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 -
+		memblock_reserve(pci_mem, memtop - pci_mem);
-				pci_mem, BOOTMEM_DEFAULT);
 		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>
@@ -312,9 +313,7 @@ setup_memory(void *kernel_end)
 {
 	struct memclust_struct * cluster;
 	struct memdesc_struct * memdesc;
-	unsigned long start_kernel_pfn, end_kernel_pfn;
+	unsigned long kernel_size;
-	unsigned long bootmap_size, bootmap_pages, bootmap_start;
-	unsigned long start, end;
 	unsigned long i;
 
 	/* Find free clusters, and init and free the bootmem accordingly.  */
@@ -322,6 +321,8 @@ setup_memory(void *kernel_end)
 	  (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.  */
+	/* Reserve the kernel memory. */
-	start_kernel_pfn = PFN_DOWN(KERNEL_START_PHYS);
+	kernel_size = virt_to_phys(kernel_end) - KERNEL_START_PHYS;
-	end_kernel_pfn = PFN_UP(virt_to_phys(kernel_end));
+	memblock_reserve(KERNEL_START_PHYS, kernel_size);
-	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));
 
 #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),
+			memblock_reserve(virt_to_phys((void *)initrd_start),
-					INITRD_SIZE, BOOTMEM_DEFAULT);
+					INITRD_SIZE);
 		}
 	}
 #endif /* CONFIG_BLK_DEV_INITRD */

arch/alpha/mm/numa.c

@@ -11,6 +11,7 @@
 #include <linux/kernel.h>
 #include <linux/mm.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/swap.h>
 #include <linux/initrd.h>
 #include <linux/pfn.h>
@@ -59,12 +60,10 @@ setup_memory_node(int nid, 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 node_pfn_start, node_pfn_end;
 	unsigned long node_min_pfn, node_max_pfn;
 	int i;
-	unsigned long node_datasz = PFN_UP(sizeof(pg_data_t));
 	int show_init = 0;
 
 	/* Find the bounds of current node */
@@ -134,24 +133,14 @@ setup_memory_node(int nid, void *kernel_end)
 	/* Cute trick to make sure our local node data is on local memory */
 	node_data[nid] = (pg_data_t *)(__va(node_min_pfn << PAGE_SHIFT));
 #endif
-	/* Quasi-mark the pg_data_t as in-use */
-	node_min_pfn += node_datasz;
-	if (node_min_pfn >= node_max_pfn) {
-		printk(" not enough mem to reserve NODE_DATA");
-		return;
-	}
-	NODE_DATA(nid)->bdata = &bootmem_node_data[nid];
-
 	printk(" Detected node memory:   start %8lu, end %8lu\n",
 	       node_min_pfn, node_max_pfn);
 
 	DBGDCONT(" DISCONTIG: node_data[%d]   is at 0x%p\n", nid, NODE_DATA(nid));
-	DBGDCONT(" DISCONTIG: NODE_DATA(%d)->bdata is at 0x%p\n", nid, NODE_DATA(nid)->bdata);
 
 	/* 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;
 
 	if (!nid && (node_max_pfn < end_kernel_pfn || node_min_pfn > start_kernel_pfn))
 		panic("kernel loaded out of ram");
@@ -161,89 +150,11 @@ setup_memory_node(int nid, void *kernel_end)
 	   has much larger alignment than 8Mb, so it's safe. */
 	node_min_pfn &= ~((1UL << (MAX_ORDER-1))-1);
 
-	/* We need to know how many physically contiguous pages
+	memblock_add(PFN_PHYS(node_min_pfn),
-	   we'll need for the bootmap.  */
+		     (node_max_pfn - node_min_pfn) << PAGE_SHIFT);
-	bootmap_pages = bootmem_bootmap_pages(node_max_pfn-node_min_pfn);
 
-	/* Now find a good region where to allocate the bootmap.  */
+	NODE_DATA(nid)->node_start_pfn = node_min_pfn;
-	for_each_mem_cluster(memdesc, cluster, i) {
+	NODE_DATA(nid)->node_present_pages = node_max_pfn - node_min_pfn;
-		if (cluster->usage & 3)
-			continue;
-
-		start = cluster->start_pfn;
-		end = start + cluster->numpages;
-
-		if (start >= node_max_pfn || end <= node_min_pfn)
-			continue;
-
-		if (end > node_max_pfn)
-			end = node_max_pfn;
-		if (start < node_min_pfn)
-			start = node_min_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 == -1)
-		panic("couldn't find a contiguous place for the bootmap");
-
-	/* Allocate the bootmap and mark the whole MM as reserved.  */
-	bootmap_size = init_bootmem_node(NODE_DATA(nid), bootmap_start,
-					 node_min_pfn, node_max_pfn);
-	DBGDCONT(" bootmap_start %lu, bootmap_size %lu, bootmap_pages %lu\n",
-		 bootmap_start, bootmap_size, bootmap_pages);
-
-	/* 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 >= node_max_pfn || end <= node_min_pfn)
-			continue;
-
-		if (end > node_max_pfn)
-			end = node_max_pfn;
-		if (start < node_min_pfn)
-			start = node_min_pfn;
-
-		if (start < start_kernel_pfn) {
-			if (end > end_kernel_pfn) {
-				free_bootmem_node(NODE_DATA(nid), 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_node(NODE_DATA(nid), PFN_PHYS(start), PFN_PHYS(end) - PFN_PHYS(start));
-		printk(" freeing pages %ld:%ld\n", start, end);
-	}
-
-	/* Reserve the bootmap memory.  */
-	reserve_bootmem_node(NODE_DATA(nid), PFN_PHYS(bootmap_start),
-			bootmap_size, BOOTMEM_DEFAULT);
-	printk(" reserving pages %ld:%ld\n", bootmap_start, bootmap_start+PFN_UP(bootmap_size));
 
 	node_set_online(nid);
 }
@@ -251,6 +162,7 @@ setup_memory_node(int nid, void *kernel_end)
 void __init
 setup_memory(void *kernel_end)
 {
+	unsigned long kernel_size;
 	int nid;
 
 	show_mem_layout();
@@ -262,6 +174,9 @@ setup_memory(void *kernel_end)
 	for (nid = 0; nid < MAX_NUMNODES; nid++)
 		setup_memory_node(nid, kernel_end);
 
+	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;
 	if (initrd_start) {
@@ -279,9 +194,8 @@ setup_memory(void *kernel_end)
 				       phys_to_virt(PFN_PHYS(max_low_pfn)));
 		} else {
 			nid = kvaddr_to_nid(initrd_start);
-			reserve_bootmem_node(NODE_DATA(nid),
+			memblock_reserve(virt_to_phys((void *)initrd_start),
-					     virt_to_phys((void *)initrd_start),
+					 INITRD_SIZE);
-					     INITRD_SIZE, BOOTMEM_DEFAULT);
 		}
 	}
 #endif /* CONFIG_BLK_DEV_INITRD */
@@ -303,9 +217,8 @@ void __init paging_init(void)
 	dma_local_pfn = virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
 
 	for_each_online_node(nid) {
-		bootmem_data_t *bdata = &bootmem_node_data[nid];
+		unsigned long start_pfn = NODE_DATA(nid)->node_start_pfn;
-		unsigned long start_pfn = bdata->node_min_pfn;
+		unsigned long end_pfn = start_pfn + NODE_DATA(nid)->node_present_pages;
-		unsigned long end_pfn = bdata->node_low_pfn;
 
 		if (dma_local_pfn >= end_pfn - start_pfn)
 			zones_size[ZONE_DMA] = end_pfn - start_pfn;

arch/arm/include/asm/hugetlb-3level.h

@@ -29,6 +29,7 @@
  * ptes.
  * (The valid bit is automatically cleared by set_pte_at for PROT_NONE ptes).
  */
+#define __HAVE_ARCH_HUGE_PTEP_GET
 static inline pte_t huge_ptep_get(pte_t *ptep)
 {
 	pte_t retval = *ptep;
@@ -37,35 +38,4 @@ static inline pte_t huge_ptep_get(pte_t *ptep)
 	return retval;
 }
 
-static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-				   pte_t *ptep, pte_t pte)
-{
-	set_pte_at(mm, addr, ptep, pte);
-}
-
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
-					 unsigned long addr, pte_t *ptep)
-{
-	ptep_clear_flush(vma, addr, ptep);
-}
-
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-					   unsigned long addr, pte_t *ptep)
-{
-	ptep_set_wrprotect(mm, addr, ptep);
-}
-
-static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
-{
-	return ptep_get_and_clear(mm, addr, ptep);
-}
-
-static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
-					     unsigned long addr, pte_t *ptep,
-					     pte_t pte, int dirty)
-{
-	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
-}
-
 #endif /* _ASM_ARM_HUGETLB_3LEVEL_H */

arch/arm/include/asm/hugetlb.h

@@ -23,18 +23,8 @@
 #define _ASM_ARM_HUGETLB_H
 
 #include <asm/page.h>
-#include <asm-generic/hugetlb.h>
-
 #include <asm/hugetlb-3level.h>
-
+#include <asm-generic/hugetlb.h>
-static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
-					  unsigned long addr, unsigned long end,
-					  unsigned long floor,
-					  unsigned long ceiling)
-{
-	free_pgd_range(tlb, addr, end, floor, ceiling);
-}
-
 
 static inline int is_hugepage_only_range(struct mm_struct *mm,
 					 unsigned long addr, unsigned long len)
@@ -42,27 +32,6 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 	return 0;
 }
 
-static inline int prepare_hugepage_range(struct file *file,
-					 unsigned long addr, unsigned long len)
-{
-	struct hstate *h = hstate_file(file);
-	if (len & ~huge_page_mask(h))
-		return -EINVAL;
-	if (addr & ~huge_page_mask(h))
-		return -EINVAL;
-	return 0;
-}
-
-static inline int huge_pte_none(pte_t pte)
-{
-	return pte_none(pte);
-}
-
-static inline pte_t huge_pte_wrprotect(pte_t pte)
-{
-	return pte_wrprotect(pte);
-}
-
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 	clear_bit(PG_dcache_clean, &page->flags);

arch/arm64/include/asm/hugetlb.h

@@ -20,48 +20,18 @@
 
 #include <asm/page.h>
 
+#define __HAVE_ARCH_HUGE_PTEP_GET
 static inline pte_t huge_ptep_get(pte_t *ptep)
 {
 	return READ_ONCE(*ptep);
 }
 
-
-
-static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
-					  unsigned long addr, unsigned long end,
-					  unsigned long floor,
-					  unsigned long ceiling)
-{
-	free_pgd_range(tlb, addr, end, floor, ceiling);
-}
-
 static inline int is_hugepage_only_range(struct mm_struct *mm,
 					 unsigned long addr, unsigned long len)
 {
 	return 0;
 }
 
-static inline int prepare_hugepage_range(struct file *file,
-					 unsigned long addr, unsigned long len)
-{
-	struct hstate *h = hstate_file(file);
-	if (len & ~huge_page_mask(h))
-		return -EINVAL;
-	if (addr & ~huge_page_mask(h))
-		return -EINVAL;
-	return 0;
-}
-
-static inline int huge_pte_none(pte_t pte)
-{
-	return pte_none(pte);
-}
-
-static inline pte_t huge_pte_wrprotect(pte_t pte)
-{
-	return pte_wrprotect(pte);
-}
-
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 	clear_bit(PG_dcache_clean, &page->flags);
@@ -70,20 +40,25 @@ static inline void arch_clear_hugepage_flags(struct page *page)
 extern pte_t arch_make_huge_pte(pte_t entry, struct vm_area_struct *vma,
 				struct page *page, int writable);
 #define arch_make_huge_pte arch_make_huge_pte
+#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
 extern void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 			    pte_t *ptep, pte_t pte);
+#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
 extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 				      unsigned long addr, pte_t *ptep,
 				      pte_t pte, int dirty);
+#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 extern pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 				     unsigned long addr, pte_t *ptep);
+#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
 extern void huge_ptep_set_wrprotect(struct mm_struct *mm,
 				    unsigned long addr, pte_t *ptep);
+#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 extern void huge_ptep_clear_flush(struct vm_area_struct *vma,
 				  unsigned long addr, pte_t *ptep);
+#define __HAVE_ARCH_HUGE_PTE_CLEAR
 extern void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 			   pte_t *ptep, unsigned long sz);
-#define huge_pte_clear huge_pte_clear
 extern void set_huge_swap_pte_at(struct mm_struct *mm, unsigned long addr,
 				 pte_t *ptep, pte_t pte, unsigned long sz);
 #define set_huge_swap_pte_at set_huge_swap_pte_at

arch/arm64/include/asm/string.h

@@ -16,6 +16,7 @@
 #ifndef __ASM_STRING_H
 #define __ASM_STRING_H
 
+#ifndef CONFIG_KASAN
 #define __HAVE_ARCH_STRRCHR
 extern char *strrchr(const char *, int c);
 
@@ -34,6 +35,13 @@ extern __kernel_size_t strlen(const char *);
 #define __HAVE_ARCH_STRNLEN
 extern __kernel_size_t strnlen(const char *, __kernel_size_t);
 
+#define __HAVE_ARCH_MEMCMP
+extern int memcmp(const void *, const void *, size_t);
+
+#define __HAVE_ARCH_MEMCHR
+extern void *memchr(const void *, int, __kernel_size_t);
+#endif
+
 #define __HAVE_ARCH_MEMCPY
 extern void *memcpy(void *, const void *, __kernel_size_t);
 extern void *__memcpy(void *, const void *, __kernel_size_t);
@@ -42,16 +50,10 @@ extern void *__memcpy(void *, const void *, __kernel_size_t);
 extern void *memmove(void *, const void *, __kernel_size_t);
 extern void *__memmove(void *, const void *, __kernel_size_t);
 
-#define __HAVE_ARCH_MEMCHR
-extern void *memchr(const void *, int, __kernel_size_t);
-
 #define __HAVE_ARCH_MEMSET
 extern void *memset(void *, int, __kernel_size_t);
 extern void *__memset(void *, int, __kernel_size_t);
 
-#define __HAVE_ARCH_MEMCMP
-extern int memcmp(const void *, const void *, size_t);
-
 #ifdef CONFIG_ARCH_HAS_UACCESS_FLUSHCACHE
 #define __HAVE_ARCH_MEMCPY_FLUSHCACHE
 void memcpy_flushcache(void *dst, const void *src, size_t cnt);

arch/arm64/kernel/arm64ksyms.c

@@ -44,20 +44,23 @@ EXPORT_SYMBOL(__arch_copy_in_user);
 EXPORT_SYMBOL(memstart_addr);
 
 	/* string / mem functions */
+#ifndef CONFIG_KASAN
 EXPORT_SYMBOL(strchr);
 EXPORT_SYMBOL(strrchr);
 EXPORT_SYMBOL(strcmp);
 EXPORT_SYMBOL(strncmp);
 EXPORT_SYMBOL(strlen);
 EXPORT_SYMBOL(strnlen);
+EXPORT_SYMBOL(memcmp);
+EXPORT_SYMBOL(memchr);
+#endif
+
 EXPORT_SYMBOL(memset);
 EXPORT_SYMBOL(memcpy);
 EXPORT_SYMBOL(memmove);
 EXPORT_SYMBOL(__memset);
 EXPORT_SYMBOL(__memcpy);
 EXPORT_SYMBOL(__memmove);
-EXPORT_SYMBOL(memchr);
-EXPORT_SYMBOL(memcmp);
 
 	/* atomic bitops */
 EXPORT_SYMBOL(set_bit);

arch/arm64/lib/memchr.S

@@ -30,7 +30,7 @@
  * Returns:
  *	x0 - address of first occurrence of 'c' or 0
  */
-ENTRY(memchr)
+WEAK(memchr)
 	and	w1, w1, #0xff
 1:	subs	x2, x2, #1
 	b.mi	2f

arch/arm64/lib/memcmp.S

@@ -58,7 +58,7 @@ pos		.req	x11
 limit_wd	.req	x12
 mask		.req	x13
 
-ENTRY(memcmp)
+WEAK(memcmp)
 	cbz	limit, .Lret0
 	eor	tmp1, src1, src2
 	tst	tmp1, #7

arch/arm64/lib/strchr.S

@@ -29,7 +29,7 @@
  * Returns:
  *	x0 - address of first occurrence of 'c' or 0
  */
-ENTRY(strchr)
+WEAK(strchr)
 	and	w1, w1, #0xff
 1:	ldrb	w2, [x0], #1
 	cmp	w2, w1

arch/arm64/lib/strcmp.S

@@ -60,7 +60,7 @@ tmp3		.req	x9
 zeroones	.req	x10
 pos		.req	x11
 
-ENTRY(strcmp)
+WEAK(strcmp)
 	eor	tmp1, src1, src2
 	mov	zeroones, #REP8_01
 	tst	tmp1, #7

arch/arm64/lib/strlen.S

@@ -56,7 +56,7 @@ pos		.req	x12
 #define REP8_7f 0x7f7f7f7f7f7f7f7f
 #define REP8_80 0x8080808080808080
 
-ENTRY(strlen)
+WEAK(strlen)
 	mov	zeroones, #REP8_01
 	bic	src, srcin, #15
 	ands	tmp1, srcin, #15

arch/arm64/lib/strncmp.S

@@ -64,7 +64,7 @@ limit_wd	.req	x13
 mask		.req	x14
 endloop		.req	x15
 
-ENTRY(strncmp)
+WEAK(strncmp)
 	cbz	limit, .Lret0
 	eor	tmp1, src1, src2
 	mov	zeroones, #REP8_01

arch/arm64/lib/strnlen.S

@@ -59,7 +59,7 @@ limit_wd	.req	x14
 #define REP8_7f 0x7f7f7f7f7f7f7f7f
 #define REP8_80 0x8080808080808080
 
-ENTRY(strnlen)
+WEAK(strnlen)
 	cbz	limit, .Lhit_limit
 	mov	zeroones, #REP8_01
 	bic	src, srcin, #15

arch/arm64/lib/strrchr.S

@@ -29,7 +29,7 @@
  * Returns:
  *	x0 - address of last occurrence of 'c' or 0
  */
-ENTRY(strrchr)
+WEAK(strrchr)
 	mov	x3, #0
 	and	w1, w1, #0xff
 1:	ldrb	w2, [x0], #1

arch/hexagon/Kconfig

@@ -21,6 +21,9 @@ config HEXAGON
 	select GENERIC_IRQ_SHOW
 	select HAVE_ARCH_KGDB
 	select HAVE_ARCH_TRACEHOOK
+	select HAVE_MEMBLOCK
+	select ARCH_DISCARD_MEMBLOCK
+	select NO_BOOTMEM
 	select NEED_SG_DMA_LENGTH
 	select NO_IOPORT_MAP
 	select GENERIC_IOMAP

arch/hexagon/mm/init.c

@@ -21,6 +21,7 @@
 #include <linux/init.h>
 #include <linux/mm.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <asm/atomic.h>
 #include <linux/highmem.h>
 #include <asm/tlb.h>
@@ -176,7 +177,6 @@ size_t hexagon_coherent_pool_size = (size_t) (DMA_RESERVE << 22);
 
 void __init setup_arch_memory(void)
 {
-	int bootmap_size;
 	/*  XXX Todo: this probably should be cleaned up  */
 	u32 *segtable = (u32 *) &swapper_pg_dir[0];
 	u32 *segtable_end;
@@ -195,18 +195,22 @@ void __init setup_arch_memory(void)
 	bootmem_lastpg = PFN_DOWN((bootmem_lastpg << PAGE_SHIFT) &
 		~((BIG_KERNEL_PAGE_SIZE) - 1));
 
+	memblock_add(PHYS_OFFSET,
+		     (bootmem_lastpg - ARCH_PFN_OFFSET) << PAGE_SHIFT);
+
+	/* Reserve kernel text/data/bss */
+	memblock_reserve(PHYS_OFFSET,
+			 (bootmem_startpg - ARCH_PFN_OFFSET) << PAGE_SHIFT);
 	/*
 	 * Reserve the top DMA_RESERVE bytes of RAM for DMA (uncached)
 	 * memory allocation
 	 */
-
 	max_low_pfn = bootmem_lastpg - PFN_DOWN(DMA_RESERVED_BYTES);
 	min_low_pfn = ARCH_PFN_OFFSET;
-	bootmap_size =  init_bootmem_node(NODE_DATA(0), bootmem_startpg, min_low_pfn, max_low_pfn);
+	memblock_reserve(PFN_PHYS(max_low_pfn), DMA_RESERVED_BYTES);
 
 	printk(KERN_INFO "bootmem_startpg:  0x%08lx\n", bootmem_startpg);
 	printk(KERN_INFO "bootmem_lastpg:  0x%08lx\n", bootmem_lastpg);
-	printk(KERN_INFO "bootmap_size:  %d\n", bootmap_size);
 	printk(KERN_INFO "min_low_pfn:  0x%08lx\n", min_low_pfn);
 	printk(KERN_INFO "max_low_pfn:  0x%08lx\n", max_low_pfn);
 
@@ -256,14 +260,6 @@ void __init setup_arch_memory(void)
 	printk(KERN_INFO "*segtable = 0x%08x\n", *segtable);
 #endif
 
-	/*
-	 * Free all the memory that wasn't taken up by the bootmap, the DMA
-	 * reserve, or kernel itself.
-	 */
-	free_bootmem(PFN_PHYS(bootmem_startpg) + bootmap_size,
-		     PFN_PHYS(bootmem_lastpg - bootmem_startpg) - bootmap_size -
-		     DMA_RESERVED_BYTES);
-
 	/*
 	 *  The bootmem allocator seemingly just lives to feed memory
 	 *  to the paging system

arch/ia64/include/asm/hugetlb.h

@@ -3,13 +3,13 @@
 #define _ASM_IA64_HUGETLB_H
 
 #include <asm/page.h>
-#include <asm-generic/hugetlb.h>
-
 
+#define __HAVE_ARCH_HUGETLB_FREE_PGD_RANGE
 void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 			    unsigned long end, unsigned long floor,
 			    unsigned long ceiling);
 
+#define __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE
 int prepare_hugepage_range(struct file *file,
 			unsigned long addr, unsigned long len);
 
@@ -21,53 +21,16 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 		REGION_NUMBER((addr)+(len)-1) == RGN_HPAGE);
 }
 
-static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
-				   pte_t *ptep, pte_t pte)
-{
-	set_pte_at(mm, addr, ptep, pte);
-}
-
-static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
-{
-	return ptep_get_and_clear(mm, addr, ptep);
-}
-
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
 }
 
-static inline int huge_pte_none(pte_t pte)
-{
-	return pte_none(pte);
-}
-
-static inline pte_t huge_pte_wrprotect(pte_t pte)
-{
-	return pte_wrprotect(pte);
-}
-
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-					   unsigned long addr, pte_t *ptep)
-{
-	ptep_set_wrprotect(mm, addr, ptep);
-}
-
-static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
-					     unsigned long addr, pte_t *ptep,
-					     pte_t pte, int dirty)
-{
-	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
-}
-
-static inline pte_t huge_ptep_get(pte_t *ptep)
-{
-	return *ptep;
-}
-
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }
 
+#include <asm-generic/hugetlb.h>
+
 #endif /* _ASM_IA64_HUGETLB_H */

arch/ia64/include/asm/pgtable.h

@@ -544,7 +544,6 @@ extern struct page *zero_page_memmap_ptr;
 
 #  ifdef CONFIG_VIRTUAL_MEM_MAP
   /* arch mem_map init routine is needed due to holes in a virtual mem_map */
-#   define __HAVE_ARCH_MEMMAP_INIT
     extern void memmap_init (unsigned long size, int nid, unsigned long zone,
 			     unsigned long start_pfn);
 #  endif /* CONFIG_VIRTUAL_MEM_MAP */

arch/mips/include/asm/hugetlb.h

@@ -10,8 +10,6 @@
 #define __ASM_HUGETLB_H
 
 #include <asm/page.h>
-#include <asm-generic/hugetlb.h>
-
 
 static inline int is_hugepage_only_range(struct mm_struct *mm,
 					 unsigned long addr,
@@ -20,6 +18,7 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 	return 0;
 }
 
+#define __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE
 static inline int prepare_hugepage_range(struct file *file,
 					 unsigned long addr,
 					 unsigned long len)
@@ -38,21 +37,7 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
+#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
-					  unsigned long addr,
-					  unsigned long end,
-					  unsigned long floor,
-					  unsigned long ceiling)
-{
-	free_pgd_range(tlb, addr, end, floor, ceiling);
-}
-
-static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-				   pte_t *ptep, pte_t pte)
-{
-	set_pte_at(mm, addr, ptep, pte);
-}
-
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 					    unsigned long addr, pte_t *ptep)
 {
@@ -64,29 +49,21 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 	return pte;
 }
 
+#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
 	flush_tlb_page(vma, addr & huge_page_mask(hstate_vma(vma)));
 }
 
+#define __HAVE_ARCH_HUGE_PTE_NONE
 static inline int huge_pte_none(pte_t pte)
 {
 	unsigned long val = pte_val(pte) & ~_PAGE_GLOBAL;
 	return !val || (val == (unsigned long)invalid_pte_table);
 }
 
-static inline pte_t huge_pte_wrprotect(pte_t pte)
+#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
-{
-	return pte_wrprotect(pte);
-}
-
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-					   unsigned long addr, pte_t *ptep)
-{
-	ptep_set_wrprotect(mm, addr, ptep);
-}
-
 static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 					     unsigned long addr,
 					     pte_t *ptep, pte_t pte,
@@ -105,13 +82,10 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 	return changed;
 }
 
-static inline pte_t huge_ptep_get(pte_t *ptep)
-{
-	return *ptep;
-}
-
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }
 
+#include <asm-generic/hugetlb.h>
+
 #endif /* __ASM_HUGETLB_H */

arch/nios2/Kconfig

@@ -23,6 +23,9 @@ config NIOS2
 	select SPARSE_IRQ
 	select USB_ARCH_HAS_HCD if USB_SUPPORT
 	select CPU_NO_EFFICIENT_FFS
+	select HAVE_MEMBLOCK
+	select ARCH_DISCARD_MEMBLOCK
+	select NO_BOOTMEM
 
 config GENERIC_CSUM
 	def_bool y

arch/nios2/kernel/prom.c

@@ -32,23 +32,6 @@
 
 #include <asm/sections.h>
 
-void __init early_init_dt_add_memory_arch(u64 base, u64 size)
-{
-	u64 kernel_start = (u64)virt_to_phys(_text);
-
-	if (!memory_size &&
-	    (kernel_start >= base) && (kernel_start < (base + size)))
-		memory_size = size;
-
-}
-
-int __init early_init_dt_reserve_memory_arch(phys_addr_t base, phys_addr_t size,
-					     bool nomap)
-{
-	reserve_bootmem(base, size, BOOTMEM_DEFAULT);
-	return 0;
-}
-
 void __init early_init_devtree(void *params)
 {
 	__be32 *dtb = (u32 *)__dtb_start;

arch/nios2/kernel/setup.c

@@ -17,6 +17,7 @@
 #include <linux/sched/task.h>
 #include <linux/console.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/initrd.h>
 #include <linux/of_fdt.h>
 #include <linux/screen_info.h>
@@ -143,10 +144,12 @@ asmlinkage void __init nios2_boot_init(unsigned r4, unsigned r5, unsigned r6,
 
 void __init setup_arch(char **cmdline_p)
 {
-	int bootmap_size;
+	int dram_start;
 
 	console_verbose();
 
+	dram_start = memblock_start_of_DRAM();
+	memory_size = memblock_phys_mem_size();
 	memory_start = PAGE_ALIGN((unsigned long)__pa(_end));
 	memory_end = (unsigned long) CONFIG_NIOS2_MEM_BASE + memory_size;
 
@@ -163,39 +166,11 @@ void __init setup_arch(char **cmdline_p)
 	max_low_pfn = PFN_DOWN(memory_end);
 	max_mapnr = max_low_pfn;
 
-	/*
+	memblock_reserve(dram_start, memory_start - dram_start);
-	 * give all the memory to the bootmap allocator,  tell it to put the
-	 * boot mem_map at the start of memory
-	 */
-	pr_debug("init_bootmem_node(?,%#lx, %#x, %#lx)\n",
-		min_low_pfn, PFN_DOWN(PHYS_OFFSET), max_low_pfn);
-	bootmap_size = init_bootmem_node(NODE_DATA(0),
-					min_low_pfn, PFN_DOWN(PHYS_OFFSET),
-					max_low_pfn);
-
-	/*
-	 * free the usable memory,  we have to make sure we do not free
-	 * the bootmem bitmap so we then reserve it after freeing it :-)
-	 */
-	pr_debug("free_bootmem(%#lx, %#lx)\n",
-		memory_start, memory_end - memory_start);
-	free_bootmem(memory_start, memory_end - memory_start);
-
-	/*
-	 * Reserve the bootmem bitmap itself as well. We do this in two
-	 * steps (first step was init_bootmem()) because this catches
-	 * the (very unlikely) case of us accidentally initializing the
-	 * bootmem allocator with an invalid RAM area.
-	 *
-	 * Arguments are start, size
-	 */
-	pr_debug("reserve_bootmem(%#lx, %#x)\n", memory_start, bootmap_size);
-	reserve_bootmem(memory_start, bootmap_size, BOOTMEM_DEFAULT);
-
 #ifdef CONFIG_BLK_DEV_INITRD
 	if (initrd_start) {
-		reserve_bootmem(virt_to_phys((void *)initrd_start),
+		memblock_reserve(virt_to_phys((void *)initrd_start),
-				initrd_end - initrd_start, BOOTMEM_DEFAULT);
+				initrd_end - initrd_start);
 	}
 #endif /* CONFIG_BLK_DEV_INITRD */
 

arch/parisc/include/asm/hugetlb.h

@@ -3,12 +3,12 @@
 #define _ASM_PARISC64_HUGETLB_H
 
 #include <asm/page.h>
-#include <asm-generic/hugetlb.h>
-
 
+#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte);
 
+#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep);
 
@@ -22,6 +22,7 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
  */
+#define __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE
 static inline int prepare_hugepage_range(struct file *file,
 			unsigned long addr, unsigned long len)
 {
@@ -32,43 +33,25 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
+#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
-					  unsigned long addr, unsigned long end,
-					  unsigned long floor,
-					  unsigned long ceiling)
-{
-	free_pgd_range(tlb, addr, end, floor, ceiling);
-}
-
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
 }
 
-static inline int huge_pte_none(pte_t pte)
+#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
-{
-	return pte_none(pte);
-}
-
-static inline pte_t huge_pte_wrprotect(pte_t pte)
-{
-	return pte_wrprotect(pte);
-}
-
 void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep);
 
+#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
 int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 					     unsigned long addr, pte_t *ptep,
 					     pte_t pte, int dirty);
 
-static inline pte_t huge_ptep_get(pte_t *ptep)
-{
-	return *ptep;
-}
-
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }
 
+#include <asm-generic/hugetlb.h>
+
 #endif /* _ASM_PARISC64_HUGETLB_H */

arch/powerpc/include/asm/book3s/32/pgtable.h

@@ -311,12 +311,6 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 {
 	pte_update(ptep, _PAGE_RW, 0);
 }
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-					   unsigned long addr, pte_t *ptep)
-{
-	ptep_set_wrprotect(mm, addr, ptep);
-}
-
 
 static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
 					   pte_t *ptep, pte_t entry,

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

@@ -426,6 +426,7 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 		pte_update(mm, addr, ptep, 0, _PAGE_PRIVILEGED, 0);
 }
 
+#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {

arch/powerpc/include/asm/hugetlb.h

@@ -4,7 +4,6 @@
 
 #ifdef CONFIG_HUGETLB_PAGE
 #include <asm/page.h>
-#include <asm-generic/hugetlb.h>
 
 extern struct kmem_cache *hugepte_cache;
 
@@ -110,31 +109,12 @@ static inline void flush_hugetlb_page(struct vm_area_struct *vma,
 void flush_hugetlb_page(struct vm_area_struct *vma, unsigned long vmaddr);
 #endif
 
+#define __HAVE_ARCH_HUGETLB_FREE_PGD_RANGE
 void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 			    unsigned long end, unsigned long floor,
 			    unsigned long ceiling);
 
-/*
+#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
- * If the arch doesn't supply something else, assume that hugepage
- * size aligned regions are ok without further preparation.
- */
-static inline int prepare_hugepage_range(struct file *file,
-			unsigned long addr, unsigned long len)
-{
-	struct hstate *h = hstate_file(file);
-	if (len & ~huge_page_mask(h))
-		return -EINVAL;
-	if (addr & ~huge_page_mask(h))
-		return -EINVAL;
-	return 0;
-}
-
-static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-				   pte_t *ptep, pte_t pte)
-{
-	set_pte_at(mm, addr, ptep, pte);
-}
-
 static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 					    unsigned long addr, pte_t *ptep)
 {
@@ -145,6 +125,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
 #endif
 }
 
+#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
@@ -153,29 +134,17 @@ static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 	flush_hugetlb_page(vma, addr);
 }
 
-static inline int huge_pte_none(pte_t pte)
+#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
-{
-	return pte_none(pte);
-}
-
-static inline pte_t huge_pte_wrprotect(pte_t pte)
-{
-	return pte_wrprotect(pte);
-}
-
 extern int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 				      unsigned long addr, pte_t *ptep,
 				      pte_t pte, int dirty);
 
-static inline pte_t huge_ptep_get(pte_t *ptep)
-{
-	return *ptep;
-}
-
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }
 
+#include <asm-generic/hugetlb.h>
+
 #else /* ! CONFIG_HUGETLB_PAGE */
 static inline void flush_hugetlb_page(struct vm_area_struct *vma,
 				      unsigned long vmaddr)

arch/powerpc/include/asm/nohash/32/pgtable.h

@@ -300,12 +300,6 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 
 	pte_update(ptep, clr, set);
 }
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-					   unsigned long addr, pte_t *ptep)
-{
-	ptep_set_wrprotect(mm, addr, ptep);
-}
-
 
 static inline void __ptep_set_access_flags(struct vm_area_struct *vma,
 					   pte_t *ptep, pte_t entry,

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

@@ -275,6 +275,7 @@ static inline void ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr,
 	pte_update(mm, addr, ptep, _PAGE_RW, 0, 0);
 }
 
+#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {

arch/powerpc/platforms/cell/cpufreq_spudemand.c

@@ -49,7 +49,7 @@ static int calc_freq(struct spu_gov_info_struct *info)
 	cpu = info->policy->cpu;
 	busy_spus = atomic_read(&cbe_spu_info[cpu_to_node(cpu)].busy_spus);
 
-	CALC_LOAD(info->busy_spus, EXP, busy_spus * FIXED_1);
+	info->busy_spus = calc_load(info->busy_spus, EXP, busy_spus * FIXED_1);
 	pr_debug("cpu %d: busy_spus=%d, info->busy_spus=%ld\n",
 			cpu, busy_spus, info->busy_spus);
 

arch/powerpc/platforms/cell/spufs/sched.c

@@ -987,9 +987,9 @@ static void spu_calc_load(void)
 	unsigned long active_tasks; /* fixed-point */
 
 	active_tasks = count_active_contexts() * FIXED_1;
-	CALC_LOAD(spu_avenrun[0], EXP_1, active_tasks);
+	spu_avenrun[0] = calc_load(spu_avenrun[0], EXP_1, active_tasks);
-	CALC_LOAD(spu_avenrun[1], EXP_5, active_tasks);
+	spu_avenrun[1] = calc_load(spu_avenrun[1], EXP_5, active_tasks);
-	CALC_LOAD(spu_avenrun[2], EXP_15, active_tasks);
+	spu_avenrun[2] = calc_load(spu_avenrun[2], EXP_15, active_tasks);
 }
 
 static void spusched_wake(struct timer_list *unused)
@@ -1071,9 +1071,6 @@ void spuctx_switch_state(struct spu_context *ctx,
 	}
 }
 
-#define LOAD_INT(x) ((x) >> FSHIFT)
-#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
-
 static int show_spu_loadavg(struct seq_file *s, void *private)
 {
 	int a, b, c;

arch/s390/appldata/appldata_os.c

@@ -25,10 +25,6 @@
 
 #include "appldata.h"
 
-
-#define LOAD_INT(x) ((x) >> FSHIFT)
-#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
-
 /*
  * OS data
  *

arch/sh/include/asm/hugetlb.h

@@ -4,8 +4,6 @@
 
 #include <asm/cacheflush.h>
 #include <asm/page.h>
-#include <asm-generic/hugetlb.h>
-
 
 static inline int is_hugepage_only_range(struct mm_struct *mm,
 					 unsigned long addr,
@@ -17,6 +15,7 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
  * If the arch doesn't supply something else, assume that hugepage
  * size aligned regions are ok without further preparation.
  */
+#define __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE
 static inline int prepare_hugepage_range(struct file *file,
 			unsigned long addr, unsigned long len)
 {
@@ -27,62 +26,17 @@ static inline int prepare_hugepage_range(struct file *file,
 	return 0;
 }
 
-static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
+#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
-					  unsigned long addr, unsigned long end,
-					  unsigned long floor,
-					  unsigned long ceiling)
-{
-	free_pgd_range(tlb, addr, end, floor, ceiling);
-}
-
-static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-				   pte_t *ptep, pte_t pte)
-{
-	set_pte_at(mm, addr, ptep, pte);
-}
-
-static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
-{
-	return ptep_get_and_clear(mm, addr, ptep);
-}
-
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
 }
 
-static inline int huge_pte_none(pte_t pte)
-{
-	return pte_none(pte);
-}
-
-static inline pte_t huge_pte_wrprotect(pte_t pte)
-{
-	return pte_wrprotect(pte);
-}
-
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-					   unsigned long addr, pte_t *ptep)
-{
-	ptep_set_wrprotect(mm, addr, ptep);
-}
-
-static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
-					     unsigned long addr, pte_t *ptep,
-					     pte_t pte, int dirty)
-{
-	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
-}
-
-static inline pte_t huge_ptep_get(pte_t *ptep)
-{
-	return *ptep;
-}
-
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 	clear_bit(PG_dcache_clean, &page->flags);
 }
 
+#include <asm-generic/hugetlb.h>
+
 #endif /* _ASM_SH_HUGETLB_H */

arch/sparc/include/asm/hugetlb.h

@@ -3,7 +3,6 @@
 #define _ASM_SPARC64_HUGETLB_H
 
 #include <asm/page.h>
-#include <asm-generic/hugetlb.h>
 
 #ifdef CONFIG_HUGETLB_PAGE
 struct pud_huge_patch_entry {
@@ -13,9 +12,11 @@ struct pud_huge_patch_entry {
 extern struct pud_huge_patch_entry __pud_huge_patch, __pud_huge_patch_end;
 #endif
 
+#define __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
 void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
 		     pte_t *ptep, pte_t pte);
 
+#define __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
 pte_t huge_ptep_get_and_clear(struct mm_struct *mm, unsigned long addr,
 			      pte_t *ptep);
 
@@ -25,37 +26,13 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 	return 0;
 }
 
-/*
+#define __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
- * If the arch doesn't supply something else, assume that hugepage
- * size aligned regions are ok without further preparation.
- */
-static inline int prepare_hugepage_range(struct file *file,
-			unsigned long addr, unsigned long len)
-{
-	struct hstate *h = hstate_file(file);
-
-	if (len & ~huge_page_mask(h))
-		return -EINVAL;
-	if (addr & ~huge_page_mask(h))
-		return -EINVAL;
-	return 0;
-}
-
 static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
 					 unsigned long addr, pte_t *ptep)
 {
 }
 
-static inline int huge_pte_none(pte_t pte)
+#define __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
-{
-	return pte_none(pte);
-}
-
-static inline pte_t huge_pte_wrprotect(pte_t pte)
-{
-	return pte_wrprotect(pte);
-}
-
 static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 					   unsigned long addr, pte_t *ptep)
 {
@@ -63,6 +40,7 @@ static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
 	set_huge_pte_at(mm, addr, ptep, pte_wrprotect(old_pte));
 }
 
+#define __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
 static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 					     unsigned long addr, pte_t *ptep,
 					     pte_t pte, int dirty)
@@ -75,17 +53,15 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
 	return changed;
 }
 
-static inline pte_t huge_ptep_get(pte_t *ptep)
-{
-	return *ptep;
-}
-
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }
 
+#define __HAVE_ARCH_HUGETLB_FREE_PGD_RANGE
 void hugetlb_free_pgd_range(struct mmu_gather *tlb, unsigned long addr,
 			    unsigned long end, unsigned long floor,
 			    unsigned long ceiling);
 
+#include <asm-generic/hugetlb.h>
+
 #endif /* _ASM_SPARC64_HUGETLB_H */

arch/um/Kconfig

@@ -12,6 +12,8 @@ config UML
 	select HAVE_UID16
 	select HAVE_FUTEX_CMPXCHG if FUTEX
 	select HAVE_DEBUG_KMEMLEAK
+	select HAVE_MEMBLOCK
+	select NO_BOOTMEM
 	select GENERIC_IRQ_SHOW
 	select GENERIC_CPU_DEVICES
 	select GENERIC_CLOCKEVENTS

arch/um/kernel/physmem.c

@@ -5,6 +5,7 @@
 
 #include <linux/module.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 #include <linux/mm.h>
 #include <linux/pfn.h>
 #include <asm/page.h>
@@ -80,28 +81,23 @@ void __init setup_physmem(unsigned long start, unsigned long reserve_end,
 			  unsigned long len, unsigned long long highmem)
 {
 	unsigned long reserve = reserve_end - start;
-	unsigned long pfn = PFN_UP(__pa(reserve_end));
+	long map_size = len - reserve;
-	unsigned long delta = (len - reserve) >> PAGE_SHIFT;
-	unsigned long offset, bootmap_size;
-	long map_size;
 	int err;
 
-	offset = uml_reserved - uml_physmem;
-	map_size = len - offset;
 	if(map_size <= 0) {
 		os_warn("Too few physical memory! Needed=%lu, given=%lu\n",
-			offset, len);
+			reserve, len);
 		exit(1);
 	}
 
 	physmem_fd = create_mem_file(len + highmem);
 
-	err = os_map_memory((void *) uml_reserved, physmem_fd, offset,
+	err = os_map_memory((void *) reserve_end, physmem_fd, reserve,
 			    map_size, 1, 1, 1);
 	if (err < 0) {
 		os_warn("setup_physmem - mapping %ld bytes of memory at 0x%p "
 			"failed - errno = %d\n", map_size,
-			(void *) uml_reserved, err);
+			(void *) reserve_end, err);
 		exit(1);
 	}
 
@@ -113,9 +109,11 @@ void __init setup_physmem(unsigned long start, unsigned long reserve_end,
 	os_write_file(physmem_fd, __syscall_stub_start, PAGE_SIZE);
 	os_fsync_file(physmem_fd);
 
-	bootmap_size = init_bootmem(pfn, pfn + delta);
+	memblock_add(__pa(start), len + highmem);
-	free_bootmem(__pa(reserve_end) + bootmap_size,
+	memblock_reserve(__pa(start), reserve);
-		     len - bootmap_size - reserve);
+
+	min_low_pfn = PFN_UP(__pa(reserve_end));
+	max_low_pfn = min_low_pfn + (map_size >> PAGE_SHIFT);
 }
 
 int phys_mapping(unsigned long phys, unsigned long long *offset_out)

arch/unicore32/Kconfig

@@ -6,6 +6,7 @@ config UNICORE32
 	select ARCH_MIGHT_HAVE_PC_SERIO
 	select DMA_DIRECT_OPS
 	select HAVE_MEMBLOCK
+	select NO_BOOTMEM
 	select HAVE_GENERIC_DMA_COHERENT
 	select HAVE_KERNEL_GZIP
 	select HAVE_KERNEL_BZIP2

arch/unicore32/mm/init.c

@@ -84,58 +84,6 @@ static void __init find_limits(unsigned long *min, unsigned long *max_low,
 	}
 }
 
-static void __init uc32_bootmem_init(unsigned long start_pfn,
-	unsigned long end_pfn)
-{
-	struct memblock_region *reg;
-	unsigned int boot_pages;
-	phys_addr_t bitmap;
-	pg_data_t *pgdat;
-
-	/*
-	 * Allocate the bootmem bitmap page.  This must be in a region
-	 * of memory which has already been mapped.
-	 */
-	boot_pages = bootmem_bootmap_pages(end_pfn - start_pfn);
-	bitmap = memblock_alloc_base(boot_pages << PAGE_SHIFT, L1_CACHE_BYTES,
-				__pfn_to_phys(end_pfn));
-
-	/*
-	 * Initialise the bootmem allocator, handing the
-	 * memory banks over to bootmem.
-	 */
-	node_set_online(0);
-	pgdat = NODE_DATA(0);
-	init_bootmem_node(pgdat, __phys_to_pfn(bitmap), start_pfn, end_pfn);
-
-	/* Free the lowmem regions from memblock into bootmem. */
-	for_each_memblock(memory, reg) {
-		unsigned long start = memblock_region_memory_base_pfn(reg);
-		unsigned long end = memblock_region_memory_end_pfn(reg);
-
-		if (end >= end_pfn)
-			end = end_pfn;
-		if (start >= end)
-			break;
-
-		free_bootmem(__pfn_to_phys(start), (end - start) << PAGE_SHIFT);
-	}
-
-	/* Reserve the lowmem memblock reserved regions in bootmem. */
-	for_each_memblock(reserved, reg) {
-		unsigned long start = memblock_region_reserved_base_pfn(reg);
-		unsigned long end = memblock_region_reserved_end_pfn(reg);
-
-		if (end >= end_pfn)
-			end = end_pfn;
-		if (start >= end)
-			break;
-
-		reserve_bootmem(__pfn_to_phys(start),
-			(end - start) << PAGE_SHIFT, BOOTMEM_DEFAULT);
-	}
-}
-
 static void __init uc32_bootmem_free(unsigned long min, unsigned long max_low,
 	unsigned long max_high)
 {
@@ -232,7 +180,7 @@ void __init bootmem_init(void)
 
 	find_limits(&min, &max_low, &max_high);
 
-	uc32_bootmem_init(min, max_low);
+	node_set_online(0);
 
 	/*
 	 * Sparsemem tries to allocate bootmem in memory_present(),

arch/x86/entry/vdso/vma.c

@@ -39,7 +39,7 @@ void __init init_vdso_image(const struct vdso_image *image)
 
 struct linux_binprm;
 
-static int vdso_fault(const struct vm_special_mapping *sm,
+static vm_fault_t vdso_fault(const struct vm_special_mapping *sm,
 		      struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	const struct vdso_image *image = vma->vm_mm->context.vdso_image;
@@ -84,12 +84,11 @@ static int vdso_mremap(const struct vm_special_mapping *sm,
 	return 0;
 }
 
-static int vvar_fault(const struct vm_special_mapping *sm,
+static vm_fault_t vvar_fault(const struct vm_special_mapping *sm,
 		      struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	const struct vdso_image *image = vma->vm_mm->context.vdso_image;
 	long sym_offset;
-	int ret = -EFAULT;
 
 	if (!image)
 		return VM_FAULT_SIGBUS;
@@ -108,29 +107,24 @@ static int vvar_fault(const struct vm_special_mapping *sm,
 		return VM_FAULT_SIGBUS;
 
 	if (sym_offset == image->sym_vvar_page) {
-		ret = vm_insert_pfn(vma, vmf->address,
+		return vmf_insert_pfn(vma, vmf->address,
-				    __pa_symbol(&__vvar_page) >> PAGE_SHIFT);
+				__pa_symbol(&__vvar_page) >> PAGE_SHIFT);
 	} else if (sym_offset == image->sym_pvclock_page) {
 		struct pvclock_vsyscall_time_info *pvti =
 			pvclock_get_pvti_cpu0_va();
 		if (pvti && vclock_was_used(VCLOCK_PVCLOCK)) {
-			ret = vm_insert_pfn_prot(
+			return vmf_insert_pfn_prot(vma, vmf->address,
-				vma,
+					__pa(pvti) >> PAGE_SHIFT,
-				vmf->address,
+					pgprot_decrypted(vma->vm_page_prot));
-				__pa(pvti) >> PAGE_SHIFT,
-				pgprot_decrypted(vma->vm_page_prot));
 		}
 	} else if (sym_offset == image->sym_hvclock_page) {
 		struct ms_hyperv_tsc_page *tsc_pg = hv_get_tsc_page();
 
 		if (tsc_pg && vclock_was_used(VCLOCK_HVCLOCK))
-			ret = vm_insert_pfn(vma, vmf->address,
+			return vmf_insert_pfn(vma, vmf->address,
-					    vmalloc_to_pfn(tsc_pg));
+					vmalloc_to_pfn(tsc_pg));
 	}
 
-	if (ret == 0 || ret == -EBUSY)
-		return VM_FAULT_NOPAGE;
-
 	return VM_FAULT_SIGBUS;
 }
 

arch/x86/include/asm/hugetlb.h

@@ -13,75 +13,6 @@ static inline int is_hugepage_only_range(struct mm_struct *mm,
 	return 0;
 }
 
-/*
- * If the arch doesn't supply something else, assume that hugepage
- * size aligned regions are ok without further preparation.
- */
-static inline int prepare_hugepage_range(struct file *file,
-			unsigned long addr, unsigned long len)
-{
-	struct hstate *h = hstate_file(file);
-	if (len & ~huge_page_mask(h))
-		return -EINVAL;
-	if (addr & ~huge_page_mask(h))
-		return -EINVAL;
-	return 0;
-}
-
-static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
-					  unsigned long addr, unsigned long end,
-					  unsigned long floor,
-					  unsigned long ceiling)
-{
-	free_pgd_range(tlb, addr, end, floor, ceiling);
-}
-
-static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
-				   pte_t *ptep, pte_t pte)
-{
-	set_pte_at(mm, addr, ptep, pte);
-}
-
-static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
-					    unsigned long addr, pte_t *ptep)
-{
-	return ptep_get_and_clear(mm, addr, ptep);
-}
-
-static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
-					 unsigned long addr, pte_t *ptep)
-{
-	ptep_clear_flush(vma, addr, ptep);
-}
-
-static inline int huge_pte_none(pte_t pte)
-{
-	return pte_none(pte);
-}
-
-static inline pte_t huge_pte_wrprotect(pte_t pte)
-{
-	return pte_wrprotect(pte);
-}
-
-static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
-					   unsigned long addr, pte_t *ptep)
-{
-	ptep_set_wrprotect(mm, addr, ptep);
-}
-
-static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
-					     unsigned long addr, pte_t *ptep,
-					     pte_t pte, int dirty)
-{
-	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
-}
-
-static inline pte_t huge_ptep_get(pte_t *ptep)
-{
-	return *ptep;
-}
-
 static inline void arch_clear_hugepage_flags(struct page *page)
 {
 }

arch/x86/kernel/e820.c

@@ -1248,7 +1248,6 @@ void __init e820__memblock_setup(void)
 {
 	int i;
 	u64 end;
-	u64 addr = 0;
 
 	/*
 	 * The bootstrap memblock region count maximum is 128 entries
@@ -1265,21 +1264,13 @@ void __init e820__memblock_setup(void)
 		struct e820_entry *entry = &e820_table->entries[i];
 
 		end = entry->addr + entry->size;
-		if (addr < entry->addr)
-			memblock_reserve(addr, entry->addr - addr);
-		addr = end;
 		if (end != (resource_size_t)end)
 			continue;
 
-		/*
-		 * all !E820_TYPE_RAM ranges (including gap ranges) are put
-		 * into memblock.reserved to make sure that struct pages in
-		 * such regions are not left uninitialized after bootup.
-		 */
 		if (entry->type != E820_TYPE_RAM && entry->type != E820_TYPE_RESERVED_KERN)
-			memblock_reserve(entry->addr, entry->size);
+			continue;
-		else
+
-			memblock_add(entry->addr, entry->size);
+		memblock_add(entry->addr, entry->size);
 	}
 
 	/* Throw away partial pages: */

arch/xtensa/include/asm/Kbuild

@@ -26,5 +26,6 @@ generic-y += rwsem.h
 generic-y += sections.h
 generic-y += topology.h
 generic-y += trace_clock.h
+generic-y += vga.h
 generic-y += word-at-a-time.h
 generic-y += xor.h

arch/xtensa/include/asm/vga.h

@@ -1,19 +0,0 @@
-/*
- * include/asm-xtensa/vga.h
- *
- * This file is subject to the terms and conditions of the GNU General Public
- * License.  See the file "COPYING" in the main directory of this archive
- * for more details.
- *
- * Copyright (C) 2001 - 2005 Tensilica Inc.
- */
-
-#ifndef _XTENSA_VGA_H
-#define _XTENSA_VGA_H
-
-#define VGA_MAP_MEM(x,s) (unsigned long)phys_to_virt(x)
-
-#define vga_readb(x)	(*(x))
-#define vga_writeb(x,y)	(*(y) = (x))
-
-#endif

block/blk-iolatency.c

@@ -153,7 +153,7 @@ struct iolatency_grp {
 #define BLKIOLATENCY_MAX_WIN_SIZE NSEC_PER_SEC
 /*
  * These are the constants used to fake the fixed-point moving average
- * calculation just like load average.  The call to CALC_LOAD folds
+ * calculation just like load average.  The call to calc_load() folds
  * (FIXED_1 (2048) - exp_factor) * new_sample into lat_avg.  The sampling
  * window size is bucketed to try to approximately calculate average
  * latency such that 1/exp (decay rate) is [1 min, 2.5 min) when windows
@@ -248,7 +248,7 @@ static inline void iolat_update_total_lat_avg(struct iolatency_grp *iolat,
 		return;
 
 	/*
-	 * CALC_LOAD takes in a number stored in fixed point representation.
+	 * calc_load() takes in a number stored in fixed point representation.
 	 * Because we are using this for IO time in ns, the values stored
 	 * are significantly larger than the FIXED_1 denominator (2048).
 	 * Therefore, rounding errors in the calculation are negligible and
@@ -257,7 +257,9 @@ static inline void iolat_update_total_lat_avg(struct iolatency_grp *iolat,
 	exp_idx = min_t(int, BLKIOLATENCY_NR_EXP_FACTORS - 1,
 			div64_u64(iolat->cur_win_nsec,
 				  BLKIOLATENCY_EXP_BUCKET_SIZE));
-	CALC_LOAD(iolat->lat_avg, iolatency_exp_factors[exp_idx], stat->rqs.mean);
+	iolat->lat_avg = calc_load(iolat->lat_avg,
+				   iolatency_exp_factors[exp_idx],
+				   stat->rqs.mean);
 }
 
 static inline bool iolatency_may_queue(struct iolatency_grp *iolat,

drivers/base/node.c

@@ -67,8 +67,11 @@ static ssize_t node_read_meminfo(struct device *dev,
 	int nid = dev->id;
 	struct pglist_data *pgdat = NODE_DATA(nid);
 	struct sysinfo i;
+	unsigned long sreclaimable, sunreclaimable;
 
 	si_meminfo_node(&i, nid);
+	sreclaimable = node_page_state(pgdat, NR_SLAB_RECLAIMABLE);
+	sunreclaimable = node_page_state(pgdat, NR_SLAB_UNRECLAIMABLE);
 	n = sprintf(buf,
 		       "Node %d MemTotal:       %8lu kB\n"
 		       "Node %d MemFree:        %8lu kB\n"
@@ -118,6 +121,7 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       "Node %d NFS_Unstable:   %8lu kB\n"
 		       "Node %d Bounce:         %8lu kB\n"
 		       "Node %d WritebackTmp:   %8lu kB\n"
+		       "Node %d KReclaimable:   %8lu kB\n"
 		       "Node %d Slab:           %8lu kB\n"
 		       "Node %d SReclaimable:   %8lu kB\n"
 		       "Node %d SUnreclaim:     %8lu kB\n"
@@ -138,20 +142,21 @@ static ssize_t node_read_meminfo(struct device *dev,
 		       nid, K(node_page_state(pgdat, NR_UNSTABLE_NFS)),
 		       nid, K(sum_zone_node_page_state(nid, NR_BOUNCE)),
 		       nid, K(node_page_state(pgdat, NR_WRITEBACK_TEMP)),
-		       nid, K(node_page_state(pgdat, NR_SLAB_RECLAIMABLE) +
+		       nid, K(sreclaimable +
-			      node_page_state(pgdat, NR_SLAB_UNRECLAIMABLE)),
+			      node_page_state(pgdat, NR_KERNEL_MISC_RECLAIMABLE)),
-		       nid, K(node_page_state(pgdat, NR_SLAB_RECLAIMABLE)),
+		       nid, K(sreclaimable + sunreclaimable),
+		       nid, K(sreclaimable),
+		       nid, K(sunreclaimable)
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
-		       nid, K(node_page_state(pgdat, NR_SLAB_UNRECLAIMABLE)),
+		       ,
 		       nid, K(node_page_state(pgdat, NR_ANON_THPS) *
 				       HPAGE_PMD_NR),
 		       nid, K(node_page_state(pgdat, NR_SHMEM_THPS) *
 				       HPAGE_PMD_NR),
 		       nid, K(node_page_state(pgdat, NR_SHMEM_PMDMAPPED) *
-				       HPAGE_PMD_NR));
+				       HPAGE_PMD_NR)
-#else
-		       nid, K(node_page_state(pgdat, NR_SLAB_UNRECLAIMABLE)));
 #endif
+		       );
 	n += hugetlb_report_node_meminfo(nid, buf + n);
 	return n;
 }

drivers/cpuidle/governors/menu.c

@@ -130,10 +130,6 @@ struct menu_device {
 	int		interval_ptr;
 };
 
-
-#define LOAD_INT(x) ((x) >> FSHIFT)
-#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
-
 static inline int get_loadavg(unsigned long load)
 {
 	return LOAD_INT(load) * 10 + LOAD_FRAC(load) / 10;

drivers/infiniband/hw/hfi1/mmu_rb.c

@@ -77,7 +77,6 @@ static void do_remove(struct mmu_rb_handler *handler,
 static void handle_remove(struct work_struct *work);
 
 static const struct mmu_notifier_ops mn_opts = {
-	.flags = MMU_INVALIDATE_DOES_NOT_BLOCK,
 	.invalidate_range_start = mmu_notifier_range_start,
 };
 

drivers/iommu/amd_iommu_v2.c

@@ -427,7 +427,6 @@ static void mn_release(struct mmu_notifier *mn, struct mm_struct *mm)
 }
 
 static const struct mmu_notifier_ops iommu_mn = {
-	.flags			= MMU_INVALIDATE_DOES_NOT_BLOCK,
 	.release		= mn_release,
 	.clear_flush_young      = mn_clear_flush_young,
 	.invalidate_range       = mn_invalidate_range,

drivers/iommu/intel-svm.c

@@ -273,7 +273,6 @@ static void intel_mm_release(struct mmu_notifier *mn, struct mm_struct *mm)
 }
 
 static const struct mmu_notifier_ops intel_mmuops = {
-	.flags = MMU_INVALIDATE_DOES_NOT_BLOCK,
 	.release = intel_mm_release,
 	.change_pte = intel_change_pte,
 	.invalidate_range = intel_invalidate_range,

drivers/misc/sgi-gru/grutlbpurge.c

@@ -261,7 +261,6 @@ static void gru_release(struct mmu_notifier *mn, struct mm_struct *mm)
 
 
 static const struct mmu_notifier_ops gru_mmuops = {
-	.flags			= MMU_INVALIDATE_DOES_NOT_BLOCK,
 	.invalidate_range_start	= gru_invalidate_range_start,
 	.invalidate_range_end	= gru_invalidate_range_end,
 	.release		= gru_release,

drivers/of/fdt.c

@@ -1127,12 +1127,13 @@ void __init __weak early_init_dt_add_memory_arch(u64 base, u64 size)
 {
 	const u64 phys_offset = MIN_MEMBLOCK_ADDR;
 
+	if (size < PAGE_SIZE - (base & ~PAGE_MASK)) {
+		pr_warn("Ignoring memory block 0x%llx - 0x%llx\n",
+			base, base + size);
+		return;
+	}
+
 	if (!PAGE_ALIGNED(base)) {
-		if (size < PAGE_SIZE - (base & ~PAGE_MASK)) {
-			pr_warn("Ignoring memory block 0x%llx - 0x%llx\n",
-				base, base + size);
-			return;
-		}
 		size -= PAGE_SIZE - (base & ~PAGE_MASK);
 		base = PAGE_ALIGN(base);
 	}

drivers/staging/android/ion/ion_page_pool.c

@@ -33,8 +33,8 @@ static void ion_page_pool_add(struct ion_page_pool *pool, struct page *page)
 		pool->low_count++;
 	}
 
-	mod_node_page_state(page_pgdat(page), NR_INDIRECTLY_RECLAIMABLE_BYTES,
+	mod_node_page_state(page_pgdat(page), NR_KERNEL_MISC_RECLAIMABLE,
-			    (1 << (PAGE_SHIFT + pool->order)));
+							1 << pool->order);
 	mutex_unlock(&pool->mutex);
 }
 
@@ -53,8 +53,8 @@ static struct page *ion_page_pool_remove(struct ion_page_pool *pool, bool high)
 	}
 
 	list_del(&page->lru);
-	mod_node_page_state(page_pgdat(page), NR_INDIRECTLY_RECLAIMABLE_BYTES,
+	mod_node_page_state(page_pgdat(page), NR_KERNEL_MISC_RECLAIMABLE,
-			    -(1 << (PAGE_SHIFT + pool->order)));
+							-(1 << pool->order));
 	return page;
 }
 

fs/cramfs/inode.c

@@ -418,9 +418,12 @@ static int cramfs_physmem_mmap(struct file *file, struct vm_area_struct *vma)
 		int i;
 		vma->vm_flags |= VM_MIXEDMAP;
 		for (i = 0; i < pages && !ret; i++) {
+			vm_fault_t vmf;
 			unsigned long off = i * PAGE_SIZE;
 			pfn_t pfn = phys_to_pfn_t(address + off, PFN_DEV);
-			ret = vm_insert_mixed(vma, vma->vm_start + off, pfn);
+			vmf = vmf_insert_mixed(vma, vma->vm_start + off, pfn);
+			if (vmf & VM_FAULT_ERROR)
+				ret = vm_fault_to_errno(vmf, 0);
 		}
 	}
 

fs/dcache.c

@@ -257,24 +257,10 @@ static void __d_free(struct rcu_head *head)
 	kmem_cache_free(dentry_cache, dentry); 
 }
 
-static void __d_free_external_name(struct rcu_head *head)
-{
-	struct external_name *name = container_of(head, struct external_name,
-						  u.head);
-
-	mod_node_page_state(page_pgdat(virt_to_page(name)),
-			    NR_INDIRECTLY_RECLAIMABLE_BYTES,
-			    -ksize(name));
-
-	kfree(name);
-}
-
 static void __d_free_external(struct rcu_head *head)
 {
 	struct dentry *dentry = container_of(head, struct dentry, d_u.d_rcu);
-
+	kfree(external_name(dentry));
-	__d_free_external_name(&external_name(dentry)->u.head);
-
 	kmem_cache_free(dentry_cache, dentry);
 }
 
@@ -306,7 +292,7 @@ void release_dentry_name_snapshot(struct name_snapshot *name)
 		struct external_name *p;
 		p = container_of(name->name, struct external_name, name[0]);
 		if (unlikely(atomic_dec_and_test(&p->u.count)))
-			call_rcu(&p->u.head, __d_free_external_name);
+			kfree_rcu(p, u.head);
 	}
 }
 EXPORT_SYMBOL(release_dentry_name_snapshot);
@@ -1606,7 +1592,6 @@ EXPORT_SYMBOL(d_invalidate);
  
 struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 {
-	struct external_name *ext = NULL;
 	struct dentry *dentry;
 	char *dname;
 	int err;
@@ -1627,14 +1612,15 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 		dname = dentry->d_iname;
 	} else if (name->len > DNAME_INLINE_LEN-1) {
 		size_t size = offsetof(struct external_name, name[1]);
-
+		struct external_name *p = kmalloc(size + name->len,
-		ext = kmalloc(size + name->len, GFP_KERNEL_ACCOUNT);
+						  GFP_KERNEL_ACCOUNT |
-		if (!ext) {
+						  __GFP_RECLAIMABLE);
+		if (!p) {
 			kmem_cache_free(dentry_cache, dentry); 
 			return NULL;
 		}
-		atomic_set(&ext->u.count, 1);
+		atomic_set(&p->u.count, 1);
-		dname = ext->name;
+		dname = p->name;
 	} else  {
 		dname = dentry->d_iname;
 	}	
@@ -1673,12 +1659,6 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 		}
 	}
 
-	if (unlikely(ext)) {
-		pg_data_t *pgdat = page_pgdat(virt_to_page(ext));
-		mod_node_page_state(pgdat, NR_INDIRECTLY_RECLAIMABLE_BYTES,
-				    ksize(ext));
-	}
-
 	this_cpu_inc(nr_dentry);
 
 	return dentry;
@@ -2707,7 +2687,7 @@ static void copy_name(struct dentry *dentry, struct dentry *target)
 		dentry->d_name.hash_len = target->d_name.hash_len;
 	}
 	if (old_name && likely(atomic_dec_and_test(&old_name->u.count)))
-		call_rcu(&old_name->u.head, __d_free_external_name);
+		kfree_rcu(old_name, u.head);
 }
 
 /*

fs/iomap.c

@@ -1057,7 +1057,7 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length,
 	return length;
 }
 
-int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops)
+vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops)
 {
 	struct page *page = vmf->page;
 	struct inode *inode = file_inode(vmf->vma->vm_file);

fs/kernfs/mount.c

@@ -236,6 +236,9 @@ static int kernfs_fill_super(struct super_block *sb, unsigned long magic)
 		sb->s_export_op = &kernfs_export_ops;
 	sb->s_time_gran = 1;
 
+	/* sysfs dentries and inodes don't require IO to create */
+	sb->s_shrink.seeks = 0;
+
 	/* get root inode, initialize and unlock it */
 	mutex_lock(&kernfs_mutex);
 	inode = kernfs_get_inode(sb, info->root->kn);

fs/ocfs2/alloc.c

@@ -5106,8 +5106,6 @@ int ocfs2_split_extent(handle_t *handle,
 	 * rightmost extent list.
 	 */
 	if (path->p_tree_depth) {
-		struct ocfs2_extent_block *eb;
-
 		ret = ocfs2_read_extent_block(et->et_ci,
 					      ocfs2_et_get_last_eb_blk(et),
 					      &last_eb_bh);
@@ -5115,8 +5113,6 @@ int ocfs2_split_extent(handle_t *handle,
 			mlog_errno(ret);
 			goto out;
 		}
-
-		eb = (struct ocfs2_extent_block *) last_eb_bh->b_data;
 	}
 
 	if (rec->e_cpos == split_rec->e_cpos &&

fs/ocfs2/aops.c

@@ -1392,8 +1392,7 @@ retry:
 unlock:
 	spin_unlock(&oi->ip_lock);
 out:
-	if (new)
+	kfree(new);
-		kfree(new);
 	return ret;
 }
 

fs/ocfs2/dlm/dlmdebug.c

@@ -329,7 +329,7 @@ void dlm_print_one_mle(struct dlm_master_list_entry *mle)
 {
 	char *buf;
 
-	buf = (char *) get_zeroed_page(GFP_NOFS);
+	buf = (char *) get_zeroed_page(GFP_ATOMIC);
 	if (buf) {
 		dump_mle(mle, buf, PAGE_SIZE - 1);
 		free_page((unsigned long)buf);

fs/ocfs2/dlm/dlmthread.c

@@ -531,7 +531,7 @@ void __dlm_dirty_lockres(struct dlm_ctxt *dlm, struct dlm_lock_resource *res)
 	assert_spin_locked(&res->spinlock);
 
 	/* don't shuffle secondary queues */
-	if ((res->owner == dlm->node_num)) {
+	if (res->owner == dlm->node_num) {
 		if (res->state & (DLM_LOCK_RES_MIGRATING |
 				  DLM_LOCK_RES_BLOCK_DIRTY))
 		    return;

fs/ocfs2/refcounttree.c

@@ -4135,7 +4135,6 @@ static int ocfs2_create_reflink_node(struct inode *s_inode,
 	struct buffer_head *ref_root_bh = NULL;
 	struct ocfs2_cached_dealloc_ctxt dealloc;
 	struct ocfs2_super *osb = OCFS2_SB(s_inode->i_sb);
-	struct ocfs2_refcount_block *rb;
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *)s_bh->b_data;
 	struct ocfs2_refcount_tree *ref_tree;
 
@@ -4162,7 +4161,6 @@ static int ocfs2_create_reflink_node(struct inode *s_inode,
 		mlog_errno(ret);
 		goto out;
 	}
-	rb = (struct ocfs2_refcount_block *)ref_root_bh->b_data;
 
 	ret = ocfs2_duplicate_extent_list(s_inode, t_inode, t_bh,
 					  &ref_tree->rf_ci, ref_root_bh,

fs/proc/inode.c

@@ -516,6 +516,9 @@ int proc_fill_super(struct super_block *s, void *data, int silent)
 	 */
 	s->s_stack_depth = FILESYSTEM_MAX_STACK_DEPTH;
 	
+	/* procfs dentries and inodes don't require IO to create */
+	s->s_shrink.seeks = 0;
+
 	pde_get(&proc_root);
 	root_inode = proc_get_inode(s, &proc_root);
 	if (!root_inode) {

fs/proc/loadavg.c

@@ -10,9 +10,6 @@
 #include <linux/seqlock.h>
 #include <linux/time.h>
 
-#define LOAD_INT(x) ((x) >> FSHIFT)
-#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
-
 static int loadavg_proc_show(struct seq_file *m, void *v)
 {
 	unsigned long avnrun[3];

fs/proc/meminfo.c

@@ -38,6 +38,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	long cached;
 	long available;
 	unsigned long pages[NR_LRU_LISTS];
+	unsigned long sreclaimable, sunreclaim;
 	int lru;
 
 	si_meminfo(&i);
@@ -53,6 +54,8 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		pages[lru] = global_node_page_state(NR_LRU_BASE + lru);
 
 	available = si_mem_available();
+	sreclaimable = global_node_page_state(NR_SLAB_RECLAIMABLE);
+	sunreclaim = global_node_page_state(NR_SLAB_UNRECLAIMABLE);
 
 	show_val_kb(m, "MemTotal:       ", i.totalram);
 	show_val_kb(m, "MemFree:        ", i.freeram);
@@ -94,14 +97,11 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 	show_val_kb(m, "Mapped:         ",
 		    global_node_page_state(NR_FILE_MAPPED));
 	show_val_kb(m, "Shmem:          ", i.sharedram);
-	show_val_kb(m, "Slab:           ",
+	show_val_kb(m, "KReclaimable:   ", sreclaimable +
-		    global_node_page_state(NR_SLAB_RECLAIMABLE) +
+		    global_node_page_state(NR_KERNEL_MISC_RECLAIMABLE));
-		    global_node_page_state(NR_SLAB_UNRECLAIMABLE));
+	show_val_kb(m, "Slab:           ", sreclaimable + sunreclaim);
-
+	show_val_kb(m, "SReclaimable:   ", sreclaimable);
-	show_val_kb(m, "SReclaimable:   ",
+	show_val_kb(m, "SUnreclaim:     ", sunreclaim);
-		    global_node_page_state(NR_SLAB_RECLAIMABLE));
-	show_val_kb(m, "SUnreclaim:     ",
-		    global_node_page_state(NR_SLAB_UNRECLAIMABLE));
 	seq_printf(m, "KernelStack:    %8lu kB\n",
 		   global_zone_page_state(NR_KERNEL_STACK_KB));
 	show_val_kb(m, "PageTables:     ",

fs/proc/task_mmu.c

@@ -713,6 +713,8 @@ static void smap_gather_stats(struct vm_area_struct *vma,
 	smaps_walk.private = mss;
 
 #ifdef CONFIG_SHMEM
+	/* In case of smaps_rollup, reset the value from previous vma */
+	mss->check_shmem_swap = false;
 	if (vma->vm_file && shmem_mapping(vma->vm_file->f_mapping)) {
 		/*
 		 * For shared or readonly shmem mappings we know that all
@@ -728,7 +730,7 @@ static void smap_gather_stats(struct vm_area_struct *vma,
 
 		if (!shmem_swapped || (vma->vm_flags & VM_SHARED) ||
 					!(vma->vm_flags & VM_WRITE)) {
-			mss->swap = shmem_swapped;
+			mss->swap += shmem_swapped;
 		} else {
 			mss->check_shmem_swap = true;
 			smaps_walk.pte_hole = smaps_pte_hole;

fs/userfaultfd.c

@@ -1026,7 +1026,7 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
 	struct userfaultfd_ctx *fork_nctx = NULL;
 
 	/* always take the fd_wqh lock before the fault_pending_wqh lock */
-	spin_lock(&ctx->fd_wqh.lock);
+	spin_lock_irq(&ctx->fd_wqh.lock);
 	__add_wait_queue(&ctx->fd_wqh, &wait);
 	for (;;) {
 		set_current_state(TASK_INTERRUPTIBLE);
@@ -1112,13 +1112,13 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
 			ret = -EAGAIN;
 			break;
 		}
-		spin_unlock(&ctx->fd_wqh.lock);
+		spin_unlock_irq(&ctx->fd_wqh.lock);
 		schedule();
-		spin_lock(&ctx->fd_wqh.lock);
+		spin_lock_irq(&ctx->fd_wqh.lock);
 	}
 	__remove_wait_queue(&ctx->fd_wqh, &wait);
 	__set_current_state(TASK_RUNNING);
-	spin_unlock(&ctx->fd_wqh.lock);
+	spin_unlock_irq(&ctx->fd_wqh.lock);
 
 	if (!ret && msg->event == UFFD_EVENT_FORK) {
 		ret = resolve_userfault_fork(ctx, fork_nctx, msg);

include/asm-generic/hugetlb.h

@@ -32,7 +32,7 @@ static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot)
 	return pte_modify(pte, newprot);
 }
 
-#ifndef huge_pte_clear
+#ifndef __HAVE_ARCH_HUGE_PTE_CLEAR
 static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 		    pte_t *ptep, unsigned long sz)
 {
@@ -40,4 +40,90 @@ static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr,
 }
 #endif
 
+#ifndef __HAVE_ARCH_HUGETLB_FREE_PGD_RANGE
+static inline void hugetlb_free_pgd_range(struct mmu_gather *tlb,
+		unsigned long addr, unsigned long end,
+		unsigned long floor, unsigned long ceiling)
+{
+	free_pgd_range(tlb, addr, end, floor, ceiling);
+}
+#endif
+
+#ifndef __HAVE_ARCH_HUGE_SET_HUGE_PTE_AT
+static inline void set_huge_pte_at(struct mm_struct *mm, unsigned long addr,
+		pte_t *ptep, pte_t pte)
+{
+	set_pte_at(mm, addr, ptep, pte);
+}
+#endif
+
+#ifndef __HAVE_ARCH_HUGE_PTEP_GET_AND_CLEAR
+static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+		unsigned long addr, pte_t *ptep)
+{
+	return ptep_get_and_clear(mm, addr, ptep);
+}
+#endif
+
+#ifndef __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH
+static inline void huge_ptep_clear_flush(struct vm_area_struct *vma,
+		unsigned long addr, pte_t *ptep)
+{
+	ptep_clear_flush(vma, addr, ptep);
+}
+#endif
+
+#ifndef __HAVE_ARCH_HUGE_PTE_NONE
+static inline int huge_pte_none(pte_t pte)
+{
+	return pte_none(pte);
+}
+#endif
+
+#ifndef __HAVE_ARCH_HUGE_PTE_WRPROTECT
+static inline pte_t huge_pte_wrprotect(pte_t pte)
+{
+	return pte_wrprotect(pte);
+}
+#endif
+
+#ifndef __HAVE_ARCH_PREPARE_HUGEPAGE_RANGE
+static inline int prepare_hugepage_range(struct file *file,
+		unsigned long addr, unsigned long len)
+{
+	struct hstate *h = hstate_file(file);
+
+	if (len & ~huge_page_mask(h))
+		return -EINVAL;
+	if (addr & ~huge_page_mask(h))
+		return -EINVAL;
+
+	return 0;
+}
+#endif
+
+#ifndef __HAVE_ARCH_HUGE_PTEP_SET_WRPROTECT
+static inline void huge_ptep_set_wrprotect(struct mm_struct *mm,
+		unsigned long addr, pte_t *ptep)
+{
+	ptep_set_wrprotect(mm, addr, ptep);
+}
+#endif
+
+#ifndef __HAVE_ARCH_HUGE_PTEP_SET_ACCESS_FLAGS
+static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+		unsigned long addr, pte_t *ptep,
+		pte_t pte, int dirty)
+{
+	return ptep_set_access_flags(vma, addr, ptep, pte, dirty);
+}
+#endif
+
+#ifndef __HAVE_ARCH_HUGE_PTEP_GET
+static inline pte_t huge_ptep_get(pte_t *ptep)
+{
+	return *ptep;
+}
+#endif
+
 #endif /* _ASM_GENERIC_HUGETLB_H */

include/asm-generic/pgtable.h

@@ -757,7 +757,7 @@ static inline pmd_t pmd_swp_clear_soft_dirty(pmd_t pmd)
 /*
  * Interfaces that can be used by architecture code to keep track of
  * memory type of pfn mappings specified by the remap_pfn_range,
- * vm_insert_pfn.
+ * vmf_insert_pfn.
  */
 
 /*
@@ -773,7 +773,7 @@ static inline int track_pfn_remap(struct vm_area_struct *vma, pgprot_t *prot,
 
 /*
  * track_pfn_insert is called when a _new_ single pfn is established
- * by vm_insert_pfn().
+ * by vmf_insert_pfn().
  */
 static inline void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
 				    pfn_t pfn)

include/linux/cgroup-defs.h

@@ -20,6 +20,7 @@
 #include <linux/u64_stats_sync.h>
 #include <linux/workqueue.h>
 #include <linux/bpf-cgroup.h>
+#include <linux/psi_types.h>
 
 #ifdef CONFIG_CGROUPS
 
@@ -436,6 +437,9 @@ struct cgroup {
 	/* used to schedule release agent */
 	struct work_struct release_agent_work;
 
+	/* used to track pressure stalls */
+	struct psi_group psi;
+
 	/* used to store eBPF programs */
 	struct cgroup_bpf bpf;
 

include/linux/cgroup.h

@@ -650,6 +650,11 @@ static inline void pr_cont_cgroup_path(struct cgroup *cgrp)
 	pr_cont_kernfs_path(cgrp->kn);
 }
 
+static inline struct psi_group *cgroup_psi(struct cgroup *cgrp)
+{
+	return &cgrp->psi;
+}
+
 static inline void cgroup_init_kthreadd(void)
 {
 	/*
@@ -703,6 +708,16 @@ static inline union kernfs_node_id *cgroup_get_kernfs_id(struct cgroup *cgrp)
 	return NULL;
 }
 
+static inline struct cgroup *cgroup_parent(struct cgroup *cgrp)
+{
+	return NULL;
+}
+
+static inline struct psi_group *cgroup_psi(struct cgroup *cgrp)
+{
+	return NULL;
+}
+
 static inline bool task_under_cgroup_hierarchy(struct task_struct *task,
 					       struct cgroup *ancestor)
 {

include/linux/delayacct.h

@@ -57,7 +57,12 @@ struct task_delay_info {
 
 	u64 freepages_start;
 	u64 freepages_delay;	/* wait for memory reclaim */
+
+	u64 thrashing_start;
+	u64 thrashing_delay;	/* wait for thrashing page */
+
 	u32 freepages_count;	/* total count of memory reclaim */
+	u32 thrashing_count;	/* total count of thrash waits */
 };
 #endif
 
@@ -76,6 +81,8 @@ extern int __delayacct_add_tsk(struct taskstats *, struct task_struct *);
 extern __u64 __delayacct_blkio_ticks(struct task_struct *);
 extern void __delayacct_freepages_start(void);
 extern void __delayacct_freepages_end(void);
+extern void __delayacct_thrashing_start(void);
+extern void __delayacct_thrashing_end(void);
 
 static inline int delayacct_is_task_waiting_on_io(struct task_struct *p)
 {
@@ -156,6 +163,18 @@ static inline void delayacct_freepages_end(void)
 		__delayacct_freepages_end();
 }
 
+static inline void delayacct_thrashing_start(void)
+{
+	if (current->delays)
+		__delayacct_thrashing_start();
+}
+
+static inline void delayacct_thrashing_end(void)
+{
+	if (current->delays)
+		__delayacct_thrashing_end();
+}
+
 #else
 static inline void delayacct_set_flag(int flag)
 {}
@@ -182,6 +201,10 @@ static inline void delayacct_freepages_start(void)
 {}
 static inline void delayacct_freepages_end(void)
 {}
+static inline void delayacct_thrashing_start(void)
+{}
+static inline void delayacct_thrashing_end(void)
+{}
 
 #endif /* CONFIG_TASK_DELAY_ACCT */
 

include/linux/hmm.h

@@ -107,7 +107,7 @@ enum hmm_pfn_flag_e {
  * HMM_PFN_ERROR: corresponding CPU page table entry points to poisoned memory
  * HMM_PFN_NONE: corresponding CPU page table entry is pte_none()
  * HMM_PFN_SPECIAL: corresponding CPU page table entry is special; i.e., the
- *      result of vm_insert_pfn() or vm_insert_page(). Therefore, it should not
+ *      result of vmf_insert_pfn() or vm_insert_page(). Therefore, it should not
  *      be mirrored by a device, because the entry will never have HMM_PFN_VALID
  *      set and the pfn value is undefined.
  *

include/linux/huge_mm.h

@@ -213,9 +213,9 @@ static inline int hpage_nr_pages(struct page *page)
 }
 
 struct page *follow_devmap_pmd(struct vm_area_struct *vma, unsigned long addr,
-		pmd_t *pmd, int flags);
+		pmd_t *pmd, int flags, struct dev_pagemap **pgmap);
 struct page *follow_devmap_pud(struct vm_area_struct *vma, unsigned long addr,
-		pud_t *pud, int flags);
+		pud_t *pud, int flags, struct dev_pagemap **pgmap);
 
 extern vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf, pmd_t orig_pmd);
 
@@ -344,13 +344,13 @@ static inline void mm_put_huge_zero_page(struct mm_struct *mm)
 }
 
 static inline struct page *follow_devmap_pmd(struct vm_area_struct *vma,
-		unsigned long addr, pmd_t *pmd, int flags)
+	unsigned long addr, pmd_t *pmd, int flags, struct dev_pagemap **pgmap)
 {
 	return NULL;
 }
 
 static inline struct page *follow_devmap_pud(struct vm_area_struct *vma,
-		unsigned long addr, pud_t *pud, int flags)
+	unsigned long addr, pud_t *pud, int flags, struct dev_pagemap **pgmap)
 {
 	return NULL;
 }

include/linux/iomap.h

@@ -6,6 +6,7 @@
 #include <linux/bitmap.h>
 #include <linux/mm.h>
 #include <linux/types.h>
+#include <linux/mm_types.h>
 
 struct address_space;
 struct fiemap_extent_info;
@@ -141,7 +142,8 @@ int iomap_zero_range(struct inode *inode, loff_t pos, loff_t len,
 		bool *did_zero, const struct iomap_ops *ops);
 int iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
 		const struct iomap_ops *ops);
-int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops);
+vm_fault_t iomap_page_mkwrite(struct vm_fault *vmf,
+			const struct iomap_ops *ops);
 int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		loff_t start, loff_t len, const struct iomap_ops *ops);
 loff_t iomap_seek_hole(struct inode *inode, loff_t offset,

include/linux/linkage.h

@@ -90,6 +90,7 @@
 #ifndef WEAK
 #define WEAK(name)	   \
 	.weak name ASM_NL   \
+	ALIGN ASM_NL \
 	name:
 #endif
 

include/linux/math64.h

@@ -281,4 +281,7 @@ static inline u64 mul_u64_u32_div(u64 a, u32 mul, u32 divisor)
 }
 #endif /* mul_u64_u32_div */
 
+#define DIV64_U64_ROUND_UP(ll, d)	\
+	({ u64 _tmp = (d); div64_u64((ll) + _tmp - 1, _tmp); })
+
 #endif /* _LINUX_MATH64_H */

include/linux/memblock.h

@@ -265,21 +265,6 @@ void __next_mem_pfn_range(int *idx, int nid, unsigned long *out_start_pfn,
 	for_each_mem_range_rev(i, &memblock.memory, &memblock.reserved,	\
 			       nid, flags, p_start, p_end, p_nid)
 
-/**
- * for_each_resv_unavail_range - iterate through reserved and unavailable memory
- * @i: u64 used as loop variable
- * @p_start: ptr to phys_addr_t for start address of the range, can be %NULL
- * @p_end: ptr to phys_addr_t for end address of the range, can be %NULL
- *
- * Walks over unavailable but reserved (reserved && !memory) areas of memblock.
- * Available as soon as memblock is initialized.
- * Note: because this memory does not belong to any physical node, flags and
- * nid arguments do not make sense and thus not exported as arguments.
- */
-#define for_each_resv_unavail_range(i, p_start, p_end)			\
-	for_each_mem_range(i, &memblock.reserved, &memblock.memory,	\
-			   NUMA_NO_NODE, MEMBLOCK_NONE, p_start, p_end, NULL)
-
 static inline void memblock_set_region_flags(struct memblock_region *r,
 					     enum memblock_flags flags)
 {

include/linux/memcontrol.h

@@ -78,7 +78,7 @@ struct mem_cgroup_reclaim_cookie {
 
 struct mem_cgroup_id {
 	int id;
-	atomic_t ref;
+	refcount_t ref;
 };
 
 /*
@@ -1268,10 +1268,11 @@ struct kmem_cache *memcg_kmem_get_cache(struct kmem_cache *cachep);
 void memcg_kmem_put_cache(struct kmem_cache *cachep);
 int memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order,
 			    struct mem_cgroup *memcg);
+
+#ifdef CONFIG_MEMCG_KMEM
 int memcg_kmem_charge(struct page *page, gfp_t gfp, int order);
 void memcg_kmem_uncharge(struct page *page, int order);
 
-#ifdef CONFIG_MEMCG_KMEM
 extern struct static_key_false memcg_kmem_enabled_key;
 extern struct workqueue_struct *memcg_kmem_cache_wq;
 
@@ -1307,6 +1308,16 @@ extern int memcg_expand_shrinker_maps(int new_id);
 extern void memcg_set_shrinker_bit(struct mem_cgroup *memcg,
 				   int nid, int shrinker_id);
 #else
+
+static inline int memcg_kmem_charge(struct page *page, gfp_t gfp, int order)
+{
+	return 0;
+}
+
+static inline void memcg_kmem_uncharge(struct page *page, int order)
+{
+}
+
 #define for_each_memcg_cache_index(_idx)	\
 	for (; NULL; )
 

include/linux/mm.h

@@ -848,6 +848,8 @@ static inline bool is_zone_device_page(const struct page *page)
 {
 	return page_zonenum(page) == ZONE_DEVICE;
 }
+extern void memmap_init_zone_device(struct zone *, unsigned long,
+				    unsigned long, struct dev_pagemap *);
 #else
 static inline bool is_zone_device_page(const struct page *page)
 {
@@ -2304,6 +2306,8 @@ extern unsigned long do_mmap(struct file *file, unsigned long addr,
 	unsigned long len, unsigned long prot, unsigned long flags,
 	vm_flags_t vm_flags, unsigned long pgoff, unsigned long *populate,
 	struct list_head *uf);
+extern int __do_munmap(struct mm_struct *, unsigned long, size_t,
+		       struct list_head *uf, bool downgrade);
 extern int do_munmap(struct mm_struct *, unsigned long, size_t,
 		     struct list_head *uf);
 
@@ -2502,11 +2506,11 @@ struct vm_area_struct *find_extend_vma(struct mm_struct *, unsigned long addr);
 int remap_pfn_range(struct vm_area_struct *, unsigned long addr,
 			unsigned long pfn, unsigned long size, pgprot_t);
 int vm_insert_page(struct vm_area_struct *, unsigned long addr, struct page *);
-int vm_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
+vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn);
-int vm_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
+vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn, pgprot_t pgprot);
-int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
+vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 			pfn_t pfn);
 vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma,
 		unsigned long addr, pfn_t pfn);
@@ -2525,32 +2529,6 @@ static inline vm_fault_t vmf_insert_page(struct vm_area_struct *vma,
 	return VM_FAULT_NOPAGE;
 }
 
-static inline vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma,
-				unsigned long addr, pfn_t pfn)
-{
-	int err = vm_insert_mixed(vma, addr, pfn);
-
-	if (err == -ENOMEM)
-		return VM_FAULT_OOM;
-	if (err < 0 && err != -EBUSY)
-		return VM_FAULT_SIGBUS;
-
-	return VM_FAULT_NOPAGE;
-}
-
-static inline vm_fault_t vmf_insert_pfn(struct vm_area_struct *vma,
-			unsigned long addr, unsigned long pfn)
-{
-	int err = vm_insert_pfn(vma, addr, pfn);
-
-	if (err == -ENOMEM)
-		return VM_FAULT_OOM;
-	if (err < 0 && err != -EBUSY)
-		return VM_FAULT_SIGBUS;
-
-	return VM_FAULT_NOPAGE;
-}
-
 static inline vm_fault_t vmf_error(int err)
 {
 	if (err == -ENOMEM)
@@ -2558,16 +2536,8 @@ static inline vm_fault_t vmf_error(int err)
 	return VM_FAULT_SIGBUS;
 }
 
-struct page *follow_page_mask(struct vm_area_struct *vma,
+struct page *follow_page(struct vm_area_struct *vma, unsigned long address,
-			      unsigned long address, unsigned int foll_flags,
+			 unsigned int foll_flags);
-			      unsigned int *page_mask);
-
-static inline struct page *follow_page(struct vm_area_struct *vma,
-		unsigned long address, unsigned int foll_flags)
-{
-	unsigned int unused_page_mask;
-	return follow_page_mask(vma, address, foll_flags, &unused_page_mask);
-}
 
 #define FOLL_WRITE	0x01	/* check pte is writable */
 #define FOLL_TOUCH	0x02	/* mark page accessed */

include/linux/mmu_notifier.h

@@ -2,7 +2,6 @@
 #ifndef _LINUX_MMU_NOTIFIER_H
 #define _LINUX_MMU_NOTIFIER_H
 
-#include <linux/types.h>
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/mm_types.h>
@@ -11,9 +10,6 @@
 struct mmu_notifier;
 struct mmu_notifier_ops;
 
-/* mmu_notifier_ops flags */
-#define MMU_INVALIDATE_DOES_NOT_BLOCK	(0x01)
-
 #ifdef CONFIG_MMU_NOTIFIER
 
 /*
@@ -30,15 +26,6 @@ struct mmu_notifier_mm {
 };
 
 struct mmu_notifier_ops {
-	/*
-	 * Flags to specify behavior of callbacks for this MMU notifier.
-	 * Used to determine which context an operation may be called.
-	 *
-	 * MMU_INVALIDATE_DOES_NOT_BLOCK: invalidate_range_* callbacks do not
-	 *	block
-	 */
-	int flags;
-
 	/*
 	 * Called either by mmu_notifier_unregister or when the mm is
 	 * being destroyed by exit_mmap, always before all pages are
@@ -153,7 +140,9 @@ struct mmu_notifier_ops {
 	 *
 	 * If blockable argument is set to false then the callback cannot
 	 * sleep and has to return with -EAGAIN. 0 should be returned
-	 * otherwise.
+	 * otherwise. Please note that if invalidate_range_start approves
+	 * a non-blocking behavior then the same applies to
+	 * invalidate_range_end.
 	 *
 	 */
 	int (*invalidate_range_start)(struct mmu_notifier *mn,
@@ -181,10 +170,6 @@ struct mmu_notifier_ops {
 	 * Note that this function might be called with just a sub-range
 	 * of what was passed to invalidate_range_start()/end(), if
 	 * called between those functions.
-	 *
-	 * If this callback cannot block, and invalidate_range_{start,end}
-	 * cannot block, mmu_notifier_ops.flags should have
-	 * MMU_INVALIDATE_DOES_NOT_BLOCK set.
 	 */
 	void (*invalidate_range)(struct mmu_notifier *mn, struct mm_struct *mm,
 				 unsigned long start, unsigned long end);
@@ -239,7 +224,6 @@ extern void __mmu_notifier_invalidate_range_end(struct mm_struct *mm,
 				  bool only_end);
 extern void __mmu_notifier_invalidate_range(struct mm_struct *mm,
 				  unsigned long start, unsigned long end);
-extern bool mm_has_blockable_invalidate_notifiers(struct mm_struct *mm);
 
 static inline void mmu_notifier_release(struct mm_struct *mm)
 {
@@ -493,11 +477,6 @@ static inline void mmu_notifier_invalidate_range(struct mm_struct *mm,
 {
 }
 
-static inline bool mm_has_blockable_invalidate_notifiers(struct mm_struct *mm)
-{
-	return false;
-}
-
 static inline void mmu_notifier_mm_init(struct mm_struct *mm)
 {
 }

include/linux/mmzone.h

@@ -161,8 +161,10 @@ enum node_stat_item {
 	NR_SLAB_UNRECLAIMABLE,
 	NR_ISOLATED_ANON,	/* Temporary isolated pages from anon lru */
 	NR_ISOLATED_FILE,	/* Temporary isolated pages from file lru */
+	WORKINGSET_NODES,
 	WORKINGSET_REFAULT,
 	WORKINGSET_ACTIVATE,
+	WORKINGSET_RESTORE,
 	WORKINGSET_NODERECLAIM,
 	NR_ANON_MAPPED,	/* Mapped anonymous pages */
 	NR_FILE_MAPPED,	/* pagecache pages mapped into pagetables.
@@ -180,7 +182,7 @@ enum node_stat_item {
 	NR_VMSCAN_IMMEDIATE,	/* Prioritise for reclaim when writeback ends */
 	NR_DIRTIED,		/* page dirtyings since bootup */
 	NR_WRITTEN,		/* page writings since bootup */
-	NR_INDIRECTLY_RECLAIMABLE_BYTES, /* measured in bytes */
+	NR_KERNEL_MISC_RECLAIMABLE,	/* reclaimable non-slab kernel pages */
 	NR_VM_NODE_STAT_ITEMS
 };
 

include/linux/page-flags.h

@@ -69,13 +69,14 @@
  */
 enum pageflags {
 	PG_locked,		/* Page is locked. Don't touch. */
-	PG_error,
 	PG_referenced,
 	PG_uptodate,
 	PG_dirty,
 	PG_lru,
 	PG_active,
+	PG_workingset,
 	PG_waiters,		/* Page has waiters, check its waitqueue. Must be bit #7 and in the same byte as "PG_locked" */
+	PG_error,
 	PG_slab,
 	PG_owner_priv_1,	/* Owner use. If pagecache, fs may use*/
 	PG_arch_1,
@@ -162,6 +163,14 @@ static inline int PagePoisoned(const struct page *page)
 	return page->flags == PAGE_POISON_PATTERN;
 }
 
+#ifdef CONFIG_DEBUG_VM
+void page_init_poison(struct page *page, size_t size);
+#else
+static inline void page_init_poison(struct page *page, size_t size)
+{
+}
+#endif
+
 /*
  * Page flags policies wrt compound pages
  *
@@ -280,6 +289,8 @@ PAGEFLAG(Dirty, dirty, PF_HEAD) TESTSCFLAG(Dirty, dirty, PF_HEAD)
 PAGEFLAG(LRU, lru, PF_HEAD) __CLEARPAGEFLAG(LRU, lru, PF_HEAD)
 PAGEFLAG(Active, active, PF_HEAD) __CLEARPAGEFLAG(Active, active, PF_HEAD)
 	TESTCLEARFLAG(Active, active, PF_HEAD)
+PAGEFLAG(Workingset, workingset, PF_HEAD)
+	TESTCLEARFLAG(Workingset, workingset, PF_HEAD)
 __PAGEFLAG(Slab, slab, PF_NO_TAIL)
 __PAGEFLAG(SlobFree, slob_free, PF_NO_TAIL)
 PAGEFLAG(Checked, checked, PF_NO_COMPOUND)	   /* Used by some filesystems */
@@ -292,6 +303,7 @@ PAGEFLAG(Foreign, foreign, PF_NO_COMPOUND);
 
 PAGEFLAG(Reserved, reserved, PF_NO_COMPOUND)
 	__CLEARPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND)
+	__SETPAGEFLAG(Reserved, reserved, PF_NO_COMPOUND)
 PAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL)
 	__CLEARPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL)
 	__SETPAGEFLAG(SwapBacked, swapbacked, PF_NO_TAIL)

include/linux/pfn_t.h

@@ -9,8 +9,10 @@
  * PFN_SG_LAST - pfn references a page and is the last scatterlist entry
  * PFN_DEV - pfn is not covered by system memmap by default
  * PFN_MAP - pfn has a dynamic page mapping established by a device driver
+ * PFN_SPECIAL - for CONFIG_FS_DAX_LIMITED builds to allow XIP, but not
+ *		 get_user_pages
  */
-#define PFN_FLAGS_MASK (((u64) ~PAGE_MASK) << (BITS_PER_LONG_LONG - PAGE_SHIFT))
+#define PFN_FLAGS_MASK (((u64) (~PAGE_MASK)) << (BITS_PER_LONG_LONG - PAGE_SHIFT))
 #define PFN_SG_CHAIN (1ULL << (BITS_PER_LONG_LONG - 1))
 #define PFN_SG_LAST (1ULL << (BITS_PER_LONG_LONG - 2))
 #define PFN_DEV (1ULL << (BITS_PER_LONG_LONG - 3))

include/linux/psi.h

@@ -0,0 +1,53 @@
+#ifndef _LINUX_PSI_H
+#define _LINUX_PSI_H
+
+#include <linux/psi_types.h>
+#include <linux/sched.h>
+
+struct seq_file;
+struct css_set;
+
+#ifdef CONFIG_PSI
+
+extern bool psi_disabled;
+
+void psi_init(void);
+
+void psi_task_change(struct task_struct *task, int clear, int set);
+
+void psi_memstall_tick(struct task_struct *task, int cpu);
+void psi_memstall_enter(unsigned long *flags);
+void psi_memstall_leave(unsigned long *flags);
+
+int psi_show(struct seq_file *s, struct psi_group *group, enum psi_res res);
+
+#ifdef CONFIG_CGROUPS
+int psi_cgroup_alloc(struct cgroup *cgrp);
+void psi_cgroup_free(struct cgroup *cgrp);
+void cgroup_move_task(struct task_struct *p, struct css_set *to);
+#endif
+
+#else /* CONFIG_PSI */
+
+static inline void psi_init(void) {}
+
+static inline void psi_memstall_enter(unsigned long *flags) {}
+static inline void psi_memstall_leave(unsigned long *flags) {}
+
+#ifdef CONFIG_CGROUPS
+static inline int psi_cgroup_alloc(struct cgroup *cgrp)
+{
+	return 0;
+}
+static inline void psi_cgroup_free(struct cgroup *cgrp)
+{
+}
+static inline void cgroup_move_task(struct task_struct *p, struct css_set *to)
+{
+	rcu_assign_pointer(p->cgroups, to);
+}
+#endif
+
+#endif /* CONFIG_PSI */
+
+#endif /* _LINUX_PSI_H */

include/linux/psi_types.h

@@ -0,0 +1,92 @@
+#ifndef _LINUX_PSI_TYPES_H
+#define _LINUX_PSI_TYPES_H
+
+#include <linux/seqlock.h>
+#include <linux/types.h>
+
+#ifdef CONFIG_PSI
+
+/* Tracked task states */
+enum psi_task_count {
+	NR_IOWAIT,
+	NR_MEMSTALL,
+	NR_RUNNING,
+	NR_PSI_TASK_COUNTS,
+};
+
+/* Task state bitmasks */
+#define TSK_IOWAIT	(1 << NR_IOWAIT)
+#define TSK_MEMSTALL	(1 << NR_MEMSTALL)
+#define TSK_RUNNING	(1 << NR_RUNNING)
+
+/* Resources that workloads could be stalled on */
+enum psi_res {
+	PSI_IO,
+	PSI_MEM,
+	PSI_CPU,
+	NR_PSI_RESOURCES,
+};
+
+/*
+ * Pressure states for each resource:
+ *
+ * SOME: Stalled tasks & working tasks
+ * FULL: Stalled tasks & no working tasks
+ */
+enum psi_states {
+	PSI_IO_SOME,
+	PSI_IO_FULL,
+	PSI_MEM_SOME,
+	PSI_MEM_FULL,
+	PSI_CPU_SOME,
+	/* Only per-CPU, to weigh the CPU in the global average: */
+	PSI_NONIDLE,
+	NR_PSI_STATES,
+};
+
+struct psi_group_cpu {
+	/* 1st cacheline updated by the scheduler */
+
+	/* Aggregator needs to know of concurrent changes */
+	seqcount_t seq ____cacheline_aligned_in_smp;
+
+	/* States of the tasks belonging to this group */
+	unsigned int tasks[NR_PSI_TASK_COUNTS];
+
+	/* Period time sampling buckets for each state of interest (ns) */
+	u32 times[NR_PSI_STATES];
+
+	/* Time of last task change in this group (rq_clock) */
+	u64 state_start;
+
+	/* 2nd cacheline updated by the aggregator */
+
+	/* Delta detection against the sampling buckets */
+	u32 times_prev[NR_PSI_STATES] ____cacheline_aligned_in_smp;
+};
+
+struct psi_group {
+	/* Protects data updated during an aggregation */
+	struct mutex stat_lock;
+
+	/* Per-cpu task state & time tracking */
+	struct psi_group_cpu __percpu *pcpu;
+
+	/* Periodic aggregation state */
+	u64 total_prev[NR_PSI_STATES - 1];
+	u64 last_update;
+	u64 next_update;
+	struct delayed_work clock_work;
+
+	/* Total stall times and sampled pressure averages */
+	u64 total[NR_PSI_STATES - 1];
+	unsigned long avg[NR_PSI_STATES - 1][3];
+};
+
+#else /* CONFIG_PSI */
+
+struct psi_group { };
+
+#endif /* CONFIG_PSI */
+
+#endif /* _LINUX_PSI_TYPES_H */

include/linux/sched.h

@@ -25,6 +25,7 @@
 #include <linux/latencytop.h>
 #include <linux/sched/prio.h>
 #include <linux/signal_types.h>
+#include <linux/psi_types.h>
 #include <linux/mm_types_task.h>
 #include <linux/task_io_accounting.h>
 #include <linux/rseq.h>
@@ -706,6 +707,10 @@ struct task_struct {
 	unsigned			sched_contributes_to_load:1;
 	unsigned			sched_migrated:1;
 	unsigned			sched_remote_wakeup:1;
+#ifdef CONFIG_PSI
+	unsigned			sched_psi_wake_requeue:1;
+#endif
+
 	/* Force alignment to the next boundary: */
 	unsigned			:0;
 
@@ -719,9 +724,6 @@ struct task_struct {
 #endif
 #ifdef CONFIG_MEMCG
 	unsigned			in_user_fault:1;
-#ifdef CONFIG_MEMCG_KMEM
-	unsigned			memcg_kmem_skip_account:1;
-#endif
 #endif
 #ifdef CONFIG_COMPAT_BRK
 	unsigned			brk_randomized:1;
@@ -965,6 +967,10 @@ struct task_struct {
 	kernel_siginfo_t		*last_siginfo;
 
 	struct task_io_accounting	ioac;
+#ifdef CONFIG_PSI
+	/* Pressure stall state */
+	unsigned int			psi_flags;
+#endif
 #ifdef CONFIG_TASK_XACCT
 	/* Accumulated RSS usage: */
 	u64				acct_rss_mem1;
@@ -1391,6 +1397,7 @@ extern struct pid *cad_pid;
 #define PF_KTHREAD		0x00200000	/* I am a kernel thread */
 #define PF_RANDOMIZE		0x00400000	/* Randomize virtual address space */
 #define PF_SWAPWRITE		0x00800000	/* Allowed to write to swap */
+#define PF_MEMSTALL		0x01000000	/* Stalled due to lack of memory */
 #define PF_NO_SETAFFINITY	0x04000000	/* Userland is not allowed to meddle with cpus_allowed */
 #define PF_MCE_EARLY		0x08000000      /* Early kill for mce process policy */
 #define PF_MUTEX_TESTER		0x20000000	/* Thread belongs to the rt mutex tester */

include/linux/sched/loadavg.h

@@ -22,10 +22,26 @@ extern void get_avenrun(unsigned long *loads, unsigned long offset, int shift);
 #define EXP_5		2014		/* 1/exp(5sec/5min) */
 #define EXP_15		2037		/* 1/exp(5sec/15min) */
 
-#define CALC_LOAD(load,exp,n) \
+/*
-	load *= exp; \
+ * a1 = a0 * e + a * (1 - e)
-	load += n*(FIXED_1-exp); \
+ */
-	load >>= FSHIFT;
+static inline unsigned long
+calc_load(unsigned long load, unsigned long exp, unsigned long active)
+{
+	unsigned long newload;
+
+	newload = load * exp + active * (FIXED_1 - exp);
+	if (active >= load)
+		newload += FIXED_1-1;
+
+	return newload / FIXED_1;
+}
+
+extern unsigned long calc_load_n(unsigned long load, unsigned long exp,
+				 unsigned long active, unsigned int n);
+
+#define LOAD_INT(x) ((x) >> FSHIFT)
+#define LOAD_FRAC(x) LOAD_INT(((x) & (FIXED_1-1)) * 100)
 
 extern void calc_global_load(unsigned long ticks);
 

include/linux/slab.h

@@ -295,11 +295,42 @@ static inline void __check_heap_object(const void *ptr, unsigned long n,
 #define SLAB_OBJ_MIN_SIZE      (KMALLOC_MIN_SIZE < 16 ? \
                                (KMALLOC_MIN_SIZE) : 16)
 
-#ifndef CONFIG_SLOB
+/*
-extern struct kmem_cache *kmalloc_caches[KMALLOC_SHIFT_HIGH + 1];
+ * Whenever changing this, take care of that kmalloc_type() and
+ * create_kmalloc_caches() still work as intended.
+ */
+enum kmalloc_cache_type {
+	KMALLOC_NORMAL = 0,
+	KMALLOC_RECLAIM,
 #ifdef CONFIG_ZONE_DMA
-extern struct kmem_cache *kmalloc_dma_caches[KMALLOC_SHIFT_HIGH + 1];
+	KMALLOC_DMA,
 #endif
+	NR_KMALLOC_TYPES
+};
+
+#ifndef CONFIG_SLOB
+extern struct kmem_cache *
+kmalloc_caches[NR_KMALLOC_TYPES][KMALLOC_SHIFT_HIGH + 1];
+
+static __always_inline enum kmalloc_cache_type kmalloc_type(gfp_t flags)
+{
+	int is_dma = 0;
+	int type_dma = 0;
+	int is_reclaimable;
+
+#ifdef CONFIG_ZONE_DMA
+	is_dma = !!(flags & __GFP_DMA);
+	type_dma = is_dma * KMALLOC_DMA;
+#endif
+
+	is_reclaimable = !!(flags & __GFP_RECLAIMABLE);
+
+	/*
+	 * If an allocation is both __GFP_DMA and __GFP_RECLAIMABLE, return
+	 * KMALLOC_DMA and effectively ignore __GFP_RECLAIMABLE
+	 */
+	return type_dma + (is_reclaimable & !is_dma) * KMALLOC_RECLAIM;
+}
 
 /*
  * Figure out which kmalloc slab an allocation of a certain size
@@ -501,18 +532,20 @@ static __always_inline void *kmalloc_large(size_t size, gfp_t flags)
 static __always_inline void *kmalloc(size_t size, gfp_t flags)
 {
 	if (__builtin_constant_p(size)) {
+#ifndef CONFIG_SLOB
+		unsigned int index;
+#endif
 		if (size > KMALLOC_MAX_CACHE_SIZE)
 			return kmalloc_large(size, flags);
 #ifndef CONFIG_SLOB
-		if (!(flags & GFP_DMA)) {
+		index = kmalloc_index(size);
-			unsigned int index = kmalloc_index(size);
 
-			if (!index)
+		if (!index)
-				return ZERO_SIZE_PTR;
+			return ZERO_SIZE_PTR;
 
-			return kmem_cache_alloc_trace(kmalloc_caches[index],
+		return kmem_cache_alloc_trace(
-					flags, size);
+				kmalloc_caches[kmalloc_type(flags)][index],
-		}
+				flags, size);
 #endif
 	}
 	return __kmalloc(size, flags);
@@ -542,13 +575,14 @@ static __always_inline void *kmalloc_node(size_t size, gfp_t flags, int node)
 {
 #ifndef CONFIG_SLOB
 	if (__builtin_constant_p(size) &&
-		size <= KMALLOC_MAX_CACHE_SIZE && !(flags & GFP_DMA)) {
+		size <= KMALLOC_MAX_CACHE_SIZE) {
 		unsigned int i = kmalloc_index(size);
 
 		if (!i)
 			return ZERO_SIZE_PTR;
 
-		return kmem_cache_alloc_node_trace(kmalloc_caches[i],
+		return kmem_cache_alloc_node_trace(
+				kmalloc_caches[kmalloc_type(flags)][i],
 						flags, node, size);
 	}
 #endif

include/linux/swap.h

@@ -167,13 +167,14 @@ enum {
 	SWP_SOLIDSTATE	= (1 << 4),	/* blkdev seeks are cheap */
 	SWP_CONTINUED	= (1 << 5),	/* swap_map has count continuation */
 	SWP_BLKDEV	= (1 << 6),	/* its a block device */
-	SWP_FILE	= (1 << 7),	/* set after swap_activate success */
+	SWP_ACTIVATED	= (1 << 7),	/* set after swap_activate success */
-	SWP_AREA_DISCARD = (1 << 8),	/* single-time swap area discards */
+	SWP_FS		= (1 << 8),	/* swap file goes through fs */
-	SWP_PAGE_DISCARD = (1 << 9),	/* freed swap page-cluster discards */
+	SWP_AREA_DISCARD = (1 << 9),	/* single-time swap area discards */
-	SWP_STABLE_WRITES = (1 << 10),	/* no overwrite PG_writeback pages */
+	SWP_PAGE_DISCARD = (1 << 10),	/* freed swap page-cluster discards */
-	SWP_SYNCHRONOUS_IO = (1 << 11),	/* synchronous IO is efficient */
+	SWP_STABLE_WRITES = (1 << 11),	/* no overwrite PG_writeback pages */
+	SWP_SYNCHRONOUS_IO = (1 << 12),	/* synchronous IO is efficient */
 					/* add others here before... */
-	SWP_SCANNING	= (1 << 12),	/* refcount in scan_swap_map */
+	SWP_SCANNING	= (1 << 13),	/* refcount in scan_swap_map */
 };
 
 #define SWAP_CLUSTER_MAX 32UL
@@ -296,7 +297,7 @@ struct vma_swap_readahead {
 
 /* linux/mm/workingset.c */
 void *workingset_eviction(struct address_space *mapping, struct page *page);
-bool workingset_refault(void *shadow);
+void workingset_refault(struct page *page, void *shadow);
 void workingset_activation(struct page *page);
 
 /* Do not use directly, use workingset_lookup_update */

include/trace/events/mmflags.h

@@ -88,6 +88,7 @@
 	{1UL << PG_dirty,		"dirty"		},		\
 	{1UL << PG_lru,			"lru"		},		\
 	{1UL << PG_active,		"active"	},		\
+	{1UL << PG_workingset,		"workingset"	},		\
 	{1UL << PG_slab,		"slab"		},		\
 	{1UL << PG_owner_priv_1,	"owner_priv_1"	},		\
 	{1UL << PG_arch_1,		"arch_1"	},		\

include/uapi/linux/taskstats.h

@@ -34,7 +34,7 @@
  */
 
 
-#define TASKSTATS_VERSION	8
+#define TASKSTATS_VERSION	9
 #define TS_COMM_LEN		32	/* should be >= TASK_COMM_LEN
 					 * in linux/sched.h */
 
@@ -164,6 +164,10 @@ struct taskstats {
 	/* Delay waiting for memory reclaim */
 	__u64	freepages_count;
 	__u64	freepages_delay_total;
+
+	/* Delay waiting for thrashing page */
+	__u64	thrashing_count;
+	__u64	thrashing_delay_total;
 };
 
 

init/Kconfig

@@ -490,6 +490,25 @@ config TASK_IO_ACCOUNTING
 
 	  Say N if unsure.
 
+config PSI
+	bool "Pressure stall information tracking"
+	help
+	  Collect metrics that indicate how overcommitted the CPU, memory,
+	  and IO capacity are in the system.
+
+	  If you say Y here, the kernel will create /proc/pressure/ with the
+	  pressure statistics files cpu, memory, and io. These will indicate
+	  the share of walltime in which some or all tasks in the system are
+	  delayed due to contention of the respective resource.
+
+	  In kernels with cgroup support, cgroups (cgroup2 only) will
+	  have cpu.pressure, memory.pressure, and io.pressure files,
+	  which aggregate pressure stalls for the grouped tasks only.
+
+	  For more details see Documentation/accounting/psi.txt.
+
+	  Say N if unsure.
+
 endmenu # "CPU/Task time and stats accounting"
 
 config CPU_ISOLATION