[PATCH v4 0/4] add hugetlb_free_vmemmap sysctl

[PATCH v4 0/4] add hugetlb_free_vmemmap sysctl

[Muchun Song]

This series is based on next-20220310.

This series amis to add hugetlb_free_vmemmap sysctl to enable the feature
of freeing vmemmap pages of HugeTLB pages.

v4:
  - Introduce STRUCT_PAGE_SIZE_IS_POWER_OF_2 inspired by Luis.

v3:
  - Add pr_warn_once() (Mike).
  - Handle the transition from enabling to disabling (Luis)

v2:
  - Fix compilation when !CONFIG_MHP_MEMMAP_ON_MEMORY reported by kernel
    test robot <lkp@intel.com>.
  - Move sysctl code from kernel/sysctl.c to mm/hugetlb_vmemmap.c.

Muchun Song (4):
  mm: hugetlb_vmemmap: introduce STRUCT_PAGE_SIZE_IS_POWER_OF_2
  mm: memory_hotplug: override memmap_on_memory when
    hugetlb_free_vmemmap=on
  sysctl: allow to set extra1 to SYSCTL_ONE
  mm: hugetlb_vmemmap: add hugetlb_free_vmemmap sysctl

 Documentation/admin-guide/sysctl/vm.rst |  14 +++++
 Kbuild                                  |  12 ++++
 fs/Kconfig                              |   2 +-
 include/linux/memory_hotplug.h          |   9 +++
 include/linux/mm_types.h                |   2 +
 kernel/sysctl.c                         |   2 +-
 mm/Kconfig                              |   3 +
 mm/hugetlb_vmemmap.c                    | 107 ++++++++++++++++++++++++--------
 mm/hugetlb_vmemmap.h                    |   4 +-
 mm/memory_hotplug.c                     |  27 ++++++--
 mm/struct_page_size.c                   |  19 ++++++
 scripts/check_struct_page_po2.sh        |  11 ++++
 12 files changed, 177 insertions(+), 35 deletions(-)
 create mode 100644 mm/struct_page_size.c
 create mode 100755 scripts/check_struct_page_po2.sh

-- 
2.11.0

[PATCH v4 1/4] mm: hugetlb_vmemmap: introduce STRUCT_PAGE_SIZE_IS_POWER_OF_2

[Muchun Song]

If the size of "struct page" is not the power of two and this
feature is enabled, then the vmemmap pages of HugeTLB will be
corrupted after remapping (panic is about to happen in theory).
But this only exists when !CONFIG_MEMCG && !CONFIG_SLUB on
x86_64.  However, it is not a conventional configuration nowadays.
So it is not a real word issue, just the result of a code review.
But we have to prevent anyone from configuring that combined
configuration.  In order to avoid many checks like "is_power_of_2
(sizeof(struct page))" through mm/hugetlb_vmemmap.c.  Introduce
STRUCT_PAGE_SIZE_IS_POWER_OF_2 to detect if the size of struct
page is power of 2 and make this feature depends on this new
config.  Then we could prevent anyone do any unexpected
configuration.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 Kbuild                           | 12 ++++++++++++
 fs/Kconfig                       |  2 +-
 include/linux/mm_types.h         |  2 ++
 mm/Kconfig                       |  3 +++
 mm/hugetlb_vmemmap.c             |  6 ------
 mm/struct_page_size.c            | 19 +++++++++++++++++++
 scripts/check_struct_page_po2.sh | 11 +++++++++++
 7 files changed, 48 insertions(+), 7 deletions(-)
 create mode 100644 mm/struct_page_size.c
 create mode 100755 scripts/check_struct_page_po2.sh

diff --git a/Kbuild b/Kbuild
index fa441b98c9f6..6bb97d348d62 100644
--- a/Kbuild
+++ b/Kbuild
@@ -14,6 +14,18 @@ $(bounds-file): kernel/bounds.s FORCE
 	$(call filechk,offsets,__LINUX_BOUNDS_H__)
 
 #####
+# Generate struct_page_size.h. Must follows bounds.h.
+
+struct_page_size-file := include/generated/struct_page_size.h
+
+always-y := $(struct_page_size-file)
+targets := mm/struct_page_size.s
+
+$(struct_page_size-file): mm/struct_page_size.s FORCE
+	$(call filechk,offsets,__LINUX_STRUCT_PAGE_SIZE_H__)
+	$(Q)$(MAKE) -f $(srctree)/Makefile syncconfig
+
+#####
 # Generate timeconst.h
 
 timeconst-file := include/generated/timeconst.h
diff --git a/fs/Kconfig b/fs/Kconfig
index 7f2455e8e18a..b8b722f7f773 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -248,7 +248,7 @@ config HUGETLB_PAGE
 config HUGETLB_PAGE_FREE_VMEMMAP
 	def_bool HUGETLB_PAGE
 	depends on X86_64
-	depends on SPARSEMEM_VMEMMAP
+	depends on SPARSEMEM_VMEMMAP && STRUCT_PAGE_SIZE_IS_POWER_OF_2
 
 config HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON
 	bool "Default freeing vmemmap pages of HugeTLB to on"
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 8834e38c06a4..b4defcea6534 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -223,6 +223,7 @@ struct page {
 #endif
 } _struct_page_alignment;
 
+#ifndef __GENERATING_STRUCT_PAGE_SIZE_IS_POWER_OF_2_H
 /**
  * struct folio - Represents a contiguous set of bytes.
  * @flags: Identical to the page flags.
@@ -844,5 +845,6 @@ enum fault_flag {
 	FAULT_FLAG_INSTRUCTION =	1 << 8,
 	FAULT_FLAG_INTERRUPTIBLE =	1 << 9,
 };
+#endif /* __GENERATING_STRUCT_PAGE_SIZE_IS_POWER_OF_2_H */
 
 #endif /* _LINUX_MM_TYPES_H */
diff --git a/mm/Kconfig b/mm/Kconfig
index 034d87953600..9314bd34f49e 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -2,6 +2,9 @@
 
 menu "Memory Management options"
 
+config STRUCT_PAGE_SIZE_IS_POWER_OF_2
+	def_bool $(success,test "$(shell, $(srctree)/scripts/check_struct_page_po2.sh)" = 1)
+
 config SELECT_MEMORY_MODEL
 	def_bool y
 	depends on ARCH_SELECT_MEMORY_MODEL
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 791626983c2e..33ecb77c2b2a 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -194,12 +194,6 @@ EXPORT_SYMBOL(hugetlb_free_vmemmap_enabled_key);
 
 static int __init early_hugetlb_free_vmemmap_param(char *buf)
 {
-	/* We cannot optimize if a "struct page" crosses page boundaries. */
-	if (!is_power_of_2(sizeof(struct page))) {
-		pr_warn("cannot free vmemmap pages because \"struct page\" crosses page boundaries\n");
-		return 0;
-	}
-
 	if (!buf)
 		return -EINVAL;
 
diff --git a/mm/struct_page_size.c b/mm/struct_page_size.c
new file mode 100644
index 000000000000..5749609aa1b3
--- /dev/null
+++ b/mm/struct_page_size.c
@@ -0,0 +1,19 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Generate definitions needed by the preprocessor.
+ * This code generates raw asm output which is post-processed
+ * to extract and format the required data.
+ */
+
+#define __GENERATING_STRUCT_PAGE_SIZE_IS_POWER_OF_2_H
+/* Include headers that define the enum constants of interest */
+#include <linux/mm_types.h>
+#include <linux/kbuild.h>
+#include <linux/log2.h>
+
+int main(void)
+{
+	DEFINE(STRUCT_PAGE_SIZE_IS_POWER_OF_2, is_power_of_2(sizeof(struct page)));
+
+	return 0;
+}
diff --git a/scripts/check_struct_page_po2.sh b/scripts/check_struct_page_po2.sh
new file mode 100755
index 000000000000..9547ad3aca05
--- /dev/null
+++ b/scripts/check_struct_page_po2.sh
@@ -0,0 +1,11 @@
+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+#
+# Check if the size of "struct page" is power of 2
+
+file="include/generated/struct_page_size.h"
+if [ ! -f "$file" ]; then
+	exit 1
+fi
+
+grep STRUCT_PAGE_SIZE_IS_POWER_OF_2 "$file" | cut -d' ' -f3
-- 
2.11.0

[PATCH v4 2/4] mm: memory_hotplug: override memmap_on_memory when hugetlb_free_vmemmap=on

[Muchun Song]

When "hugetlb_free_vmemmap=on" and "memory_hotplug.memmap_on_memory"
are both passed to boot cmdline, the variable of "memmap_on_memory"
will be set to 1 even if the vmemmap pages will not be allocated from
the hotadded memory since the former takes precedence over the latter.
In the next patch, we want to enable or disable the feature of freeing
vmemmap pages of HugeTLB via sysctl.  We need a way to know if the
feature of memory_hotplug.memmap_on_memory is enabled when enabling
the feature of freeing vmemmap pages since those two features are not
compatible, however, the variable of "memmap_on_memory" cannot indicate
this nowadays.  Do not set "memmap_on_memory" to 1 when both parameters
are passed to cmdline, in this case, "memmap_on_memory" could indicate
if this feature is enabled by the users.

Also introduce mhp_memmap_on_memory() helper to move the definition of
"memmap_on_memory" to the scope of CONFIG_MHP_MEMMAP_ON_MEMORY.  In the
next patch, mhp_memmap_on_memory() will also be exported to be used in
hugetlb_vmemmap.c.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 mm/memory_hotplug.c | 32 ++++++++++++++++++++++++++------
 1 file changed, 26 insertions(+), 6 deletions(-)

diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index 416b38ca8def..da594b382829 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -42,14 +42,36 @@
 #include "internal.h"
 #include "shuffle.h"
 
+#ifdef CONFIG_MHP_MEMMAP_ON_MEMORY
+static int memmap_on_memory_set(const char *val, const struct kernel_param *kp)
+{
+	if (hugetlb_free_vmemmap_enabled())
+		return 0;
+	return param_set_bool(val, kp);
+}
+
+static const struct kernel_param_ops memmap_on_memory_ops = {
+	.flags	= KERNEL_PARAM_OPS_FL_NOARG,
+	.set	= memmap_on_memory_set,
+	.get	= param_get_bool,
+};
 
 /*
  * memory_hotplug.memmap_on_memory parameter
  */
 static bool memmap_on_memory __ro_after_init;
-#ifdef CONFIG_MHP_MEMMAP_ON_MEMORY
-module_param(memmap_on_memory, bool, 0444);
+module_param_cb(memmap_on_memory, &memmap_on_memory_ops, &memmap_on_memory, 0444);
 MODULE_PARM_DESC(memmap_on_memory, "Enable memmap on memory for memory hotplug");
+
+static inline bool mhp_memmap_on_memory(void)
+{
+	return memmap_on_memory;
+}
+#else
+static inline bool mhp_memmap_on_memory(void)
+{
+	return false;
+}
 #endif
 
 enum {
@@ -1288,9 +1310,7 @@ bool mhp_supports_memmap_on_memory(unsigned long size)
 	 *       altmap as an alternative source of memory, and we do not exactly
 	 *       populate a single PMD.
 	 */
-	return memmap_on_memory &&
-	       !hugetlb_free_vmemmap_enabled() &&
-	       IS_ENABLED(CONFIG_MHP_MEMMAP_ON_MEMORY) &&
+	return mhp_memmap_on_memory() &&
 	       size == memory_block_size_bytes() &&
 	       IS_ALIGNED(vmemmap_size, PMD_SIZE) &&
 	       IS_ALIGNED(remaining_size, (pageblock_nr_pages << PAGE_SHIFT));
@@ -2074,7 +2094,7 @@ static int __ref try_remove_memory(u64 start, u64 size)
 	 * We only support removing memory added with MHP_MEMMAP_ON_MEMORY in
 	 * the same granularity it was added - a single memory block.
 	 */
-	if (memmap_on_memory) {
+	if (mhp_memmap_on_memory()) {
 		nr_vmemmap_pages = walk_memory_blocks(start, size, NULL,
 						      get_nr_vmemmap_pages_cb);
 		if (nr_vmemmap_pages) {
-- 
2.11.0

[PATCH v4 3/4] sysctl: allow to set extra1 to SYSCTL_ONE

[Muchun Song]

proc_do_static_key() does not consider the situation where a sysctl is only
allowed to be enabled and cannot be disabled under certain circumstances
since it set "->extra1" to SYSCTL_ZERO unconditionally.  This patch add the
functionality to set "->extra1" accordingly.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 kernel/sysctl.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 770d5f7c7ae4..1e89c3e428ad 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -1638,7 +1638,7 @@ int proc_do_static_key(struct ctl_table *table, int write,
 		.data   = &val,
 		.maxlen = sizeof(val),
 		.mode   = table->mode,
-		.extra1 = SYSCTL_ZERO,
+		.extra1 = table->extra1 == SYSCTL_ONE ? SYSCTL_ONE : SYSCTL_ZERO,
 		.extra2 = SYSCTL_ONE,
 	};
 
-- 
2.11.0

[PATCH v4 4/4] mm: hugetlb_vmemmap: add hugetlb_free_vmemmap sysctl

[Muchun Song]

We must add "hugetlb_free_vmemmap=on" to boot cmdline and reboot the
server to enable the feature of freeing vmemmap pages of HugeTLB
pages.  Rebooting usually takes a long time.  Add a sysctl to enable
or disable the feature at runtime without rebooting.

Disabling requires there is no any optimized HugeTLB page in the
system.  If you fail to disable it, you can set "nr_hugepages" to 0
and then retry.

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
 Documentation/admin-guide/sysctl/vm.rst |  14 +++++
 include/linux/memory_hotplug.h          |   9 +++
 mm/hugetlb_vmemmap.c                    | 101 +++++++++++++++++++++++++-------
 mm/hugetlb_vmemmap.h                    |   4 +-
 mm/memory_hotplug.c                     |   7 +--
 5 files changed, 108 insertions(+), 27 deletions(-)

diff --git a/Documentation/admin-guide/sysctl/vm.rst b/Documentation/admin-guide/sysctl/vm.rst
index f4804ce37c58..9e0e153ed935 100644
--- a/Documentation/admin-guide/sysctl/vm.rst
+++ b/Documentation/admin-guide/sysctl/vm.rst
@@ -561,6 +561,20 @@ Change the minimum size of the hugepage pool.
 See Documentation/admin-guide/mm/hugetlbpage.rst
 
 
+hugetlb_free_vmemmap
+====================
+
+Enable (set to 1) or disable (set to 0) the feature of optimizing vmemmap
+pages associated with each HugeTLB page.  Once true, the vmemmap pages of
+subsequent allocation of HugeTLB pages from buddy system will be optimized,
+whereas already allocated HugeTLB pages will not be optimized.  If you fail
+to disable this feature, you can set "nr_hugepages" to 0 and then retry
+since it is only allowed to be disabled after there is no any optimized
+HugeTLB page in the system.
+
+See Documentation/admin-guide/mm/hugetlbpage.rst
+
+
 nr_hugepages_mempolicy
 ======================
 
diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 1ce6f8044f1e..9b015b254e86 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -348,4 +348,13 @@ void arch_remove_linear_mapping(u64 start, u64 size);
 extern bool mhp_supports_memmap_on_memory(unsigned long size);
 #endif /* CONFIG_MEMORY_HOTPLUG */
 
+#ifdef CONFIG_MHP_MEMMAP_ON_MEMORY
+bool mhp_memmap_on_memory(void);
+#else
+static inline bool mhp_memmap_on_memory(void)
+{
+	return false;
+}
+#endif
+
 #endif /* __LINUX_MEMORY_HOTPLUG_H */
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 33ecb77c2b2a..f920073d52ba 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -176,6 +176,7 @@
  */
 #define pr_fmt(fmt)	"HugeTLB: " fmt
 
+#include <linux/memory_hotplug.h>
 #include "hugetlb_vmemmap.h"
 
 /*
@@ -192,6 +193,10 @@ DEFINE_STATIC_KEY_MAYBE(CONFIG_HUGETLB_PAGE_FREE_VMEMMAP_DEFAULT_ON,
 			hugetlb_free_vmemmap_enabled_key);
 EXPORT_SYMBOL(hugetlb_free_vmemmap_enabled_key);
 
+/* How many HugeTLB pages with vmemmap pages optimized. */
+static atomic_long_t optimized_pages = ATOMIC_LONG_INIT(0);
+static DECLARE_RWSEM(sysctl_rwsem);
+
 static int __init early_hugetlb_free_vmemmap_param(char *buf)
 {
 	if (!buf)
@@ -208,11 +213,6 @@ static int __init early_hugetlb_free_vmemmap_param(char *buf)
 }
 early_param("hugetlb_free_vmemmap", early_hugetlb_free_vmemmap_param);
 
-static inline unsigned long free_vmemmap_pages_size_per_hpage(struct hstate *h)
-{
-	return (unsigned long)free_vmemmap_pages_per_hpage(h) << PAGE_SHIFT;
-}
-
 /*
  * Previously discarded vmemmap pages will be allocated and remapping
  * after this function returns zero.
@@ -221,14 +221,18 @@ int alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
 {
 	int ret;
 	unsigned long vmemmap_addr = (unsigned long)head;
-	unsigned long vmemmap_end, vmemmap_reuse;
+	unsigned long vmemmap_end, vmemmap_reuse, vmemmap_pages;
 
 	if (!HPageVmemmapOptimized(head))
 		return 0;
 
-	vmemmap_addr += RESERVE_VMEMMAP_SIZE;
-	vmemmap_end = vmemmap_addr + free_vmemmap_pages_size_per_hpage(h);
-	vmemmap_reuse = vmemmap_addr - PAGE_SIZE;
+	vmemmap_addr	+= RESERVE_VMEMMAP_SIZE;
+	vmemmap_pages	= free_vmemmap_pages_per_hpage(h);
+	vmemmap_end	= vmemmap_addr + (vmemmap_pages << PAGE_SHIFT);
+	vmemmap_reuse	= vmemmap_addr - PAGE_SIZE;
+
+	VM_BUG_ON_PAGE(!vmemmap_pages, head);
+
 	/*
 	 * The pages which the vmemmap virtual address range [@vmemmap_addr,
 	 * @vmemmap_end) are mapped to are freed to the buddy allocator, and
@@ -238,8 +242,14 @@ int alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
 	 */
 	ret = vmemmap_remap_alloc(vmemmap_addr, vmemmap_end, vmemmap_reuse,
 				  GFP_KERNEL | __GFP_NORETRY | __GFP_THISNODE);
-	if (!ret)
+	if (!ret) {
 		ClearHPageVmemmapOptimized(head);
+		/*
+		 * Paired with acquire semantic in
+		 * hugetlb_free_vmemmap_handler().
+		 */
+		atomic_long_dec_return_release(&optimized_pages);
+	}
 
 	return ret;
 }
@@ -247,22 +257,28 @@ int alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
 void free_huge_page_vmemmap(struct hstate *h, struct page *head)
 {
 	unsigned long vmemmap_addr = (unsigned long)head;
-	unsigned long vmemmap_end, vmemmap_reuse;
+	unsigned long vmemmap_end, vmemmap_reuse, vmemmap_pages;
 
-	if (!free_vmemmap_pages_per_hpage(h))
-		return;
+	down_read(&sysctl_rwsem);
+	vmemmap_pages = free_vmemmap_pages_per_hpage(h);
+	if (!vmemmap_pages)
+		goto out;
 
-	vmemmap_addr += RESERVE_VMEMMAP_SIZE;
-	vmemmap_end = vmemmap_addr + free_vmemmap_pages_size_per_hpage(h);
-	vmemmap_reuse = vmemmap_addr - PAGE_SIZE;
+	vmemmap_addr	+= RESERVE_VMEMMAP_SIZE;
+	vmemmap_end	= vmemmap_addr + (vmemmap_pages << PAGE_SHIFT);
+	vmemmap_reuse	= vmemmap_addr - PAGE_SIZE;
 
 	/*
 	 * Remap the vmemmap virtual address range [@vmemmap_addr, @vmemmap_end)
 	 * to the page which @vmemmap_reuse is mapped to, then free the pages
 	 * which the range [@vmemmap_addr, @vmemmap_end] is mapped to.
 	 */
-	if (!vmemmap_remap_free(vmemmap_addr, vmemmap_end, vmemmap_reuse))
+	if (!vmemmap_remap_free(vmemmap_addr, vmemmap_end, vmemmap_reuse)) {
 		SetHPageVmemmapOptimized(head);
+		atomic_long_inc(&optimized_pages);
+	}
+out:
+	up_read(&sysctl_rwsem);
 }
 
 void __init hugetlb_vmemmap_init(struct hstate *h)
@@ -278,9 +294,6 @@ void __init hugetlb_vmemmap_init(struct hstate *h)
 	BUILD_BUG_ON(__NR_USED_SUBPAGE >=
 		     RESERVE_VMEMMAP_SIZE / sizeof(struct page));
 
-	if (!hugetlb_free_vmemmap_enabled())
-		return;
-
 	vmemmap_pages = (nr_pages * sizeof(struct page)) >> PAGE_SHIFT;
 	/*
 	 * The head page is not to be freed to buddy allocator, the other tail
@@ -296,3 +309,51 @@ void __init hugetlb_vmemmap_init(struct hstate *h)
 	pr_info("can free %d vmemmap pages for %s\n", h->nr_free_vmemmap_pages,
 		h->name);
 }
+
+static int hugetlb_free_vmemmap_handler(struct ctl_table *table, int write,
+					void *buffer, size_t *length,
+					loff_t *ppos)
+{
+	int ret;
+
+	down_write(&sysctl_rwsem);
+	/*
+	 * Cannot be disabled when there is at lease one optimized
+	 * HugeTLB in the system.
+	 *
+	 * The acquire semantic is paired with release semantic in
+	 * alloc_huge_page_vmemmap(). If we saw the @optimized_pages
+	 * with 0, all the operations of vmemmap pages remapping from
+	 * alloc_huge_page_vmemmap() are visible too so that we can
+	 * safely disable static key.
+	 */
+	table->extra1 = atomic_long_read_acquire(&optimized_pages) ?
+			SYSCTL_ONE : SYSCTL_ZERO;
+	ret = proc_do_static_key(table, write, buffer, length, ppos);
+	up_write(&sysctl_rwsem);
+
+	return ret;
+}
+
+static struct ctl_table hugetlb_vmemmap_sysctls[] = {
+	{
+		.procname	= "hugetlb_free_vmemmap",
+		.data		= &hugetlb_free_vmemmap_enabled_key.key,
+		.mode		= 0644,
+		.proc_handler	= hugetlb_free_vmemmap_handler,
+	},
+	{ }
+};
+
+static __init int hugetlb_vmemmap_sysctls_init(void)
+{
+	/*
+	 * The vmemmap pages cannot be optimized if
+	 * "memory_hotplug.memmap_on_memory" is enabled.
+	 */
+	if (!mhp_memmap_on_memory())
+		register_sysctl_init("vm", hugetlb_vmemmap_sysctls);
+
+	return 0;
+}
+late_initcall(hugetlb_vmemmap_sysctls_init);
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index cb2bef8f9e73..b67a159027f4 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -21,7 +21,9 @@ void hugetlb_vmemmap_init(struct hstate *h);
  */
 static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
 {
-	return h->nr_free_vmemmap_pages;
+	if (hugetlb_free_vmemmap_enabled())
+		return h->nr_free_vmemmap_pages;
+	return 0;
 }
 #else
 static inline int alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index da594b382829..793c04cfe46f 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -63,15 +63,10 @@ static bool memmap_on_memory __ro_after_init;
 module_param_cb(memmap_on_memory, &memmap_on_memory_ops, &memmap_on_memory, 0444);
 MODULE_PARM_DESC(memmap_on_memory, "Enable memmap on memory for memory hotplug");
 
-static inline bool mhp_memmap_on_memory(void)
+bool mhp_memmap_on_memory(void)
 {
 	return memmap_on_memory;
 }
-#else
-static inline bool mhp_memmap_on_memory(void)
-{
-	return false;
-}
 #endif
 
 enum {
-- 
2.11.0

Re: [PATCH v4 1/4] mm: hugetlb_vmemmap: introduce STRUCT_PAGE_SIZE_IS_POWER_OF_2

[Luis Chamberlain]

On Fri, Mar 18, 2022 at 06:07:17PM +0800, Muchun Song wrote:

You can add Suggested-by tag here.

> Signed-off-by: Muchun Song <songmuchun@bytedance.com>
> ---
>  Kbuild                           | 12 ++++++++++++
>  fs/Kconfig                       |  2 +-
>  include/linux/mm_types.h         |  2 ++
>  mm/Kconfig                       |  3 +++
>  mm/hugetlb_vmemmap.c             |  6 ------
>  mm/struct_page_size.c            | 19 +++++++++++++++++++
>  scripts/check_struct_page_po2.sh | 11 +++++++++++
>  7 files changed, 48 insertions(+), 7 deletions(-)
>  create mode 100644 mm/struct_page_size.c
>  create mode 100755 scripts/check_struct_page_po2.sh
> 
> diff --git a/Kbuild b/Kbuild
> index fa441b98c9f6..6bb97d348d62 100644
> --- a/Kbuild
> +++ b/Kbuild
> @@ -14,6 +14,18 @@ $(bounds-file): kernel/bounds.s FORCE
>  	$(call filechk,offsets,__LINUX_BOUNDS_H__)
>  
>  #####
> +# Generate struct_page_size.h. Must follows bounds.h.
> +
> +struct_page_size-file := include/generated/struct_page_size.h
> +
> +always-y := $(struct_page_size-file)
> +targets := mm/struct_page_size.s
> +
> +$(struct_page_size-file): mm/struct_page_size.s FORCE
> +	$(call filechk,offsets,__LINUX_STRUCT_PAGE_SIZE_H__)
> +	$(Q)$(MAKE) -f $(srctree)/Makefile syncconfig
> +
> +#####

Shouldn't this go into mm/Makefile instead?

> diff --git a/mm/Kconfig b/mm/Kconfig
> index 034d87953600..9314bd34f49e 100644
> --- a/mm/Kconfig
> +++ b/mm/Kconfig
> @@ -2,6 +2,9 @@
>  
>  menu "Memory Management options"
>  
> +config STRUCT_PAGE_SIZE_IS_POWER_OF_2
> +	def_bool $(success,test "$(shell, $(srctree)/scripts/check_struct_page_po2.sh)" = 1)
> +
>  config SELECT_MEMORY_MODEL
>  	def_bool y
>  	depends on ARCH_SELECT_MEMORY_MODEL
> new file mode 100755
> index 000000000000..9547ad3aca05
> --- /dev/null
> +++ b/scripts/check_struct_page_po2.sh
> @@ -0,0 +1,11 @@
> +#!/bin/sh
> +# SPDX-License-Identifier: GPL-2.0
> +#
> +# Check if the size of "struct page" is power of 2
> +
> +file="include/generated/struct_page_size.h"
> +if [ ! -f "$file" ]; then

Does this really work if one is workig off of a very clean build
like make mrproper and then make menuconfig or or mrproper followed
by a defconfig file ? Have you tried it for both cases po2 and npo2?

Because isn't include/generated/struct_page_size.h generated? At
which point does it get generated and why would the condition hole
true that the file exists at a new 'make menuconfig' time?

  Luis

Re: [PATCH v4 1/4] mm: hugetlb_vmemmap: introduce STRUCT_PAGE_SIZE_IS_POWER_OF_2

[Muchun Song]

On Sat, Mar 19, 2022 at 12:40 AM Luis Chamberlain <mcgrof@kernel.org> wrote:
>
> On Fri, Mar 18, 2022 at 06:07:17PM +0800, Muchun Song wrote:
>
> You can add Suggested-by tag here.

Will do. Sorry for forgetting it.

>
> > Signed-off-by: Muchun Song <songmuchun@bytedance.com>
> > ---
> >  Kbuild                           | 12 ++++++++++++
> >  fs/Kconfig                       |  2 +-
> >  include/linux/mm_types.h         |  2 ++
> >  mm/Kconfig                       |  3 +++
> >  mm/hugetlb_vmemmap.c             |  6 ------
> >  mm/struct_page_size.c            | 19 +++++++++++++++++++
> >  scripts/check_struct_page_po2.sh | 11 +++++++++++
> >  7 files changed, 48 insertions(+), 7 deletions(-)
> >  create mode 100644 mm/struct_page_size.c
> >  create mode 100755 scripts/check_struct_page_po2.sh
> >
> > diff --git a/Kbuild b/Kbuild
> > index fa441b98c9f6..6bb97d348d62 100644
> > --- a/Kbuild
> > +++ b/Kbuild
> > @@ -14,6 +14,18 @@ $(bounds-file): kernel/bounds.s FORCE
> >       $(call filechk,offsets,__LINUX_BOUNDS_H__)
> >
> >  #####
> > +# Generate struct_page_size.h. Must follows bounds.h.
> > +
> > +struct_page_size-file := include/generated/struct_page_size.h
> > +
> > +always-y := $(struct_page_size-file)
> > +targets := mm/struct_page_size.s
> > +
> > +$(struct_page_size-file): mm/struct_page_size.s FORCE
> > +     $(call filechk,offsets,__LINUX_STRUCT_PAGE_SIZE_H__)
> > +     $(Q)$(MAKE) -f $(srctree)/Makefile syncconfig
> > +
> > +#####
>
> Shouldn't this go into mm/Makefile instead?
>

We should guarantee that the include/generated/struct_page_size.h
which Kconfig depends on is created before processing Makefile
since processing Kconfig is before Makefile. Right?

> > diff --git a/mm/Kconfig b/mm/Kconfig
> > index 034d87953600..9314bd34f49e 100644
> > --- a/mm/Kconfig
> > +++ b/mm/Kconfig
> > @@ -2,6 +2,9 @@
> >
> >  menu "Memory Management options"
> >
> > +config STRUCT_PAGE_SIZE_IS_POWER_OF_2
> > +     def_bool $(success,test "$(shell, $(srctree)/scripts/check_struct_page_po2.sh)" = 1)
> > +
> >  config SELECT_MEMORY_MODEL
> >       def_bool y
> >       depends on ARCH_SELECT_MEMORY_MODEL
> > new file mode 100755
> > index 000000000000..9547ad3aca05
> > --- /dev/null
> > +++ b/scripts/check_struct_page_po2.sh
> > @@ -0,0 +1,11 @@
> > +#!/bin/sh
> > +# SPDX-License-Identifier: GPL-2.0
> > +#
> > +# Check if the size of "struct page" is power of 2
> > +
> > +file="include/generated/struct_page_size.h"
> > +if [ ! -f "$file" ]; then
>
> Does this really work if one is workig off of a very clean build
> like make mrproper and then make menuconfig or or mrproper followed
> by a defconfig file ? Have you tried it for both cases po2 and npo2?
>
> Because isn't include/generated/struct_page_size.h generated? At
> which point does it get generated and why would the condition hole
> true that the file exists at a new 'make menuconfig' time?
>

You are right. include/generated/struct_page_size.h does not exist
in this case, CONFIG_STRUCT_PAGE_SIZE_IS_POWER_OF_2
will be default off in .config. Then it will be switched on/off accordingly
when you build the kernel, for instance make bzImage, which is done via
"make syncconfig" which follows the generation of struct_page_size.h.

While testing this case, I found some bugs. The following patch
could fix this.  Thanks.

--- a/Kbuild
+++ b/Kbuild
@@ -21,6 +21,8 @@ struct_page_size-file := include/generated/struct_page_size.h
 always-y := $(struct_page_size-file)
 targets := mm/struct_page_size.s

+mm/struct_page_size.s: $(timeconst-file) $(bounds-file)
+
 $(struct_page_size-file): mm/struct_page_size.s FORCE
        $(call filechk,offsets,__LINUX_STRUCT_PAGE_SIZE_H__)
        $(Q)$(MAKE) -f $(srctree)/Makefile syncconfig
diff --git a/scripts/check_struct_page_po2.sh b/scripts/check_struct_page_po2.sh
index 9547ad3aca05..1764ef9a4f1d 100755
--- a/scripts/check_struct_page_po2.sh
+++ b/scripts/check_struct_page_po2.sh
@@ -4,8 +4,6 @@
 # Check if the size of "struct page" is power of 2

 file="include/generated/struct_page_size.h"
-if [ ! -f "$file" ]; then
-       exit 1
+if [ -f "$file" ]; then
+       grep STRUCT_PAGE_SIZE_IS_POWER_OF_2 "$file" | cut -d' ' -f3
 fi
-
-grep STRUCT_PAGE_SIZE_IS_POWER_OF_2 "$file" | cut -d' ' -f3