The patch titled
Subject: mm: move hot-plug specific memory init into separate functions and optimize
has been added to the -mm tree. Its filename is
mm-move-hot-plug-specific-memory-init-into-separate-functions-and-optimize.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-move-hot-plug-specific-memory-init-into-separate-functions-and-optimize.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-move-hot-plug-specific-memory-init-into-separate-functions-and-optimize.patch
Before you just go and hit "reply", please:
a) Consider who else should be cc'ed
b) Prefer to cc a suitable mailing list as well
c) Ideally: find the original patch on the mailing list and do a
reply-to-all to that, adding suitable additional cc's
*** Remember to use Documentation/process/submit-checklist.rst when testing your code ***
The -mm tree is included into linux-next and is updated
there every 3-4 working days
------------------------------------------------------
From: Alexander Duyck <alexander.h.duyck@xxxxxxxxxxxxxxx>
Subject: mm: move hot-plug specific memory init into separate functions and optimize
Combine the bits in memmap_init_zone and memmap_init_zone_device that are
related to hotplug into a single function called __memmap_init_hotplug.
Also take the opportunity to integrate __init_single_page's functionality
into this function. In doing so we can get rid of some of the redundancy
such as the LRU pointers versus the pgmap.
Link: http://lkml.kernel.org/r/154361479366.7497.13916678539146224699.stgit@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Alexander Duyck <alexander.h.duyck@xxxxxxxxxxxxxxx>
Reviewed-by: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx>
Cc: Dan Williams <dan.j.williams@xxxxxxxxx>
Cc: Dave Jiang <dave.jiang@xxxxxxxxx>
Cc: David S. Miller <davem@xxxxxxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Khalid Aziz <khalid.aziz@xxxxxxxxxx>
Cc: Kirill A. Shutemov <kirill.shutemov@xxxxxxxxxxxxxxx>
Cc: Laurent Dufour <ldufour@xxxxxxxxxxxxxxxxxx>
Cc: Matthew Wilcox <willy@xxxxxxxxxxxxx>
Cc: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Cc: Michal Hocko <mhocko@xxxxxxxx>
Cc: Mike Rapoport <rppt@xxxxxxxxxxxxxxxxxx>
Cc: Pavel Tatashin <pavel.tatashin@xxxxxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/page_alloc.c | 208 +++++++++++++++++++++++++++++-----------------
1 file changed, 135 insertions(+), 73 deletions(-)
--- a/mm/page_alloc.c~mm-move-hot-plug-specific-memory-init-into-separate-functions-and-optimize
+++ a/mm/page_alloc.c
@@ -1181,8 +1181,9 @@ static void free_one_page(struct zone *z
spin_unlock(&zone->lock);
}
-static void __meminit __init_single_page(struct page *page, unsigned long pfn,
- unsigned long zone, int nid)
+static void __meminit __init_struct_page_nolru(struct page *page,
+ unsigned long pfn,
+ unsigned long zone, int nid)
{
mm_zero_struct_page(page);
set_page_links(page, zone, nid, pfn);
@@ -1191,7 +1192,6 @@ static void __meminit __init_single_page
page_cpupid_reset_last(page);
page_kasan_tag_reset(page);
- INIT_LIST_HEAD(&page->lru);
#ifdef WANT_PAGE_VIRTUAL
/* The shift won't overflow because ZONE_NORMAL is below 4G. */
if (!is_highmem_idx(zone))
@@ -1199,6 +1199,80 @@ static void __meminit __init_single_page
#endif
}
+static void __meminit __init_single_page(struct page *page, unsigned long pfn,
+ unsigned long zone, int nid)
+{
+ __init_struct_page_nolru(page, pfn, zone, nid);
+ INIT_LIST_HEAD(&page->lru);
+}
+
+static void __meminit __init_pageblock(unsigned long start_pfn,
+ unsigned long nr_pages,
+ unsigned long zone, int nid,
+ struct dev_pagemap *pgmap)
+{
+ unsigned long nr_pgmask = pageblock_nr_pages - 1;
+ struct page *start_page = pfn_to_page(start_pfn);
+ unsigned long pfn = start_pfn + nr_pages - 1;
+ struct page *page;
+
+ /*
+ * Enforce the following requirements:
+ * size > 0
+ * size < pageblock_nr_pages
+ * start_pfn -> pfn does not cross pageblock_nr_pages boundary
+ */
+ VM_BUG_ON(((start_pfn ^ pfn) | (nr_pages - 1)) > nr_pgmask);
+
+ /*
+ * Work from highest page to lowest, this way we will still be
+ * warm in the cache when we call set_pageblock_migratetype
+ * below.
+ *
+ * The loop is based around the page pointer as the main index
+ * instead of the pfn because pfn is not used inside the loop if
+ * the section number is not in page flags and WANT_PAGE_VIRTUAL
+ * is not defined.
+ */
+ for (page = start_page + nr_pages; page-- != start_page; pfn--) {
+ __init_struct_page_nolru(page, pfn, zone, nid);
+ /*
+ * Mark page reserved as it will need to wait for onlining
+ * phase for it to be fully associated with a zone.
+ *
+ * We can use the non-atomic __set_bit operation for setting
+ * the flag as we are still initializing the pages.
+ */
+ __SetPageReserved(page);
+ /*
+ * ZONE_DEVICE pages union ->lru with a ->pgmap back
+ * pointer and hmm_data. It is a bug if a ZONE_DEVICE
+ * page is ever freed or placed on a driver-private list.
+ */
+ page->pgmap = pgmap;
+ if (!pgmap)
+ INIT_LIST_HEAD(&page->lru);
+ }
+
+ /*
+ * Mark the block movable so that blocks are reserved for
+ * movable at startup. This will force kernel allocations
+ * to reserve their blocks rather than leaking throughout
+ * the address space during boot when many long-lived
+ * kernel allocations are made.
+ *
+ * bitmap is created for zone's valid pfn range. but memmap
+ * can be created for invalid pages (for alignment)
+ * check here not to call set_pageblock_migratetype() against
+ * pfn out of zone.
+ *
+ * Please note that MEMMAP_HOTPLUG path doesn't clear memmap
+ * because this is done early in sparse_add_one_section
+ */
+ if (!(start_pfn & nr_pgmask))
+ set_pageblock_migratetype(start_page, MIGRATE_MOVABLE);
+}
+
#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
static void __meminit init_reserved_page(unsigned long pfn)
{
@@ -5697,6 +5771,25 @@ overlap_memmap_init(unsigned long zone,
return false;
}
+static void __meminit __memmap_init_hotplug(unsigned long size, int nid,
+ unsigned long zone,
+ unsigned long start_pfn,
+ struct dev_pagemap *pgmap)
+{
+ unsigned long pfn = start_pfn + size;
+
+ while (pfn != start_pfn) {
+ unsigned long stride = pfn;
+
+ pfn = max(ALIGN_DOWN(pfn - 1, pageblock_nr_pages), start_pfn);
+ stride -= pfn;
+
+ __init_pageblock(pfn, stride, zone, nid, pgmap);
+
+ cond_resched();
+ }
+}
+
/*
* Initially all pages are reserved - free ones are freed
* up by memblock_free_all() once the early boot process is
@@ -5707,49 +5800,59 @@ void __meminit memmap_init_zone(unsigned
struct vmem_altmap *altmap)
{
unsigned long pfn, end_pfn = start_pfn + size;
- struct page *page;
if (highest_memmap_pfn < end_pfn - 1)
highest_memmap_pfn = end_pfn - 1;
+ if (context == MEMMAP_HOTPLUG) {
#ifdef CONFIG_ZONE_DEVICE
- /*
- * Honor reservation requested by the driver for this ZONE_DEVICE
- * memory. We limit the total number of pages to initialize to just
- * those that might contain the memory mapping. We will defer the
- * ZONE_DEVICE page initialization until after we have released
- * the hotplug lock.
- */
- if (zone == ZONE_DEVICE) {
- if (!altmap)
- return;
+ /*
+ * Honor reservation requested by the driver for this
+ * ZONE_DEVICE memory. We limit the total number of pages to
+ * initialize to just those that might contain the memory
+ * mapping. We will defer the ZONE_DEVICE page initialization
+ * until after we have released the hotplug lock.
+ */
+ if (zone == ZONE_DEVICE) {
+ if (!altmap)
+ return;
+
+ if (start_pfn == altmap->base_pfn)
+ start_pfn += altmap->reserve;
+ end_pfn = altmap->base_pfn +
+ vmem_altmap_offset(altmap);
+ }
+#endif
+ /*
+ * For these ZONE_DEVICE pages we don't need to record the
+ * pgmap as they should represent only those pages used to
+ * store the memory map. The actual ZONE_DEVICE pages will
+ * be initialized later.
+ */
+ __memmap_init_hotplug(end_pfn - start_pfn, nid, zone,
+ start_pfn, NULL);
- if (start_pfn == altmap->base_pfn)
- start_pfn += altmap->reserve;
- end_pfn = altmap->base_pfn + vmem_altmap_offset(altmap);
+ return;
}
-#endif
for (pfn = start_pfn; pfn < end_pfn; pfn++) {
+ struct page *page;
+
/*
* There can be holes in boot-time mem_map[]s handed to this
* function. They do not exist on hotplugged memory.
*/
- if (context == MEMMAP_EARLY) {
- if (!early_pfn_valid(pfn))
- continue;
- if (!early_pfn_in_nid(pfn, nid))
- continue;
- if (overlap_memmap_init(zone, &pfn))
- continue;
- if (defer_init(nid, pfn, end_pfn))
- break;
- }
+ if (!early_pfn_valid(pfn))
+ continue;
+ if (!early_pfn_in_nid(pfn, nid))
+ continue;
+ if (overlap_memmap_init(zone, &pfn))
+ continue;
+ if (defer_init(nid, pfn, end_pfn))
+ break;
page = pfn_to_page(pfn);
__init_single_page(page, pfn, zone, nid);
- if (context == MEMMAP_HOTPLUG)
- __SetPageReserved(page);
/*
* Mark the block movable so that blocks are reserved for
@@ -5776,7 +5879,6 @@ void __ref memmap_init_zone_device(struc
unsigned long size,
struct dev_pagemap *pgmap)
{
- unsigned long pfn, end_pfn = start_pfn + size;
struct pglist_data *pgdat = zone->zone_pgdat;
unsigned long zone_idx = zone_idx(zone);
unsigned long start = jiffies;
@@ -5792,53 +5894,13 @@ void __ref memmap_init_zone_device(struc
*/
if (pgmap->altmap_valid) {
struct vmem_altmap *altmap = &pgmap->altmap;
+ unsigned long end_pfn = start_pfn + size;
start_pfn = altmap->base_pfn + vmem_altmap_offset(altmap);
size = end_pfn - start_pfn;
}
- for (pfn = start_pfn; pfn < end_pfn; pfn++) {
- struct page *page = pfn_to_page(pfn);
-
- __init_single_page(page, pfn, zone_idx, nid);
-
- /*
- * Mark page reserved as it will need to wait for onlining
- * phase for it to be fully associated with a zone.
- *
- * We can use the non-atomic __set_bit operation for setting
- * the flag as we are still initializing the pages.
- */
- __SetPageReserved(page);
-
- /*
- * ZONE_DEVICE pages union ->lru with a ->pgmap back
- * pointer and hmm_data. It is a bug if a ZONE_DEVICE
- * page is ever freed or placed on a driver-private list.
- */
- page->pgmap = pgmap;
- page->hmm_data = 0;
-
- /*
- * Mark the block movable so that blocks are reserved for
- * movable at startup. This will force kernel allocations
- * to reserve their blocks rather than leaking throughout
- * the address space during boot when many long-lived
- * kernel allocations are made.
- *
- * bitmap is created for zone's valid pfn range. but memmap
- * can be created for invalid pages (for alignment)
- * check here not to call set_pageblock_migratetype() against
- * pfn out of zone.
- *
- * Please note that MEMMAP_HOTPLUG path doesn't clear memmap
- * because this is done early in sparse_add_one_section
- */
- if (!(pfn & (pageblock_nr_pages - 1))) {
- set_pageblock_migratetype(page, MIGRATE_MOVABLE);
- cond_resched();
- }
- }
+ __memmap_init_hotplug(size, nid, zone_idx, start_pfn, pgmap);
pr_info("%s initialised, %lu pages in %ums\n", dev_name(pgmap->dev),
size, jiffies_to_msecs(jiffies - start));
_
Patches currently in -mm which might be from alexander.h.duyck@xxxxxxxxxxxxxxx are
mm-use-mm_zero_struct_page-from-sparc-on-all-64b-architectures.patch
mm-drop-meminit_pfn_in_nid-as-it-is-redundant.patch
mm-implement-new-zone-specific-memblock-iterator.patch
mm-initialize-max_order_nr_pages-at-a-time-instead-of-doing-larger-sections.patch
mm-move-hot-plug-specific-memory-init-into-separate-functions-and-optimize.patch
mm-add-reserved-flag-setting-to-set_page_links.patch
mm-use-common-iterator-for-deferred_init_pages-and-deferred_free_pages.patch
