From: Michal Nazarewicz mina86@mina86.com

This commit introduces isolate_migratepages_range() function which extracts functionality from isolate_migratepages() so that it can be used on arbitrary PFN ranges.

isolate_migratepages() function is implemented as a simple wrapper around isolate_migratepages_range().

Signed-off-by: Michal Nazarewicz mina86@mina86.com Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com Acked-by: Mel Gorman mel@csn.ul.ie Tested-by: Rob Clark rob.clark@linaro.org Tested-by: Ohad Ben-Cohen ohad@wizery.com Tested-by: Benjamin Gaignard benjamin.gaignard@linaro.org --- mm/compaction.c | 75 +++++++++++++++++++++++++++++++++++++++--------------- 1 files changed, 54 insertions(+), 21 deletions(-)

diff --git a/mm/compaction.c b/mm/compaction.c index 71a58f6..62902b6 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -250,31 +250,34 @@ typedef enum { ISOLATE_SUCCESS, /* Pages isolated, migrate */ } isolate_migrate_t;

-/* - * Isolate all pages that can be migrated from the block pointed to by - * the migrate scanner within compact_control. +/** + * isolate_migratepages_range() - isolate all migrate-able pages in range. + * @zone: Zone pages are in. + * @cc: Compaction control structure. + * @low_pfn: The first PFN of the range. + * @end_pfn: The one-past-the-last PFN of the range. + * + * Isolate all pages that can be migrated from the range specified by + * [low_pfn, end_pfn). Returns zero if there is a fatal signal + * pending), otherwise PFN of the first page that was not scanned + * (which may be both less, equal to or more then end_pfn). + * + * Assumes that cc->migratepages is empty and cc->nr_migratepages is + * zero. + * + * 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. */ -static isolate_migrate_t isolate_migratepages(struct zone *zone, - struct compact_control *cc) +static unsigned long +isolate_migratepages_range(struct zone *zone, struct compact_control *cc, + unsigned long low_pfn, unsigned long end_pfn) { - unsigned long low_pfn, end_pfn; unsigned long last_pageblock_nr = 0, pageblock_nr; unsigned long nr_scanned = 0, nr_isolated = 0; struct list_head *migratelist = &cc->migratepages; isolate_mode_t mode = ISOLATE_ACTIVE|ISOLATE_INACTIVE;

- /* Do not scan outside zone boundaries */ - low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn); - - /* Only scan within a pageblock boundary */ - end_pfn = ALIGN(low_pfn + pageblock_nr_pages, 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)) { - cc->migrate_pfn = end_pfn; - return ISOLATE_NONE; - } - /* * Ensure that there are not too many pages isolated from the LRU * list by either parallel reclaimers or compaction. If there are, @@ -283,12 +286,12 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, while (unlikely(too_many_isolated(zone))) { /* async migration should just abort */ if (!cc->sync) - return ISOLATE_ABORT; + return 0;

congestion_wait(BLK_RW_ASYNC, HZ/10);

if (fatal_signal_pending(current)) - return ISOLATE_ABORT; + return 0; }

/* Time to isolate some pages for migration */ @@ -374,10 +377,40 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, acct_isolated(zone, cc);

spin_unlock_irq(&zone->lru_lock); - cc->migrate_pfn = low_pfn;

trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated);

+ return low_pfn; +} + +/* + * Isolate all pages that can be migrated from the block pointed to by + * the migrate scanner within compact_control. + */ +static isolate_migrate_t isolate_migratepages(struct zone *zone, + struct compact_control *cc) +{ + unsigned long low_pfn, end_pfn; + + /* Do not scan outside zone boundaries */ + low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn); + + /* Only scan within a pageblock boundary */ + end_pfn = ALIGN(low_pfn + pageblock_nr_pages, 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)) { + cc->migrate_pfn = end_pfn; + return ISOLATE_NONE; + } + + /* Perform the isolation */ + low_pfn = isolate_migratepages_range(zone, cc, low_pfn, end_pfn); + if (!low_pfn) + return ISOLATE_ABORT; + + cc->migrate_pfn = low_pfn; + return ISOLATE_SUCCESS; }

From: Michal Nazarewicz mina86@mina86.com

This commit exports some of the functions from compaction.c file outside of it adding their declaration into internal.h header file so that other mm related code can use them.

This forced compaction.c to always be compiled (as opposed to being compiled only if CONFIG_COMPACTION is defined) but as to avoid introducing code that user did not ask for, part of the compaction.c is now wrapped in on #ifdef.

Signed-off-by: Michal Nazarewicz mina86@mina86.com Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com Acked-by: Mel Gorman mel@csn.ul.ie Tested-by: Rob Clark rob.clark@linaro.org Tested-by: Ohad Ben-Cohen ohad@wizery.com Tested-by: Benjamin Gaignard benjamin.gaignard@linaro.org --- mm/Makefile | 3 +- mm/compaction.c | 328 ++++++++++++++++++++++++++----------------------------- mm/internal.h | 33 ++++++ 3 files changed, 191 insertions(+), 173 deletions(-)

diff --git a/mm/Makefile b/mm/Makefile index 50ec00e..8aada89 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -13,7 +13,7 @@ obj-y := filemap.o mempool.o oom_kill.o fadvise.o \ readahead.o swap.o truncate.o vmscan.o shmem.o \ prio_tree.o util.o mmzone.o vmstat.o backing-dev.o \ page_isolation.o mm_init.o mmu_context.o percpu.o \ - $(mmu-y) + compaction.o $(mmu-y) obj-y += init-mm.o

ifdef CONFIG_NO_BOOTMEM @@ -32,7 +32,6 @@ obj-$(CONFIG_NUMA) += mempolicy.o obj-$(CONFIG_SPARSEMEM) += sparse.o obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o obj-$(CONFIG_SLOB) += slob.o -obj-$(CONFIG_COMPACTION) += compaction.o obj-$(CONFIG_MMU_NOTIFIER) += mmu_notifier.o obj-$(CONFIG_KSM) += ksm.o obj-$(CONFIG_PAGE_POISONING) += debug-pagealloc.o diff --git a/mm/compaction.c b/mm/compaction.c index 9fef891..d5174c4 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -16,30 +16,11 @@ #include <linux/sysfs.h> #include "internal.h"

+#if defined CONFIG_COMPACTION || defined CONFIG_CMA + #define CREATE_TRACE_POINTS #include <trace/events/compaction.h>

-/* - * compact_control is used to track pages being migrated and the free pages - * they are being migrated to during memory compaction. The free_pfn starts - * at the end of a zone and migrate_pfn begins at the start. Movable pages - * are moved to the end of a zone during a compaction run and the run - * completes when free_pfn <= migrate_pfn - */ -struct compact_control { - struct list_head freepages; /* List of free pages to migrate to */ - struct list_head migratepages; /* List of pages being migrated */ - unsigned long nr_freepages; /* Number of isolated free pages */ - unsigned long nr_migratepages; /* Number of pages to migrate */ - unsigned long free_pfn; /* isolate_freepages search base */ - unsigned long migrate_pfn; /* isolate_migratepages search base */ - bool sync; /* Synchronous migration */ - - unsigned int order; /* order a direct compactor needs */ - int migratetype; /* MOVABLE, RECLAIMABLE etc */ - struct zone *zone; -}; - static unsigned long release_freepages(struct list_head *freelist) { struct page *page, *next; @@ -54,6 +35,16 @@ static unsigned long release_freepages(struct list_head *freelist) return count; }

+static void map_pages(struct list_head *list) +{ + struct page *page; + + list_for_each_entry(page, list, lru) { + arch_alloc_page(page, 0); + kernel_map_pages(page, 1, 1); + } +} + /* * Isolate free pages onto a private freelist. Caller must hold zone->lock. * If @strict is true, will abort returning 0 on any invalid PFNs or non-free @@ -122,7 +113,7 @@ static unsigned long isolate_freepages_block(unsigned long blockpfn, * (which may be greater then end_pfn if end fell in a middle of * a free page). */ -static unsigned long +unsigned long isolate_freepages_range(unsigned long start_pfn, unsigned long end_pfn) { unsigned long isolated, pfn, block_end_pfn, flags; @@ -176,127 +167,6 @@ isolate_freepages_range(unsigned long start_pfn, unsigned long end_pfn) return pfn; }

-/* Returns true if the page is within a block suitable for migration to */ -static bool suitable_migration_target(struct page *page) -{ - - int migratetype = get_pageblock_migratetype(page); - - /* Don't interfere with memory hot-remove or the min_free_kbytes blocks */ - if (migratetype == MIGRATE_ISOLATE || migratetype == MIGRATE_RESERVE) - return false; - - /* If the page is a large free page, then allow migration */ - if (PageBuddy(page) && page_order(page) >= pageblock_order) - return true; - - /* If the block is MIGRATE_MOVABLE, allow migration */ - if (migratetype == MIGRATE_MOVABLE) - return true; - - /* Otherwise skip the block */ - return false; -} - -static void map_pages(struct list_head *list) -{ - struct page *page; - - list_for_each_entry(page, list, lru) { - arch_alloc_page(page, 0); - kernel_map_pages(page, 1, 1); - } -} - -/* - * Based on information in the current compact_control, find blocks - * suitable for isolating free pages from and then isolate them. - */ -static void isolate_freepages(struct zone *zone, - struct compact_control *cc) -{ - struct page *page; - unsigned long high_pfn, low_pfn, pfn, zone_end_pfn, end_pfn; - unsigned long flags; - int nr_freepages = cc->nr_freepages; - struct list_head *freelist = &cc->freepages; - - /* - * Initialise the free scanner. The starting point is where we last - * scanned from (or the end of the zone if starting). The low point - * is the end of the pageblock the migration scanner is using. - */ - pfn = cc->free_pfn; - low_pfn = cc->migrate_pfn + pageblock_nr_pages; - - /* - * Take care that if the migration scanner is at the end of the zone - * that the free scanner does not accidentally move to the next zone - * in the next isolation cycle. - */ - high_pfn = min(low_pfn, pfn); - - zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages; - - /* - * Isolate free pages until enough are available to migrate the - * pages on cc->migratepages. We stop searching if the migrate - * and free page scanners meet or enough free pages are isolated. - */ - for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages; - pfn -= pageblock_nr_pages) { - unsigned long isolated; - - if (!pfn_valid(pfn)) - continue; - - /* - * Check for overlapping nodes/zones. It's possible on some - * configurations to have a setup like - * node0 node1 node0 - * i.e. it's possible that all pages within a zones range of - * pages do not belong to a single zone. - */ - page = pfn_to_page(pfn); - if (page_zone(page) != zone) - continue; - - /* Check the block is suitable for migration */ - if (!suitable_migration_target(page)) - continue; - - /* - * Found a block suitable for isolating free pages from. Now - * we disabled interrupts, double check things are ok and - * isolate the pages. This is to minimise the time IRQs - * are disabled - */ - isolated = 0; - spin_lock_irqsave(&zone->lock, flags); - if (suitable_migration_target(page)) { - end_pfn = min(pfn + pageblock_nr_pages, zone_end_pfn); - isolated = isolate_freepages_block(pfn, end_pfn, - freelist, false); - nr_freepages += isolated; - } - spin_unlock_irqrestore(&zone->lock, flags); - - /* - * Record the highest PFN we isolated pages from. When next - * looking for free pages, the search will restart here as - * page migration may have returned some pages to the allocator - */ - if (isolated) - high_pfn = max(high_pfn, pfn); - } - - /* split_free_page does not map the pages */ - map_pages(freelist); - - cc->free_pfn = high_pfn; - cc->nr_freepages = nr_freepages; -} - /* Update the number of anon and file isolated pages in the zone */ static void acct_isolated(struct zone *zone, struct compact_control *cc) { @@ -325,13 +195,6 @@ static bool too_many_isolated(struct zone *zone) return isolated > (inactive + active) / 2; }

-/* possible outcome of isolate_migratepages */ -typedef enum { - ISOLATE_ABORT, /* Abort compaction now */ - ISOLATE_NONE, /* No pages isolated, continue scanning */ - ISOLATE_SUCCESS, /* Pages isolated, migrate */ -} isolate_migrate_t; - /** * isolate_migratepages_range() - isolate all migrate-able pages in range. * @zone: Zone pages are in. @@ -351,7 +214,7 @@ typedef enum { * does not modify any cc's fields, in particular it does not modify * (or read for that matter) cc->migrate_pfn. */ -static unsigned long +unsigned long isolate_migratepages_range(struct zone *zone, struct compact_control *cc, unsigned long low_pfn, unsigned long end_pfn) { @@ -465,35 +328,118 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, return low_pfn; }

+#endif /* CONFIG_COMPACTION || CONFIG_CMA */ +#ifdef CONFIG_COMPACTION + +/* Returns true if the page is within a block suitable for migration to */ +static bool suitable_migration_target(struct page *page) +{ + + int migratetype = get_pageblock_migratetype(page); + + /* Don't interfere with memory hot-remove or the min_free_kbytes blocks */ + if (migratetype == MIGRATE_ISOLATE || migratetype == MIGRATE_RESERVE) + return false; + + /* If the page is a large free page, then allow migration */ + if (PageBuddy(page) && page_order(page) >= pageblock_order) + return true; + + /* If the block is MIGRATE_MOVABLE, allow migration */ + if (migratetype == MIGRATE_MOVABLE) + return true; + + /* Otherwise skip the block */ + return false; +} + /* - * Isolate all pages that can be migrated from the block pointed to by - * the migrate scanner within compact_control. + * Based on information in the current compact_control, find blocks + * suitable for isolating free pages from and then isolate them. */ -static isolate_migrate_t isolate_migratepages(struct zone *zone, - struct compact_control *cc) +static void isolate_freepages(struct zone *zone, + struct compact_control *cc) { - unsigned long low_pfn, end_pfn; + struct page *page; + unsigned long high_pfn, low_pfn, pfn, zone_end_pfn, end_pfn; + unsigned long flags; + int nr_freepages = cc->nr_freepages; + struct list_head *freelist = &cc->freepages;

- /* Do not scan outside zone boundaries */ - low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn); + /* + * Initialise the free scanner. The starting point is where we last + * scanned from (or the end of the zone if starting). The low point + * is the end of the pageblock the migration scanner is using. + */ + pfn = cc->free_pfn; + low_pfn = cc->migrate_pfn + pageblock_nr_pages;

- /* Only scan within a pageblock boundary */ - end_pfn = ALIGN(low_pfn + pageblock_nr_pages, pageblock_nr_pages); + /* + * Take care that if the migration scanner is at the end of the zone + * that the free scanner does not accidentally move to the next zone + * in the next isolation cycle. + */ + high_pfn = min(low_pfn, pfn);

- /* Do not cross the free scanner or scan within a memory hole */ - if (end_pfn > cc->free_pfn || !pfn_valid(low_pfn)) { - cc->migrate_pfn = end_pfn; - return ISOLATE_NONE; - } + zone_end_pfn = zone->zone_start_pfn + zone->spanned_pages;

- /* Perform the isolation */ - low_pfn = isolate_migratepages_range(zone, cc, low_pfn, end_pfn); - if (!low_pfn) - return ISOLATE_ABORT; + /* + * Isolate free pages until enough are available to migrate the + * pages on cc->migratepages. We stop searching if the migrate + * and free page scanners meet or enough free pages are isolated. + */ + for (; pfn > low_pfn && cc->nr_migratepages > nr_freepages; + pfn -= pageblock_nr_pages) { + unsigned long isolated;

- cc->migrate_pfn = low_pfn; + if (!pfn_valid(pfn)) + continue;

- return ISOLATE_SUCCESS; + /* + * Check for overlapping nodes/zones. It's possible on some + * configurations to have a setup like + * node0 node1 node0 + * i.e. it's possible that all pages within a zones range of + * pages do not belong to a single zone. + */ + page = pfn_to_page(pfn); + if (page_zone(page) != zone) + continue; + + /* Check the block is suitable for migration */ + if (!suitable_migration_target(page)) + continue; + + /* + * Found a block suitable for isolating free pages from. Now + * we disabled interrupts, double check things are ok and + * isolate the pages. This is to minimise the time IRQs + * are disabled + */ + isolated = 0; + spin_lock_irqsave(&zone->lock, flags); + if (suitable_migration_target(page)) { + end_pfn = min(pfn + pageblock_nr_pages, zone_end_pfn); + isolated = isolate_freepages_block(pfn, end_pfn, + freelist, false); + nr_freepages += isolated; + } + spin_unlock_irqrestore(&zone->lock, flags); + + /* + * Record the highest PFN we isolated pages from. When next + * looking for free pages, the search will restart here as + * page migration may have returned some pages to the allocator + */ + if (isolated) + high_pfn = max(high_pfn, pfn); + } + + /* split_free_page does not map the pages */ + map_pages(freelist); + + cc->free_pfn = high_pfn; + cc->nr_freepages = nr_freepages; }

/* @@ -542,6 +488,44 @@ static void update_nr_listpages(struct compact_control *cc) cc->nr_freepages = nr_freepages; }

+/* possible outcome of isolate_migratepages */ +typedef enum { + ISOLATE_ABORT, /* Abort compaction now */ + ISOLATE_NONE, /* No pages isolated, continue scanning */ + ISOLATE_SUCCESS, /* Pages isolated, migrate */ +} isolate_migrate_t; + +/* + * Isolate all pages that can be migrated from the block pointed to by + * the migrate scanner within compact_control. + */ +static isolate_migrate_t isolate_migratepages(struct zone *zone, + struct compact_control *cc) +{ + unsigned long low_pfn, end_pfn; + + /* Do not scan outside zone boundaries */ + low_pfn = max(cc->migrate_pfn, zone->zone_start_pfn); + + /* Only scan within a pageblock boundary */ + end_pfn = ALIGN(low_pfn + pageblock_nr_pages, 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)) { + cc->migrate_pfn = end_pfn; + return ISOLATE_NONE; + } + + /* Perform the isolation */ + low_pfn = isolate_migratepages_range(zone, cc, low_pfn, end_pfn); + if (!low_pfn) + return ISOLATE_ABORT; + + cc->migrate_pfn = low_pfn; + + return ISOLATE_SUCCESS; +} + static int compact_finished(struct zone *zone, struct compact_control *cc) { @@ -859,3 +843,5 @@ void compaction_unregister_node(struct node *node) return device_remove_file(&node->dev, &dev_attr_compact); } #endif /* CONFIG_SYSFS && CONFIG_NUMA */ + +#endif /* CONFIG_COMPACTION */ diff --git a/mm/internal.h b/mm/internal.h index 2189af4..55e7eed 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -100,6 +100,39 @@ extern void prep_compound_page(struct page *page, unsigned long order); extern bool is_free_buddy_page(struct page *page); #endif

+#if defined CONFIG_COMPACTION || defined CONFIG_CMA + +/* + * in mm/compaction.c + */ +/* + * compact_control is used to track pages being migrated and the free pages + * they are being migrated to during memory compaction. The free_pfn starts + * at the end of a zone and migrate_pfn begins at the start. Movable pages + * are moved to the end of a zone during a compaction run and the run + * completes when free_pfn <= migrate_pfn + */ +struct compact_control { + struct list_head freepages; /* List of free pages to migrate to */ + struct list_head migratepages; /* List of pages being migrated */ + unsigned long nr_freepages; /* Number of isolated free pages */ + unsigned long nr_migratepages; /* Number of pages to migrate */ + unsigned long free_pfn; /* isolate_freepages search base */ + unsigned long migrate_pfn; /* isolate_migratepages search base */ + bool sync; /* Synchronous migration */ + + unsigned int order; /* order a direct compactor needs */ + int migratetype; /* MOVABLE, RECLAIMABLE etc */ + struct zone *zone; +}; + +unsigned long +isolate_freepages_range(unsigned long start_pfn, unsigned long end_pfn); +unsigned long +isolate_migratepages_range(struct zone *zone, struct compact_control *cc, + unsigned long low_pfn, unsigned long end_pfn); + +#endif

/* * function for dealing with page's order in buddy system.

From: Michal Nazarewicz mina86@mina86.com

This commit adds the alloc_contig_range() function which tries to allocate given range of pages. It tries to migrate all already allocated pages that fall in the range thus freeing them. Once all pages in the range are freed they are removed from the buddy system thus allocated for the caller to use.

Signed-off-by: Michal Nazarewicz mina86@mina86.com Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com Acked-by: Mel Gorman mel@csn.ul.ie Tested-by: Rob Clark rob.clark@linaro.org Tested-by: Ohad Ben-Cohen ohad@wizery.com Tested-by: Benjamin Gaignard benjamin.gaignard@linaro.org --- include/linux/gfp.h | 8 ++ mm/page_alloc.c | 185 +++++++++++++++++++++++++++++++++++++++++++++++++++ 2 files changed, 193 insertions(+), 0 deletions(-)

diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 581e74b..052a5b6 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -391,4 +391,12 @@ static inline bool pm_suspended_storage(void) } #endif /* CONFIG_PM_SLEEP */

+#ifdef CONFIG_CMA + +/* The below functions must be run on a range from a single zone. */ +extern int alloc_contig_range(unsigned long start, unsigned long end); +extern void free_contig_range(unsigned long pfn, unsigned nr_pages); + +#endif + #endif /* __LINUX_GFP_H */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7fe7697..9006e69 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -57,6 +57,7 @@ #include <linux/ftrace_event.h> #include <linux/memcontrol.h> #include <linux/prefetch.h> +#include <linux/migrate.h> #include <linux/page-debug-flags.h>

#include <asm/tlbflush.h> @@ -5505,6 +5506,190 @@ out: spin_unlock_irqrestore(&zone->lock, flags); }

+#ifdef CONFIG_CMA + +static unsigned long pfn_align_to_maxpage_down(unsigned long pfn) +{ + return pfn & ~(MAX_ORDER_NR_PAGES - 1); +} + +static unsigned long pfn_align_to_maxpage_up(unsigned long pfn) +{ + return ALIGN(pfn, MAX_ORDER_NR_PAGES); +} + +static struct page * +__alloc_contig_migrate_alloc(struct page *page, unsigned long private, + int **resultp) +{ + return alloc_page(GFP_HIGHUSER_MOVABLE); +} + +/* [start, end) must belong to a single zone. */ +static int __alloc_contig_migrate_range(unsigned long start, unsigned long end) +{ + /* This function is based on compact_zone() from compaction.c. */ + + unsigned long pfn = start; + unsigned int tries = 0; + int ret = 0; + + struct compact_control cc = { + .nr_migratepages = 0, + .order = -1, + .zone = page_zone(pfn_to_page(start)), + .sync = true, + }; + INIT_LIST_HEAD(&cc.migratepages); + + migrate_prep_local(); + + while (pfn < end || !list_empty(&cc.migratepages)) { + if (fatal_signal_pending(current)) { + ret = -EINTR; + break; + } + + if (list_empty(&cc.migratepages)) { + cc.nr_migratepages = 0; + pfn = isolate_migratepages_range(cc.zone, &cc, + pfn, end); + if (!pfn) { + ret = -EINTR; + break; + } + tries = 0; + } else if (++tries == 5) { + ret = ret < 0 ? ret : -EBUSY; + break; + } + + ret = migrate_pages(&cc.migratepages, + __alloc_contig_migrate_alloc, + 0, false, true); + } + + putback_lru_pages(&cc.migratepages); + return ret > 0 ? 0 : ret; +} + +/** + * alloc_contig_range() -- tries to allocate given range of pages + * @start: start PFN to allocate + * @end: one-past-the-last PFN to allocate + * + * The PFN range does not have to be pageblock or MAX_ORDER_NR_PAGES + * aligned, however it's the caller's responsibility to guarantee that + * we are the only thread that changes migrate type of pageblocks the + * pages fall in. + * + * The PFN range must belong to a single zone. + * + * Returns zero on success or negative error code. On success all + * pages which PFN is in [start, end) are allocated for the caller and + * need to be freed with free_contig_range(). + */ +int alloc_contig_range(unsigned long start, unsigned long end) +{ + struct zone *zone = page_zone(pfn_to_page(start)); + unsigned long outer_start, outer_end; + int ret = 0, order; + + /* + * What we do here is we mark all pageblocks in range as + * MIGRATE_ISOLATE. Because of the way page allocator work, we + * align the range to MAX_ORDER pages so that page allocator + * won't try to merge buddies from different pageblocks and + * change MIGRATE_ISOLATE to some other migration type. + * + * Once the pageblocks are marked as MIGRATE_ISOLATE, we + * migrate the pages from an unaligned range (ie. pages that + * we are interested in). This will put all the pages in + * range back to page allocator as MIGRATE_ISOLATE. + * + * When this is done, we take the pages in range from page + * allocator removing them from the buddy system. This way + * page allocator will never consider using them. + * + * This lets us mark the pageblocks back as + * MIGRATE_CMA/MIGRATE_MOVABLE so that free pages in the + * MAX_ORDER aligned range but not in the unaligned, original + * range are put back to page allocator so that buddy can use + * them. + */ + + ret = start_isolate_page_range(pfn_align_to_maxpage_down(start), + pfn_align_to_maxpage_up(end)); + if (ret) + goto done; + + ret = __alloc_contig_migrate_range(start, end); + if (ret) + goto done; + + /* + * Pages from [start, end) are within a MAX_ORDER_NR_PAGES + * aligned blocks that are marked as MIGRATE_ISOLATE. What's + * more, all pages in [start, end) are free in page allocator. + * What we are going to do is to allocate all pages from + * [start, end) (that is remove them from page allocater). + * + * The only problem is that pages at the beginning and at the + * end of interesting range may be not aligned with pages that + * page allocator holds, ie. they can be part of higher order + * pages. Because of this, we reserve the bigger range and + * once this is done free the pages we are not interested in. + * + * We don't have to hold zone->lock here because the pages are + * isolated thus they won't get removed from buddy. + */ + + lru_add_drain_all(); + drain_all_pages(); + + order = 0; + outer_start = start; + while (!PageBuddy(pfn_to_page(outer_start))) { + if (++order >= MAX_ORDER) { + ret = -EBUSY; + goto done; + } + outer_start &= ~0UL << order; + } + + /* Make sure the range is really isolated. */ + if (test_pages_isolated(outer_start, end)) { + pr_warn("alloc_contig_range test_pages_isolated(%lx, %lx) failed\n", + outer_start, end); + ret = -EBUSY; + goto done; + } + + outer_end = isolate_freepages_range(outer_start, end); + if (!outer_end) { + ret = -EBUSY; + goto done; + } + + /* Free head and tail (if any) */ + if (start != outer_start) + free_contig_range(outer_start, start - outer_start); + if (end != outer_end) + free_contig_range(end, outer_end - end); + +done: + undo_isolate_page_range(pfn_align_to_maxpage_down(start), + pfn_align_to_maxpage_up(end)); + return ret; +} + +void free_contig_range(unsigned long pfn, unsigned nr_pages) +{ + for (; nr_pages--; ++pfn) + __free_page(pfn_to_page(pfn)); +} +#endif + #ifdef CONFIG_MEMORY_HOTREMOVE /* * All pages in the range must be isolated before calling this.

From: Michal Nazarewicz mina86@mina86.com

The MIGRATE_CMA migration type has two main characteristics: (i) only movable pages can be allocated from MIGRATE_CMA pageblocks and (ii) page allocator will never change migration type of MIGRATE_CMA pageblocks.

This guarantees (to some degree) that page in a MIGRATE_CMA page block can always be migrated somewhere else (unless there's no memory left in the system).

It is designed to be used for allocating big chunks (eg. 10MiB) of physically contiguous memory. Once driver requests contiguous memory, pages from MIGRATE_CMA pageblocks may be migrated away to create a contiguous block.

To minimise number of migrations, MIGRATE_CMA migration type is the last type tried when page allocator falls back to other migration types then requested.

Signed-off-by: Michal Nazarewicz mina86@mina86.com Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com Signed-off-by: Kyungmin Park kyungmin.park@samsung.com Tested-by: Rob Clark rob.clark@linaro.org Tested-by: Ohad Ben-Cohen ohad@wizery.com Tested-by: Benjamin Gaignard benjamin.gaignard@linaro.org --- include/linux/gfp.h | 3 ++ include/linux/mmzone.h | 38 +++++++++++++++++++---- mm/Kconfig | 2 +- mm/compaction.c | 11 +++++-- mm/page_alloc.c | 78 ++++++++++++++++++++++++++++++++++++++---------- mm/vmstat.c | 3 ++ 6 files changed, 108 insertions(+), 27 deletions(-)

diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 052a5b6..78d32a7 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -397,6 +397,9 @@ static inline bool pm_suspended_storage(void) extern int alloc_contig_range(unsigned long start, unsigned long end); extern void free_contig_range(unsigned long pfn, unsigned nr_pages);

+/* CMA stuff */ +extern void init_cma_reserved_pageblock(struct page *page); + #endif

#endif /* __LINUX_GFP_H */ diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 650ba2f..82f4fa5 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -35,13 +35,37 @@ */ #define PAGE_ALLOC_COSTLY_ORDER 3

-#define MIGRATE_UNMOVABLE 0 -#define MIGRATE_RECLAIMABLE 1 -#define MIGRATE_MOVABLE 2 -#define MIGRATE_PCPTYPES 3 /* the number of types on the pcp lists */ -#define MIGRATE_RESERVE 3 -#define MIGRATE_ISOLATE 4 /* can't allocate from here */ -#define MIGRATE_TYPES 5 +enum { + MIGRATE_UNMOVABLE, + MIGRATE_RECLAIMABLE, + MIGRATE_MOVABLE, + MIGRATE_PCPTYPES, /* the number of types on the pcp lists */ + MIGRATE_RESERVE = MIGRATE_PCPTYPES, +#ifdef CONFIG_CMA + /* + * MIGRATE_CMA migration type is designed to mimic the way + * ZONE_MOVABLE works. Only movable pages can be allocated + * from MIGRATE_CMA pageblocks and page allocator never + * implicitly change migration type of MIGRATE_CMA pageblock. + * + * The way to use it is to change migratetype of a range of + * pageblocks to MIGRATE_CMA which can be done by + * __free_pageblock_cma() function. What is important though + * is that a range of pageblocks must be aligned to + * MAX_ORDER_NR_PAGES should biggest page be bigger then + * a single pageblock. + */ + MIGRATE_CMA, +#endif + MIGRATE_ISOLATE, /* can't allocate from here */ + MIGRATE_TYPES +}; + +#ifdef CONFIG_CMA +# define is_migrate_cma(migratetype) unlikely((migratetype) == MIGRATE_CMA) +#else +# define is_migrate_cma(migratetype) false +#endif

#define for_each_migratetype_order(order, type) \ for (order = 0; order < MAX_ORDER; order++) \ diff --git a/mm/Kconfig b/mm/Kconfig index e338407..3922002 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -198,7 +198,7 @@ config COMPACTION config MIGRATION bool "Page migration" def_bool y - depends on NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION + depends on NUMA || ARCH_ENABLE_MEMORY_HOTREMOVE || COMPACTION || CMA help Allows the migration of the physical location of pages of processes while the virtual addresses are not changed. This is useful in diff --git a/mm/compaction.c b/mm/compaction.c index d5174c4..a6e7c64 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -45,6 +45,11 @@ static void map_pages(struct list_head *list) } }

+static inline bool migrate_async_suitable(int migratetype) +{ + return is_migrate_cma(migratetype) || migratetype == MIGRATE_MOVABLE; +} + /* * Isolate free pages onto a private freelist. Caller must hold zone->lock. * If @strict is true, will abort returning 0 on any invalid PFNs or non-free @@ -277,7 +282,7 @@ isolate_migratepages_range(struct zone *zone, struct compact_control *cc, */ pageblock_nr = low_pfn >> pageblock_order; if (!cc->sync && last_pageblock_nr != pageblock_nr && - get_pageblock_migratetype(page) != MIGRATE_MOVABLE) { + migrate_async_suitable(get_pageblock_migratetype(page))) { low_pfn += pageblock_nr_pages; low_pfn = ALIGN(low_pfn, pageblock_nr_pages) - 1; last_pageblock_nr = pageblock_nr; @@ -345,8 +350,8 @@ static bool suitable_migration_target(struct page *page) if (PageBuddy(page) && page_order(page) >= pageblock_order) return true;

- /* If the block is MIGRATE_MOVABLE, allow migration */ - if (migratetype == MIGRATE_MOVABLE) + /* If the block is MIGRATE_MOVABLE or MIGRATE_CMA, allow migration */ + if (migrate_async_suitable(migratetype)) return true;

/* Otherwise skip the block */ diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 238fcec..993c375 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -750,6 +750,26 @@ void __meminit __free_pages_bootmem(struct page *page, unsigned int order) __free_pages(page, order); }

+#ifdef CONFIG_CMA +/* + * Free whole pageblock and set it's migration type to MIGRATE_CMA. + */ +void __init init_cma_reserved_pageblock(struct page *page) +{ + unsigned i = pageblock_nr_pages; + struct page *p = page; + + do { + __ClearPageReserved(p); + set_page_count(p, 0); + } while (++p, --i); + + set_page_refcounted(page); + set_pageblock_migratetype(page, MIGRATE_CMA); + __free_pages(page, pageblock_order); + totalram_pages += pageblock_nr_pages; +} +#endif

/* * The order of subdivision here is critical for the IO subsystem. @@ -875,10 +895,15 @@ struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, * This array describes the order lists are fallen back to when * the free lists for the desirable migrate type are depleted */ -static int fallbacks[MIGRATE_TYPES][3] = { - [MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, - [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, - [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE }, +static int fallbacks[MIGRATE_TYPES][4] = { + [MIGRATE_UNMOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, + [MIGRATE_RECLAIMABLE] = { MIGRATE_UNMOVABLE, MIGRATE_MOVABLE, MIGRATE_RESERVE }, +#ifdef CONFIG_CMA + [MIGRATE_MOVABLE] = { MIGRATE_CMA, MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE }, + [MIGRATE_CMA] = { MIGRATE_RESERVE }, /* Never used */ +#else + [MIGRATE_MOVABLE] = { MIGRATE_RECLAIMABLE, MIGRATE_UNMOVABLE, MIGRATE_RESERVE }, +#endif [MIGRATE_RESERVE] = { MIGRATE_RESERVE }, /* Never used */ [MIGRATE_ISOLATE] = { MIGRATE_RESERVE }, /* Never used */ }; @@ -995,11 +1020,18 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype) * pages to the preferred allocation list. If falling * back for a reclaimable kernel allocation, be more * aggressive about taking ownership of free pages + * + * On the other hand, never change migration + * type of MIGRATE_CMA pageblocks nor move CMA + * pages on different free lists. We don't + * want unmovable pages to be allocated from + * MIGRATE_CMA areas. */ - if (unlikely(current_order >= (pageblock_order >> 1)) || - start_migratetype == MIGRATE_RECLAIMABLE || - page_group_by_mobility_disabled) { - unsigned long pages; + if (!is_migrate_cma(migratetype) && + (unlikely(current_order >= pageblock_order / 2) || + start_migratetype == MIGRATE_RECLAIMABLE || + page_group_by_mobility_disabled)) { + int pages; pages = move_freepages_block(zone, page, start_migratetype);

@@ -1017,11 +1049,14 @@ __rmqueue_fallback(struct zone *zone, int order, int start_migratetype) rmv_page_order(page);

/* Take ownership for orders >= pageblock_order */ - if (current_order >= pageblock_order) + if (current_order >= pageblock_order && + !is_migrate_cma(migratetype)) change_pageblock_range(page, current_order, start_migratetype);

- expand(zone, page, order, current_order, area, migratetype); + expand(zone, page, order, current_order, area, + is_migrate_cma(migratetype) + ? migratetype : start_migratetype);

trace_mm_page_alloc_extfrag(page, order, current_order, start_migratetype, migratetype); @@ -1072,7 +1107,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, unsigned long count, struct list_head *list, int migratetype, int cold) { - int i; + int mt = migratetype, i;

spin_lock(&zone->lock); for (i = 0; i < count; ++i) { @@ -1093,7 +1128,12 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, list_add(&page->lru, list); else list_add_tail(&page->lru, list); - set_page_private(page, migratetype); +#ifdef CONFIG_CMA + mt = get_pageblock_migratetype(page); + if (!is_migrate_cma(mt) && mt != MIGRATE_ISOLATE) + mt = migratetype; +#endif + set_page_private(page, mt); list = &page->lru; } __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order)); @@ -1337,8 +1377,12 @@ int split_free_page(struct page *page)

if (order >= pageblock_order - 1) { struct page *endpage = page + (1 << order) - 1; - for (; page < endpage; page += pageblock_nr_pages) - set_pageblock_migratetype(page, MIGRATE_MOVABLE); + for (; page < endpage; page += pageblock_nr_pages) { + int mt = get_pageblock_migratetype(page); + if (mt != MIGRATE_ISOLATE && !is_migrate_cma(mt)) + set_pageblock_migratetype(page, + MIGRATE_MOVABLE); + } }

return 1 << order; @@ -5369,14 +5413,16 @@ static int __count_immobile_pages(struct zone *zone, struct page *page, int count) { unsigned long pfn, iter, found; + int mt; + /* * For avoiding noise data, lru_add_drain_all() should be called * If ZONE_MOVABLE, the zone never contains immobile pages */ if (zone_idx(zone) == ZONE_MOVABLE) return true; - - if (get_pageblock_migratetype(page) == MIGRATE_MOVABLE) + mt = get_pageblock_migratetype(page); + if (mt == MIGRATE_MOVABLE || is_migrate_cma(mt)) return true;

pfn = page_to_pfn(page); diff --git a/mm/vmstat.c b/mm/vmstat.c index f600557..c47ac13 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -613,6 +613,9 @@ static char * const migratetype_names[MIGRATE_TYPES] = { "Reclaimable", "Movable", "Reserve", +#ifdef CONFIG_CMA + "CMA", +#endif "Isolate", };

From: Michal Nazarewicz mina86@mina86.com

This commit changes various functions that change pages and pageblocks migrate type between MIGRATE_ISOLATE and MIGRATE_MOVABLE in such a way as to allow to work with MIGRATE_CMA migrate type.

Signed-off-by: Michal Nazarewicz mina86@mina86.com Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com Tested-by: Rob Clark rob.clark@linaro.org Tested-by: Ohad Ben-Cohen ohad@wizery.com Tested-by: Benjamin Gaignard benjamin.gaignard@linaro.org --- include/linux/gfp.h | 3 ++- include/linux/page-isolation.h | 18 +++++++++--------- mm/memory-failure.c | 2 +- mm/memory_hotplug.c | 6 +++--- mm/page_alloc.c | 18 ++++++++++++------ mm/page_isolation.c | 15 ++++++++------- 6 files changed, 35 insertions(+), 27 deletions(-)

diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 78d32a7..1e49be4 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -394,7 +394,8 @@ static inline bool pm_suspended_storage(void) #ifdef CONFIG_CMA

/* The below functions must be run on a range from a single zone. */ -extern int alloc_contig_range(unsigned long start, unsigned long end); +extern int alloc_contig_range(unsigned long start, unsigned long end, + unsigned migratetype); extern void free_contig_range(unsigned long pfn, unsigned nr_pages);

/* CMA stuff */ diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 051c1b1..3bdcab3 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -3,7 +3,7 @@

/* * Changes migrate type in [start_pfn, end_pfn) to be MIGRATE_ISOLATE. - * If specified range includes migrate types other than MOVABLE, + * If specified range includes migrate types other than MOVABLE or CMA, * this will fail with -EBUSY. * * For isolating all pages in the range finally, the caller have to @@ -11,27 +11,27 @@ * test it. */ extern int -start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn); +start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, + unsigned migratetype);

/* * Changes MIGRATE_ISOLATE to MIGRATE_MOVABLE. * target range is [start_pfn, end_pfn) */ extern int -undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn); +undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, + unsigned migratetype);

/* - * test all pages in [start_pfn, end_pfn)are isolated or not. + * Test all pages in [start_pfn, end_pfn) are isolated or not. */ -extern int -test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn); +int test_pages_isolated(unsigned long start_pfn, unsigned long end_pfn);

/* - * Internal funcs.Changes pageblock's migrate type. - * Please use make_pagetype_isolated()/make_pagetype_movable(). + * Internal functions. Changes pageblock's migrate type. */ extern int set_migratetype_isolate(struct page *page); -extern void unset_migratetype_isolate(struct page *page); +extern void unset_migratetype_isolate(struct page *page, unsigned migratetype);

#endif diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 56080ea..76b01bf 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1400,7 +1400,7 @@ static int get_any_page(struct page *p, unsigned long pfn, int flags) /* Not a free page */ ret = 1; } - unset_migratetype_isolate(p); + unset_migratetype_isolate(p, MIGRATE_MOVABLE); unlock_memory_hotplug(); return ret; } diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 6629faf..fc898cb 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -891,7 +891,7 @@ static int __ref offline_pages(unsigned long start_pfn, nr_pages = end_pfn - start_pfn;

/* set above range as isolated */ - ret = start_isolate_page_range(start_pfn, end_pfn); + ret = start_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE); if (ret) goto out;

@@ -956,7 +956,7 @@ repeat: We cannot do rollback at this point. */ offline_isolated_pages(start_pfn, end_pfn); /* reset pagetype flags and makes migrate type to be MOVABLE */ - undo_isolate_page_range(start_pfn, end_pfn); + undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE); /* removal success */ zone->present_pages -= offlined_pages; zone->zone_pgdat->node_present_pages -= offlined_pages; @@ -981,7 +981,7 @@ failed_removal: start_pfn, end_pfn); memory_notify(MEM_CANCEL_OFFLINE, &arg); /* pushback to free area */ - undo_isolate_page_range(start_pfn, end_pfn); + undo_isolate_page_range(start_pfn, end_pfn, MIGRATE_MOVABLE);

out: unlock_memory_hotplug(); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 993c375..947879c 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5539,7 +5539,7 @@ out: return ret; }

-void unset_migratetype_isolate(struct page *page) +void unset_migratetype_isolate(struct page *page, unsigned migratetype) { struct zone *zone; unsigned long flags; @@ -5547,8 +5547,8 @@ void unset_migratetype_isolate(struct page *page) spin_lock_irqsave(&zone->lock, flags); if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE) goto out; - set_pageblock_migratetype(page, MIGRATE_MOVABLE); - move_freepages_block(zone, page, MIGRATE_MOVABLE); + set_pageblock_migratetype(page, migratetype); + move_freepages_block(zone, page, migratetype); out: spin_unlock_irqrestore(&zone->lock, flags); } @@ -5624,6 +5624,10 @@ static int __alloc_contig_migrate_range(unsigned long start, unsigned long end) * alloc_contig_range() -- tries to allocate given range of pages * @start: start PFN to allocate * @end: one-past-the-last PFN to allocate + * @migratetype: migratetype of the underlaying pageblocks (either + * #MIGRATE_MOVABLE or #MIGRATE_CMA). All pageblocks + * in range must have the same migratetype and it must + * be either of the two. * * The PFN range does not have to be pageblock or MAX_ORDER_NR_PAGES * aligned, however it's the caller's responsibility to guarantee that @@ -5636,7 +5640,8 @@ static int __alloc_contig_migrate_range(unsigned long start, unsigned long end) * pages which PFN is in [start, end) are allocated for the caller and * need to be freed with free_contig_range(). */ -int alloc_contig_range(unsigned long start, unsigned long end) +int alloc_contig_range(unsigned long start, unsigned long end, + unsigned migratetype) { struct zone *zone = page_zone(pfn_to_page(start)); unsigned long outer_start, outer_end; @@ -5666,7 +5671,8 @@ int alloc_contig_range(unsigned long start, unsigned long end) */

ret = start_isolate_page_range(pfn_align_to_maxpage_down(start), - pfn_align_to_maxpage_up(end)); + pfn_align_to_maxpage_up(end), + migratetype); if (ret) goto done;

@@ -5726,7 +5732,7 @@ int alloc_contig_range(unsigned long start, unsigned long end)

done: undo_isolate_page_range(pfn_align_to_maxpage_down(start), - pfn_align_to_maxpage_up(end)); + pfn_align_to_maxpage_up(end), migratetype); return ret; }

diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 4ae42bb..c9f0477 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -24,6 +24,7 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages) * to be MIGRATE_ISOLATE. * @start_pfn: The lower PFN of the range to be isolated. * @end_pfn: The upper PFN of the range to be isolated. + * @migratetype: migrate type to set in error recovery. * * Making page-allocation-type to be MIGRATE_ISOLATE means free pages in * the range will never be allocated. Any free pages and pages freed in the @@ -32,8 +33,8 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages) * start_pfn/end_pfn must be aligned to pageblock_order. * Returns 0 on success and -EBUSY if any part of range cannot be isolated. */ -int -start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn) +int start_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, + unsigned migratetype) { unsigned long pfn; unsigned long undo_pfn; @@ -56,7 +57,7 @@ undo: for (pfn = start_pfn; pfn < undo_pfn; pfn += pageblock_nr_pages) - unset_migratetype_isolate(pfn_to_page(pfn)); + unset_migratetype_isolate(pfn_to_page(pfn), migratetype);

return -EBUSY; } @@ -64,8 +65,8 @@ undo: /* * Make isolated pages available again. */ -int -undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn) +int undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn, + unsigned migratetype) { unsigned long pfn; struct page *page; @@ -77,7 +78,7 @@ undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn) page = __first_valid_page(pfn, pageblock_nr_pages); if (!page || get_pageblock_migratetype(page) != MIGRATE_ISOLATE) continue; - unset_migratetype_isolate(page); + unset_migratetype_isolate(page, migratetype); } return 0; } @@ -86,7 +87,7 @@ undo_isolate_page_range(unsigned long start_pfn, unsigned long end_pfn) * all pages in [start_pfn...end_pfn) must be in the same zone. * zone->lock must be held before call this. * - * Returns 1 if all pages in the range is isolated. + * Returns 1 if all pages in the range are isolated. */ static int __test_page_isolated_in_pageblock(unsigned long pfn, unsigned long end_pfn)

alloc_contig_range() performs memory allocation so it also should keep track on keeping the correct level of memory watermarks. This commit adds a call to *_slowpath style reclaim to grab enough pages to make sure that the final collection of contiguous pages from freelists will not starve the system.

Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com Signed-off-by: Kyungmin Park kyungmin.park@samsung.com CC: Michal Nazarewicz mina86@mina86.com Tested-by: Rob Clark rob.clark@linaro.org Tested-by: Ohad Ben-Cohen ohad@wizery.com Tested-by: Benjamin Gaignard benjamin.gaignard@linaro.org --- mm/page_alloc.c | 47 +++++++++++++++++++++++++++++++++++++++++++++++ 1 files changed, 47 insertions(+), 0 deletions(-)

diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 983ccba..371a79f 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5632,6 +5632,46 @@ static int __alloc_contig_migrate_range(unsigned long start, unsigned long end) return ret > 0 ? 0 : ret; }

+/* + * Trigger memory pressure bump to reclaim some pages in order to be able to + * allocate 'count' pages in single page units. Does similar work as + *__alloc_pages_slowpath() function. + */ +static int __reclaim_pages(struct zone *zone, gfp_t gfp_mask, int count) +{ + enum zone_type high_zoneidx = gfp_zone(gfp_mask); + struct zonelist *zonelist = node_zonelist(0, gfp_mask); + int did_some_progress = 0; + int order = 1; + unsigned long watermark; + + /* + * Increase level of watermarks to force kswapd do his job + * to stabilize at new watermark level. + */ + min_free_kbytes += count * PAGE_SIZE / 1024; + setup_per_zone_wmarks(); + + /* Obey watermarks as if the page was being allocated */ + watermark = low_wmark_pages(zone) + count; + while (!zone_watermark_ok(zone, 0, watermark, 0, 0)) { + wake_all_kswapd(order, zonelist, high_zoneidx, zone_idx(zone)); + + did_some_progress = __perform_reclaim(gfp_mask, order, zonelist, + NULL); + if (!did_some_progress) { + /* Exhausted what can be done so it's blamo time */ + out_of_memory(zonelist, gfp_mask, order, NULL); + } + } + + /* Restore original watermark levels. */ + min_free_kbytes -= count * PAGE_SIZE / 1024; + setup_per_zone_wmarks(); + + return count; +} + /** * alloc_contig_range() -- tries to allocate given range of pages * @start: start PFN to allocate @@ -5730,6 +5770,13 @@ int alloc_contig_range(unsigned long start, unsigned long end, goto done; }

+ /* + * Reclaim enough pages to make sure that contiguous allocation + * will not starve the system. + */ + __reclaim_pages(zone, GFP_HIGHUSER_MOVABLE, end-start); + + /* Grab isolated pages from freelists. */ outer_end = isolate_freepages_range(outer_start, end); if (!outer_end) { ret = -EBUSY;

The Contiguous Memory Allocator is a set of helper functions for DMA mapping framework that improves allocations of contiguous memory chunks.

CMA grabs memory on system boot, marks it with CMA_MIGRATE_TYPE and gives back to the system. Kernel is allowed to allocate movable pages within CMA's managed memory so that it can be used for example for page cache when DMA mapping do not use it. On dma_alloc_from_contiguous() request such pages are migrated out of CMA area to free required contiguous block and fulfill the request. This allows to allocate large contiguous chunks of memory at any time assuming that there is enough free memory available in the system.

This code is heavily based on earlier works by Michal Nazarewicz.

Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com Signed-off-by: Kyungmin Park kyungmin.park@samsung.com CC: Michal Nazarewicz mina86@mina86.com Acked-by: Arnd Bergmann arnd@arndb.de Tested-by: Rob Clark rob.clark@linaro.org Tested-by: Ohad Ben-Cohen ohad@wizery.com Tested-by: Benjamin Gaignard benjamin.gaignard@linaro.org --- Documentation/kernel-parameters.txt | 5 + arch/Kconfig | 3 + drivers/base/Kconfig | 89 ++++++++ drivers/base/Makefile | 1 + drivers/base/dma-contiguous.c | 405 ++++++++++++++++++++++++++++++++++ include/asm-generic/dma-contiguous.h | 27 +++ include/linux/device.h | 4 + include/linux/dma-contiguous.h | 110 +++++++++ 8 files changed, 644 insertions(+), 0 deletions(-) create mode 100644 drivers/base/dma-contiguous.c create mode 100644 include/asm-generic/dma-contiguous.h create mode 100644 include/linux/dma-contiguous.h

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt index 033d4e6..84982e2 100644 --- a/Documentation/kernel-parameters.txt +++ b/Documentation/kernel-parameters.txt @@ -508,6 +508,11 @@ bytes respectively. Such letter suffixes can also be entirely omitted. Also note the kernel might malfunction if you disable some critical bits.

+ cma=nn[MG] [ARM,KNL] + Sets the size of kernel global memory area for contiguous + memory allocations. For more information, see + include/linux/dma-contiguous.h + cmo_free_hint= [PPC] Format: { yes | no } Specify whether pages are marked as being inactive when they are freed. This is used in CMO environments diff --git a/arch/Kconfig b/arch/Kconfig index 4f55c73..8ec200c 100644 --- a/arch/Kconfig +++ b/arch/Kconfig @@ -128,6 +128,9 @@ config HAVE_ARCH_TRACEHOOK config HAVE_DMA_ATTRS bool

+config HAVE_DMA_CONTIGUOUS + bool + config USE_GENERIC_SMP_HELPERS bool

diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig index 7be9f79..f56cb20 100644 --- a/drivers/base/Kconfig +++ b/drivers/base/Kconfig @@ -189,4 +189,93 @@ config DMA_SHARED_BUFFER APIs extension; the file's descriptor can then be passed on to other driver.

+config CMA + bool "Contiguous Memory Allocator (EXPERIMENTAL)" + depends on HAVE_DMA_CONTIGUOUS && HAVE_MEMBLOCK && EXPERIMENTAL + select MIGRATION + help + This enables the Contiguous Memory Allocator which allows drivers + to allocate big physically-contiguous blocks of memory for use with + hardware components that do not support I/O map nor scatter-gather. + + For more information see <include/linux/dma-contiguous.h>. + If unsure, say "n". + +if CMA + +config CMA_DEBUG + bool "CMA debug messages (DEVELOPMENT)" + depends on DEBUG_KERNEL + help + Turns on debug messages in CMA. This produces KERN_DEBUG + messages for every CMA call as well as various messages while + processing calls such as dma_alloc_from_contiguous(). + This option does not affect warning and error messages. + +comment "Default contiguous memory area size:" + +config CMA_SIZE_MBYTES + int "Size in Mega Bytes" + depends on !CMA_SIZE_SEL_PERCENTAGE + default 16 + help + Defines the size (in MiB) of the default memory area for Contiguous + Memory Allocator. + +config CMA_SIZE_PERCENTAGE + int "Percentage of total memory" + depends on !CMA_SIZE_SEL_MBYTES + default 10 + help + Defines the size of the default memory area for Contiguous Memory + Allocator as a percentage of the total memory in the system. + +choice + prompt "Selected region size" + default CMA_SIZE_SEL_ABSOLUTE + +config CMA_SIZE_SEL_MBYTES + bool "Use mega bytes value only" + +config CMA_SIZE_SEL_PERCENTAGE + bool "Use percentage value only" + +config CMA_SIZE_SEL_MIN + bool "Use lower value (minimum)" + +config CMA_SIZE_SEL_MAX + bool "Use higher value (maximum)" + +endchoice + +config CMA_ALIGNMENT + int "Maximum PAGE_SIZE order of alignment for contiguous buffers" + range 4 9 + default 8 + help + DMA mapping framework by default aligns all buffers to the smallest + PAGE_SIZE order which is greater than or equal to the requested buffer + size. This works well for buffers up to a few hundreds kilobytes, but + for larger buffers it just a memory waste. With this parameter you can + specify the maximum PAGE_SIZE order for contiguous buffers. Larger + buffers will be aligned only to this specified order. The order is + expressed as a power of two multiplied by the PAGE_SIZE. + + For example, if your system defaults to 4KiB pages, the order value + of 8 means that the buffers will be aligned up to 1MiB only. + + If unsure, leave the default value "8". + +config CMA_AREAS + int "Maximum count of the CMA device-private areas" + default 7 + help + CMA allows to create CMA areas for particular devices. This parameter + sets the maximum number of such device private CMA areas in the + system. + + If unsure, leave the default value "7". + +endif + endmenu diff --git a/drivers/base/Makefile b/drivers/base/Makefile index 610f999..ffd9dae 100644 --- a/drivers/base/Makefile +++ b/drivers/base/Makefile @@ -6,6 +6,7 @@ obj-y := core.o bus.o dd.o syscore.o \ attribute_container.o transport_class.o \ topology.o obj-$(CONFIG_DEVTMPFS) += devtmpfs.o +obj-$(CONFIG_CMA) += dma-contiguous.o obj-y += power/ obj-$(CONFIG_HAS_DMA) += dma-mapping.o obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o diff --git a/drivers/base/dma-contiguous.c b/drivers/base/dma-contiguous.c new file mode 100644 index 0000000..c33f771 --- /dev/null +++ b/drivers/base/dma-contiguous.c @@ -0,0 +1,405 @@ +/* + * Contiguous Memory Allocator for DMA mapping framework + * Copyright (c) 2010-2011 by Samsung Electronics. + * Written by: + * Marek Szyprowski m.szyprowski@samsung.com + * Michal Nazarewicz mina86@mina86.com + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of the + * License or (at your optional) any later version of the license. + */ + +#define pr_fmt(fmt) "cma: " fmt + +#ifdef CONFIG_CMA_DEBUG +#ifndef DEBUG +# define DEBUG +#endif +#endif + +#include <asm/page.h> +#include <asm/dma-contiguous.h> + +#include <linux/memblock.h> +#include <linux/err.h> +#include <linux/mm.h> +#include <linux/mutex.h> +#include <linux/page-isolation.h> +#include <linux/slab.h> +#include <linux/swap.h> +#include <linux/mm_types.h> +#include <linux/dma-contiguous.h> + +#ifndef SZ_1M +#define SZ_1M (1 << 20) +#endif + +struct cma { + unsigned long base_pfn; + unsigned long count; + unsigned long *bitmap; +}; + +struct cma *dma_contiguous_default_area; + +#ifdef CONFIG_CMA_SIZE_MBYTES +#define CMA_SIZE_MBYTES CONFIG_CMA_SIZE_MBYTES +#else +#define CMA_SIZE_MBYTES 0 +#endif + +#ifdef CONFIG_CMA_SIZE_PERCENTAGE +#define CMA_SIZE_PERCENTAGE CONFIG_CMA_SIZE_PERCENTAGE +#else +#define CMA_SIZE_PERCENTAGE 0 +#endif + +/* + * Default global CMA area size can be defined in kernel's .config. + * This is usefull mainly for distro maintainers to create a kernel + * that works correctly for most supported systems. + * The size can be set in bytes or as a percentage of the total memory + * in the system. + * + * Users, who want to set the size of global CMA area for their system + * should use cma= kernel parameter. + */ +static unsigned long size_bytes = CMA_SIZE_MBYTES * SZ_1M; +static unsigned long size_percent = CMA_SIZE_PERCENTAGE; +static long size_cmdline = -1; + +static int __init early_cma(char *p) +{ + pr_debug("%s(%s)\n", __func__, p); + size_cmdline = memparse(p, &p); + return 0; +} +early_param("cma", early_cma); + +static unsigned long __init cma_early_get_total_pages(void) +{ + struct memblock_region *reg; + unsigned long total_pages = 0; + + /* + * We cannot use memblock_phys_mem_size() here, because + * memblock_analyze() has not been called yet. + */ + for_each_memblock(memory, reg) + total_pages += memblock_region_memory_end_pfn(reg) - + memblock_region_memory_base_pfn(reg); + return total_pages; +} + +/** + * dma_contiguous_reserve() - reserve area for contiguous memory handling + * @limit: End address of the reserved memory (optional, 0 for any). + * + * This funtion reserves memory from early allocator. It should be + * called by arch specific code once the early allocator (memblock or bootmem) + * has been activated and all other subsystems have already allocated/reserved + * memory. + */ +void __init dma_contiguous_reserve(phys_addr_t limit) +{ + unsigned long selected_size = 0; + unsigned long total_pages; + + pr_debug("%s(limit %08lx)\n", __func__, (unsigned long)limit); + + total_pages = cma_early_get_total_pages(); + size_percent *= (total_pages << PAGE_SHIFT) / 100; + + pr_debug("%s: total available: %ld MiB, size absolute: %ld MiB, size percentage: %ld MiB\n", + __func__, (total_pages << PAGE_SHIFT) / SZ_1M, + size_bytes / SZ_1M, size_percent / SZ_1M); + +#ifdef CONFIG_CMA_SIZE_SEL_MBYTES + selected_size = size_bytes; +#elif defined(CONFIG_CMA_SIZE_SEL_PERCENTAGE) + selected_size = size_percent; +#elif defined(CONFIG_CMA_SIZE_SEL_MIN) + selected_size = min(size_bytes, size_percent); +#elif defined(CONFIG_CMA_SIZE_SEL_MAX) + selected_size = max(size_bytes, size_percent); +#endif + + if (size_cmdline != -1) + selected_size = size_cmdline; + + if (!selected_size) + return; + + pr_debug("%s: reserving %ld MiB for global area\n", __func__, + selected_size / SZ_1M); + + dma_declare_contiguous(NULL, selected_size, 0, limit); +}; + +static DEFINE_MUTEX(cma_mutex); + +static int cma_activate_area(unsigned long base_pfn, unsigned long count) +{ + unsigned long pfn = base_pfn; + unsigned i = count >> pageblock_order; + struct zone *zone; + + WARN_ON_ONCE(!pfn_valid(pfn)); + zone = page_zone(pfn_to_page(pfn)); + + do { + unsigned j; + base_pfn = pfn; + for (j = pageblock_nr_pages; j; --j, pfn++) { + WARN_ON_ONCE(!pfn_valid(pfn)); + if (page_zone(pfn_to_page(pfn)) != zone) + return -EINVAL; + } + init_cma_reserved_pageblock(pfn_to_page(base_pfn)); + } while (--i); + return 0; +} + +static struct cma *cma_create_area(unsigned long base_pfn, + unsigned long count) +{ + int bitmap_size = BITS_TO_LONGS(count) * sizeof(long); + struct cma *cma; + int ret = -ENOMEM; + + pr_debug("%s(base %08lx, count %lx)\n", __func__, base_pfn, count); + + cma = kmalloc(sizeof *cma, GFP_KERNEL); + if (!cma) + return ERR_PTR(-ENOMEM); + + cma->base_pfn = base_pfn; + cma->count = count; + cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL); + + if (!cma->bitmap) + goto no_mem; + + ret = cma_activate_area(base_pfn, count); + if (ret) + goto error; + + pr_debug("%s: returned %p\n", __func__, (void *)cma); + return cma; + +error: + kfree(cma->bitmap); +no_mem: + kfree(cma); + return ERR_PTR(ret); +} + +static struct cma_reserved { + phys_addr_t start; + unsigned long size; + struct device *dev; +} cma_reserved[MAX_CMA_AREAS] __initdata; +static unsigned cma_reserved_count __initdata; + +static int __init cma_init_reserved_areas(void) +{ + struct cma_reserved *r = cma_reserved; + unsigned i = cma_reserved_count; + + pr_debug("%s()\n", __func__); + + for (; i; --i, ++r) { + struct cma *cma; + cma = cma_create_area(PFN_DOWN(r->start), + r->size >> PAGE_SHIFT); + if (!IS_ERR(cma)) + dev_set_cma_area(r->dev, cma); + } + return 0; +} +core_initcall(cma_init_reserved_areas); + +/** + * dma_declare_contiguous() - reserve area for contiguous memory handling + * for particular device + * @dev: Pointer to device structure. + * @size: Size of the reserved memory. + * @start: Start address of the reserved memory (optional, 0 for any). + * @limit: End address of the reserved memory (optional, 0 for any). + * + * This funtion reserves memory for specified device. It should be + * called by board specific code when early allocator (memblock or bootmem) + * is still activate. + */ +int __init dma_declare_contiguous(struct device *dev, unsigned long size, + phys_addr_t base, phys_addr_t limit) +{ + struct cma_reserved *r = &cma_reserved[cma_reserved_count]; + unsigned long alignment; + + pr_debug("%s(size %lx, base %08lx, limit %08lx)\n", __func__, + (unsigned long)size, (unsigned long)base, + (unsigned long)limit); + + /* Sanity checks */ + if (cma_reserved_count == ARRAY_SIZE(cma_reserved)) { + pr_err("Not enough slots for CMA reserved regions!\n"); + return -ENOSPC; + } + + if (!size) + return -EINVAL; + + /* Sanitise input arguments */ + alignment = PAGE_SIZE << max(MAX_ORDER, pageblock_order); + base = ALIGN(base, alignment); + size = ALIGN(size, alignment); + limit &= ~(alignment - 1); + + /* Reserve memory */ + if (base) { + if (memblock_is_region_reserved(base, size) || + memblock_reserve(base, size) < 0) { + base = -EBUSY; + goto err; + } + } else { + /* + * Use __memblock_alloc_base() since + * memblock_alloc_base() panic()s. + */ + phys_addr_t addr = __memblock_alloc_base(size, alignment, limit); + if (!addr) { + base = -ENOMEM; + goto err; + } else if (addr + size > ~(unsigned long)0) { + memblock_free(addr, size); + base = -EINVAL; + goto err; + } else { + base = addr; + } + } + + /* + * Each reserved area must be initialised later, when more kernel + * subsystems (like slab allocator) are available. + */ + r->start = base; + r->size = size; + r->dev = dev; + cma_reserved_count++; + pr_info("CMA: reserved %ld MiB at %08lx\n", size / SZ_1M, + (unsigned long)base); + + /* + * Architecture specific contiguous memory fixup. + */ + dma_contiguous_early_fixup(base, size); + return 0; +err: + pr_err("CMA: failed to reserve %ld MiB\n", size / SZ_1M); + return base; +} + +/** + * dma_alloc_from_contiguous() - allocate pages from contiguous area + * @dev: Pointer to device for which the allocation is performed. + * @count: Requested number of pages. + * @align: Requested alignment of pages (in PAGE_SIZE order). + * + * This funtion allocates memory buffer for specified device. It uses + * device specific contiguous memory area if available or the default + * global one. Requires architecture specific get_dev_cma_area() helper + * function. + */ +struct page *dma_alloc_from_contiguous(struct device *dev, int count, + unsigned int align) +{ + unsigned long mask, pfn, pageno, start = 0; + struct cma *cma = dev_get_cma_area(dev); + int ret; + + if (!cma || !cma->count) + return NULL; + + if (align > CONFIG_CMA_ALIGNMENT) + align = CONFIG_CMA_ALIGNMENT; + + pr_debug("%s(cma %p, count %d, align %d)\n", __func__, (void *)cma, + count, align); + + if (!count) + return NULL; + + mask = (1 << align) - 1; + + mutex_lock(&cma_mutex); + + for (;;) { + pageno = bitmap_find_next_zero_area(cma->bitmap, cma->count, + start, count, mask); + if (pageno >= cma->count) { + ret = -ENOMEM; + goto error; + } + + pfn = cma->base_pfn + pageno; + ret = alloc_contig_range(pfn, pfn + count, MIGRATE_CMA); + if (ret == 0) { + bitmap_set(cma->bitmap, pageno, count); + break; + } else if (ret != -EBUSY) { + goto error; + } + pr_debug("%s(): memory range at %p is busy, retrying\n", + __func__, pfn_to_page(pfn)); + /* try again with a bit different memory target */ + start = pageno + mask + 1; + } + + mutex_unlock(&cma_mutex); + + pr_debug("%s(): returned %p\n", __func__, pfn_to_page(pfn)); + return pfn_to_page(pfn); +error: + mutex_unlock(&cma_mutex); + return NULL; +} + +/** + * dma_release_from_contiguous() - release allocated pages + * @dev: Pointer to device for which the pages were allocated. + * @pages: Allocated pages. + * @count: Number of allocated pages. + * + * This funtion releases memory allocated by dma_alloc_from_contiguous(). + * It return 0 when provided pages doen't belongs to contiguous area and + * 1 on success. + */ +int dma_release_from_contiguous(struct device *dev, struct page *pages, + int count) +{ + struct cma *cma = dev_get_cma_area(dev); + unsigned long pfn; + + if (!cma || !pages) + return 0; + + pr_debug("%s(page %p)\n", __func__, (void *)pages); + + pfn = page_to_pfn(pages); + + if (pfn < cma->base_pfn || pfn >= cma->base_pfn + cma->count) + return 0; + + mutex_lock(&cma_mutex); + + bitmap_clear(cma->bitmap, pfn - cma->base_pfn, count); + free_contig_range(pfn, count); + + mutex_unlock(&cma_mutex); + return 1; +} diff --git a/include/asm-generic/dma-contiguous.h b/include/asm-generic/dma-contiguous.h new file mode 100644 index 0000000..bf2bccc --- /dev/null +++ b/include/asm-generic/dma-contiguous.h @@ -0,0 +1,27 @@ +#ifndef ASM_DMA_CONTIGUOUS_H +#define ASM_DMA_CONTIGUOUS_H + +#ifdef __KERNEL__ + +#include <linux/device.h> +#include <linux/dma-contiguous.h> + +#ifdef CONFIG_CMA + +static inline struct cma *dev_get_cma_area(struct device *dev) +{ + if (dev && dev->cma_area) + return dev->cma_area; + return dma_contiguous_default_area; +} + +static inline void dev_set_cma_area(struct device *dev, struct cma *cma) +{ + if (dev) + dev->cma_area = cma; + dma_contiguous_default_area = cma; +} + +#endif +#endif +#endif diff --git a/include/linux/device.h b/include/linux/device.h index b63fb39..9559c18 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -667,6 +667,10 @@ struct device {

struct dma_coherent_mem *dma_mem; /* internal for coherent mem override */ +#ifdef CONFIG_CMA + struct cma *cma_area; /* contiguous memory area for dma + allocations */ +#endif /* arch specific additions */ struct dev_archdata archdata;

diff --git a/include/linux/dma-contiguous.h b/include/linux/dma-contiguous.h new file mode 100644 index 0000000..ffb4b40 --- /dev/null +++ b/include/linux/dma-contiguous.h @@ -0,0 +1,110 @@ +#ifndef __LINUX_CMA_H +#define __LINUX_CMA_H + +/* + * Contiguous Memory Allocator for DMA mapping framework + * Copyright (c) 2010-2011 by Samsung Electronics. + * Written by: + * Marek Szyprowski m.szyprowski@samsung.com + * Michal Nazarewicz mina86@mina86.com + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License as + * published by the Free Software Foundation; either version 2 of the + * License or (at your optional) any later version of the license. + */ + +/* + * Contiguous Memory Allocator + * + * The Contiguous Memory Allocator (CMA) makes it possible to + * allocate big contiguous chunks of memory after the system has + * booted. + * + * Why is it needed? + * + * Various devices on embedded systems have no scatter-getter and/or + * IO map support and require contiguous blocks of memory to + * operate. They include devices such as cameras, hardware video + * coders, etc. + * + * Such devices often require big memory buffers (a full HD frame + * is, for instance, more then 2 mega pixels large, i.e. more than 6 + * MB of memory), which makes mechanisms such as kmalloc() or + * alloc_page() ineffective. + * + * At the same time, a solution where a big memory region is + * reserved for a device is suboptimal since often more memory is + * reserved then strictly required and, moreover, the memory is + * inaccessible to page system even if device drivers don't use it. + * + * CMA tries to solve this issue by operating on memory regions + * where only movable pages can be allocated from. This way, kernel + * can use the memory for pagecache and when device driver requests + * it, allocated pages can be migrated. + * + * Driver usage + * + * CMA should not be used by the device drivers directly. It is + * only a helper framework for dma-mapping subsystem. + * + * For more information, see kernel-docs in drivers/base/dma-contiguous.c + */ + +#ifdef __KERNEL__ + +struct cma; +struct page; +struct device; + +#ifdef CONFIG_CMA + +/* + * There is always at least global CMA area and a few optional device + * private areas configured in kernel .config. + */ +#define MAX_CMA_AREAS (1 + CONFIG_CMA_AREAS) + +extern struct cma *dma_contiguous_default_area; + +void dma_contiguous_reserve(phys_addr_t addr_limit); +int dma_declare_contiguous(struct device *dev, unsigned long size, + phys_addr_t base, phys_addr_t limit); + +struct page *dma_alloc_from_contiguous(struct device *dev, int count, + unsigned int order); +int dma_release_from_contiguous(struct device *dev, struct page *pages, + int count); + +#else + +#define MAX_CMA_AREAS (0) + +static inline void dma_contiguous_reserve(phys_addr_t limit) { } + +static inline +int dma_declare_contiguous(struct device *dev, unsigned long size, + phys_addr_t base, phys_addr_t limit) +{ + return -ENOSYS; +} + +static inline +struct page *dma_alloc_from_contiguous(struct device *dev, int count, + unsigned int order) +{ + return NULL; +} + +static inline +int dma_release_from_contiguous(struct device *dev, struct page *pages, + int count) +{ + return 0; +} + +#endif + +#endif + +#endif

This patch adds support for CMA to dma-mapping subsystem for x86 architecture that uses common pci-dma/pci-nommu implementation. This allows to test CMA on KVM/QEMU and a lot of common x86 boxes.

Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com Signed-off-by: Kyungmin Park kyungmin.park@samsung.com CC: Michal Nazarewicz mina86@mina86.com Acked-by: Arnd Bergmann arnd@arndb.de --- arch/x86/Kconfig | 1 + arch/x86/include/asm/dma-contiguous.h | 13 +++++++++++++ arch/x86/include/asm/dma-mapping.h | 4 ++++ arch/x86/kernel/pci-dma.c | 18 ++++++++++++++++-- arch/x86/kernel/pci-nommu.c | 8 +------- arch/x86/kernel/setup.c | 2 ++ 6 files changed, 37 insertions(+), 9 deletions(-) create mode 100644 arch/x86/include/asm/dma-contiguous.h

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 5bed94e..de6e069 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -31,6 +31,7 @@ config X86 select ARCH_WANT_OPTIONAL_GPIOLIB select ARCH_WANT_FRAME_POINTERS select HAVE_DMA_ATTRS + select HAVE_DMA_CONTIGUOUS if !SWIOTLB select HAVE_KRETPROBES select HAVE_OPTPROBES select HAVE_FTRACE_MCOUNT_RECORD diff --git a/arch/x86/include/asm/dma-contiguous.h b/arch/x86/include/asm/dma-contiguous.h new file mode 100644 index 0000000..8fb117d --- /dev/null +++ b/arch/x86/include/asm/dma-contiguous.h @@ -0,0 +1,13 @@ +#ifndef ASMX86_DMA_CONTIGUOUS_H +#define ASMX86_DMA_CONTIGUOUS_H + +#ifdef __KERNEL__ + +#include <linux/device.h> +#include <linux/dma-contiguous.h> +#include <asm-generic/dma-contiguous.h> + +static inline void dma_contiguous_early_fixup(phys_addr_t base, unsigned long size) { } + +#endif +#endif diff --git a/arch/x86/include/asm/dma-mapping.h b/arch/x86/include/asm/dma-mapping.h index ed3065f..90ac6f0 100644 --- a/arch/x86/include/asm/dma-mapping.h +++ b/arch/x86/include/asm/dma-mapping.h @@ -13,6 +13,7 @@ #include <asm/io.h> #include <asm/swiotlb.h> #include <asm-generic/dma-coherent.h> +#include <linux/dma-contiguous.h>

#ifdef CONFIG_ISA # define ISA_DMA_BIT_MASK DMA_BIT_MASK(24) @@ -61,6 +62,9 @@ extern int dma_set_mask(struct device *dev, u64 mask); extern void *dma_generic_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, gfp_t flag);

+extern void dma_generic_free_coherent(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_addr); + static inline bool dma_capable(struct device *dev, dma_addr_t addr, size_t size) { if (!dev->dma_mask) diff --git a/arch/x86/kernel/pci-dma.c b/arch/x86/kernel/pci-dma.c index 1c4d769..d3c3723 100644 --- a/arch/x86/kernel/pci-dma.c +++ b/arch/x86/kernel/pci-dma.c @@ -99,14 +99,18 @@ void *dma_generic_alloc_coherent(struct device *dev, size_t size, dma_addr_t *dma_addr, gfp_t flag) { unsigned long dma_mask; - struct page *page; + struct page *page = NULL; + unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; dma_addr_t addr;

dma_mask = dma_alloc_coherent_mask(dev, flag);

flag |= __GFP_ZERO; again: - page = alloc_pages_node(dev_to_node(dev), flag, get_order(size)); + if (!(flag & GFP_ATOMIC)) + page = dma_alloc_from_contiguous(dev, count, get_order(size)); + if (!page) + page = alloc_pages_node(dev_to_node(dev), flag, get_order(size)); if (!page) return NULL;

@@ -126,6 +130,16 @@ again: return page_address(page); }

+void dma_generic_free_coherent(struct device *dev, size_t size, void *vaddr, + dma_addr_t dma_addr) +{ + unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; + struct page *page = virt_to_page(vaddr); + + if (!dma_release_from_contiguous(dev, page, count)) + free_pages((unsigned long)vaddr, get_order(size)); +} + /* * See <Documentation/x86/x86_64/boot-options.txt> for the iommu kernel * parameter documentation. diff --git a/arch/x86/kernel/pci-nommu.c b/arch/x86/kernel/pci-nommu.c index 3af4af8..656566f 100644 --- a/arch/x86/kernel/pci-nommu.c +++ b/arch/x86/kernel/pci-nommu.c @@ -74,12 +74,6 @@ static int nommu_map_sg(struct device *hwdev, struct scatterlist *sg, return nents; }

-static void nommu_free_coherent(struct device *dev, size_t size, void *vaddr, - dma_addr_t dma_addr) -{ - free_pages((unsigned long)vaddr, get_order(size)); -} - static void nommu_sync_single_for_device(struct device *dev, dma_addr_t addr, size_t size, enum dma_data_direction dir) @@ -97,7 +91,7 @@ static void nommu_sync_sg_for_device(struct device *dev,

struct dma_map_ops nommu_dma_ops = { .alloc_coherent = dma_generic_alloc_coherent, - .free_coherent = nommu_free_coherent, + .free_coherent = dma_generic_free_coherent, .map_sg = nommu_map_sg, .map_page = nommu_map_page, .sync_single_for_device = nommu_sync_single_for_device, diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c index d7d5099..be6795f 100644 --- a/arch/x86/kernel/setup.c +++ b/arch/x86/kernel/setup.c @@ -50,6 +50,7 @@ #include <asm/pci-direct.h> #include <linux/init_ohci1394_dma.h> #include <linux/kvm_para.h> +#include <linux/dma-contiguous.h>

#include <linux/errno.h> #include <linux/kernel.h> @@ -938,6 +939,7 @@ void __init setup_arch(char **cmdline_p) } #endif memblock.current_limit = get_max_mapped(); + dma_contiguous_reserve(0);

/* * NOTE: On x86-32, only from this point on, fixmaps are ready for use.

Replace custom memory bank initialization using memblock_reserve and dma_declare_coherent with a single call to CMA's dma_declare_contiguous.

Signed-off-by: Marek Szyprowski m.szyprowski@samsung.com Signed-off-by: Kyungmin Park kyungmin.park@samsung.com Acked-by: Arnd Bergmann arnd@arndb.de --- arch/arm/plat-s5p/dev-mfc.c | 51 ++++++------------------------------------- 1 files changed, 7 insertions(+), 44 deletions(-)

diff --git a/arch/arm/plat-s5p/dev-mfc.c b/arch/arm/plat-s5p/dev-mfc.c index a30d36b..fcb8400 100644 --- a/arch/arm/plat-s5p/dev-mfc.c +++ b/arch/arm/plat-s5p/dev-mfc.c @@ -14,6 +14,7 @@ #include <linux/interrupt.h> #include <linux/platform_device.h> #include <linux/dma-mapping.h> +#include <linux/dma-contiguous.h> #include <linux/memblock.h> #include <linux/ioport.h>

@@ -22,52 +23,14 @@ #include <plat/irqs.h> #include <plat/mfc.h>

-struct s5p_mfc_reserved_mem { - phys_addr_t base; - unsigned long size; - struct device *dev; -}; - -static struct s5p_mfc_reserved_mem s5p_mfc_mem[2] __initdata; - void __init s5p_mfc_reserve_mem(phys_addr_t rbase, unsigned int rsize, phys_addr_t lbase, unsigned int lsize) { - int i; - - s5p_mfc_mem[0].dev = &s5p_device_mfc_r.dev; - s5p_mfc_mem[0].base = rbase; - s5p_mfc_mem[0].size = rsize; - - s5p_mfc_mem[1].dev = &s5p_device_mfc_l.dev; - s5p_mfc_mem[1].base = lbase; - s5p_mfc_mem[1].size = lsize; - - for (i = 0; i < ARRAY_SIZE(s5p_mfc_mem); i++) { - struct s5p_mfc_reserved_mem *area = &s5p_mfc_mem[i]; - if (memblock_remove(area->base, area->size)) { - printk(KERN_ERR "Failed to reserve memory for MFC device (%ld bytes at 0x%08lx)\n", - area->size, (unsigned long) area->base); - area->base = 0; - } - } -} - -static int __init s5p_mfc_memory_init(void) -{ - int i; - - for (i = 0; i < ARRAY_SIZE(s5p_mfc_mem); i++) { - struct s5p_mfc_reserved_mem *area = &s5p_mfc_mem[i]; - if (!area->base) - continue; + if (dma_declare_contiguous(&s5p_device_mfc_r.dev, rsize, rbase, 0)) + printk(KERN_ERR "Failed to reserve memory for MFC device (%u bytes at 0x%08lx)\n", + rsize, (unsigned long) rbase);

- if (dma_declare_coherent_memory(area->dev, area->base, - area->base, area->size, - DMA_MEMORY_MAP | DMA_MEMORY_EXCLUSIVE) == 0) - printk(KERN_ERR "Failed to declare coherent memory for MFC device (%ld bytes at 0x%08lx)\n", - area->size, (unsigned long) area->base); - } - return 0; + if (dma_declare_contiguous(&s5p_device_mfc_l.dev, lsize, lbase, 0)) + printk(KERN_ERR "Failed to reserve memory for MFC device (%u bytes at 0x%08lx)\n", + rsize, (unsigned long) rbase); } -device_initcall(s5p_mfc_memory_init);