Merge branch 'akpm' (patches from Andrew)

Merge misc fixes from Andrew Morton:
 "13 patches.

  Subsystems affected by this patch series: mips, mm (kfence, debug,
  pagealloc, memory-hotplug, hugetlb, kasan, and hugetlb), init, proc,
  lib, ocfs2, and mailmap"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>:
  mailmap: use private address for Michel Lespinasse
  ocfs2: fix data corruption by fallocate
  lib: crc64: fix kernel-doc warning
  mm, hugetlb: fix simple resv_huge_pages underflow on UFFDIO_COPY
  mm/kasan/init.c: fix doc warning
  proc: add .gitignore for proc-subset-pid selftest
  hugetlb: pass head page to remove_hugetlb_page()
  drivers/base/memory: fix trying offlining memory blocks with memory holes on aarch64
  mm/page_alloc: fix counting of free pages after take off from buddy
  mm/debug_vm_pgtable: fix alignment for pmd/pud_advanced_tests()
  pid: take a reference when initializing `cad_pid`
  kfence: use TASK_IDLE when awaiting allocation
  Revert "MIPS: make userspace mapping young by default"

14 files changed, 107 insertions, 36 deletions

diff --git a/.mailmap b/.mailmap
index ce6c497767e2..c79a78766c07 100644
--- a/.mailmap
+++ b/.mailmap
@@ -243,6 +243,9 @@ Maxime Ripard <mripard@kernel.org> <maxime.ripard@free-electrons.com>
 Mayuresh Janorkar <mayur@ti.com>
 Michael Buesch <m@bues.ch>
 Michel Dänzer <michel@tungstengraphics.com>
+Michel Lespinasse <michel@lespinasse.org>
+Michel Lespinasse <michel@lespinasse.org> <walken@google.com>
+Michel Lespinasse <michel@lespinasse.org> <walken@zoy.org>
 Miguel Ojeda <ojeda@kernel.org> <miguel.ojeda.sandonis@gmail.com>
 Mike Rapoport <rppt@kernel.org> <mike@compulab.co.il>
 Mike Rapoport <rppt@kernel.org> <mike.rapoport@gmail.com>
diff --git a/arch/mips/mm/cache.c b/arch/mips/mm/cache.c
index a7bf0c80371c..830ab91e574f 100644
--- a/arch/mips/mm/cache.c
+++ b/arch/mips/mm/cache.c
@@ -158,31 +158,29 @@ unsigned long _page_cachable_default;
 EXPORT_SYMBOL(_page_cachable_default);
 
 #define PM(p)	__pgprot(_page_cachable_default | (p))
-#define PVA(p)	PM(_PAGE_VALID | _PAGE_ACCESSED | (p))
 
 static inline void setup_protection_map(void)
 {
 	protection_map[0]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
-	protection_map[1]  = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC);
-	protection_map[2]  = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
-	protection_map[3]  = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC);
-	protection_map[4]  = PVA(_PAGE_PRESENT);
-	protection_map[5]  = PVA(_PAGE_PRESENT);
-	protection_map[6]  = PVA(_PAGE_PRESENT);
-	protection_map[7]  = PVA(_PAGE_PRESENT);
+	protection_map[1]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC);
+	protection_map[2]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
+	protection_map[3]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC);
+	protection_map[4]  = PM(_PAGE_PRESENT);
+	protection_map[5]  = PM(_PAGE_PRESENT);
+	protection_map[6]  = PM(_PAGE_PRESENT);
+	protection_map[7]  = PM(_PAGE_PRESENT);
 
 	protection_map[8]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_NO_READ);
-	protection_map[9]  = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC);
-	protection_map[10] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE |
+	protection_map[9]  = PM(_PAGE_PRESENT | _PAGE_NO_EXEC);
+	protection_map[10] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE |
 				_PAGE_NO_READ);
-	protection_map[11] = PVA(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE);
-	protection_map[12] = PVA(_PAGE_PRESENT);
-	protection_map[13] = PVA(_PAGE_PRESENT);
-	protection_map[14] = PVA(_PAGE_PRESENT);
-	protection_map[15] = PVA(_PAGE_PRESENT);
+	protection_map[11] = PM(_PAGE_PRESENT | _PAGE_NO_EXEC | _PAGE_WRITE);
+	protection_map[12] = PM(_PAGE_PRESENT);
+	protection_map[13] = PM(_PAGE_PRESENT);
+	protection_map[14] = PM(_PAGE_PRESENT | _PAGE_WRITE);
+	protection_map[15] = PM(_PAGE_PRESENT | _PAGE_WRITE);
 }
 
-#undef _PVA
 #undef PM
 
 void cpu_cache_init(void)
diff --git a/drivers/base/memory.c b/drivers/base/memory.c
index b31b3af5c490..d5ffaab3cb61 100644
--- a/drivers/base/memory.c
+++ b/drivers/base/memory.c
@@ -218,14 +218,14 @@ static int memory_block_offline(struct memory_block *mem)
 	struct zone *zone;
 	int ret;
 
-	zone = page_zone(pfn_to_page(start_pfn));
-
 	/*
 	 * Unaccount before offlining, such that unpopulated zone and kthreads
 	 * can properly be torn down in offline_pages().
 	 */
-	if (nr_vmemmap_pages)
+	if (nr_vmemmap_pages) {
+		zone = page_zone(pfn_to_page(start_pfn));
 		adjust_present_page_count(zone, -nr_vmemmap_pages);
+	}
 
 	ret = offline_pages(start_pfn + nr_vmemmap_pages,
 			    nr_pages - nr_vmemmap_pages);
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index f17c3d33fb18..775657943057 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -1856,6 +1856,45 @@ out:
 }
 
 /*
+ * zero out partial blocks of one cluster.
+ *
+ * start: file offset where zero starts, will be made upper block aligned.
+ * len: it will be trimmed to the end of current cluster if "start + len"
+ *      is bigger than it.
+ */
+static int ocfs2_zeroout_partial_cluster(struct inode *inode,
+					u64 start, u64 len)
+{
+	int ret;
+	u64 start_block, end_block, nr_blocks;
+	u64 p_block, offset;
+	u32 cluster, p_cluster, nr_clusters;
+	struct super_block *sb = inode->i_sb;
+	u64 end = ocfs2_align_bytes_to_clusters(sb, start);
+
+	if (start + len < end)
+		end = start + len;
+
+	start_block = ocfs2_blocks_for_bytes(sb, start);
+	end_block = ocfs2_blocks_for_bytes(sb, end);
+	nr_blocks = end_block - start_block;
+	if (!nr_blocks)
+		return 0;
+
+	cluster = ocfs2_bytes_to_clusters(sb, start);
+	ret = ocfs2_get_clusters(inode, cluster, &p_cluster,
+				&nr_clusters, NULL);
+	if (ret)
+		return ret;
+	if (!p_cluster)
+		return 0;
+
+	offset = start_block - ocfs2_clusters_to_blocks(sb, cluster);
+	p_block = ocfs2_clusters_to_blocks(sb, p_cluster) + offset;
+	return sb_issue_zeroout(sb, p_block, nr_blocks, GFP_NOFS);
+}
+
+/*
  * Parts of this function taken from xfs_change_file_space()
  */
 static int __ocfs2_change_file_space(struct file *file, struct inode *inode,
@@ -1865,7 +1904,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode,
 {
 	int ret;
 	s64 llen;
-	loff_t size;
+	loff_t size, orig_isize;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	struct buffer_head *di_bh = NULL;
 	handle_t *handle;
@@ -1896,6 +1935,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode,
 		goto out_inode_unlock;
 	}
 
+	orig_isize = i_size_read(inode);
 	switch (sr->l_whence) {
 	case 0: /*SEEK_SET*/
 		break;
@@ -1903,7 +1943,7 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode,
 		sr->l_start += f_pos;
 		break;
 	case 2: /*SEEK_END*/
-		sr->l_start += i_size_read(inode);
+		sr->l_start += orig_isize;
 		break;
 	default:
 		ret = -EINVAL;
@@ -1957,6 +1997,14 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode,
 	default:
 		ret = -EINVAL;
 	}
+
+	/* zeroout eof blocks in the cluster. */
+	if (!ret && change_size && orig_isize < size) {
+		ret = ocfs2_zeroout_partial_cluster(inode, orig_isize,
+					size - orig_isize);
+		if (!ret)
+			i_size_write(inode, size);
+	}
 	up_write(&OCFS2_I(inode)->ip_alloc_sem);
 	if (ret) {
 		mlog_errno(ret);
@@ -1973,9 +2021,6 @@ static int __ocfs2_change_file_space(struct file *file, struct inode *inode,
 		goto out_inode_unlock;
 	}
 
-	if (change_size && i_size_read(inode) < size)
-		i_size_write(inode, size);
-
 	inode->i_ctime = inode->i_mtime = current_time(inode);
 	ret = ocfs2_mark_inode_dirty(handle, inode, di_bh);
 	if (ret < 0)
diff --git a/include/linux/pgtable.h b/include/linux/pgtable.h
index 46b13780c2c8..a43047b1030d 100644
--- a/include/linux/pgtable.h
+++ b/include/linux/pgtable.h
@@ -432,6 +432,14 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addres
  * To be differentiate with macro pte_mkyoung, this macro is used on platforms
  * where software maintains page access bit.
  */
+#ifndef pte_sw_mkyoung
+static inline pte_t pte_sw_mkyoung(pte_t pte)
+{
+	return pte;
+}
+#define pte_sw_mkyoung	pte_sw_mkyoung
+#endif
+
 #ifndef pte_savedwrite
 #define pte_savedwrite pte_write
 #endif
diff --git a/init/main.c b/init/main.c
index eb01e121d2f1..e9c42a183e33 100644
--- a/init/main.c
+++ b/init/main.c
@@ -1537,7 +1537,7 @@ static noinline void __init kernel_init_freeable(void)
 	 */
 	set_mems_allowed(node_states[N_MEMORY]);
 
-	cad_pid = task_pid(current);
+	cad_pid = get_pid(task_pid(current));
 
 	smp_prepare_cpus(setup_max_cpus);
 
diff --git a/lib/crc64.c b/lib/crc64.c
index 47cfa054827f..9f852a89ee2a 100644
--- a/lib/crc64.c
+++ b/lib/crc64.c
@@ -37,7 +37,7 @@ MODULE_LICENSE("GPL v2");
 /**
  * crc64_be - Calculate bitwise big-endian ECMA-182 CRC64
  * @crc: seed value for computation. 0 or (u64)~0 for a new CRC calculation,
-	or the previous crc64 value if computing incrementally.
+ *       or the previous crc64 value if computing incrementally.
  * @p: pointer to buffer over which CRC64 is run
  * @len: length of buffer @p
  */
diff --git a/mm/debug_vm_pgtable.c b/mm/debug_vm_pgtable.c
index 05efe98a9ac2..297d1b349c19 100644
--- a/mm/debug_vm_pgtable.c
+++ b/mm/debug_vm_pgtable.c
@@ -192,7 +192,7 @@ static void __init pmd_advanced_tests(struct mm_struct *mm,
 
 	pr_debug("Validating PMD advanced\n");
 	/* Align the address wrt HPAGE_PMD_SIZE */
-	vaddr = (vaddr & HPAGE_PMD_MASK) + HPAGE_PMD_SIZE;
+	vaddr &= HPAGE_PMD_MASK;
 
 	pgtable_trans_huge_deposit(mm, pmdp, pgtable);
 
@@ -330,7 +330,7 @@ static void __init pud_advanced_tests(struct mm_struct *mm,
 
 	pr_debug("Validating PUD advanced\n");
 	/* Align the address wrt HPAGE_PUD_SIZE */
-	vaddr = (vaddr & HPAGE_PUD_MASK) + HPAGE_PUD_SIZE;
+	vaddr &= HPAGE_PUD_MASK;
 
 	set_pud_at(mm, vaddr, pudp, pud);
 	pudp_set_wrprotect(mm, vaddr, pudp);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 95918f410c0f..5560b50876fb 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1793,7 +1793,7 @@ retry:
 			SetPageHWPoison(page);
 			ClearPageHWPoison(head);
 		}
-		remove_hugetlb_page(h, page, false);
+		remove_hugetlb_page(h, head, false);
 		h->max_huge_pages--;
 		spin_unlock_irq(&hugetlb_lock);
 		update_and_free_page(h, head);
@@ -4889,10 +4889,20 @@ int hugetlb_mcopy_atomic_pte(struct mm_struct *dst_mm,
 		if (!page)
 			goto out;
 	} else if (!*pagep) {
-		ret = -ENOMEM;
+		/* If a page already exists, then it's UFFDIO_COPY for
+		 * a non-missing case. Return -EEXIST.
+		 */
+		if (vm_shared &&
+		    hugetlbfs_pagecache_present(h, dst_vma, dst_addr)) {
+			ret = -EEXIST;
+			goto out;
+		}
+
 		page = alloc_huge_page(dst_vma, dst_addr, 0);
-		if (IS_ERR(page))
+		if (IS_ERR(page)) {
+			ret = -ENOMEM;
 			goto out;
+		}
 
 		ret = copy_huge_page_from_user(page,
 						(const void __user *) src_addr,
diff --git a/mm/kasan/init.c b/mm/kasan/init.c
index c4605ac9837b..348f31d15a97 100644
--- a/mm/kasan/init.c
+++ b/mm/kasan/init.c
@@ -220,8 +220,8 @@ static int __ref zero_p4d_populate(pgd_t *pgd, unsigned long addr,
 /**
  * kasan_populate_early_shadow - populate shadow memory region with
  *                               kasan_early_shadow_page
- * @shadow_start - start of the memory range to populate
- * @shadow_end   - end of the memory range to populate
+ * @shadow_start: start of the memory range to populate
+ * @shadow_end: end of the memory range to populate
  */
 int __ref kasan_populate_early_shadow(const void *shadow_start,
 					const void *shadow_end)
diff --git a/mm/kfence/core.c b/mm/kfence/core.c
index e18fbbd5d9b4..4d21ac44d5d3 100644
--- a/mm/kfence/core.c
+++ b/mm/kfence/core.c
@@ -627,10 +627,10 @@ static void toggle_allocation_gate(struct work_struct *work)
 		 * During low activity with no allocations we might wait a
 		 * while; let's avoid the hung task warning.
 		 */
-		wait_event_timeout(allocation_wait, atomic_read(&kfence_allocation_gate),
-				   sysctl_hung_task_timeout_secs * HZ / 2);
+		wait_event_idle_timeout(allocation_wait, atomic_read(&kfence_allocation_gate),
+					sysctl_hung_task_timeout_secs * HZ / 2);
 	} else {
-		wait_event(allocation_wait, atomic_read(&kfence_allocation_gate));
+		wait_event_idle(allocation_wait, atomic_read(&kfence_allocation_gate));
 	}
 
 	/* Disable static key and reset timer. */
diff --git a/mm/memory.c b/mm/memory.c
index 730daa00952b..f3ffab9b9e39 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2939,6 +2939,7 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf)
 		}
 		flush_cache_page(vma, vmf->address, pte_pfn(vmf->orig_pte));
 		entry = mk_pte(new_page, vma->vm_page_prot);
+		entry = pte_sw_mkyoung(entry);
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
 
 		/*
@@ -3602,6 +3603,7 @@ static vm_fault_t do_anonymous_page(struct vm_fault *vmf)
 	__SetPageUptodate(page);
 
 	entry = mk_pte(page, vma->vm_page_prot);
+	entry = pte_sw_mkyoung(entry);
 	if (vma->vm_flags & VM_WRITE)
 		entry = pte_mkwrite(pte_mkdirty(entry));
 
@@ -3786,6 +3788,8 @@ void do_set_pte(struct vm_fault *vmf, struct page *page, unsigned long addr)
 
 	if (prefault && arch_wants_old_prefaulted_pte())
 		entry = pte_mkold(entry);
+	else
+		entry = pte_sw_mkyoung(entry);
 
 	if (write)
 		entry = maybe_mkwrite(pte_mkdirty(entry), vma);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index aaa1655cf682..d1f5de1c1283 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -9158,6 +9158,8 @@ bool take_page_off_buddy(struct page *page)
 			del_page_from_free_list(page_head, zone, page_order);
 			break_down_buddy_pages(zone, page_head, page, 0,
 						page_order, migratetype);
+			if (!is_migrate_isolate(migratetype))
+				__mod_zone_freepage_state(zone, -1, migratetype);
 			ret = true;
 			break;
 		}
diff --git a/tools/testing/selftests/proc/.gitignore b/tools/testing/selftests/proc/.gitignore
index bed4b5318a86..8f3e72e626fa 100644
--- a/tools/testing/selftests/proc/.gitignore
+++ b/tools/testing/selftests/proc/.gitignore
@@ -10,6 +10,7 @@
 /proc-self-map-files-002
 /proc-self-syscall
 /proc-self-wchan
+/proc-subset-pid
 /proc-uptime-001
 /proc-uptime-002
 /read