summaryrefslogtreecommitdiffstats
path: root/mm/huge_memory.c
diff options
context:
space:
mode:
Diffstat (limited to 'mm/huge_memory.c')
-rw-r--r--mm/huge_memory.c104
1 files changed, 61 insertions, 43 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index 533f9b00147d..55478ab3c83b 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -629,21 +629,40 @@ release:
* available
* never: never stall for any thp allocation
*/
-static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma)
+static inline gfp_t alloc_hugepage_direct_gfpmask(struct vm_area_struct *vma, unsigned long addr)
{
const bool vma_madvised = !!(vma->vm_flags & VM_HUGEPAGE);
+ gfp_t this_node = 0;
+
+#ifdef CONFIG_NUMA
+ struct mempolicy *pol;
+ /*
+ * __GFP_THISNODE is used only when __GFP_DIRECT_RECLAIM is not
+ * specified, to express a general desire to stay on the current
+ * node for optimistic allocation attempts. If the defrag mode
+ * and/or madvise hint requires the direct reclaim then we prefer
+ * to fallback to other node rather than node reclaim because that
+ * can lead to excessive reclaim even though there is free memory
+ * on other nodes. We expect that NUMA preferences are specified
+ * by memory policies.
+ */
+ pol = get_vma_policy(vma, addr);
+ if (pol->mode != MPOL_BIND)
+ this_node = __GFP_THISNODE;
+ mpol_cond_put(pol);
+#endif
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_DIRECT_FLAG, &transparent_hugepage_flags))
return GFP_TRANSHUGE | (vma_madvised ? 0 : __GFP_NORETRY);
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_FLAG, &transparent_hugepage_flags))
- return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM;
+ return GFP_TRANSHUGE_LIGHT | __GFP_KSWAPD_RECLAIM | this_node;
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_KSWAPD_OR_MADV_FLAG, &transparent_hugepage_flags))
return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
- __GFP_KSWAPD_RECLAIM);
+ __GFP_KSWAPD_RECLAIM | this_node);
if (test_bit(TRANSPARENT_HUGEPAGE_DEFRAG_REQ_MADV_FLAG, &transparent_hugepage_flags))
return GFP_TRANSHUGE_LIGHT | (vma_madvised ? __GFP_DIRECT_RECLAIM :
- 0);
- return GFP_TRANSHUGE_LIGHT;
+ this_node);
+ return GFP_TRANSHUGE_LIGHT | this_node;
}
/* Caller must hold page table lock. */
@@ -715,8 +734,8 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
pte_free(vma->vm_mm, pgtable);
return ret;
}
- gfp = alloc_hugepage_direct_gfpmask(vma);
- page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER);
+ gfp = alloc_hugepage_direct_gfpmask(vma, haddr);
+ page = alloc_pages_vma(gfp, HPAGE_PMD_ORDER, vma, haddr, numa_node_id());
if (unlikely(!page)) {
count_vm_event(THP_FAULT_FALLBACK);
return VM_FAULT_FALLBACK;
@@ -852,11 +871,10 @@ static void touch_pmd(struct vm_area_struct *vma, unsigned long addr,
}
struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
- pmd_t *pmd, int flags)
+ pmd_t *pmd, int flags, struct dev_pagemap **pgmap)
{
unsigned long pfn = pmd_pfn(*pmd);
struct mm_struct *mm = vma->vm_mm;
- struct dev_pagemap *pgmap;
struct page *page;
assert_spin_locked(pmd_lockptr(mm, pmd));
@@ -886,12 +904,11 @@ struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
return ERR_PTR(-EEXIST);
pfn += (addr & ~PMD_MASK) >> PAGE_SHIFT;
- pgmap = get_dev_pagemap(pfn, NULL);
- if (!pgmap)
+ *pgmap = get_dev_pagemap(pfn, *pgmap);
+ if (!*pgmap)
return ERR_PTR(-EFAULT);
page = pfn_to_page(pfn);
get_page(page);
- put_dev_pagemap(pgmap);
return page;
}
@@ -1000,11 +1017,10 @@ static void touch_pud(struct vm_area_struct *vma, unsigned long addr,
}
struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
- pud_t *pud, int flags)
+ pud_t *pud, int flags, struct dev_pagemap **pgmap)
{
unsigned long pfn = pud_pfn(*pud);
struct mm_struct *mm = vma->vm_mm;
- struct dev_pagemap *pgmap;
struct page *page;
assert_spin_locked(pud_lockptr(mm, pud));
@@ -1028,12 +1044,11 @@ struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
return ERR_PTR(-EEXIST);
pfn += (addr & ~PUD_MASK) >> PAGE_SHIFT;
- pgmap = get_dev_pagemap(pfn, NULL);
- if (!pgmap)
+ *pgmap = get_dev_pagemap(pfn, *pgmap);
+ if (!*pgmap)
return ERR_PTR(-EFAULT);
page = pfn_to_page(pfn);
get_page(page);
- put_dev_pagemap(pgmap);
return page;
}
@@ -1290,8 +1305,9 @@ vm_fault_t do_huge_pmd_wp_page(struct vm_fault *vmf, pmd_t orig_pmd)
alloc:
if (transparent_hugepage_enabled(vma) &&
!transparent_hugepage_debug_cow()) {
- huge_gfp = alloc_hugepage_direct_gfpmask(vma);
- new_page = alloc_hugepage_vma(huge_gfp, vma, haddr, HPAGE_PMD_ORDER);
+ huge_gfp = alloc_hugepage_direct_gfpmask(vma, haddr);
+ new_page = alloc_pages_vma(huge_gfp, HPAGE_PMD_ORDER, vma,
+ haddr, numa_node_id());
} else
new_page = NULL;
@@ -1562,8 +1578,20 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t pmd)
* We are not sure a pending tlb flush here is for a huge page
* mapping or not. Hence use the tlb range variant
*/
- if (mm_tlb_flush_pending(vma->vm_mm))
+ if (mm_tlb_flush_pending(vma->vm_mm)) {
flush_tlb_range(vma, haddr, haddr + HPAGE_PMD_SIZE);
+ /*
+ * change_huge_pmd() released the pmd lock before
+ * invalidating the secondary MMUs sharing the primary
+ * MMU pagetables (with ->invalidate_range()). The
+ * mmu_notifier_invalidate_range_end() (which
+ * internally calls ->invalidate_range()) in
+ * change_pmd_range() will run after us, so we can't
+ * rely on it here and we need an explicit invalidate.
+ */
+ mmu_notifier_invalidate_range(vma->vm_mm, haddr,
+ haddr + HPAGE_PMD_SIZE);
+ }
/*
* Migrate the THP to the requested node, returns with page unlocked
@@ -1780,7 +1808,7 @@ static pmd_t move_soft_dirty_pmd(pmd_t pmd)
bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
unsigned long new_addr, unsigned long old_end,
- pmd_t *old_pmd, pmd_t *new_pmd, bool *need_flush)
+ pmd_t *old_pmd, pmd_t *new_pmd)
{
spinlock_t *old_ptl, *new_ptl;
pmd_t pmd;
@@ -1811,7 +1839,7 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
if (new_ptl != old_ptl)
spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING);
pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd);
- if (pmd_present(pmd) && pmd_dirty(pmd))
+ if (pmd_present(pmd))
force_flush = true;
VM_BUG_ON(!pmd_none(*new_pmd));
@@ -1822,12 +1850,10 @@ bool move_huge_pmd(struct vm_area_struct *vma, unsigned long old_addr,
}
pmd = move_soft_dirty_pmd(pmd);
set_pmd_at(mm, new_addr, new_pmd, pmd);
- if (new_ptl != old_ptl)
- spin_unlock(new_ptl);
if (force_flush)
flush_tlb_range(vma, old_addr, old_addr + PMD_SIZE);
- else
- *need_flush = true;
+ if (new_ptl != old_ptl)
+ spin_unlock(new_ptl);
spin_unlock(old_ptl);
return true;
}
@@ -2371,6 +2397,7 @@ static void __split_huge_page_tail(struct page *head, int tail,
(1L << PG_mlocked) |
(1L << PG_uptodate) |
(1L << PG_active) |
+ (1L << PG_workingset) |
(1L << PG_locked) |
(1L << PG_unevictable) |
(1L << PG_dirty)));
@@ -2443,13 +2470,13 @@ static void __split_huge_page(struct page *page, struct list_head *list,
ClearPageCompound(head);
/* See comment in __split_huge_page_tail() */
if (PageAnon(head)) {
- /* Additional pin to radix tree of swap cache */
+ /* Additional pin to swap cache */
if (PageSwapCache(head))
page_ref_add(head, 2);
else
page_ref_inc(head);
} else {
- /* Additional pin to radix tree */
+ /* Additional pin to page cache */
page_ref_add(head, 2);
xa_unlock(&head->mapping->i_pages);
}
@@ -2561,7 +2588,7 @@ bool can_split_huge_page(struct page *page, int *pextra_pins)
{
int extra_pins;
- /* Additional pins from radix tree */
+ /* Additional pins from page cache */
if (PageAnon(page))
extra_pins = PageSwapCache(page) ? HPAGE_PMD_NR : 0;
else
@@ -2657,17 +2684,14 @@ int split_huge_page_to_list(struct page *page, struct list_head *list)
spin_lock_irqsave(zone_lru_lock(page_zone(head)), flags);
if (mapping) {
- void **pslot;
+ XA_STATE(xas, &mapping->i_pages, page_index(head));
- xa_lock(&mapping->i_pages);
- pslot = radix_tree_lookup_slot(&mapping->i_pages,
- page_index(head));
/*
- * Check if the head page is present in radix tree.
+ * Check if the head page is present in page cache.
* We assume all tail are present too, if head is there.
*/
- if (radix_tree_deref_slot_protected(pslot,
- &mapping->i_pages.xa_lock) != head)
+ xa_lock(&mapping->i_pages);
+ if (xas_load(&xas) != head)
goto fail;
}
@@ -2885,9 +2909,6 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
if (!(pvmw->pmd && !pvmw->pte))
return;
- mmu_notifier_invalidate_range_start(mm, address,
- address + HPAGE_PMD_SIZE);
-
flush_cache_range(vma, address, address + HPAGE_PMD_SIZE);
pmdval = *pvmw->pmd;
pmdp_invalidate(vma, address, pvmw->pmd);
@@ -2900,9 +2921,6 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
set_pmd_at(mm, address, pvmw->pmd, pmdswp);
page_remove_rmap(page, true);
put_page(page);
-
- mmu_notifier_invalidate_range_end(mm, address,
- address + HPAGE_PMD_SIZE);
}
void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
@@ -2931,7 +2949,7 @@ void remove_migration_pmd(struct page_vma_mapped_walk *pvmw, struct page *new)
else
page_add_file_rmap(new, true);
set_pmd_at(mm, mmun_start, pvmw->pmd, pmde);
- if (vma->vm_flags & VM_LOCKED)
+ if ((vma->vm_flags & VM_LOCKED) && !PageDoubleMap(new))
mlock_vma_page(new);
update_mmu_cache_pmd(vma, address, pvmw->pmd);
}
generated by cgit v1.2.3 (git 2.25.1) at 2025-03-13 17:22:23 +0000