The patch titled
Subject: mm: implement new zone specific memblock iterator
has been added to the -mm tree. Its filename is
mm-implement-new-zone-specific-memblock-iterator.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-implement-new-zone-specific-memblock-iterator.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-implement-new-zone-specific-memblock-iterator.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: implement new zone specific memblock iterator
This patch introduces a new iterator for_each_free_mem_pfn_range_in_zone.
This iterator will take care of making sure a given memory range provided
is in fact contained within a zone. It takes are of all the bounds
checking we were doing in deferred_grow_zone, and deferred_init_memmap.
In addition it should help to speed up the search a bit by iterating until
the end of a range is greater than the start of the zone pfn range, and
will exit completely if the start is beyond the end of the zone.
Link: http://lkml.kernel.org/r/154145278071.30046.9022571960145979137.stgit@xxxxxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Alexander Duyck <alexander.h.duyck@xxxxxxxxxxxxxxx>
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>
Cc: Oscar Salvador <osalvador@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
include/linux/memblock.h | 22 ++++++++++++
mm/memblock.c | 63 +++++++++++++++++++++++++++++++++++++
mm/page_alloc.c | 31 +++++++-----------
3 files changed, 97 insertions(+), 19 deletions(-)
--- a/include/linux/memblock.h~mm-implement-new-zone-specific-memblock-iterator
+++ a/include/linux/memblock.h
@@ -248,6 +248,28 @@ void __next_mem_pfn_range(int *idx, int
i >= 0; __next_mem_pfn_range(&i, nid, p_start, p_end, p_nid))
#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
+#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+void __next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone,
+ unsigned long *out_spfn,
+ unsigned long *out_epfn);
+/**
+ * for_each_free_mem_range_in_zone - iterate through zone specific free
+ * memblock areas
+ * @i: u64 used as loop variable
+ * @zone: zone in which all of the memory blocks reside
+ * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
+ * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
+ *
+ * Walks over free (memory && !reserved) areas of memblock in a specific
+ * zone. Available as soon as memblock is initialized.
+ */
+#define for_each_free_mem_pfn_range_in_zone(i, zone, p_start, p_end) \
+ for (i = 0, \
+ __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end); \
+ i != (u64)ULLONG_MAX; \
+ __next_mem_pfn_range_in_zone(&i, zone, p_start, p_end))
+#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
+
/**
* for_each_free_mem_range - iterate through free memblock areas
* @i: u64 used as loop variable
--- a/mm/memblock.c~mm-implement-new-zone-specific-memblock-iterator
+++ a/mm/memblock.c
@@ -1239,6 +1239,69 @@ int __init_memblock memblock_set_node(ph
return 0;
}
#endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */
+#ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+/**
+ * __next_mem_pfn_range_in_zone - iterator for for_each_*_range_in_zone()
+ *
+ * @idx: pointer to u64 loop variable
+ * @zone: zone in which all of the memory blocks reside
+ * @out_start: ptr to ulong for start pfn of the range, can be %NULL
+ * @out_end: ptr to ulong for end pfn of the range, can be %NULL
+ *
+ * This function is meant to be a zone/pfn specific wrapper for the
+ * for_each_mem_range type iterators. Specifically they are used in the
+ * deferred memory init routines and as such we were duplicating much of
+ * this logic throughout the code. So instead of having it in multiple
+ * locations it seemed like it would make more sense to centralize this to
+ * one new iterator that does everything they need.
+ */
+void __init_memblock
+__next_mem_pfn_range_in_zone(u64 *idx, struct zone *zone,
+ unsigned long *out_spfn, unsigned long *out_epfn)
+{
+ int zone_nid = zone_to_nid(zone);
+ phys_addr_t spa, epa;
+ int nid;
+
+ __next_mem_range(idx, zone_nid, MEMBLOCK_NONE,
+ &memblock.memory, &memblock.reserved,
+ &spa, &epa, &nid);
+
+ while (*idx != ULLONG_MAX) {
+ unsigned long epfn = PFN_DOWN(epa);
+ unsigned long spfn = PFN_UP(spa);
+
+ /*
+ * Verify the end is at least past the start of the zone and
+ * that we have at least one PFN to initialize.
+ */
+ if (zone->zone_start_pfn < epfn && spfn < epfn) {
+ /* if we went too far just stop searching */
+ if (zone_end_pfn(zone) <= spfn)
+ break;
+
+ if (out_spfn)
+ *out_spfn = max(zone->zone_start_pfn, spfn);
+ if (out_epfn)
+ *out_epfn = min(zone_end_pfn(zone), epfn);
+
+ return;
+ }
+
+ __next_mem_range(idx, zone_nid, MEMBLOCK_NONE,
+ &memblock.memory, &memblock.reserved,
+ &spa, &epa, &nid);
+ }
+
+ /* signal end of iteration */
+ *idx = ULLONG_MAX;
+ if (out_spfn)
+ *out_spfn = ULONG_MAX;
+ if (out_epfn)
+ *out_epfn = 0;
+}
+
+#endif /* CONFIG_DEFERRED_STRUCT_PAGE_INIT */
static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size,
phys_addr_t align, phys_addr_t start,
--- a/mm/page_alloc.c~mm-implement-new-zone-specific-memblock-iterator
+++ a/mm/page_alloc.c
@@ -1520,11 +1520,9 @@ static unsigned long __init deferred_in
static int __init deferred_init_memmap(void *data)
{
pg_data_t *pgdat = data;
- int nid = pgdat->node_id;
unsigned long start = jiffies;
unsigned long nr_pages = 0;
unsigned long spfn, epfn, first_init_pfn, flags;
- phys_addr_t spa, epa;
int zid;
struct zone *zone;
const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
@@ -1561,14 +1559,12 @@ static int __init deferred_init_memmap(v
* freeing pages we can access pages that are ahead (computing buddy
* page in __free_one_page()).
*/
- for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) {
- spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa));
- epfn = min_t(unsigned long, zone_end_pfn(zone), PFN_DOWN(epa));
+ for_each_free_mem_pfn_range_in_zone(i, zone, &spfn, &epfn) {
+ spfn = max_t(unsigned long, first_init_pfn, spfn);
nr_pages += deferred_init_pages(zone, spfn, epfn);
}
- for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) {
- spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa));
- epfn = min_t(unsigned long, zone_end_pfn(zone), PFN_DOWN(epa));
+ for_each_free_mem_pfn_range_in_zone(i, zone, &spfn, &epfn) {
+ spfn = max_t(unsigned long, first_init_pfn, spfn);
deferred_free_pages(spfn, epfn);
}
pgdat_resize_unlock(pgdat, &flags);
@@ -1576,8 +1572,8 @@ static int __init deferred_init_memmap(v
/* Sanity check that the next zone really is unpopulated */
WARN_ON(++zid < MAX_NR_ZONES && populated_zone(++zone));
- pr_info("node %d initialised, %lu pages in %ums\n", nid, nr_pages,
- jiffies_to_msecs(jiffies - start));
+ pr_info("node %d initialised, %lu pages in %ums\n",
+ pgdat->node_id, nr_pages, jiffies_to_msecs(jiffies - start));
pgdat_init_report_one_done();
return 0;
@@ -1608,13 +1604,11 @@ static DEFINE_STATIC_KEY_TRUE(deferred_p
static noinline bool __init
deferred_grow_zone(struct zone *zone, unsigned int order)
{
- int nid = zone_to_nid(zone);
- pg_data_t *pgdat = NODE_DATA(nid);
unsigned long nr_pages_needed = ALIGN(1 << order, PAGES_PER_SECTION);
+ pg_data_t *pgdat = zone->zone_pgdat;
unsigned long nr_pages = 0;
unsigned long first_init_pfn, spfn, epfn, t, flags;
unsigned long first_deferred_pfn = pgdat->first_deferred_pfn;
- phys_addr_t spa, epa;
u64 i;
/* Only the last zone may have deferred pages */
@@ -1650,9 +1644,8 @@ deferred_grow_zone(struct zone *zone, un
return false;
}
- for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) {
- spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa));
- epfn = min_t(unsigned long, zone_end_pfn(zone), PFN_DOWN(epa));
+ for_each_free_mem_pfn_range_in_zone(i, zone, &spfn, &epfn) {
+ spfn = max_t(unsigned long, first_init_pfn, spfn);
while (spfn < epfn && nr_pages < nr_pages_needed) {
t = ALIGN(spfn + PAGES_PER_SECTION, PAGES_PER_SECTION);
@@ -1666,9 +1659,9 @@ deferred_grow_zone(struct zone *zone, un
break;
}
- for_each_free_mem_range(i, nid, MEMBLOCK_NONE, &spa, &epa, NULL) {
- spfn = max_t(unsigned long, first_init_pfn, PFN_UP(spa));
- epfn = min_t(unsigned long, first_deferred_pfn, PFN_DOWN(epa));
+ for_each_free_mem_pfn_range_in_zone(i, zone, &spfn, &epfn) {
+ spfn = max_t(unsigned long, first_init_pfn, spfn);
+ epfn = min_t(unsigned long, first_deferred_pfn, epfn);
deferred_free_pages(spfn, epfn);
if (first_deferred_pfn == epfn)
_
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
