Merge branch 'akpm' (patches from Andrew)

345671ea · Linus Torvalds <[email protected]> · 2018-10-26 19:33:41 -07:00

Merge updates from Andrew Morton:

 - a few misc things

 - ocfs2 updates

 - most of MM

* emailed patches from Andrew Morton <[email protected]>: (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
  ...

Commit: 345671ea0f9258f410eb057b9ced9cefbbe5dc78
Parents: 49040081 · 22146c3c

Merge commit. Changes below are compared with the first parent: 49040081.

Changes

156 files changed · +3400 −1988

File	Status	Add	Del	Content
Documentation/accounting/psi.txt	added	+73	−0	View file
Documentation/admin-guide/cgroup-v2.rst	modified	+22	−0	View file
Documentation/admin-guide/kernel-parameters.txt	modified	+12	−0	View file
Documentation/filesystems/proc.txt	modified	+4	−0	View file
Documentation/vm/slub.rst	modified	+9	−3	View file
Documentation/x86/pat.txt	modified	+2	−2	View file
arch/alpha/Kconfig	modified	+2	−0	View file
arch/alpha/kernel/core_irongate.c	modified	+2	−2	View file
arch/alpha/kernel/setup.c	modified	+12	−86	View file
arch/alpha/mm/numa.c	modified	+13	−100	View file
arch/arm/include/asm/hugetlb-3level.h	modified	+1	−31	View file
arch/arm/include/asm/hugetlb.h	modified	+1	−32	View file
arch/arm64/include/asm/hugetlb.h	modified	+7	−32	View file
arch/arm64/include/asm/string.h	modified	+8	−6	View file
arch/arm64/kernel/arm64ksyms.c	modified	+5	−2	View file
arch/arm64/lib/memchr.S	modified	+1	−1	View file
arch/arm64/lib/memcmp.S	modified	+1	−1	View file
arch/arm64/lib/strchr.S	modified	+1	−1	View file
arch/arm64/lib/strcmp.S	modified	+1	−1	View file
arch/arm64/lib/strlen.S	modified	+1	−1	View file
arch/arm64/lib/strncmp.S	modified	+1	−1	View file
arch/arm64/lib/strnlen.S	modified	+1	−1	View file
arch/arm64/lib/strrchr.S	modified	+1	−1	View file
arch/hexagon/Kconfig	modified	+3	−0	View file
arch/hexagon/mm/init.c	modified	+8	−12	View file
arch/ia64/include/asm/hugetlb.h	modified	+5	−42	View file
arch/ia64/include/asm/pgtable.h	modified	+0	−1	View file
arch/mips/include/asm/hugetlb.h	modified	+7	−33	View file
arch/nios2/Kconfig	modified	+3	−0	View file
arch/nios2/kernel/prom.c	modified	+0	−17	View file
arch/nios2/kernel/setup.c	modified	+7	−32	View file
arch/parisc/include/asm/hugetlb.h	modified	+8	−25	View file
arch/powerpc/include/asm/book3s/32/pgtable.h	modified	+0	−6	View file
arch/powerpc/include/asm/book3s/64/pgtable.h	modified	+1	−0	View file
arch/powerpc/include/asm/hugetlb.h	modified	+6	−37	View file
arch/powerpc/include/asm/nohash/32/pgtable.h	modified	+0	−6	View file
arch/powerpc/include/asm/nohash/64/pgtable.h	modified	+1	−0	View file
arch/powerpc/platforms/cell/cpufreq_spudemand.c	modified	+1	−1	View file
arch/powerpc/platforms/cell/spufs/sched.c	modified	+3	−6	View file
arch/s390/appldata/appldata_os.c	modified	+0	−4	View file
arch/sh/include/asm/hugetlb.h	modified	+4	−50	View file
arch/sparc/include/asm/hugetlb.h	modified	+8	−32	View file
arch/um/Kconfig	modified	+2	−0	View file
arch/um/kernel/physmem.c	modified	+10	−12	View file
arch/unicore32/Kconfig	modified	+1	−0	View file
arch/unicore32/mm/init.c	modified	+1	−53	View file
arch/x86/entry/vdso/vma.c	modified	+9	−15	View file
arch/x86/include/asm/hugetlb.h	modified	+0	−69	View file
arch/x86/kernel/e820.c	modified	+3	−12	View file
arch/xtensa/include/asm/Kbuild	modified	+1	−0	View file
arch/xtensa/include/asm/vga.h	deleted	+0	−19	View before deletion
block/blk-iolatency.c	modified	+5	−3	View file
drivers/base/node.c	modified	+12	−7	View file
drivers/cpuidle/governors/menu.c	modified	+0	−4	View file
drivers/infiniband/hw/hfi1/mmu_rb.c	modified	+0	−1	View file
drivers/iommu/amd_iommu_v2.c	modified	+0	−1	View file
drivers/iommu/intel-svm.c	modified	+0	−1	View file
drivers/misc/sgi-gru/grutlbpurge.c	modified	+0	−1	View file
drivers/of/fdt.c	modified	+6	−5	View file
drivers/staging/android/ion/ion_page_pool.c	modified	+4	−4	View file
fs/cramfs/inode.c	modified	+4	−1	View file
fs/dcache.c	modified	+9	−29	View file
fs/iomap.c	modified	+1	−1	View file
fs/kernfs/mount.c	modified	+3	−0	View file
fs/ocfs2/alloc.c	modified	+0	−4	View file
fs/ocfs2/aops.c	modified	+1	−2	View file
fs/ocfs2/dlm/dlmdebug.c	modified	+1	−1	View file
fs/ocfs2/dlm/dlmthread.c	modified	+1	−1	View file
fs/ocfs2/refcounttree.c	modified	+0	−2	View file
fs/proc/inode.c	modified	+3	−0	View file
fs/proc/loadavg.c	modified	+0	−3	View file
fs/proc/meminfo.c	modified	+8	−8	View file
fs/proc/task_mmu.c	modified	+3	−1	View file
fs/userfaultfd.c	modified	+4	−4	View file
include/asm-generic/hugetlb.h	modified	+87	−1	View file
include/asm-generic/pgtable.h	modified	+2	−2	View file
include/linux/cgroup-defs.h	modified	+4	−0	View file
include/linux/cgroup.h	modified	+15	−0	View file
include/linux/delayacct.h	modified	+23	−0	View file
include/linux/hmm.h	modified	+1	−1	View file
include/linux/huge_mm.h	modified	+4	−4	View file
include/linux/iomap.h	modified	+3	−1	View file
include/linux/linkage.h	modified	+1	−0	View file
include/linux/math64.h	modified	+3	−0	View file
include/linux/memblock.h	modified	+0	−15	View file
include/linux/memcontrol.h	modified	+13	−2	View file
include/linux/mm.h	modified	+9	−39	View file
include/linux/mmu_notifier.h	modified	+3	−24	View file
include/linux/mmzone.h	modified	+3	−1	View file
include/linux/page-flags.h	modified	+13	−1	View file
include/linux/pfn_t.h	modified	+3	−1	View file
include/linux/psi.h	added	+53	−0	View file
include/linux/psi_types.h	added	+92	−0	View file
include/linux/sched.h	modified	+10	−3	View file
include/linux/sched/loadavg.h	modified	+20	−4	View file
include/linux/slab.h	modified	+45	−11	View file
include/linux/swap.h	modified	+8	−7	View file
include/trace/events/mmflags.h	modified	+1	−0	View file
include/uapi/linux/taskstats.h	modified	+5	−1	View file
init/Kconfig	modified	+19	−0	View file
kernel/cgroup/cgroup.c	modified	+43	−2	View file
kernel/debug/kdb/kdb_main.c	modified	+1	−6	View file
kernel/delayacct.c	modified	+15	−0	View file
kernel/fork.c	modified	+53	−6	View file
kernel/memremap.c	modified	+10	−15	View file
kernel/sched/Makefile	modified	+1	−0	View file
kernel/sched/core.c	modified	+11	−5	View file
kernel/sched/loadavg.c	modified	+62	−77	View file
kernel/sched/psi.c	added	+759	−0	View file
kernel/sched/sched.h	modified	+96	−82	View file
kernel/sched/stats.h	modified	+86	−0	View file
lib/test_kasan.c	modified	+70	−0	View file
mm/compaction.c	modified	+5	−0	View file
mm/debug.c	modified	+46	−0	View file
mm/filemap.c	modified	+25	−12	View file
mm/gup.c	modified	+67	−48	View file
mm/gup_benchmark.c	modified	+33	−4	View file
mm/hmm.c	modified	+7	−5	View file
mm/huge_memory.c	modified	+20	−11	View file
mm/hugetlb.c	modified	+6	−0	View file
mm/kasan/quarantine.c	modified	+9	−9	View file
mm/kmemleak.c	modified	+35	−7	View file
mm/memblock.c	modified	+2	−3	View file
mm/memcontrol.c	modified	+16	−38	View file
mm/memory.c	modified	+90	−66	View file
mm/memory_hotplug.c	modified	+40	−106	View file
mm/mempolicy.c	modified	+22	−13	View file
mm/migrate.c	modified	+25	−19	View file
mm/mmap.c	modified	+74	−22	View file
mm/mmu_notifier.c	modified	+0	−31	View file
mm/mremap.c	modified	+16	−4	View file
mm/nommu.c	modified	+2	−4	View file
mm/page-writeback.c	modified	+15	−18	View file
mm/page_alloc.c	modified	+230	−132	View file
mm/page_io.c	modified	+3	−3	View file
mm/slab.c	modified	+6	−2	View file
mm/slab_common.c	modified	+68	−47	View file
mm/slub.c	modified	+58	−25	View file
mm/sparse.c	modified	+1	−3	View file
mm/swap.c	modified	+0	−1	View file
mm/swap_state.c	modified	+1	−0	View file
mm/swapfile.c	modified	+38	−45	View file
mm/util.c	modified	+2	−3	View file
mm/vmalloc.c	modified	+4	−0	View file
mm/vmscan.c	modified	+26	−5	View file
mm/vmstat.c	modified	+5	−5	View file
mm/workingset.c	modified	+89	−46	View file
mm/zsmalloc.c	modified	+1	−1	View file
scripts/tags.sh	modified	+1	−1	View file
tools/accounting/getdelays.c	modified	+7	−1	View file
tools/testing/selftests/vm/.gitignore	modified	+1	−0	View file
tools/testing/selftests/vm/Makefile	modified	+1	−0	View file
tools/testing/selftests/vm/gup_benchmark.c	modified	+35	−7	View file
tools/testing/selftests/vm/map_fixed_noreplace.c	added	+206	−0	View file
tools/testing/selftests/vm/userfaultfd.c	modified	+77	−57	View file
virt/kvm/kvm_main.c	modified	+0	−1	View file

Only the first 600 diff lines are shown. Download the complete patch.

Documentation/accounting/psi.txt

View file

diff --git a/Documentation/accounting/psi.txt b/Documentation/accounting/psi.txt
new file mode 100644
index 0000000..b8ca28b
--- /dev/null
+++ b/Documentation/accounting/psi.txt
@@ -0,0 +1,73 @@
+================================
+PSI - Pressure Stall Information
+================================
+
+:Date: April, 2018
+:Author: Johannes Weiner <[email protected]>
+
+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

View file

diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
index caf3610..8384c68 100644
--- a/Documentation/admin-guide/cgroup-v2.rst
+++ b/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

View file

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 47ca5cd..b90fe3b 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/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

View file

diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index 22b4b00..12a5e6e 100644
--- a/Documentation/filesystems/proc.txt
+++ b/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

View file

diff --git a/Documentation/vm/slub.rst b/Documentation/vm/slub.rst
index 3a775fd..1959288 100644
--- a/Documentation/vm/slub.rst
+++ b/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

View file

diff --git a/Documentation/x86/pat.txt b/Documentation/x86/pat.txt
index 2a4ee63..481d8d8 100644
--- a/Documentation/x86/pat.txt
+++ b/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

View file

diff --git a/arch/alpha/Kconfig b/arch/alpha/Kconfig
index 5b4f883..620b0a7 100644
--- a/arch/alpha/Kconfig
+++ b/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

View file

diff --git a/arch/alpha/kernel/core_irongate.c b/arch/alpha/kernel/core_irongate.c
index aec7572..f709866 100644
--- a/arch/alpha/kernel/core_irongate.c
+++ b/arch/alpha/kernel/core_irongate.c
@@ -21,6 +21,7 @@
 #include <linux/init.h>
 #include <linux/initrd.h>
 #include <linux/bootmem.h>
+#include <linux/memblock.h>
 
 #include <asm/ptrace.h>
 #include <asm/cacheflush.h>
@@ -241,8 +242,7 @@ albacore_init_arch(void)
 				       size / 1024);
 		}
 #endif
-		reserve_bootmem_node(NODE_DATA(0), pci_mem, memtop -
-				pci_mem, BOOTMEM_DEFAULT);
+		memblock_reserve(pci_mem, memtop - pci_mem);
 		printk("irongate_init_arch: temporarily reserving "
 			"region %08lx-%08lx for PCI\n", pci_mem, memtop - 1);
 	}

arch/alpha/kernel/setup.c

View file

diff --git a/arch/alpha/kernel/setup.c b/arch/alpha/kernel/setup.c
index 5576f76..4f0d944 100644
--- a/arch/alpha/kernel/setup.c
+++ b/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 bootmap_size, bootmap_pages, bootmap_start;
-	unsigned long start, end;
+	unsigned long kernel_size;
 	unsigned long i;
 
 	/* Find free clusters, and init and free the bootmem accordingly.  */
@@ -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.  */
-	start_kernel_pfn = PFN_DOWN(KERNEL_START_PHYS);
-	end_kernel_pfn = PFN_UP(virt_to_phys(kernel_end));
-	bootmap_start = -1;
-
- try_again:
-	if (max_low_pfn <= end_kernel_pfn)
-		panic("not enough memory to boot");
-
-	/* We need to know how many physically contiguous pages
-	   we'll need for the bootmap.  */
-	bootmap_pages = bootmem_bootmap_pages(max_low_pfn);
-
-	/* Now find a good region where to allocate the bootmap.  */
-	for_each_mem_cluster(memdesc, cluster, i) {
-		if (cluster->usage & 3)
-			continue;
-
-		start = cluster->start_pfn;
-		end = start + cluster->numpages;
-		if (start >= max_low_pfn)
-			continue;
-		if (end > max_low_pfn)
-			end = max_low_pfn;
-		if (start < start_kernel_pfn) {
-			if (end > end_kernel_pfn
-			    && end - end_kernel_pfn >= bootmap_pages) {
-				bootmap_start = end_kernel_pfn;
-				break;
-			} else if (end > start_kernel_pfn)
-				end = start_kernel_pfn;
-		} else if (start < end_kernel_pfn)
-			start = end_kernel_pfn;
-		if (end - start >= bootmap_pages) {
-			bootmap_start = start;
-			break;
-		}
-	}
-
-	if (bootmap_start == ~0UL) {
-		max_low_pfn >>= 1;
-		goto try_again;
-	}
-
-	/* Allocate the bootmap and mark the whole MM as reserved.  */
-	bootmap_size = init_bootmem(bootmap_start, max_low_pfn);
-
-	/* Mark the free regions.  */
-	for_each_mem_cluster(memdesc, cluster, i) {
-		if (cluster->usage & 3)
-			continue;
-
-		start = cluster->start_pfn;
-		end = cluster->start_pfn + cluster->numpages;
-		if (start >= max_low_pfn)
-			continue;
-		if (end > max_low_pfn)
-			end = max_low_pfn;
-		if (start < start_kernel_pfn) {
-			if (end > end_kernel_pfn) {
-				free_bootmem(PFN_PHYS(start),
-					     (PFN_PHYS(start_kernel_pfn)
-					      - PFN_PHYS(start)));
-				printk("freeing pages %ld:%ld\n",
-				       start, start_kernel_pfn);
-				start = end_kernel_pfn;
-			} else if (end > start_kernel_pfn)
-				end = start_kernel_pfn;
-		} else if (start < end_kernel_pfn)
-			start = end_kernel_pfn;
-		if (start >= end)
-			continue;
-
-		free_bootmem(PFN_PHYS(start), PFN_PHYS(end) - PFN_PHYS(start));
-		printk("freeing pages %ld:%ld\n", start, end);
-	}
-
-	/* Reserve the bootmap memory.  */
-	reserve_bootmem(PFN_PHYS(bootmap_start), bootmap_size,
-			BOOTMEM_DEFAULT);
-	printk("reserving pages %ld:%ld\n", bootmap_start, bootmap_start+PFN_UP(bootmap_size));
+	/* Reserve the kernel memory. */
+	kernel_size = virt_to_phys(kernel_end) - KERNEL_START_PHYS;
+	memblock_reserve(KERNEL_START_PHYS, kernel_size);
 
 #ifdef CONFIG_BLK_DEV_INITRD
 	initrd_start = INITRD_START;
@@ -459,8 +385,8 @@ setup_memory(void *kernel_end)
 				       initrd_end,
 				       phys_to_virt(PFN_PHYS(max_low_pfn)));
 		} else {
-			reserve_bootmem(virt_to_phys((void *)initrd_start),
-					INITRD_SIZE, BOOTMEM_DEFAULT);
+			memblock_reserve(virt_to_phys((void *)initrd_start),
+					INITRD_SIZE);
 		}
 	}
 #endif /* CONFIG_BLK_DEV_INITRD */

arch/alpha/mm/numa.c

View file

diff --git a/arch/alpha/mm/numa.c b/arch/alpha/mm/numa.c
index a9e8647..26cd925 100644
--- a/arch/alpha/mm/numa.c
+++ b/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
-	   we'll need for the bootmap.  */
-	bootmap_pages = bootmem_bootmap_pages(node_max_pfn-node_min_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 >= 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);
+	memblock_add(PFN_PHYS(node_min_pfn),
+		     (node_max_pfn - node_min_pfn) << PAGE_SHIFT);
 
-	/* 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_DATA(nid)->node_start_pfn = node_min_pfn;
+	NODE_DATA(nid)->node_present_pages = node_max_pfn - node_min_pfn;
 
 	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),
-					     virt_to_phys((void *)initrd_start),
-					     INITRD_SIZE, BOOTMEM_DEFAULT);
+			memblock_reserve(virt_to_phys((void *)initrd_start),
+					 INITRD_SIZE);
 		}
 	}
 #endif /* CONFIG_BLK_DEV_INITRD */
@@ -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 = bdata->node_min_pfn;
-		unsigned long end_pfn = bdata->node_low_pfn;
+		unsigned long start_pfn = NODE_DATA(nid)->node_start_pfn;
+		unsigned long end_pfn = start_pfn + NODE_DATA(nid)->node_present_pages;
 
 		if (dma_local_pfn >= end_pfn - start_pfn)
 			zones_size[ZONE_DMA] = end_pfn - start_pfn;

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

View file

diff --git a/arch/arm/include/asm/hugetlb-3level.h b/arch/arm/include/asm/hugetlb-3level.h
index d4014fb..0d9f391 100644
--- a/arch/arm/include/asm/hugetlb-3level.h
+++ b/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).

This diff is incomplete. Download the complete patch.