Merge v5.6-rc5 into drm-next

Requested my mripard for some misc patches that need this as a base.

Signed-off-by: Dave Airlie <airlied@redhat.com>

12 files changed, 82 insertions, 27 deletions

diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index b08b199f9a11..24ad53b4dfc0 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -3043,8 +3043,7 @@ void set_pmd_migration_entry(struct page_vma_mapped_walk *pvmw,
 		return;
 
 	flush_cache_range(vma, address, address + HPAGE_PMD_SIZE);
-	pmdval = *pvmw->pmd;
-	pmdp_invalidate(vma, address, pvmw->pmd);
+	pmdval = pmdp_invalidate(vma, address, pvmw->pmd);
 	if (pmd_dirty(pmdval))
 		set_page_dirty(page);
 	entry = make_migration_entry(page, pmd_write(pmdval));
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 6f6dc8712e39..d09776cd6e10 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -409,8 +409,10 @@ int memcg_expand_shrinker_maps(int new_id)
 		if (mem_cgroup_is_root(memcg))
 			continue;
 		ret = memcg_expand_one_shrinker_map(memcg, size, old_size);
-		if (ret)
+		if (ret) {
+			mem_cgroup_iter_break(NULL, memcg);
 			goto unlock;
+		}
 	}
 unlock:
 	if (!ret)
diff --git a/mm/memory.c b/mm/memory.c
index 0bccc622e482..e8bfdf0d9d1d 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -2257,7 +2257,7 @@ static inline bool cow_user_page(struct page *dst, struct page *src,
 	bool ret;
 	void *kaddr;
 	void __user *uaddr;
-	bool force_mkyoung;
+	bool locked = false;
 	struct vm_area_struct *vma = vmf->vma;
 	struct mm_struct *mm = vma->vm_mm;
 	unsigned long addr = vmf->address;
@@ -2282,11 +2282,11 @@ static inline bool cow_user_page(struct page *dst, struct page *src,
 	 * On architectures with software "accessed" bits, we would
 	 * take a double page fault, so mark it accessed here.
 	 */
-	force_mkyoung = arch_faults_on_old_pte() && !pte_young(vmf->orig_pte);
-	if (force_mkyoung) {
+	if (arch_faults_on_old_pte() && !pte_young(vmf->orig_pte)) {
 		pte_t entry;
 
 		vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl);
+		locked = true;
 		if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) {
 			/*
 			 * Other thread has already handled the fault
@@ -2310,18 +2310,37 @@ static inline bool cow_user_page(struct page *dst, struct page *src,
 	 * zeroes.
 	 */
 	if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) {
+		if (locked)
+			goto warn;
+
+		/* Re-validate under PTL if the page is still mapped */
+		vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl);
+		locked = true;
+		if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) {
+			/* The PTE changed under us. Retry page fault. */
+			ret = false;
+			goto pte_unlock;
+		}
+
 		/*
-		 * Give a warn in case there can be some obscure
-		 * use-case
+		 * The same page can be mapped back since last copy attampt.
+		 * Try to copy again under PTL.
 		 */
-		WARN_ON_ONCE(1);
-		clear_page(kaddr);
+		if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) {
+			/*
+			 * Give a warn in case there can be some obscure
+			 * use-case
+			 */
+warn:
+			WARN_ON_ONCE(1);
+			clear_page(kaddr);
+		}
 	}
 
 	ret = true;
 
 pte_unlock:
-	if (force_mkyoung)
+	if (locked)
 		pte_unmap_unlock(vmf->pte, vmf->ptl);
 	kunmap_atomic(kaddr);
 	flush_dcache_page(dst);
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 0a54ffac8c68..19389cdc16a5 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -574,7 +574,13 @@ EXPORT_SYMBOL_GPL(restore_online_page_callback);
 
 void generic_online_page(struct page *page, unsigned int order)
 {
-	kernel_map_pages(page, 1 << order, 1);
+	/*
+	 * Freeing the page with debug_pagealloc enabled will try to unmap it,
+	 * so we should map it first. This is better than introducing a special
+	 * case in page freeing fast path.
+	 */
+	if (debug_pagealloc_enabled_static())
+		kernel_map_pages(page, 1 << order, 1);
 	__free_pages_core(page, order);
 	totalram_pages_add(1UL << order);
 #ifdef CONFIG_HIGHMEM
diff --git a/mm/mmap.c b/mm/mmap.c
index 6756b8bb0033..d681a20eb4ea 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -195,8 +195,6 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
 	bool downgraded = false;
 	LIST_HEAD(uf);
 
-	brk = untagged_addr(brk);
-
 	if (down_write_killable(&mm->mmap_sem))
 		return -EINTR;
 
@@ -1557,8 +1555,6 @@ unsigned long ksys_mmap_pgoff(unsigned long addr, unsigned long len,
 	struct file *file = NULL;
 	unsigned long retval;
 
-	addr = untagged_addr(addr);
-
 	if (!(flags & MAP_ANONYMOUS)) {
 		audit_mmap_fd(fd, flags);
 		file = fget(fd);
diff --git a/mm/mprotect.c b/mm/mprotect.c
index 7a8e84f86831..311c0dadf71c 100644
--- a/mm/mprotect.c
+++ b/mm/mprotect.c
@@ -161,6 +161,31 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
 	return pages;
 }
 
+/*
+ * Used when setting automatic NUMA hinting protection where it is
+ * critical that a numa hinting PMD is not confused with a bad PMD.
+ */
+static inline int pmd_none_or_clear_bad_unless_trans_huge(pmd_t *pmd)
+{
+	pmd_t pmdval = pmd_read_atomic(pmd);
+
+	/* See pmd_none_or_trans_huge_or_clear_bad for info on barrier */
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+	barrier();
+#endif
+
+	if (pmd_none(pmdval))
+		return 1;
+	if (pmd_trans_huge(pmdval))
+		return 0;
+	if (unlikely(pmd_bad(pmdval))) {
+		pmd_clear_bad(pmd);
+		return 1;
+	}
+
+	return 0;
+}
+
 static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		pud_t *pud, unsigned long addr, unsigned long end,
 		pgprot_t newprot, int dirty_accountable, int prot_numa)
@@ -178,8 +203,17 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma,
 		unsigned long this_pages;
 
 		next = pmd_addr_end(addr, end);
-		if (!is_swap_pmd(*pmd) && !pmd_trans_huge(*pmd) && !pmd_devmap(*pmd)
-				&& pmd_none_or_clear_bad(pmd))
+
+		/*
+		 * Automatic NUMA balancing walks the tables with mmap_sem
+		 * held for read. It's possible a parallel update to occur
+		 * between pmd_trans_huge() and a pmd_none_or_clear_bad()
+		 * check leading to a false positive and clearing.
+		 * Hence, it's necessary to atomically read the PMD value
+		 * for all the checks.
+		 */
+		if (!is_swap_pmd(*pmd) && !pmd_devmap(*pmd) &&
+		     pmd_none_or_clear_bad_unless_trans_huge(pmd))
 			goto next;
 
 		/* invoke the mmu notifier if the pmd is populated */
diff --git a/mm/mremap.c b/mm/mremap.c
index 122938dcec15..af363063ea23 100644
--- a/mm/mremap.c
+++ b/mm/mremap.c
@@ -607,7 +607,6 @@ SYSCALL_DEFINE5(mremap, unsigned long, addr, unsigned long, old_len,
 	LIST_HEAD(uf_unmap);
 
 	addr = untagged_addr(addr);
-	new_addr = untagged_addr(new_addr);
 
 	if (flags & ~(MREMAP_FIXED | MREMAP_MAYMOVE))
 		return ret;
diff --git a/mm/shmem.c b/mm/shmem.c
index c8f7540ef048..aad3ba74b0e9 100644
--- a/mm/shmem.c
+++ b/mm/shmem.c
@@ -3386,8 +3386,6 @@ static const struct constant_table shmem_param_enums_huge[] = {
 	{"always",	SHMEM_HUGE_ALWAYS },
 	{"within_size",	SHMEM_HUGE_WITHIN_SIZE },
 	{"advise",	SHMEM_HUGE_ADVISE },
-	{"deny",	SHMEM_HUGE_DENY },
-	{"force",	SHMEM_HUGE_FORCE },
 	{}
 };
 
diff --git a/mm/sparse.c b/mm/sparse.c
index c184b69460b7..596b2a45b100 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -876,7 +876,7 @@ int __meminit sparse_add_section(int nid, unsigned long start_pfn,
 	 * Poison uninitialized struct pages in order to catch invalid flags
 	 * combinations.
 	 */
-	page_init_poison(pfn_to_page(start_pfn), sizeof(struct page) * nr_pages);
+	page_init_poison(memmap, sizeof(struct page) * nr_pages);
 
 	ms = __nr_to_section(section_nr);
 	set_section_nid(section_nr, nid);
diff --git a/mm/swapfile.c b/mm/swapfile.c
index 2c33ff456ed5..b2a2e45c9a36 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -3157,7 +3157,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags)
 	mapping = swap_file->f_mapping;
 	inode = mapping->host;
 
-	/* If S_ISREG(inode->i_mode) will do inode_lock(inode); */
+	/* will take i_rwsem; */
 	error = claim_swapfile(p, inode);
 	if (unlikely(error))
 		goto bad_swap;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index c05eb9efec07..876370565455 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2415,10 +2415,13 @@ out:
 			/*
 			 * Scan types proportional to swappiness and
 			 * their relative recent reclaim efficiency.
-			 * Make sure we don't miss the last page
-			 * because of a round-off error.
+			 * Make sure we don't miss the last page on
+			 * the offlined memory cgroups because of a
+			 * round-off error.
 			 */
-			scan = DIV64_U64_ROUND_UP(scan * fraction[file],
+			scan = mem_cgroup_online(memcg) ?
+			       div64_u64(scan * fraction[file], denominator) :
+			       DIV64_U64_ROUND_UP(scan * fraction[file],
 						  denominator);
 			break;
 		case SCAN_FILE:
diff --git a/mm/z3fold.c b/mm/z3fold.c
index 43754d8ebce8..42f31c4b53ad 100644
--- a/mm/z3fold.c
+++ b/mm/z3fold.c
@@ -41,7 +41,6 @@
 #include <linux/workqueue.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
-#include <linux/rwlock.h>
 #include <linux/zpool.h>
 #include <linux/magic.h>