred_free_range(pfn - nr_free, nr_free);
-			nr_free = 1;
-			touch_nmi_watchdog();
+	unsigned long i, pfn, count;
+
+	for_each_deferred_pfn_valid_range(i, start_pfn, end_pfn, pfn, count) {
+		struct page *page = pfn_to_page(pfn);
+
+		if (count == pageblock_nr_pages) {
+			__free_pages_core(page, pageblock_order);
 		} else {
-			nr_free++;
+			while (count--)
+				__free_pages_core(page++, 0);
 		}
+
+		touch_nmi_watchdog();
 	}
-	/* Free the last block of pages to allocator */
-	deferred_free_range(pfn - nr_free, nr_free);
 }
 
 /*
@@ -1571,29 +1574,22 @@  static void __init deferred_free_pages(unsigned long pfn,
  * Return number of pages initialized.
  */
 static unsigned long  __init deferred_init_pages(struct zone *zone,
-						 unsigned long pfn,
+						 unsigned long start_pfn,
 						 unsigned long end_pfn)
 {
-	unsigned long nr_pgmask = pageblock_nr_pages - 1;
+	unsigned long i, pfn, count;
 	int nid = zone_to_nid(zone);
 	unsigned long nr_pages = 0;
 	int zid = zone_idx(zone);
-	struct page *page = NULL;
 
-	for (; pfn < end_pfn; pfn++) {
-		if (!deferred_pfn_valid(pfn)) {
-			page = NULL;
-			continue;
-		} else if (!page || !(pfn & nr_pgmask)) {
-			page = pfn_to_page(pfn);
-			touch_nmi_watchdog();
-		} else {
-			page++;
-		}
-		__init_single_page(page, pfn, zid, nid);
-		nr_pages++;
+	for_each_deferred_pfn_valid_range(i, start_pfn, end_pfn, pfn, count) {
+		nr_pages += count;
+		__init_pageblock(pfn, count, zid, nid, NULL, false);
+
+		touch_nmi_watchdog();
 	}
-	return (nr_pages);
+
+	return nr_pages;
 }
 
 /*