A migrating transparent huge page has to already be unmapped. Otherwise, the page could be modified while it is being copied to a new page and data could be lost. The function __split_huge_pmd() checks for a PMD migration entry before calling __split_huge_pmd_locked() leading one to think that __split_huge_pmd_locked() can handle splitting a migrating PMD. However, the code always increments the page->_mapcount and adjusts the memory control group accounting assuming the page is mapped. Also, if the PMD entry is a migration PMD entry, the call to is_huge_zero_pmd(*pmd) is incorrect because it calls pmd_pfn(pmd) instead of migration_entry_to_pfn(pmd_to_swp_entry(pmd)). Fix these problems by checking for a PMD migration entry.

Signed-off-by: Ralph Campbell rcampbell@nvidia.com --- mm/huge_memory.c | 42 +++++++++++++++++++++++------------------- 1 file changed, 23 insertions(+), 19 deletions(-)

diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 2a468a4acb0a..606d712d9505 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2023,7 +2023,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, put_page(page); add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR); return; - } else if (is_huge_zero_pmd(*pmd)) { + } else if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) { /* * FIXME: Do we want to invalidate secondary mmu by calling * mmu_notifier_invalidate_range() see comments below inside @@ -2117,30 +2117,34 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, pte = pte_offset_map(&_pmd, addr); BUG_ON(!pte_none(*pte)); set_pte_at(mm, addr, pte, entry); - atomic_inc(&page[i]._mapcount); - pte_unmap(pte); - } - - /* - * Set PG_double_map before dropping compound_mapcount to avoid - * false-negative page_mapped(). - */ - if (compound_mapcount(page) > 1 && !TestSetPageDoubleMap(page)) { - for (i = 0; i < HPAGE_PMD_NR; i++) + if (!pmd_migration) atomic_inc(&page[i]._mapcount); + pte_unmap(pte); }

- lock_page_memcg(page); - if (atomic_add_negative(-1, compound_mapcount_ptr(page))) { - /* Last compound_mapcount is gone. */ - __dec_lruvec_page_state(page, NR_ANON_THPS); - if (TestClearPageDoubleMap(page)) { - /* No need in mapcount reference anymore */ + if (!pmd_migration) { + /* + * Set PG_double_map before dropping compound_mapcount to avoid + * false-negative page_mapped(). + */ + if (compound_mapcount(page) > 1 && + !TestSetPageDoubleMap(page)) { for (i = 0; i < HPAGE_PMD_NR; i++) - atomic_dec(&page[i]._mapcount); + atomic_inc(&page[i]._mapcount); + } + + lock_page_memcg(page); + if (atomic_add_negative(-1, compound_mapcount_ptr(page))) { + /* Last compound_mapcount is gone. */ + __dec_lruvec_page_state(page, NR_ANON_THPS); + if (TestClearPageDoubleMap(page)) { + /* No need in mapcount reference anymore */ + for (i = 0; i < HPAGE_PMD_NR; i++) + atomic_dec(&page[i]._mapcount); + } } + unlock_page_memcg(page); } - unlock_page_memcg(page);

smp_wmb(); /* make pte visible before pmd */ pmd_populate(mm, pmd, pgtable);

Support transparent huge page migration to ZONE_DEVICE private memory. A new selection flag (MIGRATE_VMA_SELECT_COMPOUND) is added to request THP migration. Otherwise, THPs are split when filling in the source PFN array. A new flag (MIGRATE_PFN_COMPOUND) is added to the source PFN array to indicate a huge page can be migrated. If the device driver can allocate a huge page, it sets the MIGRATE_PFN_COMPOUND flag in the destination PFN array. migrate_vma_pages() will fallback to PAGE_SIZE pages if MIGRATE_PFN_COMPOUND is not set in both source and destination arrays.

Signed-off-by: Ralph Campbell rcampbell@nvidia.com --- include/linux/huge_mm.h | 7 + include/linux/memremap.h | 9 + include/linux/migrate.h | 2 + mm/huge_memory.c | 113 ++++++++--- mm/memory.c | 10 +- mm/migrate.c | 413 ++++++++++++++++++++++++++++++++------- mm/rmap.c | 2 +- 7 files changed, 459 insertions(+), 97 deletions(-)

diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h index 8a8bc46a2432..87b42c81dedc 100644 --- a/include/linux/huge_mm.h +++ b/include/linux/huge_mm.h @@ -192,6 +192,8 @@ bool is_transparent_hugepage(struct page *page);

bool can_split_huge_page(struct page *page, int *pextra_pins); int split_huge_page_to_list(struct page *page, struct list_head *list); +int split_migrating_huge_page(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long address, struct page *page); static inline int split_huge_page(struct page *page) { return split_huge_page_to_list(page, NULL); @@ -454,6 +456,11 @@ static inline bool is_huge_zero_page(struct page *page) return false; }

+static inline bool is_huge_zero_pmd(pmd_t pmd) +{ + return false; +} + static inline bool is_huge_zero_pud(pud_t pud) { return false; diff --git a/include/linux/memremap.h b/include/linux/memremap.h index 4e9c738f4b31..5175b1eaea01 100644 --- a/include/linux/memremap.h +++ b/include/linux/memremap.h @@ -88,6 +88,15 @@ struct dev_pagemap_ops { * the page back to a CPU accessible page. */ vm_fault_t (*migrate_to_ram)(struct vm_fault *vmf); + + /* + * Used for private (un-addressable) device memory only. + * This is called when a compound device private page is split. + * The driver uses this callback to set tail_page->pgmap and + * tail_page->zone_device_data appropriately based on the head + * page. + */ + void (*page_split)(struct page *head, struct page *tail_page); };

#define PGMAP_ALTMAP_VALID (1 << 0) diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 0f8d1583fa8e..92179bf360d1 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -144,6 +144,7 @@ static inline int migrate_misplaced_transhuge_page(struct mm_struct *mm, #define MIGRATE_PFN_MIGRATE (1UL << 1) #define MIGRATE_PFN_LOCKED (1UL << 2) #define MIGRATE_PFN_WRITE (1UL << 3) +#define MIGRATE_PFN_COMPOUND (1UL << 4) #define MIGRATE_PFN_SHIFT 6

static inline struct page *migrate_pfn_to_page(unsigned long mpfn) @@ -161,6 +162,7 @@ static inline unsigned long migrate_pfn(unsigned long pfn) enum migrate_vma_direction { MIGRATE_VMA_SELECT_SYSTEM = 1 << 0, MIGRATE_VMA_SELECT_DEVICE_PRIVATE = 1 << 1, + MIGRATE_VMA_SELECT_COMPOUND = 1 << 2, };

struct migrate_vma { diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 606d712d9505..a8d48994481a 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1644,23 +1644,35 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, } else { struct page *page = NULL; int flush_needed = 1; + bool is_anon = false;

if (pmd_present(orig_pmd)) { page = pmd_page(orig_pmd); + is_anon = PageAnon(page); page_remove_rmap(page, true); VM_BUG_ON_PAGE(page_mapcount(page) < 0, page); VM_BUG_ON_PAGE(!PageHead(page), page); } else if (thp_migration_supported()) { swp_entry_t entry;

- VM_BUG_ON(!is_pmd_migration_entry(orig_pmd)); entry = pmd_to_swp_entry(orig_pmd); - page = pfn_to_page(swp_offset(entry)); + if (is_device_private_entry(entry)) { + page = device_private_entry_to_page(entry); + is_anon = PageAnon(page); + page_remove_rmap(page, true); + VM_BUG_ON_PAGE(page_mapcount(page) < 0, page); + VM_BUG_ON_PAGE(!PageHead(page), page); + put_page(page); + } else { + VM_BUG_ON(!is_pmd_migration_entry(orig_pmd)); + page = pfn_to_page(swp_offset(entry)); + is_anon = PageAnon(page); + } flush_needed = 0; } else WARN_ONCE(1, "Non present huge pmd without pmd migration enabled!");

- if (PageAnon(page)) { + if (is_anon) { zap_deposited_table(tlb->mm, pmd); add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR); } else { @@ -2320,9 +2332,10 @@ static void remap_page(struct page *page) }

static void __split_huge_page_tail(struct page *head, int tail, - struct lruvec *lruvec, struct list_head *list) + struct lruvec *lruvec, struct list_head *list, bool remap) { struct page *page_tail = head + tail; + int pin_count;

VM_BUG_ON_PAGE(atomic_read(&page_tail->_mapcount) != -1, page_tail);

@@ -2360,10 +2373,17 @@ static void __split_huge_page_tail(struct page *head, int tail, * After successful get_page_unless_zero() might follow put_page() * which needs correct compound_head(). */ - clear_compound_head(page_tail); + if (is_device_private_page(head)) { + /* Restore page_tail->pgmap and page_tail->zone_device_data. */ + head->pgmap->ops->page_split(head, page_tail); + pin_count = 2; + } else { + clear_compound_head(page_tail); + pin_count = 1; + }

/* Finally unfreeze refcount. Additional reference from page cache. */ - page_ref_unfreeze(page_tail, 1 + (!PageAnon(head) || + page_ref_unfreeze(page_tail, pin_count + (!PageAnon(head) || PageSwapCache(head)));

if (page_is_young(head)) @@ -2378,11 +2398,12 @@ static void __split_huge_page_tail(struct page *head, int tail, * pages to show after the currently processed elements - e.g. * migrate_pages */ - lru_add_page_tail(head, page_tail, lruvec, list); + if (remap) + lru_add_page_tail(head, page_tail, lruvec, list); }

static void __split_huge_page(struct page *page, struct list_head *list, - pgoff_t end, unsigned long flags) + pgoff_t end, unsigned long flags, bool remap) { struct page *head = compound_head(page); pg_data_t *pgdat = page_pgdat(head); @@ -2405,7 +2426,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, }

for (i = HPAGE_PMD_NR - 1; i >= 1; i--) { - __split_huge_page_tail(head, i, lruvec, list); + __split_huge_page_tail(head, i, lruvec, list, remap); /* Some pages can be beyond i_size: drop them from page cache */ if (head[i].index >= end) { ClearPageDirty(head + i); @@ -2432,6 +2453,8 @@ static void __split_huge_page(struct page *page, struct list_head *list, if (PageSwapCache(head)) { page_ref_add(head, 2); xa_unlock(&swap_cache->i_pages); + } else if (is_device_private_page(head)) { + page_ref_add(head, 2); } else { page_ref_inc(head); } @@ -2443,6 +2466,9 @@ static void __split_huge_page(struct page *page, struct list_head *list,

spin_unlock_irqrestore(&pgdat->lru_lock, flags);

+ if (!remap) + return; + remap_page(head);

for (i = 0; i < HPAGE_PMD_NR; i++) { @@ -2577,7 +2603,8 @@ bool can_split_huge_page(struct page *page, int *pextra_pins) * Returns -EBUSY if the page is pinned or if anon_vma disappeared from under * us. */ -int split_huge_page_to_list(struct page *page, struct list_head *list) +static int __split_huge_page_to_list(struct page *page, struct list_head *list, + bool remap) { struct page *head = compound_head(page); struct pglist_data *pgdata = NODE_DATA(page_to_nid(head)); @@ -2590,7 +2617,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)

VM_BUG_ON_PAGE(is_huge_zero_page(head), head); VM_BUG_ON_PAGE(!PageLocked(head), head); - VM_BUG_ON_PAGE(!PageCompound(head), head); + VM_BUG_ON_PAGE(!PageHead(head), head);

if (PageWriteback(head)) return -EBUSY; @@ -2604,14 +2631,16 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) * is taken to serialise against parallel split or collapse * operations. */ - anon_vma = page_get_anon_vma(head); - if (!anon_vma) { - ret = -EBUSY; - goto out; + if (remap) { + anon_vma = page_get_anon_vma(head); + if (!anon_vma) { + ret = -EBUSY; + goto out; + } + anon_vma_lock_write(anon_vma); } end = -1; mapping = NULL; - anon_vma_lock_write(anon_vma); } else { mapping = head->mapping;

@@ -2637,13 +2666,18 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) /* * Racy check if we can split the page, before unmap_page() will * split PMDs + * If we are splitting a migrating THP, there is no check needed + * because the page is already unmapped and isolated from the LRU. */ - if (!can_split_huge_page(head, &extra_pins)) { + if (!remap) + extra_pins = HPAGE_PMD_NR - 1 + is_device_private_page(head); + else if (!can_split_huge_page(head, &extra_pins)) { ret = -EBUSY; goto out_unlock; }

- unmap_page(head); + if (remap) + unmap_page(head); VM_BUG_ON_PAGE(compound_mapcount(head), head);

/* prevent PageLRU to go away from under us, and freeze lru stats */ @@ -2668,7 +2702,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) if (!mapcount && page_ref_freeze(head, 1 + extra_pins)) { if (!list_empty(page_deferred_list(head))) { ds_queue->split_queue_len--; - list_del(page_deferred_list(head)); + list_del_init(page_deferred_list(head)); } spin_unlock(&ds_queue->split_queue_lock); if (mapping) { @@ -2678,7 +2712,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) __dec_node_page_state(head, NR_FILE_THPS); }

- __split_huge_page(page, list, end, flags); + __split_huge_page(page, list, end, flags, remap); if (PageSwapCache(head)) { swp_entry_t entry = { .val = page_private(head) };

@@ -2698,7 +2732,8 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) fail: if (mapping) xa_unlock(&mapping->i_pages); spin_unlock_irqrestore(&pgdata->lru_lock, flags); - remap_page(head); + if (remap) + remap_page(head); ret = -EBUSY; }

@@ -2714,6 +2749,36 @@ fail: if (mapping) return ret; }

+int split_huge_page_to_list(struct page *page, struct list_head *list) +{ + return __split_huge_page_to_list(page, list, true); +} + +/* + * Split a migrating huge page. + * The caller should have mmap_lock_read() held, the huge page unmapped and + * isolated, and the PMD page table entry set to a migration entry for the + * given head page. + */ +int split_migrating_huge_page(struct vm_area_struct *vma, pmd_t *pmd, + unsigned long address, struct page *head) +{ + spinlock_t *ptl; + + VM_BUG_ON_PAGE(is_huge_zero_page(head), head); + VM_BUG_ON_PAGE(!PageLocked(head), head); + VM_BUG_ON_PAGE(!PageHead(head), head); + VM_BUG_ON_PAGE(PageWriteback(head), head); + VM_BUG_ON_PAGE(PageLRU(head), head); + VM_BUG_ON_PAGE(compound_mapcount(head), head); + + ptl = pmd_lock(vma->vm_mm, pmd); + __split_huge_pmd_locked(vma, pmd, address, false); + spin_unlock(ptl); + + return __split_huge_page_to_list(head, NULL, false); +} + void free_transhuge_page(struct page *page) { struct deferred_split *ds_queue = get_deferred_split_queue(page); @@ -2722,7 +2787,7 @@ void free_transhuge_page(struct page *page) spin_lock_irqsave(&ds_queue->split_queue_lock, flags); if (!list_empty(page_deferred_list(page))) { ds_queue->split_queue_len--; - list_del(page_deferred_list(page)); + list_del_init(page_deferred_list(page)); } spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags); free_compound_page(page); @@ -2942,6 +3007,10 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new) pmde = pmd_mksoft_dirty(pmde); if (is_write_migration_entry(entry)) pmde = maybe_pmd_mkwrite(pmde, vma); + if (unlikely(is_device_private_page(new))) { + entry = make_device_private_entry(new, pmd_write(pmde)); + pmde = swp_entry_to_pmd(entry); + }

flush_cache_range(vma, mmun_start, mmun_start + HPAGE_PMD_SIZE); if (PageAnon(new)) diff --git a/mm/memory.c b/mm/memory.c index fb5463153351..81fcf5101fc6 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -4346,9 +4346,15 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,

barrier(); if (unlikely(is_swap_pmd(orig_pmd))) { + swp_entry_t entry = pmd_to_swp_entry(orig_pmd); + + if (is_device_private_entry(entry)) { + vmf.page = device_private_entry_to_page(entry); + return vmf.page->pgmap->ops->migrate_to_ram(&vmf); + } VM_BUG_ON(thp_migration_supported() && - !is_pmd_migration_entry(orig_pmd)); - if (is_pmd_migration_entry(orig_pmd)) + !is_migration_entry(entry)); + if (is_migration_entry(entry)) pmd_migration_entry_wait(mm, vmf.pmd); return 0; } diff --git a/mm/migrate.c b/mm/migrate.c index ce16ed3deab6..139844534dd8 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -51,6 +51,7 @@ #include <linux/oom.h>

#include <asm/tlbflush.h> +#include <asm/pgalloc.h>

#define CREATE_TRACE_POINTS #include <trace/events/migrate.h> @@ -2276,19 +2277,28 @@ static int migrate_vma_collect_hole(unsigned long start, { struct migrate_vma *migrate = walk->private; unsigned long addr; + unsigned long mpfn;

/* Only allow populating anonymous memory. */ - if (!vma_is_anonymous(walk->vma)) { - for (addr = start; addr < end; addr += PAGE_SIZE) { - migrate->src[migrate->npages] = 0; - migrate->dst[migrate->npages] = 0; - migrate->npages++; - } - return 0; + if (!vma_is_anonymous(walk->vma) || + !((migrate->flags & MIGRATE_VMA_SELECT_SYSTEM))) + return migrate_vma_collect_skip(start, end, walk); + + if (thp_migration_supported() && + (migrate->flags & MIGRATE_VMA_SELECT_COMPOUND) && + (start & ~PMD_MASK) == 0 && (end & ~PMD_MASK) == 0) { + migrate->src[migrate->npages] = MIGRATE_PFN_MIGRATE | + MIGRATE_PFN_COMPOUND; + migrate->dst[migrate->npages] = 0; + migrate->npages++; + migrate->cpages++; + return migrate_vma_collect_skip(start + PAGE_SIZE, end, walk); }

+ mpfn = (migrate->vma->vm_flags & VM_WRITE) ? + (MIGRATE_PFN_MIGRATE | MIGRATE_PFN_WRITE) : MIGRATE_PFN_MIGRATE; for (addr = start; addr < end; addr += PAGE_SIZE) { - migrate->src[migrate->npages] = MIGRATE_PFN_MIGRATE; + migrate->src[migrate->npages] = mpfn; migrate->dst[migrate->npages] = 0; migrate->npages++; migrate->cpages++; @@ -2297,59 +2307,133 @@ static int migrate_vma_collect_hole(unsigned long start, return 0; }

-static int migrate_vma_collect_pmd(pmd_t *pmdp, - unsigned long start, - unsigned long end, - struct mm_walk *walk) +static int migrate_vma_handle_pmd(pmd_t *pmdp, unsigned long start, + unsigned long end, struct mm_walk *walk) { struct migrate_vma *migrate = walk->private; struct vm_area_struct *vma = walk->vma; struct mm_struct *mm = vma->vm_mm; - unsigned long addr = start, unmapped = 0; spinlock_t *ptl; - pte_t *ptep; + struct page *page; + unsigned long write = 0; + int ret;

-again: - if (pmd_none(*pmdp)) + ptl = pmd_lock(mm, pmdp); + if (pmd_none(*pmdp)) { + spin_unlock(ptl); return migrate_vma_collect_hole(start, end, -1, walk); - + } if (pmd_trans_huge(*pmdp)) { - struct page *page; - - ptl = pmd_lock(mm, pmdp); - if (unlikely(!pmd_trans_huge(*pmdp))) { + if (!(migrate->flags & MIGRATE_VMA_SELECT_SYSTEM)) { spin_unlock(ptl); - goto again; + return migrate_vma_collect_skip(start, end, walk); } - page = pmd_page(*pmdp); if (is_huge_zero_page(page)) { spin_unlock(ptl); - split_huge_pmd(vma, pmdp, addr); - if (pmd_trans_unstable(pmdp)) - return migrate_vma_collect_skip(start, end, - walk); - } else { - int ret; + return migrate_vma_collect_hole(start, end, -1, walk); + } + if (pmd_write(*pmdp)) + write = MIGRATE_PFN_WRITE; + } else if (!pmd_present(*pmdp)) { + swp_entry_t entry = pmd_to_swp_entry(*pmdp); + + if (is_migration_entry(entry)) { + bool wait;

- get_page(page); + page = migration_entry_to_page(entry); + wait = get_page_unless_zero(page); spin_unlock(ptl); - if (unlikely(!trylock_page(page))) - return migrate_vma_collect_skip(start, end, - walk); - ret = split_huge_page(page); - unlock_page(page); - put_page(page); - if (ret) - return migrate_vma_collect_skip(start, end, - walk); - if (pmd_none(*pmdp)) - return migrate_vma_collect_hole(start, end, -1, - walk); + if (wait) + put_and_wait_on_page_locked(page); + return -EAGAIN; + } + if (!is_device_private_entry(entry)) { + spin_unlock(ptl); + return migrate_vma_collect_skip(start, end, walk); + } + page = device_private_entry_to_page(entry); + if (!(migrate->flags & MIGRATE_VMA_SELECT_DEVICE_PRIVATE) || + page->pgmap->owner != migrate->pgmap_owner) { + spin_unlock(ptl); + return migrate_vma_collect_skip(start, end, walk); } + if (is_write_device_private_entry(entry)) + write = MIGRATE_PFN_WRITE; + } else { + spin_unlock(ptl); + return -EAGAIN; + } + + get_page(page); + if (unlikely(!trylock_page(page))) { + spin_unlock(ptl); + put_page(page); + return migrate_vma_collect_skip(start, end, walk); + } + if (thp_migration_supported() && + (migrate->flags & MIGRATE_VMA_SELECT_COMPOUND) && + (start & ~PMD_MASK) == 0 && (start + PMD_SIZE) == end) { + struct page_vma_mapped_walk vmw = { + .vma = vma, + .address = start, + .pmd = pmdp, + .ptl = ptl, + }; + + migrate->src[migrate->npages] = write | + migrate_pfn(page_to_pfn(page)) | + MIGRATE_PFN_MIGRATE | MIGRATE_PFN_LOCKED | + MIGRATE_PFN_COMPOUND; + migrate->dst[migrate->npages] = 0; + migrate->npages++; + migrate->cpages++; + migrate_vma_collect_skip(start + PAGE_SIZE, end, walk); + + /* Note this also removes the page from the rmap. */ + set_pmd_migration_entry(&vmw, page); + spin_unlock(ptl); + + return 0; + } + spin_unlock(ptl); + + ret = split_huge_page(page); + unlock_page(page); + put_page(page); + + if (ret) + return migrate_vma_collect_skip(start, end, walk); + if (pmd_none(*pmdp)) + return migrate_vma_collect_hole(start, end, -1, walk); + + /* This just causes migrate_vma_collect_pmd() to handle PTEs. */ + return -ENOENT; +} + +static int migrate_vma_collect_pmd(pmd_t *pmdp, + unsigned long start, + unsigned long end, + struct mm_walk *walk) +{ + struct migrate_vma *migrate = walk->private; + struct vm_area_struct *vma = walk->vma; + struct mm_struct *mm = vma->vm_mm; + unsigned long addr = start, unmapped = 0; + spinlock_t *ptl; + pte_t *ptep; + +again: + if (pmd_trans_huge(*pmdp) || !pmd_present(*pmdp)) { + int ret = migrate_vma_handle_pmd(pmdp, start, end, walk); + + if (!ret) + return 0; + if (ret == -EAGAIN) + goto again; }

- if (unlikely(pmd_bad(*pmdp))) + if (unlikely(pmd_bad(*pmdp) || pmd_devmap(*pmdp))) return migrate_vma_collect_skip(start, end, walk);

ptep = pte_offset_map_lock(mm, pmdp, addr, &ptl); @@ -2405,8 +2489,7 @@ static int migrate_vma_collect_pmd(pmd_t *pmdp, mpfn |= pte_write(pte) ? MIGRATE_PFN_WRITE : 0; }

- /* FIXME support THP */ - if (!page || !page->mapping || PageTransCompound(page)) { + if (!page || !page->mapping) { mpfn = 0; goto next; } @@ -2528,14 +2611,6 @@ static bool migrate_vma_check_page(struct page *page) */ int extra = 1;

- /* - * FIXME support THP (transparent huge page), it is bit more complex to - * check them than regular pages, because they can be mapped with a pmd - * or with a pte (split pte mapping). - */ - if (PageCompound(page)) - return false; - /* Page from ZONE_DEVICE have one extra reference */ if (is_zone_device_page(page)) { /* @@ -2834,13 +2909,191 @@ int migrate_vma_setup(struct migrate_vma *args) } EXPORT_SYMBOL(migrate_vma_setup);

+static pmd_t *find_pmd(struct mm_struct *mm, unsigned long addr) +{ + pgd_t *pgdp; + p4d_t *p4dp; + pud_t *pudp; + + pgdp = pgd_offset(mm, addr); + p4dp = p4d_alloc(mm, pgdp, addr); + if (!p4dp) + return NULL; + pudp = pud_alloc(mm, p4dp, addr); + if (!pudp) + return NULL; + return pmd_alloc(mm, pudp, addr); +} + +#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION +/* + * This code closely follows: + * do_huge_pmd_anonymous_page() + * __do_huge_pmd_anonymous_page() + * except that the page being inserted is likely to be a device private page + * instead of an allocated or zero page. + */ +static int insert_huge_pmd_anonymous_page(struct vm_area_struct *vma, + unsigned long haddr, + struct page *page, + unsigned long *src, + pmd_t *pmdp) +{ + struct mm_struct *mm = vma->vm_mm; + unsigned int i; + spinlock_t *ptl; + bool flush = false; + pgtable_t pgtable; + gfp_t gfp; + pmd_t entry; + + if (WARN_ON_ONCE(compound_order(page) != HPAGE_PMD_ORDER)) + goto abort; + + if (unlikely(anon_vma_prepare(vma))) + goto abort; + + prep_transhuge_page(page); + + gfp = GFP_TRANSHUGE_LIGHT; + if (mem_cgroup_charge(page, mm, gfp)) + goto abort; + + pgtable = pte_alloc_one(mm); + if (unlikely(!pgtable)) + goto abort; + + __SetPageUptodate(page); + + if (is_zone_device_page(page)) { + if (!is_device_private_page(page)) + goto pgtable_abort; + entry = swp_entry_to_pmd(make_device_private_entry(page, + vma->vm_flags & VM_WRITE)); + } else { + entry = mk_huge_pmd(page, vma->vm_page_prot); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + } + + ptl = pmd_lock(mm, pmdp); + + if (check_stable_address_space(mm)) + goto unlock_abort; + + /* + * Check for userfaultfd but do not deliver the fault. Instead, + * just back off. + */ + if (userfaultfd_missing(vma)) + goto unlock_abort; + + if (pmd_present(*pmdp)) { + if (!is_huge_zero_pmd(*pmdp)) + goto unlock_abort; + flush = true; + } else if (!pmd_none(*pmdp)) + goto unlock_abort; + + get_page(page); + page_add_new_anon_rmap(page, vma, haddr, true); + if (!is_zone_device_page(page)) + lru_cache_add_inactive_or_unevictable(page, vma); + if (flush) { + pte_free(mm, pgtable); + flush_cache_range(vma, haddr, haddr + HPAGE_PMD_SIZE); + pmdp_invalidate(vma, haddr, pmdp); + } else { + pgtable_trans_huge_deposit(mm, pmdp, pgtable); + mm_inc_nr_ptes(mm); + } + set_pmd_at(mm, haddr, pmdp, entry); + update_mmu_cache_pmd(vma, haddr, pmdp); + add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR); + spin_unlock(ptl); + count_vm_event(THP_FAULT_ALLOC); + count_memcg_event_mm(mm, THP_FAULT_ALLOC); + + return 0; + +unlock_abort: + spin_unlock(ptl); +pgtable_abort: + pte_free(mm, pgtable); +abort: + for (i = 0; i < HPAGE_PMD_NR; i++) + src[i] &= ~MIGRATE_PFN_MIGRATE; + return -EINVAL; +} + +static void migrate_vma_split(struct migrate_vma *migrate, unsigned long i, + unsigned long addr) +{ + const unsigned long npages = i + HPAGE_PMD_NR; + unsigned long mpfn; + unsigned long j; + bool migrating = false; + struct page *page; + + migrate->src[i] &= ~MIGRATE_PFN_COMPOUND; + + /* If no part of the THP is migrating, we can skip splitting. */ + for (j = i; j < npages; j++) { + if (migrate->dst[j] & MIGRATE_PFN_VALID) { + migrating = true; + break; + } + } + if (!migrating) + return; + + mpfn = migrate->src[i]; + page = migrate_pfn_to_page(mpfn); + if (page) { + pmd_t *pmdp; + int ret; + + pmdp = find_pmd(migrate->vma->vm_mm, addr); + if (!pmdp) { + migrate->src[i] = mpfn & ~MIGRATE_PFN_MIGRATE; + return; + } + ret = split_migrating_huge_page(migrate->vma, pmdp, addr, page); + if (ret) { + migrate->src[i] = mpfn & ~MIGRATE_PFN_MIGRATE; + return; + } + while (++i < npages) { + mpfn += 1UL << MIGRATE_PFN_SHIFT; + migrate->src[i] = mpfn; + } + } else { + while (++i < npages) + migrate->src[i] = mpfn; + } +} +#else +static int insert_huge_pmd_anonymous_page(struct vm_area_struct *vma, + unsigned long haddr, + struct page *page, + unsigned long *src, + pmd_t *pmdp) +{ + return 0; +} + +static void migrate_vma_split(struct migrate_vma *migrate, unsigned long i, + unsigned long addr) +{ +} +#endif + /* * This code closely matches the code in: * __handle_mm_fault() * handle_pte_fault() * do_anonymous_page() - * to map in an anonymous zero page but the struct page will be a ZONE_DEVICE - * private page. + * to map in an anonymous zero page except the struct page is already allocated + * and will likely be a ZONE_DEVICE private page. */ static void migrate_vma_insert_page(struct migrate_vma *migrate, unsigned long addr, @@ -2853,9 +3106,6 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, bool flush = false; spinlock_t *ptl; pte_t entry; - pgd_t *pgdp; - p4d_t *p4dp; - pud_t *pudp; pmd_t *pmdp; pte_t *ptep;

@@ -2863,19 +3113,25 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, if (!vma_is_anonymous(vma)) goto abort;

- pgdp = pgd_offset(mm, addr); - p4dp = p4d_alloc(mm, pgdp, addr); - if (!p4dp) - goto abort; - pudp = pud_alloc(mm, p4dp, addr); - if (!pudp) - goto abort; - pmdp = pmd_alloc(mm, pudp, addr); + pmdp = find_pmd(migrate->vma->vm_mm, addr); if (!pmdp) goto abort;

- if (pmd_trans_huge(*pmdp) || pmd_devmap(*pmdp)) - goto abort; + if (thp_migration_supported() && *dst & MIGRATE_PFN_COMPOUND) { + int ret = insert_huge_pmd_anonymous_page(vma, addr, page, src, + pmdp); + if (ret) + goto abort; + return; + } + if (!pmd_none(*pmdp)) { + if (pmd_trans_huge(*pmdp)) { + if (!is_huge_zero_pmd(*pmdp)) + goto abort; + __split_huge_pmd(vma, pmdp, addr, false, NULL); + } else if (pmd_leaf(*pmdp)) + goto abort; + }

/* * Use pte_alloc() instead of pte_alloc_map(). We can't run @@ -2910,9 +3166,11 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, if (is_device_private_page(page)) { swp_entry_t swp_entry;

- swp_entry = make_device_private_entry(page, vma->vm_flags & VM_WRITE); + swp_entry = make_device_private_entry(page, + vma->vm_flags & VM_WRITE); entry = swp_entry_to_pte(swp_entry); - } + } else + goto abort; } else { entry = mk_pte(page, vma->vm_page_prot); if (vma->vm_flags & VM_WRITE) @@ -2941,10 +3199,10 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, goto unlock_abort;

inc_mm_counter(mm, MM_ANONPAGES); + get_page(page); page_add_new_anon_rmap(page, vma, addr, false); if (!is_zone_device_page(page)) lru_cache_add_inactive_or_unevictable(page, vma); - get_page(page);

if (flush) { flush_cache_page(vma, addr, pte_pfn(*ptep)); @@ -2958,7 +3216,6 @@ static void migrate_vma_insert_page(struct migrate_vma *migrate, }

pte_unmap_unlock(ptep, ptl); - *src = MIGRATE_PFN_MIGRATE; return;

unlock_abort: @@ -2989,11 +3246,23 @@ void migrate_vma_pages(struct migrate_vma *migrate) struct address_space *mapping; int r;

+ /* + * If the caller didn't allocate a THP, split the PMD and + * fix up the src array. + */ + if (thp_migration_supported() && + (migrate->src[i] & MIGRATE_PFN_MIGRATE) && + (migrate->src[i] & MIGRATE_PFN_COMPOUND) && + !(migrate->dst[i] & MIGRATE_PFN_COMPOUND)) + migrate_vma_split(migrate, i, addr); + + newpage = migrate_pfn_to_page(migrate->dst[i]); if (!newpage) { migrate->src[i] &= ~MIGRATE_PFN_MIGRATE; continue; }

+ page = migrate_pfn_to_page(migrate->src[i]); if (!page) { if (!(migrate->src[i] & MIGRATE_PFN_MIGRATE)) continue; diff --git a/mm/rmap.c b/mm/rmap.c index 9425260774a1..4a4d24ea5008 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -1497,7 +1497,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, }

if (IS_ENABLED(CONFIG_MIGRATION) && - (flags & TTU_MIGRATION) && + (flags & (TTU_MIGRATION | TTU_SPLIT_FREEZE)) && is_zone_device_page(page)) { swp_entry_t entry; pte_t swp_pte;

Transparent huge page allocation policy is controlled by several sysfs variables. Rather than expose these to each device driver that needs to allocate THPs, provide a helper function.

Signed-off-by: Ralph Campbell rcampbell@nvidia.com --- include/linux/gfp.h | 10 ++++++++++ mm/huge_memory.c | 14 ++++++++++++++ 2 files changed, 24 insertions(+)

diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 67a0774e080b..6faf4ea5501b 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -562,6 +562,16 @@ extern struct page *alloc_pages_vma(gfp_t gfp_mask, int order, alloc_pages_vma(gfp_mask, 0, vma, addr, numa_node_id(), false) #define alloc_page_vma_node(gfp_mask, vma, addr, node) \ alloc_pages_vma(gfp_mask, 0, vma, addr, node, false) +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +extern struct page *alloc_transhugepage(struct vm_area_struct *vma, + unsigned long addr); +#else +static inline struct page *alloc_transhugepage(struct vm_area_struct *vma, + unsigned long addr) +{ + return NULL; +} +#endif

extern unsigned long __get_free_pages(gfp_t gfp_mask, unsigned int order); extern unsigned long get_zeroed_page(gfp_t gfp_mask); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 1e848cc0c3dc..e4e1fe199dc1 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -764,6 +764,20 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf) return __do_huge_pmd_anonymous_page(vmf, page, gfp); }

+struct page *alloc_transhugepage(struct vm_area_struct *vma, + unsigned long haddr) +{ + gfp_t gfp; + struct page *page; + + gfp = alloc_hugepage_direct_gfpmask(vma); + page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER); + if (page) + prep_transhuge_page(page); + return page; +} +EXPORT_SYMBOL_GPL(alloc_transhugepage); + static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr, pmd_t *pmd, pfn_t pfn, pgprot_t prot, bool write, pgtable_t pgtable)

Add support for migrating transparent huge pages to and from device private memory.

Signed-off-by: Ralph Campbell rcampbell@nvidia.com --- drivers/gpu/drm/nouveau/nouveau_dmem.c | 289 ++++++++++++++++++------- drivers/gpu/drm/nouveau/nouveau_svm.c | 11 +- drivers/gpu/drm/nouveau/nouveau_svm.h | 3 +- 3 files changed, 215 insertions(+), 88 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/nouveau_dmem.c b/drivers/gpu/drm/nouveau/nouveau_dmem.c index a13c6215bba8..78ad0ee77b3d 100644 --- a/drivers/gpu/drm/nouveau/nouveau_dmem.c +++ b/drivers/gpu/drm/nouveau/nouveau_dmem.c @@ -82,6 +82,7 @@ struct nouveau_dmem { struct list_head chunks; struct mutex mutex; struct page *free_pages; + struct page *free_huge_pages; spinlock_t lock; };

@@ -112,8 +113,13 @@ static void nouveau_dmem_page_free(struct page *page) struct nouveau_dmem *dmem = chunk->drm->dmem;

spin_lock(&dmem->lock); - page->zone_device_data = dmem->free_pages; - dmem->free_pages = page; + if (PageHead(page)) { + page->zone_device_data = dmem->free_huge_pages; + dmem->free_huge_pages = page; + } else { + page->zone_device_data = dmem->free_pages; + dmem->free_pages = page; + }

WARN_ON(!chunk->callocated); chunk->callocated--; @@ -139,51 +145,100 @@ static void nouveau_dmem_fence_done(struct nouveau_fence **fence)

static vm_fault_t nouveau_dmem_fault_copy_one(struct nouveau_drm *drm, struct vm_fault *vmf, struct migrate_vma *args, - dma_addr_t *dma_addr) + struct page *spage, bool is_huge, dma_addr_t *dma_addr) { + struct nouveau_svmm *svmm = spage->zone_device_data; struct device *dev = drm->dev->dev; - struct page *dpage, *spage; - struct nouveau_svmm *svmm; - - spage = migrate_pfn_to_page(args->src[0]); - if (!spage || !(args->src[0] & MIGRATE_PFN_MIGRATE)) - return 0; + struct page *dpage; + unsigned int i;

- dpage = alloc_page_vma(GFP_HIGHUSER, vmf->vma, vmf->address); + if (is_huge) + dpage = alloc_transhugepage(vmf->vma, args->start); + else + dpage = alloc_page_vma(GFP_HIGHUSER, vmf->vma, vmf->address); if (!dpage) - return VM_FAULT_SIGBUS; - lock_page(dpage); + return VM_FAULT_OOM; + WARN_ON_ONCE(compound_order(spage) != compound_order(dpage));

- *dma_addr = dma_map_page(dev, dpage, 0, PAGE_SIZE, DMA_BIDIRECTIONAL); + *dma_addr = dma_map_page(dev, dpage, 0, page_size(dpage), + DMA_BIDIRECTIONAL); if (dma_mapping_error(dev, *dma_addr)) goto error_free_page;

- svmm = spage->zone_device_data; + lock_page(dpage); + i = (vmf->address - args->start) >> PAGE_SHIFT; + spage += i; mutex_lock(&svmm->mutex); nouveau_svmm_invalidate(svmm, args->start, args->end); - if (drm->dmem->migrate.copy_func(drm, 1, NOUVEAU_APER_HOST, *dma_addr, - NOUVEAU_APER_VRAM, nouveau_dmem_page_addr(spage))) + if (drm->dmem->migrate.copy_func(drm, compound_nr(dpage), + NOUVEAU_APER_HOST, *dma_addr, NOUVEAU_APER_VRAM, + nouveau_dmem_page_addr(spage))) goto error_dma_unmap; mutex_unlock(&svmm->mutex);

- args->dst[0] = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; + args->dst[i] = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; + if (is_huge) + args->dst[i] |= MIGRATE_PFN_COMPOUND; return 0;

error_dma_unmap: mutex_unlock(&svmm->mutex); - dma_unmap_page(dev, *dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL); + unlock_page(dpage); + dma_unmap_page(dev, *dma_addr, page_size(dpage), DMA_BIDIRECTIONAL); error_free_page: __free_page(dpage); return VM_FAULT_SIGBUS; }

+static vm_fault_t nouveau_dmem_fault_chunk(struct nouveau_drm *drm, + struct vm_fault *vmf, struct migrate_vma *args) +{ + struct device *dev = drm->dev->dev; + struct nouveau_fence *fence; + struct page *spage; + unsigned long src = args->src[0]; + bool is_huge = (src & (MIGRATE_PFN_MIGRATE | MIGRATE_PFN_COMPOUND)) == + (MIGRATE_PFN_MIGRATE | MIGRATE_PFN_COMPOUND); + unsigned long dma_page_size; + dma_addr_t dma_addr; + vm_fault_t ret = 0; + + spage = migrate_pfn_to_page(src); + if (!spage) { + ret = VM_FAULT_SIGBUS; + goto out; + } + if (is_huge) { + dma_page_size = PMD_SIZE; + ret = nouveau_dmem_fault_copy_one(drm, vmf, args, spage, true, + &dma_addr); + if (!ret) + goto fence; + /* + * If we couldn't allocate a huge page, fallback to migrating + * a single page. + */ + } + dma_page_size = PAGE_SIZE; + ret = nouveau_dmem_fault_copy_one(drm, vmf, args, spage, false, + &dma_addr); + if (ret) + goto out; +fence: + nouveau_fence_new(drm->dmem->migrate.chan, false, &fence); + migrate_vma_pages(args); + nouveau_dmem_fence_done(&fence); + dma_unmap_page(dev, dma_addr, dma_page_size, DMA_BIDIRECTIONAL); +out: + migrate_vma_finalize(args); + return ret; +} + static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) { struct nouveau_drm *drm = page_to_drm(vmf->page); - struct nouveau_dmem *dmem = drm->dmem; - struct nouveau_fence *fence; unsigned long src = 0, dst = 0; - dma_addr_t dma_addr = 0; + struct page *page; vm_fault_t ret; struct migrate_vma args = { .vma = vmf->vma, @@ -192,39 +247,64 @@ static vm_fault_t nouveau_dmem_migrate_to_ram(struct vm_fault *vmf) .src = &src, .dst = &dst, .pgmap_owner = drm->dev, - .flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE, + .flags = MIGRATE_VMA_SELECT_DEVICE_PRIVATE | + MIGRATE_VMA_SELECT_COMPOUND, };

+ /* + * If the page was migrated to the GPU as a huge page, try to + * migrate it back the same way. + */ + page = compound_head(vmf->page); + if (PageHead(page)) { + unsigned int order = compound_order(page); + unsigned int nr_pages = 1U << order; + + args.start &= PAGE_MASK << order; + args.end = args.start + (PAGE_SIZE << order); + args.src = kmalloc_array(nr_pages, sizeof(*args.src), + GFP_KERNEL); + if (!args.src) + return VM_FAULT_OOM; + args.dst = kmalloc_array(nr_pages, sizeof(*args.dst), + GFP_KERNEL); + if (!args.dst) { + ret = VM_FAULT_OOM; + goto error_src; + } + } + /* * FIXME what we really want is to find some heuristic to migrate more * than just one page on CPU fault. When such fault happens it is very * likely that more surrounding page will CPU fault too. */ - if (migrate_vma_setup(&args) < 0) - return VM_FAULT_SIGBUS; - if (!args.cpages) - return 0; - - ret = nouveau_dmem_fault_copy_one(drm, vmf, &args, &dma_addr); - if (ret || dst == 0) - goto done; - - nouveau_fence_new(dmem->migrate.chan, false, &fence); - migrate_vma_pages(&args); - nouveau_dmem_fence_done(&fence); - dma_unmap_page(drm->dev->dev, dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL); -done: - migrate_vma_finalize(&args); + if (migrate_vma_setup(&args)) + ret = VM_FAULT_SIGBUS; + else + ret = nouveau_dmem_fault_chunk(drm, vmf, &args); + if (args.dst != &dst) + kfree(args.dst); +error_src: + if (args.src != &src) + kfree(args.src); return ret; }

+static void nouveau_page_split(struct page *head, struct page *page) +{ + page->pgmap = head->pgmap; + page->zone_device_data = head->zone_device_data; +} + static const struct dev_pagemap_ops nouveau_dmem_pagemap_ops = { .page_free = nouveau_dmem_page_free, .migrate_to_ram = nouveau_dmem_migrate_to_ram, + .page_split = nouveau_page_split, };

-static int -nouveau_dmem_chunk_alloc(struct nouveau_drm *drm, struct page **ppage) +static int nouveau_dmem_chunk_alloc(struct nouveau_drm *drm, bool is_huge, + struct page **ppage) { struct nouveau_dmem_chunk *chunk; struct resource *res; @@ -278,16 +358,20 @@ nouveau_dmem_chunk_alloc(struct nouveau_drm *drm, struct page **ppage) pfn_first = chunk->pagemap.range.start >> PAGE_SHIFT; page = pfn_to_page(pfn_first); spin_lock(&drm->dmem->lock); - for (i = 0; i < DMEM_CHUNK_NPAGES - 1; ++i, ++page) { - page->zone_device_data = drm->dmem->free_pages; - drm->dmem->free_pages = page; - } + if (IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && is_huge) + prep_transhuge_device_private_page(page); + else + for (i = 0; i < DMEM_CHUNK_NPAGES - 1; ++i, ++page) { + page->zone_device_data = drm->dmem->free_pages; + drm->dmem->free_pages = page; + } *ppage = page; chunk->callocated++; spin_unlock(&drm->dmem->lock);

- NV_INFO(drm, "DMEM: registered %ldMB of device memory\n", - DMEM_CHUNK_SIZE >> 20); + NV_INFO(drm, "DMEM: registered %ldMB of %sdevice memory %lx %lx\n", + DMEM_CHUNK_SIZE >> 20, is_huge ? "huge " : "", pfn_first, + nouveau_dmem_page_addr(page));

return 0;

@@ -304,14 +388,20 @@ nouveau_dmem_chunk_alloc(struct nouveau_drm *drm, struct page **ppage) }

static struct page * -nouveau_dmem_page_alloc_locked(struct nouveau_drm *drm) +nouveau_dmem_page_alloc_locked(struct nouveau_drm *drm, bool is_huge) { struct nouveau_dmem_chunk *chunk; struct page *page = NULL; int ret;

spin_lock(&drm->dmem->lock); - if (drm->dmem->free_pages) { + if (is_huge && drm->dmem->free_huge_pages) { + page = drm->dmem->free_huge_pages; + drm->dmem->free_huge_pages = page->zone_device_data; + chunk = nouveau_page_to_chunk(page); + chunk->callocated++; + spin_unlock(&drm->dmem->lock); + } else if (!is_huge && drm->dmem->free_pages) { page = drm->dmem->free_pages; drm->dmem->free_pages = page->zone_device_data; chunk = nouveau_page_to_chunk(page); @@ -319,7 +409,7 @@ nouveau_dmem_page_alloc_locked(struct nouveau_drm *drm) spin_unlock(&drm->dmem->lock); } else { spin_unlock(&drm->dmem->lock); - ret = nouveau_dmem_chunk_alloc(drm, &page); + ret = nouveau_dmem_chunk_alloc(drm, is_huge, &page); if (ret) return NULL; } @@ -567,31 +657,22 @@ nouveau_dmem_init(struct nouveau_drm *drm)

static unsigned long nouveau_dmem_migrate_copy_one(struct nouveau_drm *drm, struct nouveau_svmm *svmm, unsigned long src, - dma_addr_t *dma_addr, u64 *pfn) + struct page *spage, bool is_huge, dma_addr_t dma_addr, u64 *pfn) { - struct device *dev = drm->dev->dev; - struct page *dpage, *spage; + struct page *dpage; unsigned long paddr; + unsigned long dst;

- spage = migrate_pfn_to_page(src); - if (!(src & MIGRATE_PFN_MIGRATE)) - goto out; - - dpage = nouveau_dmem_page_alloc_locked(drm); + dpage = nouveau_dmem_page_alloc_locked(drm, is_huge); if (!dpage) goto out;

paddr = nouveau_dmem_page_addr(dpage); if (spage) { - *dma_addr = dma_map_page(dev, spage, 0, page_size(spage), - DMA_BIDIRECTIONAL); - if (dma_mapping_error(dev, *dma_addr)) + if (drm->dmem->migrate.copy_func(drm, compound_nr(dpage), + NOUVEAU_APER_VRAM, paddr, NOUVEAU_APER_HOST, dma_addr)) goto out_free_page; - if (drm->dmem->migrate.copy_func(drm, 1, - NOUVEAU_APER_VRAM, paddr, NOUVEAU_APER_HOST, *dma_addr)) - goto out_dma_unmap; } else { - *dma_addr = DMA_MAPPING_ERROR; if (drm->dmem->migrate.clear_func(drm, page_size(dpage), NOUVEAU_APER_VRAM, paddr)) goto out_free_page; @@ -602,10 +683,11 @@ static unsigned long nouveau_dmem_migrate_copy_one(struct nouveau_drm *drm, ((paddr >> PAGE_SHIFT) << NVIF_VMM_PFNMAP_V0_ADDR_SHIFT); if (src & MIGRATE_PFN_WRITE) *pfn |= NVIF_VMM_PFNMAP_V0_W; - return migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; + dst = migrate_pfn(page_to_pfn(dpage)) | MIGRATE_PFN_LOCKED; + if (PageHead(dpage)) + dst |= MIGRATE_PFN_COMPOUND; + return dst;

-out_dma_unmap: - dma_unmap_page(dev, *dma_addr, PAGE_SIZE, DMA_BIDIRECTIONAL); out_free_page: nouveau_dmem_page_free_locked(drm, dpage); out: @@ -617,26 +699,64 @@ static void nouveau_dmem_migrate_chunk(struct nouveau_drm *drm, struct nouveau_svmm *svmm, struct migrate_vma *args, dma_addr_t *dma_addrs, u64 *pfns) { + struct device *dev = drm->dev->dev; struct nouveau_fence *fence; unsigned long addr = args->start, nr_dma = 0, i; + unsigned int page_shift = PAGE_SHIFT; + struct page *spage; + unsigned long src = args->src[0]; + bool is_huge = (src & (MIGRATE_PFN_MIGRATE | MIGRATE_PFN_COMPOUND)) == + (MIGRATE_PFN_MIGRATE | MIGRATE_PFN_COMPOUND); + unsigned long dma_page_size = is_huge ? PMD_SIZE : PAGE_SIZE; + + if (is_huge) { + spage = migrate_pfn_to_page(src); + if (spage) { + dma_addrs[nr_dma] = dma_map_page(dev, spage, 0, + page_size(spage), + DMA_BIDIRECTIONAL); + if (dma_mapping_error(dev, dma_addrs[nr_dma])) + goto out; + nr_dma++; + } + args->dst[0] = nouveau_dmem_migrate_copy_one(drm, svmm, src, + spage, true, *dma_addrs, pfns); + if (args->dst[0] & MIGRATE_PFN_COMPOUND) { + page_shift = PMD_SHIFT; + i = 1; + goto fence; + } + }

- for (i = 0; addr < args->end; i++) { - args->dst[i] = nouveau_dmem_migrate_copy_one(drm, svmm, - args->src[i], dma_addrs + nr_dma, pfns + i); - if (!dma_mapping_error(drm->dev->dev, dma_addrs[nr_dma])) + for (i = 0; addr < args->end; i++, addr += PAGE_SIZE) { + src = args->src[i]; + if (!(src & MIGRATE_PFN_MIGRATE)) + continue; + spage = migrate_pfn_to_page(src); + if (spage && !is_huge) { + dma_addrs[i] = dma_map_page(dev, spage, 0, + page_size(spage), + DMA_BIDIRECTIONAL); + if (dma_mapping_error(dev, dma_addrs[i])) + break; nr_dma++; - addr += PAGE_SIZE; + } else if (spage && is_huge && i != 0) + dma_addrs[i] = dma_addrs[i - 1] + PAGE_SIZE; + args->dst[i] = nouveau_dmem_migrate_copy_one(drm, svmm, src, + spage, false, dma_addrs[i], pfns + i); }

+fence: nouveau_fence_new(drm->dmem->migrate.chan, false, &fence); migrate_vma_pages(args); nouveau_dmem_fence_done(&fence); - nouveau_pfns_map(svmm, args->vma->vm_mm, args->start, pfns, i); + nouveau_pfns_map(svmm, args->vma->vm_mm, args->start, pfns, i, + page_shift);

- while (nr_dma--) { - dma_unmap_page(drm->dev->dev, dma_addrs[nr_dma], PAGE_SIZE, - DMA_BIDIRECTIONAL); - } + while (nr_dma) + dma_unmap_page(drm->dev->dev, dma_addrs[--nr_dma], + dma_page_size, DMA_BIDIRECTIONAL); +out: migrate_vma_finalize(args); }

@@ -648,25 +768,25 @@ nouveau_dmem_migrate_vma(struct nouveau_drm *drm, unsigned long end) { unsigned long npages = (end - start) >> PAGE_SHIFT; - unsigned long max = min(SG_MAX_SINGLE_ALLOC, npages); + unsigned long max = min(1UL << (PMD_SHIFT - PAGE_SHIFT), npages); dma_addr_t *dma_addrs; struct migrate_vma args = { .vma = vma, .start = start, .pgmap_owner = drm->dev, - .flags = MIGRATE_VMA_SELECT_SYSTEM, + .flags = MIGRATE_VMA_SELECT_SYSTEM | + MIGRATE_VMA_SELECT_COMPOUND, }; - unsigned long i; u64 *pfns; int ret = -ENOMEM;

if (drm->dmem == NULL) return -ENODEV;

- args.src = kcalloc(max, sizeof(*args.src), GFP_KERNEL); + args.src = kmalloc_array(max, sizeof(*args.src), GFP_KERNEL); if (!args.src) goto out; - args.dst = kcalloc(max, sizeof(*args.dst), GFP_KERNEL); + args.dst = kmalloc_array(max, sizeof(*args.dst), GFP_KERNEL); if (!args.dst) goto out_free_src;

@@ -678,8 +798,10 @@ nouveau_dmem_migrate_vma(struct nouveau_drm *drm, if (!pfns) goto out_free_dma;

- for (i = 0; i < npages; i += max) { - args.end = start + (max << PAGE_SHIFT); + for (; args.start < end; args.start = args.end) { + args.end = min(end, ALIGN(args.start, PMD_SIZE)); + if (args.start == args.end) + args.end = min(end, args.start + PMD_SIZE); ret = migrate_vma_setup(&args); if (ret) goto out_free_pfns; @@ -687,7 +809,6 @@ nouveau_dmem_migrate_vma(struct nouveau_drm *drm, if (args.cpages) nouveau_dmem_migrate_chunk(drm, svmm, &args, dma_addrs, pfns); - args.start = args.end; }

ret = 0; diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.c b/drivers/gpu/drm/nouveau/nouveau_svm.c index 4f69e4c3dafd..3db0997f21b5 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.c +++ b/drivers/gpu/drm/nouveau/nouveau_svm.c @@ -681,7 +681,6 @@ nouveau_svm_fault(struct nvif_notify *notify) nouveau_svm_fault_cancel_fault(svm, buffer->fault[fi]); continue; } - SVMM_DBG(svmm, "addr %016llx", buffer->fault[fi]->addr);

/* We try and group handling of faults within a small * window into a single update. @@ -733,6 +732,10 @@ nouveau_svm_fault(struct nvif_notify *notify) } mmput(mm);

+ SVMM_DBG(svmm, "addr %llx %s %c", buffer->fault[fi]->addr, + args.phys[0] & NVIF_VMM_PFNMAP_V0_VRAM ? + "vram" : "sysmem", + args.i.p.size > PAGE_SIZE ? 'H' : 'N'); limit = args.i.p.addr + args.i.p.size; for (fn = fi; ++fn < buffer->fault_nr; ) { /* It's okay to skip over duplicate addresses from the @@ -804,13 +807,15 @@ nouveau_pfns_free(u64 *pfns)

void nouveau_pfns_map(struct nouveau_svmm *svmm, struct mm_struct *mm, - unsigned long addr, u64 *pfns, unsigned long npages) + unsigned long addr, u64 *pfns, unsigned long npages, + unsigned int page_shift) { struct nouveau_pfnmap_args *args = nouveau_pfns_to_args(pfns); int ret;

args->p.addr = addr; - args->p.size = npages << PAGE_SHIFT; + args->p.page = page_shift; + args->p.size = npages << args->p.page;

mutex_lock(&svmm->mutex);

diff --git a/drivers/gpu/drm/nouveau/nouveau_svm.h b/drivers/gpu/drm/nouveau/nouveau_svm.h index e7d63d7f0c2d..3fd78662f17e 100644 --- a/drivers/gpu/drm/nouveau/nouveau_svm.h +++ b/drivers/gpu/drm/nouveau/nouveau_svm.h @@ -33,7 +33,8 @@ void nouveau_svmm_invalidate(struct nouveau_svmm *svmm, u64 start, u64 limit); u64 *nouveau_pfns_alloc(unsigned long npages); void nouveau_pfns_free(u64 *pfns); void nouveau_pfns_map(struct nouveau_svmm *svmm, struct mm_struct *mm, - unsigned long addr, u64 *pfns, unsigned long npages); + unsigned long addr, u64 *pfns, unsigned long npages, + unsigned int page_shift); #else /* IS_ENABLED(CONFIG_DRM_NOUVEAU_SVM) */ static inline void nouveau_svm_init(struct nouveau_drm *drm) {} static inline void nouveau_svm_fini(struct nouveau_drm *drm) {}