Merge branch 'akpm' (patches from Andrew)

Merge misc updates from Andrew Morton:
 "173 patches.

  Subsystems affected by this series: ia64, ocfs2, block, and mm (debug,
  pagecache, gup, swap, shmem, memcg, selftests, pagemap, mremap,
  bootmem, sparsemem, vmalloc, kasan, pagealloc, memory-failure,
  hugetlb, userfaultfd, vmscan, compaction, mempolicy, memblock,
  oom-kill, migration, ksm, percpu, vmstat, and madvise)"

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (173 commits)
  mm/madvise: add MADV_WILLNEED to process_madvise()
  mm/vmstat: remove unneeded return value
  mm/vmstat: simplify the array size calculation
  mm/vmstat: correct some wrong comments
  mm/percpu,c: remove obsolete comments of pcpu_chunk_populated()
  selftests: vm: add COW time test for KSM pages
  selftests: vm: add KSM merging time test
  mm: KSM: fix data type
  selftests: vm: add KSM merging across nodes test
  selftests: vm: add KSM zero page merging test
  selftests: vm: add KSM unmerge test
  selftests: vm: add KSM merge test
  mm/migrate: correct kernel-doc notation
  mm: wire up syscall process_mrelease
  mm: introduce process_mrelease system call
  memblock: make memblock_find_in_range method private
  mm/mempolicy.c: use in_task() in mempolicy_slab_node()
  mm/mempolicy: unify the create() func for bind/interleave/prefer-many policies
  mm/mempolicy: advertise new MPOL_PREFERRED_MANY
  mm/hugetlb: add support for mempolicy MPOL_PREFERRED_MANY
  ...

8 files changed, 27 insertions, 21 deletions

diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
index a5beae6daf20..61f18b72552b 100644
--- a/arch/x86/entry/syscalls/syscall_32.tbl
+++ b/arch/x86/entry/syscalls/syscall_32.tbl
@@ -452,3 +452,4 @@
 445	i386	landlock_add_rule	sys_landlock_add_rule
 446	i386	landlock_restrict_self	sys_landlock_restrict_self
 447	i386	memfd_secret		sys_memfd_secret
+448	i386	process_mrelease	sys_process_mrelease
diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
index f6b57799c1ea..807b6a1de8e8 100644
--- a/arch/x86/entry/syscalls/syscall_64.tbl
+++ b/arch/x86/entry/syscalls/syscall_64.tbl
@@ -369,6 +369,7 @@
 445	common	landlock_add_rule	sys_landlock_add_rule
 446	common	landlock_restrict_self	sys_landlock_restrict_self
 447	common	memfd_secret		sys_memfd_secret
+448	common	process_mrelease	sys_process_mrelease
 
 #
 # Due to a historical design error, certain syscalls are numbered differently
diff --git a/arch/x86/kernel/aperture_64.c b/arch/x86/kernel/aperture_64.c
index 294ed4392a0e..10562885f5fc 100644
--- a/arch/x86/kernel/aperture_64.c
+++ b/arch/x86/kernel/aperture_64.c
@@ -109,14 +109,13 @@ static u32 __init allocate_aperture(void)
 	 * memory. Unfortunately we cannot move it up because that would
 	 * make the IOMMU useless.
 	 */
-	addr = memblock_find_in_range(GART_MIN_ADDR, GART_MAX_ADDR,
-				      aper_size, aper_size);
+	addr = memblock_phys_alloc_range(aper_size, aper_size,
+					 GART_MIN_ADDR, GART_MAX_ADDR);
 	if (!addr) {
 		pr_err("Cannot allocate aperture memory hole [mem %#010lx-%#010lx] (%uKB)\n",
 		       addr, addr + aper_size - 1, aper_size >> 10);
 		return 0;
 	}
-	memblock_reserve(addr, aper_size);
 	pr_info("Mapping aperture over RAM [mem %#010lx-%#010lx] (%uKB)\n",
 		addr, addr + aper_size - 1, aper_size >> 10);
 	register_nosave_region(addr >> PAGE_SHIFT,
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index aa15132228da..525876e7b9f4 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -154,7 +154,7 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries)
 	if (num_entries > LDT_ENTRIES)
 		return NULL;
 
-	new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL);
+	new_ldt = kmalloc(sizeof(struct ldt_struct), GFP_KERNEL_ACCOUNT);
 	if (!new_ldt)
 		return NULL;
 
@@ -168,9 +168,9 @@ static struct ldt_struct *alloc_ldt_struct(unsigned int num_entries)
 	 * than PAGE_SIZE.
 	 */
 	if (alloc_size > PAGE_SIZE)
-		new_ldt->entries = vzalloc(alloc_size);
+		new_ldt->entries = __vmalloc(alloc_size, GFP_KERNEL_ACCOUNT | __GFP_ZERO);
 	else
-		new_ldt->entries = (void *)get_zeroed_page(GFP_KERNEL);
+		new_ldt->entries = (void *)get_zeroed_page(GFP_KERNEL_ACCOUNT);
 
 	if (!new_ldt->entries) {
 		kfree(new_ldt);
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 75ef19aa8903..23a14d82e783 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -127,14 +127,12 @@ __ref void *alloc_low_pages(unsigned int num)
 		unsigned long ret = 0;
 
 		if (min_pfn_mapped < max_pfn_mapped) {
-			ret = memblock_find_in_range(
+			ret = memblock_phys_alloc_range(
+					PAGE_SIZE * num, PAGE_SIZE,
 					min_pfn_mapped << PAGE_SHIFT,
-					max_pfn_mapped << PAGE_SHIFT,
-					PAGE_SIZE * num , PAGE_SIZE);
+					max_pfn_mapped << PAGE_SHIFT);
 		}
-		if (ret)
-			memblock_reserve(ret, PAGE_SIZE * num);
-		else if (can_use_brk_pgt)
+		if (!ret && can_use_brk_pgt)
 			ret = __pa(extend_brk(PAGE_SIZE * num, PAGE_SIZE));
 
 		if (!ret)
@@ -610,8 +608,17 @@ static void __init memory_map_top_down(unsigned long map_start,
 	unsigned long addr;
 	unsigned long mapped_ram_size = 0;
 
-	/* xen has big range in reserved near end of ram, skip it at first.*/
-	addr = memblock_find_in_range(map_start, map_end, PMD_SIZE, PMD_SIZE);
+	/*
+	 * Systems that have many reserved areas near top of the memory,
+	 * e.g. QEMU with less than 1G RAM and EFI enabled, or Xen, will
+	 * require lots of 4K mappings which may exhaust pgt_buf.
+	 * Start with top-most PMD_SIZE range aligned at PMD_SIZE to ensure
+	 * there is enough mapped memory that can be allocated from
+	 * memblock.
+	 */
+	addr = memblock_phys_alloc_range(PMD_SIZE, PMD_SIZE, map_start,
+					 map_end);
+	memblock_free(addr, PMD_SIZE);
 	real_end = addr + PMD_SIZE;
 
 	/* step_size need to be small so pgt_buf from BRK could cover it */
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index e94da744386f..a1b5c71099e6 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -376,15 +376,14 @@ static int __init numa_alloc_distance(void)
 	cnt++;
 	size = cnt * cnt * sizeof(numa_distance[0]);
 
-	phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
-				      size, PAGE_SIZE);
+	phys = memblock_phys_alloc_range(size, PAGE_SIZE, 0,
+					 PFN_PHYS(max_pfn_mapped));
 	if (!phys) {
 		pr_warn("Warning: can't allocate distance table!\n");
 		/* don't retry until explicitly reset */
 		numa_distance = (void *)1LU;
 		return -ENOMEM;
 	}
-	memblock_reserve(phys, size);
 
 	numa_distance = __va(phys);
 	numa_distance_cnt = cnt;
diff --git a/arch/x86/mm/numa_emulation.c b/arch/x86/mm/numa_emulation.c
index 87d77cc52f86..737491b13728 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/arch/x86/mm/numa_emulation.c
@@ -447,13 +447,12 @@ void __init numa_emulation(struct numa_meminfo *numa_meminfo, int numa_dist_cnt)
 	if (numa_dist_cnt) {
 		u64 phys;
 
-		phys = memblock_find_in_range(0, PFN_PHYS(max_pfn_mapped),
-					      phys_size, PAGE_SIZE);
+		phys = memblock_phys_alloc_range(phys_size, PAGE_SIZE, 0,
+						 PFN_PHYS(max_pfn_mapped));
 		if (!phys) {
 			pr_warn("NUMA: Warning: can't allocate copy of distance table, disabling emulation\n");
 			goto no_emu;
 		}
-		memblock_reserve(phys, phys_size);
 		phys_dist = __va(phys);
 
 		for (i = 0; i < numa_dist_cnt; i++)
diff --git a/arch/x86/realmode/init.c b/arch/x86/realmode/init.c
index 6534c92d0f83..31b5856010cb 100644
--- a/arch/x86/realmode/init.c
+++ b/arch/x86/realmode/init.c
@@ -28,7 +28,7 @@ void __init reserve_real_mode(void)
 	WARN_ON(slab_is_available());
 
 	/* Has to be under 1M so we can execute real-mode AP code. */
-	mem = memblock_find_in_range(0, 1<<20, size, PAGE_SIZE);
+	mem = memblock_phys_alloc_range(size, PAGE_SIZE, 0, 1<<20);
 	if (!mem)
 		pr_info("No sub-1M memory is available for the trampoline\n");
 	else