Commit edc2ca61 authored by Vlastimil Babka's avatar Vlastimil Babka Committed by Linus Torvalds

mm, compaction: move pageblock checks up from isolate_migratepages_range()

isolate_migratepages_range() is the main function of the compaction
scanner, called either on a single pageblock by isolate_migratepages()
during regular compaction, or on an arbitrary range by CMA's
__alloc_contig_migrate_range().  It currently perfoms two pageblock-wide
compaction suitability checks, and because of the CMA callpath, it tracks
if it crossed a pageblock boundary in order to repeat those checks.

However, closer inspection shows that those checks are always true for CMA:
- isolation_suitable() is true because CMA sets cc->ignore_skip_hint to true
- migrate_async_suitable() check is skipped because CMA uses sync compaction

We can therefore move the compaction-specific checks to
isolate_migratepages() and simplify isolate_migratepages_range().
Furthermore, we can mimic the freepage scanner family of functions, which
has isolate_freepages_block() function called both by compaction from
isolate_freepages() and by CMA from isolate_freepages_range(), where each
use-case adds own specific glue code.  This allows further code
simplification.

Thus, we rename isolate_migratepages_range() to
isolate_migratepages_block() and limit its functionality to a single
pageblock (or its subset).  For CMA, a new different
isolate_migratepages_range() is created as a CMA-specific wrapper for the
_block() function.  The checks specific to compaction are moved to
isolate_migratepages().  As part of the unification of these two families
of functions, we remove the redundant zone parameter where applicable,
since zone pointer is already passed in cc->zone.

Furthermore, going back to compact_zone() and compact_finished() when
pageblock is found unsuitable (now by isolate_migratepages()) is wasteful
- the checks are meant to skip pageblocks quickly.  The patch therefore
also introduces a simple loop into isolate_migratepages() so that it does
not return immediately on failed pageblock checks, but keeps going until
isolate_migratepages_range() gets called once.  Similarily to
isolate_freepages(), the function periodically checks if it needs to
reschedule or abort async compaction.

[iamjoonsoo.kim@lge.com: fix isolated page counting bug in compaction]
Signed-off-by: default avatarVlastimil Babka <vbabka@suse.cz>
Cc: Minchan Kim <minchan@kernel.org>
Acked-by: default avatarMel Gorman <mgorman@suse.de>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Michal Nazarewicz <mina86@mina86.com>
Cc: Naoya Horiguchi <n-horiguchi@ah.jp.nec.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent f8224aa5
...@@ -132,7 +132,7 @@ void reset_isolation_suitable(pg_data_t *pgdat) ...@@ -132,7 +132,7 @@ void reset_isolation_suitable(pg_data_t *pgdat)
*/ */
static void update_pageblock_skip(struct compact_control *cc, static void update_pageblock_skip(struct compact_control *cc,
struct page *page, unsigned long nr_isolated, struct page *page, unsigned long nr_isolated,
bool set_unsuitable, bool migrate_scanner) bool migrate_scanner)
{ {
struct zone *zone = cc->zone; struct zone *zone = cc->zone;
unsigned long pfn; unsigned long pfn;
...@@ -146,12 +146,7 @@ static void update_pageblock_skip(struct compact_control *cc, ...@@ -146,12 +146,7 @@ static void update_pageblock_skip(struct compact_control *cc,
if (nr_isolated) if (nr_isolated)
return; return;
/* set_pageblock_skip(page);
* Only skip pageblocks when all forms of compaction will be known to
* fail in the near future.
*/
if (set_unsuitable)
set_pageblock_skip(page);
pfn = page_to_pfn(page); pfn = page_to_pfn(page);
...@@ -180,7 +175,7 @@ static inline bool isolation_suitable(struct compact_control *cc, ...@@ -180,7 +175,7 @@ static inline bool isolation_suitable(struct compact_control *cc,
static void update_pageblock_skip(struct compact_control *cc, static void update_pageblock_skip(struct compact_control *cc,
struct page *page, unsigned long nr_isolated, struct page *page, unsigned long nr_isolated,
bool set_unsuitable, bool migrate_scanner) bool migrate_scanner)
{ {
} }
#endif /* CONFIG_COMPACTION */ #endif /* CONFIG_COMPACTION */
...@@ -348,8 +343,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, ...@@ -348,8 +343,7 @@ static unsigned long isolate_freepages_block(struct compact_control *cc,
/* Update the pageblock-skip if the whole pageblock was scanned */ /* Update the pageblock-skip if the whole pageblock was scanned */
if (blockpfn == end_pfn) if (blockpfn == end_pfn)
update_pageblock_skip(cc, valid_page, total_isolated, true, update_pageblock_skip(cc, valid_page, total_isolated, false);
false);
count_compact_events(COMPACTFREE_SCANNED, nr_scanned); count_compact_events(COMPACTFREE_SCANNED, nr_scanned);
if (total_isolated) if (total_isolated)
...@@ -420,22 +414,19 @@ isolate_freepages_range(struct compact_control *cc, ...@@ -420,22 +414,19 @@ isolate_freepages_range(struct compact_control *cc,
} }
/* Update the number of anon and file isolated pages in the zone */ /* Update the number of anon and file isolated pages in the zone */
static void acct_isolated(struct zone *zone, bool locked, struct compact_control *cc) static void acct_isolated(struct zone *zone, struct compact_control *cc)
{ {
struct page *page; struct page *page;
unsigned int count[2] = { 0, }; unsigned int count[2] = { 0, };
if (list_empty(&cc->migratepages))
return;
list_for_each_entry(page, &cc->migratepages, lru) list_for_each_entry(page, &cc->migratepages, lru)
count[!!page_is_file_cache(page)]++; count[!!page_is_file_cache(page)]++;
/* If locked we can use the interrupt unsafe versions */ mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
if (locked) { mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
__mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
__mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
} else {
mod_zone_page_state(zone, NR_ISOLATED_ANON, count[0]);
mod_zone_page_state(zone, NR_ISOLATED_FILE, count[1]);
}
} }
/* Similar to reclaim, but different enough that they don't share logic */ /* Similar to reclaim, but different enough that they don't share logic */
...@@ -454,40 +445,34 @@ static bool too_many_isolated(struct zone *zone) ...@@ -454,40 +445,34 @@ static bool too_many_isolated(struct zone *zone)
} }
/** /**
* isolate_migratepages_range() - isolate all migrate-able pages in range. * isolate_migratepages_block() - isolate all migrate-able pages within
* @zone: Zone pages are in. * a single pageblock
* @cc: Compaction control structure. * @cc: Compaction control structure.
* @low_pfn: The first PFN of the range. * @low_pfn: The first PFN to isolate
* @end_pfn: The one-past-the-last PFN of the range. * @end_pfn: The one-past-the-last PFN to isolate, within same pageblock
* @unevictable: true if it allows to isolate unevictable pages * @isolate_mode: Isolation mode to be used.
* *
* Isolate all pages that can be migrated from the range specified by * Isolate all pages that can be migrated from the range specified by
* [low_pfn, end_pfn). Returns zero if there is a fatal signal * [low_pfn, end_pfn). The range is expected to be within same pageblock.
* pending), otherwise PFN of the first page that was not scanned * Returns zero if there is a fatal signal pending, otherwise PFN of the
* (which may be both less, equal to or more then end_pfn). * first page that was not scanned (which may be both less, equal to or more
* than end_pfn).
* *
* Assumes that cc->migratepages is empty and cc->nr_migratepages is * The pages are isolated on cc->migratepages list (not required to be empty),
* zero. * and cc->nr_migratepages is updated accordingly. The cc->migrate_pfn field
* * is neither read nor updated.
* Apart from cc->migratepages and cc->nr_migratetypes this function
* does not modify any cc's fields, in particular it does not modify
* (or read for that matter) cc->migrate_pfn.
*/ */
unsigned long static unsigned long
isolate_migratepages_range(struct zone *zone, struct compact_control *cc, isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn,
unsigned long low_pfn, unsigned long end_pfn, bool unevictable) unsigned long end_pfn, isolate_mode_t isolate_mode)
{ {
unsigned long last_pageblock_nr = 0, pageblock_nr; struct zone *zone = cc->zone;
unsigned long nr_scanned = 0, nr_isolated = 0; unsigned long nr_scanned = 0, nr_isolated = 0;
struct list_head *migratelist = &cc->migratepages; struct list_head *migratelist = &cc->migratepages;
struct lruvec *lruvec; struct lruvec *lruvec;
unsigned long flags; unsigned long flags;
bool locked = false; bool locked = false;
struct page *page = NULL, *valid_page = NULL; struct page *page = NULL, *valid_page = NULL;
bool set_unsuitable = true;
const isolate_mode_t mode = (cc->mode == MIGRATE_ASYNC ?
ISOLATE_ASYNC_MIGRATE : 0) |
(unevictable ? ISOLATE_UNEVICTABLE : 0);
/* /*
* Ensure that there are not too many pages isolated from the LRU * Ensure that there are not too many pages isolated from the LRU
...@@ -518,19 +503,6 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, ...@@ -518,19 +503,6 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
} }
} }
/*
* migrate_pfn does not necessarily start aligned to a
* pageblock. Ensure that pfn_valid is called when moving
* into a new MAX_ORDER_NR_PAGES range in case of large
* memory holes within the zone
*/
if ((low_pfn & (MAX_ORDER_NR_PAGES - 1)) == 0) {
if (!pfn_valid(low_pfn)) {
low_pfn += MAX_ORDER_NR_PAGES - 1;
continue;
}
}
if (!pfn_valid_within(low_pfn)) if (!pfn_valid_within(low_pfn))
continue; continue;
nr_scanned++; nr_scanned++;
...@@ -548,28 +520,6 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, ...@@ -548,28 +520,6 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
if (!valid_page) if (!valid_page)
valid_page = page; valid_page = page;
/* If isolation recently failed, do not retry */
pageblock_nr = low_pfn >> pageblock_order;
if (last_pageblock_nr != pageblock_nr) {
int mt;
last_pageblock_nr = pageblock_nr;
if (!isolation_suitable(cc, page))
goto next_pageblock;
/*
* For async migration, also only scan in MOVABLE
* blocks. Async migration is optimistic to see if
* the minimum amount of work satisfies the allocation
*/
mt = get_pageblock_migratetype(page);
if (cc->mode == MIGRATE_ASYNC &&
!migrate_async_suitable(mt)) {
set_unsuitable = false;
goto next_pageblock;
}
}
/* /*
* Skip if free. page_order cannot be used without zone->lock * Skip if free. page_order cannot be used without zone->lock
* as nothing prevents parallel allocations or buddy merging. * as nothing prevents parallel allocations or buddy merging.
...@@ -604,8 +554,11 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, ...@@ -604,8 +554,11 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
*/ */
if (PageTransHuge(page)) { if (PageTransHuge(page)) {
if (!locked) if (!locked)
goto next_pageblock; low_pfn = ALIGN(low_pfn + 1,
low_pfn += (1 << compound_order(page)) - 1; pageblock_nr_pages) - 1;
else
low_pfn += (1 << compound_order(page)) - 1;
continue; continue;
} }
...@@ -635,7 +588,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, ...@@ -635,7 +588,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
lruvec = mem_cgroup_page_lruvec(page, zone); lruvec = mem_cgroup_page_lruvec(page, zone);
/* Try isolate the page */ /* Try isolate the page */
if (__isolate_lru_page(page, mode) != 0) if (__isolate_lru_page(page, isolate_mode) != 0)
continue; continue;
VM_BUG_ON_PAGE(PageTransCompound(page), page); VM_BUG_ON_PAGE(PageTransCompound(page), page);
...@@ -654,15 +607,8 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, ...@@ -654,15 +607,8 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
++low_pfn; ++low_pfn;
break; break;
} }
continue;
next_pageblock:
low_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages) - 1;
} }
acct_isolated(zone, locked, cc);
if (locked) if (locked)
spin_unlock_irqrestore(&zone->lru_lock, flags); spin_unlock_irqrestore(&zone->lru_lock, flags);
...@@ -671,8 +617,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, ...@@ -671,8 +617,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
* if the whole pageblock was scanned without isolating any page. * if the whole pageblock was scanned without isolating any page.
*/ */
if (low_pfn == end_pfn) if (low_pfn == end_pfn)
update_pageblock_skip(cc, valid_page, nr_isolated, update_pageblock_skip(cc, valid_page, nr_isolated, true);
set_unsuitable, true);
trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated); trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);
...@@ -683,15 +628,63 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, ...@@ -683,15 +628,63 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc,
return low_pfn; return low_pfn;
} }
/**
* isolate_migratepages_range() - isolate migrate-able pages in a PFN range
* @cc: Compaction control structure.
* @start_pfn: The first PFN to start isolating.
* @end_pfn: The one-past-last PFN.
*
* Returns zero if isolation fails fatally due to e.g. pending signal.
* Otherwise, function returns one-past-the-last PFN of isolated page
* (which may be greater than end_pfn if end fell in a middle of a THP page).
*/
unsigned long
isolate_migratepages_range(struct compact_control *cc, unsigned long start_pfn,
unsigned long end_pfn)
{
unsigned long pfn, block_end_pfn;
/* Scan block by block. First and last block may be incomplete */
pfn = start_pfn;
block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages);
for (; pfn < end_pfn; pfn = block_end_pfn,
block_end_pfn += pageblock_nr_pages) {
block_end_pfn = min(block_end_pfn, end_pfn);
/* Skip whole pageblock in case of a memory hole */
if (!pfn_valid(pfn))
continue;
pfn = isolate_migratepages_block(cc, pfn, block_end_pfn,
ISOLATE_UNEVICTABLE);
/*
* In case of fatal failure, release everything that might
* have been isolated in the previous iteration, and signal
* the failure back to caller.
*/
if (!pfn) {
putback_movable_pages(&cc->migratepages);
cc->nr_migratepages = 0;
break;
}
}
acct_isolated(cc->zone, cc);
return pfn;
}
#endif /* CONFIG_COMPACTION || CONFIG_CMA */ #endif /* CONFIG_COMPACTION || CONFIG_CMA */
#ifdef CONFIG_COMPACTION #ifdef CONFIG_COMPACTION
/* /*
* Based on information in the current compact_control, find blocks * Based on information in the current compact_control, find blocks
* suitable for isolating free pages from and then isolate them. * suitable for isolating free pages from and then isolate them.
*/ */
static void isolate_freepages(struct zone *zone, static void isolate_freepages(struct compact_control *cc)
struct compact_control *cc)
{ {
struct zone *zone = cc->zone;
struct page *page; struct page *page;
unsigned long block_start_pfn; /* start of current pageblock */ unsigned long block_start_pfn; /* start of current pageblock */
unsigned long block_end_pfn; /* end of current pageblock */ unsigned long block_end_pfn; /* end of current pageblock */
...@@ -809,7 +802,7 @@ static struct page *compaction_alloc(struct page *migratepage, ...@@ -809,7 +802,7 @@ static struct page *compaction_alloc(struct page *migratepage,
*/ */
if (list_empty(&cc->freepages)) { if (list_empty(&cc->freepages)) {
if (!cc->contended) if (!cc->contended)
isolate_freepages(cc->zone, cc); isolate_freepages(cc);
if (list_empty(&cc->freepages)) if (list_empty(&cc->freepages))
return NULL; return NULL;
...@@ -843,34 +836,82 @@ typedef enum { ...@@ -843,34 +836,82 @@ typedef enum {
} isolate_migrate_t; } isolate_migrate_t;
/* /*
* Isolate all pages that can be migrated from the block pointed to by * Isolate all pages that can be migrated from the first suitable block,
* the migrate scanner within compact_control. * starting at the block pointed to by the migrate scanner pfn within
* compact_control.
*/ */
static isolate_migrate_t isolate_migratepages(struct zone *zone, static isolate_migrate_t isolate_migratepages(struct zone *zone,
struct compact_control *cc) struct compact_control *cc)
{ {
unsigned long low_pfn, end_pfn; unsigned long low_pfn, end_pfn;
struct page *page;
const isolate_mode_t isolate_mode =
(cc->mode == MIGRATE_ASYNC ? ISOLATE_ASYNC_MIGRATE : 0);
/* Do not scan outside zone boundaries */ /*
low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn); * Start at where we last stopped, or beginning of the zone as
* initialized by compact_zone()
*/
low_pfn = cc->migrate_pfn;
/* Only scan within a pageblock boundary */ /* Only scan within a pageblock boundary */
end_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages); end_pfn = ALIGN(low_pfn + 1, pageblock_nr_pages);
/* Do not cross the free scanner or scan within a memory hole */ /*
if (end_pfn > cc->free_pfn || !pfn_valid(low_pfn)) { * Iterate over whole pageblocks until we find the first suitable.
cc->migrate_pfn = end_pfn; * Do not cross the free scanner.
return ISOLATE_NONE; */
} for (; end_pfn <= cc->free_pfn;
low_pfn = end_pfn, end_pfn += pageblock_nr_pages) {
/* Perform the isolation */ /*
low_pfn = isolate_migratepages_range(zone, cc, low_pfn, end_pfn, false); * This can potentially iterate a massively long zone with
if (!low_pfn || cc->contended) * many pageblocks unsuitable, so periodically check if we
return ISOLATE_ABORT; * need to schedule, or even abort async compaction.
*/
if (!(low_pfn % (SWAP_CLUSTER_MAX * pageblock_nr_pages))
&& compact_should_abort(cc))
break;
/* Skip whole pageblock in case of a memory hole */
if (!pfn_valid(low_pfn))
continue;
page = pfn_to_page(low_pfn);
/* If isolation recently failed, do not retry */
if (!isolation_suitable(cc, page))
continue;
/*
* For async compaction, also only scan in MOVABLE blocks.
* Async compaction is optimistic to see if the minimum amount
* of work satisfies the allocation.
*/
if (cc->mode == MIGRATE_ASYNC &&
!migrate_async_suitable(get_pageblock_migratetype(page)))
continue;
/* Perform the isolation */
low_pfn = isolate_migratepages_block(cc, low_pfn, end_pfn,
isolate_mode);
if (!low_pfn || cc->contended)
return ISOLATE_ABORT;
/*
* Either we isolated something and proceed with migration. Or
* we failed and compact_zone should decide if we should
* continue or not.
*/
break;
}
acct_isolated(zone, cc);
/* Record where migration scanner will be restarted */
cc->migrate_pfn = low_pfn; cc->migrate_pfn = low_pfn;
return ISOLATE_SUCCESS; return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE;
} }
static int compact_finished(struct zone *zone, static int compact_finished(struct zone *zone,
...@@ -1043,9 +1084,6 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) ...@@ -1043,9 +1084,6 @@ static int compact_zone(struct zone *zone, struct compact_control *cc)
; ;
} }
if (!cc->nr_migratepages)
continue;
err = migrate_pages(&cc->migratepages, compaction_alloc, err = migrate_pages(&cc->migratepages, compaction_alloc,
compaction_free, (unsigned long)cc, cc->mode, compaction_free, (unsigned long)cc, cc->mode,
MR_COMPACTION); MR_COMPACTION);
......
...@@ -154,8 +154,8 @@ unsigned long ...@@ -154,8 +154,8 @@ unsigned long
isolate_freepages_range(struct compact_control *cc, isolate_freepages_range(struct compact_control *cc,
unsigned long start_pfn, unsigned long end_pfn); unsigned long start_pfn, unsigned long end_pfn);
unsigned long unsigned long
isolate_migratepages_range(struct zone *zone, struct compact_control *cc, isolate_migratepages_range(struct compact_control *cc,
unsigned long low_pfn, unsigned long end_pfn, bool unevictable); unsigned long low_pfn, unsigned long end_pfn);
#endif #endif
......
...@@ -6288,8 +6288,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc, ...@@ -6288,8 +6288,7 @@ static int __alloc_contig_migrate_range(struct compact_control *cc,
if (list_empty(&cc->migratepages)) { if (list_empty(&cc->migratepages)) {
cc->nr_migratepages = 0; cc->nr_migratepages = 0;
pfn = isolate_migratepages_range(cc->zone, cc, pfn = isolate_migratepages_range(cc, pfn, end);
pfn, end, true);
if (!pfn) { if (!pfn) {
ret = -EINTR; ret = -EINTR;
break; break;
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment