The patch titled
Subject: mm: drop meminit_pfn_in_nid as it is redundant
has been added to the -mm tree. Its filename is
mm-drop-meminit_pfn_in_nid-as-it-is-redundant.patch
This patch should soon appear at
http://ozlabs.org/~akpm/mmots/broken-out/mm-drop-meminit_pfn_in_nid-as-it-is-redundant.patch
and later at
http://ozlabs.org/~akpm/mmotm/broken-out/mm-drop-meminit_pfn_in_nid-as-it-is-redundant.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: drop meminit_pfn_in_nid as it is redundant
As best as I can tell the meminit_pfn_in_nid call is completely redundant.
The deferred memory initialization is already making use of
for_each_free_mem_range which in turn will call into __next_mem_range
which will only return a memory range if it matches the node ID provided
assuming it is not NUMA_NO_NODE.
I am operating on the assumption that there are no zones or pgdata_t
structures that have a NUMA node of NUMA_NO_NODE associated with them. If
that is the case then __next_mem_range will never return a memory range
that doesn't match the zone's node ID and as such the check is redundant.
So one piece I would like to verify on this is if this works for ia64.
Technically it was using a different approach to get the node ID, but it
seems to have the node ID also encoded into the memblock. So I am
assuming this is okay, but would like to get confirmation on that.
On my x86_64 test system with 384GB of memory per node I saw a reduction
in initialization time from 2.80s to 1.85s as a result of this patch.
Link: http://lkml.kernel.org/r/154145277561.30046.12617658691920831062.stgit@xxxxxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Alexander Duyck <alexander.h.duyck@xxxxxxxxxxxxxxx>
Reviewed-by: Pavel Tatashin <pavel.tatashin@xxxxxxxxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxxx>
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: Mike Rapoport <rppt@xxxxxxxxxxxxxxxxxx>
Cc: Vlastimil Babka <vbabka@xxxxxxx>
Cc: Oscar Salvador <osalvador@xxxxxxxxxxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
mm/page_alloc.c | 51 ++++++++++++----------------------------------
1 file changed, 14 insertions(+), 37 deletions(-)
--- a/mm/page_alloc.c~mm-drop-meminit_pfn_in_nid-as-it-is-redundant
+++ a/mm/page_alloc.c
@@ -1305,36 +1305,22 @@ int __meminit early_pfn_to_nid(unsigned
#endif
#ifdef CONFIG_NODES_SPAN_OTHER_NODES
-static inline bool __meminit __maybe_unused
-meminit_pfn_in_nid(unsigned long pfn, int node,
- struct mminit_pfnnid_cache *state)
+/* Only safe to use early in boot when initialisation is single-threaded */
+static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
{
int nid;
- nid = __early_pfn_to_nid(pfn, state);
+ nid = __early_pfn_to_nid(pfn, &early_pfnnid_cache);
if (nid >= 0 && nid != node)
return false;
return true;
}
-/* Only safe to use early in boot when initialisation is single-threaded */
-static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
-{
- return meminit_pfn_in_nid(pfn, node, &early_pfnnid_cache);
-}
-
#else
-
static inline bool __meminit early_pfn_in_nid(unsigned long pfn, int node)
{
return true;
}
-static inline bool __meminit __maybe_unused
-meminit_pfn_in_nid(unsigned long pfn, int node,
- struct mminit_pfnnid_cache *state)
-{
- return true;
-}
#endif
@@ -1463,21 +1449,13 @@ static inline void __init pgdat_init_rep
*
* Then, we check if a current large page is valid by only checking the validity
* of the head pfn.
- *
- * Finally, meminit_pfn_in_nid is checked on systems where pfns can interleave
- * within a node: a pfn is between start and end of a node, but does not belong
- * to this memory node.
*/
-static inline bool __init
-deferred_pfn_valid(int nid, unsigned long pfn,
- struct mminit_pfnnid_cache *nid_init_state)
+static inline bool __init deferred_pfn_valid(unsigned long pfn)
{
if (!pfn_valid_within(pfn))
return false;
if (!(pfn & (pageblock_nr_pages - 1)) && !pfn_valid(pfn))
return false;
- if (!meminit_pfn_in_nid(pfn, nid, nid_init_state))
- return false;
return true;
}
@@ -1485,15 +1463,14 @@ deferred_pfn_valid(int nid, unsigned lon
* Free pages to buddy allocator. Try to free aligned pages in
* pageblock_nr_pages sizes.
*/
-static void __init deferred_free_pages(int nid, int zid, unsigned long pfn,
+static void __init deferred_free_pages(unsigned long pfn,
unsigned long end_pfn)
{
- struct mminit_pfnnid_cache nid_init_state = { };
unsigned long nr_pgmask = pageblock_nr_pages - 1;
unsigned long nr_free = 0;
for (; pfn < end_pfn; pfn++) {
- if (!deferred_pfn_valid(nid, pfn, &nid_init_state)) {
+ if (!deferred_pfn_valid(pfn)) {
deferred_free_range(pfn - nr_free, nr_free);
nr_free = 0;
} else if (!(pfn & nr_pgmask)) {
@@ -1513,17 +1490,18 @@ static void __init deferred_free_pages(i
* by performing it only once every pageblock_nr_pages.
* Return number of pages initialized.
*/
-static unsigned long __init deferred_init_pages(int nid, int zid,
+static unsigned long __init deferred_init_pages(struct zone *zone,
unsigned long pfn,
unsigned long end_pfn)
{
- struct mminit_pfnnid_cache nid_init_state = { };
unsigned long nr_pgmask = pageblock_nr_pages - 1;
+ 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(nid, pfn, &nid_init_state)) {
+ if (!deferred_pfn_valid(pfn)) {
page = NULL;
continue;
} else if (!page || !(pfn & nr_pgmask)) {
@@ -1586,12 +1564,12 @@ static int __init deferred_init_memmap(v
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));
- nr_pages += deferred_init_pages(nid, zid, spfn, epfn);
+ 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));
- deferred_free_pages(nid, zid, spfn, epfn);
+ deferred_free_pages(spfn, epfn);
}
pgdat_resize_unlock(pgdat, &flags);
@@ -1630,7 +1608,6 @@ static DEFINE_STATIC_KEY_TRUE(deferred_p
static noinline bool __init
deferred_grow_zone(struct zone *zone, unsigned int order)
{
- int zid = zone_idx(zone);
int nid = zone_to_nid(zone);
pg_data_t *pgdat = NODE_DATA(nid);
unsigned long nr_pages_needed = ALIGN(1 << order, PAGES_PER_SECTION);
@@ -1680,7 +1657,7 @@ deferred_grow_zone(struct zone *zone, un
while (spfn < epfn && nr_pages < nr_pages_needed) {
t = ALIGN(spfn + PAGES_PER_SECTION, PAGES_PER_SECTION);
first_deferred_pfn = min(t, epfn);
- nr_pages += deferred_init_pages(nid, zid, spfn,
+ nr_pages += deferred_init_pages(zone, spfn,
first_deferred_pfn);
spfn = first_deferred_pfn;
}
@@ -1692,7 +1669,7 @@ deferred_grow_zone(struct zone *zone, un
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));
- deferred_free_pages(nid, zid, spfn, epfn);
+ deferred_free_pages(spfn, epfn);
if (first_deferred_pfn == epfn)
break;
_
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
