Merge branch 'akpm' (more incoming from Andrew)

5ce1a70e · Linus Torvalds <[email protected]> · 2013-02-23 17:50:35 -08:00

Merge second patch-bomb from Andrew Morton:

 - A little DM fix

 - the MM queue

* emailed patches from Andrew Morton <[email protected]>: (154 commits)
  ksm: allocate roots when needed
  mm: cleanup "swapcache" in do_swap_page
  mm,ksm: swapoff might need to copy
  mm,ksm: FOLL_MIGRATION do migration_entry_wait
  ksm: shrink 32-bit rmap_item back to 32 bytes
  ksm: treat unstable nid like in stable tree
  ksm: add some comments
  tmpfs: fix mempolicy object leaks
  tmpfs: fix use-after-free of mempolicy object
  mm/fadvise.c: drain all pagevecs if POSIX_FADV_DONTNEED fails to discard all pages
  mm: export mmu notifier invalidates
  mm: accelerate mm_populate() treatment of THP pages
  mm: use long type for page counts in mm_populate() and get_user_pages()
  mm: accurately document nr_free_*_pages functions with code comments
  HWPOISON: change order of error_states[]'s elements
  HWPOISON: fix misjudgement of page_action() for errors on mlocked pages
  memcg: stop warning on memcg_propagate_kmem
  net: change type of virtio_chan->p9_max_pages
  vmscan: change type of vm_total_pages to unsigned long
  fs/nfsd: change type of max_delegations, nfsd_drc_max_mem and nfsd_drc_mem_used
  ...

Commit: 5ce1a70e2f00f0bce0cab57f798ca354b9496169
Parents: 9d3cae26 · ef53d16c

Merge commit. Changes below are compared with the first parent: 9d3cae26.

Changes

113 files changed · +4408 −1632

File	Status	Add	Del	Content
Documentation/ABI/testing/sysfs-kernel-mm-ksm	added	+52	−0	View file
Documentation/kernel-parameters.txt	modified	+36	−0	View file
Documentation/vm/ksm.txt	modified	+15	−0	View file
arch/arm64/mm/mmu.c	modified	+3	−0	View file
arch/ia64/mm/contig.c	modified	+1	−1	View file
arch/ia64/mm/discontig.c	modified	+5	−1	View file
arch/ia64/mm/init.c	modified	+18	−0	View file
arch/powerpc/mm/init_64.c	modified	+5	−0	View file
arch/powerpc/mm/mem.c	modified	+12	−0	View file
arch/s390/mm/init.c	modified	+12	−0	View file
arch/s390/mm/vmem.c	modified	+4	−0	View file
arch/sh/mm/init.c	modified	+17	−0	View file
arch/sparc/mm/init_32.c	modified	+1	−1	View file
arch/sparc/mm/init_64.c	modified	+5	−0	View file
arch/tile/mm/elf.c	modified	+0	−1	View file
arch/tile/mm/init.c	modified	+8	−0	View file
arch/tile/mm/pgtable.c	modified	+1	−1	View file
arch/x86/include/asm/numa.h	modified	+2	−2	View file
arch/x86/include/asm/pgtable_types.h	modified	+1	−0	View file
arch/x86/kernel/acpi/boot.c	modified	+4	−0	View file
arch/x86/kernel/setup.c	modified	+9	−4	View file
arch/x86/mm/init_32.c	modified	+12	−0	View file
arch/x86/mm/init_64.c	modified	+397	−0	View file
arch/x86/mm/numa.c	modified	+9	−8	View file
arch/x86/mm/pageattr.c	modified	+25	−22	View file
arch/x86/mm/srat.c	modified	+122	−3	View file
block/genhd.c	modified	+10	−0	View file
drivers/acpi/acpi_memhotplug.c	modified	+6	−2	View file
drivers/acpi/numa.c	modified	+13	−10	View file
drivers/acpi/processor_driver.c	modified	+2	−0	View file
drivers/base/memory.c	modified	+6	−0	View file
drivers/base/power/runtime.c	modified	+88	−1	View file
drivers/firmware/memmap.c	modified	+183	−13	View file
drivers/md/persistent-data/dm-transaction-manager.c	modified	+7	−7	View file
drivers/staging/zcache/zbud.c	modified	+1	−1	View file
drivers/staging/zsmalloc/zsmalloc-main.c	modified	+1	−1	View file
drivers/usb/core/hub.c	modified	+13	−0	View file
fs/aio.c	modified	+5	−2	View file
fs/buffer.c	modified	+2	−2	View file
fs/nfsd/nfs4state.c	modified	+3	−3	View file
fs/nfsd/nfsd.h	modified	+3	−3	View file
fs/nfsd/nfssvc.c	modified	+3	−3	View file
fs/proc/meminfo.c	modified	+3	−3	View file
include/linux/acpi.h	modified	+8	−0	View file
include/linux/bootmem.h	modified	+1	−0	View file
include/linux/compaction.h	modified	+2	−3	View file
include/linux/firmware-map.h	modified	+6	−0	View file
include/linux/highmem.h	modified	+0	−6	View file
include/linux/huge_mm.h	modified	+1	−1	View file
include/linux/hugetlb.h	modified	+3	−3	View file
include/linux/ksm.h	modified	+4	−14	View file
include/linux/memblock.h	modified	+2	−0	View file
include/linux/memcontrol.h	modified	+0	−7	View file
include/linux/memory_hotplug.h	modified	+12	−8	View file
include/linux/migrate.h	modified	+6	−8	View file
include/linux/mm.h	modified	+99	−79	View file
include/linux/mm_types.h	modified	+5	−4	View file
include/linux/mman.h	modified	+3	−1	View file
include/linux/mmzone.h	modified	+33	−25	View file
include/linux/page-flags-layout.h	added	+88	−0	View file
include/linux/page-isolation.h	modified	+19	−0	View file
include/linux/pm.h	modified	+1	−0	View file
include/linux/pm_runtime.h	modified	+3	−0	View file
include/linux/rmap.h	modified	+1	−1	View file
include/linux/sched.h	modified	+22	−0	View file
include/linux/swap.h	modified	+36	−13	View file
include/linux/vm_event_item.h	modified	+0	−1	View file
include/linux/vmstat.h	modified	+1	−1	View file
ipc/shm.c	modified	+7	−5	View file
kernel/sched/core.c	modified	+19	−9	View file
kernel/sysctl.c	modified	+0	−1	View file
mm/Kconfig	modified	+9	−1	View file
mm/compaction.c	modified	+18	−17	View file
mm/fadvise.c	modified	+16	−2	View file
mm/fremap.c	modified	+27	−24	View file
mm/huge_memory.c	modified	+24	−71	View file
mm/hugetlb.c	modified	+15	−19	View file
mm/internal.h	modified	+2	−2	View file
mm/kmemleak.c	modified	+2	−3	View file
mm/ksm.c	modified	+529	−128	View file
mm/madvise.c	modified	+101	−4	View file
mm/memblock.c	modified	+50	−0	View file
mm/memcontrol.c	modified	+268	−205	View file
mm/memory-failure.c	modified	+124	−78	View file
mm/memory.c	modified	+68	−57	View file
mm/memory_hotplug.c	modified	+494	−59	View file
mm/mempolicy.c	modified	+32	−27	View file
mm/migrate.c	modified	+68	−96	View file
mm/mincore.c	modified	+3	−2	View file
mm/mlock.c	modified	+30	−71	View file
mm/mm_init.c	modified	+19	−12	View file
mm/mmap.c	modified	+49	−34	View file
mm/mmu_notifier.c	modified	+44	−40	View file
mm/mmzone.c	modified	+19	−1	View file
mm/mremap.c	modified	+14	−13	View file
mm/nommu.c	modified	+17	−11	View file
mm/oom_kill.c	modified	+4	−2	View file
mm/page-writeback.c	modified	+3	−0	View file
mm/page_alloc.c	modified	+371	−68	View file
mm/rmap.c	modified	+3	−3	View file
mm/shmem.c	modified	+30	−18	View file
mm/slob.c	modified	+1	−1	View file
mm/slub.c	modified	+1	−1	View file
mm/sparse.c	modified	+8	−4	View file
mm/swap.c	modified	+7	−2	View file
mm/swap_state.c	modified	+40	−18	View file
mm/swapfile.c	modified	+125	−49	View file
mm/util.c	modified	+25	−1	View file
mm/vmalloc.c	modified	+18	−15	View file
mm/vmscan.c	modified	+213	−184	View file
mm/vmstat.c	modified	+4	−3	View file
net/9p/trans_virtio.c	modified	+1	−1	View file
net/core/net-sysfs.c	modified	+5	−0	View file

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

Documentation/ABI/testing/sysfs-kernel-mm-ksm

View file

diff --git a/Documentation/ABI/testing/sysfs-kernel-mm-ksm b/Documentation/ABI/testing/sysfs-kernel-mm-ksm
new file mode 100644
index 0000000..73e653e
--- /dev/null
+++ b/Documentation/ABI/testing/sysfs-kernel-mm-ksm
@@ -0,0 +1,52 @@
+What:		/sys/kernel/mm/ksm
+Date:		September 2009
+KernelVersion:	2.6.32
+Contact:	Linux memory management mailing list <[email protected]>
+Description:	Interface for Kernel Samepage Merging (KSM)
+
+What:		/sys/kernel/mm/ksm/full_scans
+What:		/sys/kernel/mm/ksm/pages_shared
+What:		/sys/kernel/mm/ksm/pages_sharing
+What:		/sys/kernel/mm/ksm/pages_to_scan
+What:		/sys/kernel/mm/ksm/pages_unshared
+What:		/sys/kernel/mm/ksm/pages_volatile
+What:		/sys/kernel/mm/ksm/run
+What:		/sys/kernel/mm/ksm/sleep_millisecs
+Date:		September 2009
+Contact:	Linux memory management mailing list <[email protected]>
+Description:	Kernel Samepage Merging daemon sysfs interface
+
+		full_scans: how many times all mergeable areas have been
+		scanned.
+
+		pages_shared: how many shared pages are being used.
+
+		pages_sharing: how many more sites are sharing them i.e. how
+		much saved.
+
+		pages_to_scan: how many present pages to scan before ksmd goes
+		to sleep.
+
+		pages_unshared: how many pages unique but repeatedly checked
+		for merging.
+
+		pages_volatile: how many pages changing too fast to be placed
+		in a tree.
+
+		run: write 0 to disable ksm, read 0 while ksm is disabled.
+			write 1 to run ksm, read 1 while ksm is running.
+			write 2 to disable ksm and unmerge all its pages.
+
+		sleep_millisecs: how many milliseconds ksm should sleep between
+		scans.
+
+		See Documentation/vm/ksm.txt for more information.
+
+What:		/sys/kernel/mm/ksm/merge_across_nodes
+Date:		January 2013
+KernelVersion:	3.9
+Contact:	Linux memory management mailing list <[email protected]>
+Description:	Control merging pages across different NUMA nodes.
+
+		When it is set to 0 only pages from the same node are merged,
+		otherwise pages from all nodes can be merged together (default).

Documentation/kernel-parameters.txt

View file

diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index 9aa8ff3..7660877 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -1640,6 +1640,42 @@ bytes respectively. Such letter suffixes can also be entirely omitted.
 			that the amount of memory usable for all allocations
 			is not too small.
 
+	movablemem_map=acpi
+			[KNL,X86,IA-64,PPC] This parameter is similar to
+			memmap except it specifies the memory map of
+			ZONE_MOVABLE.
+			This option inform the kernel to use Hot Pluggable bit
+			in flags from SRAT from ACPI BIOS to determine which
+			memory devices could be hotplugged. The corresponding
+			memory ranges will be set as ZONE_MOVABLE.
+			NOTE: Whatever node the kernel resides in will always
+			      be un-hotpluggable.
+
+	movablemem_map=nn[KMG]@ss[KMG]
+			[KNL,X86,IA-64,PPC] This parameter is similar to
+			memmap except it specifies the memory map of
+			ZONE_MOVABLE.
+			If user specifies memory ranges, the info in SRAT will
+			be ingored. And it works like the following:
+			- If more ranges are all within one node, then from
+			  lowest ss to the end of the node will be ZONE_MOVABLE.
+			- If a range is within a node, then from ss to the end
+			  of the node will be ZONE_MOVABLE.
+			- If a range covers two or more nodes, then from ss to
+			  the end of the 1st node will be ZONE_MOVABLE, and all
+			  the rest nodes will only have ZONE_MOVABLE.
+			If memmap is specified at the same time, the
+			movablemem_map will be limited within the memmap
+			areas. If kernelcore or movablecore is also specified,
+			movablemem_map will have higher priority to be
+			satisfied. So the administrator should be careful that
+			the amount of movablemem_map areas are not too large.
+			Otherwise kernel won't have enough memory to start.
+			NOTE: We don't stop users specifying the node the
+			      kernel resides in as hotpluggable so that this
+			      option can be used as a workaround of firmware
+                              bugs.
+
 	MTD_Partition=	[MTD]
 			Format: <name>,<region-number>,<size>,<offset>
 

Documentation/vm/ksm.txt

View file

diff --git a/Documentation/vm/ksm.txt b/Documentation/vm/ksm.txt
index b392e49..f34a8ee 100644
--- a/Documentation/vm/ksm.txt
+++ b/Documentation/vm/ksm.txt
@@ -58,6 +58,21 @@ sleep_millisecs  - how many milliseconds ksmd should sleep before next scan
                    e.g. "echo 20 > /sys/kernel/mm/ksm/sleep_millisecs"
                    Default: 20 (chosen for demonstration purposes)
 
+merge_across_nodes - specifies if pages from different numa nodes can be merged.
+                   When set to 0, ksm merges only pages which physically
+                   reside in the memory area of same NUMA node. That brings
+                   lower latency to access of shared pages. Systems with more
+                   nodes, at significant NUMA distances, are likely to benefit
+                   from the lower latency of setting 0. Smaller systems, which
+                   need to minimize memory usage, are likely to benefit from
+                   the greater sharing of setting 1 (default). You may wish to
+                   compare how your system performs under each setting, before
+                   deciding on which to use. merge_across_nodes setting can be
+                   changed only when there are no ksm shared pages in system:
+                   set run 2 to unmerge pages first, then to 1 after changing
+                   merge_across_nodes, to remerge according to the new setting.
+                   Default: 1 (merging across nodes as in earlier releases)
+
 run              - set 0 to stop ksmd from running but keep merged pages,
                    set 1 to run ksmd e.g. "echo 1 > /sys/kernel/mm/ksm/run",
                    set 2 to stop ksmd and unmerge all pages currently merged,

arch/arm64/mm/mmu.c

View file

diff --git a/arch/arm64/mm/mmu.c b/arch/arm64/mm/mmu.c
index f4dd585..224b44a 100644
--- a/arch/arm64/mm/mmu.c
+++ b/arch/arm64/mm/mmu.c
@@ -434,4 +434,7 @@ int __meminit vmemmap_populate(struct page *start_page,
 	return 0;
 }
 #endif	/* CONFIG_ARM64_64K_PAGES */
+void vmemmap_free(struct page *memmap, unsigned long nr_pages)
+{
+}
 #endif	/* CONFIG_SPARSEMEM_VMEMMAP */

arch/ia64/mm/contig.c

View file

diff --git a/arch/ia64/mm/contig.c b/arch/ia64/mm/contig.c
index 1516d1d..80dab50 100644
--- a/arch/ia64/mm/contig.c
+++ b/arch/ia64/mm/contig.c
@@ -93,7 +93,7 @@ void show_mem(unsigned int filter)
 	printk(KERN_INFO "%d pages swap cached\n", total_cached);
 	printk(KERN_INFO "Total of %ld pages in page table cache\n",
 	       quicklist_total_size());
-	printk(KERN_INFO "%d free buffer pages\n", nr_free_buffer_pages());
+	printk(KERN_INFO "%ld free buffer pages\n", nr_free_buffer_pages());
 }
 
 

arch/ia64/mm/discontig.c

View file

diff --git a/arch/ia64/mm/discontig.c b/arch/ia64/mm/discontig.c
index c641333..c2e955e 100644
--- a/arch/ia64/mm/discontig.c
+++ b/arch/ia64/mm/discontig.c
@@ -666,7 +666,7 @@ void show_mem(unsigned int filter)
 	printk(KERN_INFO "%d pages swap cached\n", total_cached);
 	printk(KERN_INFO "Total of %ld pages in page table cache\n",
 	       quicklist_total_size());
-	printk(KERN_INFO "%d free buffer pages\n", nr_free_buffer_pages());
+	printk(KERN_INFO "%ld free buffer pages\n", nr_free_buffer_pages());
 }
 
 /**
@@ -822,4 +822,8 @@ int __meminit vmemmap_populate(struct page *start_page,
 {
 	return vmemmap_populate_basepages(start_page, size, node);
 }
+
+void vmemmap_free(struct page *memmap, unsigned long nr_pages)
+{
+}
 #endif

arch/ia64/mm/init.c

View file

diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index b755ea9..20bc967 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -688,6 +688,24 @@ int arch_add_memory(int nid, u64 start, u64 size)
 
 	return ret;
 }
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+int arch_remove_memory(u64 start, u64 size)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+	struct zone *zone;
+	int ret;
+
+	zone = page_zone(pfn_to_page(start_pfn));
+	ret = __remove_pages(zone, start_pfn, nr_pages);
+	if (ret)
+		pr_warn("%s: Problem encountered in __remove_pages() as"
+			" ret=%d\n", __func__,  ret);
+
+	return ret;
+}
+#endif
 #endif
 
 /*

arch/powerpc/mm/init_64.c

View file

diff --git a/arch/powerpc/mm/init_64.c b/arch/powerpc/mm/init_64.c
index 95a4529..7e2246f 100644
--- a/arch/powerpc/mm/init_64.c
+++ b/arch/powerpc/mm/init_64.c
@@ -297,5 +297,10 @@ int __meminit vmemmap_populate(struct page *start_page,
 
 	return 0;
 }
+
+void vmemmap_free(struct page *memmap, unsigned long nr_pages)
+{
+}
+
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 

arch/powerpc/mm/mem.c

View file

diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
index 40df7c8..f1f7409 100644
--- a/arch/powerpc/mm/mem.c
+++ b/arch/powerpc/mm/mem.c
@@ -133,6 +133,18 @@ int arch_add_memory(int nid, u64 start, u64 size)
 
 	return __add_pages(nid, zone, start_pfn, nr_pages);
 }
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+int arch_remove_memory(u64 start, u64 size)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+	struct zone *zone;
+
+	zone = page_zone(pfn_to_page(start_pfn));
+	return __remove_pages(zone, start_pfn, nr_pages);
+}
+#endif
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
 /*

arch/s390/mm/init.c

View file

diff --git a/arch/s390/mm/init.c b/arch/s390/mm/init.c
index ae672f4..49ce6bb 100644
--- a/arch/s390/mm/init.c
+++ b/arch/s390/mm/init.c
@@ -228,4 +228,16 @@ int arch_add_memory(int nid, u64 start, u64 size)
 		vmem_remove_mapping(start, size);
 	return rc;
 }
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+int arch_remove_memory(u64 start, u64 size)
+{
+	/*
+	 * There is no hardware or firmware interface which could trigger a
+	 * hot memory remove on s390. So there is nothing that needs to be
+	 * implemented.
+	 */
+	return -EBUSY;
+}
+#endif
 #endif /* CONFIG_MEMORY_HOTPLUG */

arch/s390/mm/vmem.c

View file

diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index 79699f4..e21aaf4 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -268,6 +268,10 @@ out:
 	return ret;
 }
 
+void vmemmap_free(struct page *memmap, unsigned long nr_pages)
+{
+}
+
 /*
  * Add memory segment to the segment list if it doesn't overlap with
  * an already present segment.

arch/sh/mm/init.c

View file

diff --git a/arch/sh/mm/init.c b/arch/sh/mm/init.c
index 82cc576..1057940 100644
--- a/arch/sh/mm/init.c
+++ b/arch/sh/mm/init.c
@@ -558,4 +558,21 @@ int memory_add_physaddr_to_nid(u64 addr)
 EXPORT_SYMBOL_GPL(memory_add_physaddr_to_nid);
 #endif
 
+#ifdef CONFIG_MEMORY_HOTREMOVE
+int arch_remove_memory(u64 start, u64 size)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+	struct zone *zone;
+	int ret;
+
+	zone = page_zone(pfn_to_page(start_pfn));
+	ret = __remove_pages(zone, start_pfn, nr_pages);
+	if (unlikely(ret))
+		pr_warn("%s: Failed, __remove_pages() == %d\n", __func__,
+			ret);
+
+	return ret;
+}
+#endif
 #endif /* CONFIG_MEMORY_HOTPLUG */

arch/sparc/mm/init_32.c

View file

diff --git a/arch/sparc/mm/init_32.c b/arch/sparc/mm/init_32.c
index dde85ef..48e0c03 100644
--- a/arch/sparc/mm/init_32.c
+++ b/arch/sparc/mm/init_32.c
@@ -57,7 +57,7 @@ void show_mem(unsigned int filter)
 	printk("Mem-info:\n");
 	show_free_areas(filter);
 	printk("Free swap:       %6ldkB\n",
-	       nr_swap_pages << (PAGE_SHIFT-10));
+	       get_nr_swap_pages() << (PAGE_SHIFT-10));
 	printk("%ld pages of RAM\n", totalram_pages);
 	printk("%ld free pages\n", nr_free_pages());
 }

arch/sparc/mm/init_64.c

View file

diff --git a/arch/sparc/mm/init_64.c b/arch/sparc/mm/init_64.c
index 5c2c6e6..1588d33 100644
--- a/arch/sparc/mm/init_64.c
+++ b/arch/sparc/mm/init_64.c
@@ -2235,6 +2235,11 @@ void __meminit vmemmap_populate_print_last(void)
 		node_start = 0;
 	}
 }
+
+void vmemmap_free(struct page *memmap, unsigned long nr_pages)
+{
+}
+
 #endif /* CONFIG_SPARSEMEM_VMEMMAP */
 
 static void prot_init_common(unsigned long page_none,

arch/tile/mm/elf.c

View file

diff --git a/arch/tile/mm/elf.c b/arch/tile/mm/elf.c
index 3cfa98b..743c951 100644
--- a/arch/tile/mm/elf.c
+++ b/arch/tile/mm/elf.c
@@ -130,7 +130,6 @@ int arch_setup_additional_pages(struct linux_binprm *bprm,
 	if (!retval) {
 		unsigned long addr = MEM_USER_INTRPT;
 		addr = mmap_region(NULL, addr, INTRPT_SIZE,
-				   MAP_FIXED|MAP_ANONYMOUS|MAP_PRIVATE,
 				   VM_READ|VM_EXEC|
 				   VM_MAYREAD|VM_MAYWRITE|VM_MAYEXEC, 0);
 		if (addr > (unsigned long) -PAGE_SIZE)

arch/tile/mm/init.c

View file

diff --git a/arch/tile/mm/init.c b/arch/tile/mm/init.c
index ef29d6c..2749515 100644
--- a/arch/tile/mm/init.c
+++ b/arch/tile/mm/init.c
@@ -935,6 +935,14 @@ int remove_memory(u64 start, u64 size)
 {
 	return -EINVAL;
 }
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+int arch_remove_memory(u64 start, u64 size)
+{
+	/* TODO */
+	return -EBUSY;
+}
+#endif
 #endif
 
 struct kmem_cache *pgd_cache;

arch/tile/mm/pgtable.c

View file

diff --git a/arch/tile/mm/pgtable.c b/arch/tile/mm/pgtable.c
index de0de0c..b3b4972 100644
--- a/arch/tile/mm/pgtable.c
+++ b/arch/tile/mm/pgtable.c
@@ -61,7 +61,7 @@ void show_mem(unsigned int filter)
 	       global_page_state(NR_PAGETABLE),
 	       global_page_state(NR_BOUNCE),
 	       global_page_state(NR_FILE_PAGES),
-	       nr_swap_pages);
+	       get_nr_swap_pages());
 
 	for_each_zone(zone) {
 		unsigned long flags, order, total = 0, largest_order = -1;

arch/x86/include/asm/numa.h

View file

diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index 52560a2..1b99ee5 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -57,8 +57,8 @@ static inline int numa_cpu_node(int cpu)
 #endif
 
 #ifdef CONFIG_NUMA
-extern void __cpuinit numa_set_node(int cpu, int node);
-extern void __cpuinit numa_clear_node(int cpu);
+extern void numa_set_node(int cpu, int node);
+extern void numa_clear_node(int cpu);
 extern void __init init_cpu_to_node(void);
 extern void __cpuinit numa_add_cpu(int cpu);
 extern void __cpuinit numa_remove_cpu(int cpu);

arch/x86/include/asm/pgtable_types.h

View file

diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h
index e642300..567b5d0 100644
--- a/arch/x86/include/asm/pgtable_types.h
+++ b/arch/x86/include/asm/pgtable_types.h
@@ -351,6 +351,7 @@ static inline void update_page_count(int level, unsigned long pages) { }
  * as a pte too.
  */
 extern pte_t *lookup_address(unsigned long address, unsigned int *level);
+extern int __split_large_page(pte_t *kpte, unsigned long address, pte_t *pbase);
 extern phys_addr_t slow_virt_to_phys(void *__address);
 
 #endif	/* !__ASSEMBLY__ */

arch/x86/kernel/acpi/boot.c

View file

diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
index cfc755d..230c8ea 100644
--- a/arch/x86/kernel/acpi/boot.c
+++ b/arch/x86/kernel/acpi/boot.c
@@ -696,6 +696,10 @@ EXPORT_SYMBOL(acpi_map_lsapic);
 
 int acpi_unmap_lsapic(int cpu)
 {
+#ifdef CONFIG_ACPI_NUMA
+	set_apicid_to_node(per_cpu(x86_cpu_to_apicid, cpu), NUMA_NO_NODE);
+#endif
+
 	per_cpu(x86_cpu_to_apicid, cpu) = -1;
 	set_cpu_present(cpu, false);
 	num_processors--;

arch/x86/kernel/setup.c

View file

diff --git a/arch/x86/kernel/setup.c b/arch/x86/kernel/setup.c
index 915f5ef..9c857f0 100644
--- a/arch/x86/kernel/setup.c
+++ b/arch/x86/kernel/setup.c
@@ -1056,6 +1056,15 @@ void __init setup_arch(char **cmdline_p)
 	setup_bios_corruption_check();
 #endif
 
+	/*
+	 * In the memory hotplug case, the kernel needs info from SRAT to
+	 * determine which memory is hotpluggable before allocating memory
+	 * using memblock.
+	 */
+	acpi_boot_table_init();
+	early_acpi_boot_init();
+	early_parse_srat();
+
 #ifdef CONFIG_X86_32
 	printk(KERN_DEBUG "initial memory mapped: [mem 0x00000000-%#010lx]\n",
 			(max_pfn_mapped<<PAGE_SHIFT) - 1);
@@ -1101,10 +1110,6 @@ void __init setup_arch(char **cmdline_p)
 	/*
 	 * Parse the ACPI tables for possible boot-time SMP configuration.
 	 */
-	acpi_boot_table_init();
-
-	early_acpi_boot_init();
-
 	initmem_init();
 	memblock_find_dma_reserve();
 

arch/x86/mm/init_32.c

View file

diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index b299724..2d19001 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -862,6 +862,18 @@ int arch_add_memory(int nid, u64 start, u64 size)
 
 	return __add_pages(nid, zone, start_pfn, nr_pages);
 }
+
+#ifdef CONFIG_MEMORY_HOTREMOVE
+int arch_remove_memory(u64 start, u64 size)
+{
+	unsigned long start_pfn = start >> PAGE_SHIFT;
+	unsigned long nr_pages = size >> PAGE_SHIFT;
+	struct zone *zone;
+
+	zone = page_zone(pfn_to_page(start_pfn));
+	return __remove_pages(zone, start_pfn, nr_pages);
+}
+#endif
 #endif
 
 /*

arch/x86/mm/init_64.c

View file

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 3eba7f4..474e28f 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -707,6 +707,343 @@ int arch_add_memory(int nid, u64 start, u64 size)
 }
 EXPORT_SYMBOL_GPL(arch_add_memory);
 
+#define PAGE_INUSE 0xFD
+
+static void __meminit free_pagetable(struct page *page, int order)
+{
+	struct zone *zone;
+	bool bootmem = false;
+	unsigned long magic;
+	unsigned int nr_pages = 1 << order;
+
+	/* bootmem page has reserved flag */
+	if (PageReserved(page)) {
+		__ClearPageReserved(page);
+		bootmem = true;
+
+		magic = (unsigned long)page->lru.next;
+		if (magic == SECTION_INFO || magic == MIX_SECTION_INFO) {
+			while (nr_pages--)
+				put_page_bootmem(page++);
+		} else
+			__free_pages_bootmem(page, order);
+	} else
+		free_pages((unsigned long)page_address(page), order);
+
+	/*
+	 * SECTION_INFO pages and MIX_SECTION_INFO pages
+	 * are all allocated by bootmem.
+	 */
+	if (bootmem) {
+		zone = page_zone(page);
+		zone_span_writelock(zone);
+		zone->present_pages += nr_pages;
+		zone_span_writeunlock(zone);
+		totalram_pages += nr_pages;
+	}
+}
+
+static void __meminit free_pte_table(pte_t *pte_start, pmd_t *pmd)
+{
+	pte_t *pte;
+	int i;
+
+	for (i = 0; i < PTRS_PER_PTE; i++) {
+		pte = pte_start + i;
+		if (pte_val(*pte))
+			return;
+	}
+
+	/* free a pte talbe */
+	free_pagetable(pmd_page(*pmd), 0);
+	spin_lock(&init_mm.page_table_lock);
+	pmd_clear(pmd);
+	spin_unlock(&init_mm.page_table_lock);
+}
+
+static void __meminit free_pmd_table(pmd_t *pmd_start, pud_t *pud)
+{
+	pmd_t *pmd;
+	int i;
+
+	for (i = 0; i < PTRS_PER_PMD; i++) {
+		pmd = pmd_start + i;
+		if (pmd_val(*pmd))
+			return;
+	}
+
+	/* free a pmd talbe */
+	free_pagetable(pud_page(*pud), 0);
+	spin_lock(&init_mm.page_table_lock);
+	pud_clear(pud);
+	spin_unlock(&init_mm.page_table_lock);
+}
+
+/* Return true if pgd is changed, otherwise return false. */
+static bool __meminit free_pud_table(pud_t *pud_start, pgd_t *pgd)
+{
+	pud_t *pud;
+	int i;
+
+	for (i = 0; i < PTRS_PER_PUD; i++) {
+		pud = pud_start + i;
+		if (pud_val(*pud))
+			return false;
+	}
+
+	/* free a pud table */
+	free_pagetable(pgd_page(*pgd), 0);
+	spin_lock(&init_mm.page_table_lock);
+	pgd_clear(pgd);
+	spin_unlock(&init_mm.page_table_lock);
+
+	return true;
+}
+
+static void __meminit
+remove_pte_table(pte_t *pte_start, unsigned long addr, unsigned long end,
+		 bool direct)
+{
+	unsigned long next, pages = 0;
+	pte_t *pte;
+	void *page_addr;
+	phys_addr_t phys_addr;
+
+	pte = pte_start + pte_index(addr);
+	for (; addr < end; addr = next, pte++) {
+		next = (addr + PAGE_SIZE) & PAGE_MASK;
+		if (next > end)
+			next = end;
+
+		if (!pte_present(*pte))
+			continue;
+
+		/*
+		 * We mapped [0,1G) memory as identity mapping when
+		 * initializing, in arch/x86/kernel/head_64.S. These
+		 * pagetables cannot be removed.
+		 */