Merge remote-tracking branch 'tip/sched/arm64' into for-next/core

* tip/sched/arm64: (785 commits)
  Documentation: arm64: describe asymmetric 32-bit support
  arm64: Remove logic to kill 32-bit tasks on 64-bit-only cores
  arm64: Hook up cmdline parameter to allow mismatched 32-bit EL0
  arm64: Advertise CPUs capable of running 32-bit applications in sysfs
  arm64: Prevent offlining first CPU with 32-bit EL0 on mismatched system
  arm64: exec: Adjust affinity for compat tasks with mismatched 32-bit EL0
  arm64: Implement task_cpu_possible_mask()
  sched: Introduce dl_task_check_affinity() to check proposed affinity
  sched: Allow task CPU affinity to be restricted on asymmetric systems
  sched: Split the guts of sched_setaffinity() into a helper function
  sched: Introduce task_struct::user_cpus_ptr to track requested affinity
  sched: Reject CPU affinity changes based on task_cpu_possible_mask()
  cpuset: Cleanup cpuset_cpus_allowed_fallback() use in select_fallback_rq()
  cpuset: Honour task_cpu_possible_mask() in guarantee_online_cpus()
  cpuset: Don't use the cpu_possible_mask as a last resort for cgroup v1
  sched: Introduce task_cpu_possible_mask() to limit fallback rq selection
  sched: Cgroup SCHED_IDLE support
  sched/topology: Skip updating masks for non-online nodes
  Linux 5.14-rc6
  lib: use PFN_PHYS() in devmem_is_allowed()
  ...

7 files changed, 41 insertions, 28 deletions

diff --git a/mm/gup.c b/mm/gup.c
index 42b8b1fa6521..b94717977d17 100644
--- a/mm/gup.c
+++ b/mm/gup.c
@@ -1558,9 +1558,12 @@ long faultin_vma_page_range(struct vm_area_struct *vma, unsigned long start,
 		gup_flags |= FOLL_WRITE;
 
 	/*
-	 * See check_vma_flags(): Will return -EFAULT on incompatible mappings
-	 * or with insufficient permissions.
+	 * We want to report -EINVAL instead of -EFAULT for any permission
+	 * problems or incompatible mappings.
 	 */
+	if (check_vma_flags(vma, gup_flags))
+		return -EINVAL;
+
 	return __get_user_pages(mm, start, nr_pages, gup_flags,
 				NULL, NULL, locked);
 }
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 228a2fbe0657..73d46d16d575 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -290,7 +290,7 @@ static void hex_dump_object(struct seq_file *seq,
 	warn_or_seq_printf(seq, "  hex dump (first %zu bytes):\n", len);
 	kasan_disable_current();
 	warn_or_seq_hex_dump(seq, DUMP_PREFIX_NONE, HEX_ROW_SIZE,
-			     HEX_GROUP_SIZE, ptr, len, HEX_ASCII);
+			     HEX_GROUP_SIZE, kasan_reset_tag((void *)ptr), len, HEX_ASCII);
 	kasan_enable_current();
 }
 
@@ -1171,7 +1171,7 @@ static bool update_checksum(struct kmemleak_object *object)
 
 	kasan_disable_current();
 	kcsan_disable_current();
-	object->checksum = crc32(0, (void *)object->pointer, object->size);
+	object->checksum = crc32(0, kasan_reset_tag((void *)object->pointer), object->size);
 	kasan_enable_current();
 	kcsan_enable_current();
 
@@ -1246,7 +1246,7 @@ static void scan_block(void *_start, void *_end,
 			break;
 
 		kasan_disable_current();
-		pointer = *ptr;
+		pointer = *(unsigned long *)kasan_reset_tag((void *)ptr);
 		kasan_enable_current();
 
 		untagged_ptr = (unsigned long)kasan_reset_tag((void *)pointer);
diff --git a/mm/madvise.c b/mm/madvise.c
index 6d3d348b17f4..5c065bc8b5f6 100644
--- a/mm/madvise.c
+++ b/mm/madvise.c
@@ -862,10 +862,12 @@ static long madvise_populate(struct vm_area_struct *vma,
 			switch (pages) {
 			case -EINTR:
 				return -EINTR;
-			case -EFAULT: /* Incompatible mappings / permissions. */
+			case -EINVAL: /* Incompatible mappings / permissions. */
 				return -EINVAL;
 			case -EHWPOISON:
 				return -EHWPOISON;
+			case -EFAULT: /* VM_FAULT_SIGBUS or VM_FAULT_SIGSEGV */
+				return -EFAULT;
 			default:
 				pr_warn_once("%s: unhandled return value: %ld\n",
 					     __func__, pages);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index ae1f5d0cb581..702a81dfe72d 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -3106,13 +3106,15 @@ void mod_objcg_state(struct obj_cgroup *objcg, struct pglist_data *pgdat,
 		stock->cached_pgdat = pgdat;
 	} else if (stock->cached_pgdat != pgdat) {
 		/* Flush the existing cached vmstat data */
+		struct pglist_data *oldpg = stock->cached_pgdat;
+
 		if (stock->nr_slab_reclaimable_b) {
-			mod_objcg_mlstate(objcg, pgdat, NR_SLAB_RECLAIMABLE_B,
+			mod_objcg_mlstate(objcg, oldpg, NR_SLAB_RECLAIMABLE_B,
 					  stock->nr_slab_reclaimable_b);
 			stock->nr_slab_reclaimable_b = 0;
 		}
 		if (stock->nr_slab_unreclaimable_b) {
-			mod_objcg_mlstate(objcg, pgdat, NR_SLAB_UNRECLAIMABLE_B,
+			mod_objcg_mlstate(objcg, oldpg, NR_SLAB_UNRECLAIMABLE_B,
 					  stock->nr_slab_unreclaimable_b);
 			stock->nr_slab_unreclaimable_b = 0;
 		}
@@ -3574,7 +3576,8 @@ static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap)
 	unsigned long val;
 
 	if (mem_cgroup_is_root(memcg)) {
-		cgroup_rstat_flush(memcg->css.cgroup);
+		/* mem_cgroup_threshold() calls here from irqsafe context */
+		cgroup_rstat_flush_irqsafe(memcg->css.cgroup);
 		val = memcg_page_state(memcg, NR_FILE_PAGES) +
 			memcg_page_state(memcg, NR_ANON_MAPPED);
 		if (swap)
diff --git a/mm/migrate.c b/mm/migrate.c
index 34a9ad3e0a4f..7e240437e7d9 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -2068,7 +2068,7 @@ int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma,
 	LIST_HEAD(migratepages);
 	new_page_t *new;
 	bool compound;
-	unsigned int nr_pages = thp_nr_pages(page);
+	int nr_pages = thp_nr_pages(page);
 
 	/*
 	 * PTE mapped THP or HugeTLB page can't reach here so the page could
diff --git a/mm/slab.h b/mm/slab.h
index f997fd5e42c8..58c01a34e5b8 100644
--- a/mm/slab.h
+++ b/mm/slab.h
@@ -346,7 +346,7 @@ static inline void memcg_slab_free_hook(struct kmem_cache *s_orig,
 			continue;
 
 		page = virt_to_head_page(p[i]);
-		objcgs = page_objcgs(page);
+		objcgs = page_objcgs_check(page);
 		if (!objcgs)
 			continue;
 
diff --git a/mm/slub.c b/mm/slub.c
index 090fa14628f9..f77d8cd79ef7 100644
--- a/mm/slub.c
+++ b/mm/slub.c
@@ -576,8 +576,8 @@ static void print_section(char *level, char *text, u8 *addr,
 			  unsigned int length)
 {
 	metadata_access_enable();
-	print_hex_dump(level, kasan_reset_tag(text), DUMP_PREFIX_ADDRESS,
-			16, 1, addr, length, 1);
+	print_hex_dump(level, text, DUMP_PREFIX_ADDRESS,
+			16, 1, kasan_reset_tag((void *)addr), length, 1);
 	metadata_access_disable();
 }
 
@@ -1400,12 +1400,13 @@ check_slabs:
 static int __init setup_slub_debug(char *str)
 {
 	slab_flags_t flags;
+	slab_flags_t global_flags;
 	char *saved_str;
 	char *slab_list;
 	bool global_slub_debug_changed = false;
 	bool slab_list_specified = false;
 
-	slub_debug = DEBUG_DEFAULT_FLAGS;
+	global_flags = DEBUG_DEFAULT_FLAGS;
 	if (*str++ != '=' || !*str)
 		/*
 		 * No options specified. Switch on full debugging.
@@ -1417,7 +1418,7 @@ static int __init setup_slub_debug(char *str)
 		str = parse_slub_debug_flags(str, &flags, &slab_list, true);
 
 		if (!slab_list) {
-			slub_debug = flags;
+			global_flags = flags;
 			global_slub_debug_changed = true;
 		} else {
 			slab_list_specified = true;
@@ -1426,16 +1427,18 @@ static int __init setup_slub_debug(char *str)
 
 	/*
 	 * For backwards compatibility, a single list of flags with list of
-	 * slabs means debugging is only enabled for those slabs, so the global
-	 * slub_debug should be 0. We can extended that to multiple lists as
+	 * slabs means debugging is only changed for those slabs, so the global
+	 * slub_debug should be unchanged (0 or DEBUG_DEFAULT_FLAGS, depending
+	 * on CONFIG_SLUB_DEBUG_ON). We can extended that to multiple lists as
 	 * long as there is no option specifying flags without a slab list.
 	 */
 	if (slab_list_specified) {
 		if (!global_slub_debug_changed)
-			slub_debug = 0;
+			global_flags = slub_debug;
 		slub_debug_string = saved_str;
 	}
 out:
+	slub_debug = global_flags;
 	if (slub_debug != 0 || slub_debug_string)
 		static_branch_enable(&slub_debug_enabled);
 	else
@@ -3236,6 +3239,16 @@ struct detached_freelist {
 	struct kmem_cache *s;
 };
 
+static inline void free_nonslab_page(struct page *page, void *object)
+{
+	unsigned int order = compound_order(page);
+
+	VM_BUG_ON_PAGE(!PageCompound(page), page);
+	kfree_hook(object);
+	mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B, -(PAGE_SIZE << order));
+	__free_pages(page, order);
+}
+
 /*
  * This function progressively scans the array with free objects (with
  * a limited look ahead) and extract objects belonging to the same
@@ -3272,9 +3285,7 @@ int build_detached_freelist(struct kmem_cache *s, size_t size,
 	if (!s) {
 		/* Handle kalloc'ed objects */
 		if (unlikely(!PageSlab(page))) {
-			BUG_ON(!PageCompound(page));
-			kfree_hook(object);
-			__free_pages(page, compound_order(page));
+			free_nonslab_page(page, object);
 			p[size] = NULL; /* mark object processed */
 			return size;
 		}
@@ -4250,13 +4261,7 @@ void kfree(const void *x)
 
 	page = virt_to_head_page(x);
 	if (unlikely(!PageSlab(page))) {
-		unsigned int order = compound_order(page);
-
-		BUG_ON(!PageCompound(page));
-		kfree_hook(object);
-		mod_lruvec_page_state(page, NR_SLAB_UNRECLAIMABLE_B,
-				      -(PAGE_SIZE << order));
-		__free_pages(page, order);
+		free_nonslab_page(page, object);
 		return;
 	}
 	slab_free(page->slab_cache, page, object, NULL, 1, _RET_IP_);