Merge tag 'v4.5-rc1' into x86/asm, to refresh the branch before merging new changes

Signed-off-by: Ingo Molnar <mingo@kernel.org>

1 files changed, 78 insertions, 73 deletions

diff --git a/mm/memory.c b/mm/memory.c
index a29f0b90fc56..5aa4f55eb786 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -50,6 +50,7 @@
 #include <linux/export.h>
 #include <linux/delayacct.h>
 #include <linux/init.h>
+#include <linux/pfn_t.h>
 #include <linux/writeback.h>
 #include <linux/memcontrol.h>
 #include <linux/mmu_notifier.h>
@@ -566,7 +567,6 @@ int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 {
 	spinlock_t *ptl;
 	pgtable_t new = pte_alloc_one(mm, address);
-	int wait_split_huge_page;
 	if (!new)
 		return -ENOMEM;
 
@@ -586,18 +586,14 @@ int __pte_alloc(struct mm_struct *mm, struct vm_area_struct *vma,
 	smp_wmb(); /* Could be smp_wmb__xxx(before|after)_spin_lock */
 
 	ptl = pmd_lock(mm, pmd);
-	wait_split_huge_page = 0;
 	if (likely(pmd_none(*pmd))) {	/* Has another populated it ? */
 		atomic_long_inc(&mm->nr_ptes);
 		pmd_populate(mm, pmd, new);
 		new = NULL;
-	} else if (unlikely(pmd_trans_splitting(*pmd)))
-		wait_split_huge_page = 1;
+	}
 	spin_unlock(ptl);
 	if (new)
 		pte_free(mm, new);
-	if (wait_split_huge_page)
-		wait_split_huge_page(vma->anon_vma, pmd);
 	return 0;
 }
 
@@ -613,8 +609,7 @@ int __pte_alloc_kernel(pmd_t *pmd, unsigned long address)
 	if (likely(pmd_none(*pmd))) {	/* Has another populated it ? */
 		pmd_populate_kernel(&init_mm, pmd, new);
 		new = NULL;
-	} else
-		VM_BUG_ON(pmd_trans_splitting(*pmd));
+	}
 	spin_unlock(&init_mm.page_table_lock);
 	if (new)
 		pte_free_kernel(&init_mm, new);
@@ -832,10 +827,7 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 		} else if (is_migration_entry(entry)) {
 			page = migration_entry_to_page(entry);
 
-			if (PageAnon(page))
-				rss[MM_ANONPAGES]++;
-			else
-				rss[MM_FILEPAGES]++;
+			rss[mm_counter(page)]++;
 
 			if (is_write_migration_entry(entry) &&
 					is_cow_mapping(vm_flags)) {
@@ -873,11 +865,8 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 	page = vm_normal_page(vma, addr, pte);
 	if (page) {
 		get_page(page);
-		page_dup_rmap(page);
-		if (PageAnon(page))
-			rss[MM_ANONPAGES]++;
-		else
-			rss[MM_FILEPAGES]++;
+		page_dup_rmap(page, false);
+		rss[mm_counter(page)]++;
 	}
 
 out_set_pte:
@@ -961,7 +950,7 @@ static inline int copy_pmd_range(struct mm_struct *dst_mm, struct mm_struct *src
 	src_pmd = pmd_offset(src_pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
-		if (pmd_trans_huge(*src_pmd)) {
+		if (pmd_trans_huge(*src_pmd) || pmd_devmap(*src_pmd)) {
 			int err;
 			VM_BUG_ON(next-addr != HPAGE_PMD_SIZE);
 			err = copy_huge_pmd(dst_mm, src_mm,
@@ -1113,9 +1102,8 @@ again:
 			tlb_remove_tlb_entry(tlb, pte, addr);
 			if (unlikely(!page))
 				continue;
-			if (PageAnon(page))
-				rss[MM_ANONPAGES]--;
-			else {
+
+			if (!PageAnon(page)) {
 				if (pte_dirty(ptent)) {
 					force_flush = 1;
 					set_page_dirty(page);
@@ -1123,9 +1111,9 @@ again:
 				if (pte_young(ptent) &&
 				    likely(!(vma->vm_flags & VM_SEQ_READ)))
 					mark_page_accessed(page);
-				rss[MM_FILEPAGES]--;
 			}
-			page_remove_rmap(page);
+			rss[mm_counter(page)]--;
+			page_remove_rmap(page, false);
 			if (unlikely(page_mapcount(page) < 0))
 				print_bad_pte(vma, addr, ptent, page);
 			if (unlikely(!__tlb_remove_page(tlb, page))) {
@@ -1146,11 +1134,7 @@ again:
 			struct page *page;
 
 			page = migration_entry_to_page(entry);
-
-			if (PageAnon(page))
-				rss[MM_ANONPAGES]--;
-			else
-				rss[MM_FILEPAGES]--;
+			rss[mm_counter(page)]--;
 		}
 		if (unlikely(!free_swap_and_cache(entry)))
 			print_bad_pte(vma, addr, ptent, NULL);
@@ -1193,7 +1177,7 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
 	pmd = pmd_offset(pud, addr);
 	do {
 		next = pmd_addr_end(addr, end);
-		if (pmd_trans_huge(*pmd)) {
+		if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) {
 			if (next - addr != HPAGE_PMD_SIZE) {
 #ifdef CONFIG_DEBUG_VM
 				if (!rwsem_is_locked(&tlb->mm->mmap_sem)) {
@@ -1204,7 +1188,7 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb,
 					BUG();
 				}
 #endif
-				split_huge_page_pmd(vma, addr, pmd);
+				split_huge_pmd(vma, pmd, addr);
 			} else if (zap_huge_pmd(tlb, vma, pmd, addr))
 				goto next;
 			/* fall through */
@@ -1460,7 +1444,7 @@ static int insert_page(struct vm_area_struct *vma, unsigned long addr,
 
 	/* Ok, finally just insert the thing.. */
 	get_page(page);
-	inc_mm_counter_fast(mm, MM_FILEPAGES);
+	inc_mm_counter_fast(mm, mm_counter_file(page));
 	page_add_file_rmap(page);
 	set_pte_at(mm, addr, pte, mk_pte(page, prot));
 
@@ -1517,7 +1501,7 @@ int vm_insert_page(struct vm_area_struct *vma, unsigned long addr,
 EXPORT_SYMBOL(vm_insert_page);
 
 static int insert_pfn(struct vm_area_struct *vma, unsigned long addr,
-			unsigned long pfn, pgprot_t prot)
+			pfn_t pfn, pgprot_t prot)
 {
 	struct mm_struct *mm = vma->vm_mm;
 	int retval;
@@ -1533,7 +1517,10 @@ static int insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 		goto out_unlock;
 
 	/* Ok, finally just insert the thing.. */
-	entry = pte_mkspecial(pfn_pte(pfn, prot));
+	if (pfn_t_devmap(pfn))
+		entry = pte_mkdevmap(pfn_t_pte(pfn, prot));
+	else
+		entry = pte_mkspecial(pfn_t_pte(pfn, prot));
 	set_pte_at(mm, addr, pte, entry);
 	update_mmu_cache(vma, addr, pte); /* XXX: why not for insert_page? */
 
@@ -1601,17 +1588,17 @@ int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
 
 	if (addr < vma->vm_start || addr >= vma->vm_end)
 		return -EFAULT;
-	if (track_pfn_insert(vma, &pgprot, pfn))
+	if (track_pfn_insert(vma, &pgprot, __pfn_to_pfn_t(pfn, PFN_DEV)))
 		return -EINVAL;
 
-	ret = insert_pfn(vma, addr, pfn, pgprot);
+	ret = insert_pfn(vma, addr, __pfn_to_pfn_t(pfn, PFN_DEV), pgprot);
 
 	return ret;
 }
 EXPORT_SYMBOL(vm_insert_pfn_prot);
 
 int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
-			unsigned long pfn)
+			pfn_t pfn)
 {
 	BUG_ON(!(vma->vm_flags & VM_MIXEDMAP));
 
@@ -1625,10 +1612,10 @@ int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 	 * than insert_pfn).  If a zero_pfn were inserted into a VM_MIXEDMAP
 	 * without pte special, it would there be refcounted as a normal page.
 	 */
-	if (!HAVE_PTE_SPECIAL && pfn_valid(pfn)) {
+	if (!HAVE_PTE_SPECIAL && pfn_t_valid(pfn)) {
 		struct page *page;
 
-		page = pfn_to_page(pfn);
+		page = pfn_t_to_page(pfn);
 		return insert_page(vma, addr, page, vma->vm_page_prot);
 	}
 	return insert_pfn(vma, addr, pfn, vma->vm_page_prot);
@@ -1970,6 +1957,20 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo
 		copy_user_highpage(dst, src, va, vma);
 }
 
+static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma)
+{
+	struct file *vm_file = vma->vm_file;
+
+	if (vm_file)
+		return mapping_gfp_mask(vm_file->f_mapping) | __GFP_FS | __GFP_IO;
+
+	/*
+	 * Special mappings (e.g. VDSO) do not have any file so fake
+	 * a default GFP_KERNEL for them.
+	 */
+	return GFP_KERNEL;
+}
+
 /*
  * Notify the address space that the page is about to become writable so that
  * it can prohibit this or wait for the page to get into an appropriate state.
@@ -1985,6 +1986,7 @@ static int do_page_mkwrite(struct vm_area_struct *vma, struct page *page,
 	vmf.virtual_address = (void __user *)(address & PAGE_MASK);
 	vmf.pgoff = page->index;
 	vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE;
+	vmf.gfp_mask = __get_fault_gfp_mask(vma);
 	vmf.page = page;
 	vmf.cow_page = NULL;
 
@@ -2104,7 +2106,7 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma,
 		cow_user_page(new_page, old_page, address, vma);
 	}
 
-	if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg))
+	if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg, false))
 		goto oom_free_new;
 
 	__SetPageUptodate(new_page);
@@ -2118,7 +2120,8 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (likely(pte_same(*page_table, orig_pte))) {
 		if (old_page) {
 			if (!PageAnon(old_page)) {
-				dec_mm_counter_fast(mm, MM_FILEPAGES);
+				dec_mm_counter_fast(mm,
+						mm_counter_file(old_page));
 				inc_mm_counter_fast(mm, MM_ANONPAGES);
 			}
 		} else {
@@ -2134,8 +2137,8 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma,
 		 * thread doing COW.
 		 */
 		ptep_clear_flush_notify(vma, address, page_table);
-		page_add_new_anon_rmap(new_page, vma, address);
-		mem_cgroup_commit_charge(new_page, memcg, false);
+		page_add_new_anon_rmap(new_page, vma, address, false);
+		mem_cgroup_commit_charge(new_page, memcg, false, false);
 		lru_cache_add_active_or_unevictable(new_page, vma);
 		/*
 		 * We call the notify macro here because, when using secondary
@@ -2167,14 +2170,14 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma,
 			 * mapcount is visible. So transitively, TLBs to
 			 * old page will be flushed before it can be reused.
 			 */
-			page_remove_rmap(old_page);
+			page_remove_rmap(old_page, false);
 		}
 
 		/* Free the old page.. */
 		new_page = old_page;
 		page_copied = 1;
 	} else {
-		mem_cgroup_cancel_charge(new_page, memcg);
+		mem_cgroup_cancel_charge(new_page, memcg, false);
 	}
 
 	if (new_page)
@@ -2189,7 +2192,8 @@ static int wp_page_copy(struct mm_struct *mm, struct vm_area_struct *vma,
 		 */
 		if (page_copied && (vma->vm_flags & VM_LOCKED)) {
 			lock_page(old_page);	/* LRU manipulation */
-			munlock_vma_page(old_page);
+			if (PageMlocked(old_page))
+				munlock_vma_page(old_page);
 			unlock_page(old_page);
 		}
 		page_cache_release(old_page);
@@ -2549,7 +2553,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto out_page;
 	}
 
-	if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg)) {
+	if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg, false)) {
 		ret = VM_FAULT_OOM;
 		goto out_page;
 	}
@@ -2583,7 +2587,7 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		pte = maybe_mkwrite(pte_mkdirty(pte), vma);
 		flags &= ~FAULT_FLAG_WRITE;
 		ret |= VM_FAULT_WRITE;
-		exclusive = 1;
+		exclusive = RMAP_EXCLUSIVE;
 	}
 	flush_icache_page(vma, page);
 	if (pte_swp_soft_dirty(orig_pte))
@@ -2591,15 +2595,16 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	set_pte_at(mm, address, page_table, pte);
 	if (page == swapcache) {
 		do_page_add_anon_rmap(page, vma, address, exclusive);
-		mem_cgroup_commit_charge(page, memcg, true);
+		mem_cgroup_commit_charge(page, memcg, true, false);
 	} else { /* ksm created a completely new copy */
-		page_add_new_anon_rmap(page, vma, address);
-		mem_cgroup_commit_charge(page, memcg, false);
+		page_add_new_anon_rmap(page, vma, address, false);
+		mem_cgroup_commit_charge(page, memcg, false, false);
 		lru_cache_add_active_or_unevictable(page, vma);
 	}
 
 	swap_free(entry);
-	if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
+	if (mem_cgroup_swap_full(page) ||
+	    (vma->vm_flags & VM_LOCKED) || PageMlocked(page))
 		try_to_free_swap(page);
 	unlock_page(page);
 	if (page != swapcache) {
@@ -2629,7 +2634,7 @@ unlock:
 out:
 	return ret;
 out_nomap:
-	mem_cgroup_cancel_charge(page, memcg);
+	mem_cgroup_cancel_charge(page, memcg, false);
 	pte_unmap_unlock(page_table, ptl);
 out_page:
 	unlock_page(page);
@@ -2723,7 +2728,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (!page)
 		goto oom;
 
-	if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg))
+	if (mem_cgroup_try_charge(page, mm, GFP_KERNEL, &memcg, false))
 		goto oom_free_page;
 
 	/*
@@ -2744,15 +2749,15 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma,
 	/* Deliver the page fault to userland, check inside PT lock */
 	if (userfaultfd_missing(vma)) {
 		pte_unmap_unlock(page_table, ptl);
-		mem_cgroup_cancel_charge(page, memcg);
+		mem_cgroup_cancel_charge(page, memcg, false);
 		page_cache_release(page);
 		return handle_userfault(vma, address, flags,
 					VM_UFFD_MISSING);
 	}
 
 	inc_mm_counter_fast(mm, MM_ANONPAGES);
-	page_add_new_anon_rmap(page, vma, address);
-	mem_cgroup_commit_charge(page, memcg, false);
+	page_add_new_anon_rmap(page, vma, address, false);
+	mem_cgroup_commit_charge(page, memcg, false, false);
 	lru_cache_add_active_or_unevictable(page, vma);
 setpte:
 	set_pte_at(mm, address, page_table, entry);
@@ -2763,7 +2768,7 @@ unlock:
 	pte_unmap_unlock(page_table, ptl);
 	return 0;
 release:
-	mem_cgroup_cancel_charge(page, memcg);
+	mem_cgroup_cancel_charge(page, memcg, false);
 	page_cache_release(page);
 	goto unlock;
 oom_free_page:
@@ -2788,6 +2793,7 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address,
 	vmf.pgoff = pgoff;
 	vmf.flags = flags;
 	vmf.page = NULL;
+	vmf.gfp_mask = __get_fault_gfp_mask(vma);
 	vmf.cow_page = cow_page;
 
 	ret = vma->vm_ops->fault(vma, &vmf);
@@ -2839,9 +2845,9 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address,
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 	if (anon) {
 		inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES);
-		page_add_new_anon_rmap(page, vma, address);
+		page_add_new_anon_rmap(page, vma, address, false);
 	} else {
-		inc_mm_counter_fast(vma->vm_mm, MM_FILEPAGES);
+		inc_mm_counter_fast(vma->vm_mm, mm_counter_file(page));
 		page_add_file_rmap(page);
 	}
 	set_pte_at(vma->vm_mm, address, pte, entry);
@@ -2954,6 +2960,7 @@ static void do_fault_around(struct vm_area_struct *vma, unsigned long address,
 	vmf.pgoff = pgoff;
 	vmf.max_pgoff = max_pgoff;
 	vmf.flags = flags;
+	vmf.gfp_mask = __get_fault_gfp_mask(vma);
 	vma->vm_ops->map_pages(vma, &vmf);
 }
 
@@ -3014,7 +3021,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	if (!new_page)
 		return VM_FAULT_OOM;
 
-	if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg)) {
+	if (mem_cgroup_try_charge(new_page, mm, GFP_KERNEL, &memcg, false)) {
 		page_cache_release(new_page);
 		return VM_FAULT_OOM;
 	}
@@ -3043,7 +3050,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		goto uncharge_out;
 	}
 	do_set_pte(vma, address, new_page, pte, true, true);
-	mem_cgroup_commit_charge(new_page, memcg, false);
+	mem_cgroup_commit_charge(new_page, memcg, false, false);
 	lru_cache_add_active_or_unevictable(new_page, vma);
 	pte_unmap_unlock(pte, ptl);
 	if (fault_page) {
@@ -3058,7 +3065,7 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	}
 	return ret;
 uncharge_out:
-	mem_cgroup_cancel_charge(new_page, memcg);
+	mem_cgroup_cancel_charge(new_page, memcg, false);
 	page_cache_release(new_page);
 	return ret;
 }
@@ -3110,7 +3117,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	 * pinned by vma->vm_file's reference.  We rely on unlock_page()'s
 	 * release semantics to prevent the compiler from undoing this copying.
 	 */
-	mapping = fault_page->mapping;
+	mapping = page_rmapping(fault_page);
 	unlock_page(fault_page);
 	if ((dirtied || vma->vm_ops->page_mkwrite) && mapping) {
 		/*
@@ -3212,6 +3219,12 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma,
 		return 0;
 	}
 
+	/* TODO: handle PTE-mapped THP */
+	if (PageCompound(page)) {
+		pte_unmap_unlock(ptep, ptl);
+		return 0;
+	}
+
 	/*
 	 * Avoid grouping on RO pages in general. RO pages shouldn't hurt as
 	 * much anyway since they can be in shared cache state. This misses
@@ -3384,17 +3397,9 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 		int ret;
 
 		barrier();
-		if (pmd_trans_huge(orig_pmd)) {
+		if (pmd_trans_huge(orig_pmd) || pmd_devmap(orig_pmd)) {
 			unsigned int dirty = flags & FAULT_FLAG_WRITE;
 
-			/*
-			 * If the pmd is splitting, return and retry the
-			 * the fault.  Alternative: wait until the split
-			 * is done, and goto retry.
-			 */
-			if (pmd_trans_splitting(orig_pmd))
-				return 0;
-
 			if (pmd_protnone(orig_pmd))
 				return do_huge_pmd_numa_page(mm, vma, address,
 							     orig_pmd, pmd);
@@ -3421,7 +3426,7 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma,
 	    unlikely(__pte_alloc(mm, vma, pmd, address)))
 		return VM_FAULT_OOM;
 	/* if an huge pmd materialized from under us just retry later */
-	if (unlikely(pmd_trans_huge(*pmd)))
+	if (unlikely(pmd_trans_huge(*pmd) || pmd_devmap(*pmd)))
 		return 0;
 	/*
 	 * A regular pmd is established and it can't morph into a huge pmd