Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:

 - a few misc things

 - ocfs2 updates

 - most of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (159 commits)
  tools/testing/selftests/proc/proc-self-syscall.c: remove duplicate include
  proc: more robust bulk read test
  proc: test /proc/*/maps, smaps, smaps_rollup, statm
  proc: use seq_puts() everywhere
  proc: read kernel cpu stat pointer once
  proc: remove unused argument in proc_pid_lookup()
  fs/proc/thread_self.c: code cleanup for proc_setup_thread_self()
  fs/proc/self.c: code cleanup for proc_setup_self()
  proc: return exit code 4 for skipped tests
  mm,mremap: bail out earlier in mremap_to under map pressure
  mm/sparse: fix a bad comparison
  mm/memory.c: do_fault: avoid usage of stale vm_area_struct
  writeback: fix inode cgroup switching comment
  mm/huge_memory.c: fix "orig_pud" set but not used
  mm/hotplug: fix an imbalance with DEBUG_PAGEALLOC
  mm/memcontrol.c: fix bad line in comment
  mm/cma.c: cma_declare_contiguous: correct err handling
  mm/page_ext.c: fix an imbalance with kmemleak
  mm/compaction: pass pgdat to too_many_isolated() instead of zone
  mm: remove zone_lru_lock() function, access ->lru_lock directly
  ...

Documentation/admin-guide/cgroup-v2.rst

@@ -1189,6 +1189,10 @@ PAGE_SIZE multiple when read back.
 		Amount of cached filesystem data that was modified and
 		is currently being written back to disk
 
+	  anon_thp
+		Amount of memory used in anonymous mappings backed by
+		transparent hugepages
+
 	  inactive_anon, active_anon, inactive_file, active_file, unevictable
 		Amount of memory, swap-backed and filesystem-backed,
 		on the internal memory management lists used by the
@@ -1248,6 +1252,18 @@ PAGE_SIZE multiple when read back.
 
 		Amount of reclaimed lazyfree pages
 
+	  thp_fault_alloc
+
+		Number of transparent hugepages which were allocated to satisfy
+		a page fault, including COW faults. This counter is not present
+		when CONFIG_TRANSPARENT_HUGEPAGE is not set.
+
+	  thp_collapse_alloc
+
+		Number of transparent hugepages which were allocated to allow
+		collapsing an existing range of pages. This counter is not
+		present when CONFIG_TRANSPARENT_HUGEPAGE is not set.
+
   memory.swap.current
 	A read-only single value file which exists on non-root
 	cgroups.

Documentation/admin-guide/mm/pagemap.rst

@@ -75,9 +75,10 @@ number of times a page is mapped.
     20. NOPAGE
     21. KSM
     22. THP
-    23. BALLOON
+    23. OFFLINE
     24. ZERO_PAGE
     25. IDLE
+    26. PGTABLE
 
  * ``/proc/kpagecgroup``.  This file contains a 64-bit inode number of the
    memory cgroup each page is charged to, indexed by PFN. Only available when
@@ -118,8 +119,8 @@ Short descriptions to the page flags
     identical memory pages dynamically shared between one or more processes
 22 - THP
     contiguous pages which construct transparent hugepages
-23 - BALLOON
-    balloon compaction page
+23 - OFFLINE
+    page is logically offline
 24 - ZERO_PAGE
     zero page for pfn_zero or huge_zero page
 25 - IDLE
@@ -128,6 +129,8 @@ Short descriptions to the page flags
     Note that this flag may be stale in case the page was accessed via
     a PTE. To make sure the flag is up-to-date one has to read
     ``/sys/kernel/mm/page_idle/bitmap`` first.
+26 - PGTABLE
+    page is in use as a page table
 
 IO related page flags
 ---------------------

Documentation/cgroup-v1/memcg_test.txt

@@ -107,9 +107,9 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
 
 8. LRU
         Each memcg has its own private LRU. Now, its handling is under global
-	VM's control (means that it's handled under global zone_lru_lock).
+	VM's control (means that it's handled under global pgdat->lru_lock).
 	Almost all routines around memcg's LRU is called by global LRU's
-	list management functions under zone_lru_lock().
+	list management functions under pgdat->lru_lock.
 
 	A special function is mem_cgroup_isolate_pages(). This scans
 	memcg's private LRU and call __isolate_lru_page() to extract a page

Documentation/cgroup-v1/memory.txt

@@ -267,11 +267,11 @@ When oom event notifier is registered, event will be delivered.
    Other lock order is following:
    PG_locked.
    mm->page_table_lock
-       zone_lru_lock
+       pgdat->lru_lock
 	  lock_page_cgroup.
   In many cases, just lock_page_cgroup() is called.
   per-zone-per-cgroup LRU (cgroup's private LRU) is just guarded by
-  zone_lru_lock, it has no lock of its own.
+  pgdat->lru_lock, it has no lock of its own.
 
 2.7 Kernel Memory Extension (CONFIG_MEMCG_KMEM)
 

MAINTAINERS

@@ -9835,6 +9835,14 @@ F:	kernel/sched/membarrier.c
 F:	include/uapi/linux/membarrier.h
 F:	arch/powerpc/include/asm/membarrier.h
 
+MEMBLOCK
+M:	Mike Rapoport <rppt@linux.ibm.com>
+L:	linux-mm@kvack.org
+S:	Maintained
+F:	include/linux/memblock.h
+F:	mm/memblock.c
+F:	Documentation/core-api/boot-time-mm.rst
+
 MEMORY MANAGEMENT
 L:	linux-mm@kvack.org
 W:	http://www.linux-mm.org

arch/alpha/include/asm/topology.h

@@ -4,6 +4,7 @@
 
 #include <linux/smp.h>
 #include <linux/threads.h>
+#include <linux/numa.h>
 #include <asm/machvec.h>
 
 #ifdef CONFIG_NUMA
@@ -29,7 +30,7 @@ static const struct cpumask *cpumask_of_node(int node)
 {
 	int cpu;
 
-	if (node == -1)
+	if (node == NUMA_NO_NODE)
 		return cpu_all_mask;
 
 	cpumask_clear(&node_to_cpumask_map[node]);

arch/arm64/Kconfig

@@ -1467,6 +1467,10 @@ config SYSVIPC_COMPAT
 	def_bool y
 	depends on COMPAT && SYSVIPC
 
+config ARCH_ENABLE_HUGEPAGE_MIGRATION
+	def_bool y
+	depends on HUGETLB_PAGE && MIGRATION
+
 menu "Power management options"
 
 source "kernel/power/Kconfig"

arch/arm64/include/asm/hugetlb.h

@@ -20,6 +20,11 @@
 
 #include <asm/page.h>
 
+#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
+#define arch_hugetlb_migration_supported arch_hugetlb_migration_supported
+extern bool arch_hugetlb_migration_supported(struct hstate *h);
+#endif
+
 #define __HAVE_ARCH_HUGE_PTEP_GET
 static inline pte_t huge_ptep_get(pte_t *ptep)
 {

arch/arm64/include/asm/memory.h

@@ -80,11 +80,7 @@
  */
 #ifdef CONFIG_KASAN
 #define KASAN_SHADOW_SIZE	(UL(1) << (VA_BITS - KASAN_SHADOW_SCALE_SHIFT))
-#ifdef CONFIG_KASAN_EXTRA
-#define KASAN_THREAD_SHIFT	2
-#else
 #define KASAN_THREAD_SHIFT	1
-#endif /* CONFIG_KASAN_EXTRA */
 #else
 #define KASAN_SHADOW_SIZE	(0)
 #define KASAN_THREAD_SHIFT	0

arch/arm64/kernel/machine_kexec.c

@@ -321,7 +321,7 @@ void crash_post_resume(void)
  * but does not hold any data of loaded kernel image.
  *
  * Note that all the pages in crash dump kernel memory have been initially
- * marked as Reserved in kexec_reserve_crashkres_pages().
+ * marked as Reserved as memory was allocated via memblock_reserve().
  *
  * In hibernation, the pages which are Reserved and yet "nosave" are excluded
  * from the hibernation iamge. crash_is_nosave() does thich check for crash
@@ -361,7 +361,6 @@ void crash_free_reserved_phys_range(unsigned long begin, unsigned long end)
 
 	for (addr = begin; addr < end; addr += PAGE_SIZE) {
 		page = phys_to_page(addr);
-		ClearPageReserved(page);
 		free_reserved_page(page);
 	}
 }

arch/arm64/mm/hugetlbpage.c

@@ -27,6 +27,26 @@
 #include <asm/tlbflush.h>
 #include <asm/pgalloc.h>
 
+#ifdef CONFIG_ARCH_ENABLE_HUGEPAGE_MIGRATION
+bool arch_hugetlb_migration_supported(struct hstate *h)
+{
+	size_t pagesize = huge_page_size(h);
+
+	switch (pagesize) {
+#ifdef CONFIG_ARM64_4K_PAGES
+	case PUD_SIZE:
+#endif
+	case PMD_SIZE:
+	case CONT_PMD_SIZE:
+	case CONT_PTE_SIZE:
+		return true;
+	}
+	pr_warn("%s: unrecognized huge page size 0x%lx\n",
+			__func__, pagesize);
+	return false;
+}
+#endif
+
 int pmd_huge(pmd_t pmd)
 {
 	return pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT);

arch/arm64/mm/init.c

@@ -118,35 +118,10 @@ static void __init reserve_crashkernel(void)
 	crashk_res.start = crash_base;
 	crashk_res.end = crash_base + crash_size - 1;
 }
-
-static void __init kexec_reserve_crashkres_pages(void)
-{
-#ifdef CONFIG_HIBERNATION
-	phys_addr_t addr;
-	struct page *page;
-
-	if (!crashk_res.end)
-		return;
-
-	/*
-	 * To reduce the size of hibernation image, all the pages are
-	 * marked as Reserved initially.
-	 */
-	for (addr = crashk_res.start; addr < (crashk_res.end + 1);
-			addr += PAGE_SIZE) {
-		page = phys_to_page(addr);
-		SetPageReserved(page);
-	}
-#endif
-}
 #else
 static void __init reserve_crashkernel(void)
 {
 }
-
-static void __init kexec_reserve_crashkres_pages(void)
-{
-}
 #endif /* CONFIG_KEXEC_CORE */
 
 #ifdef CONFIG_CRASH_DUMP
@@ -586,8 +561,6 @@ void __init mem_init(void)
 	/* this will put all unused low memory onto the freelists */
 	memblock_free_all();
 
-	kexec_reserve_crashkres_pages();
-
 	mem_init_print_info(NULL);
 
 	/*

arch/arm64/mm/numa.c

@@ -120,7 +120,7 @@ static void __init setup_node_to_cpumask_map(void)
 	}
 
 	/* cpumask_of_node() will now work */
-	pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids);
+	pr_debug("Node to cpumask map for %u nodes\n", nr_node_ids);
 }
 
 /*

arch/ia64/kernel/numa.c

@@ -74,7 +74,7 @@ void __init build_cpu_to_node_map(void)
 		cpumask_clear(&node_to_cpu_mask[node]);
 
 	for_each_possible_early_cpu(cpu) {
-		node = -1;
+		node = NUMA_NO_NODE;
 		for (i = 0; i < NR_CPUS; ++i)
 			if (cpu_physical_id(cpu) == node_cpuid[i].phys_id) {
 				node = node_cpuid[i].nid;

arch/ia64/kernel/perfmon.c

@@ -583,17 +583,6 @@ pfm_put_task(struct task_struct *task)
 	if (task != current) put_task_struct(task);
 }
 
-static inline void
-pfm_reserve_page(unsigned long a)
-{
-	SetPageReserved(vmalloc_to_page((void *)a));
-}
-static inline void
-pfm_unreserve_page(unsigned long a)
-{
-	ClearPageReserved(vmalloc_to_page((void*)a));
-}
-
 static inline unsigned long
 pfm_protect_ctx_ctxsw(pfm_context_t *x)
 {
@@ -816,44 +805,6 @@ pfm_reset_msgq(pfm_context_t *ctx)
 	DPRINT(("ctx=%p msgq reset\n", ctx));
 }
 
-static void *
-pfm_rvmalloc(unsigned long size)
-{
-	void *mem;
-	unsigned long addr;
-
-	size = PAGE_ALIGN(size);
-	mem  = vzalloc(size);
-	if (mem) {
-		//printk("perfmon: CPU%d pfm_rvmalloc(%ld)=%p\n", smp_processor_id(), size, mem);
-		addr = (unsigned long)mem;
-		while (size > 0) {
-			pfm_reserve_page(addr);
-			addr+=PAGE_SIZE;
-			size-=PAGE_SIZE;
-		}
-	}
-	return mem;
-}
-
-static void
-pfm_rvfree(void *mem, unsigned long size)
-{
-	unsigned long addr;
-
-	if (mem) {
-		DPRINT(("freeing physical buffer @%p size=%lu\n", mem, size));
-		addr = (unsigned long) mem;
-		while ((long) size > 0) {
-			pfm_unreserve_page(addr);
-			addr+=PAGE_SIZE;
-			size-=PAGE_SIZE;
-		}
-		vfree(mem);
-	}
-	return;
-}
-
 static pfm_context_t *
 pfm_context_alloc(int ctx_flags)
 {
@@ -1498,7 +1449,7 @@ pfm_free_smpl_buffer(pfm_context_t *ctx)
 	/*
 	 * free the buffer
 	 */
-	pfm_rvfree(ctx->ctx_smpl_hdr, ctx->ctx_smpl_size);
+	vfree(ctx->ctx_smpl_hdr);
 
 	ctx->ctx_smpl_hdr  = NULL;
 	ctx->ctx_smpl_size = 0UL;
@@ -2137,7 +2088,7 @@ doit:
 	 * All memory free operations (especially for vmalloc'ed memory)
 	 * MUST be done with interrupts ENABLED.
 	 */
-	if (smpl_buf_addr)  pfm_rvfree(smpl_buf_addr, smpl_buf_size);
+	vfree(smpl_buf_addr);
 
 	/*
 	 * return the memory used by the context
@@ -2266,10 +2217,8 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t
 
 	/*
 	 * We do the easy to undo allocations first.
- 	 *
-	 * pfm_rvmalloc(), clears the buffer, so there is no leak
 	 */
-	smpl_buf = pfm_rvmalloc(size);
+	smpl_buf = vzalloc(size);
 	if (smpl_buf == NULL) {
 		DPRINT(("Can't allocate sampling buffer\n"));
 		return -ENOMEM;
@@ -2346,7 +2295,7 @@ pfm_smpl_buffer_alloc(struct task_struct *task, struct file *filp, pfm_context_t
 error:
 	vm_area_free(vma);
 error_kmem:
-	pfm_rvfree(smpl_buf, size);
+	vfree(smpl_buf);
 
 	return -ENOMEM;
 }

arch/ia64/mm/discontig.c

@@ -227,7 +227,7 @@ void __init setup_per_cpu_areas(void)
 	 * CPUs are put into groups according to node.  Walk cpu_map
 	 * and create new groups at node boundaries.
 	 */
-	prev_node = -1;
+	prev_node = NUMA_NO_NODE;
 	ai->nr_groups = 0;
 	for (unit = 0; unit < nr_units; unit++) {
 		cpu = cpu_map[unit];
@@ -435,7 +435,7 @@ static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize)
 {
 	void *ptr = NULL;
 	u8 best = 0xff;
-	int bestnode = -1, node, anynode = 0;
+	int bestnode = NUMA_NO_NODE, node, anynode = 0;
 
 	for_each_online_node(node) {
 		if (node_isset(node, memory_less_mask))
@@ -447,7 +447,7 @@ static void __init *memory_less_node_alloc(int nid, unsigned long pernodesize)
 		anynode = node;
 	}
 
-	if (bestnode == -1)
+	if (bestnode == NUMA_NO_NODE)
 		bestnode = anynode;
 
 	ptr = memblock_alloc_try_nid(pernodesize, PERCPU_PAGE_SIZE,

arch/m68k/mm/memory.c

@@ -51,7 +51,7 @@ void __init init_pointer_table(unsigned long ptable)
 	pr_debug("init_pointer_table: %lx, %x\n", ptable, PD_MARKBITS(dp));
 
 	/* unreserve the page so it's possible to free that page */
-	PD_PAGE(dp)->flags &= ~(1 << PG_reserved);
+	__ClearPageReserved(PD_PAGE(dp));
 	init_page_count(PD_PAGE(dp));
 
 	return;

arch/powerpc/include/asm/book3s/64/hugetlb.h

@@ -13,6 +13,10 @@ radix__hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 				unsigned long len, unsigned long pgoff,
 				unsigned long flags);
 
+extern void radix__huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+						unsigned long addr, pte_t *ptep,
+						pte_t old_pte, pte_t pte);
+
 static inline int hstate_get_psize(struct hstate *hstate)
 {
 	unsigned long shift;
@@ -42,4 +46,12 @@ static inline bool gigantic_page_supported(void)
 /* hugepd entry valid bit */
 #define HUGEPD_VAL_BITS		(0x8000000000000000UL)
 
+#define huge_ptep_modify_prot_start huge_ptep_modify_prot_start
+extern pte_t huge_ptep_modify_prot_start(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep);
+
+#define huge_ptep_modify_prot_commit huge_ptep_modify_prot_commit
+extern void huge_ptep_modify_prot_commit(struct vm_area_struct *vma,
+					 unsigned long addr, pte_t *ptep,
+					 pte_t old_pte, pte_t new_pte);
 #endif

arch/powerpc/include/asm/book3s/64/pgtable.h

@@ -1306,6 +1306,24 @@ static inline int pud_pfn(pud_t pud)
 	BUILD_BUG();
 	return 0;
 }
+#define __HAVE_ARCH_PTEP_MODIFY_PROT_TRANSACTION
+pte_t ptep_modify_prot_start(struct vm_area_struct *, unsigned long, pte_t *);
+void ptep_modify_prot_commit(struct vm_area_struct *, unsigned long,
+			     pte_t *, pte_t, pte_t);
+
+/*
+ * Returns true for a R -> RW upgrade of pte
+ */
+static inline bool is_pte_rw_upgrade(unsigned long old_val, unsigned long new_val)
+{
+	if (!(old_val & _PAGE_READ))
+		return false;
+
+	if ((!(old_val & _PAGE_WRITE)) && (new_val & _PAGE_WRITE))
+		return true;
+
+	return false;
+}
 
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_POWERPC_BOOK3S_64_PGTABLE_H_ */

arch/powerpc/include/asm/book3s/64/radix.h

@@ -127,6 +127,10 @@ extern void radix__ptep_set_access_flags(struct vm_area_struct *vma, pte_t *ptep
 					 pte_t entry, unsigned long address,
 					 int psize);
 
+extern void radix__ptep_modify_prot_commit(struct vm_area_struct *vma,
+					   unsigned long addr, pte_t *ptep,
+					   pte_t old_pte, pte_t pte);
+
 static inline unsigned long __radix_pte_update(pte_t *ptep, unsigned long clr,
 					       unsigned long set)
 {