[PATCH v6 00/16] Free some vmemmap pages of hugetlb page

[PATCH v6 00/16] Free some vmemmap pages of hugetlb page

[Muchun Song]

Hi all,

This patch series will free some vmemmap pages(struct page structures)
associated with each hugetlbpage when preallocated to save memory.

In order to reduce the difficulty of the first version of code review.
From this version, we disable PMD/huge page mapping of vmemmap if this
feature was enabled. This accutualy eliminate a bunch of the complex code
doing page table manipulation. When this patch series is solid, we cam add
the code of vmemmap page table manipulation in the future.

The struct page structures (page structs) are used to describe a physical
page frame. By default, there is a one-to-one mapping from a page frame to
it's corresponding page struct.

The HugeTLB pages consist of multiple base page size pages and is supported
by many architectures. See hugetlbpage.rst in the Documentation directory
for more details. On the x86 architecture, HugeTLB pages of size 2MB and 1GB
are currently supported. Since the base page size on x86 is 4KB, a 2MB
HugeTLB page consists of 512 base pages and a 1GB HugeTLB page consists of
4096 base pages. For each base page, there is a corresponding page struct.

Within the HugeTLB subsystem, only the first 4 page structs are used to
contain unique information about a HugeTLB page. HUGETLB_CGROUP_MIN_ORDER
provides this upper limit. The only 'useful' information in the remaining
page structs is the compound_head field, and this field is the same for all
tail pages.

By removing redundant page structs for HugeTLB pages, memory can returned to
the buddy allocator for other uses.

When the system boot up, every 2M HugeTLB has 512 struct page structs which
size is 8 pages(sizeof(struct page) * 512 / PAGE_SIZE).

    HugeTLB                  struct pages(8 pages)         page frame(8 pages)
 +-----------+ ---virt_to_page---> +-----------+   mapping to   +-----------+
 |           |                     |     0     | -------------> |     0     |
 |           |                     +-----------+                +-----------+
 |           |                     |     1     | -------------> |     1     |
 |           |                     +-----------+                +-----------+
 |           |                     |     2     | -------------> |     2     |
 |           |                     +-----------+                +-----------+
 |           |                     |     3     | -------------> |     3     |
 |           |                     +-----------+                +-----------+
 |           |                     |     4     | -------------> |     4     |
 |    2MB    |                     +-----------+                +-----------+
 |           |                     |     5     | -------------> |     5     |
 |           |                     +-----------+                +-----------+
 |           |                     |     6     | -------------> |     6     |
 |           |                     +-----------+                +-----------+
 |           |                     |     7     | -------------> |     7     |
 |           |                     +-----------+                +-----------+
 |           |
 |           |
 |           |
 +-----------+

The value of page->compound_head is the same for all tail pages. The first
page of page structs (page 0) associated with the HugeTLB page contains the 4
page structs necessary to describe the HugeTLB. The only use of the remaining
pages of page structs (page 1 to page 7) is to point to page->compound_head.
Therefore, we can remap pages 2 to 7 to page 1. Only 2 pages of page structs
will be used for each HugeTLB page. This will allow us to free the remaining
6 pages to the buddy allocator.

Here is how things look after remapping.

    HugeTLB                  struct pages(8 pages)         page frame(8 pages)
 +-----------+ ---virt_to_page---> +-----------+   mapping to   +-----------+
 |           |                     |     0     | -------------> |     0     |
 |           |                     +-----------+                +-----------+
 |           |                     |     1     | -------------> |     1     |
 |           |                     +-----------+                +-----------+
 |           |                     |     2     | ----------------^ ^ ^ ^ ^ ^
 |           |                     +-----------+                   | | | | |
 |           |                     |     3     | ------------------+ | | | |
 |           |                     +-----------+                     | | | |
 |           |                     |     4     | --------------------+ | | |
 |    2MB    |                     +-----------+                       | | |
 |           |                     |     5     | ----------------------+ | |
 |           |                     +-----------+                         | |
 |           |                     |     6     | ------------------------+ |
 |           |                     +-----------+                           |
 |           |                     |     7     | --------------------------+
 |           |                     +-----------+
 |           |
 |           |
 |           |
 +-----------+

When a HugeTLB is freed to the buddy system, we should allocate 6 pages for
vmemmap pages and restore the previous mapping relationship.

Apart from 2MB HugeTLB page, we also have 1GB HugeTLB page. It is similar
to the 2MB HugeTLB page. We also can use this approach to free the vmemmap
pages.

In this case, for the 1GB HugeTLB page, we can save 4088 pages(There are
4096 pages for struct page structs, we reserve 2 pages for vmemmap and 8
pages for page tables. So we can save 4088 pages). This is a very substantial
gain. On our server, run some SPDK/QEMU applications which will use 1024GB
hugetlbpage. With this feature enabled, we can save ~16GB(1G hugepage)/~11GB
(2MB hugepage, the worst case is 10GB while the best is 12GB) memory.

Because there are vmemmap page tables reconstruction on the freeing/allocating
path, it increases some overhead. Here are some overhead analysis.

1) Allocating 10240 2MB hugetlb pages.

   a) With this patch series applied:
   # time echo 10240 > /proc/sys/vm/nr_hugepages

   real     0m0.166s
   user     0m0.000s
   sys      0m0.166s

   # bpftrace -e 'kprobe:alloc_fresh_huge_page { @start[tid] = nsecs; } kretprobe:alloc_fresh_huge_page /@start[tid]/ { @latency = hist(nsecs - @start[tid]); delete(@start[tid]); }'
   Attaching 2 probes...

   @latency:
   [8K, 16K)           8360 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
   [16K, 32K)          1868 |@@@@@@@@@@@                                         |
   [32K, 64K)            10 |                                                    |
   [64K, 128K)            2 |                                                    |

   b) Without this patch series:
   # time echo 10240 > /proc/sys/vm/nr_hugepages

   real     0m0.066s
   user     0m0.000s
   sys      0m0.066s

   # bpftrace -e 'kprobe:alloc_fresh_huge_page { @start[tid] = nsecs; } kretprobe:alloc_fresh_huge_page /@start[tid]/ { @latency = hist(nsecs - @start[tid]); delete(@start[tid]); }'
   Attaching 2 probes...

   @latency:
   [4K, 8K)           10176 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
   [8K, 16K)             62 |                                                    |
   [16K, 32K)             2 |                                                    |

   Summarize: this feature is about ~2x slower than before.

2) Freeing 10240 2MB hugetlb pages.

   a) With this patch series applied:
   # time echo 0 > /proc/sys/vm/nr_hugepages

   real     0m0.004s
   user     0m0.000s
   sys      0m0.002s

   # bpftrace -e 'kprobe:__free_hugepage { @start[tid] = nsecs; } kretprobe:__free_hugepage /@start[tid]/ { @latency = hist(nsecs - @start[tid]); delete(@start[tid]); }'
   Attaching 2 probes...

   @latency:
   [16K, 32K)         10240 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|

   b) Without this patch series:
   # time echo 0 > /proc/sys/vm/nr_hugepages

   real     0m0.077s
   user     0m0.001s
   sys      0m0.075s

   # bpftrace -e 'kprobe:__free_hugepage { @start[tid] = nsecs; } kretprobe:__free_hugepage /@start[tid]/ { @latency = hist(nsecs - @start[tid]); delete(@start[tid]); }'
   Attaching 2 probes...

   @latency:
   [4K, 8K)            9950 |@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@|
   [8K, 16K)            287 |@                                                   |
   [16K, 32K)             3 |                                                    |

   Summarize: The overhead of __free_hugepage is about ~2-4x slower than before.
              But according to the allocation test above, I think that here is
	      also ~2x slower than before.

              But why the 'real' time of patched is smaller than before? Because
	      In this patch series, the freeing hugetlb is asynchronous(through
	      kwoker).

Although the overhead has increased, the overhead is not significant. Like Mike
said, "However, remember that the majority of use cases create hugetlb pages at
or shortly after boot time and add them to the pool. So, additional overhead is
at pool creation time. There is no change to 'normal run time' operations of
getting a page from or returning a page to the pool (think page fault/unmap)".

Todo:
  1. Free all of the tail vmemmap pages
     Now for the 2MB HugrTLB page, we only free 6 vmemmap pages. we really can
     free 7 vmemmap pages. In this case, we can see 8 of the 512 struct page
     structures has beed set PG_head flag. If we can adjust compound_head()
     slightly and make compound_head() return the real head struct page when
     the parameter is the tail struct page but with PG_head flag set.

     In order to make the code evolution route clearer. This feature can can be
     a separate patch after this patchset is solid.
  2. Support for other architectures (e.g. aarch64).
  3. Enable PMD/huge page mapping of vmemmap even if this feature was enabled.

  Changelog in v6:
  1. Disable PMD/huge page mapping of vmemmap if this feature was enabled.
  2. Simplify the first version code.

  Changelog in v5:
  1. Rework somme comments and code in the [PATCH v4 04/21] and [PATCH v4 05/21].
     Thanks to Mike and Oscar's suggestions.

  Changelog in v4:
  1. Move all the vmemmap functions to hugetlb_vmemmap.c.
  2. Make the CONFIG_HUGETLB_PAGE_FREE_VMEMMAP default to y, if we want to
     disable this feature, we should disable it by a boot/kernel command line.
  3. Remove vmemmap_pgtable_{init, deposit, withdraw}() helper functions.
  4. Initialize page table lock for vmemmap through core_initcall mechanism.

  Thanks for Mike and Oscar's suggestions.

  Changelog in v3:
  1. Rename some helps function name. Thanks Mike.
  2. Rework some code. Thanks Mike and Oscar.
  3. Remap the tail vmemmap page with PAGE_KERNEL_RO instead of
     PAGE_KERNEL. Thanks Matthew.
  4. Add some overhead analysis in the cover letter.
  5. Use vmemap pmd table lock instead of a hugetlb specific global lock.

  Changelog in v2:
  1. Fix do not call dissolve_compound_page in alloc_huge_page_vmemmap().
  2. Fix some typo and code style problems.
  3. Remove unused handle_vmemmap_fault().
  4. Merge some commits to one commit suggested by Mike.

Muchun Song (16):
  mm/memory_hotplug: Move bootmem info registration API to
    bootmem_info.c
  mm/memory_hotplug: Move {get,put}_page_bootmem() to bootmem_info.c
  mm/hugetlb: Introduce a new config HUGETLB_PAGE_FREE_VMEMMAP
  mm/hugetlb: Introduce nr_free_vmemmap_pages in the struct hstate
  mm/bootmem_info: Introduce {free,prepare}_vmemmap_page()
  mm/hugetlb: Disable freeing vmemmap if struct page size is not power
    of two
  x86/mm/64: Disable PMD page mapping of vmemmap
  mm/hugetlb: Free the vmemmap pages associated with each hugetlb page
  mm/hugetlb: Defer freeing of HugeTLB pages
  mm/hugetlb: Allocate the vmemmap pages associated with each hugetlb
    page
  mm/hugetlb: Introduce remap_huge_page_pmd_vmemmap helper
  mm/hugetlb: Set the PageHWPoison to the raw error page
  mm/hugetlb: Flush work when dissolving hugetlb page
  mm/hugetlb: Add a kernel parameter hugetlb_free_vmemmap
  mm/hugetlb: Gather discrete indexes of tail page
  mm/hugetlb: Add BUILD_BUG_ON to catch invalid usage of tail struct
    page

 Documentation/admin-guide/kernel-parameters.txt |   9 +
 Documentation/admin-guide/mm/hugetlbpage.rst    |   3 +
 arch/x86/include/asm/pgtable_64_types.h         |   8 +
 arch/x86/mm/init_64.c                           |  12 +-
 fs/Kconfig                                      |  14 +
 include/linux/bootmem_info.h                    |  64 +++++
 include/linux/hugetlb.h                         |  16 ++
 include/linux/hugetlb_cgroup.h                  |  15 +-
 include/linux/memory_hotplug.h                  |  27 --
 mm/Makefile                                     |   2 +
 mm/bootmem_info.c                               | 124 ++++++++
 mm/hugetlb.c                                    | 144 ++++++++--
 mm/hugetlb_vmemmap.c                            | 365 ++++++++++++++++++++++++
 mm/hugetlb_vmemmap.h                            |  79 +++++
 mm/memory_hotplug.c                             | 116 --------
 mm/sparse.c                                     |   1 +
 16 files changed, 820 insertions(+), 179 deletions(-)
 create mode 100644 include/linux/bootmem_info.h
 create mode 100644 mm/bootmem_info.c
 create mode 100644 mm/hugetlb_vmemmap.c
 create mode 100644 mm/hugetlb_vmemmap.h

-- 
2.11.0

[PATCH v6 01/16] mm/memory_hotplug: Move bootmem info registration API to bootmem_info.c

[Muchun Song]

Move bootmem info registration common API to individual bootmem_info.c
for later patch use. This is just code movement without any functional
change.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
---
 arch/x86/mm/init_64.c          |  1 +
 include/linux/bootmem_info.h   | 27 ++++++++++++
 include/linux/memory_hotplug.h | 23 ----------
 mm/Makefile                    |  1 +
 mm/bootmem_info.c              | 99 ++++++++++++++++++++++++++++++++++++++++++
 mm/memory_hotplug.c            | 91 +-------------------------------------
 6 files changed, 129 insertions(+), 113 deletions(-)
 create mode 100644 include/linux/bootmem_info.h
 create mode 100644 mm/bootmem_info.c

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index b5a3fa4033d3..c7f7ad55b625 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -33,6 +33,7 @@
 #include <linux/nmi.h>
 #include <linux/gfp.h>
 #include <linux/kcore.h>
+#include <linux/bootmem_info.h>
 
 #include <asm/processor.h>
 #include <asm/bios_ebda.h>
diff --git a/include/linux/bootmem_info.h b/include/linux/bootmem_info.h
new file mode 100644
index 000000000000..65bb9b23140f
--- /dev/null
+++ b/include/linux/bootmem_info.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_BOOTMEM_INFO_H
+#define __LINUX_BOOTMEM_INFO_H
+
+#include <linux/mmzone.h>
+
+/*
+ * Types for free bootmem stored in page->lru.next. These have to be in
+ * some random range in unsigned long space for debugging purposes.
+ */
+enum {
+	MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12,
+	SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE,
+	MIX_SECTION_INFO,
+	NODE_INFO,
+	MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO,
+};
+
+#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
+void __init register_page_bootmem_info_node(struct pglist_data *pgdat);
+#else
+static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
+{
+}
+#endif
+
+#endif /* __LINUX_BOOTMEM_INFO_H */
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 51a877fec8da..19e5d067294c 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -33,18 +33,6 @@ struct vmem_altmap;
 	___page;						   \
 })
 
-/*
- * Types for free bootmem stored in page->lru.next. These have to be in
- * some random range in unsigned long space for debugging purposes.
- */
-enum {
-	MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12,
-	SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE,
-	MIX_SECTION_INFO,
-	NODE_INFO,
-	MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO,
-};
-
 /* Types for control the zone type of onlined and offlined memory */
 enum {
 	/* Offline the memory. */
@@ -209,13 +197,6 @@ static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
 #endif /* CONFIG_NUMA */
 #endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
 
-#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
-extern void __init register_page_bootmem_info_node(struct pglist_data *pgdat);
-#else
-static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
-{
-}
-#endif
 extern void put_page_bootmem(struct page *page);
 extern void get_page_bootmem(unsigned long ingo, struct page *page,
 			     unsigned long type);
@@ -254,10 +235,6 @@ static inline int mhp_notimplemented(const char *func)
 	return -ENOSYS;
 }
 
-static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
-{
-}
-
 static inline int try_online_node(int nid)
 {
 	return 0;
diff --git a/mm/Makefile b/mm/Makefile
index d5649f1c12c0..752111587c99 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -82,6 +82,7 @@ obj-$(CONFIG_SLAB) += slab.o
 obj-$(CONFIG_SLUB) += slub.o
 obj-$(CONFIG_KASAN)	+= kasan/
 obj-$(CONFIG_FAILSLAB) += failslab.o
+obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o
 obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_MEMTEST)		+= memtest.o
 obj-$(CONFIG_MIGRATION) += migrate.o
diff --git a/mm/bootmem_info.c b/mm/bootmem_info.c
new file mode 100644
index 000000000000..39fa8fc120bc
--- /dev/null
+++ b/mm/bootmem_info.c
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/mm/bootmem_info.c
+ *
+ *  Copyright (C)
+ */
+#include <linux/mm.h>
+#include <linux/compiler.h>
+#include <linux/memblock.h>
+#include <linux/bootmem_info.h>
+#include <linux/memory_hotplug.h>
+
+#ifndef CONFIG_SPARSEMEM_VMEMMAP
+static void register_page_bootmem_info_section(unsigned long start_pfn)
+{
+	unsigned long mapsize, section_nr, i;
+	struct mem_section *ms;
+	struct page *page, *memmap;
+	struct mem_section_usage *usage;
+
+	section_nr = pfn_to_section_nr(start_pfn);
+	ms = __nr_to_section(section_nr);
+
+	/* Get section's memmap address */
+	memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
+
+	/*
+	 * Get page for the memmap's phys address
+	 * XXX: need more consideration for sparse_vmemmap...
+	 */
+	page = virt_to_page(memmap);
+	mapsize = sizeof(struct page) * PAGES_PER_SECTION;
+	mapsize = PAGE_ALIGN(mapsize) >> PAGE_SHIFT;
+
+	/* remember memmap's page */
+	for (i = 0; i < mapsize; i++, page++)
+		get_page_bootmem(section_nr, page, SECTION_INFO);
+
+	usage = ms->usage;
+	page = virt_to_page(usage);
+
+	mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT;
+
+	for (i = 0; i < mapsize; i++, page++)
+		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
+
+}
+#else /* CONFIG_SPARSEMEM_VMEMMAP */
+static void register_page_bootmem_info_section(unsigned long start_pfn)
+{
+	unsigned long mapsize, section_nr, i;
+	struct mem_section *ms;
+	struct page *page, *memmap;
+	struct mem_section_usage *usage;
+
+	section_nr = pfn_to_section_nr(start_pfn);
+	ms = __nr_to_section(section_nr);
+
+	memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
+
+	register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION);
+
+	usage = ms->usage;
+	page = virt_to_page(usage);
+
+	mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT;
+
+	for (i = 0; i < mapsize; i++, page++)
+		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
+}
+#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
+
+void __init register_page_bootmem_info_node(struct pglist_data *pgdat)
+{
+	unsigned long i, pfn, end_pfn, nr_pages;
+	int node = pgdat->node_id;
+	struct page *page;
+
+	nr_pages = PAGE_ALIGN(sizeof(struct pglist_data)) >> PAGE_SHIFT;
+	page = virt_to_page(pgdat);
+
+	for (i = 0; i < nr_pages; i++, page++)
+		get_page_bootmem(node, page, NODE_INFO);
+
+	pfn = pgdat->node_start_pfn;
+	end_pfn = pgdat_end_pfn(pgdat);
+
+	/* register section info */
+	for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+		/*
+		 * Some platforms can assign the same pfn to multiple nodes - on
+		 * node0 as well as nodeN.  To avoid registering a pfn against
+		 * multiple nodes we check that this pfn does not already
+		 * reside in some other nodes.
+		 */
+		if (pfn_valid(pfn) && (early_pfn_to_nid(pfn) == node))
+			register_page_bootmem_info_section(pfn);
+	}
+}
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index baded53b9ff9..2da4ad071456 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -21,6 +21,7 @@
 #include <linux/memory.h>
 #include <linux/memremap.h>
 #include <linux/memory_hotplug.h>
+#include <linux/bootmem_info.h>
 #include <linux/highmem.h>
 #include <linux/vmalloc.h>
 #include <linux/ioport.h>
@@ -167,96 +168,6 @@ void put_page_bootmem(struct page *page)
 	}
 }
 
-#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
-#ifndef CONFIG_SPARSEMEM_VMEMMAP
-static void register_page_bootmem_info_section(unsigned long start_pfn)
-{
-	unsigned long mapsize, section_nr, i;
-	struct mem_section *ms;
-	struct page *page, *memmap;
-	struct mem_section_usage *usage;
-
-	section_nr = pfn_to_section_nr(start_pfn);
-	ms = __nr_to_section(section_nr);
-
-	/* Get section's memmap address */
-	memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
-
-	/*
-	 * Get page for the memmap's phys address
-	 * XXX: need more consideration for sparse_vmemmap...
-	 */
-	page = virt_to_page(memmap);
-	mapsize = sizeof(struct page) * PAGES_PER_SECTION;
-	mapsize = PAGE_ALIGN(mapsize) >> PAGE_SHIFT;
-
-	/* remember memmap's page */
-	for (i = 0; i < mapsize; i++, page++)
-		get_page_bootmem(section_nr, page, SECTION_INFO);
-
-	usage = ms->usage;
-	page = virt_to_page(usage);
-
-	mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT;
-
-	for (i = 0; i < mapsize; i++, page++)
-		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
-
-}
-#else /* CONFIG_SPARSEMEM_VMEMMAP */
-static void register_page_bootmem_info_section(unsigned long start_pfn)
-{
-	unsigned long mapsize, section_nr, i;
-	struct mem_section *ms;
-	struct page *page, *memmap;
-	struct mem_section_usage *usage;
-
-	section_nr = pfn_to_section_nr(start_pfn);
-	ms = __nr_to_section(section_nr);
-
-	memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
-
-	register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION);
-
-	usage = ms->usage;
-	page = virt_to_page(usage);
-
-	mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT;
-
-	for (i = 0; i < mapsize; i++, page++)
-		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
-}
-#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
-
-void __init register_page_bootmem_info_node(struct pglist_data *pgdat)
-{
-	unsigned long i, pfn, end_pfn, nr_pages;
-	int node = pgdat->node_id;
-	struct page *page;
-
-	nr_pages = PAGE_ALIGN(sizeof(struct pglist_data)) >> PAGE_SHIFT;
-	page = virt_to_page(pgdat);
-
-	for (i = 0; i < nr_pages; i++, page++)
-		get_page_bootmem(node, page, NODE_INFO);
-
-	pfn = pgdat->node_start_pfn;
-	end_pfn = pgdat_end_pfn(pgdat);
-
-	/* register section info */
-	for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
-		/*
-		 * Some platforms can assign the same pfn to multiple nodes - on
-		 * node0 as well as nodeN.  To avoid registering a pfn against
-		 * multiple nodes we check that this pfn does not already
-		 * reside in some other nodes.
-		 */
-		if (pfn_valid(pfn) && (early_pfn_to_nid(pfn) == node))
-			register_page_bootmem_info_section(pfn);
-	}
-}
-#endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */
-
 static int check_pfn_span(unsigned long pfn, unsigned long nr_pages,
 		const char *reason)
 {
-- 
2.11.0

[PATCH v6 02/16] mm/memory_hotplug: Move {get,put}_page_bootmem() to bootmem_info.c

[Muchun Song]

In the later patch, we will use {get,put}_page_bootmem() to initialize
the page for vmemmap or free vmemmap page to buddy. So move them out of
CONFIG_MEMORY_HOTPLUG_SPARSE. This is just code movement without any
functional change.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
---
 arch/x86/mm/init_64.c          |  2 +-
 include/linux/bootmem_info.h   | 13 +++++++++++++
 include/linux/memory_hotplug.h |  4 ----
 mm/bootmem_info.c              | 25 +++++++++++++++++++++++++
 mm/memory_hotplug.c            | 27 ---------------------------
 mm/sparse.c                    |  1 +
 6 files changed, 40 insertions(+), 32 deletions(-)

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index c7f7ad55b625..0a45f062826e 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1572,7 +1572,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 	return err;
 }
 
-#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HAVE_BOOTMEM_INFO_NODE)
+#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
 void register_page_bootmem_memmap(unsigned long section_nr,
 				  struct page *start_page, unsigned long nr_pages)
 {
diff --git a/include/linux/bootmem_info.h b/include/linux/bootmem_info.h
index 65bb9b23140f..4ed6dee1adc9 100644
--- a/include/linux/bootmem_info.h
+++ b/include/linux/bootmem_info.h
@@ -18,10 +18,23 @@ enum {
 
 #ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
 void __init register_page_bootmem_info_node(struct pglist_data *pgdat);
+
+void get_page_bootmem(unsigned long info, struct page *page,
+		      unsigned long type);
+void put_page_bootmem(struct page *page);
 #else
 static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
 {
 }
+
+static inline void put_page_bootmem(struct page *page)
+{
+}
+
+static inline void get_page_bootmem(unsigned long info, struct page *page,
+				    unsigned long type)
+{
+}
 #endif
 
 #endif /* __LINUX_BOOTMEM_INFO_H */
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 19e5d067294c..c9f3361fe84b 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -197,10 +197,6 @@ static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
 #endif /* CONFIG_NUMA */
 #endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
 
-extern void put_page_bootmem(struct page *page);
-extern void get_page_bootmem(unsigned long ingo, struct page *page,
-			     unsigned long type);
-
 void get_online_mems(void);
 void put_online_mems(void);
 
diff --git a/mm/bootmem_info.c b/mm/bootmem_info.c
index 39fa8fc120bc..fcab5a3f8cc0 100644
--- a/mm/bootmem_info.c
+++ b/mm/bootmem_info.c
@@ -10,6 +10,31 @@
 #include <linux/bootmem_info.h>
 #include <linux/memory_hotplug.h>
 
+void get_page_bootmem(unsigned long info, struct page *page, unsigned long type)
+{
+	page->freelist = (void *)type;
+	SetPagePrivate(page);
+	set_page_private(page, info);
+	page_ref_inc(page);
+}
+
+void put_page_bootmem(struct page *page)
+{
+	unsigned long type;
+
+	type = (unsigned long) page->freelist;
+	BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
+	       type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE);
+
+	if (page_ref_dec_return(page) == 1) {
+		page->freelist = NULL;
+		ClearPagePrivate(page);
+		set_page_private(page, 0);
+		INIT_LIST_HEAD(&page->lru);
+		free_reserved_page(page);
+	}
+}
+
 #ifndef CONFIG_SPARSEMEM_VMEMMAP
 static void register_page_bootmem_info_section(unsigned long start_pfn)
 {
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 2da4ad071456..ae57eedc341f 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -21,7 +21,6 @@
 #include <linux/memory.h>
 #include <linux/memremap.h>
 #include <linux/memory_hotplug.h>
-#include <linux/bootmem_info.h>
 #include <linux/highmem.h>
 #include <linux/vmalloc.h>
 #include <linux/ioport.h>
@@ -142,32 +141,6 @@ static void release_memory_resource(struct resource *res)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
-void get_page_bootmem(unsigned long info,  struct page *page,
-		      unsigned long type)
-{
-	page->freelist = (void *)type;
-	SetPagePrivate(page);
-	set_page_private(page, info);
-	page_ref_inc(page);
-}
-
-void put_page_bootmem(struct page *page)
-{
-	unsigned long type;
-
-	type = (unsigned long) page->freelist;
-	BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
-	       type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE);
-
-	if (page_ref_dec_return(page) == 1) {
-		page->freelist = NULL;
-		ClearPagePrivate(page);
-		set_page_private(page, 0);
-		INIT_LIST_HEAD(&page->lru);
-		free_reserved_page(page);
-	}
-}
-
 static int check_pfn_span(unsigned long pfn, unsigned long nr_pages,
 		const char *reason)
 {
diff --git a/mm/sparse.c b/mm/sparse.c
index b25ad8e64839..a4138410d890 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -13,6 +13,7 @@
 #include <linux/vmalloc.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/bootmem_info.h>
 
 #include "internal.h"
 #include <asm/dma.h>
-- 
2.11.0

[PATCH v6 03/16] mm/hugetlb: Introduce a new config HUGETLB_PAGE_FREE_VMEMMAP

[Muchun Song]

The purpose of introducing HUGETLB_PAGE_FREE_VMEMMAP is to configure
whether to enable the feature of freeing unused vmemmap associated
with HugeTLB pages. And this is just for dependency check. Now only
support x86.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 arch/x86/mm/init_64.c |  2 +-
 fs/Kconfig            | 14 ++++++++++++++
 2 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 0a45f062826e..0435bee2e172 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1225,7 +1225,7 @@ static struct kcore_list kcore_vsyscall;
 
 static void __init register_page_bootmem_info(void)
 {
-#ifdef CONFIG_NUMA
+#if defined(CONFIG_NUMA) || defined(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP)
 	int i;
 
 	for_each_online_node(i)
diff --git a/fs/Kconfig b/fs/Kconfig
index 976e8b9033c4..4961dd488444 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -245,6 +245,20 @@ config HUGETLBFS
 config HUGETLB_PAGE
 	def_bool HUGETLBFS
 
+config HUGETLB_PAGE_FREE_VMEMMAP
+	def_bool HUGETLB_PAGE
+	depends on X86
+	depends on SPARSEMEM_VMEMMAP
+	depends on HAVE_BOOTMEM_INFO_NODE
+	help
+	  When using HUGETLB_PAGE_FREE_VMEMMAP, the system can save up some
+	  memory from pre-allocated HugeTLB pages when they are not used.
+	  6 pages per 2MB HugeTLB page and 4094 per 1GB HugeTLB page.
+
+	  When the pages are going to be used or freed up, the vmemmap array
+	  representing that range needs to be remapped again and the pages
+	  we discarded earlier need to be rellocated again.
+
 config MEMFD_CREATE
 	def_bool TMPFS || HUGETLBFS
 
-- 
2.11.0

[PATCH v6 04/16] mm/hugetlb: Introduce nr_free_vmemmap_pages in the struct hstate

[Muchun Song]

Every HugeTLB has more than one struct page structure. The 2M HugeTLB
has 512 struct page structure and 1G HugeTLB has 4096 struct page
structures. We __know__ that we only use the first 4(HUGETLB_CGROUP_MIN_ORDER)
struct page structures to store metadata associated with each HugeTLB.

There are a lot of struct page structures(8 page frames for 2MB HugeTLB
page and 4096 page frames for 1GB HugeTLB page) associated with each
HugeTLB page. For tail pages, the value of compound_head is the same.
So we can reuse first page of tail page structures. We map the virtual
addresses of the remaining pages of tail page structures to the first
tail page struct, and then free these page frames. Therefore, we need
to reserve two pages as vmemmap areas.

So we introduce a new nr_free_vmemmap_pages field in the hstate to
indicate how many vmemmap pages associated with a HugeTLB page that we
can free to buddy system.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
---
 include/linux/hugetlb.h |   3 ++
 mm/Makefile             |   1 +
 mm/hugetlb.c            |   3 ++
 mm/hugetlb_vmemmap.c    | 129 ++++++++++++++++++++++++++++++++++++++++++++++++
 mm/hugetlb_vmemmap.h    |  20 ++++++++
 5 files changed, 156 insertions(+)
 create mode 100644 mm/hugetlb_vmemmap.c
 create mode 100644 mm/hugetlb_vmemmap.h

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d5cc5f802dd4..eed3dd3bd626 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -492,6 +492,9 @@ struct hstate {
 	unsigned int nr_huge_pages_node[MAX_NUMNODES];
 	unsigned int free_huge_pages_node[MAX_NUMNODES];
 	unsigned int surplus_huge_pages_node[MAX_NUMNODES];
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+	unsigned int nr_free_vmemmap_pages;
+#endif
 #ifdef CONFIG_CGROUP_HUGETLB
 	/* cgroup control files */
 	struct cftype cgroup_files_dfl[7];
diff --git a/mm/Makefile b/mm/Makefile
index 752111587c99..2a734576bbc0 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -71,6 +71,7 @@ obj-$(CONFIG_FRONTSWAP)	+= frontswap.o
 obj-$(CONFIG_ZSWAP)	+= zswap.o
 obj-$(CONFIG_HAS_DMA)	+= dmapool.o
 obj-$(CONFIG_HUGETLBFS)	+= hugetlb.o
+obj-$(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP)	+= hugetlb_vmemmap.o
 obj-$(CONFIG_NUMA) 	+= mempolicy.o
 obj-$(CONFIG_SPARSEMEM)	+= sparse.o
 obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 81a41aa080a5..f88032c24667 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -42,6 +42,7 @@
 #include <linux/userfaultfd_k.h>
 #include <linux/page_owner.h>
 #include "internal.h"
+#include "hugetlb_vmemmap.h"
 
 int hugetlb_max_hstate __read_mostly;
 unsigned int default_hstate_idx;
@@ -3285,6 +3286,8 @@ void __init hugetlb_add_hstate(unsigned int order)
 	snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB",
 					huge_page_size(h)/1024);
 
+	hugetlb_vmemmap_init(h);
+
 	parsed_hstate = h;
 }
 
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
new file mode 100644
index 000000000000..fad760483e01
--- /dev/null
+++ b/mm/hugetlb_vmemmap.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Free some vmemmap pages of HugeTLB
+ *
+ * Copyright (c) 2020, Bytedance. All rights reserved.
+ *
+ *     Author: Muchun Song <songmuchun@bytedance.com>
+ *
+ * The struct page structures (page structs) are used to describe a physical
+ * page frame. By default, there is a one-to-one mapping from a page frame to
+ * it's corresponding page struct.
+ *
+ * The HugeTLB pages consist of multiple base page size pages and is supported
+ * by many architectures. See hugetlbpage.rst in the Documentation directory
+ * for more details. On the x86 architecture, HugeTLB pages of size 2MB and 1GB
+ * are currently supported. Since the base page size on x86 is 4KB, a 2MB
+ * HugeTLB page consists of 512 base pages and a 1GB HugeTLB page consists of
+ * 4096 base pages. For each base page, there is a corresponding page struct.
+ *
+ * Within the HugeTLB subsystem, only the first 4 page structs are used to
+ * contain unique information about a HugeTLB page. HUGETLB_CGROUP_MIN_ORDER
+ * provides this upper limit. The only 'useful' information in the remaining
+ * page structs is the compound_head field, and this field is the same for all
+ * tail pages.
+ *
+ * By removing redundant page structs for HugeTLB pages, memory can returned to
+ * the buddy allocator for other uses.
+ *
+ * When the system boot up, every 2M HugeTLB has 512 struct page structs which
+ * size is 8 pages(sizeof(struct page) * 512 / PAGE_SIZE).
+ *
+ *    HugeTLB                  struct pages(8 pages)         page frame(8 pages)
+ * +-----------+ ---virt_to_page---> +-----------+   mapping to   +-----------+
+ * |           |                     |     0     | -------------> |     0     |
+ * |           |                     +-----------+                +-----------+
+ * |           |                     |     1     | -------------> |     1     |
+ * |           |                     +-----------+                +-----------+
+ * |           |                     |     2     | -------------> |     2     |
+ * |           |                     +-----------+                +-----------+
+ * |           |                     |     3     | -------------> |     3     |
+ * |           |                     +-----------+                +-----------+
+ * |           |                     |     4     | -------------> |     4     |
+ * |    2MB    |                     +-----------+                +-----------+
+ * |           |                     |     5     | -------------> |     5     |
+ * |           |                     +-----------+                +-----------+
+ * |           |                     |     6     | -------------> |     6     |
+ * |           |                     +-----------+                +-----------+
+ * |           |                     |     7     | -------------> |     7     |
+ * |           |                     +-----------+                +-----------+
+ * |           |
+ * |           |
+ * |           |
+ * +-----------+
+ *
+ * The value of page->compound_head is the same for all tail pages. The first
+ * page of page structs (page 0) associated with the HugeTLB page contains the 4
+ * page structs necessary to describe the HugeTLB. The only use of the remaining
+ * pages of page structs (page 1 to page 7) is to point to page->compound_head.
+ * Therefore, we can remap pages 2 to 7 to page 1. Only 2 pages of page structs
+ * will be used for each HugeTLB page. This will allow us to free the remaining
+ * 6 pages to the buddy allocator.
+ *
+ * Here is how things look after remapping.
+ *
+ *    HugeTLB                  struct pages(8 pages)         page frame(8 pages)
+ * +-----------+ ---virt_to_page---> +-----------+   mapping to   +-----------+
+ * |           |                     |     0     | -------------> |     0     |
+ * |           |                     +-----------+                +-----------+
+ * |           |                     |     1     | -------------> |     1     |
+ * |           |                     +-----------+                +-----------+
+ * |           |                     |     2     | ----------------^ ^ ^ ^ ^ ^
+ * |           |                     +-----------+                   | | | | |
+ * |           |                     |     3     | ------------------+ | | | |
+ * |           |                     +-----------+                     | | | |
+ * |           |                     |     4     | --------------------+ | | |
+ * |    2MB    |                     +-----------+                       | | |
+ * |           |                     |     5     | ----------------------+ | |
+ * |           |                     +-----------+                         | |
+ * |           |                     |     6     | ------------------------+ |
+ * |           |                     +-----------+                           |
+ * |           |                     |     7     | --------------------------+
+ * |           |                     +-----------+
+ * |           |
+ * |           |
+ * |           |
+ * +-----------+
+ *
+ * When a HugeTLB is freed to the buddy system, we should allocate 6 pages for
+ * vmemmap pages and restore the previous mapping relationship.
+ *
+ * Apart from 2MB HugeTLB page, we also have 1GB HugeTLB page. It is similar
+ * to the 2MB HugeTLB page. We also can use this approach to free the vmemmap
+ * pages.
+ */
+#define pr_fmt(fmt)	"HugeTLB Vmemmap: " fmt
+
+#include "hugetlb_vmemmap.h"
+
+/*
+ * There are a lot of struct page structures(8 page frames for 2MB HugeTLB page
+ * and 4096 page frames for 1GB HugeTLB page) associated with each HugeTLB page.
+ * For tail pages, the value of compound_head is the same. So we can reuse first
+ * page of tail page structures. We map the virtual addresses of the remaining
+ * pages of tail page structures to the first tail page struct, and then free
+ * these page frames. Therefore, we need to reserve two pages as vmemmap areas.
+ */
+#define RESERVE_VMEMMAP_NR		2U
+
+void __init hugetlb_vmemmap_init(struct hstate *h)
+{
+	unsigned int order = huge_page_order(h);
+	unsigned int vmemmap_pages;
+
+	vmemmap_pages = ((1 << order) * sizeof(struct page)) >> PAGE_SHIFT;
+	/*
+	 * The head page and the first tail page are not to be freed to buddy
+	 * system, the others page will map to the first tail page. So there
+	 * are the remaining pages that can be freed.
+	 *
+	 * Could RESERVE_VMEMMAP_NR be greater than @vmemmap_pages? This is
+	 * not expected to happen unless the system is corrupted. So on the
+	 * safe side, it is only a safety net.
+	 */
+	if (likely(vmemmap_pages > RESERVE_VMEMMAP_NR))
+		h->nr_free_vmemmap_pages = vmemmap_pages - RESERVE_VMEMMAP_NR;
+
+	pr_debug("can free %d vmemmap pages for %s\n", h->nr_free_vmemmap_pages,
+		 h->name);
+}
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
new file mode 100644
index 000000000000..40c0c7dfb60d
--- /dev/null
+++ b/mm/hugetlb_vmemmap.h
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Free some vmemmap pages of HugeTLB
+ *
+ * Copyright (c) 2020, Bytedance. All rights reserved.
+ *
+ *     Author: Muchun Song <songmuchun@bytedance.com>
+ */
+#ifndef _LINUX_HUGETLB_VMEMMAP_H
+#define _LINUX_HUGETLB_VMEMMAP_H
+#include <linux/hugetlb.h>
+
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+void __init hugetlb_vmemmap_init(struct hstate *h);
+#else
+static inline void hugetlb_vmemmap_init(struct hstate *h)
+{
+}
+#endif /* CONFIG_HUGETLB_PAGE_FREE_VMEMMAP */
+#endif /* _LINUX_HUGETLB_VMEMMAP_H */
-- 
2.11.0

[PATCH v6 05/16] mm/bootmem_info: Introduce {free,prepare}_vmemmap_page()

[Muchun Song]

In the later patch, we can use the free_vmemmap_page() to free the
unused vmemmap pages and initialize a page for vmemmap page using
via prepare_vmemmap_page().

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 include/linux/bootmem_info.h | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/include/linux/bootmem_info.h b/include/linux/bootmem_info.h
index 4ed6dee1adc9..239e3cc8f86c 100644
--- a/include/linux/bootmem_info.h
+++ b/include/linux/bootmem_info.h
@@ -3,6 +3,7 @@
 #define __LINUX_BOOTMEM_INFO_H
 
 #include <linux/mmzone.h>
+#include <linux/mm.h>
 
 /*
  * Types for free bootmem stored in page->lru.next. These have to be in
@@ -22,6 +23,29 @@ void __init register_page_bootmem_info_node(struct pglist_data *pgdat);
 void get_page_bootmem(unsigned long info, struct page *page,
 		      unsigned long type);
 void put_page_bootmem(struct page *page);
+
+static inline void free_vmemmap_page(struct page *page)
+{
+	VM_WARN_ON(!PageReserved(page) || page_ref_count(page) != 2);
+
+	/* bootmem page has reserved flag in the reserve_bootmem_region */
+	if (PageReserved(page)) {
+		unsigned long magic = (unsigned long)page->freelist;
+
+		if (magic == SECTION_INFO || magic == MIX_SECTION_INFO)
+			put_page_bootmem(page);
+		else
+			WARN_ON(1);
+	}
+}
+
+static inline void prepare_vmemmap_page(struct page *page)
+{
+	unsigned long section_nr = pfn_to_section_nr(page_to_pfn(page));
+
+	get_page_bootmem(section_nr, page, SECTION_INFO);
+	mark_page_reserved(page);
+}
 #else
 static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
 {
-- 
2.11.0

[PATCH v6 06/16] mm/hugetlb: Disable freeing vmemmap if struct page size is not power of two

[Muchun Song]

We only can free the tail vmemmap pages of HugeTLB to the buddy allocator
when the size of struct page is a power of two.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 mm/hugetlb_vmemmap.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index fad760483e01..fd60cfdf3d40 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -111,6 +111,11 @@ void __init hugetlb_vmemmap_init(struct hstate *h)
 	unsigned int order = huge_page_order(h);
 	unsigned int vmemmap_pages;
 
+	if (!is_power_of_2(sizeof(struct page))) {
+		pr_info("disable freeing vmemmap pages for %s\n", h->name);
+		return;
+	}
+
 	vmemmap_pages = ((1 << order) * sizeof(struct page)) >> PAGE_SHIFT;
 	/*
 	 * The head page and the first tail page are not to be freed to buddy
-- 
2.11.0

[PATCH v6 07/16] x86/mm/64: Disable PMD page mapping of vmemmap

[Muchun Song]

If we enable the CONFIG_HUGETLB_PAGE_FREE_VMEMMAP, we can just
disbale PMD page mapping of vmemmap to simplify the code. In this
case, we do not need complex code doing vmemmap page table
manipulation. This is a way to simply the first version of this
patch series. In the future, we can add some code doing page table
manipulation.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 arch/x86/mm/init_64.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 0435bee2e172..155cb06a6961 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1557,7 +1557,9 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 {
 	int err;
 
-	if (end - start < PAGES_PER_SECTION * sizeof(struct page))
+	if (IS_ENABLED(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP))
+		err = vmemmap_populate_basepages(start, end, node, NULL);
+	else if (end - start < PAGES_PER_SECTION * sizeof(struct page))
 		err = vmemmap_populate_basepages(start, end, node, NULL);
 	else if (boot_cpu_has(X86_FEATURE_PSE))
 		err = vmemmap_populate_hugepages(start, end, node, altmap);
@@ -1610,7 +1612,8 @@ void register_page_bootmem_memmap(unsigned long section_nr,
 		}
 		get_page_bootmem(section_nr, pud_page(*pud), MIX_SECTION_INFO);
 
-		if (!boot_cpu_has(X86_FEATURE_PSE)) {
+		if (!boot_cpu_has(X86_FEATURE_PSE) ||
+		    IS_ENABLED(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP)) {
 			next = (addr + PAGE_SIZE) & PAGE_MASK;
 			pmd = pmd_offset(pud, addr);
 			if (pmd_none(*pmd))
-- 
2.11.0

[PATCH v6 08/16] mm/hugetlb: Free the vmemmap pages associated with each hugetlb page

[Muchun Song]

When we allocate a hugetlb page from the buddy, we should free the
unused vmemmap pages associated with it. We can do that in the
prep_new_huge_page().

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 arch/x86/include/asm/pgtable_64_types.h |   8 ++
 mm/hugetlb.c                            |   2 +
 mm/hugetlb_vmemmap.c                    | 133 +++++++++++++++++++++++++++++++-
 mm/hugetlb_vmemmap.h                    |   5 ++
 4 files changed, 147 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 52e5f5f2240d..bedbd2e7d06c 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -139,6 +139,14 @@ extern unsigned int ptrs_per_p4d;
 # define VMEMMAP_START		__VMEMMAP_BASE_L4
 #endif /* CONFIG_DYNAMIC_MEMORY_LAYOUT */
 
+/*
+ * VMEMMAP_SIZE - allows the whole linear region to be covered by
+ *                a struct page array.
+ */
+#define VMEMMAP_SIZE		(1UL << (__VIRTUAL_MASK_SHIFT - PAGE_SHIFT - \
+					 1 + ilog2(sizeof(struct page))))
+#define VMEMMAP_END		(VMEMMAP_START + VMEMMAP_SIZE)
+
 #define VMALLOC_END		(VMALLOC_START + (VMALLOC_SIZE_TB << 40) - 1)
 
 #define MODULES_VADDR		(__START_KERNEL_map + KERNEL_IMAGE_SIZE)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index f88032c24667..9662b5535f3a 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1499,6 +1499,8 @@ void free_huge_page(struct page *page)
 
 static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 {
+	free_huge_page_vmemmap(h, page);
+
 	INIT_LIST_HEAD(&page->lru);
 	set_compound_page_dtor(page, HUGETLB_PAGE_DTOR);
 	set_hugetlb_cgroup(page, NULL);
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index fd60cfdf3d40..1576f69bd1d3 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -92,8 +92,9 @@
  * to the 2MB HugeTLB page. We also can use this approach to free the vmemmap
  * pages.
  */
-#define pr_fmt(fmt)	"HugeTLB Vmemmap: " fmt
+#define pr_fmt(fmt)	"HugeTLB vmemmap: " fmt
 
+#include <linux/bootmem_info.h>
 #include "hugetlb_vmemmap.h"
 
 /*
@@ -105,6 +106,136 @@
  * these page frames. Therefore, we need to reserve two pages as vmemmap areas.
  */
 #define RESERVE_VMEMMAP_NR		2U
+#define RESERVE_VMEMMAP_SIZE		(RESERVE_VMEMMAP_NR << PAGE_SHIFT)
+#define TAIL_PAGE_REUSE			-1
+
+#ifndef VMEMMAP_HPAGE_SHIFT
+#define VMEMMAP_HPAGE_SHIFT		HPAGE_SHIFT
+#endif
+#define VMEMMAP_HPAGE_ORDER		(VMEMMAP_HPAGE_SHIFT - PAGE_SHIFT)
+#define VMEMMAP_HPAGE_NR		(1 << VMEMMAP_HPAGE_ORDER)
+#define VMEMMAP_HPAGE_SIZE		((1UL) << VMEMMAP_HPAGE_SHIFT)
+#define VMEMMAP_HPAGE_MASK		(~(VMEMMAP_HPAGE_SIZE - 1))
+
+#define vmemmap_hpage_addr_end(addr, end)				 \
+({									 \
+	unsigned long __boundary;					 \
+	__boundary = ((addr) + VMEMMAP_HPAGE_SIZE) & VMEMMAP_HPAGE_MASK; \
+	(__boundary - 1 < (end) - 1) ? __boundary : (end);		 \
+})
+
+static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
+{
+	return h->nr_free_vmemmap_pages;
+}
+
+static inline unsigned int vmemmap_pages_per_hpage(struct hstate *h)
+{
+	return free_vmemmap_pages_per_hpage(h) + RESERVE_VMEMMAP_NR;
+}
+
+static inline unsigned long vmemmap_pages_size_per_hpage(struct hstate *h)
+{
+	return (unsigned long)vmemmap_pages_per_hpage(h) << PAGE_SHIFT;
+}
+
+/*
+ * Walk a vmemmap address to the pmd it maps.
+ */
+static pmd_t *vmemmap_to_pmd(unsigned long page)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+
+	if (page < VMEMMAP_START || page >= VMEMMAP_END)
+		return NULL;
+
+	pgd = pgd_offset_k(page);
+	if (pgd_none(*pgd))
+		return NULL;
+	p4d = p4d_offset(pgd, page);
+	if (p4d_none(*p4d))
+		return NULL;
+	pud = pud_offset(p4d, page);
+	if (pud_none(*pud) || pud_bad(*pud))
+		return NULL;
+
+	return pmd_offset(pud, page);
+}
+
+static inline void free_vmemmap_page_list(struct list_head *list)
+{
+	struct page *page, *next;
+
+	list_for_each_entry_safe(page, next, list, lru) {
+		list_del(&page->lru);
+		free_vmemmap_page(page);
+	}
+}
+
+static void __free_huge_page_pte_vmemmap(struct page *reuse, pte_t *ptep,
+					 unsigned long start,
+					 unsigned long end,
+					 struct list_head *free_pages)
+{
+	/* Make the tail pages are mapped read-only. */
+	pgprot_t pgprot = PAGE_KERNEL_RO;
+	pte_t entry = mk_pte(reuse, pgprot);
+	unsigned long addr;
+
+	for (addr = start; addr < end; addr += PAGE_SIZE, ptep++) {
+		struct page *page;
+		pte_t old = *ptep;
+
+		VM_WARN_ON(!pte_present(old));
+		page = pte_page(old);
+		list_add(&page->lru, free_pages);
+
+		set_pte_at(&init_mm, addr, ptep, entry);
+	}
+}
+
+static void __free_huge_page_pmd_vmemmap(pmd_t *pmd, unsigned long start,
+					 unsigned long end,
+					 struct list_head *vmemmap_pages)
+{
+	unsigned long next, addr = start;
+	struct page *reuse = NULL;
+
+	do {
+		pte_t *ptep;
+
+		ptep = pte_offset_kernel(pmd, addr);
+		if (!reuse)
+			reuse = pte_page(ptep[TAIL_PAGE_REUSE]);
+
+		next = vmemmap_hpage_addr_end(addr, end);
+		__free_huge_page_pte_vmemmap(reuse, ptep, addr, next,
+					     vmemmap_pages);
+	} while (pmd++, addr = next, addr != end);
+
+	flush_tlb_kernel_range(start, end);
+}
+
+void free_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+	pmd_t *pmd;
+	unsigned long start, end;
+	unsigned long vmemmap_addr = (unsigned long)head;
+	LIST_HEAD(free_pages);
+
+	if (!free_vmemmap_pages_per_hpage(h))
+		return;
+
+	pmd = vmemmap_to_pmd(vmemmap_addr);
+	BUG_ON(!pmd);
+
+	start = vmemmap_addr + RESERVE_VMEMMAP_SIZE;
+	end = vmemmap_addr + vmemmap_pages_size_per_hpage(h);
+	__free_huge_page_pmd_vmemmap(pmd, start, end, &free_pages);
+	free_vmemmap_page_list(&free_pages);
+}
 
 void __init hugetlb_vmemmap_init(struct hstate *h)
 {
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index 40c0c7dfb60d..67113b67495f 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -12,9 +12,14 @@
 
 #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
 void __init hugetlb_vmemmap_init(struct hstate *h);
+void free_huge_page_vmemmap(struct hstate *h, struct page *head);
 #else
 static inline void hugetlb_vmemmap_init(struct hstate *h)
 {
 }
+
+static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+}
 #endif /* CONFIG_HUGETLB_PAGE_FREE_VMEMMAP */
 #endif /* _LINUX_HUGETLB_VMEMMAP_H */
-- 
2.11.0

[PATCH v6 09/16] mm/hugetlb: Defer freeing of HugeTLB pages

[Muchun Song]

In the subsequent patch, we will allocate the vmemmap pages when free
HugeTLB pages. But update_and_free_page() is called from a non-task
context(and hold hugetlb_lock), so we can defer the actual freeing in
a workqueue to prevent use GFP_ATOMIC to allocate the vmemmap pages.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 mm/hugetlb.c         | 96 ++++++++++++++++++++++++++++++++++++++++++++++------
 mm/hugetlb_vmemmap.c |  5 ---
 mm/hugetlb_vmemmap.h | 10 ++++++
 3 files changed, 95 insertions(+), 16 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 9662b5535f3a..41056b4230f1 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1221,7 +1221,7 @@ static void destroy_compound_gigantic_page(struct page *page,
 	__ClearPageHead(page);
 }
 
-static void free_gigantic_page(struct page *page, unsigned int order)
+static void __free_gigantic_page(struct page *page, unsigned int order)
 {
 	/*
 	 * If the page isn't allocated using the cma allocator,
@@ -1288,20 +1288,100 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
 {
 	return NULL;
 }
-static inline void free_gigantic_page(struct page *page, unsigned int order) { }
+static inline void __free_gigantic_page(struct page *page,
+					unsigned int order) { }
 static inline void destroy_compound_gigantic_page(struct page *page,
 						unsigned int order) { }
 #endif
 
-static void update_and_free_page(struct hstate *h, struct page *page)
+static void __free_hugepage(struct hstate *h, struct page *page);
+
+/*
+ * As update_and_free_page() is be called from a non-task context(and hold
+ * hugetlb_lock), we can defer the actual freeing in a workqueue to prevent
+ * use GFP_ATOMIC to allocate a lot of vmemmap pages.
+ *
+ * update_hpage_vmemmap_workfn() locklessly retrieves the linked list of
+ * pages to be freed and frees them one-by-one. As the page->mapping pointer
+ * is going to be cleared in update_hpage_vmemmap_workfn() anyway, it is
+ * reused as the llist_node structure of a lockless linked list of huge
+ * pages to be freed.
+ */
+static LLIST_HEAD(hpage_update_freelist);
+
+static void update_hpage_vmemmap_workfn(struct work_struct *work)
 {
-	int i;
+	struct llist_node *node;
+	struct page *page;
+
+	node = llist_del_all(&hpage_update_freelist);
+
+	while (node) {
+		page = container_of((struct address_space **)node,
+				     struct page, mapping);
+		node = node->next;
+		page->mapping = NULL;
+		__free_hugepage(page_hstate(page), page);
 
+		cond_resched();
+	}
+}
+static DECLARE_WORK(hpage_update_work, update_hpage_vmemmap_workfn);
+
+static inline void __update_and_free_page(struct hstate *h, struct page *page)
+{
+	/* No need to allocate vmemmap pages */
+	if (!free_vmemmap_pages_per_hpage(h)) {
+		__free_hugepage(h, page);
+		return;
+	}
+
+	/*
+	 * Defer freeing to avoid using GFP_ATOMIC to allocate vmemmap
+	 * pages.
+	 *
+	 * Only call schedule_work() if hpage_update_freelist is previously
+	 * empty. Otherwise, schedule_work() had been called but the workfn
+	 * hasn't retrieved the list yet.
+	 */
+	if (llist_add((struct llist_node *)&page->mapping,
+		      &hpage_update_freelist))
+		schedule_work(&hpage_update_work);
+}
+
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+static inline void free_gigantic_page(struct hstate *h, struct page *page)
+{
+	__free_gigantic_page(page, huge_page_order(h));
+}
+#else
+static inline void free_gigantic_page(struct hstate *h, struct page *page)
+{
+	/*
+	 * Temporarily drop the hugetlb_lock, because
+	 * we might block in __free_gigantic_page().
+	 */
+	spin_unlock(&hugetlb_lock);
+	__free_gigantic_page(page, huge_page_order(h));
+	spin_lock(&hugetlb_lock);
+}
+#endif
+
+static void update_and_free_page(struct hstate *h, struct page *page)
+{
 	if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
 		return;
 
 	h->nr_huge_pages--;
 	h->nr_huge_pages_node[page_to_nid(page)]--;
+
+	__update_and_free_page(h, page);
+}
+
+static void __free_hugepage(struct hstate *h, struct page *page)
+{
+	int i;
+
 	for (i = 0; i < pages_per_huge_page(h); i++) {
 		page[i].flags &= ~(1 << PG_locked | 1 << PG_error |
 				1 << PG_referenced | 1 << PG_dirty |
@@ -1313,14 +1393,8 @@ static void update_and_free_page(struct hstate *h, struct page *page)
 	set_compound_page_dtor(page, NULL_COMPOUND_DTOR);
 	set_page_refcounted(page);
 	if (hstate_is_gigantic(h)) {
-		/*
-		 * Temporarily drop the hugetlb_lock, because
-		 * we might block in free_gigantic_page().
-		 */
-		spin_unlock(&hugetlb_lock);
 		destroy_compound_gigantic_page(page, huge_page_order(h));
-		free_gigantic_page(page, huge_page_order(h));
-		spin_lock(&hugetlb_lock);
+		free_gigantic_page(h, page);
 	} else {
 		__free_pages(page, huge_page_order(h));
 	}
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 1576f69bd1d3..f6ba288966d4 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -124,11 +124,6 @@
 	(__boundary - 1 < (end) - 1) ? __boundary : (end);		 \
 })
 
-static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
-{
-	return h->nr_free_vmemmap_pages;
-}
-
 static inline unsigned int vmemmap_pages_per_hpage(struct hstate *h)
 {
 	return free_vmemmap_pages_per_hpage(h) + RESERVE_VMEMMAP_NR;
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index 67113b67495f..293897b9f1d8 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -13,6 +13,11 @@
 #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
 void __init hugetlb_vmemmap_init(struct hstate *h);
 void free_huge_page_vmemmap(struct hstate *h, struct page *head);
+
+static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
+{
+	return h->nr_free_vmemmap_pages;
+}
 #else
 static inline void hugetlb_vmemmap_init(struct hstate *h)
 {
@@ -21,5 +26,10 @@ static inline void hugetlb_vmemmap_init(struct hstate *h)
 static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 {
 }
+
+static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
+{
+	return 0;
+}
 #endif /* CONFIG_HUGETLB_PAGE_FREE_VMEMMAP */
 #endif /* _LINUX_HUGETLB_VMEMMAP_H */
-- 
2.11.0

[PATCH v6 10/16] mm/hugetlb: Allocate the vmemmap pages associated with each hugetlb page

[Muchun Song]

When we free a hugetlb page to the buddy, we should allocate the vmemmap
pages associated with it. We can do that in the __free_hugepage().

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 mm/hugetlb.c         |   2 +
 mm/hugetlb_vmemmap.c | 102 +++++++++++++++++++++++++++++++++++++++++++++++++++
 mm/hugetlb_vmemmap.h |   5 +++
 3 files changed, 109 insertions(+)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 41056b4230f1..3fafa39fcac6 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1382,6 +1382,8 @@ static void __free_hugepage(struct hstate *h, struct page *page)
 {
 	int i;
 
+	alloc_huge_page_vmemmap(h, page);
+
 	for (i = 0; i < pages_per_huge_page(h); i++) {
 		page[i].flags &= ~(1 << PG_locked | 1 << PG_error |
 				1 << PG_referenced | 1 << PG_dirty |
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index f6ba288966d4..d6a1b06c1322 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -95,6 +95,7 @@
 #define pr_fmt(fmt)	"HugeTLB vmemmap: " fmt
 
 #include <linux/bootmem_info.h>
+#include <linux/delay.h>
 #include "hugetlb_vmemmap.h"
 
 /*
@@ -108,6 +109,8 @@
 #define RESERVE_VMEMMAP_NR		2U
 #define RESERVE_VMEMMAP_SIZE		(RESERVE_VMEMMAP_NR << PAGE_SHIFT)
 #define TAIL_PAGE_REUSE			-1
+#define GFP_VMEMMAP_PAGE		\
+	(GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_HIGH)
 
 #ifndef VMEMMAP_HPAGE_SHIFT
 #define VMEMMAP_HPAGE_SHIFT		HPAGE_SHIFT
@@ -159,6 +162,105 @@ static pmd_t *vmemmap_to_pmd(unsigned long page)
 	return pmd_offset(pud, page);
 }
 
+static void __remap_huge_page_pte_vmemmap(struct page *reuse, pte_t *ptep,
+					  unsigned long start,
+					  unsigned long end,
+					  struct list_head *remap_pages)
+{
+	pgprot_t pgprot = PAGE_KERNEL;
+	void *from = page_to_virt(reuse);
+	unsigned long addr;
+
+	for (addr = start; addr < end; addr += PAGE_SIZE) {
+		void *to;
+		struct page *page;
+		pte_t entry, old = *ptep;
+
+		page = list_first_entry(remap_pages, struct page, lru);
+		list_del(&page->lru);
+		to = page_to_virt(page);
+		copy_page(to, from);
+
+		/*
+		 * Make sure that any data that writes to the @to is made
+		 * visible to the physical page.
+		 */
+		flush_kernel_vmap_range(to, PAGE_SIZE);
+
+		prepare_vmemmap_page(page);
+
+		entry = mk_pte(page, pgprot);
+		set_pte_at(&init_mm, addr, ptep++, entry);
+
+		VM_BUG_ON(!pte_present(old) || pte_page(old) != reuse);
+	}
+}
+
+static void __remap_huge_page_pmd_vmemmap(pmd_t *pmd, unsigned long start,
+					  unsigned long end,
+					  struct list_head *vmemmap_pages)
+{
+	unsigned long next, addr = start;
+	struct page *reuse = NULL;
+
+	do {
+		pte_t *ptep;
+
+		ptep = pte_offset_kernel(pmd, addr);
+		if (!reuse)
+			reuse = pte_page(ptep[TAIL_PAGE_REUSE]);
+
+		next = vmemmap_hpage_addr_end(addr, end);
+		__remap_huge_page_pte_vmemmap(reuse, ptep, addr, next,
+					      vmemmap_pages);
+	} while (pmd++, addr = next, addr != end);
+
+	flush_tlb_kernel_range(start, end);
+}
+
+static inline void alloc_vmemmap_pages(struct hstate *h, struct list_head *list)
+{
+	unsigned int nr = free_vmemmap_pages_per_hpage(h);
+
+	while (nr--) {
+		struct page *page;
+
+retry:
+		page = alloc_page(GFP_VMEMMAP_PAGE);
+		if (unlikely(!page)) {
+			msleep(100);
+			/*
+			 * We should retry infinitely, because we cannot
+			 * handle allocation failures. Once we allocate
+			 * vmemmap pages successfully, then we can free
+			 * a HugeTLB page.
+			 */
+			goto retry;
+		}
+		list_add_tail(&page->lru, list);
+	}
+}
+
+void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+	pmd_t *pmd;
+	unsigned long start, end;
+	unsigned long vmemmap_addr = (unsigned long)head;
+	LIST_HEAD(map_pages);
+
+	if (!free_vmemmap_pages_per_hpage(h))
+		return;
+
+	alloc_vmemmap_pages(h, &map_pages);
+
+	pmd = vmemmap_to_pmd(vmemmap_addr);
+	BUG_ON(!pmd);
+
+	start = vmemmap_addr + RESERVE_VMEMMAP_SIZE;
+	end = vmemmap_addr + vmemmap_pages_size_per_hpage(h);
+	__remap_huge_page_pmd_vmemmap(pmd, start, end, &map_pages);
+}
+
 static inline void free_vmemmap_page_list(struct list_head *list)
 {
 	struct page *page, *next;
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index 293897b9f1d8..7887095488f4 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -12,6 +12,7 @@
 
 #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
 void __init hugetlb_vmemmap_init(struct hstate *h);
+void alloc_huge_page_vmemmap(struct hstate *h, struct page *head);
 void free_huge_page_vmemmap(struct hstate *h, struct page *head);
 
 static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
@@ -23,6 +24,10 @@ static inline void hugetlb_vmemmap_init(struct hstate *h)
 {
 }
 
+static inline void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+}
+
 static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 {
 }
-- 
2.11.0

[PATCH v6 11/16] mm/hugetlb: Introduce remap_huge_page_pmd_vmemmap helper

[Muchun Song]

The __free_huge_page_pmd_vmemmap and __remap_huge_page_pmd_vmemmap are
almost the same code. So introduce remap_free_huge_page_pmd_vmemmap
helper to simplify the code.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 mm/hugetlb_vmemmap.c | 87 +++++++++++++++++++++-------------------------------
 1 file changed, 35 insertions(+), 52 deletions(-)

diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index d6a1b06c1322..509ca451e232 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -127,6 +127,10 @@
 	(__boundary - 1 < (end) - 1) ? __boundary : (end);		 \
 })
 
+typedef void (*vmemmap_pte_remap_func_t)(struct page *reuse, pte_t *ptep,
+					 unsigned long start, unsigned long end,
+					 void *priv);
+
 static inline unsigned int vmemmap_pages_per_hpage(struct hstate *h)
 {
 	return free_vmemmap_pages_per_hpage(h) + RESERVE_VMEMMAP_NR;
@@ -162,21 +166,42 @@ static pmd_t *vmemmap_to_pmd(unsigned long page)
 	return pmd_offset(pud, page);
 }
 
+static void remap_huge_page_pmd_vmemmap(pmd_t *pmd, unsigned long start,
+					unsigned long end,
+					vmemmap_pte_remap_func_t fn, void *priv)
+{
+	unsigned long next, addr = start;
+	struct page *reuse = NULL;
+
+	do {
+		pte_t *ptep;
+
+		ptep = pte_offset_kernel(pmd, addr);
+		if (!reuse)
+			reuse = pte_page(ptep[TAIL_PAGE_REUSE]);
+
+		next = vmemmap_hpage_addr_end(addr, end);
+		fn(reuse, ptep, addr, next, priv);
+	} while (pmd++, addr = next, addr != end);
+
+	flush_tlb_kernel_range(start, end);
+}
+
 static void __remap_huge_page_pte_vmemmap(struct page *reuse, pte_t *ptep,
 					  unsigned long start,
-					  unsigned long end,
-					  struct list_head *remap_pages)
+					  unsigned long end, void *priv)
 {
 	pgprot_t pgprot = PAGE_KERNEL;
 	void *from = page_to_virt(reuse);
 	unsigned long addr;
+	struct list_head *pages = priv;
 
 	for (addr = start; addr < end; addr += PAGE_SIZE) {
 		void *to;
 		struct page *page;
 		pte_t entry, old = *ptep;
 
-		page = list_first_entry(remap_pages, struct page, lru);
+		page = list_first_entry(pages, struct page, lru);
 		list_del(&page->lru);
 		to = page_to_virt(page);
 		copy_page(to, from);
@@ -196,28 +221,6 @@ static void __remap_huge_page_pte_vmemmap(struct page *reuse, pte_t *ptep,
 	}
 }
 
-static void __remap_huge_page_pmd_vmemmap(pmd_t *pmd, unsigned long start,
-					  unsigned long end,
-					  struct list_head *vmemmap_pages)
-{
-	unsigned long next, addr = start;
-	struct page *reuse = NULL;
-
-	do {
-		pte_t *ptep;
-
-		ptep = pte_offset_kernel(pmd, addr);
-		if (!reuse)
-			reuse = pte_page(ptep[TAIL_PAGE_REUSE]);
-
-		next = vmemmap_hpage_addr_end(addr, end);
-		__remap_huge_page_pte_vmemmap(reuse, ptep, addr, next,
-					      vmemmap_pages);
-	} while (pmd++, addr = next, addr != end);
-
-	flush_tlb_kernel_range(start, end);
-}
-
 static inline void alloc_vmemmap_pages(struct hstate *h, struct list_head *list)
 {
 	unsigned int nr = free_vmemmap_pages_per_hpage(h);
@@ -258,7 +261,8 @@ void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
 
 	start = vmemmap_addr + RESERVE_VMEMMAP_SIZE;
 	end = vmemmap_addr + vmemmap_pages_size_per_hpage(h);
-	__remap_huge_page_pmd_vmemmap(pmd, start, end, &map_pages);
+	remap_huge_page_pmd_vmemmap(pmd, start, end,
+				    __remap_huge_page_pte_vmemmap, &map_pages);
 }
 
 static inline void free_vmemmap_page_list(struct list_head *list)
@@ -273,13 +277,13 @@ static inline void free_vmemmap_page_list(struct list_head *list)
 
 static void __free_huge_page_pte_vmemmap(struct page *reuse, pte_t *ptep,
 					 unsigned long start,
-					 unsigned long end,
-					 struct list_head *free_pages)
+					 unsigned long end, void *priv)
 {
 	/* Make the tail pages are mapped read-only. */
 	pgprot_t pgprot = PAGE_KERNEL_RO;
 	pte_t entry = mk_pte(reuse, pgprot);
 	unsigned long addr;
+	struct list_head *pages = priv;
 
 	for (addr = start; addr < end; addr += PAGE_SIZE, ptep++) {
 		struct page *page;
@@ -287,34 +291,12 @@ static void __free_huge_page_pte_vmemmap(struct page *reuse, pte_t *ptep,
 
 		VM_WARN_ON(!pte_present(old));
 		page = pte_page(old);
-		list_add(&page->lru, free_pages);
+		list_add(&page->lru, pages);
 
 		set_pte_at(&init_mm, addr, ptep, entry);
 	}
 }
 
-static void __free_huge_page_pmd_vmemmap(pmd_t *pmd, unsigned long start,
-					 unsigned long end,
-					 struct list_head *vmemmap_pages)
-{
-	unsigned long next, addr = start;
-	struct page *reuse = NULL;
-
-	do {
-		pte_t *ptep;
-
-		ptep = pte_offset_kernel(pmd, addr);
-		if (!reuse)
-			reuse = pte_page(ptep[TAIL_PAGE_REUSE]);
-
-		next = vmemmap_hpage_addr_end(addr, end);
-		__free_huge_page_pte_vmemmap(reuse, ptep, addr, next,
-					     vmemmap_pages);
-	} while (pmd++, addr = next, addr != end);
-
-	flush_tlb_kernel_range(start, end);
-}
-
 void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 {
 	pmd_t *pmd;
@@ -330,7 +312,8 @@ void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 
 	start = vmemmap_addr + RESERVE_VMEMMAP_SIZE;
 	end = vmemmap_addr + vmemmap_pages_size_per_hpage(h);
-	__free_huge_page_pmd_vmemmap(pmd, start, end, &free_pages);
+	remap_huge_page_pmd_vmemmap(pmd, start, end,
+				    __free_huge_page_pte_vmemmap, &free_pages);
 	free_vmemmap_page_list(&free_pages);
 }
 
-- 
2.11.0

[PATCH v6 12/16] mm/hugetlb: Set the PageHWPoison to the raw error page

[Muchun Song]

Because we reuse the first tail vmemmap page frame and remap it
with read-only, we cannot set the PageHWPosion on a tail page.
So we can use the head[4].mapping to record the real error page
index and set the raw error page PageHWPoison later.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 mm/hugetlb.c         | 11 +++--------
 mm/hugetlb_vmemmap.h | 39 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 42 insertions(+), 8 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 3fafa39fcac6..ade20954eb81 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1383,6 +1383,7 @@ static void __free_hugepage(struct hstate *h, struct page *page)
 	int i;
 
 	alloc_huge_page_vmemmap(h, page);
+	subpage_hwpoison_deliver(page);
 
 	for (i = 0; i < pages_per_huge_page(h); i++) {
 		page[i].flags &= ~(1 << PG_locked | 1 << PG_error |
@@ -1930,14 +1931,8 @@ int dissolve_free_huge_page(struct page *page)
 		int nid = page_to_nid(head);
 		if (h->free_huge_pages - h->resv_huge_pages == 0)
 			goto out;
-		/*
-		 * Move PageHWPoison flag from head page to the raw error page,
-		 * which makes any subpages rather than the error page reusable.
-		 */
-		if (PageHWPoison(head) && page != head) {
-			SetPageHWPoison(page);
-			ClearPageHWPoison(head);
-		}
+
+		set_subpage_hwpoison(head, page);
 		list_del(&head->lru);
 		h->free_huge_pages--;
 		h->free_huge_pages_node[nid]--;
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index 7887095488f4..4bb35d87ae10 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -15,6 +15,29 @@ void __init hugetlb_vmemmap_init(struct hstate *h);
 void alloc_huge_page_vmemmap(struct hstate *h, struct page *head);
 void free_huge_page_vmemmap(struct hstate *h, struct page *head);
 
+static inline void subpage_hwpoison_deliver(struct page *head)
+{
+	struct page *page = head;
+
+	if (PageHWPoison(head))
+		page = head + page_private(head + 4);
+
+	/*
+	 * Move PageHWPoison flag from head page to the raw error page,
+	 * which makes any subpages rather than the error page reusable.
+	 */
+	if (page != head) {
+		SetPageHWPoison(page);
+		ClearPageHWPoison(head);
+	}
+}
+
+static inline void set_subpage_hwpoison(struct page *head, struct page *page)
+{
+	if (PageHWPoison(head))
+		set_page_private(head + 4, page - head);
+}
+
 static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
 {
 	return h->nr_free_vmemmap_pages;
@@ -32,6 +55,22 @@ static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 {
 }
 
+static inline void subpage_hwpoison_deliver(struct page *head)
+{
+}
+
+static inline void set_subpage_hwpoison(struct page *head, struct page *page)
+{
+	/*
+	 * Move PageHWPoison flag from head page to the raw error page,
+	 * which makes any subpages rather than the error page reusable.
+	 */
+	if (PageHWPoison(head) && page != head) {
+		SetPageHWPoison(page);
+		ClearPageHWPoison(head);
+	}
+}
+
 static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
 {
 	return 0;
-- 
2.11.0

[PATCH v6 13/16] mm/hugetlb: Flush work when dissolving hugetlb page

[Muchun Song]

We should flush work when dissolving a hugetlb page to make sure that
the hugetlb page is freed to the buddy.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 mm/hugetlb.c | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ade20954eb81..15e2c1dd32ea 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1328,6 +1328,12 @@ static void update_hpage_vmemmap_workfn(struct work_struct *work)
 }
 static DECLARE_WORK(hpage_update_work, update_hpage_vmemmap_workfn);
 
+static inline void flush_hpage_update_work(struct hstate *h)
+{
+	if (free_vmemmap_pages_per_hpage(h))
+		flush_work(&hpage_update_work);
+}
+
 static inline void __update_and_free_page(struct hstate *h, struct page *page)
 {
 	/* No need to allocate vmemmap pages */
@@ -1914,6 +1920,7 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
 int dissolve_free_huge_page(struct page *page)
 {
 	int rc = -EBUSY;
+	struct hstate *h = NULL;
 
 	/* Not to disrupt normal path by vainly holding hugetlb_lock */
 	if (!PageHuge(page))
@@ -1927,8 +1934,9 @@ int dissolve_free_huge_page(struct page *page)
 
 	if (!page_count(page)) {
 		struct page *head = compound_head(page);
-		struct hstate *h = page_hstate(head);
 		int nid = page_to_nid(head);
+
+		h = page_hstate(head);
 		if (h->free_huge_pages - h->resv_huge_pages == 0)
 			goto out;
 
@@ -1942,6 +1950,14 @@ int dissolve_free_huge_page(struct page *page)
 	}
 out:
 	spin_unlock(&hugetlb_lock);
+
+	/*
+	 * We should flush work before return to make sure that
+	 * the HugeTLB page is freed to the buddy.
+	 */
+	if (!rc && h)
+		flush_hpage_update_work(h);
+
 	return rc;
 }
 
-- 
2.11.0

[PATCH v6 14/16] mm/hugetlb: Add a kernel parameter hugetlb_free_vmemmap

[Muchun Song]

Add a kernel parameter hugetlb_free_vmemmap to disable the feature of
freeing unused vmemmap pages associated with each hugetlb page on boot.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 Documentation/admin-guide/kernel-parameters.txt |  9 +++++++++
 Documentation/admin-guide/mm/hugetlbpage.rst    |  3 +++
 mm/hugetlb_vmemmap.c                            | 19 ++++++++++++++++++-
 3 files changed, 30 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 5debfe238027..d28c3acde965 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1551,6 +1551,15 @@
 			Documentation/admin-guide/mm/hugetlbpage.rst.
 			Format: size[KMG]
 
+	hugetlb_free_vmemmap=
+			[KNL] When CONFIG_HUGETLB_PAGE_FREE_VMEMMAP is set,
+			this controls freeing unused vmemmap pages associated
+			with each HugeTLB page.
+			Format: { on | off (default) }
+
+			on:  enable the feature
+			off: disable the feature
+
 	hung_task_panic=
 			[KNL] Should the hung task detector generate panics.
 			Format: 0 | 1
diff --git a/Documentation/admin-guide/mm/hugetlbpage.rst b/Documentation/admin-guide/mm/hugetlbpage.rst
index f7b1c7462991..6a8b57f6d3b7 100644
--- a/Documentation/admin-guide/mm/hugetlbpage.rst
+++ b/Documentation/admin-guide/mm/hugetlbpage.rst
@@ -145,6 +145,9 @@ default_hugepagesz
 
 	will all result in 256 2M huge pages being allocated.  Valid default
 	huge page size is architecture dependent.
+hugetlb_free_vmemmap
+	When CONFIG_HUGETLB_PAGE_FREE_VMEMMAP is set, this enables freeing
+	unused vmemmap pages associated each HugeTLB page.
 
 When multiple huge page sizes are supported, ``/proc/sys/vm/nr_hugepages``
 indicates the current number of pre-allocated huge pages of the default size.
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 509ca451e232..b2222f8d1245 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -131,6 +131,22 @@ typedef void (*vmemmap_pte_remap_func_t)(struct page *reuse, pte_t *ptep,
 					 unsigned long start, unsigned long end,
 					 void *priv);
 
+static bool hugetlb_free_vmemmap_enabled __initdata;
+
+static int __init early_hugetlb_free_vmemmap_param(char *buf)
+{
+	if (!buf)
+		return -EINVAL;
+
+	if (!strcmp(buf, "on"))
+		hugetlb_free_vmemmap_enabled = true;
+	else if (strcmp(buf, "off"))
+		return -EINVAL;
+
+	return 0;
+}
+early_param("hugetlb_free_vmemmap", early_hugetlb_free_vmemmap_param);
+
 static inline unsigned int vmemmap_pages_per_hpage(struct hstate *h)
 {
 	return free_vmemmap_pages_per_hpage(h) + RESERVE_VMEMMAP_NR;
@@ -322,7 +338,8 @@ void __init hugetlb_vmemmap_init(struct hstate *h)
 	unsigned int order = huge_page_order(h);
 	unsigned int vmemmap_pages;
 
-	if (!is_power_of_2(sizeof(struct page))) {
+	if (!is_power_of_2(sizeof(struct page)) ||
+	    !hugetlb_free_vmemmap_enabled) {
 		pr_info("disable freeing vmemmap pages for %s\n", h->name);
 		return;
 	}
-- 
2.11.0

[PATCH v6 15/16] mm/hugetlb: Gather discrete indexes of tail page

[Muchun Song]

For hugetlb page, there are more metadata to save in the struct
page. But the head struct page cannot meet our needs, so we have
to abuse other tail struct page to store the metadata. In order
to avoid conflicts caused by subsequent use of more tail struct
pages, we can gather these discrete indexes of tail struct page
In this case, it will be easier to add a new tail page index later.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 include/linux/hugetlb.h        | 13 +++++++++++++
 include/linux/hugetlb_cgroup.h | 15 +++++++++------
 mm/hugetlb.c                   | 12 ++++++------
 mm/hugetlb_vmemmap.h           |  4 ++--
 4 files changed, 30 insertions(+), 14 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index eed3dd3bd626..8a615ae2d233 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -28,6 +28,19 @@ typedef struct { unsigned long pd; } hugepd_t;
 #include <linux/shm.h>
 #include <asm/tlbflush.h>
 
+enum {
+	SUBPAGE_INDEX_ACTIVE = 1,	/* reuse page flags of PG_private */
+	SUBPAGE_INDEX_TEMPORARY,	/* reuse page->mapping */
+#ifdef CONFIG_CGROUP_HUGETLB
+	SUBPAGE_INDEX_CGROUP = SUBPAGE_INDEX_TEMPORARY,/* reuse page->private */
+	SUBPAGE_INDEX_CGROUP_RSVD,	/* reuse page->private */
+#endif
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+	SUBPAGE_INDEX_HWPOISON,		/* reuse page->private */
+#endif
+	NR_USED_SUBPAGE,
+};
+
 struct hugepage_subpool {
 	spinlock_t lock;
 	long count;
diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h
index 2ad6e92f124a..3d3c1c49efe4 100644
--- a/include/linux/hugetlb_cgroup.h
+++ b/include/linux/hugetlb_cgroup.h
@@ -24,8 +24,9 @@ struct file_region;
 /*
  * Minimum page order trackable by hugetlb cgroup.
  * At least 4 pages are necessary for all the tracking information.
- * The second tail page (hpage[2]) is the fault usage cgroup.
- * The third tail page (hpage[3]) is the reservation usage cgroup.
+ * The second tail page (hpage[SUBPAGE_INDEX_CGROUP]) is the fault
+ * usage cgroup. The third tail page (hpage[SUBPAGE_INDEX_CGROUP_RSVD])
+ * is the reservation usage cgroup.
  */
 #define HUGETLB_CGROUP_MIN_ORDER	2
 
@@ -66,9 +67,9 @@ __hugetlb_cgroup_from_page(struct page *page, bool rsvd)
 	if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER)
 		return NULL;
 	if (rsvd)
-		return (struct hugetlb_cgroup *)page[3].private;
+		return (void *)page_private(page + SUBPAGE_INDEX_CGROUP_RSVD);
 	else
-		return (struct hugetlb_cgroup *)page[2].private;
+		return (void *)page_private(page + SUBPAGE_INDEX_CGROUP);
 }
 
 static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page)
@@ -90,9 +91,11 @@ static inline int __set_hugetlb_cgroup(struct page *page,
 	if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER)
 		return -1;
 	if (rsvd)
-		page[3].private = (unsigned long)h_cg;
+		set_page_private(page + SUBPAGE_INDEX_CGROUP_RSVD,
+				 (unsigned long)h_cg);
 	else
-		page[2].private = (unsigned long)h_cg;
+		set_page_private(page + SUBPAGE_INDEX_CGROUP,
+				 (unsigned long)h_cg);
 	return 0;
 }
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 15e2c1dd32ea..7700da372716 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1429,20 +1429,20 @@ struct hstate *size_to_hstate(unsigned long size)
 bool page_huge_active(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageHuge(page), page);
-	return PageHead(page) && PagePrivate(&page[1]);
+	return PageHead(page) && PagePrivate(&page[SUBPAGE_INDEX_ACTIVE]);
 }
 
 /* never called for tail page */
 static void set_page_huge_active(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageHeadHuge(page), page);
-	SetPagePrivate(&page[1]);
+	SetPagePrivate(&page[SUBPAGE_INDEX_ACTIVE]);
 }
 
 static void clear_page_huge_active(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageHeadHuge(page), page);
-	ClearPagePrivate(&page[1]);
+	ClearPagePrivate(&page[SUBPAGE_INDEX_ACTIVE]);
 }
 
 /*
@@ -1454,17 +1454,17 @@ static inline bool PageHugeTemporary(struct page *page)
 	if (!PageHuge(page))
 		return false;
 
-	return (unsigned long)page[2].mapping == -1U;
+	return (unsigned long)page[SUBPAGE_INDEX_TEMPORARY].mapping == -1U;
 }
 
 static inline void SetPageHugeTemporary(struct page *page)
 {
-	page[2].mapping = (void *)-1U;
+	page[SUBPAGE_INDEX_TEMPORARY].mapping = (void *)-1U;
 }
 
 static inline void ClearPageHugeTemporary(struct page *page)
 {
-	page[2].mapping = NULL;
+	page[SUBPAGE_INDEX_TEMPORARY].mapping = NULL;
 }
 
 static void __free_huge_page(struct page *page)
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index 4bb35d87ae10..54c2ca0e0dbe 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -20,7 +20,7 @@ static inline void subpage_hwpoison_deliver(struct page *head)
 	struct page *page = head;
 
 	if (PageHWPoison(head))
-		page = head + page_private(head + 4);
+		page = head + page_private(head + SUBPAGE_INDEX_HWPOISON);
 
 	/*
 	 * Move PageHWPoison flag from head page to the raw error page,
@@ -35,7 +35,7 @@ static inline void subpage_hwpoison_deliver(struct page *head)
 static inline void set_subpage_hwpoison(struct page *head, struct page *page)
 {
 	if (PageHWPoison(head))
-		set_page_private(head + 4, page - head);
+		set_page_private(head + SUBPAGE_INDEX_HWPOISON, page - head);
 }
 
 static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
-- 
2.11.0

[PATCH v6 16/16] mm/hugetlb: Add BUILD_BUG_ON to catch invalid usage of tail struct page

[Muchun Song]

There are only `RESERVE_VMEMMAP_SIZE / sizeof(struct page)` struct pages
can be used when CONFIG_HUGETLB_PAGE_FREE_VMEMMAP, so add a BUILD_BUG_ON
to catch this invalid usage of tail struct page.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 mm/hugetlb_vmemmap.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index b2222f8d1245..d2c013582110 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -338,6 +338,9 @@ void __init hugetlb_vmemmap_init(struct hstate *h)
 	unsigned int order = huge_page_order(h);
 	unsigned int vmemmap_pages;
 
+	BUILD_BUG_ON(NR_USED_SUBPAGE >=
+		     RESERVE_VMEMMAP_SIZE / sizeof(struct page));
+
 	if (!is_power_of_2(sizeof(struct page)) ||
 	    !hugetlb_free_vmemmap_enabled) {
 		pr_info("disable freeing vmemmap pages for %s\n", h->name);
-- 
2.11.0

Re: [PATCH v6 07/16] x86/mm/64: Disable PMD page mapping of vmemmap

[Oscar Salvador]

On Tue, Nov 24, 2020 at 05:52:50PM +0800, Muchun Song wrote:
> If we enable the CONFIG_HUGETLB_PAGE_FREE_VMEMMAP, we can just
> disbale PMD page mapping of vmemmap to simplify the code. In this
> case, we do not need complex code doing vmemmap page table
> manipulation. This is a way to simply the first version of this
> patch series. In the future, we can add some code doing page table
> manipulation.

IIRC, CONFIG_HUGETLB_PAGE_FREE_VMEMMAP was supposed to be enabled by default,
right?
And we would control whether we __really__ want to this by a boot option,
which was disabled by default?

If you go for populating the memmap with basepages by checking
CONFIG_HUGETLB_PAGE_FREE_VMEMMAP, would not everybody, even the ones that
did not enable this by the boot option be affected?

-- 
Oscar Salvador
SUSE L3

RE: [PATCH v6 07/16] x86/mm/64: Disable PMD page mapping of vmemmap

[Song Bao Hua (Barry Song)]

> -----Original Message-----
> From: owner-linux-mm@kvack.org [mailto:owner-linux-mm@kvack.org] On
> Behalf Of Oscar Salvador
> Sent: Tuesday, November 24, 2020 11:25 PM
> To: Muchun Song <songmuchun@bytedance.com>
> Cc: corbet@lwn.net; mike.kravetz@oracle.com; tglx@linutronix.de;
> mingo@redhat.com; bp@alien8.de; x86@kernel.org; hpa@zytor.com;
> dave.hansen@linux.intel.com; luto@kernel.org; peterz@infradead.org;
> viro@zeniv.linux.org.uk; akpm@linux-foundation.org; paulmck@kernel.org;
> mchehab+huawei@kernel.org; pawan.kumar.gupta@linux.intel.com;
> rdunlap@infradead.org; oneukum@suse.com; anshuman.khandual@arm.com;
> jroedel@suse.de; almasrymina@google.com; rientjes@google.com;
> willy@infradead.org; mhocko@suse.com; Song Bao Hua (Barry Song)
> <song.bao.hua@hisilicon.com>; duanxiongchun@bytedance.com;
> linux-doc@vger.kernel.org; linux-kernel@vger.kernel.org; linux-mm@kvack.org;
> linux-fsdevel@vger.kernel.org
> Subject: Re: [PATCH v6 07/16] x86/mm/64: Disable PMD page mapping of
> vmemmap
> 
> On Tue, Nov 24, 2020 at 05:52:50PM +0800, Muchun Song wrote:
> > If we enable the CONFIG_HUGETLB_PAGE_FREE_VMEMMAP, we can just
> > disbale PMD page mapping of vmemmap to simplify the code. In this
> > case, we do not need complex code doing vmemmap page table
> > manipulation. This is a way to simply the first version of this
> > patch series. In the future, we can add some code doing page table
> > manipulation.
> 
> IIRC, CONFIG_HUGETLB_PAGE_FREE_VMEMMAP was supposed to be enabled
> by default,
> right?
> And we would control whether we __really__ want to this by a boot option,
> which was disabled by default?
> 
> If you go for populating the memmap with basepages by checking
> CONFIG_HUGETLB_PAGE_FREE_VMEMMAP, would not everybody, even the
> ones that
> did not enable this by the boot option be affected?
> 

I would believe we could only bypass the pmd mapping of vmemmap while
free_vmemmap is explicitly enabled.
pmd mapping shouldn't be disabled in default. Would a cmdline of enabling
vmemmap_free be used for the first patchset?

> --
> Oscar Salvador
> SUSE L3

Thanks
Barry

RE: [PATCH v6 14/16] mm/hugetlb: Add a kernel parameter hugetlb_free_vmemmap

[Song Bao Hua (Barry Song)]

> -----Original Message-----
> From: Muchun Song [mailto:songmuchun@bytedance.com]
> Sent: Tuesday, November 24, 2020 10:53 PM
> To: corbet@lwn.net; mike.kravetz@oracle.com; tglx@linutronix.de;
> mingo@redhat.com; bp@alien8.de; x86@kernel.org; hpa@zytor.com;
> dave.hansen@linux.intel.com; luto@kernel.org; peterz@infradead.org;
> viro@zeniv.linux.org.uk; akpm@linux-foundation.org; paulmck@kernel.org;
> mchehab+huawei@kernel.org; pawan.kumar.gupta@linux.intel.com;
> rdunlap@infradead.org; oneukum@suse.com; anshuman.khandual@arm.com;
> jroedel@suse.de; almasrymina@google.com; rientjes@google.com;
> willy@infradead.org; osalvador@suse.de; mhocko@suse.com; Song Bao Hua
> (Barry Song) <song.bao.hua@hisilicon.com>
> Cc: duanxiongchun@bytedance.com; linux-doc@vger.kernel.org;
> linux-kernel@vger.kernel.org; linux-mm@kvack.org;
> linux-fsdevel@vger.kernel.org; Muchun Song <songmuchun@bytedance.com>
> Subject: [PATCH v6 14/16] mm/hugetlb: Add a kernel parameter
> hugetlb_free_vmemmap
> 
> Add a kernel parameter hugetlb_free_vmemmap to disable the feature of
> freeing unused vmemmap pages associated with each hugetlb page on boot.
> 
> Signed-off-by: Muchun Song <songmuchun@bytedance.com>
> ---
>  Documentation/admin-guide/kernel-parameters.txt |  9 +++++++++
>  Documentation/admin-guide/mm/hugetlbpage.rst    |  3 +++
>  mm/hugetlb_vmemmap.c                            | 19
> ++++++++++++++++++-
>  3 files changed, 30 insertions(+), 1 deletion(-)
> 
> diff --git a/Documentation/admin-guide/kernel-parameters.txt
> b/Documentation/admin-guide/kernel-parameters.txt
> index 5debfe238027..d28c3acde965 100644
> --- a/Documentation/admin-guide/kernel-parameters.txt
> +++ b/Documentation/admin-guide/kernel-parameters.txt
> @@ -1551,6 +1551,15 @@
>  			Documentation/admin-guide/mm/hugetlbpage.rst.
>  			Format: size[KMG]
> 
> +	hugetlb_free_vmemmap=
> +			[KNL] When CONFIG_HUGETLB_PAGE_FREE_VMEMMAP is set,
> +			this controls freeing unused vmemmap pages associated
> +			with each HugeTLB page.
> +			Format: { on | off (default) }
> +
> +			on:  enable the feature
> +			off: disable the feature
> +

We've a parameter here. but wouldn't it be applied to "x86/mm/64/:disable
Pmd page mapping of vmemmap" as well?
If (hugetlb_free_vmemmap_enabled)
	Do Basepage mapping?

>  	hung_task_panic=
>  			[KNL] Should the hung task detector generate panics.
>  			Format: 0 | 1
> diff --git a/Documentation/admin-guide/mm/hugetlbpage.rst
> b/Documentation/admin-guide/mm/hugetlbpage.rst
> index f7b1c7462991..6a8b57f6d3b7 100644
> --- a/Documentation/admin-guide/mm/hugetlbpage.rst
> +++ b/Documentation/admin-guide/mm/hugetlbpage.rst
> @@ -145,6 +145,9 @@ default_hugepagesz
> 
>  	will all result in 256 2M huge pages being allocated.  Valid default
>  	huge page size is architecture dependent.
> +hugetlb_free_vmemmap
> +	When CONFIG_HUGETLB_PAGE_FREE_VMEMMAP is set, this enables
> freeing
> +	unused vmemmap pages associated each HugeTLB page.
> 
>  When multiple huge page sizes are supported, ``/proc/sys/vm/nr_hugepages``
>  indicates the current number of pre-allocated huge pages of the default size.
> diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
> index 509ca451e232..b2222f8d1245 100644
> --- a/mm/hugetlb_vmemmap.c
> +++ b/mm/hugetlb_vmemmap.c
> @@ -131,6 +131,22 @@ typedef void (*vmemmap_pte_remap_func_t)(struct
> page *reuse, pte_t *ptep,
>  					 unsigned long start, unsigned long end,
>  					 void *priv);
> 
> +static bool hugetlb_free_vmemmap_enabled __initdata;
> +
> +static int __init early_hugetlb_free_vmemmap_param(char *buf)
> +{
> +	if (!buf)
> +		return -EINVAL;
> +
> +	if (!strcmp(buf, "on"))
> +		hugetlb_free_vmemmap_enabled = true;
> +	else if (strcmp(buf, "off"))
> +		return -EINVAL;
> +
> +	return 0;
> +}
> +early_param("hugetlb_free_vmemmap",
> early_hugetlb_free_vmemmap_param);
> +
>  static inline unsigned int vmemmap_pages_per_hpage(struct hstate *h)
>  {
>  	return free_vmemmap_pages_per_hpage(h) + RESERVE_VMEMMAP_NR;
> @@ -322,7 +338,8 @@ void __init hugetlb_vmemmap_init(struct hstate *h)
>  	unsigned int order = huge_page_order(h);
>  	unsigned int vmemmap_pages;
> 
> -	if (!is_power_of_2(sizeof(struct page))) {
> +	if (!is_power_of_2(sizeof(struct page)) ||
> +	    !hugetlb_free_vmemmap_enabled) {
>  		pr_info("disable freeing vmemmap pages for %s\n", h->name);
>  		return;
>  	}
> --
> 2.11.0

Thanks
Barry

Re: [External] RE: [PATCH v6 14/16] mm/hugetlb: Add a kernel parameter hugetlb_free_vmemmap

[Muchun Song]

On Tue, Nov 24, 2020 at 6:54 PM Song Bao Hua (Barry Song)
<song.bao.hua@hisilicon.com> wrote:
>
>
>
> > -----Original Message-----
> > From: Muchun Song [mailto:songmuchun@bytedance.com]
> > Sent: Tuesday, November 24, 2020 10:53 PM
> > To: corbet@lwn.net; mike.kravetz@oracle.com; tglx@linutronix.de;
> > mingo@redhat.com; bp@alien8.de; x86@kernel.org; hpa@zytor.com;
> > dave.hansen@linux.intel.com; luto@kernel.org; peterz@infradead.org;
> > viro@zeniv.linux.org.uk; akpm@linux-foundation.org; paulmck@kernel.org;
> > mchehab+huawei@kernel.org; pawan.kumar.gupta@linux.intel.com;
> > rdunlap@infradead.org; oneukum@suse.com; anshuman.khandual@arm.com;
> > jroedel@suse.de; almasrymina@google.com; rientjes@google.com;
> > willy@infradead.org; osalvador@suse.de; mhocko@suse.com; Song Bao Hua
> > (Barry Song) <song.bao.hua@hisilicon.com>
> > Cc: duanxiongchun@bytedance.com; linux-doc@vger.kernel.org;
> > linux-kernel@vger.kernel.org; linux-mm@kvack.org;
> > linux-fsdevel@vger.kernel.org; Muchun Song <songmuchun@bytedance.com>
> > Subject: [PATCH v6 14/16] mm/hugetlb: Add a kernel parameter
> > hugetlb_free_vmemmap
> >
> > Add a kernel parameter hugetlb_free_vmemmap to disable the feature of
> > freeing unused vmemmap pages associated with each hugetlb page on boot.
> >
> > Signed-off-by: Muchun Song <songmuchun@bytedance.com>
> > ---
> >  Documentation/admin-guide/kernel-parameters.txt |  9 +++++++++
> >  Documentation/admin-guide/mm/hugetlbpage.rst    |  3 +++
> >  mm/hugetlb_vmemmap.c                            | 19
> > ++++++++++++++++++-
> >  3 files changed, 30 insertions(+), 1 deletion(-)
> >
> > diff --git a/Documentation/admin-guide/kernel-parameters.txt
> > b/Documentation/admin-guide/kernel-parameters.txt
> > index 5debfe238027..d28c3acde965 100644
> > --- a/Documentation/admin-guide/kernel-parameters.txt
> > +++ b/Documentation/admin-guide/kernel-parameters.txt
> > @@ -1551,6 +1551,15 @@
> >                       Documentation/admin-guide/mm/hugetlbpage.rst.
> >                       Format: size[KMG]
> >
> > +     hugetlb_free_vmemmap=
> > +                     [KNL] When CONFIG_HUGETLB_PAGE_FREE_VMEMMAP is set,
> > +                     this controls freeing unused vmemmap pages associated
> > +                     with each HugeTLB page.
> > +                     Format: { on | off (default) }
> > +
> > +                     on:  enable the feature
> > +                     off: disable the feature
> > +
>
> We've a parameter here. but wouldn't it be applied to "x86/mm/64/:disable
> Pmd page mapping of vmemmap" as well?
> If (hugetlb_free_vmemmap_enabled)
>         Do Basepage mapping?

Oh, yeah, we can. Thanks.

>
> >       hung_task_panic=
> >                       [KNL] Should the hung task detector generate panics.
> >                       Format: 0 | 1
> > diff --git a/Documentation/admin-guide/mm/hugetlbpage.rst
> > b/Documentation/admin-guide/mm/hugetlbpage.rst
> > index f7b1c7462991..6a8b57f6d3b7 100644
> > --- a/Documentation/admin-guide/mm/hugetlbpage.rst
> > +++ b/Documentation/admin-guide/mm/hugetlbpage.rst
> > @@ -145,6 +145,9 @@ default_hugepagesz
> >
> >       will all result in 256 2M huge pages being allocated.  Valid default
> >       huge page size is architecture dependent.
> > +hugetlb_free_vmemmap
> > +     When CONFIG_HUGETLB_PAGE_FREE_VMEMMAP is set, this enables
> > freeing
> > +     unused vmemmap pages associated each HugeTLB page.
> >
> >  When multiple huge page sizes are supported, ``/proc/sys/vm/nr_hugepages``
> >  indicates the current number of pre-allocated huge pages of the default size.
> > diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
> > index 509ca451e232..b2222f8d1245 100644
> > --- a/mm/hugetlb_vmemmap.c
> > +++ b/mm/hugetlb_vmemmap.c
> > @@ -131,6 +131,22 @@ typedef void (*vmemmap_pte_remap_func_t)(struct
> > page *reuse, pte_t *ptep,
> >                                        unsigned long start, unsigned long end,
> >                                        void *priv);
> >
> > +static bool hugetlb_free_vmemmap_enabled __initdata;
> > +
> > +static int __init early_hugetlb_free_vmemmap_param(char *buf)
> > +{
> > +     if (!buf)
> > +             return -EINVAL;
> > +
> > +     if (!strcmp(buf, "on"))
> > +             hugetlb_free_vmemmap_enabled = true;
> > +     else if (strcmp(buf, "off"))
> > +             return -EINVAL;
> > +
> > +     return 0;
> > +}
> > +early_param("hugetlb_free_vmemmap",
> > early_hugetlb_free_vmemmap_param);
> > +
> >  static inline unsigned int vmemmap_pages_per_hpage(struct hstate *h)
> >  {
> >       return free_vmemmap_pages_per_hpage(h) + RESERVE_VMEMMAP_NR;
> > @@ -322,7 +338,8 @@ void __init hugetlb_vmemmap_init(struct hstate *h)
> >       unsigned int order = huge_page_order(h);
> >       unsigned int vmemmap_pages;
> >
> > -     if (!is_power_of_2(sizeof(struct page))) {
> > +     if (!is_power_of_2(sizeof(struct page)) ||
> > +         !hugetlb_free_vmemmap_enabled) {
> >               pr_info("disable freeing vmemmap pages for %s\n", h->name);
> >               return;
> >       }
> > --
> > 2.11.0
>
> Thanks
> Barry
>


-- 
Yours,
Muchun

Re: [External] Re: [PATCH v6 07/16] x86/mm/64: Disable PMD page mapping of vmemmap

[Muchun Song]

On Tue, Nov 24, 2020 at 6:24 PM Oscar Salvador <osalvador@suse.de> wrote:
>
> On Tue, Nov 24, 2020 at 05:52:50PM +0800, Muchun Song wrote:
> > If we enable the CONFIG_HUGETLB_PAGE_FREE_VMEMMAP, we can just
> > disbale PMD page mapping of vmemmap to simplify the code. In this
> > case, we do not need complex code doing vmemmap page table
> > manipulation. This is a way to simply the first version of this
> > patch series. In the future, we can add some code doing page table
> > manipulation.
>
> IIRC, CONFIG_HUGETLB_PAGE_FREE_VMEMMAP was supposed to be enabled by default,
> right?
> And we would control whether we __really__ want to this by a boot option,
> which was disabled by default?
>
> If you go for populating the memmap with basepages by checking
> CONFIG_HUGETLB_PAGE_FREE_VMEMMAP, would not everybody, even the ones that
> did not enable this by the boot option be affected?

Yeah, this should be improved. We should enable the basepage mapping
of vmemmap only when this feature is enabled via boot command line.
I will apply the suggestions mentioned by Barry. Thanks.

>
> --
> Oscar Salvador
> SUSE L3



-- 
Yours,
Muchun

Re: [PATCH v6 09/16] mm/hugetlb: Defer freeing of HugeTLB pages

[Michal Hocko]

On Tue 24-11-20 17:52:52, Muchun Song wrote:
> In the subsequent patch, we will allocate the vmemmap pages when free
> HugeTLB pages. But update_and_free_page() is called from a non-task
> context(and hold hugetlb_lock), so we can defer the actual freeing in
> a workqueue to prevent use GFP_ATOMIC to allocate the vmemmap pages.

This has been brought up earlier without any satisfying answer. Do we
really have bother with the freeing from the pool and reconstructing the
vmemmap page tables? Do existing usecases really require such a dynamic
behavior? In other words, wouldn't it be much simpler to allow to use
hugetlb pages with sparse vmemmaps only for the boot time reservations
and never allow them to be freed back to the allocator. This is pretty
restrictive, no question about that, but it would drop quite some code
AFAICS and the resulting series would be much easier to review really
carefully. Additional enhancements can be done on top with specifics
about usecases which require more flexibility.

> Signed-off-by: Muchun Song <songmuchun@bytedance.com>
> ---
>  mm/hugetlb.c         | 96 ++++++++++++++++++++++++++++++++++++++++++++++------
>  mm/hugetlb_vmemmap.c |  5 ---
>  mm/hugetlb_vmemmap.h | 10 ++++++
>  3 files changed, 95 insertions(+), 16 deletions(-)
-- 
Michal Hocko
SUSE Labs

Re: [External] Re: [PATCH v6 09/16] mm/hugetlb: Defer freeing of HugeTLB pages

[Muchun Song]

On Tue, Nov 24, 2020 at 7:51 PM Michal Hocko <mhocko@suse.com> wrote:
>
> On Tue 24-11-20 17:52:52, Muchun Song wrote:
> > In the subsequent patch, we will allocate the vmemmap pages when free
> > HugeTLB pages. But update_and_free_page() is called from a non-task
> > context(and hold hugetlb_lock), so we can defer the actual freeing in
> > a workqueue to prevent use GFP_ATOMIC to allocate the vmemmap pages.
>
> This has been brought up earlier without any satisfying answer. Do we
> really have bother with the freeing from the pool and reconstructing the
> vmemmap page tables? Do existing usecases really require such a dynamic
> behavior? In other words, wouldn't it be much simpler to allow to use

If someone wants to free a HugeTLB page, there is no way to do that if we
do not allow this behavior. When do we need this? On our server, we will
allocate a lot of HugeTLB pages for SPDK or virtualization. Sometimes,
we want to debug some issues and want to apt install some debug tools,
but if the host has little memory and the install operation can be failed
because of no memory. In this time, we can try to free some HugeTLB
pages to buddy in order to continue debugging. So maybe we need this.

> hugetlb pages with sparse vmemmaps only for the boot time reservations
> and never allow them to be freed back to the allocator. This is pretty
> restrictive, no question about that, but it would drop quite some code

Yeah, if we do not allow freeing the HugeTLB page to buddy, it actually
can drop some code. But I think that it only drop this one and next one
patch. It seems not a lot. And if we drop this patch, we need to add some
another code to do the boot time reservations and other code to disallow
freeing HugeTLB pages. So why not support freeing now.

> AFAICS and the resulting series would be much easier to review really
> carefully. Additional enhancements can be done on top with specifics
> about usecases which require more flexibility.

The code of allocating vmemmap pages for the HugeTLB page is very
similar to the freeing vmemmap pages. The two operations are opposite.
I think that if someone can understand the freeing path, it is also easy
for him to understand the allcating path. If you look at close to this patch,
I believe that it is easy for you.

>
> > Signed-off-by: Muchun Song <songmuchun@bytedance.com>
> > ---
> >  mm/hugetlb.c         | 96 ++++++++++++++++++++++++++++++++++++++++++++++------
> >  mm/hugetlb_vmemmap.c |  5 ---
> >  mm/hugetlb_vmemmap.h | 10 ++++++
> >  3 files changed, 95 insertions(+), 16 deletions(-)
> --
> Michal Hocko
> SUSE Labs



-- 
Yours,
Muchun

Re: [External] Re: [PATCH v6 09/16] mm/hugetlb: Defer freeing of HugeTLB pages

[Michal Hocko]

On Tue 24-11-20 20:45:30, Muchun Song wrote:
> On Tue, Nov 24, 2020 at 7:51 PM Michal Hocko <mhocko@suse.com> wrote:
> >
> > On Tue 24-11-20 17:52:52, Muchun Song wrote:
> > > In the subsequent patch, we will allocate the vmemmap pages when free
> > > HugeTLB pages. But update_and_free_page() is called from a non-task
> > > context(and hold hugetlb_lock), so we can defer the actual freeing in
> > > a workqueue to prevent use GFP_ATOMIC to allocate the vmemmap pages.
> >
> > This has been brought up earlier without any satisfying answer. Do we
> > really have bother with the freeing from the pool and reconstructing the
> > vmemmap page tables? Do existing usecases really require such a dynamic
> > behavior? In other words, wouldn't it be much simpler to allow to use
> 
> If someone wants to free a HugeTLB page, there is no way to do that if we
> do not allow this behavior.

Right. The question is how much that matters for the _initial_ feature
submission. Is this restriction so important that it would render it
unsuable?

> When do we need this? On our server, we will
> allocate a lot of HugeTLB pages for SPDK or virtualization. Sometimes,
> we want to debug some issues and want to apt install some debug tools,
> but if the host has little memory and the install operation can be failed
> because of no memory. In this time, we can try to free some HugeTLB
> pages to buddy in order to continue debugging. So maybe we need this.

Or maybe you can still allocate hugetlb pages for debugging in runtime
and try to free those when you need to.

> > hugetlb pages with sparse vmemmaps only for the boot time reservations
> > and never allow them to be freed back to the allocator. This is pretty
> > restrictive, no question about that, but it would drop quite some code
> 
> Yeah, if we do not allow freeing the HugeTLB page to buddy, it actually
> can drop some code. But I think that it only drop this one and next one
> patch. It seems not a lot. And if we drop this patch, we need to add some
> another code to do the boot time reservations and other code to disallow
> freeing HugeTLB pages.

you need a per hugetlb page flag to note the sparse vmemmap anyway so
the freeing path should be a trivial check for the flag. Early boot
reservation. Special casing for the early boot reservation shouldn't be
that hard either. But I haven't checked closely.

> So why not support freeing now.

Because it adds some non trivial challenges which would be better to
deal with with a stable and tested and feature limited implementation.
The most obvious one is the problem with vmemmap allocations when
freeing hugetlb page. Others like vmemmap manipulation is quite some
code but no surprises. Btw. that should be implemented in vmemmap proper
and ready for other potential users. But this is a minor detail.

-- 
Michal Hocko
SUSE Labs

[PATCH v6 01/16] mm/memory_hotplug: Move bootmem info registration API to bootmem_info.c

[chengkaitao]

From: Muchun Song <songmuchun@bytedance.com>

Move bootmem info registration common API to individual bootmem_info.c
for later patch use. This is just code movement without any functional
change.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
---
 arch/x86/mm/init_64.c          |  1 +
 include/linux/bootmem_info.h   | 27 ++++++++++++
 include/linux/memory_hotplug.h | 23 ----------
 mm/Makefile                    |  1 +
 mm/bootmem_info.c              | 99 ++++++++++++++++++++++++++++++++++++++++++
 mm/memory_hotplug.c            | 91 +-------------------------------------
 6 files changed, 129 insertions(+), 113 deletions(-)
 create mode 100644 include/linux/bootmem_info.h
 create mode 100644 mm/bootmem_info.c

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index b5a3fa4033d3..c7f7ad55b625 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -33,6 +33,7 @@
 #include <linux/nmi.h>
 #include <linux/gfp.h>
 #include <linux/kcore.h>
+#include <linux/bootmem_info.h>
 
 #include <asm/processor.h>
 #include <asm/bios_ebda.h>
diff --git a/include/linux/bootmem_info.h b/include/linux/bootmem_info.h
new file mode 100644
index 000000000000..65bb9b23140f
--- /dev/null
+++ b/include/linux/bootmem_info.h
@@ -0,0 +1,27 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __LINUX_BOOTMEM_INFO_H
+#define __LINUX_BOOTMEM_INFO_H
+
+#include <linux/mmzone.h>
+
+/*
+ * Types for free bootmem stored in page->lru.next. These have to be in
+ * some random range in unsigned long space for debugging purposes.
+ */
+enum {
+	MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12,
+	SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE,
+	MIX_SECTION_INFO,
+	NODE_INFO,
+	MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO,
+};
+
+#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
+void __init register_page_bootmem_info_node(struct pglist_data *pgdat);
+#else
+static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
+{
+}
+#endif
+
+#endif /* __LINUX_BOOTMEM_INFO_H */
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 51a877fec8da..19e5d067294c 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -33,18 +33,6 @@ struct vmem_altmap;
 	___page;						   \
 })
 
-/*
- * Types for free bootmem stored in page->lru.next. These have to be in
- * some random range in unsigned long space for debugging purposes.
- */
-enum {
-	MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE = 12,
-	SECTION_INFO = MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE,
-	MIX_SECTION_INFO,
-	NODE_INFO,
-	MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE = NODE_INFO,
-};
-
 /* Types for control the zone type of onlined and offlined memory */
 enum {
 	/* Offline the memory. */
@@ -209,13 +197,6 @@ static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
 #endif /* CONFIG_NUMA */
 #endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
 
-#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
-extern void __init register_page_bootmem_info_node(struct pglist_data *pgdat);
-#else
-static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
-{
-}
-#endif
 extern void put_page_bootmem(struct page *page);
 extern void get_page_bootmem(unsigned long ingo, struct page *page,
 			     unsigned long type);
@@ -254,10 +235,6 @@ static inline int mhp_notimplemented(const char *func)
 	return -ENOSYS;
 }
 
-static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
-{
-}
-
 static inline int try_online_node(int nid)
 {
 	return 0;
diff --git a/mm/Makefile b/mm/Makefile
index d5649f1c12c0..752111587c99 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -82,6 +82,7 @@ obj-$(CONFIG_SLAB) += slab.o
 obj-$(CONFIG_SLUB) += slub.o
 obj-$(CONFIG_KASAN)	+= kasan/
 obj-$(CONFIG_FAILSLAB) += failslab.o
+obj-$(CONFIG_HAVE_BOOTMEM_INFO_NODE) += bootmem_info.o
 obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
 obj-$(CONFIG_MEMTEST)		+= memtest.o
 obj-$(CONFIG_MIGRATION) += migrate.o
diff --git a/mm/bootmem_info.c b/mm/bootmem_info.c
new file mode 100644
index 000000000000..39fa8fc120bc
--- /dev/null
+++ b/mm/bootmem_info.c
@@ -0,0 +1,99 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ *  linux/mm/bootmem_info.c
+ *
+ *  Copyright (C)
+ */
+#include <linux/mm.h>
+#include <linux/compiler.h>
+#include <linux/memblock.h>
+#include <linux/bootmem_info.h>
+#include <linux/memory_hotplug.h>
+
+#ifndef CONFIG_SPARSEMEM_VMEMMAP
+static void register_page_bootmem_info_section(unsigned long start_pfn)
+{
+	unsigned long mapsize, section_nr, i;
+	struct mem_section *ms;
+	struct page *page, *memmap;
+	struct mem_section_usage *usage;
+
+	section_nr = pfn_to_section_nr(start_pfn);
+	ms = __nr_to_section(section_nr);
+
+	/* Get section's memmap address */
+	memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
+
+	/*
+	 * Get page for the memmap's phys address
+	 * XXX: need more consideration for sparse_vmemmap...
+	 */
+	page = virt_to_page(memmap);
+	mapsize = sizeof(struct page) * PAGES_PER_SECTION;
+	mapsize = PAGE_ALIGN(mapsize) >> PAGE_SHIFT;
+
+	/* remember memmap's page */
+	for (i = 0; i < mapsize; i++, page++)
+		get_page_bootmem(section_nr, page, SECTION_INFO);
+
+	usage = ms->usage;
+	page = virt_to_page(usage);
+
+	mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT;
+
+	for (i = 0; i < mapsize; i++, page++)
+		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
+
+}
+#else /* CONFIG_SPARSEMEM_VMEMMAP */
+static void register_page_bootmem_info_section(unsigned long start_pfn)
+{
+	unsigned long mapsize, section_nr, i;
+	struct mem_section *ms;
+	struct page *page, *memmap;
+	struct mem_section_usage *usage;
+
+	section_nr = pfn_to_section_nr(start_pfn);
+	ms = __nr_to_section(section_nr);
+
+	memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
+
+	register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION);
+
+	usage = ms->usage;
+	page = virt_to_page(usage);
+
+	mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT;
+
+	for (i = 0; i < mapsize; i++, page++)
+		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
+}
+#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
+
+void __init register_page_bootmem_info_node(struct pglist_data *pgdat)
+{
+	unsigned long i, pfn, end_pfn, nr_pages;
+	int node = pgdat->node_id;
+	struct page *page;
+
+	nr_pages = PAGE_ALIGN(sizeof(struct pglist_data)) >> PAGE_SHIFT;
+	page = virt_to_page(pgdat);
+
+	for (i = 0; i < nr_pages; i++, page++)
+		get_page_bootmem(node, page, NODE_INFO);
+
+	pfn = pgdat->node_start_pfn;
+	end_pfn = pgdat_end_pfn(pgdat);
+
+	/* register section info */
+	for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
+		/*
+		 * Some platforms can assign the same pfn to multiple nodes - on
+		 * node0 as well as nodeN.  To avoid registering a pfn against
+		 * multiple nodes we check that this pfn does not already
+		 * reside in some other nodes.
+		 */
+		if (pfn_valid(pfn) && (early_pfn_to_nid(pfn) == node))
+			register_page_bootmem_info_section(pfn);
+	}
+}
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index baded53b9ff9..2da4ad071456 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -21,6 +21,7 @@
 #include <linux/memory.h>
 #include <linux/memremap.h>
 #include <linux/memory_hotplug.h>
+#include <linux/bootmem_info.h>
 #include <linux/highmem.h>
 #include <linux/vmalloc.h>
 #include <linux/ioport.h>
@@ -167,96 +168,6 @@ void put_page_bootmem(struct page *page)
 	}
 }
 
-#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
-#ifndef CONFIG_SPARSEMEM_VMEMMAP
-static void register_page_bootmem_info_section(unsigned long start_pfn)
-{
-	unsigned long mapsize, section_nr, i;
-	struct mem_section *ms;
-	struct page *page, *memmap;
-	struct mem_section_usage *usage;
-
-	section_nr = pfn_to_section_nr(start_pfn);
-	ms = __nr_to_section(section_nr);
-
-	/* Get section's memmap address */
-	memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
-
-	/*
-	 * Get page for the memmap's phys address
-	 * XXX: need more consideration for sparse_vmemmap...
-	 */
-	page = virt_to_page(memmap);
-	mapsize = sizeof(struct page) * PAGES_PER_SECTION;
-	mapsize = PAGE_ALIGN(mapsize) >> PAGE_SHIFT;
-
-	/* remember memmap's page */
-	for (i = 0; i < mapsize; i++, page++)
-		get_page_bootmem(section_nr, page, SECTION_INFO);
-
-	usage = ms->usage;
-	page = virt_to_page(usage);
-
-	mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT;
-
-	for (i = 0; i < mapsize; i++, page++)
-		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
-
-}
-#else /* CONFIG_SPARSEMEM_VMEMMAP */
-static void register_page_bootmem_info_section(unsigned long start_pfn)
-{
-	unsigned long mapsize, section_nr, i;
-	struct mem_section *ms;
-	struct page *page, *memmap;
-	struct mem_section_usage *usage;
-
-	section_nr = pfn_to_section_nr(start_pfn);
-	ms = __nr_to_section(section_nr);
-
-	memmap = sparse_decode_mem_map(ms->section_mem_map, section_nr);
-
-	register_page_bootmem_memmap(section_nr, memmap, PAGES_PER_SECTION);
-
-	usage = ms->usage;
-	page = virt_to_page(usage);
-
-	mapsize = PAGE_ALIGN(mem_section_usage_size()) >> PAGE_SHIFT;
-
-	for (i = 0; i < mapsize; i++, page++)
-		get_page_bootmem(section_nr, page, MIX_SECTION_INFO);
-}
-#endif /* !CONFIG_SPARSEMEM_VMEMMAP */
-
-void __init register_page_bootmem_info_node(struct pglist_data *pgdat)
-{
-	unsigned long i, pfn, end_pfn, nr_pages;
-	int node = pgdat->node_id;
-	struct page *page;
-
-	nr_pages = PAGE_ALIGN(sizeof(struct pglist_data)) >> PAGE_SHIFT;
-	page = virt_to_page(pgdat);
-
-	for (i = 0; i < nr_pages; i++, page++)
-		get_page_bootmem(node, page, NODE_INFO);
-
-	pfn = pgdat->node_start_pfn;
-	end_pfn = pgdat_end_pfn(pgdat);
-
-	/* register section info */
-	for (; pfn < end_pfn; pfn += PAGES_PER_SECTION) {
-		/*
-		 * Some platforms can assign the same pfn to multiple nodes - on
-		 * node0 as well as nodeN.  To avoid registering a pfn against
-		 * multiple nodes we check that this pfn does not already
-		 * reside in some other nodes.
-		 */
-		if (pfn_valid(pfn) && (early_pfn_to_nid(pfn) == node))
-			register_page_bootmem_info_section(pfn);
-	}
-}
-#endif /* CONFIG_HAVE_BOOTMEM_INFO_NODE */
-
 static int check_pfn_span(unsigned long pfn, unsigned long nr_pages,
 		const char *reason)
 {

From patchwork Tue Nov 24 09:52:45 2020
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
X-Patchwork-Submitter: Muchun Song <songmuchun@bytedance.com>
X-Patchwork-Id: 1344530
Return-Path: <linux-kernel-owner@kernel.org>
Received: from mail.kernel.org (mail.kernel.org [198.145.29.99])
	by smtp.lore.kernel.org (Postfix) with ESMTP id DFBC9C64E7C
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:57:10 +0000 (UTC)
Received: from vger.kernel.org (vger.kernel.org [23.128.96.18])
	by mail.kernel.org (Postfix) with ESMTP id 9F7AC20857
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:57:10 +0000 (UTC)
Authentication-Results: mail.kernel.org;
	dkim=pass (2048-bit key) header.d=bytedance-com.20150623.gappssmtp.com
 header.i=@bytedance-com.20150623.gappssmtp.com header.b="rqnVg68d"
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1727792AbgKXJ5F (ORCPT
        <rfc822;linux-kernel@archiver.kernel.org>);
        Tue, 24 Nov 2020 04:57:05 -0500
Received: from lindbergh.monkeyblade.net ([23.128.96.19]:57090 "EHLO
        lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1728137AbgKXJ5E (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Tue, 24 Nov 2020 04:57:04 -0500
Received: from mail-pf1-x441.google.com (mail-pf1-x441.google.com
 [IPv6:2607:f8b0:4864:20::441])
        by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 1486AC061A4D
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:57:03 -0800 (PST)
Received: by mail-pf1-x441.google.com with SMTP id w6so18011903pfu.1
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:57:03 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=bytedance-com.20150623.gappssmtp.com; s=20150623;
        h=from:to:cc:subject:date:message-id:in-reply-to:references
         :mime-version:content-transfer-encoding;
        bh=YQYB74FkwOxFI1h+l2VXl2pw2h4ZcuxqFh5PVtqZk4E=;
        b=rqnVg68d76PVpgYg3/d6F2C6WFWhKKmKAt+sAzW8rWgezC1C6s3/SNDuelVbsJp1zL
         0eFsyionvitpceHC0+x4a/HHMxRsFvmG/9bSdSzW4py6xxJZfBxAO9EtZYPHe2Hbwzs6
         l6Tf1AeyY53trSaLqCk6GE6tH0klj9dAG2zIA0EJs7wDIpGe1HUv7go+JBwsPMpIRrYr
         4q8IqNU6W9PjZVjjl7yE4LFASyZQXmdeB4Ia+Yui2bLkJmtQnmxoMdOPpA9RY6fOGg7x
         4OgNliJip2aX4s8PPIWEkLttCFdqqBKq5n0jMiXXBKSu3x7z6Ti9xqMrNMrzoLTNWKz5
         0klQ==
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=1e100.net; s=20161025;
        h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to
         :references:mime-version:content-transfer-encoding;
        bh=YQYB74FkwOxFI1h+l2VXl2pw2h4ZcuxqFh5PVtqZk4E=;
        b=AmsplYVJ4GNUG5VWyL1S+SKm3hgnnD/TYKePoddDnrWfkEJtdVxVifb0nh7MX+Xj7f
         o97HHCBc3tA8RI79gbUzk7iLtt4zNHYMyoJ2ivFT/q4Z5L5PWdBGwYn7GrxMlHIFGKfo
         CY7zIIu7jugHuDg/0Em6MvFPDGYNoor9n9YkwU/V7MRt3iTwGwUJWJoqpR0uFJ3tP87F
         Zd3YvgMI+tWxVucc4GNzXffpp3vGHMccCZ9x3hn8v16yWH4G+d5dPJ4H5uI3gN0or0Gn
         dSA9yxWsOB8IygNJHsrXyM40pxkdO8YJiWz0QE8Cnw1ObVBSlcRPRRh0/SBH/e1TjBI9
         QYdQ==
X-Gm-Message-State: AOAM532sQwCgNxsfcUHiRJU/Sfxvr8UjFK3gB/E1X4LSjEUGOg0fxyNJ
        illSYuJsTngGcP00dXFAvJOahw==
X-Google-Smtp-Source: 
 ABdhPJxA57sXMzwbpUoFJsMDr4i9xEcSLLTQNrVmo0S2leZIkvnwpTZ4NSXZA6eVceqAnBsSOoK+Yg==
X-Received: by 2002:a63:cc01:: with SMTP id x1mr3153166pgf.15.1606211822617;
        Tue, 24 Nov 2020 01:57:02 -0800 (PST)
Received: from localhost.localdomain ([103.136.220.120])
        by smtp.gmail.com with ESMTPSA id
 t20sm2424562pjg.25.2020.11.24.01.56.52
        (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128);
        Tue, 24 Nov 2020 01:57:02 -0800 (PST)
From: Muchun Song <songmuchun@bytedance.com>
To: corbet@lwn.net, mike.kravetz@oracle.com, tglx@linutronix.de,
        mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com,
        dave.hansen@linux.intel.com, luto@kernel.org, peterz@infradead.org,
        viro@zeniv.linux.org.uk, akpm@linux-foundation.org,
        paulmck@kernel.org, mchehab+huawei@kernel.org,
        pawan.kumar.gupta@linux.intel.com, rdunlap@infradead.org,
        oneukum@suse.com, anshuman.khandual@arm.com, jroedel@suse.de,
        almasrymina@google.com, rientjes@google.com, willy@infradead.org,
        osalvador@suse.de, mhocko@suse.com, song.bao.hua@hisilicon.com
Cc: duanxiongchun@bytedance.com, linux-doc@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        linux-fsdevel@vger.kernel.org,
        Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH v6 02/16] mm/memory_hotplug: Move {get,put}_page_bootmem() to
 bootmem_info.c
Date: Tue, 24 Nov 2020 17:52:45 +0800
Message-Id: <20201124095259.58755-3-songmuchun@bytedance.com>
X-Mailer: git-send-email 2.21.0 (Apple Git-122)
In-Reply-To: <20201124095259.58755-1-songmuchun@bytedance.com>
References: <20201124095259.58755-1-songmuchun@bytedance.com>
MIME-Version: 1.0
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

In the later patch, we will use {get,put}_page_bootmem() to initialize
the page for vmemmap or free vmemmap page to buddy. So move them out of
CONFIG_MEMORY_HOTPLUG_SPARSE. This is just code movement without any
functional change.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
Reviewed-by: Oscar Salvador <osalvador@suse.de>
---
 arch/x86/mm/init_64.c          |  2 +-
 include/linux/bootmem_info.h   | 13 +++++++++++++
 include/linux/memory_hotplug.h |  4 ----
 mm/bootmem_info.c              | 25 +++++++++++++++++++++++++
 mm/memory_hotplug.c            | 27 ---------------------------
 mm/sparse.c                    |  1 +
 6 files changed, 40 insertions(+), 32 deletions(-)

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index c7f7ad55b625..0a45f062826e 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1572,7 +1572,7 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 	return err;
 }
 
-#if defined(CONFIG_MEMORY_HOTPLUG_SPARSE) && defined(CONFIG_HAVE_BOOTMEM_INFO_NODE)
+#ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
 void register_page_bootmem_memmap(unsigned long section_nr,
 				  struct page *start_page, unsigned long nr_pages)
 {
diff --git a/include/linux/bootmem_info.h b/include/linux/bootmem_info.h
index 65bb9b23140f..4ed6dee1adc9 100644
--- a/include/linux/bootmem_info.h
+++ b/include/linux/bootmem_info.h
@@ -18,10 +18,23 @@ enum {
 
 #ifdef CONFIG_HAVE_BOOTMEM_INFO_NODE
 void __init register_page_bootmem_info_node(struct pglist_data *pgdat);
+
+void get_page_bootmem(unsigned long info, struct page *page,
+		      unsigned long type);
+void put_page_bootmem(struct page *page);
 #else
 static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
 {
 }
+
+static inline void put_page_bootmem(struct page *page)
+{
+}
+
+static inline void get_page_bootmem(unsigned long info, struct page *page,
+				    unsigned long type)
+{
+}
 #endif
 
 #endif /* __LINUX_BOOTMEM_INFO_H */
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 19e5d067294c..c9f3361fe84b 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -197,10 +197,6 @@ static inline void arch_refresh_nodedata(int nid, pg_data_t *pgdat)
 #endif /* CONFIG_NUMA */
 #endif /* CONFIG_HAVE_ARCH_NODEDATA_EXTENSION */
 
-extern void put_page_bootmem(struct page *page);
-extern void get_page_bootmem(unsigned long ingo, struct page *page,
-			     unsigned long type);
-
 void get_online_mems(void);
 void put_online_mems(void);
 
diff --git a/mm/bootmem_info.c b/mm/bootmem_info.c
index 39fa8fc120bc..fcab5a3f8cc0 100644
--- a/mm/bootmem_info.c
+++ b/mm/bootmem_info.c
@@ -10,6 +10,31 @@
 #include <linux/bootmem_info.h>
 #include <linux/memory_hotplug.h>
 
+void get_page_bootmem(unsigned long info, struct page *page, unsigned long type)
+{
+	page->freelist = (void *)type;
+	SetPagePrivate(page);
+	set_page_private(page, info);
+	page_ref_inc(page);
+}
+
+void put_page_bootmem(struct page *page)
+{
+	unsigned long type;
+
+	type = (unsigned long) page->freelist;
+	BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
+	       type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE);
+
+	if (page_ref_dec_return(page) == 1) {
+		page->freelist = NULL;
+		ClearPagePrivate(page);
+		set_page_private(page, 0);
+		INIT_LIST_HEAD(&page->lru);
+		free_reserved_page(page);
+	}
+}
+
 #ifndef CONFIG_SPARSEMEM_VMEMMAP
 static void register_page_bootmem_info_section(unsigned long start_pfn)
 {
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 2da4ad071456..ae57eedc341f 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -21,7 +21,6 @@
 #include <linux/memory.h>
 #include <linux/memremap.h>
 #include <linux/memory_hotplug.h>
-#include <linux/bootmem_info.h>
 #include <linux/highmem.h>
 #include <linux/vmalloc.h>
 #include <linux/ioport.h>
@@ -142,32 +141,6 @@ static void release_memory_resource(struct resource *res)
 }
 
 #ifdef CONFIG_MEMORY_HOTPLUG_SPARSE
-void get_page_bootmem(unsigned long info,  struct page *page,
-		      unsigned long type)
-{
-	page->freelist = (void *)type;
-	SetPagePrivate(page);
-	set_page_private(page, info);
-	page_ref_inc(page);
-}
-
-void put_page_bootmem(struct page *page)
-{
-	unsigned long type;
-
-	type = (unsigned long) page->freelist;
-	BUG_ON(type < MEMORY_HOTPLUG_MIN_BOOTMEM_TYPE ||
-	       type > MEMORY_HOTPLUG_MAX_BOOTMEM_TYPE);
-
-	if (page_ref_dec_return(page) == 1) {
-		page->freelist = NULL;
-		ClearPagePrivate(page);
-		set_page_private(page, 0);
-		INIT_LIST_HEAD(&page->lru);
-		free_reserved_page(page);
-	}
-}
-
 static int check_pfn_span(unsigned long pfn, unsigned long nr_pages,
 		const char *reason)
 {
diff --git a/mm/sparse.c b/mm/sparse.c
index b25ad8e64839..a4138410d890 100644
--- a/mm/sparse.c
+++ b/mm/sparse.c
@@ -13,6 +13,7 @@
 #include <linux/vmalloc.h>
 #include <linux/swap.h>
 #include <linux/swapops.h>
+#include <linux/bootmem_info.h>
 
 #include "internal.h"
 #include <asm/dma.h>

From patchwork Tue Nov 24 09:52:46 2020
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
X-Patchwork-Submitter: Muchun Song <songmuchun@bytedance.com>
X-Patchwork-Id: 1344531
Return-Path: <linux-kernel-owner@kernel.org>
Received: from mail.kernel.org (mail.kernel.org [198.145.29.99])
	by smtp.lore.kernel.org (Postfix) with ESMTP id CFCC8C2D0E4
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:57:37 +0000 (UTC)
Received: from vger.kernel.org (vger.kernel.org [23.128.96.18])
	by mail.kernel.org (Postfix) with ESMTP id 74AFD2076B
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:57:37 +0000 (UTC)
Authentication-Results: mail.kernel.org;
	dkim=pass (2048-bit key) header.d=bytedance-com.20150623.gappssmtp.com
 header.i=@bytedance-com.20150623.gappssmtp.com header.b="Teew9Gvu"
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1731566AbgKXJ5R (ORCPT
        <rfc822;linux-kernel@archiver.kernel.org>);
        Tue, 24 Nov 2020 04:57:17 -0500
Received: from lindbergh.monkeyblade.net ([23.128.96.19]:57130 "EHLO
        lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1731321AbgKXJ5Q (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Tue, 24 Nov 2020 04:57:16 -0500
Received: from mail-pl1-x642.google.com (mail-pl1-x642.google.com
 [IPv6:2607:f8b0:4864:20::642])
        by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 68979C0617A6
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:57:15 -0800 (PST)
Received: by mail-pl1-x642.google.com with SMTP id u2so10423701pls.10
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:57:15 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=bytedance-com.20150623.gappssmtp.com; s=20150623;
        h=from:to:cc:subject:date:message-id:in-reply-to:references
         :mime-version:content-transfer-encoding;
        bh=s5A1WGxjr1FnragMjsAXSXENwZtbX/VCL9QpT/2OWj4=;
        b=Teew9GvubUfF7KXPZ0vrHLrrdljg0Jw0SHTS0miGJ+H6HSyJHNWx1gygUfRYCkCrw+
         EFlGXQHbhIpnw8VIJKvVn4N3/oQ/DX9sOoWurp6agSO9mb8j7HwAT5HTBnBH1IQVvsna
         fDeuYUqOhNQomskdJzjwkVHcasMWrx3FEUjTx3ntf1w2c+IiqrHinlQ3zoo6pFATvJ1G
         K45S4R7n1zZbkYNmNDSvo2Lc5p4+HIJ5CL1tSne7ARclcUu/D609C3ImDl6jiPGuS9ZX
         gXvkFgnL1TrHD1X2zyk+ZphWPFsdUlyNF1qz7TBA6lPcHVBeCqRT5PHJO4KwXbDrDI+v
         9u0A==
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=1e100.net; s=20161025;
        h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to
         :references:mime-version:content-transfer-encoding;
        bh=s5A1WGxjr1FnragMjsAXSXENwZtbX/VCL9QpT/2OWj4=;
        b=uUW1+pxfDyFTuxCawZpvmYkHEgDcjjSiWFi4zHVib0DWhMFNl0QIhvSPtz0rd+Vv2l
         FrTyLkSgK0NESYU8orb/USDAyGs2t6G0h0tM3YT6aoeuE1Z1O5hdlUwzzjnEMIr0tDvI
         dpIrp5xLaGKjovJKRRLE5tXrdG7kaTL4Bea6J1133qSbNpLWciqvJhRhVKudQFystPY7
         fF2yHm5WRX6vZnUc5yZ5RcU1zZumUV0e1d5Rag3E1blApfApHUwKpiU9xyKMRLQ0HEsn
         SRYiClrQPzRBLI+1f2B8IJk6T5t6LYcdLyZfPMJwLYzXktHCAGTd4eZHpZVjEJb9Qrqs
         wz8Q==
X-Gm-Message-State: AOAM530ka+rsGomc+6QCak8fzduQquEiRWSuep2qiPm1tAcmeVx2B/RJ
        yNEF1h3y8DwM2MDdg3ZUTCkYVA==
X-Google-Smtp-Source: 
 ABdhPJzwWHwqGMfwuSes+ofTOYpFZkuqkNbGuqv07A6D+lBpddBbGPWVNDBt6EKW68EcbG3uetJiWA==
X-Received: by 2002:a17:902:b192:b029:d7:ca4a:4ec1 with SMTP id
 s18-20020a170902b192b02900d7ca4a4ec1mr3406894plr.76.1606211834998;
        Tue, 24 Nov 2020 01:57:14 -0800 (PST)
Received: from localhost.localdomain ([103.136.220.120])
        by smtp.gmail.com with ESMTPSA id
 t20sm2424562pjg.25.2020.11.24.01.57.02
        (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128);
        Tue, 24 Nov 2020 01:57:14 -0800 (PST)
From: Muchun Song <songmuchun@bytedance.com>
To: corbet@lwn.net, mike.kravetz@oracle.com, tglx@linutronix.de,
        mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com,
        dave.hansen@linux.intel.com, luto@kernel.org, peterz@infradead.org,
        viro@zeniv.linux.org.uk, akpm@linux-foundation.org,
        paulmck@kernel.org, mchehab+huawei@kernel.org,
        pawan.kumar.gupta@linux.intel.com, rdunlap@infradead.org,
        oneukum@suse.com, anshuman.khandual@arm.com, jroedel@suse.de,
        almasrymina@google.com, rientjes@google.com, willy@infradead.org,
        osalvador@suse.de, mhocko@suse.com, song.bao.hua@hisilicon.com
Cc: duanxiongchun@bytedance.com, linux-doc@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        linux-fsdevel@vger.kernel.org,
        Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH v6 03/16] mm/hugetlb: Introduce a new config
 HUGETLB_PAGE_FREE_VMEMMAP
Date: Tue, 24 Nov 2020 17:52:46 +0800
Message-Id: <20201124095259.58755-4-songmuchun@bytedance.com>
X-Mailer: git-send-email 2.21.0 (Apple Git-122)
In-Reply-To: <20201124095259.58755-1-songmuchun@bytedance.com>
References: <20201124095259.58755-1-songmuchun@bytedance.com>
MIME-Version: 1.0
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

The purpose of introducing HUGETLB_PAGE_FREE_VMEMMAP is to configure
whether to enable the feature of freeing unused vmemmap associated
with HugeTLB pages. And this is just for dependency check. Now only
support x86.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 arch/x86/mm/init_64.c |  2 +-
 fs/Kconfig            | 14 ++++++++++++++
 2 files changed, 15 insertions(+), 1 deletion(-)

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 0a45f062826e..0435bee2e172 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1225,7 +1225,7 @@ static struct kcore_list kcore_vsyscall;
 
 static void __init register_page_bootmem_info(void)
 {
-#ifdef CONFIG_NUMA
+#if defined(CONFIG_NUMA) || defined(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP)
 	int i;
 
 	for_each_online_node(i)
diff --git a/fs/Kconfig b/fs/Kconfig
index 976e8b9033c4..4961dd488444 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -245,6 +245,20 @@ config HUGETLBFS
 config HUGETLB_PAGE
 	def_bool HUGETLBFS
 
+config HUGETLB_PAGE_FREE_VMEMMAP
+	def_bool HUGETLB_PAGE
+	depends on X86
+	depends on SPARSEMEM_VMEMMAP
+	depends on HAVE_BOOTMEM_INFO_NODE
+	help
+	  When using HUGETLB_PAGE_FREE_VMEMMAP, the system can save up some
+	  memory from pre-allocated HugeTLB pages when they are not used.
+	  6 pages per 2MB HugeTLB page and 4094 per 1GB HugeTLB page.
+
+	  When the pages are going to be used or freed up, the vmemmap array
+	  representing that range needs to be remapped again and the pages
+	  we discarded earlier need to be rellocated again.
+
 config MEMFD_CREATE
 	def_bool TMPFS || HUGETLBFS
 

From patchwork Tue Nov 24 09:52:47 2020
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
X-Patchwork-Submitter: Muchun Song <songmuchun@bytedance.com>
X-Patchwork-Id: 1344532
Return-Path: <linux-kernel-owner@kernel.org>
Received: from mail.kernel.org (mail.kernel.org [198.145.29.99])
	by smtp.lore.kernel.org (Postfix) with ESMTP id 9FD5CC64E7A
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:57:38 +0000 (UTC)
Received: from vger.kernel.org (vger.kernel.org [23.128.96.18])
	by mail.kernel.org (Postfix) with ESMTP id 432692076E
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:57:38 +0000 (UTC)
Authentication-Results: mail.kernel.org;
	dkim=pass (2048-bit key) header.d=bytedance-com.20150623.gappssmtp.com
 header.i=@bytedance-com.20150623.gappssmtp.com header.b="nB2biY17"
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1731624AbgKXJ51 (ORCPT
        <rfc822;linux-kernel@archiver.kernel.org>);
        Tue, 24 Nov 2020 04:57:27 -0500
Received: from lindbergh.monkeyblade.net ([23.128.96.19]:57162 "EHLO
        lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1731210AbgKXJ50 (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Tue, 24 Nov 2020 04:57:26 -0500
Received: from mail-pg1-x532.google.com (mail-pg1-x532.google.com
 [IPv6:2607:f8b0:4864:20::532])
        by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 390DAC0617A6
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:57:26 -0800 (PST)
Received: by mail-pg1-x532.google.com with SMTP id t37so16921666pga.7
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:57:26 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=bytedance-com.20150623.gappssmtp.com; s=20150623;
        h=from:to:cc:subject:date:message-id:in-reply-to:references
         :mime-version:content-transfer-encoding;
        bh=RMs53eG3LNPeSYWBw7UeJT//wAK2SKIhi0UahgCqvGo=;
        b=nB2biY17c1xHJJtyysg9/RdKIqh/WyRzZLTm27dFW9u5FnxjgtcNLn/45HQW3BzUIR
         9wHuN4gS2AYhLDDCALsU/mVlJ2GIHNiAFiSrovSnLrICF3OHSkuUTh4BFLH22+cksTwD
         1PgcWa2PTxXWvcrDQje0NQYCteS9oBQS7eqXHe8QPwWA3noro7qF0se2rPAuI0l4LOYc
         2seU1h2eFiD0dcKzuLIClZh9RA3DgYIwKdJ01w8ZZeUzB1T/6AxZ3xMWBG465OwznCBC
         uFNY5wD8H8IRg/nWgL1+Yc1Mpnb3kRtZzp1hRR9kw4cE6C1OFjZ68z+CSIgEQJMJuYpV
         Akng==
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=1e100.net; s=20161025;
        h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to
         :references:mime-version:content-transfer-encoding;
        bh=RMs53eG3LNPeSYWBw7UeJT//wAK2SKIhi0UahgCqvGo=;
        b=R8Oavyod6Me0eiTPyc44xy1koeTOjMuBKrgSx8uiz0C/8zC80g/uZdzczL4rauzr6N
         YOPmTy7W7yMOvx6+u30PnKUiXpGVceHFndnHPkkSf5imCSGw7JWVfhzTODs201v+ajh5
         7+72hirJlIaRSqsENVVjsh5fydFJM4M1f0Vxev75oAWHsc84tMvRUlYOXzakLn8pibKI
         GP30XcSLrem3HjS+mjuo4uF8CuBubs1mPbONUd8Vfqi2lZhHrt29KZoGrY/5CpGbfygp
         FO3HMJcuYTLfjIKSo7G2Xe6naAaFTagks6tlgPvSW3AnoK5UrHxHkQyKjBKkxy6Rs+HR
         JFiA==
X-Gm-Message-State: AOAM530o/cXKQV1uxcnBDyEY9C+H+QG0hD1E3sLvesE0Y7/r2ZoEhl1E
        6tDQNpwaHuqbwTjJBupQpIBzzQ==
X-Google-Smtp-Source: 
 ABdhPJz6R1rHuo8sewOYy6Re4ZKmMVZcLwxrF7DkD4k/dIylF9KTzobi1SpweTyz/dYGGlxFz545/g==
X-Received: by 2002:a17:90a:c214:: with SMTP id
 e20mr4147249pjt.212.1606211845770;
        Tue, 24 Nov 2020 01:57:25 -0800 (PST)
Received: from localhost.localdomain ([103.136.220.120])
        by smtp.gmail.com with ESMTPSA id
 t20sm2424562pjg.25.2020.11.24.01.57.15
        (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128);
        Tue, 24 Nov 2020 01:57:25 -0800 (PST)
From: Muchun Song <songmuchun@bytedance.com>
To: corbet@lwn.net, mike.kravetz@oracle.com, tglx@linutronix.de,
        mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com,
        dave.hansen@linux.intel.com, luto@kernel.org, peterz@infradead.org,
        viro@zeniv.linux.org.uk, akpm@linux-foundation.org,
        paulmck@kernel.org, mchehab+huawei@kernel.org,
        pawan.kumar.gupta@linux.intel.com, rdunlap@infradead.org,
        oneukum@suse.com, anshuman.khandual@arm.com, jroedel@suse.de,
        almasrymina@google.com, rientjes@google.com, willy@infradead.org,
        osalvador@suse.de, mhocko@suse.com, song.bao.hua@hisilicon.com
Cc: duanxiongchun@bytedance.com, linux-doc@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        linux-fsdevel@vger.kernel.org,
        Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH v6 04/16] mm/hugetlb: Introduce nr_free_vmemmap_pages in the
 struct hstate
Date: Tue, 24 Nov 2020 17:52:47 +0800
Message-Id: <20201124095259.58755-5-songmuchun@bytedance.com>
X-Mailer: git-send-email 2.21.0 (Apple Git-122)
In-Reply-To: <20201124095259.58755-1-songmuchun@bytedance.com>
References: <20201124095259.58755-1-songmuchun@bytedance.com>
MIME-Version: 1.0
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

Every HugeTLB has more than one struct page structure. The 2M HugeTLB
has 512 struct page structure and 1G HugeTLB has 4096 struct page
structures. We __know__ that we only use the first 4(HUGETLB_CGROUP_MIN_ORDER)
struct page structures to store metadata associated with each HugeTLB.

There are a lot of struct page structures(8 page frames for 2MB HugeTLB
page and 4096 page frames for 1GB HugeTLB page) associated with each
HugeTLB page. For tail pages, the value of compound_head is the same.
So we can reuse first page of tail page structures. We map the virtual
addresses of the remaining pages of tail page structures to the first
tail page struct, and then free these page frames. Therefore, we need
to reserve two pages as vmemmap areas.

So we introduce a new nr_free_vmemmap_pages field in the hstate to
indicate how many vmemmap pages associated with a HugeTLB page that we
can free to buddy system.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
Acked-by: Mike Kravetz <mike.kravetz@oracle.com>
---
 include/linux/hugetlb.h |   3 ++
 mm/Makefile             |   1 +
 mm/hugetlb.c            |   3 ++
 mm/hugetlb_vmemmap.c    | 129 ++++++++++++++++++++++++++++++++++++++++++++++++
 mm/hugetlb_vmemmap.h    |  20 ++++++++
 5 files changed, 156 insertions(+)
 create mode 100644 mm/hugetlb_vmemmap.c
 create mode 100644 mm/hugetlb_vmemmap.h

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d5cc5f802dd4..eed3dd3bd626 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -492,6 +492,9 @@ struct hstate {
 	unsigned int nr_huge_pages_node[MAX_NUMNODES];
 	unsigned int free_huge_pages_node[MAX_NUMNODES];
 	unsigned int surplus_huge_pages_node[MAX_NUMNODES];
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+	unsigned int nr_free_vmemmap_pages;
+#endif
 #ifdef CONFIG_CGROUP_HUGETLB
 	/* cgroup control files */
 	struct cftype cgroup_files_dfl[7];
diff --git a/mm/Makefile b/mm/Makefile
index 752111587c99..2a734576bbc0 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -71,6 +71,7 @@ obj-$(CONFIG_FRONTSWAP)	+= frontswap.o
 obj-$(CONFIG_ZSWAP)	+= zswap.o
 obj-$(CONFIG_HAS_DMA)	+= dmapool.o
 obj-$(CONFIG_HUGETLBFS)	+= hugetlb.o
+obj-$(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP)	+= hugetlb_vmemmap.o
 obj-$(CONFIG_NUMA) 	+= mempolicy.o
 obj-$(CONFIG_SPARSEMEM)	+= sparse.o
 obj-$(CONFIG_SPARSEMEM_VMEMMAP) += sparse-vmemmap.o
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 81a41aa080a5..f88032c24667 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -42,6 +42,7 @@
 #include <linux/userfaultfd_k.h>
 #include <linux/page_owner.h>
 #include "internal.h"
+#include "hugetlb_vmemmap.h"
 
 int hugetlb_max_hstate __read_mostly;
 unsigned int default_hstate_idx;
@@ -3285,6 +3286,8 @@ void __init hugetlb_add_hstate(unsigned int order)
 	snprintf(h->name, HSTATE_NAME_LEN, "hugepages-%lukB",
 					huge_page_size(h)/1024);
 
+	hugetlb_vmemmap_init(h);
+
 	parsed_hstate = h;
 }
 
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
new file mode 100644
index 000000000000..fad760483e01
--- /dev/null
+++ b/mm/hugetlb_vmemmap.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Free some vmemmap pages of HugeTLB
+ *
+ * Copyright (c) 2020, Bytedance. All rights reserved.
+ *
+ *     Author: Muchun Song <songmuchun@bytedance.com>
+ *
+ * The struct page structures (page structs) are used to describe a physical
+ * page frame. By default, there is a one-to-one mapping from a page frame to
+ * it's corresponding page struct.
+ *
+ * The HugeTLB pages consist of multiple base page size pages and is supported
+ * by many architectures. See hugetlbpage.rst in the Documentation directory
+ * for more details. On the x86 architecture, HugeTLB pages of size 2MB and 1GB
+ * are currently supported. Since the base page size on x86 is 4KB, a 2MB
+ * HugeTLB page consists of 512 base pages and a 1GB HugeTLB page consists of
+ * 4096 base pages. For each base page, there is a corresponding page struct.
+ *
+ * Within the HugeTLB subsystem, only the first 4 page structs are used to
+ * contain unique information about a HugeTLB page. HUGETLB_CGROUP_MIN_ORDER
+ * provides this upper limit. The only 'useful' information in the remaining
+ * page structs is the compound_head field, and this field is the same for all
+ * tail pages.
+ *
+ * By removing redundant page structs for HugeTLB pages, memory can returned to
+ * the buddy allocator for other uses.
+ *
+ * When the system boot up, every 2M HugeTLB has 512 struct page structs which
+ * size is 8 pages(sizeof(struct page) * 512 / PAGE_SIZE).
+ *
+ *    HugeTLB                  struct pages(8 pages)         page frame(8 pages)
+ * +-----------+ ---virt_to_page---> +-----------+   mapping to   +-----------+
+ * |           |                     |     0     | -------------> |     0     |
+ * |           |                     +-----------+                +-----------+
+ * |           |                     |     1     | -------------> |     1     |
+ * |           |                     +-----------+                +-----------+
+ * |           |                     |     2     | -------------> |     2     |
+ * |           |                     +-----------+                +-----------+
+ * |           |                     |     3     | -------------> |     3     |
+ * |           |                     +-----------+                +-----------+
+ * |           |                     |     4     | -------------> |     4     |
+ * |    2MB    |                     +-----------+                +-----------+
+ * |           |                     |     5     | -------------> |     5     |
+ * |           |                     +-----------+                +-----------+
+ * |           |                     |     6     | -------------> |     6     |
+ * |           |                     +-----------+                +-----------+
+ * |           |                     |     7     | -------------> |     7     |
+ * |           |                     +-----------+                +-----------+
+ * |           |
+ * |           |
+ * |           |
+ * +-----------+
+ *
+ * The value of page->compound_head is the same for all tail pages. The first
+ * page of page structs (page 0) associated with the HugeTLB page contains the 4
+ * page structs necessary to describe the HugeTLB. The only use of the remaining
+ * pages of page structs (page 1 to page 7) is to point to page->compound_head.
+ * Therefore, we can remap pages 2 to 7 to page 1. Only 2 pages of page structs
+ * will be used for each HugeTLB page. This will allow us to free the remaining
+ * 6 pages to the buddy allocator.
+ *
+ * Here is how things look after remapping.
+ *
+ *    HugeTLB                  struct pages(8 pages)         page frame(8 pages)
+ * +-----------+ ---virt_to_page---> +-----------+   mapping to   +-----------+
+ * |           |                     |     0     | -------------> |     0     |
+ * |           |                     +-----------+                +-----------+
+ * |           |                     |     1     | -------------> |     1     |
+ * |           |                     +-----------+                +-----------+
+ * |           |                     |     2     | ----------------^ ^ ^ ^ ^ ^
+ * |           |                     +-----------+                   | | | | |
+ * |           |                     |     3     | ------------------+ | | | |
+ * |           |                     +-----------+                     | | | |
+ * |           |                     |     4     | --------------------+ | | |
+ * |    2MB    |                     +-----------+                       | | |
+ * |           |                     |     5     | ----------------------+ | |
+ * |           |                     +-----------+                         | |
+ * |           |                     |     6     | ------------------------+ |
+ * |           |                     +-----------+                           |
+ * |           |                     |     7     | --------------------------+
+ * |           |                     +-----------+
+ * |           |
+ * |           |
+ * |           |
+ * +-----------+
+ *
+ * When a HugeTLB is freed to the buddy system, we should allocate 6 pages for
+ * vmemmap pages and restore the previous mapping relationship.
+ *
+ * Apart from 2MB HugeTLB page, we also have 1GB HugeTLB page. It is similar
+ * to the 2MB HugeTLB page. We also can use this approach to free the vmemmap
+ * pages.
+ */
+#define pr_fmt(fmt)	"HugeTLB Vmemmap: " fmt
+
+#include "hugetlb_vmemmap.h"
+
+/*
+ * There are a lot of struct page structures(8 page frames for 2MB HugeTLB page
+ * and 4096 page frames for 1GB HugeTLB page) associated with each HugeTLB page.
+ * For tail pages, the value of compound_head is the same. So we can reuse first
+ * page of tail page structures. We map the virtual addresses of the remaining
+ * pages of tail page structures to the first tail page struct, and then free
+ * these page frames. Therefore, we need to reserve two pages as vmemmap areas.
+ */
+#define RESERVE_VMEMMAP_NR		2U
+
+void __init hugetlb_vmemmap_init(struct hstate *h)
+{
+	unsigned int order = huge_page_order(h);
+	unsigned int vmemmap_pages;
+
+	vmemmap_pages = ((1 << order) * sizeof(struct page)) >> PAGE_SHIFT;
+	/*
+	 * The head page and the first tail page are not to be freed to buddy
+	 * system, the others page will map to the first tail page. So there
+	 * are the remaining pages that can be freed.
+	 *
+	 * Could RESERVE_VMEMMAP_NR be greater than @vmemmap_pages? This is
+	 * not expected to happen unless the system is corrupted. So on the
+	 * safe side, it is only a safety net.
+	 */
+	if (likely(vmemmap_pages > RESERVE_VMEMMAP_NR))
+		h->nr_free_vmemmap_pages = vmemmap_pages - RESERVE_VMEMMAP_NR;
+
+	pr_debug("can free %d vmemmap pages for %s\n", h->nr_free_vmemmap_pages,
+		 h->name);
+}
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
new file mode 100644
index 000000000000..40c0c7dfb60d
--- /dev/null
+++ b/mm/hugetlb_vmemmap.h
@@ -0,0 +1,20 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Free some vmemmap pages of HugeTLB
+ *
+ * Copyright (c) 2020, Bytedance. All rights reserved.
+ *
+ *     Author: Muchun Song <songmuchun@bytedance.com>
+ */
+#ifndef _LINUX_HUGETLB_VMEMMAP_H
+#define _LINUX_HUGETLB_VMEMMAP_H
+#include <linux/hugetlb.h>
+
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+void __init hugetlb_vmemmap_init(struct hstate *h);
+#else
+static inline void hugetlb_vmemmap_init(struct hstate *h)
+{
+}
+#endif /* CONFIG_HUGETLB_PAGE_FREE_VMEMMAP */
+#endif /* _LINUX_HUGETLB_VMEMMAP_H */

From patchwork Tue Nov 24 09:52:48 2020
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
X-Patchwork-Submitter: Muchun Song <songmuchun@bytedance.com>
X-Patchwork-Id: 1344533
Return-Path: <linux-kernel-owner@kernel.org>
Received: from mail.kernel.org (mail.kernel.org [198.145.29.99])
	by smtp.lore.kernel.org (Postfix) with ESMTP id 636A0C64E7B
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:57:39 +0000 (UTC)
Received: from vger.kernel.org (vger.kernel.org [23.128.96.18])
	by mail.kernel.org (Postfix) with ESMTP id 0A52B2076B
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:57:38 +0000 (UTC)
Authentication-Results: mail.kernel.org;
	dkim=pass (2048-bit key) header.d=bytedance-com.20150623.gappssmtp.com
 header.i=@bytedance-com.20150623.gappssmtp.com header.b="XLegzWPa"
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1731641AbgKXJ5h (ORCPT
        <rfc822;linux-kernel@archiver.kernel.org>);
        Tue, 24 Nov 2020 04:57:37 -0500
Received: from lindbergh.monkeyblade.net ([23.128.96.19]:57200 "EHLO
        lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1731628AbgKXJ5g (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Tue, 24 Nov 2020 04:57:36 -0500
Received: from mail-pl1-x641.google.com (mail-pl1-x641.google.com
 [IPv6:2607:f8b0:4864:20::641])
        by lindbergh.monkeyblade.net (Postfix) with ESMTPS id AC6B5C061A4D
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:57:36 -0800 (PST)
Received: by mail-pl1-x641.google.com with SMTP id k5so3994148plt.6
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:57:36 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=bytedance-com.20150623.gappssmtp.com; s=20150623;
        h=from:to:cc:subject:date:message-id:in-reply-to:references
         :mime-version:content-transfer-encoding;
        bh=9VN22FTK/cp8gibu50+JlwycxClP9nhjODvnGGV4tug=;
        b=XLegzWPaw4syhictcJDtdO8UlkWiQesAIDyjezsiGhWLYuWMqEXoinK2ALJ8vmvQSZ
         BvUt+1LFjXIBzla2PEW+QARNYV9h7cyU9JD1U2M1q36WdZQk3IUrcFT19L7vp4lT8DMq
         BZUyc42SDVQmpNFqRg7Tdjw1YHFvUTpN8afa+VvcqJHp7Yk4E1ogM+NIkAPfiOs29t0K
         qkYlWJblARlDVzKPsJTzyqtP7URpFQRJ244SGxw3ExqgNtZdWk6qWjkA+cz01UAE8jjW
         c+HeVQYFmzstVWSkSGecvWrwt3U7ILbmZGi2kEA5YajcZKL8YGfmIginV+jTZ3Cl1i3N
         4esw==
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=1e100.net; s=20161025;
        h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to
         :references:mime-version:content-transfer-encoding;
        bh=9VN22FTK/cp8gibu50+JlwycxClP9nhjODvnGGV4tug=;
        b=gUmSlRaCi+M9s8fhyV7RVuIBhjdaWfgulQ6af/gyfp3wF158WaXZnwY/tetJfaBJqq
         tupScD/BrUE9AUcuLqqEb55PkaAQMU0hS00CiKPZmsIGScs9AcgeyhL+7mU19BMUK0Pu
         nR36MO4BNcv3epn6xUI0ME7lAP3EGPQl0Fa+GfAV9g79DfmuE2Te7+48LuQUNMUFLyS0
         Sb2XNepOdN2TO2N3dCELKxKV8TS1945xFdBSWKc4LPvQGUJvbh0a0k3FuBz5Eeq6577c
         7TkjkkqcBfkwp6dJR0WmEh81VvwvCIFhKeIOQxZ4N4xBoVCrmObs1NH+O4CbBuG001Uu
         WAGw==
X-Gm-Message-State: AOAM531WDePh7ErssKdwCjmeRKFmYeWDFLpCji4X3iqNwu8DetpcyuJY
        cW3IP2uyqvysLRjlqOjYT+3n+g==
X-Google-Smtp-Source: 
 ABdhPJzkfWmZzIezFc+/XShwSpl+HYDK87BrOmp7V7j23AYWeRgU/oTmRV9QXDo9TveCXF8djbdG6Q==
X-Received: by 2002:a17:902:6949:b029:da:17d0:d10f with SMTP id
 k9-20020a1709026949b02900da17d0d10fmr3322210plt.71.1606211856275;
        Tue, 24 Nov 2020 01:57:36 -0800 (PST)
Received: from localhost.localdomain ([103.136.220.120])
        by smtp.gmail.com with ESMTPSA id
 t20sm2424562pjg.25.2020.11.24.01.57.26
        (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128);
        Tue, 24 Nov 2020 01:57:35 -0800 (PST)
From: Muchun Song <songmuchun@bytedance.com>
To: corbet@lwn.net, mike.kravetz@oracle.com, tglx@linutronix.de,
        mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com,
        dave.hansen@linux.intel.com, luto@kernel.org, peterz@infradead.org,
        viro@zeniv.linux.org.uk, akpm@linux-foundation.org,
        paulmck@kernel.org, mchehab+huawei@kernel.org,
        pawan.kumar.gupta@linux.intel.com, rdunlap@infradead.org,
        oneukum@suse.com, anshuman.khandual@arm.com, jroedel@suse.de,
        almasrymina@google.com, rientjes@google.com, willy@infradead.org,
        osalvador@suse.de, mhocko@suse.com, song.bao.hua@hisilicon.com
Cc: duanxiongchun@bytedance.com, linux-doc@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        linux-fsdevel@vger.kernel.org,
        Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH v6 05/16] mm/bootmem_info: Introduce
 {free,prepare}_vmemmap_page()
Date: Tue, 24 Nov 2020 17:52:48 +0800
Message-Id: <20201124095259.58755-6-songmuchun@bytedance.com>
X-Mailer: git-send-email 2.21.0 (Apple Git-122)
In-Reply-To: <20201124095259.58755-1-songmuchun@bytedance.com>
References: <20201124095259.58755-1-songmuchun@bytedance.com>
MIME-Version: 1.0
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

In the later patch, we can use the free_vmemmap_page() to free the
unused vmemmap pages and initialize a page for vmemmap page using
via prepare_vmemmap_page().

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 include/linux/bootmem_info.h | 24 ++++++++++++++++++++++++
 1 file changed, 24 insertions(+)

diff --git a/include/linux/bootmem_info.h b/include/linux/bootmem_info.h
index 4ed6dee1adc9..239e3cc8f86c 100644
--- a/include/linux/bootmem_info.h
+++ b/include/linux/bootmem_info.h
@@ -3,6 +3,7 @@
 #define __LINUX_BOOTMEM_INFO_H
 
 #include <linux/mmzone.h>
+#include <linux/mm.h>
 
 /*
  * Types for free bootmem stored in page->lru.next. These have to be in
@@ -22,6 +23,29 @@ void __init register_page_bootmem_info_node(struct pglist_data *pgdat);
 void get_page_bootmem(unsigned long info, struct page *page,
 		      unsigned long type);
 void put_page_bootmem(struct page *page);
+
+static inline void free_vmemmap_page(struct page *page)
+{
+	VM_WARN_ON(!PageReserved(page) || page_ref_count(page) != 2);
+
+	/* bootmem page has reserved flag in the reserve_bootmem_region */
+	if (PageReserved(page)) {
+		unsigned long magic = (unsigned long)page->freelist;
+
+		if (magic == SECTION_INFO || magic == MIX_SECTION_INFO)
+			put_page_bootmem(page);
+		else
+			WARN_ON(1);
+	}
+}
+
+static inline void prepare_vmemmap_page(struct page *page)
+{
+	unsigned long section_nr = pfn_to_section_nr(page_to_pfn(page));
+
+	get_page_bootmem(section_nr, page, SECTION_INFO);
+	mark_page_reserved(page);
+}
 #else
 static inline void register_page_bootmem_info_node(struct pglist_data *pgdat)
 {

From patchwork Tue Nov 24 09:52:49 2020
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
X-Patchwork-Submitter: Muchun Song <songmuchun@bytedance.com>
X-Patchwork-Id: 1344534
Return-Path: <linux-kernel-owner@kernel.org>
Received: from mail.kernel.org (mail.kernel.org [198.145.29.99])
	by smtp.lore.kernel.org (Postfix) with ESMTP id 28112C63798
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:58:18 +0000 (UTC)
Received: from vger.kernel.org (vger.kernel.org [23.128.96.18])
	by mail.kernel.org (Postfix) with ESMTP id D4FC520637
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:58:17 +0000 (UTC)
Authentication-Results: mail.kernel.org;
	dkim=pass (2048-bit key) header.d=bytedance-com.20150623.gappssmtp.com
 header.i=@bytedance-com.20150623.gappssmtp.com header.b="tIraSHcG"
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1731657AbgKXJ5s (ORCPT
        <rfc822;linux-kernel@archiver.kernel.org>);
        Tue, 24 Nov 2020 04:57:48 -0500
Received: from lindbergh.monkeyblade.net ([23.128.96.19]:57230 "EHLO
        lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1731643AbgKXJ5s (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Tue, 24 Nov 2020 04:57:48 -0500
Received: from mail-pg1-x542.google.com (mail-pg1-x542.google.com
 [IPv6:2607:f8b0:4864:20::542])
        by lindbergh.monkeyblade.net (Postfix) with ESMTPS id CB7EBC061A4D
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:57:46 -0800 (PST)
Received: by mail-pg1-x542.google.com with SMTP id w4so16974221pgg.13
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:57:46 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=bytedance-com.20150623.gappssmtp.com; s=20150623;
        h=from:to:cc:subject:date:message-id:in-reply-to:references
         :mime-version:content-transfer-encoding;
        bh=wHH3/jV+QgVymFROaAhyfWbEGBmLguB5hGi6rHX+6Xk=;
        b=tIraSHcGfsyLsDtWBE3f6AbmDLC7hMtycXi3qi3o3exCsJUurK5k90ln0isM5Drjro
         DB3XS0aPqP3k6MAuAEVkri+xicJsmaoBVJ6XcZdWf8bJSsOSZ+4lKenrLm+w/1Hl8vqf
         tOk3a9jGCBOgRSLz+QSj9jE2Cn6cwR3NOsMBDXeJjikoBRbZqjJTCH/zd9viZZRoNDeN
         KbNVk81Mtl72BMRuaz22/mNFA91Rf2fvN2O6zk32JPUzAltYH9HoWnvWrsY96Hb5ULYA
         mHCgOqrC+bIuwKv1R0RntDu8DmcEb0G2EVW6bSQp02sUOQyIxIFHjEe++uDDOc5ZkbBd
         YtRA==
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=1e100.net; s=20161025;
        h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to
         :references:mime-version:content-transfer-encoding;
        bh=wHH3/jV+QgVymFROaAhyfWbEGBmLguB5hGi6rHX+6Xk=;
        b=ouY52xD7M3qr+UBcKl2sVrxqfgEv1K8tsAfMjg3K0Y1DnD9SkssqtWOzJOOtXGuUZP
         ui73H2Ieyy7UGBVGRksAuX3X52ecvaqzoQq+KyYVPt4NWolAgdYAfAzBFmw0Kqx6sT3g
         iep6vn6n6n34PgfJopPDXF5wdC3wyytUqwqzYUCNRiY10djqPjTf5h65m36PtzNlT5ap
         H7RXajocBzsKjOH5hyWKkjrNctQ/i2bBm93T6aM5Zyexuaz06vtON+xJZq82v9U1J3qX
         OJwXBt69aSU8vmAJlVzxJhHBQ06X8ieN0MKlXzBt/l7Q9lz6ZK8vaOqnQi8VwQxPuBKb
         EgVQ==
X-Gm-Message-State: AOAM5323TuGVVEsVYafYeJoEBJKTcM2V7cSNT0ODpRbr9f++iZV0Sn3w
        8hkXB/DvKNzNGolI24E8aThdDQ==
X-Google-Smtp-Source: 
 ABdhPJysdofJSVH3w1/BPgZk3TLFnf6hemKsSPCvyi4+CmocLeKlIa0h4pckqN8WwHQ4tU+2hvxHEQ==
X-Received: by 2002:a62:2a81:0:b029:18c:310f:74fe with SMTP id
 q123-20020a622a810000b029018c310f74femr3356086pfq.50.1606211866326;
        Tue, 24 Nov 2020 01:57:46 -0800 (PST)
Received: from localhost.localdomain ([103.136.220.120])
        by smtp.gmail.com with ESMTPSA id
 t20sm2424562pjg.25.2020.11.24.01.57.36
        (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128);
        Tue, 24 Nov 2020 01:57:45 -0800 (PST)
From: Muchun Song <songmuchun@bytedance.com>
To: corbet@lwn.net, mike.kravetz@oracle.com, tglx@linutronix.de,
        mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com,
        dave.hansen@linux.intel.com, luto@kernel.org, peterz@infradead.org,
        viro@zeniv.linux.org.uk, akpm@linux-foundation.org,
        paulmck@kernel.org, mchehab+huawei@kernel.org,
        pawan.kumar.gupta@linux.intel.com, rdunlap@infradead.org,
        oneukum@suse.com, anshuman.khandual@arm.com, jroedel@suse.de,
        almasrymina@google.com, rientjes@google.com, willy@infradead.org,
        osalvador@suse.de, mhocko@suse.com, song.bao.hua@hisilicon.com
Cc: duanxiongchun@bytedance.com, linux-doc@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        linux-fsdevel@vger.kernel.org,
        Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH v6 06/16] mm/hugetlb: Disable freeing vmemmap if struct page
 size is not power of two
Date: Tue, 24 Nov 2020 17:52:49 +0800
Message-Id: <20201124095259.58755-7-songmuchun@bytedance.com>
X-Mailer: git-send-email 2.21.0 (Apple Git-122)
In-Reply-To: <20201124095259.58755-1-songmuchun@bytedance.com>
References: <20201124095259.58755-1-songmuchun@bytedance.com>
MIME-Version: 1.0
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

We only can free the tail vmemmap pages of HugeTLB to the buddy allocator
when the size of struct page is a power of two.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 mm/hugetlb_vmemmap.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index fad760483e01..fd60cfdf3d40 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -111,6 +111,11 @@ void __init hugetlb_vmemmap_init(struct hstate *h)
 	unsigned int order = huge_page_order(h);
 	unsigned int vmemmap_pages;
 
+	if (!is_power_of_2(sizeof(struct page))) {
+		pr_info("disable freeing vmemmap pages for %s\n", h->name);
+		return;
+	}
+
 	vmemmap_pages = ((1 << order) * sizeof(struct page)) >> PAGE_SHIFT;
 	/*
 	 * The head page and the first tail page are not to be freed to buddy

From patchwork Tue Nov 24 09:52:50 2020
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
X-Patchwork-Submitter: Muchun Song <songmuchun@bytedance.com>
X-Patchwork-Id: 1344535
Return-Path: <linux-kernel-owner@kernel.org>
Received: from mail.kernel.org (mail.kernel.org [198.145.29.99])
	by smtp.lore.kernel.org (Postfix) with ESMTP id 04474C64E7B
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:58:19 +0000 (UTC)
Received: from vger.kernel.org (vger.kernel.org [23.128.96.18])
	by mail.kernel.org (Postfix) with ESMTP id A53372076B
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:58:18 +0000 (UTC)
Authentication-Results: mail.kernel.org;
	dkim=pass (2048-bit key) header.d=bytedance-com.20150623.gappssmtp.com
 header.i=@bytedance-com.20150623.gappssmtp.com header.b="B7s2QSZd"
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1731700AbgKXJ56 (ORCPT
        <rfc822;linux-kernel@archiver.kernel.org>);
        Tue, 24 Nov 2020 04:57:58 -0500
Received: from lindbergh.monkeyblade.net ([23.128.96.19]:57262 "EHLO
        lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1731643AbgKXJ54 (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Tue, 24 Nov 2020 04:57:56 -0500
Received: from mail-pg1-x544.google.com (mail-pg1-x544.google.com
 [IPv6:2607:f8b0:4864:20::544])
        by lindbergh.monkeyblade.net (Postfix) with ESMTPS id C3374C061A4D
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:57:56 -0800 (PST)
Received: by mail-pg1-x544.google.com with SMTP id v21so17024789pgi.2
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:57:56 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=bytedance-com.20150623.gappssmtp.com; s=20150623;
        h=from:to:cc:subject:date:message-id:in-reply-to:references
         :mime-version:content-transfer-encoding;
        bh=oSUrQajIlhHrZQJhWJQy1InopKyNlwdkkxQ0BvZwQN0=;
        b=B7s2QSZdwKs6D656MgfnkoLqCCJ2k2pYSfIOnNWNNwqAEh9uEpIuiX6LDtbE178WrC
         jjuUSq3hI3hM9sGyUKnOwI2f/d9Q40hQClsq9HYgFoO3ChJdL6Qx7I6vsp2nbvr1gRts
         qcBkPfLQu3qC95KdnFaki+XdTFWPz/K1bW75zQR8DP+pwj+gpuQifRbQCErRjYqaOurf
         KXWOnmuvUSM50zWK0gtccC3PATob4pad+REin14akFJ0RKcNtv2Fap12YEtyFV5pE4bc
         jwRhZFLQOH/bxopGPWardMumil0DeJldoqEwMI4vR86WvTDOOwS4e5JZPH+pDNUxWuEv
         wO0g==
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=1e100.net; s=20161025;
        h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to
         :references:mime-version:content-transfer-encoding;
        bh=oSUrQajIlhHrZQJhWJQy1InopKyNlwdkkxQ0BvZwQN0=;
        b=VX2IDi6ercnTxA8pHQrM/WQVTsMDqAXUPDo9phHVpoJvpFgMzVemd9UhU4vbByKQaY
         rS9Gi5WglopNrHIrG2wxhvvviSKt+v8/RtF0M5zTSI8sku9/FrFC39wrn+oSqcO34HLG
         U8PZGp1XrzDv0vGtEbCalc+suob0PWjKa79THuy8vU1exVawFj7R2h4fG2LtEGPSnRhq
         QH/z2C3Kxnr+/MFzB/D/7pCYrDdnVcTqkfTkGfbVK3kmPn5H7DiUAIKHjy3Jw7lFvcVk
         WZMWMvRC7i8SGFT9L3DQnvxDVsRh9GxMNEpZZYGXED+tNDdhK1c0TB4dTuTRSQx8LHEe
         klcw==
X-Gm-Message-State: AOAM533+S+nQyDM+EKoAHVa2OuceIiO2dnkVtVR4LjEYfFM+q9n1Tjy0
        k0jTopYtk4lTqdRrpDpXnr1hxg==
X-Google-Smtp-Source: 
 ABdhPJyMrb78F1w9ZubIENSfiY4yzl9F3+dQeY4OKhrOsOuJH8YxUhUghcDgoJFYUmMbp5zY3YWt3A==
X-Received: by 2002:a17:90a:f406:: with SMTP id
 ch6mr3827991pjb.134.1606211876417;
        Tue, 24 Nov 2020 01:57:56 -0800 (PST)
Received: from localhost.localdomain ([103.136.220.120])
        by smtp.gmail.com with ESMTPSA id
 t20sm2424562pjg.25.2020.11.24.01.57.46
        (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128);
        Tue, 24 Nov 2020 01:57:55 -0800 (PST)
From: Muchun Song <songmuchun@bytedance.com>
To: corbet@lwn.net, mike.kravetz@oracle.com, tglx@linutronix.de,
        mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com,
        dave.hansen@linux.intel.com, luto@kernel.org, peterz@infradead.org,
        viro@zeniv.linux.org.uk, akpm@linux-foundation.org,
        paulmck@kernel.org, mchehab+huawei@kernel.org,
        pawan.kumar.gupta@linux.intel.com, rdunlap@infradead.org,
        oneukum@suse.com, anshuman.khandual@arm.com, jroedel@suse.de,
        almasrymina@google.com, rientjes@google.com, willy@infradead.org,
        osalvador@suse.de, mhocko@suse.com, song.bao.hua@hisilicon.com
Cc: duanxiongchun@bytedance.com, linux-doc@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        linux-fsdevel@vger.kernel.org,
        Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH v6 07/16] x86/mm/64: Disable PMD page mapping of vmemmap
Date: Tue, 24 Nov 2020 17:52:50 +0800
Message-Id: <20201124095259.58755-8-songmuchun@bytedance.com>
X-Mailer: git-send-email 2.21.0 (Apple Git-122)
In-Reply-To: <20201124095259.58755-1-songmuchun@bytedance.com>
References: <20201124095259.58755-1-songmuchun@bytedance.com>
MIME-Version: 1.0
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

If we enable the CONFIG_HUGETLB_PAGE_FREE_VMEMMAP, we can just
disbale PMD page mapping of vmemmap to simplify the code. In this
case, we do not need complex code doing vmemmap page table
manipulation. This is a way to simply the first version of this
patch series. In the future, we can add some code doing page table
manipulation.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 arch/x86/mm/init_64.c | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 0435bee2e172..155cb06a6961 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -1557,7 +1557,9 @@ int __meminit vmemmap_populate(unsigned long start, unsigned long end, int node,
 {
 	int err;
 
-	if (end - start < PAGES_PER_SECTION * sizeof(struct page))
+	if (IS_ENABLED(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP))
+		err = vmemmap_populate_basepages(start, end, node, NULL);
+	else if (end - start < PAGES_PER_SECTION * sizeof(struct page))
 		err = vmemmap_populate_basepages(start, end, node, NULL);
 	else if (boot_cpu_has(X86_FEATURE_PSE))
 		err = vmemmap_populate_hugepages(start, end, node, altmap);
@@ -1610,7 +1612,8 @@ void register_page_bootmem_memmap(unsigned long section_nr,
 		}
 		get_page_bootmem(section_nr, pud_page(*pud), MIX_SECTION_INFO);
 
-		if (!boot_cpu_has(X86_FEATURE_PSE)) {
+		if (!boot_cpu_has(X86_FEATURE_PSE) ||
+		    IS_ENABLED(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP)) {
 			next = (addr + PAGE_SIZE) & PAGE_MASK;
 			pmd = pmd_offset(pud, addr);
 			if (pmd_none(*pmd))

From patchwork Tue Nov 24 09:52:51 2020
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
X-Patchwork-Submitter: Muchun Song <songmuchun@bytedance.com>
X-Patchwork-Id: 1344537
Return-Path: <linux-kernel-owner@kernel.org>
Received: from mail.kernel.org (mail.kernel.org [198.145.29.99])
	by smtp.lore.kernel.org (Postfix) with ESMTP id 49931C56201
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:58:20 +0000 (UTC)
Received: from vger.kernel.org (vger.kernel.org [23.128.96.18])
	by mail.kernel.org (Postfix) with ESMTP id DD9B120637
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:58:19 +0000 (UTC)
Authentication-Results: mail.kernel.org;
	dkim=pass (2048-bit key) header.d=bytedance-com.20150623.gappssmtp.com
 header.i=@bytedance-com.20150623.gappssmtp.com header.b="FwWSJi2c"
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1731715AbgKXJ6I (ORCPT
        <rfc822;linux-kernel@archiver.kernel.org>);
        Tue, 24 Nov 2020 04:58:08 -0500
Received: from lindbergh.monkeyblade.net ([23.128.96.19]:57296 "EHLO
        lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1731706AbgKXJ6H (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Tue, 24 Nov 2020 04:58:07 -0500
Received: from mail-pf1-x443.google.com (mail-pf1-x443.google.com
 [IPv6:2607:f8b0:4864:20::443])
        by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 39FEFC061A4D
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:58:07 -0800 (PST)
Received: by mail-pf1-x443.google.com with SMTP id b6so7547877pfp.7
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:58:07 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=bytedance-com.20150623.gappssmtp.com; s=20150623;
        h=from:to:cc:subject:date:message-id:in-reply-to:references
         :mime-version:content-transfer-encoding;
        bh=BbFCNgyPE8nizGGDJDZBGUHg6UO+mJRBaj4BfE6x8So=;
        b=FwWSJi2cHVLIvbiOkLH6oUoM/YtuKQ9XtRGesAdYMI8WK/9ZQRRLTsMwEun+e1dW4R
         WJf3KMSYagwqAkOJl39z+uBWiCKjtOVdYqd84WGW33xAGCtWyyZ2MZhj6ghdETJ5mX9W
         pk+kX0lq3SP2kWM2s9gwaHeBiQtgXFDcMw4o+CygYAAuqpgs1ZY+czuXaEoAnUX7ob8x
         0ldPerB5AR0kLOKkKWUacv2367EhY1Wp1ejTVHv9/y31UF1L6b2arv+hIs4WcRP8FpDG
         WRmEK1V0zzx4XPrAM9G0UE8kTphJnNhaheePBt+e/IPjR7xKioUsJnKUfFwtm9y6vAJT
         JtTg==
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=1e100.net; s=20161025;
        h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to
         :references:mime-version:content-transfer-encoding;
        bh=BbFCNgyPE8nizGGDJDZBGUHg6UO+mJRBaj4BfE6x8So=;
        b=e6Fs5i6xygmyAenlMJ0moPpcvyfh31jqzqISTanDp4Cuzi8MrSs6VuhxSzoYLoHv+o
         hUg0pOnOjHS/SoG/VWKwTHUvof6MpXYsZwaKDeUQRrVC6rNyBgaT7wMQX9Bk3qPJWcDg
         c3xMrvCXnG66GtZkwY+VULpKkJgRAOUXY+28kC4c96EJfPtMHLCq0Sim44UI3IP6Hdk+
         wVR3eQSGYVTmhiNFg2fT1WnjIioTccZeb3If6T+rAWWC8/VFXoff7mpaoFFbggUhvWNa
         TP9+a1ugRrm2JBBJJIRGpNi6wDIviFAMQYTGm8y7OEFiFlL2+sEYhsSQrM9KaW/vONHY
         YIEw==
X-Gm-Message-State: AOAM530ST3zgrGzXe0GEEqj/OMkiHz3fAJr+IH8wQx8xrx5xTHDLFq+p
        dkt5l1DgIfcVRRQW/iL9G7vKXw==
X-Google-Smtp-Source: 
 ABdhPJwX9HQ0VjDIqeOVrfmO9iIZzoKa4yniFwFtNwTWpg2A7NszkjO8GLva5IH0THXOXslntQZcCQ==
X-Received: by 2002:a17:90a:fd0e:: with SMTP id
 cv14mr3877515pjb.182.1606211886807;
        Tue, 24 Nov 2020 01:58:06 -0800 (PST)
Received: from localhost.localdomain ([103.136.220.120])
        by smtp.gmail.com with ESMTPSA id
 t20sm2424562pjg.25.2020.11.24.01.57.56
        (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128);
        Tue, 24 Nov 2020 01:58:06 -0800 (PST)
From: Muchun Song <songmuchun@bytedance.com>
To: corbet@lwn.net, mike.kravetz@oracle.com, tglx@linutronix.de,
        mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com,
        dave.hansen@linux.intel.com, luto@kernel.org, peterz@infradead.org,
        viro@zeniv.linux.org.uk, akpm@linux-foundation.org,
        paulmck@kernel.org, mchehab+huawei@kernel.org,
        pawan.kumar.gupta@linux.intel.com, rdunlap@infradead.org,
        oneukum@suse.com, anshuman.khandual@arm.com, jroedel@suse.de,
        almasrymina@google.com, rientjes@google.com, willy@infradead.org,
        osalvador@suse.de, mhocko@suse.com, song.bao.hua@hisilicon.com
Cc: duanxiongchun@bytedance.com, linux-doc@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        linux-fsdevel@vger.kernel.org,
        Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH v6 08/16] mm/hugetlb: Free the vmemmap pages associated with
 each hugetlb page
Date: Tue, 24 Nov 2020 17:52:51 +0800
Message-Id: <20201124095259.58755-9-songmuchun@bytedance.com>
X-Mailer: git-send-email 2.21.0 (Apple Git-122)
In-Reply-To: <20201124095259.58755-1-songmuchun@bytedance.com>
References: <20201124095259.58755-1-songmuchun@bytedance.com>
MIME-Version: 1.0
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

When we allocate a hugetlb page from the buddy, we should free the
unused vmemmap pages associated with it. We can do that in the
prep_new_huge_page().

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 arch/x86/include/asm/pgtable_64_types.h |   8 ++
 mm/hugetlb.c                            |   2 +
 mm/hugetlb_vmemmap.c                    | 133 +++++++++++++++++++++++++++++++-
 mm/hugetlb_vmemmap.h                    |   5 ++
 4 files changed, 147 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 52e5f5f2240d..bedbd2e7d06c 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -139,6 +139,14 @@ extern unsigned int ptrs_per_p4d;
 # define VMEMMAP_START		__VMEMMAP_BASE_L4
 #endif /* CONFIG_DYNAMIC_MEMORY_LAYOUT */
 
+/*
+ * VMEMMAP_SIZE - allows the whole linear region to be covered by
+ *                a struct page array.
+ */
+#define VMEMMAP_SIZE		(1UL << (__VIRTUAL_MASK_SHIFT - PAGE_SHIFT - \
+					 1 + ilog2(sizeof(struct page))))
+#define VMEMMAP_END		(VMEMMAP_START + VMEMMAP_SIZE)
+
 #define VMALLOC_END		(VMALLOC_START + (VMALLOC_SIZE_TB << 40) - 1)
 
 #define MODULES_VADDR		(__START_KERNEL_map + KERNEL_IMAGE_SIZE)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index f88032c24667..9662b5535f3a 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1499,6 +1499,8 @@ void free_huge_page(struct page *page)
 
 static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
 {
+	free_huge_page_vmemmap(h, page);
+
 	INIT_LIST_HEAD(&page->lru);
 	set_compound_page_dtor(page, HUGETLB_PAGE_DTOR);
 	set_hugetlb_cgroup(page, NULL);
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index fd60cfdf3d40..1576f69bd1d3 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -92,8 +92,9 @@
  * to the 2MB HugeTLB page. We also can use this approach to free the vmemmap
  * pages.
  */
-#define pr_fmt(fmt)	"HugeTLB Vmemmap: " fmt
+#define pr_fmt(fmt)	"HugeTLB vmemmap: " fmt
 
+#include <linux/bootmem_info.h>
 #include "hugetlb_vmemmap.h"
 
 /*
@@ -105,6 +106,136 @@
  * these page frames. Therefore, we need to reserve two pages as vmemmap areas.
  */
 #define RESERVE_VMEMMAP_NR		2U
+#define RESERVE_VMEMMAP_SIZE		(RESERVE_VMEMMAP_NR << PAGE_SHIFT)
+#define TAIL_PAGE_REUSE			-1
+
+#ifndef VMEMMAP_HPAGE_SHIFT
+#define VMEMMAP_HPAGE_SHIFT		HPAGE_SHIFT
+#endif
+#define VMEMMAP_HPAGE_ORDER		(VMEMMAP_HPAGE_SHIFT - PAGE_SHIFT)
+#define VMEMMAP_HPAGE_NR		(1 << VMEMMAP_HPAGE_ORDER)
+#define VMEMMAP_HPAGE_SIZE		((1UL) << VMEMMAP_HPAGE_SHIFT)
+#define VMEMMAP_HPAGE_MASK		(~(VMEMMAP_HPAGE_SIZE - 1))
+
+#define vmemmap_hpage_addr_end(addr, end)				 \
+({									 \
+	unsigned long __boundary;					 \
+	__boundary = ((addr) + VMEMMAP_HPAGE_SIZE) & VMEMMAP_HPAGE_MASK; \
+	(__boundary - 1 < (end) - 1) ? __boundary : (end);		 \
+})
+
+static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
+{
+	return h->nr_free_vmemmap_pages;
+}
+
+static inline unsigned int vmemmap_pages_per_hpage(struct hstate *h)
+{
+	return free_vmemmap_pages_per_hpage(h) + RESERVE_VMEMMAP_NR;
+}
+
+static inline unsigned long vmemmap_pages_size_per_hpage(struct hstate *h)
+{
+	return (unsigned long)vmemmap_pages_per_hpage(h) << PAGE_SHIFT;
+}
+
+/*
+ * Walk a vmemmap address to the pmd it maps.
+ */
+static pmd_t *vmemmap_to_pmd(unsigned long page)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+
+	if (page < VMEMMAP_START || page >= VMEMMAP_END)
+		return NULL;
+
+	pgd = pgd_offset_k(page);
+	if (pgd_none(*pgd))
+		return NULL;
+	p4d = p4d_offset(pgd, page);
+	if (p4d_none(*p4d))
+		return NULL;
+	pud = pud_offset(p4d, page);
+	if (pud_none(*pud) || pud_bad(*pud))
+		return NULL;
+
+	return pmd_offset(pud, page);
+}
+
+static inline void free_vmemmap_page_list(struct list_head *list)
+{
+	struct page *page, *next;
+
+	list_for_each_entry_safe(page, next, list, lru) {
+		list_del(&page->lru);
+		free_vmemmap_page(page);
+	}
+}
+
+static void __free_huge_page_pte_vmemmap(struct page *reuse, pte_t *ptep,
+					 unsigned long start,
+					 unsigned long end,
+					 struct list_head *free_pages)
+{
+	/* Make the tail pages are mapped read-only. */
+	pgprot_t pgprot = PAGE_KERNEL_RO;
+	pte_t entry = mk_pte(reuse, pgprot);
+	unsigned long addr;
+
+	for (addr = start; addr < end; addr += PAGE_SIZE, ptep++) {
+		struct page *page;
+		pte_t old = *ptep;
+
+		VM_WARN_ON(!pte_present(old));
+		page = pte_page(old);
+		list_add(&page->lru, free_pages);
+
+		set_pte_at(&init_mm, addr, ptep, entry);
+	}
+}
+
+static void __free_huge_page_pmd_vmemmap(pmd_t *pmd, unsigned long start,
+					 unsigned long end,
+					 struct list_head *vmemmap_pages)
+{
+	unsigned long next, addr = start;
+	struct page *reuse = NULL;
+
+	do {
+		pte_t *ptep;
+
+		ptep = pte_offset_kernel(pmd, addr);
+		if (!reuse)
+			reuse = pte_page(ptep[TAIL_PAGE_REUSE]);
+
+		next = vmemmap_hpage_addr_end(addr, end);
+		__free_huge_page_pte_vmemmap(reuse, ptep, addr, next,
+					     vmemmap_pages);
+	} while (pmd++, addr = next, addr != end);
+
+	flush_tlb_kernel_range(start, end);
+}
+
+void free_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+	pmd_t *pmd;
+	unsigned long start, end;
+	unsigned long vmemmap_addr = (unsigned long)head;
+	LIST_HEAD(free_pages);
+
+	if (!free_vmemmap_pages_per_hpage(h))
+		return;
+
+	pmd = vmemmap_to_pmd(vmemmap_addr);
+	BUG_ON(!pmd);
+
+	start = vmemmap_addr + RESERVE_VMEMMAP_SIZE;
+	end = vmemmap_addr + vmemmap_pages_size_per_hpage(h);
+	__free_huge_page_pmd_vmemmap(pmd, start, end, &free_pages);
+	free_vmemmap_page_list(&free_pages);
+}
 
 void __init hugetlb_vmemmap_init(struct hstate *h)
 {
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index 40c0c7dfb60d..67113b67495f 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -12,9 +12,14 @@
 
 #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
 void __init hugetlb_vmemmap_init(struct hstate *h);
+void free_huge_page_vmemmap(struct hstate *h, struct page *head);
 #else
 static inline void hugetlb_vmemmap_init(struct hstate *h)
 {
 }
+
+static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+}
 #endif /* CONFIG_HUGETLB_PAGE_FREE_VMEMMAP */
 #endif /* _LINUX_HUGETLB_VMEMMAP_H */

From patchwork Tue Nov 24 09:52:52 2020
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
X-Patchwork-Submitter: Muchun Song <songmuchun@bytedance.com>
X-Patchwork-Id: 1344536
Return-Path: <linux-kernel-owner@kernel.org>
Received: from mail.kernel.org (mail.kernel.org [198.145.29.99])
	by smtp.lore.kernel.org (Postfix) with ESMTP id 6DE54C71156
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:58:20 +0000 (UTC)
Received: from vger.kernel.org (vger.kernel.org [23.128.96.18])
	by mail.kernel.org (Postfix) with ESMTP id 254EE20857
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:58:20 +0000 (UTC)
Authentication-Results: mail.kernel.org;
	dkim=pass (2048-bit key) header.d=bytedance-com.20150623.gappssmtp.com
 header.i=@bytedance-com.20150623.gappssmtp.com header.b="QuTKi5Le"
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1731730AbgKXJ6S (ORCPT
        <rfc822;linux-kernel@archiver.kernel.org>);
        Tue, 24 Nov 2020 04:58:18 -0500
Received: from lindbergh.monkeyblade.net ([23.128.96.19]:57324 "EHLO
        lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1731717AbgKXJ6R (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Tue, 24 Nov 2020 04:58:17 -0500
Received: from mail-pg1-x543.google.com (mail-pg1-x543.google.com
 [IPv6:2607:f8b0:4864:20::543])
        by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 9160DC0613D6
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:58:17 -0800 (PST)
Received: by mail-pg1-x543.google.com with SMTP id t3so3157674pgi.11
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:58:17 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=bytedance-com.20150623.gappssmtp.com; s=20150623;
        h=from:to:cc:subject:date:message-id:in-reply-to:references
         :mime-version:content-transfer-encoding;
        bh=Lo85sr+ys6lf1U70qdtLk1A2yy6l0L87SOY5IKt+Rqg=;
        b=QuTKi5LeFc78ApnwKtQnKFpGpAFaDKYR2SPEUmVWgj/4ZUR2v9AJyfuVW5WVruRFoN
         FEET+MlGGH2GJqOaxPwIghe/UnIRZSlhrKcvxotqSlPEoiKkQ6MzkI+7L799Zttov95a
         5ESstlLDRvECWy8oer4helYMUoiejTAZVivERzLIA4DIoXk12ZgRh9AESBhUU58mm+Tq
         MQ1vggCT8xvopG0hkJahoUzZu+i1zc6KIeJytn1q0RbymNBA6QjVrr+uAxAVTyaQQPYw
         kMmaMQ0RVA4b4TdaTAvyE1uPbdrl5KaLcfZZIduwUOj+rlzVO1MuKKmzrPYebm1E8B8G
         GAow==
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=1e100.net; s=20161025;
        h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to
         :references:mime-version:content-transfer-encoding;
        bh=Lo85sr+ys6lf1U70qdtLk1A2yy6l0L87SOY5IKt+Rqg=;
        b=h0dnMmYrNSMN/gEUwZFTAx/DGh1zKLKIEoNZKSxu6kvwvX3NcNM1pbJXnyBhxc/skz
         kPZ854vuYdlkVcHzFu9mbXNbowVKqFhXcC0Ff9/oReQVReRHqR/WQTiTqPRfPvBoWXwp
         Np6aDTyCbzYPeJ3npmkGVX9T2qIp0/t5v/JpIoNH/cnkXqDJaR+USYmYIJ8Ffr1yBB/9
         eG3fNgp6bpBuoT4iwmMgmj54VOVT0RN8bZnhc/MWe3FT0hQF0tpfLaH5/eo4lq9WLSav
         XcpuJ55El8CZLwihtYDutTq+XNRfe165zqdlRQydjYyfVoN5pyQ4Rds0/R41/VCBfz+V
         iDfA==
X-Gm-Message-State: AOAM5321Tps51c460mV42TzBCh0REZgG1/DdKUtWi5uHA5W4+LVh8tRa
        t7ilTMVqUxcRNVj0vhyJzp7gWQ==
X-Google-Smtp-Source: 
 ABdhPJyAtKbJcYyB5s0iPG+oh91QP+h3kDFCwvnUvcYufL0PAPrifyoMdxkl3ZhCw8GYFXaszwlw9g==
X-Received: by 2002:a62:f20e:0:b029:197:f6d8:8d4d with SMTP id
 m14-20020a62f20e0000b0290197f6d88d4dmr3405377pfh.58.1606211897122;
        Tue, 24 Nov 2020 01:58:17 -0800 (PST)
Received: from localhost.localdomain ([103.136.220.120])
        by smtp.gmail.com with ESMTPSA id
 t20sm2424562pjg.25.2020.11.24.01.58.07
        (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128);
        Tue, 24 Nov 2020 01:58:16 -0800 (PST)
From: Muchun Song <songmuchun@bytedance.com>
To: corbet@lwn.net, mike.kravetz@oracle.com, tglx@linutronix.de,
        mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com,
        dave.hansen@linux.intel.com, luto@kernel.org, peterz@infradead.org,
        viro@zeniv.linux.org.uk, akpm@linux-foundation.org,
        paulmck@kernel.org, mchehab+huawei@kernel.org,
        pawan.kumar.gupta@linux.intel.com, rdunlap@infradead.org,
        oneukum@suse.com, anshuman.khandual@arm.com, jroedel@suse.de,
        almasrymina@google.com, rientjes@google.com, willy@infradead.org,
        osalvador@suse.de, mhocko@suse.com, song.bao.hua@hisilicon.com
Cc: duanxiongchun@bytedance.com, linux-doc@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        linux-fsdevel@vger.kernel.org,
        Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH v6 09/16] mm/hugetlb: Defer freeing of HugeTLB pages
Date: Tue, 24 Nov 2020 17:52:52 +0800
Message-Id: <20201124095259.58755-10-songmuchun@bytedance.com>
X-Mailer: git-send-email 2.21.0 (Apple Git-122)
In-Reply-To: <20201124095259.58755-1-songmuchun@bytedance.com>
References: <20201124095259.58755-1-songmuchun@bytedance.com>
MIME-Version: 1.0
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

In the subsequent patch, we will allocate the vmemmap pages when free
HugeTLB pages. But update_and_free_page() is called from a non-task
context(and hold hugetlb_lock), so we can defer the actual freeing in
a workqueue to prevent use GFP_ATOMIC to allocate the vmemmap pages.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 mm/hugetlb.c         | 96 ++++++++++++++++++++++++++++++++++++++++++++++------
 mm/hugetlb_vmemmap.c |  5 ---
 mm/hugetlb_vmemmap.h | 10 ++++++
 3 files changed, 95 insertions(+), 16 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 9662b5535f3a..41056b4230f1 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1221,7 +1221,7 @@ static void destroy_compound_gigantic_page(struct page *page,
 	__ClearPageHead(page);
 }
 
-static void free_gigantic_page(struct page *page, unsigned int order)
+static void __free_gigantic_page(struct page *page, unsigned int order)
 {
 	/*
 	 * If the page isn't allocated using the cma allocator,
@@ -1288,20 +1288,100 @@ static struct page *alloc_gigantic_page(struct hstate *h, gfp_t gfp_mask,
 {
 	return NULL;
 }
-static inline void free_gigantic_page(struct page *page, unsigned int order) { }
+static inline void __free_gigantic_page(struct page *page,
+					unsigned int order) { }
 static inline void destroy_compound_gigantic_page(struct page *page,
 						unsigned int order) { }
 #endif
 
-static void update_and_free_page(struct hstate *h, struct page *page)
+static void __free_hugepage(struct hstate *h, struct page *page);
+
+/*
+ * As update_and_free_page() is be called from a non-task context(and hold
+ * hugetlb_lock), we can defer the actual freeing in a workqueue to prevent
+ * use GFP_ATOMIC to allocate a lot of vmemmap pages.
+ *
+ * update_hpage_vmemmap_workfn() locklessly retrieves the linked list of
+ * pages to be freed and frees them one-by-one. As the page->mapping pointer
+ * is going to be cleared in update_hpage_vmemmap_workfn() anyway, it is
+ * reused as the llist_node structure of a lockless linked list of huge
+ * pages to be freed.
+ */
+static LLIST_HEAD(hpage_update_freelist);
+
+static void update_hpage_vmemmap_workfn(struct work_struct *work)
 {
-	int i;
+	struct llist_node *node;
+	struct page *page;
+
+	node = llist_del_all(&hpage_update_freelist);
+
+	while (node) {
+		page = container_of((struct address_space **)node,
+				     struct page, mapping);
+		node = node->next;
+		page->mapping = NULL;
+		__free_hugepage(page_hstate(page), page);
 
+		cond_resched();
+	}
+}
+static DECLARE_WORK(hpage_update_work, update_hpage_vmemmap_workfn);
+
+static inline void __update_and_free_page(struct hstate *h, struct page *page)
+{
+	/* No need to allocate vmemmap pages */
+	if (!free_vmemmap_pages_per_hpage(h)) {
+		__free_hugepage(h, page);
+		return;
+	}
+
+	/*
+	 * Defer freeing to avoid using GFP_ATOMIC to allocate vmemmap
+	 * pages.
+	 *
+	 * Only call schedule_work() if hpage_update_freelist is previously
+	 * empty. Otherwise, schedule_work() had been called but the workfn
+	 * hasn't retrieved the list yet.
+	 */
+	if (llist_add((struct llist_node *)&page->mapping,
+		      &hpage_update_freelist))
+		schedule_work(&hpage_update_work);
+}
+
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+static inline void free_gigantic_page(struct hstate *h, struct page *page)
+{
+	__free_gigantic_page(page, huge_page_order(h));
+}
+#else
+static inline void free_gigantic_page(struct hstate *h, struct page *page)
+{
+	/*
+	 * Temporarily drop the hugetlb_lock, because
+	 * we might block in __free_gigantic_page().
+	 */
+	spin_unlock(&hugetlb_lock);
+	__free_gigantic_page(page, huge_page_order(h));
+	spin_lock(&hugetlb_lock);
+}
+#endif
+
+static void update_and_free_page(struct hstate *h, struct page *page)
+{
 	if (hstate_is_gigantic(h) && !gigantic_page_runtime_supported())
 		return;
 
 	h->nr_huge_pages--;
 	h->nr_huge_pages_node[page_to_nid(page)]--;
+
+	__update_and_free_page(h, page);
+}
+
+static void __free_hugepage(struct hstate *h, struct page *page)
+{
+	int i;
+
 	for (i = 0; i < pages_per_huge_page(h); i++) {
 		page[i].flags &= ~(1 << PG_locked | 1 << PG_error |
 				1 << PG_referenced | 1 << PG_dirty |
@@ -1313,14 +1393,8 @@ static void update_and_free_page(struct hstate *h, struct page *page)
 	set_compound_page_dtor(page, NULL_COMPOUND_DTOR);
 	set_page_refcounted(page);
 	if (hstate_is_gigantic(h)) {
-		/*
-		 * Temporarily drop the hugetlb_lock, because
-		 * we might block in free_gigantic_page().
-		 */
-		spin_unlock(&hugetlb_lock);
 		destroy_compound_gigantic_page(page, huge_page_order(h));
-		free_gigantic_page(page, huge_page_order(h));
-		spin_lock(&hugetlb_lock);
+		free_gigantic_page(h, page);
 	} else {
 		__free_pages(page, huge_page_order(h));
 	}
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 1576f69bd1d3..f6ba288966d4 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -124,11 +124,6 @@
 	(__boundary - 1 < (end) - 1) ? __boundary : (end);		 \
 })
 
-static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
-{
-	return h->nr_free_vmemmap_pages;
-}
-
 static inline unsigned int vmemmap_pages_per_hpage(struct hstate *h)
 {
 	return free_vmemmap_pages_per_hpage(h) + RESERVE_VMEMMAP_NR;
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index 67113b67495f..293897b9f1d8 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -13,6 +13,11 @@
 #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
 void __init hugetlb_vmemmap_init(struct hstate *h);
 void free_huge_page_vmemmap(struct hstate *h, struct page *head);
+
+static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
+{
+	return h->nr_free_vmemmap_pages;
+}
 #else
 static inline void hugetlb_vmemmap_init(struct hstate *h)
 {
@@ -21,5 +26,10 @@ static inline void hugetlb_vmemmap_init(struct hstate *h)
 static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 {
 }
+
+static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
+{
+	return 0;
+}
 #endif /* CONFIG_HUGETLB_PAGE_FREE_VMEMMAP */
 #endif /* _LINUX_HUGETLB_VMEMMAP_H */

From patchwork Tue Nov 24 09:52:53 2020
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
X-Patchwork-Submitter: Muchun Song <songmuchun@bytedance.com>
X-Patchwork-Id: 1344538
Return-Path: <linux-kernel-owner@kernel.org>
Received: from mail.kernel.org (mail.kernel.org [198.145.29.99])
	by smtp.lore.kernel.org (Postfix) with ESMTP id C6556C56202
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:59:10 +0000 (UTC)
Received: from vger.kernel.org (vger.kernel.org [23.128.96.18])
	by mail.kernel.org (Postfix) with ESMTP id 836A22076E
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:59:10 +0000 (UTC)
Authentication-Results: mail.kernel.org;
	dkim=pass (2048-bit key) header.d=bytedance-com.20150623.gappssmtp.com
 header.i=@bytedance-com.20150623.gappssmtp.com header.b="Gm0mjZUZ"
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1731743AbgKXJ6a (ORCPT
        <rfc822;linux-kernel@archiver.kernel.org>);
        Tue, 24 Nov 2020 04:58:30 -0500
Received: from lindbergh.monkeyblade.net ([23.128.96.19]:57354 "EHLO
        lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1731727AbgKXJ63 (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Tue, 24 Nov 2020 04:58:29 -0500
Received: from mail-pf1-x441.google.com (mail-pf1-x441.google.com
 [IPv6:2607:f8b0:4864:20::441])
        by lindbergh.monkeyblade.net (Postfix) with ESMTPS id AE682C0613D6
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:58:27 -0800 (PST)
Received: by mail-pf1-x441.google.com with SMTP id n137so7960779pfd.3
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:58:27 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=bytedance-com.20150623.gappssmtp.com; s=20150623;
        h=from:to:cc:subject:date:message-id:in-reply-to:references
         :mime-version:content-transfer-encoding;
        bh=JpttDQ3+UpRWFZGIokSg/wUkYwNYHQgTk6UVKoBkeLU=;
        b=Gm0mjZUZo7zA0izrHNveruNSQpbuz5ojd5lRvjZkLwR0sKbaTIRLwKpZEXmqd+1d81
         5e1PHD0YUicJwnVh/wuHh4JiLhY1/A627ofFS8cxdsQjeMpmX03OkJ3aGK9MrbfrDDkK
         lvWchEmQh6eOTBP6pl2QPC+E7TbtkEfWPGdQotIQhNG2uOdY4dJNN4vfam6//Wmnf/wa
         DC0Rk6sE/dIvBxNyAP1PxoSnIReJQdF+9Ctxl1NVTVYnbckZYmXhQP7DFe0imgIl0Dly
         d6Z9Qn8jYZawRcSKTjHPRhawGY0J/UKmsv0bJrw9kkQe3dMZlD7iuOi49kzFGgxFlDv9
         yXmA==
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=1e100.net; s=20161025;
        h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to
         :references:mime-version:content-transfer-encoding;
        bh=JpttDQ3+UpRWFZGIokSg/wUkYwNYHQgTk6UVKoBkeLU=;
        b=MuQUadkPQYYhoO3O8nLs+vWOr4bUN91OmirGA1m8QeyYVNp0ZIgzAUo7nbHXtziuZk
         AiScRMJ8W+r7ez1EAn3m/hB2Tj9ouitStdIh2UmxnI1Q2uOCPv3UUjlNWp4HO1OfF7NQ
         K5XXjfP0XYGCYGSl5yZUH51NygBbTz7yYBa4p/NNjj9QBgrATeUCHYtHgtiiITt7OD5z
         bqi7Mv9LS6BPTpLHRjBS0IGOmXJmLGbeWYji+xJfj5l501fG2ZQhhIJzEfxpJ0b+Ruyg
         s3H8bytFNeKs9KuXNT+eJXCQHT0a8ApvS/yjFUdlVT7dKrmR7vSOPnObhCG7hXZRTuCP
         o+Zw==
X-Gm-Message-State: AOAM533aScXUlX9Kwi14Yfgp/DQUWdK65/uj31eOc+xpCpX8NX5XlZVS
        TMwc1a6LzfY37rDX7vdxqdIimQ==
X-Google-Smtp-Source: 
 ABdhPJz3kRh7lpNK/DAxol80hx9LY0gJYD6O17ncIwy1kSZ2WnppJR53a574t27X7WEHzvtZF0+IHg==
X-Received: by 2002:a17:90a:4283:: with SMTP id
 p3mr4150189pjg.174.1606211907222;
        Tue, 24 Nov 2020 01:58:27 -0800 (PST)
Received: from localhost.localdomain ([103.136.220.120])
        by smtp.gmail.com with ESMTPSA id
 t20sm2424562pjg.25.2020.11.24.01.58.17
        (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128);
        Tue, 24 Nov 2020 01:58:26 -0800 (PST)
From: Muchun Song <songmuchun@bytedance.com>
To: corbet@lwn.net, mike.kravetz@oracle.com, tglx@linutronix.de,
        mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com,
        dave.hansen@linux.intel.com, luto@kernel.org, peterz@infradead.org,
        viro@zeniv.linux.org.uk, akpm@linux-foundation.org,
        paulmck@kernel.org, mchehab+huawei@kernel.org,
        pawan.kumar.gupta@linux.intel.com, rdunlap@infradead.org,
        oneukum@suse.com, anshuman.khandual@arm.com, jroedel@suse.de,
        almasrymina@google.com, rientjes@google.com, willy@infradead.org,
        osalvador@suse.de, mhocko@suse.com, song.bao.hua@hisilicon.com
Cc: duanxiongchun@bytedance.com, linux-doc@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        linux-fsdevel@vger.kernel.org,
        Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH v6 10/16] mm/hugetlb: Allocate the vmemmap pages associated
 with each hugetlb page
Date: Tue, 24 Nov 2020 17:52:53 +0800
Message-Id: <20201124095259.58755-11-songmuchun@bytedance.com>
X-Mailer: git-send-email 2.21.0 (Apple Git-122)
In-Reply-To: <20201124095259.58755-1-songmuchun@bytedance.com>
References: <20201124095259.58755-1-songmuchun@bytedance.com>
MIME-Version: 1.0
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

When we free a hugetlb page to the buddy, we should allocate the vmemmap
pages associated with it. We can do that in the __free_hugepage().

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 mm/hugetlb.c         |   2 +
 mm/hugetlb_vmemmap.c | 102 +++++++++++++++++++++++++++++++++++++++++++++++++++
 mm/hugetlb_vmemmap.h |   5 +++
 3 files changed, 109 insertions(+)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 41056b4230f1..3fafa39fcac6 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1382,6 +1382,8 @@ static void __free_hugepage(struct hstate *h, struct page *page)
 {
 	int i;
 
+	alloc_huge_page_vmemmap(h, page);
+
 	for (i = 0; i < pages_per_huge_page(h); i++) {
 		page[i].flags &= ~(1 << PG_locked | 1 << PG_error |
 				1 << PG_referenced | 1 << PG_dirty |
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index f6ba288966d4..d6a1b06c1322 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -95,6 +95,7 @@
 #define pr_fmt(fmt)	"HugeTLB vmemmap: " fmt
 
 #include <linux/bootmem_info.h>
+#include <linux/delay.h>
 #include "hugetlb_vmemmap.h"
 
 /*
@@ -108,6 +109,8 @@
 #define RESERVE_VMEMMAP_NR		2U
 #define RESERVE_VMEMMAP_SIZE		(RESERVE_VMEMMAP_NR << PAGE_SHIFT)
 #define TAIL_PAGE_REUSE			-1
+#define GFP_VMEMMAP_PAGE		\
+	(GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_HIGH)
 
 #ifndef VMEMMAP_HPAGE_SHIFT
 #define VMEMMAP_HPAGE_SHIFT		HPAGE_SHIFT
@@ -159,6 +162,105 @@ static pmd_t *vmemmap_to_pmd(unsigned long page)
 	return pmd_offset(pud, page);
 }
 
+static void __remap_huge_page_pte_vmemmap(struct page *reuse, pte_t *ptep,
+					  unsigned long start,
+					  unsigned long end,
+					  struct list_head *remap_pages)
+{
+	pgprot_t pgprot = PAGE_KERNEL;
+	void *from = page_to_virt(reuse);
+	unsigned long addr;
+
+	for (addr = start; addr < end; addr += PAGE_SIZE) {
+		void *to;
+		struct page *page;
+		pte_t entry, old = *ptep;
+
+		page = list_first_entry(remap_pages, struct page, lru);
+		list_del(&page->lru);
+		to = page_to_virt(page);
+		copy_page(to, from);
+
+		/*
+		 * Make sure that any data that writes to the @to is made
+		 * visible to the physical page.
+		 */
+		flush_kernel_vmap_range(to, PAGE_SIZE);
+
+		prepare_vmemmap_page(page);
+
+		entry = mk_pte(page, pgprot);
+		set_pte_at(&init_mm, addr, ptep++, entry);
+
+		VM_BUG_ON(!pte_present(old) || pte_page(old) != reuse);
+	}
+}
+
+static void __remap_huge_page_pmd_vmemmap(pmd_t *pmd, unsigned long start,
+					  unsigned long end,
+					  struct list_head *vmemmap_pages)
+{
+	unsigned long next, addr = start;
+	struct page *reuse = NULL;
+
+	do {
+		pte_t *ptep;
+
+		ptep = pte_offset_kernel(pmd, addr);
+		if (!reuse)
+			reuse = pte_page(ptep[TAIL_PAGE_REUSE]);
+
+		next = vmemmap_hpage_addr_end(addr, end);
+		__remap_huge_page_pte_vmemmap(reuse, ptep, addr, next,
+					      vmemmap_pages);
+	} while (pmd++, addr = next, addr != end);
+
+	flush_tlb_kernel_range(start, end);
+}
+
+static inline void alloc_vmemmap_pages(struct hstate *h, struct list_head *list)
+{
+	unsigned int nr = free_vmemmap_pages_per_hpage(h);
+
+	while (nr--) {
+		struct page *page;
+
+retry:
+		page = alloc_page(GFP_VMEMMAP_PAGE);
+		if (unlikely(!page)) {
+			msleep(100);
+			/*
+			 * We should retry infinitely, because we cannot
+			 * handle allocation failures. Once we allocate
+			 * vmemmap pages successfully, then we can free
+			 * a HugeTLB page.
+			 */
+			goto retry;
+		}
+		list_add_tail(&page->lru, list);
+	}
+}
+
+void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+	pmd_t *pmd;
+	unsigned long start, end;
+	unsigned long vmemmap_addr = (unsigned long)head;
+	LIST_HEAD(map_pages);
+
+	if (!free_vmemmap_pages_per_hpage(h))
+		return;
+
+	alloc_vmemmap_pages(h, &map_pages);
+
+	pmd = vmemmap_to_pmd(vmemmap_addr);
+	BUG_ON(!pmd);
+
+	start = vmemmap_addr + RESERVE_VMEMMAP_SIZE;
+	end = vmemmap_addr + vmemmap_pages_size_per_hpage(h);
+	__remap_huge_page_pmd_vmemmap(pmd, start, end, &map_pages);
+}
+
 static inline void free_vmemmap_page_list(struct list_head *list)
 {
 	struct page *page, *next;
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index 293897b9f1d8..7887095488f4 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -12,6 +12,7 @@
 
 #ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
 void __init hugetlb_vmemmap_init(struct hstate *h);
+void alloc_huge_page_vmemmap(struct hstate *h, struct page *head);
 void free_huge_page_vmemmap(struct hstate *h, struct page *head);
 
 static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
@@ -23,6 +24,10 @@ static inline void hugetlb_vmemmap_init(struct hstate *h)
 {
 }
 
+static inline void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+}
+
 static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 {
 }

From patchwork Tue Nov 24 09:52:54 2020
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
X-Patchwork-Submitter: Muchun Song <songmuchun@bytedance.com>
X-Patchwork-Id: 1344539
Return-Path: <linux-kernel-owner@kernel.org>
Received: from mail.kernel.org (mail.kernel.org [198.145.29.99])
	by smtp.lore.kernel.org (Postfix) with ESMTP id 8656AC64E7B
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:59:11 +0000 (UTC)
Received: from vger.kernel.org (vger.kernel.org [23.128.96.18])
	by mail.kernel.org (Postfix) with ESMTP id 455E720637
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:59:11 +0000 (UTC)
Authentication-Results: mail.kernel.org;
	dkim=pass (2048-bit key) header.d=bytedance-com.20150623.gappssmtp.com
 header.i=@bytedance-com.20150623.gappssmtp.com header.b="XDYX4dXd"
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1731754AbgKXJ6k (ORCPT
        <rfc822;linux-kernel@archiver.kernel.org>);
        Tue, 24 Nov 2020 04:58:40 -0500
Received: from lindbergh.monkeyblade.net ([23.128.96.19]:57392 "EHLO
        lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1731207AbgKXJ6j (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Tue, 24 Nov 2020 04:58:39 -0500
Received: from mail-pf1-x443.google.com (mail-pf1-x443.google.com
 [IPv6:2607:f8b0:4864:20::443])
        by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 38ED4C061A4D
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:58:38 -0800 (PST)
Received: by mail-pf1-x443.google.com with SMTP id b63so17970408pfg.12
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:58:38 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=bytedance-com.20150623.gappssmtp.com; s=20150623;
        h=from:to:cc:subject:date:message-id:in-reply-to:references
         :mime-version:content-transfer-encoding;
        bh=ZFwyQlsscT2RBnxHWArfuTVJVgRwj0xOpsgIKb91Ge0=;
        b=XDYX4dXdNWF3Fzn1dtGBYeifCfGEgb75fiQL65NrdLEisMD4Yjgdvk+N3BLItujm2a
         5JfBNhqze5ZmKNgmb89doGH/AVnWBc3oYcTwUB6v9/vBFfJ+eGIGaXWtcCtPNocKonY2
         kf0Pe5l2R4v/U84HUg8jxCoLkeTAsG9C5UtfLckgc3/SHCik32CyJ9ErPu/2B2AeXp4B
         37/TibIqva5tDvTnGJQ/Z26Box1IlLx/ZpK1cfdoD4kyV4mfV+Y2JmlmdIqDhize0RU1
         lABC0IrCkGG5KdoT+6mSWOtT9BbVzcXez3Iupgxa9K82Kav6b5abq0J0W1KWZHEjaDTA
         JPHA==
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=1e100.net; s=20161025;
        h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to
         :references:mime-version:content-transfer-encoding;
        bh=ZFwyQlsscT2RBnxHWArfuTVJVgRwj0xOpsgIKb91Ge0=;
        b=DnFm1p8TG9LlevT1NVo7VF+fPymifJ1CpEQIeTRWvw8jkdmSJ+0TzScgPHXvn2ECf+
         oTzmrnGLLeQNl83vxcU7aJ4HPZZtdc1CaNbTCCZjDwnSoLeI0Ql/npOd/DCHdBi+gQuV
         sZzJ+Mla1kn6cu91kzDnbeF1pk6alQW/ZkoW9+jRLYrIlVBfBf4mWyjdgWDGpB8cVzag
         G8V+Uu476SY0txAsabnvRGXkmauE8rx0Ov/v2Kgkqe5mBvk1++zBrsPDB0bJCDSYjRZT
         YhgFpcYaByowhOtepuichElBGuDHH/tvjvyS9GJfS1TUuiK3upLqOzLvQJM8E+ccLYxs
         L5kA==
X-Gm-Message-State: AOAM533BT5n9L/QjlFH8m8fuSSZlW11ccE+d1hi3QopuHLRN6ECugIhR
        l/a/GKBn+tmVaDbLZsLupDEOZA==
X-Google-Smtp-Source: 
 ABdhPJxo20c2KFbIHjZgWLrl89GNL9t8kpfDAKmq+mis09TlkPg6pRW/DaEm5NbaUDzC6/ruk91INQ==
X-Received: by 2002:a17:90b:3781:: with SMTP id
 mz1mr3959844pjb.229.1606211917751;
        Tue, 24 Nov 2020 01:58:37 -0800 (PST)
Received: from localhost.localdomain ([103.136.220.120])
        by smtp.gmail.com with ESMTPSA id
 t20sm2424562pjg.25.2020.11.24.01.58.27
        (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128);
        Tue, 24 Nov 2020 01:58:37 -0800 (PST)
From: Muchun Song <songmuchun@bytedance.com>
To: corbet@lwn.net, mike.kravetz@oracle.com, tglx@linutronix.de,
        mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com,
        dave.hansen@linux.intel.com, luto@kernel.org, peterz@infradead.org,
        viro@zeniv.linux.org.uk, akpm@linux-foundation.org,
        paulmck@kernel.org, mchehab+huawei@kernel.org,
        pawan.kumar.gupta@linux.intel.com, rdunlap@infradead.org,
        oneukum@suse.com, anshuman.khandual@arm.com, jroedel@suse.de,
        almasrymina@google.com, rientjes@google.com, willy@infradead.org,
        osalvador@suse.de, mhocko@suse.com, song.bao.hua@hisilicon.com
Cc: duanxiongchun@bytedance.com, linux-doc@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        linux-fsdevel@vger.kernel.org,
        Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH v6 11/16] mm/hugetlb: Introduce remap_huge_page_pmd_vmemmap
 helper
Date: Tue, 24 Nov 2020 17:52:54 +0800
Message-Id: <20201124095259.58755-12-songmuchun@bytedance.com>
X-Mailer: git-send-email 2.21.0 (Apple Git-122)
In-Reply-To: <20201124095259.58755-1-songmuchun@bytedance.com>
References: <20201124095259.58755-1-songmuchun@bytedance.com>
MIME-Version: 1.0
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

The __free_huge_page_pmd_vmemmap and __remap_huge_page_pmd_vmemmap are
almost the same code. So introduce remap_free_huge_page_pmd_vmemmap
helper to simplify the code.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 mm/hugetlb_vmemmap.c | 87 +++++++++++++++++++++-------------------------------
 1 file changed, 35 insertions(+), 52 deletions(-)

diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index d6a1b06c1322..509ca451e232 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -127,6 +127,10 @@
 	(__boundary - 1 < (end) - 1) ? __boundary : (end);		 \
 })
 
+typedef void (*vmemmap_pte_remap_func_t)(struct page *reuse, pte_t *ptep,
+					 unsigned long start, unsigned long end,
+					 void *priv);
+
 static inline unsigned int vmemmap_pages_per_hpage(struct hstate *h)
 {
 	return free_vmemmap_pages_per_hpage(h) + RESERVE_VMEMMAP_NR;
@@ -162,21 +166,42 @@ static pmd_t *vmemmap_to_pmd(unsigned long page)
 	return pmd_offset(pud, page);
 }
 
+static void remap_huge_page_pmd_vmemmap(pmd_t *pmd, unsigned long start,
+					unsigned long end,
+					vmemmap_pte_remap_func_t fn, void *priv)
+{
+	unsigned long next, addr = start;
+	struct page *reuse = NULL;
+
+	do {
+		pte_t *ptep;
+
+		ptep = pte_offset_kernel(pmd, addr);
+		if (!reuse)
+			reuse = pte_page(ptep[TAIL_PAGE_REUSE]);
+
+		next = vmemmap_hpage_addr_end(addr, end);
+		fn(reuse, ptep, addr, next, priv);
+	} while (pmd++, addr = next, addr != end);
+
+	flush_tlb_kernel_range(start, end);
+}
+
 static void __remap_huge_page_pte_vmemmap(struct page *reuse, pte_t *ptep,
 					  unsigned long start,
-					  unsigned long end,
-					  struct list_head *remap_pages)
+					  unsigned long end, void *priv)
 {
 	pgprot_t pgprot = PAGE_KERNEL;
 	void *from = page_to_virt(reuse);
 	unsigned long addr;
+	struct list_head *pages = priv;
 
 	for (addr = start; addr < end; addr += PAGE_SIZE) {
 		void *to;
 		struct page *page;
 		pte_t entry, old = *ptep;
 
-		page = list_first_entry(remap_pages, struct page, lru);
+		page = list_first_entry(pages, struct page, lru);
 		list_del(&page->lru);
 		to = page_to_virt(page);
 		copy_page(to, from);
@@ -196,28 +221,6 @@ static void __remap_huge_page_pte_vmemmap(struct page *reuse, pte_t *ptep,
 	}
 }
 
-static void __remap_huge_page_pmd_vmemmap(pmd_t *pmd, unsigned long start,
-					  unsigned long end,
-					  struct list_head *vmemmap_pages)
-{
-	unsigned long next, addr = start;
-	struct page *reuse = NULL;
-
-	do {
-		pte_t *ptep;
-
-		ptep = pte_offset_kernel(pmd, addr);
-		if (!reuse)
-			reuse = pte_page(ptep[TAIL_PAGE_REUSE]);
-
-		next = vmemmap_hpage_addr_end(addr, end);
-		__remap_huge_page_pte_vmemmap(reuse, ptep, addr, next,
-					      vmemmap_pages);
-	} while (pmd++, addr = next, addr != end);
-
-	flush_tlb_kernel_range(start, end);
-}
-
 static inline void alloc_vmemmap_pages(struct hstate *h, struct list_head *list)
 {
 	unsigned int nr = free_vmemmap_pages_per_hpage(h);
@@ -258,7 +261,8 @@ void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
 
 	start = vmemmap_addr + RESERVE_VMEMMAP_SIZE;
 	end = vmemmap_addr + vmemmap_pages_size_per_hpage(h);
-	__remap_huge_page_pmd_vmemmap(pmd, start, end, &map_pages);
+	remap_huge_page_pmd_vmemmap(pmd, start, end,
+				    __remap_huge_page_pte_vmemmap, &map_pages);
 }
 
 static inline void free_vmemmap_page_list(struct list_head *list)
@@ -273,13 +277,13 @@ static inline void free_vmemmap_page_list(struct list_head *list)
 
 static void __free_huge_page_pte_vmemmap(struct page *reuse, pte_t *ptep,
 					 unsigned long start,
-					 unsigned long end,
-					 struct list_head *free_pages)
+					 unsigned long end, void *priv)
 {
 	/* Make the tail pages are mapped read-only. */
 	pgprot_t pgprot = PAGE_KERNEL_RO;
 	pte_t entry = mk_pte(reuse, pgprot);
 	unsigned long addr;
+	struct list_head *pages = priv;
 
 	for (addr = start; addr < end; addr += PAGE_SIZE, ptep++) {
 		struct page *page;
@@ -287,34 +291,12 @@ static void __free_huge_page_pte_vmemmap(struct page *reuse, pte_t *ptep,
 
 		VM_WARN_ON(!pte_present(old));
 		page = pte_page(old);
-		list_add(&page->lru, free_pages);
+		list_add(&page->lru, pages);
 
 		set_pte_at(&init_mm, addr, ptep, entry);
 	}
 }
 
-static void __free_huge_page_pmd_vmemmap(pmd_t *pmd, unsigned long start,
-					 unsigned long end,
-					 struct list_head *vmemmap_pages)
-{
-	unsigned long next, addr = start;
-	struct page *reuse = NULL;
-
-	do {
-		pte_t *ptep;
-
-		ptep = pte_offset_kernel(pmd, addr);
-		if (!reuse)
-			reuse = pte_page(ptep[TAIL_PAGE_REUSE]);
-
-		next = vmemmap_hpage_addr_end(addr, end);
-		__free_huge_page_pte_vmemmap(reuse, ptep, addr, next,
-					     vmemmap_pages);
-	} while (pmd++, addr = next, addr != end);
-
-	flush_tlb_kernel_range(start, end);
-}
-
 void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 {
 	pmd_t *pmd;
@@ -330,7 +312,8 @@ void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 
 	start = vmemmap_addr + RESERVE_VMEMMAP_SIZE;
 	end = vmemmap_addr + vmemmap_pages_size_per_hpage(h);
-	__free_huge_page_pmd_vmemmap(pmd, start, end, &free_pages);
+	remap_huge_page_pmd_vmemmap(pmd, start, end,
+				    __free_huge_page_pte_vmemmap, &free_pages);
 	free_vmemmap_page_list(&free_pages);
 }
 

From patchwork Tue Nov 24 09:52:55 2020
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
X-Patchwork-Submitter: Muchun Song <songmuchun@bytedance.com>
X-Patchwork-Id: 1344540
Return-Path: <linux-kernel-owner@kernel.org>
Received: from mail.kernel.org (mail.kernel.org [198.145.29.99])
	by smtp.lore.kernel.org (Postfix) with ESMTP id C4B85C64E90
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:59:11 +0000 (UTC)
Received: from vger.kernel.org (vger.kernel.org [23.128.96.18])
	by mail.kernel.org (Postfix) with ESMTP id 804B02076B
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:59:11 +0000 (UTC)
Authentication-Results: mail.kernel.org;
	dkim=pass (2048-bit key) header.d=bytedance-com.20150623.gappssmtp.com
 header.i=@bytedance-com.20150623.gappssmtp.com header.b="R/NFgWFz"
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1731766AbgKXJ6t (ORCPT
        <rfc822;linux-kernel@archiver.kernel.org>);
        Tue, 24 Nov 2020 04:58:49 -0500
Received: from lindbergh.monkeyblade.net ([23.128.96.19]:57432 "EHLO
        lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1731748AbgKXJ6s (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Tue, 24 Nov 2020 04:58:48 -0500
Received: from mail-pf1-x443.google.com (mail-pf1-x443.google.com
 [IPv6:2607:f8b0:4864:20::443])
        by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 7137AC0617A6
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:58:48 -0800 (PST)
Received: by mail-pf1-x443.google.com with SMTP id 131so17994388pfb.9
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:58:48 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=bytedance-com.20150623.gappssmtp.com; s=20150623;
        h=from:to:cc:subject:date:message-id:in-reply-to:references
         :mime-version:content-transfer-encoding;
        bh=RFw3IJ+e2PheHYuR5pwkJRvmAhprgLu2/OHbj9OxvOs=;
        b=R/NFgWFzv5XD8+fMmy9hSPore6Nhp1q1lz+iTh/Z6t/bPrllx4dpov59KYoAon2lNA
         GBpERZR/JZMY3ulmkYQpKDP8DV953PQ3RZzUQxKM4mnyWNwRhDa1wb4snI4zBh2wr5Kb
         oXkrMON3RrVLHJTImt44dHhTRUluYGutuVa+Os1DRIMMBtTcn1CMLLEZ94p2kvJTScoi
         /oK4DbQV2PgqhlLFxSIpN6IZAYBXesDQpPwdvfStSi3uUNLJyrQfB+zmcM3hkx4A7BYj
         ZK6OtqPE/foVctZ5CI9SefAoHhTozBrksQuotfIRLF6NPlQ4HBdzxuvEFbwwoy4rwUfi
         M9yA==
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=1e100.net; s=20161025;
        h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to
         :references:mime-version:content-transfer-encoding;
        bh=RFw3IJ+e2PheHYuR5pwkJRvmAhprgLu2/OHbj9OxvOs=;
        b=VnKTXR/ioF1Xs73j06b7SWNu0YBBytuU6vuWj5K81gcgeJ+j8TZhPoVEh74tnsKROS
         kaw3hjHk0a/qHBeSy0v6Zs/5eGDNvCRPvw8jKbvVqfYbtgkaDy9gRVavfxBWlaLuIkXe
         xj7Y1u57x3k9Uc1vk0BVVrJXv5udJpyPlFbQErvmrqi6MZWiRcIDHWjws/ts9HL0qjl8
         +CpSed9FHLytDWhLq81cQL0KfE2TKLzk3GkRTt1h3OuSMlYV7BtWM2nSaFGqqrSVXxMr
         7NdiV8Gr+5hI07sL9wIHFT7KYXqgjFyIqIj4TVA0K6Oe28ZwDj8Jccs/+LuVQkO8yoyu
         SOvQ==
X-Gm-Message-State: AOAM5307WclYN1EC2cfBU96mNmrtijVhbpmWtR9BC+149bJdX2CUAaZF
        EUTV8Q44uYBuCFc2bp9CNcQuIw==
X-Google-Smtp-Source: 
 ABdhPJzdxw87RN1KSfcNqb2JmA6MNZy/cqHyN2dAAW7ioN9KAQtWf+p2mboNDrApUqfrr5RM9+njBA==
X-Received: by 2002:a62:78d3:0:b029:198:ad8:7d05 with SMTP id
 t202-20020a6278d30000b02901980ad87d05mr3424298pfc.18.1606211928001;
        Tue, 24 Nov 2020 01:58:48 -0800 (PST)
Received: from localhost.localdomain ([103.136.220.120])
        by smtp.gmail.com with ESMTPSA id
 t20sm2424562pjg.25.2020.11.24.01.58.38
        (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128);
        Tue, 24 Nov 2020 01:58:47 -0800 (PST)
From: Muchun Song <songmuchun@bytedance.com>
To: corbet@lwn.net, mike.kravetz@oracle.com, tglx@linutronix.de,
        mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com,
        dave.hansen@linux.intel.com, luto@kernel.org, peterz@infradead.org,
        viro@zeniv.linux.org.uk, akpm@linux-foundation.org,
        paulmck@kernel.org, mchehab+huawei@kernel.org,
        pawan.kumar.gupta@linux.intel.com, rdunlap@infradead.org,
        oneukum@suse.com, anshuman.khandual@arm.com, jroedel@suse.de,
        almasrymina@google.com, rientjes@google.com, willy@infradead.org,
        osalvador@suse.de, mhocko@suse.com, song.bao.hua@hisilicon.com
Cc: duanxiongchun@bytedance.com, linux-doc@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        linux-fsdevel@vger.kernel.org,
        Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH v6 12/16] mm/hugetlb: Set the PageHWPoison to the raw error
 page
Date: Tue, 24 Nov 2020 17:52:55 +0800
Message-Id: <20201124095259.58755-13-songmuchun@bytedance.com>
X-Mailer: git-send-email 2.21.0 (Apple Git-122)
In-Reply-To: <20201124095259.58755-1-songmuchun@bytedance.com>
References: <20201124095259.58755-1-songmuchun@bytedance.com>
MIME-Version: 1.0
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

Because we reuse the first tail vmemmap page frame and remap it
with read-only, we cannot set the PageHWPosion on a tail page.
So we can use the head[4].mapping to record the real error page
index and set the raw error page PageHWPoison later.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 mm/hugetlb.c         | 11 +++--------
 mm/hugetlb_vmemmap.h | 39 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 42 insertions(+), 8 deletions(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 3fafa39fcac6..ade20954eb81 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1383,6 +1383,7 @@ static void __free_hugepage(struct hstate *h, struct page *page)
 	int i;
 
 	alloc_huge_page_vmemmap(h, page);
+	subpage_hwpoison_deliver(page);
 
 	for (i = 0; i < pages_per_huge_page(h); i++) {
 		page[i].flags &= ~(1 << PG_locked | 1 << PG_error |
@@ -1930,14 +1931,8 @@ int dissolve_free_huge_page(struct page *page)
 		int nid = page_to_nid(head);
 		if (h->free_huge_pages - h->resv_huge_pages == 0)
 			goto out;
-		/*
-		 * Move PageHWPoison flag from head page to the raw error page,
-		 * which makes any subpages rather than the error page reusable.
-		 */
-		if (PageHWPoison(head) && page != head) {
-			SetPageHWPoison(page);
-			ClearPageHWPoison(head);
-		}
+
+		set_subpage_hwpoison(head, page);
 		list_del(&head->lru);
 		h->free_huge_pages--;
 		h->free_huge_pages_node[nid]--;
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index 7887095488f4..4bb35d87ae10 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -15,6 +15,29 @@ void __init hugetlb_vmemmap_init(struct hstate *h);
 void alloc_huge_page_vmemmap(struct hstate *h, struct page *head);
 void free_huge_page_vmemmap(struct hstate *h, struct page *head);
 
+static inline void subpage_hwpoison_deliver(struct page *head)
+{
+	struct page *page = head;
+
+	if (PageHWPoison(head))
+		page = head + page_private(head + 4);
+
+	/*
+	 * Move PageHWPoison flag from head page to the raw error page,
+	 * which makes any subpages rather than the error page reusable.
+	 */
+	if (page != head) {
+		SetPageHWPoison(page);
+		ClearPageHWPoison(head);
+	}
+}
+
+static inline void set_subpage_hwpoison(struct page *head, struct page *page)
+{
+	if (PageHWPoison(head))
+		set_page_private(head + 4, page - head);
+}
+
 static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
 {
 	return h->nr_free_vmemmap_pages;
@@ -32,6 +55,22 @@ static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 {
 }
 
+static inline void subpage_hwpoison_deliver(struct page *head)
+{
+}
+
+static inline void set_subpage_hwpoison(struct page *head, struct page *page)
+{
+	/*
+	 * Move PageHWPoison flag from head page to the raw error page,
+	 * which makes any subpages rather than the error page reusable.
+	 */
+	if (PageHWPoison(head) && page != head) {
+		SetPageHWPoison(page);
+		ClearPageHWPoison(head);
+	}
+}
+
 static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
 {
 	return 0;

From patchwork Tue Nov 24 09:52:56 2020
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
X-Patchwork-Submitter: Muchun Song <songmuchun@bytedance.com>
X-Patchwork-Id: 1344541
Return-Path: <linux-kernel-owner@kernel.org>
Received: from mail.kernel.org (mail.kernel.org [198.145.29.99])
	by smtp.lore.kernel.org (Postfix) with ESMTP id 6AF35C71156
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:59:13 +0000 (UTC)
Received: from vger.kernel.org (vger.kernel.org [23.128.96.18])
	by mail.kernel.org (Postfix) with ESMTP id 1508B20637
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:59:13 +0000 (UTC)
Authentication-Results: mail.kernel.org;
	dkim=pass (2048-bit key) header.d=bytedance-com.20150623.gappssmtp.com
 header.i=@bytedance-com.20150623.gappssmtp.com header.b="Z5F/w/tm"
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1731778AbgKXJ7C (ORCPT
        <rfc822;linux-kernel@archiver.kernel.org>);
        Tue, 24 Nov 2020 04:59:02 -0500
Received: from lindbergh.monkeyblade.net ([23.128.96.19]:57462 "EHLO
        lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1731767AbgKXJ7A (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Tue, 24 Nov 2020 04:59:00 -0500
Received: from mail-pl1-x643.google.com (mail-pl1-x643.google.com
 [IPv6:2607:f8b0:4864:20::643])
        by lindbergh.monkeyblade.net (Postfix) with ESMTPS id AF129C0617A6
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:58:58 -0800 (PST)
Received: by mail-pl1-x643.google.com with SMTP id bj5so9621700plb.4
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:58:58 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=bytedance-com.20150623.gappssmtp.com; s=20150623;
        h=from:to:cc:subject:date:message-id:in-reply-to:references
         :mime-version:content-transfer-encoding;
        bh=AhLUtLFhMowsX7y4QUFW0UEwoN/NQ4MXIPAKrIe+pb4=;
        b=Z5F/w/tm3Uj3uOWyx+XA5NHR0bbcoVlS2LknPto/PCroM31hRPIweQWnTy65FM0+Nd
         0DBzo7aNdGPxnpgna4W+Z/RWKX6GP/rVs4V3l+zZcXsOKkMusa6AcJ8h1c2j+OWp5Ibm
         UcisxXP4wMSLAVbbGLILP52x66590iml6M7Q8F8Q4rnH9h+QEDKv2Ka/whnqoYDBwki3
         jagqwwe7lDrSk9dze123ufHSv/p8nERtOPQ6BHE5nfAb1GQDgyhBvocIgy0hghu31ifr
         xMYofHJkBKmADKxtUfkOsuzLp7tdi3j3qSmPWBPXnCYp+EOrOcpw8ODfN3PV0w4jM/HA
         tTMA==
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=1e100.net; s=20161025;
        h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to
         :references:mime-version:content-transfer-encoding;
        bh=AhLUtLFhMowsX7y4QUFW0UEwoN/NQ4MXIPAKrIe+pb4=;
        b=f8jG0FKh7MkSdn3AMufkcCaPtVsRs5WfKdiL887Tau9eNWRDdsKv8WTrGW5R/8pmk0
         MGIcEp2aWNONdKlQukvQZ6ohABpY/9RIwTt0GVn4ywIWouW7QMgBkdHDPPu+L55NsdcH
         fs9x/dHc67AjwjgT3jSVhlwDmyjFCgK7ikvsfeo/GoAGrbI3CP6yDv/jrJg/pHAoqP+Z
         SQ4NJg/bmSRDNzOZWA8Z8kkHI8sclB3lK/DmwicMyj6w3P+7WTWxwOiHOeizHrLBSwgL
         fTBK615h2MweZ+mglJymm6QVu1y8nXG8Rv9ardX359WOBQeJiMvLKGmP+uSNduVt+vOm
         e6tg==
X-Gm-Message-State: AOAM533yIqfwXkrxT0kYx5jzcb8OhlBaeFEbmUY9j0X/vh8kdwcpgVkH
        ghXn3u5dp0UKv5ldo9RF9GkUQQ==
X-Google-Smtp-Source: 
 ABdhPJxOhASAWI7bhf2EZ3rDH1q81mI7X3+WN0iuPQlauueb9EcbgaGjAccpG4m6xdjfy0iZs2IWQQ==
X-Received: by 2002:a17:902:bc46:b029:d6:d98a:1a68 with SMTP id
 t6-20020a170902bc46b02900d6d98a1a68mr3310014plz.63.1606211938283;
        Tue, 24 Nov 2020 01:58:58 -0800 (PST)
Received: from localhost.localdomain ([103.136.220.120])
        by smtp.gmail.com with ESMTPSA id
 t20sm2424562pjg.25.2020.11.24.01.58.48
        (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128);
        Tue, 24 Nov 2020 01:58:57 -0800 (PST)
From: Muchun Song <songmuchun@bytedance.com>
To: corbet@lwn.net, mike.kravetz@oracle.com, tglx@linutronix.de,
        mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com,
        dave.hansen@linux.intel.com, luto@kernel.org, peterz@infradead.org,
        viro@zeniv.linux.org.uk, akpm@linux-foundation.org,
        paulmck@kernel.org, mchehab+huawei@kernel.org,
        pawan.kumar.gupta@linux.intel.com, rdunlap@infradead.org,
        oneukum@suse.com, anshuman.khandual@arm.com, jroedel@suse.de,
        almasrymina@google.com, rientjes@google.com, willy@infradead.org,
        osalvador@suse.de, mhocko@suse.com, song.bao.hua@hisilicon.com
Cc: duanxiongchun@bytedance.com, linux-doc@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        linux-fsdevel@vger.kernel.org,
        Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH v6 13/16] mm/hugetlb: Flush work when dissolving hugetlb page
Date: Tue, 24 Nov 2020 17:52:56 +0800
Message-Id: <20201124095259.58755-14-songmuchun@bytedance.com>
X-Mailer: git-send-email 2.21.0 (Apple Git-122)
In-Reply-To: <20201124095259.58755-1-songmuchun@bytedance.com>
References: <20201124095259.58755-1-songmuchun@bytedance.com>
MIME-Version: 1.0
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

We should flush work when dissolving a hugetlb page to make sure that
the hugetlb page is freed to the buddy.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 mm/hugetlb.c | 18 +++++++++++++++++-
 1 file changed, 17 insertions(+), 1 deletion(-)

diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ade20954eb81..15e2c1dd32ea 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1328,6 +1328,12 @@ static void update_hpage_vmemmap_workfn(struct work_struct *work)
 }
 static DECLARE_WORK(hpage_update_work, update_hpage_vmemmap_workfn);
 
+static inline void flush_hpage_update_work(struct hstate *h)
+{
+	if (free_vmemmap_pages_per_hpage(h))
+		flush_work(&hpage_update_work);
+}
+
 static inline void __update_and_free_page(struct hstate *h, struct page *page)
 {
 	/* No need to allocate vmemmap pages */
@@ -1914,6 +1920,7 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed,
 int dissolve_free_huge_page(struct page *page)
 {
 	int rc = -EBUSY;
+	struct hstate *h = NULL;
 
 	/* Not to disrupt normal path by vainly holding hugetlb_lock */
 	if (!PageHuge(page))
@@ -1927,8 +1934,9 @@ int dissolve_free_huge_page(struct page *page)
 
 	if (!page_count(page)) {
 		struct page *head = compound_head(page);
-		struct hstate *h = page_hstate(head);
 		int nid = page_to_nid(head);
+
+		h = page_hstate(head);
 		if (h->free_huge_pages - h->resv_huge_pages == 0)
 			goto out;
 
@@ -1942,6 +1950,14 @@ int dissolve_free_huge_page(struct page *page)
 	}
 out:
 	spin_unlock(&hugetlb_lock);
+
+	/*
+	 * We should flush work before return to make sure that
+	 * the HugeTLB page is freed to the buddy.
+	 */
+	if (!rc && h)
+		flush_hpage_update_work(h);
+
 	return rc;
 }
 

From patchwork Tue Nov 24 09:52:57 2020
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
X-Patchwork-Submitter: Muchun Song <songmuchun@bytedance.com>
X-Patchwork-Id: 1344542
Return-Path: <linux-kernel-owner@kernel.org>
Received: from mail.kernel.org (mail.kernel.org [198.145.29.99])
	by smtp.lore.kernel.org (Postfix) with ESMTP id 95545C8300C
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:59:13 +0000 (UTC)
Received: from vger.kernel.org (vger.kernel.org [23.128.96.18])
	by mail.kernel.org (Postfix) with ESMTP id 53C1920708
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:59:13 +0000 (UTC)
Authentication-Results: mail.kernel.org;
	dkim=pass (2048-bit key) header.d=bytedance-com.20150623.gappssmtp.com
 header.i=@bytedance-com.20150623.gappssmtp.com header.b="fuMUt74x"
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1731790AbgKXJ7K (ORCPT
        <rfc822;linux-kernel@archiver.kernel.org>);
        Tue, 24 Nov 2020 04:59:10 -0500
Received: from lindbergh.monkeyblade.net ([23.128.96.19]:57492 "EHLO
        lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1731767AbgKXJ7I (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Tue, 24 Nov 2020 04:59:08 -0500
Received: from mail-pg1-x543.google.com (mail-pg1-x543.google.com
 [IPv6:2607:f8b0:4864:20::543])
        by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 8F93CC0613D6
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:59:08 -0800 (PST)
Received: by mail-pg1-x543.google.com with SMTP id w4so16977116pgg.13
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:59:08 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=bytedance-com.20150623.gappssmtp.com; s=20150623;
        h=from:to:cc:subject:date:message-id:in-reply-to:references
         :mime-version:content-transfer-encoding;
        bh=RvROAgOOAQ4kY4iKE3ESPFWS7AbcyyeQezHTq1QFTAg=;
        b=fuMUt74xPel262JKZcWj7UdAWTy2xxyYGTNPRBO2ViJpSb3cOepUJiAuAL5eAr2ooz
         j2AHvTaxLpMpe17XuGaalenP6FFJcPzfpy9YqA23Bq2eUtD1M3G8z51lfjCSJya72zRY
         Cqsck+YkGPmh1FnH25pcEzUHMUjFjiVc3fm2OCsWimzfMVj9RcOe98i0MZLz6Kmym7e4
         /K5gvmzeNjSQjb5v/FXLbtcDiHPYmOJUPWJlz1ldS8ljQO9iC0uEm2rIxpMCB8mcFTC1
         7kQOBSiW05idLnK6y4kUUNxTqg1SlWoQCaGLWLXOnm4r0vJ38ZT0iZv8dgHT3KKv09NC
         vzUA==
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=1e100.net; s=20161025;
        h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to
         :references:mime-version:content-transfer-encoding;
        bh=RvROAgOOAQ4kY4iKE3ESPFWS7AbcyyeQezHTq1QFTAg=;
        b=Tx2JdY6tb+KrOBoxbBWRESszpdI1Nt3nKwl5QZxSNhsNKGy7wYOnDiJuGsY1zrjECD
         LrRGTFBZrS0EI4TBld+iVk58EyS1DlBYG4hD3iIFBfVRkwXTHjQdHN8YU0jCRck2FOKW
         v+2ZSjTOYmarHixuzgYBvJvBFoSUm97Ity9RicmpoXIbO2kksg8W9udnyoIymvBEiFIb
         dLOZBzSFOY1ZFlE0Y+Romvnh7NRcEIzoWdPn12dghUiQ3TLvii7sv9RbxSKfXco+s09V
         +KyrSs0SRFeadD1OddwP58hSrTkaeS7dZDsJ3ooU5aV4u/eyjsF6I3lUXgPgdJiru0gD
         3CsA==
X-Gm-Message-State: AOAM533cwGIX3wbmQ51dHpYCH1lrDSvFavB8UKAx1W786NX7jh47I3GJ
        RGzFqCXzrvUw17K1cYRdA10o5w==
X-Google-Smtp-Source: 
 ABdhPJxlanZ/RJAQaev8flwUs/w/EGF8DKrJNUyiGS3fentCZnvyeLaxGW2GOzpgkK7Q4Y0SmdGDQg==
X-Received: by 2002:a17:90a:c214:: with SMTP id
 e20mr4154217pjt.212.1606211948164;
        Tue, 24 Nov 2020 01:59:08 -0800 (PST)
Received: from localhost.localdomain ([103.136.220.120])
        by smtp.gmail.com with ESMTPSA id
 t20sm2424562pjg.25.2020.11.24.01.58.58
        (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128);
        Tue, 24 Nov 2020 01:59:07 -0800 (PST)
From: Muchun Song <songmuchun@bytedance.com>
To: corbet@lwn.net, mike.kravetz@oracle.com, tglx@linutronix.de,
        mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com,
        dave.hansen@linux.intel.com, luto@kernel.org, peterz@infradead.org,
        viro@zeniv.linux.org.uk, akpm@linux-foundation.org,
        paulmck@kernel.org, mchehab+huawei@kernel.org,
        pawan.kumar.gupta@linux.intel.com, rdunlap@infradead.org,
        oneukum@suse.com, anshuman.khandual@arm.com, jroedel@suse.de,
        almasrymina@google.com, rientjes@google.com, willy@infradead.org,
        osalvador@suse.de, mhocko@suse.com, song.bao.hua@hisilicon.com
Cc: duanxiongchun@bytedance.com, linux-doc@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        linux-fsdevel@vger.kernel.org,
        Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH v6 14/16] mm/hugetlb: Add a kernel parameter
 hugetlb_free_vmemmap
Date: Tue, 24 Nov 2020 17:52:57 +0800
Message-Id: <20201124095259.58755-15-songmuchun@bytedance.com>
X-Mailer: git-send-email 2.21.0 (Apple Git-122)
In-Reply-To: <20201124095259.58755-1-songmuchun@bytedance.com>
References: <20201124095259.58755-1-songmuchun@bytedance.com>
MIME-Version: 1.0
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

Add a kernel parameter hugetlb_free_vmemmap to disable the feature of
freeing unused vmemmap pages associated with each hugetlb page on boot.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 Documentation/admin-guide/kernel-parameters.txt |  9 +++++++++
 Documentation/admin-guide/mm/hugetlbpage.rst    |  3 +++
 mm/hugetlb_vmemmap.c                            | 19 ++++++++++++++++++-
 3 files changed, 30 insertions(+), 1 deletion(-)

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 5debfe238027..d28c3acde965 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -1551,6 +1551,15 @@
 			Documentation/admin-guide/mm/hugetlbpage.rst.
 			Format: size[KMG]
 
+	hugetlb_free_vmemmap=
+			[KNL] When CONFIG_HUGETLB_PAGE_FREE_VMEMMAP is set,
+			this controls freeing unused vmemmap pages associated
+			with each HugeTLB page.
+			Format: { on | off (default) }
+
+			on:  enable the feature
+			off: disable the feature
+
 	hung_task_panic=
 			[KNL] Should the hung task detector generate panics.
 			Format: 0 | 1
diff --git a/Documentation/admin-guide/mm/hugetlbpage.rst b/Documentation/admin-guide/mm/hugetlbpage.rst
index f7b1c7462991..6a8b57f6d3b7 100644
--- a/Documentation/admin-guide/mm/hugetlbpage.rst
+++ b/Documentation/admin-guide/mm/hugetlbpage.rst
@@ -145,6 +145,9 @@ default_hugepagesz
 
 	will all result in 256 2M huge pages being allocated.  Valid default
 	huge page size is architecture dependent.
+hugetlb_free_vmemmap
+	When CONFIG_HUGETLB_PAGE_FREE_VMEMMAP is set, this enables freeing
+	unused vmemmap pages associated each HugeTLB page.
 
 When multiple huge page sizes are supported, ``/proc/sys/vm/nr_hugepages``
 indicates the current number of pre-allocated huge pages of the default size.
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 509ca451e232..b2222f8d1245 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -131,6 +131,22 @@ typedef void (*vmemmap_pte_remap_func_t)(struct page *reuse, pte_t *ptep,
 					 unsigned long start, unsigned long end,
 					 void *priv);
 
+static bool hugetlb_free_vmemmap_enabled __initdata;
+
+static int __init early_hugetlb_free_vmemmap_param(char *buf)
+{
+	if (!buf)
+		return -EINVAL;
+
+	if (!strcmp(buf, "on"))
+		hugetlb_free_vmemmap_enabled = true;
+	else if (strcmp(buf, "off"))
+		return -EINVAL;
+
+	return 0;
+}
+early_param("hugetlb_free_vmemmap", early_hugetlb_free_vmemmap_param);
+
 static inline unsigned int vmemmap_pages_per_hpage(struct hstate *h)
 {
 	return free_vmemmap_pages_per_hpage(h) + RESERVE_VMEMMAP_NR;
@@ -322,7 +338,8 @@ void __init hugetlb_vmemmap_init(struct hstate *h)
 	unsigned int order = huge_page_order(h);
 	unsigned int vmemmap_pages;
 
-	if (!is_power_of_2(sizeof(struct page))) {
+	if (!is_power_of_2(sizeof(struct page)) ||
+	    !hugetlb_free_vmemmap_enabled) {
 		pr_info("disable freeing vmemmap pages for %s\n", h->name);
 		return;
 	}

From patchwork Tue Nov 24 09:52:58 2020
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
X-Patchwork-Submitter: Muchun Song <songmuchun@bytedance.com>
X-Patchwork-Id: 1344543
Return-Path: <linux-kernel-owner@kernel.org>
Received: from mail.kernel.org (mail.kernel.org [198.145.29.99])
	by smtp.lore.kernel.org (Postfix) with ESMTP id 45CDCC63798
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:59:52 +0000 (UTC)
Received: from vger.kernel.org (vger.kernel.org [23.128.96.18])
	by mail.kernel.org (Postfix) with ESMTP id E853120637
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:59:51 +0000 (UTC)
Authentication-Results: mail.kernel.org;
	dkim=pass (2048-bit key) header.d=bytedance-com.20150623.gappssmtp.com
 header.i=@bytedance-com.20150623.gappssmtp.com header.b="IOq24E+r"
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1731802AbgKXJ7X (ORCPT
        <rfc822;linux-kernel@archiver.kernel.org>);
        Tue, 24 Nov 2020 04:59:23 -0500
Received: from lindbergh.monkeyblade.net ([23.128.96.19]:57530 "EHLO
        lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1731374AbgKXJ7V (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Tue, 24 Nov 2020 04:59:21 -0500
Received: from mail-pg1-x543.google.com (mail-pg1-x543.google.com
 [IPv6:2607:f8b0:4864:20::543])
        by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 036B3C0617A6
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:59:20 -0800 (PST)
Received: by mail-pg1-x543.google.com with SMTP id w4so16977546pgg.13
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:59:19 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=bytedance-com.20150623.gappssmtp.com; s=20150623;
        h=from:to:cc:subject:date:message-id:in-reply-to:references
         :mime-version:content-transfer-encoding;
        bh=W96GcRd95QFdsA9bezqiYZ3Ng26OfkYqhZoucFhsfUs=;
        b=IOq24E+rzU6pmMRQtMPcpQIT6iptbDJPPOGq7RrMFzQc6u6a6R3IoEEUTJxmWY4tyx
         6j/2S1cv7Ne7sIIVXPRTpBfD/AbCdP4lx5a+oxnnEbbbvd6ENxujpYsvvwlQsK0dSuCQ
         txljfZ8j1e2GgA5+H3ywIdlDP1SdzRFuIq4B+LVd+aGSxcM55c9UBR1uzCy4Il9J+Nnf
         DMIEBjm0nESe7pNwQJEZOzG2+KVlL4wLDAsHyXLghlG2ta82jOVfXOo+tRownh+gOEM1
         eQJPyBQMmUpqGhR4DQnDNPpWg4Pf98fINfRSUkKGim9tXpuLwNlar9HwyhMJx4M6LptL
         f5Lg==
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=1e100.net; s=20161025;
        h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to
         :references:mime-version:content-transfer-encoding;
        bh=W96GcRd95QFdsA9bezqiYZ3Ng26OfkYqhZoucFhsfUs=;
        b=dzycmOex7BAL0DRBeZc5OZG3moHzN9MBTep9VeIeB3kKHnciD7w0M4N3oK+ipaNzX+
         5pUJnhG0qR3wEhAQDsf4MFUMAJXWjYX5H8iAqkFoSZWiB6W77OSOxQrv8A6nlZw09XDO
         czIbwK1WZ12Pm2IlDGr4zofRQBhFRV6BJG8Ok35nAtHYH3wbb0JCMmVc6p6r3poZU4iC
         4gp6CLHQxUCEbus30x5RKjN7byLMZrlnor6aEH0lJM8MDOmGSGXI1OpNRjdR0vEr3FyT
         I2ieysPrGi+lgGiZckZ0aNEnp8YNFBRcZcvOaDHaG99n0nfE4lcAxDLJyFcZjhBR/BNT
         n2Zg==
X-Gm-Message-State: AOAM530V1xsUDYuvMOxVUKimUJJ3BJzKxKjtyq7LjtY9EwMP7LTjoN7u
        x8CT3oyvcE65jz6pK3vmXdAJPw==
X-Google-Smtp-Source: 
 ABdhPJyGXLT2YnZQYT7GzU/fcRtiRnLECo0raO0CeaMKvw08Ynj/2beYY0SZU8ZQI0PWkm3CFnfVoA==
X-Received: by 2002:a62:18c9:0:b029:197:e24e:60f2 with SMTP id
 192-20020a6218c90000b0290197e24e60f2mr3356423pfy.14.1606211959566;
        Tue, 24 Nov 2020 01:59:19 -0800 (PST)
Received: from localhost.localdomain ([103.136.220.120])
        by smtp.gmail.com with ESMTPSA id
 t20sm2424562pjg.25.2020.11.24.01.59.08
        (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128);
        Tue, 24 Nov 2020 01:59:19 -0800 (PST)
From: Muchun Song <songmuchun@bytedance.com>
To: corbet@lwn.net, mike.kravetz@oracle.com, tglx@linutronix.de,
        mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com,
        dave.hansen@linux.intel.com, luto@kernel.org, peterz@infradead.org,
        viro@zeniv.linux.org.uk, akpm@linux-foundation.org,
        paulmck@kernel.org, mchehab+huawei@kernel.org,
        pawan.kumar.gupta@linux.intel.com, rdunlap@infradead.org,
        oneukum@suse.com, anshuman.khandual@arm.com, jroedel@suse.de,
        almasrymina@google.com, rientjes@google.com, willy@infradead.org,
        osalvador@suse.de, mhocko@suse.com, song.bao.hua@hisilicon.com
Cc: duanxiongchun@bytedance.com, linux-doc@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        linux-fsdevel@vger.kernel.org,
        Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH v6 15/16] mm/hugetlb: Gather discrete indexes of tail page
Date: Tue, 24 Nov 2020 17:52:58 +0800
Message-Id: <20201124095259.58755-16-songmuchun@bytedance.com>
X-Mailer: git-send-email 2.21.0 (Apple Git-122)
In-Reply-To: <20201124095259.58755-1-songmuchun@bytedance.com>
References: <20201124095259.58755-1-songmuchun@bytedance.com>
MIME-Version: 1.0
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

For hugetlb page, there are more metadata to save in the struct
page. But the head struct page cannot meet our needs, so we have
to abuse other tail struct page to store the metadata. In order
to avoid conflicts caused by subsequent use of more tail struct
pages, we can gather these discrete indexes of tail struct page
In this case, it will be easier to add a new tail page index later.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 include/linux/hugetlb.h        | 13 +++++++++++++
 include/linux/hugetlb_cgroup.h | 15 +++++++++------
 mm/hugetlb.c                   | 12 ++++++------
 mm/hugetlb_vmemmap.h           |  4 ++--
 4 files changed, 30 insertions(+), 14 deletions(-)

diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
index eed3dd3bd626..8a615ae2d233 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -28,6 +28,19 @@ typedef struct { unsigned long pd; } hugepd_t;
 #include <linux/shm.h>
 #include <asm/tlbflush.h>
 
+enum {
+	SUBPAGE_INDEX_ACTIVE = 1,	/* reuse page flags of PG_private */
+	SUBPAGE_INDEX_TEMPORARY,	/* reuse page->mapping */
+#ifdef CONFIG_CGROUP_HUGETLB
+	SUBPAGE_INDEX_CGROUP = SUBPAGE_INDEX_TEMPORARY,/* reuse page->private */
+	SUBPAGE_INDEX_CGROUP_RSVD,	/* reuse page->private */
+#endif
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+	SUBPAGE_INDEX_HWPOISON,		/* reuse page->private */
+#endif
+	NR_USED_SUBPAGE,
+};
+
 struct hugepage_subpool {
 	spinlock_t lock;
 	long count;
diff --git a/include/linux/hugetlb_cgroup.h b/include/linux/hugetlb_cgroup.h
index 2ad6e92f124a..3d3c1c49efe4 100644
--- a/include/linux/hugetlb_cgroup.h
+++ b/include/linux/hugetlb_cgroup.h
@@ -24,8 +24,9 @@ struct file_region;
 /*
  * Minimum page order trackable by hugetlb cgroup.
  * At least 4 pages are necessary for all the tracking information.
- * The second tail page (hpage[2]) is the fault usage cgroup.
- * The third tail page (hpage[3]) is the reservation usage cgroup.
+ * The second tail page (hpage[SUBPAGE_INDEX_CGROUP]) is the fault
+ * usage cgroup. The third tail page (hpage[SUBPAGE_INDEX_CGROUP_RSVD])
+ * is the reservation usage cgroup.
  */
 #define HUGETLB_CGROUP_MIN_ORDER	2
 
@@ -66,9 +67,9 @@ __hugetlb_cgroup_from_page(struct page *page, bool rsvd)
 	if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER)
 		return NULL;
 	if (rsvd)
-		return (struct hugetlb_cgroup *)page[3].private;
+		return (void *)page_private(page + SUBPAGE_INDEX_CGROUP_RSVD);
 	else
-		return (struct hugetlb_cgroup *)page[2].private;
+		return (void *)page_private(page + SUBPAGE_INDEX_CGROUP);
 }
 
 static inline struct hugetlb_cgroup *hugetlb_cgroup_from_page(struct page *page)
@@ -90,9 +91,11 @@ static inline int __set_hugetlb_cgroup(struct page *page,
 	if (compound_order(page) < HUGETLB_CGROUP_MIN_ORDER)
 		return -1;
 	if (rsvd)
-		page[3].private = (unsigned long)h_cg;
+		set_page_private(page + SUBPAGE_INDEX_CGROUP_RSVD,
+				 (unsigned long)h_cg);
 	else
-		page[2].private = (unsigned long)h_cg;
+		set_page_private(page + SUBPAGE_INDEX_CGROUP,
+				 (unsigned long)h_cg);
 	return 0;
 }
 
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 15e2c1dd32ea..7700da372716 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1429,20 +1429,20 @@ struct hstate *size_to_hstate(unsigned long size)
 bool page_huge_active(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageHuge(page), page);
-	return PageHead(page) && PagePrivate(&page[1]);
+	return PageHead(page) && PagePrivate(&page[SUBPAGE_INDEX_ACTIVE]);
 }
 
 /* never called for tail page */
 static void set_page_huge_active(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageHeadHuge(page), page);
-	SetPagePrivate(&page[1]);
+	SetPagePrivate(&page[SUBPAGE_INDEX_ACTIVE]);
 }
 
 static void clear_page_huge_active(struct page *page)
 {
 	VM_BUG_ON_PAGE(!PageHeadHuge(page), page);
-	ClearPagePrivate(&page[1]);
+	ClearPagePrivate(&page[SUBPAGE_INDEX_ACTIVE]);
 }
 
 /*
@@ -1454,17 +1454,17 @@ static inline bool PageHugeTemporary(struct page *page)
 	if (!PageHuge(page))
 		return false;
 
-	return (unsigned long)page[2].mapping == -1U;
+	return (unsigned long)page[SUBPAGE_INDEX_TEMPORARY].mapping == -1U;
 }
 
 static inline void SetPageHugeTemporary(struct page *page)
 {
-	page[2].mapping = (void *)-1U;
+	page[SUBPAGE_INDEX_TEMPORARY].mapping = (void *)-1U;
 }
 
 static inline void ClearPageHugeTemporary(struct page *page)
 {
-	page[2].mapping = NULL;
+	page[SUBPAGE_INDEX_TEMPORARY].mapping = NULL;
 }
 
 static void __free_huge_page(struct page *page)
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index 4bb35d87ae10..54c2ca0e0dbe 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -20,7 +20,7 @@ static inline void subpage_hwpoison_deliver(struct page *head)
 	struct page *page = head;
 
 	if (PageHWPoison(head))
-		page = head + page_private(head + 4);
+		page = head + page_private(head + SUBPAGE_INDEX_HWPOISON);
 
 	/*
 	 * Move PageHWPoison flag from head page to the raw error page,
@@ -35,7 +35,7 @@ static inline void subpage_hwpoison_deliver(struct page *head)
 static inline void set_subpage_hwpoison(struct page *head, struct page *page)
 {
 	if (PageHWPoison(head))
-		set_page_private(head + 4, page - head);
+		set_page_private(head + SUBPAGE_INDEX_HWPOISON, page - head);
 }
 
 static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)

From patchwork Tue Nov 24 09:52:59 2020
Content-Type: text/plain; charset="utf-8"
MIME-Version: 1.0
Content-Transfer-Encoding: 7bit
X-Patchwork-Submitter: Muchun Song <songmuchun@bytedance.com>
X-Patchwork-Id: 1344544
Return-Path: <linux-kernel-owner@kernel.org>
Received: from mail.kernel.org (mail.kernel.org [198.145.29.99])
	by smtp.lore.kernel.org (Postfix) with ESMTP id 33BE4C64E7A
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:59:53 +0000 (UTC)
Received: from vger.kernel.org (vger.kernel.org [23.128.96.18])
	by mail.kernel.org (Postfix) with ESMTP id 921BF20708
	for <linux-kernel@archiver.kernel.org>; Tue, 24 Nov 2020 09:59:52 +0000 (UTC)
Authentication-Results: mail.kernel.org;
	dkim=pass (2048-bit key) header.d=bytedance-com.20150623.gappssmtp.com
 header.i=@bytedance-com.20150623.gappssmtp.com header.b="fU4syUhx"
Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand
        id S1731814AbgKXJ7f (ORCPT
        <rfc822;linux-kernel@archiver.kernel.org>);
        Tue, 24 Nov 2020 04:59:35 -0500
Received: from lindbergh.monkeyblade.net ([23.128.96.19]:57564 "EHLO
        lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org
        with ESMTP id S1731779AbgKXJ7a (ORCPT
        <rfc822;linux-kernel@vger.kernel.org>);
        Tue, 24 Nov 2020 04:59:30 -0500
Received: from mail-pf1-x442.google.com (mail-pf1-x442.google.com
 [IPv6:2607:f8b0:4864:20::442])
        by lindbergh.monkeyblade.net (Postfix) with ESMTPS id C9E7DC061A4D
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:59:30 -0800 (PST)
Received: by mail-pf1-x442.google.com with SMTP id v12so17968974pfm.13
        for <linux-kernel@vger.kernel.org>;
 Tue, 24 Nov 2020 01:59:30 -0800 (PST)
DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=bytedance-com.20150623.gappssmtp.com; s=20150623;
        h=from:to:cc:subject:date:message-id:in-reply-to:references
         :mime-version:content-transfer-encoding;
        bh=Bynt/1YGSIdeJG2cOcgImXpzmEpwnUEaY6/7f6Ae/g4=;
        b=fU4syUhxdPJXkfQh34bMos1Y3zr1DCPrRNdijHklOltKrH8VvpAXtOADs20QwQcEjW
         A2lK/GIaljVc1gKpKY+vWKXPR9OX02jV7LL2OxqKTKdW4TMY9bWP+fnxOuc6z68yESqq
         gPQsJIyUY3JrkeRY5zHkeN2Y8rM6TmLsRERR3l+Scp4P6MJ+uxijHnXpyVuclcExnT3i
         gzDQQIfKE2CNH1P5PIdE0F04T9wEPhqMpEHIzsrjT1bfyLdmVV1Yc+Rcj7e9TKtK/A6B
         43CvqdjuVYMGBrGRpCljlvKSDsJaaJr0BCU5Ev8i5DzEfhLX4j3RvZAfincG31o5Ls53
         GL8Q==
X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed;
        d=1e100.net; s=20161025;
        h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to
         :references:mime-version:content-transfer-encoding;
        bh=Bynt/1YGSIdeJG2cOcgImXpzmEpwnUEaY6/7f6Ae/g4=;
        b=K9gWQu1BzVjDC1h3ICVDPwEcHmeJVgrCd+zPfqEuoxCb6GZ0aEAb8sWlOaPPCfohij
         dZJGiKQBOlJ/WdI1eAM2YIHWErjkwDDNShELIy/XhrEBrNBhHAZyAukbNdR8tRkb5A6X
         s1drygKcSOJlewlGqeGdjSbsd5eF6DuqjMOIKdo4ddlxp9US6P6YlHkgN9nDdqfG/W7E
         1clh4UWnzsWR2jEFTe9pyxqSO7etOk7YDf6wkI6BZhjM+6vsNGgiybg02By7/8+BAqF3
         217g/qJ03r8+4tusYXf0Ze6Gx2grw1joZbGE0Y+zHZv9+vNfPFZtb/Qc3rbsqOVkiXik
         wX3g==
X-Gm-Message-State: AOAM5307Ts94poDQ9fozJ7pC2yWR5t4+Usp5t8Txeb79Z305BCmG1x+o
        PjCzttcCOA3RTsF2w6jHNARuPA==
X-Google-Smtp-Source: 
 ABdhPJy1pVteQcfd7t6pUTOEaOSYXhdcK1qTpL/2aKqFlzz5VS2SYxybBYu983LImuXmPOsDkOMJAQ==
X-Received: by 2002:a63:f857:: with SMTP id v23mr3071328pgj.174.1606211970431;
        Tue, 24 Nov 2020 01:59:30 -0800 (PST)
Received: from localhost.localdomain ([103.136.220.120])
        by smtp.gmail.com with ESMTPSA id
 t20sm2424562pjg.25.2020.11.24.01.59.19
        (version=TLS1_2 cipher=ECDHE-ECDSA-AES128-GCM-SHA256 bits=128/128);
        Tue, 24 Nov 2020 01:59:29 -0800 (PST)
From: Muchun Song <songmuchun@bytedance.com>
To: corbet@lwn.net, mike.kravetz@oracle.com, tglx@linutronix.de,
        mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com,
        dave.hansen@linux.intel.com, luto@kernel.org, peterz@infradead.org,
        viro@zeniv.linux.org.uk, akpm@linux-foundation.org,
        paulmck@kernel.org, mchehab+huawei@kernel.org,
        pawan.kumar.gupta@linux.intel.com, rdunlap@infradead.org,
        oneukum@suse.com, anshuman.khandual@arm.com, jroedel@suse.de,
        almasrymina@google.com, rientjes@google.com, willy@infradead.org,
        osalvador@suse.de, mhocko@suse.com, song.bao.hua@hisilicon.com
Cc: duanxiongchun@bytedance.com, linux-doc@vger.kernel.org,
        linux-kernel@vger.kernel.org, linux-mm@kvack.org,
        linux-fsdevel@vger.kernel.org,
        Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH v6 16/16] mm/hugetlb: Add BUILD_BUG_ON to catch invalid usage
 of tail struct page
Date: Tue, 24 Nov 2020 17:52:59 +0800
Message-Id: <20201124095259.58755-17-songmuchun@bytedance.com>
X-Mailer: git-send-email 2.21.0 (Apple Git-122)
In-Reply-To: <20201124095259.58755-1-songmuchun@bytedance.com>
References: <20201124095259.58755-1-songmuchun@bytedance.com>
MIME-Version: 1.0
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

There are only `RESERVE_VMEMMAP_SIZE / sizeof(struct page)` struct pages
can be used when CONFIG_HUGETLB_PAGE_FREE_VMEMMAP, so add a BUILD_BUG_ON
to catch this invalid usage of tail struct page.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 mm/hugetlb_vmemmap.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index b2222f8d1245..d2c013582110 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -338,6 +338,9 @@ void __init hugetlb_vmemmap_init(struct hstate *h)
 	unsigned int order = huge_page_order(h);
 	unsigned int vmemmap_pages;
 
+	BUILD_BUG_ON(NR_USED_SUBPAGE >=
+		     RESERVE_VMEMMAP_SIZE / sizeof(struct page));
+
 	if (!is_power_of_2(sizeof(struct page)) ||
 	    !hugetlb_free_vmemmap_enabled) {
 		pr_info("disable freeing vmemmap pages for %s\n", h->name);