Merge branch 'akpm' (patches from Andrew)

Merge updates from Andrew Morton:

 - a few misc things

 - ocfs2 updates

 - most of MM

* emailed patches from Andrew Morton <akpm@linux-foundation.org>: (132 commits)
  hugetlbfs: dirty pages as they are added to pagecache
  mm: export add_swap_extent()
  mm: split SWP_FILE into SWP_ACTIVATED and SWP_FS
  tools/testing/selftests/vm/map_fixed_noreplace.c: add test for MAP_FIXED_NOREPLACE
  mm: thp: relocate flush_cache_range() in migrate_misplaced_transhuge_page()
  mm: thp: fix mmu_notifier in migrate_misplaced_transhuge_page()
  mm: thp: fix MADV_DONTNEED vs migrate_misplaced_transhuge_page race condition
  mm/kasan/quarantine.c: make quarantine_lock a raw_spinlock_t
  mm/gup: cache dev_pagemap while pinning pages
  Revert "x86/e820: put !E820_TYPE_RAM regions into memblock.reserved"
  mm: return zero_resv_unavail optimization
  mm: zero remaining unavailable struct pages
  tools/testing/selftests/vm/gup_benchmark.c: add MAP_HUGETLB option
  tools/testing/selftests/vm/gup_benchmark.c: add MAP_SHARED option
  tools/testing/selftests/vm/gup_benchmark.c: allow user specified file
  tools/testing/selftests/vm/gup_benchmark.c: fix 'write' flag usage
  mm/gup_benchmark.c: add additional pinning methods
  mm/gup_benchmark.c: time put_page()
  mm: don't raise MEMCG_OOM event due to failed high-order allocation
  mm/page-writeback.c: fix range_cyclic writeback vs writepages deadlock
  ...

Documentation/accounting/psi.txt

@@ -0,0 +1,73 @@
+================================
+PSI - Pressure Stall Information
+================================
+
+:Date: April, 2018
+:Author: Johannes Weiner <hannes@cmpxchg.org>
+
+When CPU, memory or IO devices are contended, workloads experience
+latency spikes, throughput losses, and run the risk of OOM kills.
+
+Without an accurate measure of such contention, users are forced to
+either play it safe and under-utilize their hardware resources, or
+roll the dice and frequently suffer the disruptions resulting from
+excessive overcommit.
+
+The psi feature identifies and quantifies the disruptions caused by
+such resource crunches and the time impact it has on complex workloads
+or even entire systems.
+
+Having an accurate measure of productivity losses caused by resource
+scarcity aids users in sizing workloads to hardware--or provisioning
+hardware according to workload demand.
+
+As psi aggregates this information in realtime, systems can be managed
+dynamically using techniques such as load shedding, migrating jobs to
+other systems or data centers, or strategically pausing or killing low
+priority or restartable batch jobs.
+
+This allows maximizing hardware utilization without sacrificing
+workload health or risking major disruptions such as OOM kills.
+
+Pressure interface
+==================
+
+Pressure information for each resource is exported through the
+respective file in /proc/pressure/ -- cpu, memory, and io.
+
+The format for CPU is as such:
+
+some avg10=0.00 avg60=0.00 avg300=0.00 total=0
+
+and for memory and IO:
+
+some avg10=0.00 avg60=0.00 avg300=0.00 total=0
+full avg10=0.00 avg60=0.00 avg300=0.00 total=0
+
+The "some" line indicates the share of time in which at least some
+tasks are stalled on a given resource.
+
+The "full" line indicates the share of time in which all non-idle
+tasks are stalled on a given resource simultaneously. In this state
+actual CPU cycles are going to waste, and a workload that spends
+extended time in this state is considered to be thrashing. This has
+severe impact on performance, and it's useful to distinguish this
+situation from a state where some tasks are stalled but the CPU is
+still doing productive work. As such, time spent in this subset of the
+stall state is tracked separately and exported in the "full" averages.
+
+The ratios are tracked as recent trends over ten, sixty, and three
+hundred second windows, which gives insight into short term events as
+well as medium and long term trends. The total absolute stall time is
+tracked and exported as well, to allow detection of latency spikes
+which wouldn't necessarily make a dent in the time averages, or to
+average trends over custom time frames.
+
+Cgroup2 interface
+=================
+
+In a system with a CONFIG_CGROUP=y kernel and the cgroup2 filesystem
+mounted, pressure stall information is also tracked for tasks grouped
+into cgroups. Each subdirectory in the cgroupfs mountpoint contains
+cpu.pressure, memory.pressure, and io.pressure files; the format is
+the same as the /proc/pressure/ files.

Documentation/admin-guide/cgroup-v2.rst

@@ -966,6 +966,12 @@ All time durations are in microseconds.
 	$PERIOD duration.  "max" for $MAX indicates no limit.  If only
 	one number is written, $MAX is updated.
 
+  cpu.pressure
+	A read-only nested-key file which exists on non-root cgroups.
+
+	Shows pressure stall information for CPU. See
+	Documentation/accounting/psi.txt for details.
+
 
 Memory
 ------
@@ -1127,6 +1133,10 @@ PAGE_SIZE multiple when read back.
 		disk readahead.  For now OOM in memory cgroup kills
 		tasks iff shortage has happened inside page fault.
 
+		This event is not raised if the OOM killer is not
+		considered as an option, e.g. for failed high-order
+		allocations.
+
 	  oom_kill
 		The number of processes belonging to this cgroup
 		killed by any kind of OOM killer.
@@ -1271,6 +1281,12 @@ PAGE_SIZE multiple when read back.
 	higher than the limit for an extended period of time.  This
 	reduces the impact on the workload and memory management.
 
+  memory.pressure
+	A read-only nested-key file which exists on non-root cgroups.
+
+	Shows pressure stall information for memory. See
+	Documentation/accounting/psi.txt for details.
+
 
 Usage Guidelines
 ~~~~~~~~~~~~~~~~
@@ -1408,6 +1424,12 @@ IO Interface Files
 
 	  8:16 rbps=2097152 wbps=max riops=max wiops=max
 
+  io.pressure
+	A read-only nested-key file which exists on non-root cgroups.
+
+	Shows pressure stall information for IO. See
+	Documentation/accounting/psi.txt for details.
+
 
 Writeback
 ~~~~~~~~~

Documentation/admin-guide/kernel-parameters.txt

@@ -4851,6 +4851,18 @@
 			This is actually a boot loader parameter; the value is
 			passed to the kernel using a special protocol.
 
+	vm_debug[=options]	[KNL] Available with CONFIG_DEBUG_VM=y.
+			May slow down system boot speed, especially when
+			enabled on systems with a large amount of memory.
+			All options are enabled by default, and this
+			interface is meant to allow for selectively
+			enabling or disabling specific virtual memory
+			debugging features.
+
+			Available options are:
+			  P	Enable page structure init time poisoning
+			  -	Disable all of the above options
+
 	vmalloc=nn[KMG]	[KNL,BOOT] Forces the vmalloc area to have an exact
 			size of <nn>. This can be used to increase the
 			minimum size (128MB on x86). It can also be used to

Documentation/filesystems/proc.txt

@@ -858,6 +858,7 @@ Writeback:           0 kB
 AnonPages:      861800 kB
 Mapped:         280372 kB
 Shmem:             644 kB
+KReclaimable:   168048 kB
 Slab:           284364 kB
 SReclaimable:   159856 kB
 SUnreclaim:     124508 kB
@@ -925,6 +926,9 @@ AnonHugePages: Non-file backed huge pages mapped into userspace page tables
 ShmemHugePages: Memory used by shared memory (shmem) and tmpfs allocated
               with huge pages
 ShmemPmdMapped: Shared memory mapped into userspace with huge pages
+KReclaimable: Kernel allocations that the kernel will attempt to reclaim
+              under memory pressure. Includes SReclaimable (below), and other
+              direct allocations with a shrinker.
         Slab: in-kernel data structures cache
 SReclaimable: Part of Slab, that might be reclaimed, such as caches
   SUnreclaim: Part of Slab, that cannot be reclaimed on memory pressure

Documentation/vm/slub.rst

@@ -36,9 +36,10 @@ debugging is enabled. Format:
 
 slub_debug=<Debug-Options>
 	Enable options for all slabs
-slub_debug=<Debug-Options>,<slab name>
-	Enable options only for select slabs
 
+slub_debug=<Debug-Options>,<slab name1>,<slab name2>,...
+	Enable options only for select slabs (no spaces
+	after a comma)
 
 Possible debug options are::
 
@@ -62,7 +63,12 @@ Trying to find an issue in the dentry cache? Try::
 
 	slub_debug=,dentry
 
-to only enable debugging on the dentry cache.
+to only enable debugging on the dentry cache.  You may use an asterisk at the
+end of the slab name, in order to cover all slabs with the same prefix.  For
+example, here's how you can poison the dentry cache as well as all kmalloc
+slabs:
+
+	slub_debug=P,kmalloc-*,dentry
 
 Red zoning and tracking may realign the slab.  We can just apply sanity checks
 to the dentry cache with::

Documentation/x86/pat.txt

@@ -90,12 +90,12 @@ pci proc               |    --    |    --      |       WC         |
 Advanced APIs for drivers
 -------------------------
 A. Exporting pages to users with remap_pfn_range, io_remap_pfn_range,
-vm_insert_pfn
+vmf_insert_pfn
 
 Drivers wanting to export some pages to userspace do it by using mmap
 interface and a combination of
 1) pgprot_noncached()
-2) io_remap_pfn_range() or remap_pfn_range() or vm_insert_pfn()
+2) io_remap_pfn_range() or remap_pfn_range() or vmf_insert_pfn()
 
 With PAT support, a new API pgprot_writecombine is being added. So, drivers can
 continue to use the above sequence, with either pgprot_noncached() or

arch/alpha/Kconfig

@@ -31,6 +31,8 @@ config ALPHA
 	select ODD_RT_SIGACTION
 	select OLD_SIGSUSPEND
 	select CPU_NO_EFFICIENT_FFS if !ALPHA_EV67
+	select HAVE_MEMBLOCK
+	select NO_BOOTMEM
 	help
 	  The Alpha is a 64-bit general-purpose processor designed and
 	  marketed by the Digital Equipment Corporation of blessed memory,

arch/alpha/kernel/core_irongate.c

@@ -21,6 +21,7 @@
 #include <linux/init.h>
 #include <linux/initrd.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 
 #include <asm/ptrace.h>
 #include <asm/cacheflush.h>
@@ -241,8 +242,7 @@ albacore_init_arch(void)
 				       size / 1024);
 		}
 #endif
-		reserve_bootmem_node(NODE_DATA(0), pci_mem, memtop -
-				pci_mem, BOOTMEM_DEFAULT);
+		memblock_reserve(pci_mem, memtop - pci_mem);
 		printk("irongate_init_arch: temporarily reserving "
 			"region %08lx-%08lx for PCI\n", pci_mem, memtop - 1);
 	}

arch/alpha/kernel/setup.c

@@ -30,6 +30,7 @@
 #include <linux/ioport.h>
 #include <linux/platform_device.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/pci.h>
 #include <linux/seq_file.h>
 #include <linux/root_dev.h>
@@ -312,16 +313,16 @@ setup_memory(void *kernel_end)
 {
 	struct memclust_struct * cluster;
 	struct memdesc_struct * memdesc;
-	unsigned long start_kernel_pfn, end_kernel_pfn;
-	unsigned long bootmap_size, bootmap_pages, bootmap_start;
-	unsigned long start, end;
+	unsigned long kernel_size;
 	unsigned long i;
 
 	/* Find free clusters, and init and free the bootmem accordingly.  */
 	memdesc = (struct memdesc_struct *)
 	  (hwrpb->mddt_offset + (unsigned long) hwrpb);
 
 	for_each_mem_cluster(memdesc, cluster, i) {
+		unsigned long end;
+
 		printk("memcluster %lu, usage %01lx, start %8lu, end %8lu\n",
 		       i, cluster->usage, cluster->start_pfn,
 		       cluster->start_pfn + cluster->numpages);
@@ -335,6 +336,9 @@ setup_memory(void *kernel_end)
 		end = cluster->start_pfn + cluster->numpages;
 		if (end > max_low_pfn)
 			max_low_pfn = end;
+
+		memblock_add(PFN_PHYS(cluster->start_pfn),
+			     cluster->numpages << PAGE_SHIFT);
 	}
 
 	/*
@@ -363,87 +367,9 @@ setup_memory(void *kernel_end)
 		max_low_pfn = mem_size_limit;
 	}
 
-	/* Find the bounds of kernel memory.  */
-	start_kernel_pfn = PFN_DOWN(KERNEL_START_PHYS);
-	end_kernel_pfn = PFN_UP(virt_to_phys(kernel_end));
-	bootmap_start = -1;
-
- try_again:
-	if (max_low_pfn <= end_kernel_pfn)
-		panic("not enough memory to boot");
-
-	/* We need to know how many physically contiguous pages
-	   we'll need for the bootmap.  */
-	bootmap_pages = bootmem_bootmap_pages(max_low_pfn);
-
-	/* Now find a good region where to allocate the bootmap.  */
-	for_each_mem_cluster(memdesc, cluster, i) {
-		if (cluster->usage & 3)
-			continue;
-
-		start = cluster->start_pfn;
-		end = start + cluster->numpages;
-		if (start >= max_low_pfn)
-			continue;
-		if (end > max_low_pfn)
-			end = max_low_pfn;
-		if (start < start_kernel_pfn) {
-			if (end > end_kernel_pfn
-			    && end - end_kernel_pfn >= bootmap_pages) {
-				bootmap_start = end_kernel_pfn;
-				break;
-			} else if (end > start_kernel_pfn)
-				end = start_kernel_pfn;
-		} else if (start < end_kernel_pfn)
-			start = end_kernel_pfn;
-		if (end - start >= bootmap_pages) {
-			bootmap_start = start;
-			break;
-		}
-	}
-
-	if (bootmap_start == ~0UL) {
-		max_low_pfn >>= 1;
-		goto try_again;
-	}
-
-	/* Allocate the bootmap and mark the whole MM as reserved.  */
-	bootmap_size = init_bootmem(bootmap_start, max_low_pfn);
-
-	/* Mark the free regions.  */
-	for_each_mem_cluster(memdesc, cluster, i) {
-		if (cluster->usage & 3)
-			continue;
-
-		start = cluster->start_pfn;
-		end = cluster->start_pfn + cluster->numpages;
-		if (start >= max_low_pfn)
-			continue;
-		if (end > max_low_pfn)
-			end = max_low_pfn;
-		if (start < start_kernel_pfn) {
-			if (end > end_kernel_pfn) {
-				free_bootmem(PFN_PHYS(start),
-					     (PFN_PHYS(start_kernel_pfn)
-					      - PFN_PHYS(start)));
-				printk("freeing pages %ld:%ld\n",
-				       start, start_kernel_pfn);
-				start = end_kernel_pfn;
-			} else if (end > start_kernel_pfn)
-				end = start_kernel_pfn;
-		} else if (start < end_kernel_pfn)
-			start = end_kernel_pfn;
-		if (start >= end)
-			continue;
-
-		free_bootmem(PFN_PHYS(start), PFN_PHYS(end) - PFN_PHYS(start));
-		printk("freeing pages %ld:%ld\n", start, end);
-	}
-
-	/* Reserve the bootmap memory.  */
-	reserve_bootmem(PFN_PHYS(bootmap_start), bootmap_size,
-			BOOTMEM_DEFAULT);
-	printk("reserving pages %ld:%ld\n", bootmap_start, bootmap_start+PFN_UP(bootmap_size));
+	/* Reserve the kernel memory. */
+	kernel_size = virt_to_phys(kernel_end) - KERNEL_START_PHYS;
+	memblock_reserve(KERNEL_START_PHYS, kernel_size);
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	initrd_start = INITRD_START;
@@ -459,8 +385,8 @@ setup_memory(void *kernel_end)
 				       initrd_end,
 				       phys_to_virt(PFN_PHYS(max_low_pfn)));
 		} else {
-			reserve_bootmem(virt_to_phys((void *)initrd_start),
-					INITRD_SIZE, BOOTMEM_DEFAULT);
+			memblock_reserve(virt_to_phys((void *)initrd_start),
+					INITRD_SIZE);
 		}
 	}
 #endif /* CONFIG_BLK_DEV_INITRD */