* [PATCH 1/2] mm/hugetlb: extract sysfs into hugetlb_sysfs.c
2025-11-03 8:22 [PATCH 0/2] mm/hugetlb: refactor sysfs/sysctl interfaces Hui Zhu
@ 2025-11-03 8:22 ` Hui Zhu
2025-11-03 16:28 ` David Hildenbrand (Red Hat)
2025-11-03 8:22 ` [PATCH 2/2] mm/hugetlb: extract sysctl into hugetlb_sysctl.c Hui Zhu
2025-11-04 4:43 ` [PATCH 0/2] mm/hugetlb: refactor sysfs/sysctl interfaces SeongJae Park
2 siblings, 1 reply; 8+ messages in thread
From: Hui Zhu @ 2025-11-03 8:22 UTC (permalink / raw)
To: Andrew Morton, Muchun Song, Oscar Salvador, David Hildenbrand,
linux-kernel, linux-mm
Cc: Geliang Tang, Hui Zhu
From: Geliang Tang <geliang@kernel.org>
Currently, hugetlb.c contains both core management logic and sysfs
interface implementations, making it difficult to maintain. This patch
extracts the sysfs-related code into a dedicated file to improve code
organization.
The following components are moved to mm/hugetlb_sysfs.c:
- hugetlb page demote functions (demote_free_hugetlb_folios,
demote_pool_huge_page)
- sysfs attribute definitions and handlers
- sysfs kobject management functions
- NUMA per-node hstate attribute registration
Several inline helper functions and macros are moved to
mm/hugetlb_internal.h:
- hstate_is_gigantic_no_runtime()
- next_node_allowed()
- get_valid_node_allowed()
- hstate_next_node_to_alloc()
- hstate_next_node_to_free()
- for_each_node_mask_to_alloc/to_free macros
To support code sharing, these functions are changed from static to
exported symbols:
- remove_hugetlb_folio()
- add_hugetlb_folio()
- init_new_hugetlb_folio()
- prep_and_add_allocated_folios()
- __nr_hugepages_store_common()
The Makefile is updated to compile hugetlb_sysfs.o when
CONFIG_HUGETLBFS is enabled. This maintains all existing functionality
while improving maintainability by separating concerns.
Signed-off-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Hui Zhu <zhuhui@kylinos.cn>
---
mm/Makefile | 2 +-
mm/hugetlb.c | 720 +-----------------------------------------
mm/hugetlb_internal.h | 110 +++++++
mm/hugetlb_sysfs.c | 632 ++++++++++++++++++++++++++++++++++++
4 files changed, 752 insertions(+), 712 deletions(-)
create mode 100644 mm/hugetlb_internal.h
create mode 100644 mm/hugetlb_sysfs.c
diff --git a/mm/Makefile b/mm/Makefile
index 21abb3353550..b9edfce6c202 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -78,7 +78,7 @@ endif
obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o
obj-$(CONFIG_ZSWAP) += zswap.o
obj-$(CONFIG_HAS_DMA) += dmapool.o
-obj-$(CONFIG_HUGETLBFS) += hugetlb.o
+obj-$(CONFIG_HUGETLBFS) += hugetlb.o hugetlb_sysfs.o
ifdef CONFIG_CMA
obj-$(CONFIG_HUGETLBFS) += hugetlb_cma.o
endif
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 1ea459723cce..1fc24f7e63ac 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -19,7 +19,6 @@
#include <linux/mutex.h>
#include <linux/memblock.h>
#include <linux/minmax.h>
-#include <linux/sysfs.h>
#include <linux/slab.h>
#include <linux/sched/mm.h>
#include <linux/mmdebug.h>
@@ -46,13 +45,12 @@
#include <asm/setup.h>
#include <linux/io.h>
-#include <linux/hugetlb.h>
-#include <linux/hugetlb_cgroup.h>
#include <linux/node.h>
#include <linux/page_owner.h>
#include "internal.h"
#include "hugetlb_vmemmap.h"
#include "hugetlb_cma.h"
+#include "hugetlb_internal.h"
#include <linux/page-isolation.h>
int hugetlb_max_hstate __read_mostly;
@@ -134,17 +132,6 @@ static void hugetlb_free_folio(struct folio *folio)
folio_put(folio);
}
-/*
- * Check if the hstate represents gigantic pages but gigantic page
- * runtime support is not available. This is a common condition used to
- * skip operations that cannot be performed on gigantic pages when runtime
- * support is disabled.
- */
-static inline bool hstate_is_gigantic_no_runtime(struct hstate *h)
-{
- return hstate_is_gigantic(h) && !gigantic_page_runtime_supported();
-}
-
static inline bool subpool_is_free(struct hugepage_subpool *spool)
{
if (spool->count)
@@ -1431,77 +1418,6 @@ static struct folio *dequeue_hugetlb_folio_vma(struct hstate *h,
return NULL;
}
-/*
- * common helper functions for hstate_next_node_to_{alloc|free}.
- * We may have allocated or freed a huge page based on a different
- * nodes_allowed previously, so h->next_node_to_{alloc|free} might
- * be outside of *nodes_allowed. Ensure that we use an allowed
- * node for alloc or free.
- */
-static int next_node_allowed(int nid, nodemask_t *nodes_allowed)
-{
- nid = next_node_in(nid, *nodes_allowed);
- VM_BUG_ON(nid >= MAX_NUMNODES);
-
- return nid;
-}
-
-static int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed)
-{
- if (!node_isset(nid, *nodes_allowed))
- nid = next_node_allowed(nid, nodes_allowed);
- return nid;
-}
-
-/*
- * returns the previously saved node ["this node"] from which to
- * allocate a persistent huge page for the pool and advance the
- * next node from which to allocate, handling wrap at end of node
- * mask.
- */
-static int hstate_next_node_to_alloc(int *next_node,
- nodemask_t *nodes_allowed)
-{
- int nid;
-
- VM_BUG_ON(!nodes_allowed);
-
- nid = get_valid_node_allowed(*next_node, nodes_allowed);
- *next_node = next_node_allowed(nid, nodes_allowed);
-
- return nid;
-}
-
-/*
- * helper for remove_pool_hugetlb_folio() - return the previously saved
- * node ["this node"] from which to free a huge page. Advance the
- * next node id whether or not we find a free huge page to free so
- * that the next attempt to free addresses the next node.
- */
-static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed)
-{
- int nid;
-
- VM_BUG_ON(!nodes_allowed);
-
- nid = get_valid_node_allowed(h->next_nid_to_free, nodes_allowed);
- h->next_nid_to_free = next_node_allowed(nid, nodes_allowed);
-
- return nid;
-}
-
-#define for_each_node_mask_to_alloc(next_node, nr_nodes, node, mask) \
- for (nr_nodes = nodes_weight(*mask); \
- nr_nodes > 0 && \
- ((node = hstate_next_node_to_alloc(next_node, mask)) || 1); \
- nr_nodes--)
-
-#define for_each_node_mask_to_free(hs, nr_nodes, node, mask) \
- for (nr_nodes = nodes_weight(*mask); \
- nr_nodes > 0 && \
- ((node = hstate_next_node_to_free(hs, mask)) || 1); \
- nr_nodes--)
-
#ifdef CONFIG_ARCH_HAS_GIGANTIC_PAGE
#ifdef CONFIG_CONTIG_ALLOC
static struct folio *alloc_gigantic_folio(int order, gfp_t gfp_mask,
@@ -1557,8 +1473,8 @@ static struct folio *alloc_gigantic_folio(int order, gfp_t gfp_mask, int nid,
*
* Must be called with hugetlb lock held.
*/
-static void remove_hugetlb_folio(struct hstate *h, struct folio *folio,
- bool adjust_surplus)
+void remove_hugetlb_folio(struct hstate *h, struct folio *folio,
+ bool adjust_surplus)
{
int nid = folio_nid(folio);
@@ -1593,8 +1509,8 @@ static void remove_hugetlb_folio(struct hstate *h, struct folio *folio,
h->nr_huge_pages_node[nid]--;
}
-static void add_hugetlb_folio(struct hstate *h, struct folio *folio,
- bool adjust_surplus)
+void add_hugetlb_folio(struct hstate *h, struct folio *folio,
+ bool adjust_surplus)
{
int nid = folio_nid(folio);
@@ -1925,7 +1841,7 @@ static void account_new_hugetlb_folio(struct hstate *h, struct folio *folio)
h->nr_huge_pages_node[folio_nid(folio)]++;
}
-static void init_new_hugetlb_folio(struct folio *folio)
+void init_new_hugetlb_folio(struct folio *folio)
{
__folio_set_hugetlb(folio);
INIT_LIST_HEAD(&folio->lru);
@@ -2037,8 +1953,8 @@ static struct folio *alloc_fresh_hugetlb_folio(struct hstate *h,
return folio;
}
-static void prep_and_add_allocated_folios(struct hstate *h,
- struct list_head *folio_list)
+void prep_and_add_allocated_folios(struct hstate *h,
+ struct list_head *folio_list)
{
unsigned long flags;
struct folio *folio, *tmp_f;
@@ -4034,179 +3950,7 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
return 0;
}
-static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst,
- struct list_head *src_list)
-{
- long rc;
- struct folio *folio, *next;
- LIST_HEAD(dst_list);
- LIST_HEAD(ret_list);
-
- rc = hugetlb_vmemmap_restore_folios(src, src_list, &ret_list);
- list_splice_init(&ret_list, src_list);
-
- /*
- * Taking target hstate mutex synchronizes with set_max_huge_pages.
- * Without the mutex, pages added to target hstate could be marked
- * as surplus.
- *
- * Note that we already hold src->resize_lock. To prevent deadlock,
- * use the convention of always taking larger size hstate mutex first.
- */
- mutex_lock(&dst->resize_lock);
-
- list_for_each_entry_safe(folio, next, src_list, lru) {
- int i;
- bool cma;
-
- if (folio_test_hugetlb_vmemmap_optimized(folio))
- continue;
-
- cma = folio_test_hugetlb_cma(folio);
-
- list_del(&folio->lru);
-
- split_page_owner(&folio->page, huge_page_order(src), huge_page_order(dst));
- pgalloc_tag_split(folio, huge_page_order(src), huge_page_order(dst));
-
- for (i = 0; i < pages_per_huge_page(src); i += pages_per_huge_page(dst)) {
- struct page *page = folio_page(folio, i);
- /* Careful: see __split_huge_page_tail() */
- struct folio *new_folio = (struct folio *)page;
-
- clear_compound_head(page);
- prep_compound_page(page, dst->order);
-
- new_folio->mapping = NULL;
- init_new_hugetlb_folio(new_folio);
- /* Copy the CMA flag so that it is freed correctly */
- if (cma)
- folio_set_hugetlb_cma(new_folio);
- list_add(&new_folio->lru, &dst_list);
- }
- }
-
- prep_and_add_allocated_folios(dst, &dst_list);
-
- mutex_unlock(&dst->resize_lock);
-
- return rc;
-}
-
-static long demote_pool_huge_page(struct hstate *src, nodemask_t *nodes_allowed,
- unsigned long nr_to_demote)
- __must_hold(&hugetlb_lock)
-{
- int nr_nodes, node;
- struct hstate *dst;
- long rc = 0;
- long nr_demoted = 0;
-
- lockdep_assert_held(&hugetlb_lock);
-
- /* We should never get here if no demote order */
- if (!src->demote_order) {
- pr_warn("HugeTLB: NULL demote order passed to demote_pool_huge_page.\n");
- return -EINVAL; /* internal error */
- }
- dst = size_to_hstate(PAGE_SIZE << src->demote_order);
-
- for_each_node_mask_to_free(src, nr_nodes, node, nodes_allowed) {
- LIST_HEAD(list);
- struct folio *folio, *next;
-
- list_for_each_entry_safe(folio, next, &src->hugepage_freelists[node], lru) {
- if (folio_test_hwpoison(folio))
- continue;
-
- remove_hugetlb_folio(src, folio, false);
- list_add(&folio->lru, &list);
-
- if (++nr_demoted == nr_to_demote)
- break;
- }
-
- spin_unlock_irq(&hugetlb_lock);
-
- rc = demote_free_hugetlb_folios(src, dst, &list);
-
- spin_lock_irq(&hugetlb_lock);
-
- list_for_each_entry_safe(folio, next, &list, lru) {
- list_del(&folio->lru);
- add_hugetlb_folio(src, folio, false);
-
- nr_demoted--;
- }
-
- if (rc < 0 || nr_demoted == nr_to_demote)
- break;
- }
-
- /*
- * Not absolutely necessary, but for consistency update max_huge_pages
- * based on pool changes for the demoted page.
- */
- src->max_huge_pages -= nr_demoted;
- dst->max_huge_pages += nr_demoted << (huge_page_order(src) - huge_page_order(dst));
-
- if (rc < 0)
- return rc;
-
- if (nr_demoted)
- return nr_demoted;
- /*
- * Only way to get here is if all pages on free lists are poisoned.
- * Return -EBUSY so that caller will not retry.
- */
- return -EBUSY;
-}
-
-#define HSTATE_ATTR_RO(_name) \
- static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
-
-#define HSTATE_ATTR_WO(_name) \
- static struct kobj_attribute _name##_attr = __ATTR_WO(_name)
-
-#define HSTATE_ATTR(_name) \
- static struct kobj_attribute _name##_attr = __ATTR_RW(_name)
-
-static struct kobject *hugepages_kobj;
-static struct kobject *hstate_kobjs[HUGE_MAX_HSTATE];
-
-static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp);
-
-static struct hstate *kobj_to_hstate(struct kobject *kobj, int *nidp)
-{
- int i;
-
- for (i = 0; i < HUGE_MAX_HSTATE; i++)
- if (hstate_kobjs[i] == kobj) {
- if (nidp)
- *nidp = NUMA_NO_NODE;
- return &hstates[i];
- }
-
- return kobj_to_node_hstate(kobj, nidp);
-}
-
-static ssize_t nr_hugepages_show_common(struct kobject *kobj,
- struct kobj_attribute *attr, char *buf)
-{
- struct hstate *h;
- unsigned long nr_huge_pages;
- int nid;
-
- h = kobj_to_hstate(kobj, &nid);
- if (nid == NUMA_NO_NODE)
- nr_huge_pages = h->nr_huge_pages;
- else
- nr_huge_pages = h->nr_huge_pages_node[nid];
-
- return sysfs_emit(buf, "%lu\n", nr_huge_pages);
-}
-
-static ssize_t __nr_hugepages_store_common(bool obey_mempolicy,
+ssize_t __nr_hugepages_store_common(bool obey_mempolicy,
struct hstate *h, int nid,
unsigned long count, size_t len)
{
@@ -4239,452 +3983,6 @@ static ssize_t __nr_hugepages_store_common(bool obey_mempolicy,
return err ? err : len;
}
-static ssize_t nr_hugepages_store_common(bool obey_mempolicy,
- struct kobject *kobj, const char *buf,
- size_t len)
-{
- struct hstate *h;
- unsigned long count;
- int nid;
- int err;
-
- err = kstrtoul(buf, 10, &count);
- if (err)
- return err;
-
- h = kobj_to_hstate(kobj, &nid);
- return __nr_hugepages_store_common(obey_mempolicy, h, nid, count, len);
-}
-
-static ssize_t nr_hugepages_show(struct kobject *kobj,
- struct kobj_attribute *attr, char *buf)
-{
- return nr_hugepages_show_common(kobj, attr, buf);
-}
-
-static ssize_t nr_hugepages_store(struct kobject *kobj,
- struct kobj_attribute *attr, const char *buf, size_t len)
-{
- return nr_hugepages_store_common(false, kobj, buf, len);
-}
-HSTATE_ATTR(nr_hugepages);
-
-#ifdef CONFIG_NUMA
-
-/*
- * hstate attribute for optionally mempolicy-based constraint on persistent
- * huge page alloc/free.
- */
-static ssize_t nr_hugepages_mempolicy_show(struct kobject *kobj,
- struct kobj_attribute *attr,
- char *buf)
-{
- return nr_hugepages_show_common(kobj, attr, buf);
-}
-
-static ssize_t nr_hugepages_mempolicy_store(struct kobject *kobj,
- struct kobj_attribute *attr, const char *buf, size_t len)
-{
- return nr_hugepages_store_common(true, kobj, buf, len);
-}
-HSTATE_ATTR(nr_hugepages_mempolicy);
-#endif
-
-
-static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj,
- struct kobj_attribute *attr, char *buf)
-{
- struct hstate *h = kobj_to_hstate(kobj, NULL);
- return sysfs_emit(buf, "%lu\n", h->nr_overcommit_huge_pages);
-}
-
-static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj,
- struct kobj_attribute *attr, const char *buf, size_t count)
-{
- int err;
- unsigned long input;
- struct hstate *h = kobj_to_hstate(kobj, NULL);
-
- if (hstate_is_gigantic_no_runtime(h))
- return -EINVAL;
-
- err = kstrtoul(buf, 10, &input);
- if (err)
- return err;
-
- spin_lock_irq(&hugetlb_lock);
- h->nr_overcommit_huge_pages = input;
- spin_unlock_irq(&hugetlb_lock);
-
- return count;
-}
-HSTATE_ATTR(nr_overcommit_hugepages);
-
-static ssize_t free_hugepages_show(struct kobject *kobj,
- struct kobj_attribute *attr, char *buf)
-{
- struct hstate *h;
- unsigned long free_huge_pages;
- int nid;
-
- h = kobj_to_hstate(kobj, &nid);
- if (nid == NUMA_NO_NODE)
- free_huge_pages = h->free_huge_pages;
- else
- free_huge_pages = h->free_huge_pages_node[nid];
-
- return sysfs_emit(buf, "%lu\n", free_huge_pages);
-}
-HSTATE_ATTR_RO(free_hugepages);
-
-static ssize_t resv_hugepages_show(struct kobject *kobj,
- struct kobj_attribute *attr, char *buf)
-{
- struct hstate *h = kobj_to_hstate(kobj, NULL);
- return sysfs_emit(buf, "%lu\n", h->resv_huge_pages);
-}
-HSTATE_ATTR_RO(resv_hugepages);
-
-static ssize_t surplus_hugepages_show(struct kobject *kobj,
- struct kobj_attribute *attr, char *buf)
-{
- struct hstate *h;
- unsigned long surplus_huge_pages;
- int nid;
-
- h = kobj_to_hstate(kobj, &nid);
- if (nid == NUMA_NO_NODE)
- surplus_huge_pages = h->surplus_huge_pages;
- else
- surplus_huge_pages = h->surplus_huge_pages_node[nid];
-
- return sysfs_emit(buf, "%lu\n", surplus_huge_pages);
-}
-HSTATE_ATTR_RO(surplus_hugepages);
-
-static ssize_t demote_store(struct kobject *kobj,
- struct kobj_attribute *attr, const char *buf, size_t len)
-{
- unsigned long nr_demote;
- unsigned long nr_available;
- nodemask_t nodes_allowed, *n_mask;
- struct hstate *h;
- int err;
- int nid;
-
- err = kstrtoul(buf, 10, &nr_demote);
- if (err)
- return err;
- h = kobj_to_hstate(kobj, &nid);
-
- if (nid != NUMA_NO_NODE) {
- init_nodemask_of_node(&nodes_allowed, nid);
- n_mask = &nodes_allowed;
- } else {
- n_mask = &node_states[N_MEMORY];
- }
-
- /* Synchronize with other sysfs operations modifying huge pages */
- mutex_lock(&h->resize_lock);
- spin_lock_irq(&hugetlb_lock);
-
- while (nr_demote) {
- long rc;
-
- /*
- * Check for available pages to demote each time thorough the
- * loop as demote_pool_huge_page will drop hugetlb_lock.
- */
- if (nid != NUMA_NO_NODE)
- nr_available = h->free_huge_pages_node[nid];
- else
- nr_available = h->free_huge_pages;
- nr_available -= h->resv_huge_pages;
- if (!nr_available)
- break;
-
- rc = demote_pool_huge_page(h, n_mask, nr_demote);
- if (rc < 0) {
- err = rc;
- break;
- }
-
- nr_demote -= rc;
- }
-
- spin_unlock_irq(&hugetlb_lock);
- mutex_unlock(&h->resize_lock);
-
- if (err)
- return err;
- return len;
-}
-HSTATE_ATTR_WO(demote);
-
-static ssize_t demote_size_show(struct kobject *kobj,
- struct kobj_attribute *attr, char *buf)
-{
- struct hstate *h = kobj_to_hstate(kobj, NULL);
- unsigned long demote_size = (PAGE_SIZE << h->demote_order) / SZ_1K;
-
- return sysfs_emit(buf, "%lukB\n", demote_size);
-}
-
-static ssize_t demote_size_store(struct kobject *kobj,
- struct kobj_attribute *attr,
- const char *buf, size_t count)
-{
- struct hstate *h, *demote_hstate;
- unsigned long demote_size;
- unsigned int demote_order;
-
- demote_size = (unsigned long)memparse(buf, NULL);
-
- demote_hstate = size_to_hstate(demote_size);
- if (!demote_hstate)
- return -EINVAL;
- demote_order = demote_hstate->order;
- if (demote_order < HUGETLB_PAGE_ORDER)
- return -EINVAL;
-
- /* demote order must be smaller than hstate order */
- h = kobj_to_hstate(kobj, NULL);
- if (demote_order >= h->order)
- return -EINVAL;
-
- /* resize_lock synchronizes access to demote size and writes */
- mutex_lock(&h->resize_lock);
- h->demote_order = demote_order;
- mutex_unlock(&h->resize_lock);
-
- return count;
-}
-HSTATE_ATTR(demote_size);
-
-static struct attribute *hstate_attrs[] = {
- &nr_hugepages_attr.attr,
- &nr_overcommit_hugepages_attr.attr,
- &free_hugepages_attr.attr,
- &resv_hugepages_attr.attr,
- &surplus_hugepages_attr.attr,
-#ifdef CONFIG_NUMA
- &nr_hugepages_mempolicy_attr.attr,
-#endif
- NULL,
-};
-
-static const struct attribute_group hstate_attr_group = {
- .attrs = hstate_attrs,
-};
-
-static struct attribute *hstate_demote_attrs[] = {
- &demote_size_attr.attr,
- &demote_attr.attr,
- NULL,
-};
-
-static const struct attribute_group hstate_demote_attr_group = {
- .attrs = hstate_demote_attrs,
-};
-
-static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent,
- struct kobject **hstate_kobjs,
- const struct attribute_group *hstate_attr_group)
-{
- int retval;
- int hi = hstate_index(h);
-
- hstate_kobjs[hi] = kobject_create_and_add(h->name, parent);
- if (!hstate_kobjs[hi])
- return -ENOMEM;
-
- retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group);
- if (retval) {
- kobject_put(hstate_kobjs[hi]);
- hstate_kobjs[hi] = NULL;
- return retval;
- }
-
- if (h->demote_order) {
- retval = sysfs_create_group(hstate_kobjs[hi],
- &hstate_demote_attr_group);
- if (retval) {
- pr_warn("HugeTLB unable to create demote interfaces for %s\n", h->name);
- sysfs_remove_group(hstate_kobjs[hi], hstate_attr_group);
- kobject_put(hstate_kobjs[hi]);
- hstate_kobjs[hi] = NULL;
- return retval;
- }
- }
-
- return 0;
-}
-
-#ifdef CONFIG_NUMA
-static bool hugetlb_sysfs_initialized __ro_after_init;
-
-/*
- * node_hstate/s - associate per node hstate attributes, via their kobjects,
- * with node devices in node_devices[] using a parallel array. The array
- * index of a node device or _hstate == node id.
- * This is here to avoid any static dependency of the node device driver, in
- * the base kernel, on the hugetlb module.
- */
-struct node_hstate {
- struct kobject *hugepages_kobj;
- struct kobject *hstate_kobjs[HUGE_MAX_HSTATE];
-};
-static struct node_hstate node_hstates[MAX_NUMNODES];
-
-/*
- * A subset of global hstate attributes for node devices
- */
-static struct attribute *per_node_hstate_attrs[] = {
- &nr_hugepages_attr.attr,
- &free_hugepages_attr.attr,
- &surplus_hugepages_attr.attr,
- NULL,
-};
-
-static const struct attribute_group per_node_hstate_attr_group = {
- .attrs = per_node_hstate_attrs,
-};
-
-/*
- * kobj_to_node_hstate - lookup global hstate for node device hstate attr kobj.
- * Returns node id via non-NULL nidp.
- */
-static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp)
-{
- int nid;
-
- for (nid = 0; nid < nr_node_ids; nid++) {
- struct node_hstate *nhs = &node_hstates[nid];
- int i;
- for (i = 0; i < HUGE_MAX_HSTATE; i++)
- if (nhs->hstate_kobjs[i] == kobj) {
- if (nidp)
- *nidp = nid;
- return &hstates[i];
- }
- }
-
- BUG();
- return NULL;
-}
-
-/*
- * Unregister hstate attributes from a single node device.
- * No-op if no hstate attributes attached.
- */
-void hugetlb_unregister_node(struct node *node)
-{
- struct hstate *h;
- struct node_hstate *nhs = &node_hstates[node->dev.id];
-
- if (!nhs->hugepages_kobj)
- return; /* no hstate attributes */
-
- for_each_hstate(h) {
- int idx = hstate_index(h);
- struct kobject *hstate_kobj = nhs->hstate_kobjs[idx];
-
- if (!hstate_kobj)
- continue;
- if (h->demote_order)
- sysfs_remove_group(hstate_kobj, &hstate_demote_attr_group);
- sysfs_remove_group(hstate_kobj, &per_node_hstate_attr_group);
- kobject_put(hstate_kobj);
- nhs->hstate_kobjs[idx] = NULL;
- }
-
- kobject_put(nhs->hugepages_kobj);
- nhs->hugepages_kobj = NULL;
-}
-
-
-/*
- * Register hstate attributes for a single node device.
- * No-op if attributes already registered.
- */
-void hugetlb_register_node(struct node *node)
-{
- struct hstate *h;
- struct node_hstate *nhs = &node_hstates[node->dev.id];
- int err;
-
- if (!hugetlb_sysfs_initialized)
- return;
-
- if (nhs->hugepages_kobj)
- return; /* already allocated */
-
- nhs->hugepages_kobj = kobject_create_and_add("hugepages",
- &node->dev.kobj);
- if (!nhs->hugepages_kobj)
- return;
-
- for_each_hstate(h) {
- err = hugetlb_sysfs_add_hstate(h, nhs->hugepages_kobj,
- nhs->hstate_kobjs,
- &per_node_hstate_attr_group);
- if (err) {
- pr_err("HugeTLB: Unable to add hstate %s for node %d\n",
- h->name, node->dev.id);
- hugetlb_unregister_node(node);
- break;
- }
- }
-}
-
-/*
- * hugetlb init time: register hstate attributes for all registered node
- * devices of nodes that have memory. All on-line nodes should have
- * registered their associated device by this time.
- */
-static void __init hugetlb_register_all_nodes(void)
-{
- int nid;
-
- for_each_online_node(nid)
- hugetlb_register_node(node_devices[nid]);
-}
-#else /* !CONFIG_NUMA */
-
-static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp)
-{
- BUG();
- if (nidp)
- *nidp = -1;
- return NULL;
-}
-
-static void hugetlb_register_all_nodes(void) { }
-
-#endif
-
-static void __init hugetlb_sysfs_init(void)
-{
- struct hstate *h;
- int err;
-
- hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj);
- if (!hugepages_kobj)
- return;
-
- for_each_hstate(h) {
- err = hugetlb_sysfs_add_hstate(h, hugepages_kobj,
- hstate_kobjs, &hstate_attr_group);
- if (err)
- pr_err("HugeTLB: Unable to add hstate %s\n", h->name);
- }
-
-#ifdef CONFIG_NUMA
- hugetlb_sysfs_initialized = true;
-#endif
- hugetlb_register_all_nodes();
-}
-
#ifdef CONFIG_SYSCTL
static void hugetlb_sysctl_init(void);
#else
diff --git a/mm/hugetlb_internal.h b/mm/hugetlb_internal.h
new file mode 100644
index 000000000000..63ab13cfb072
--- /dev/null
+++ b/mm/hugetlb_internal.h
@@ -0,0 +1,110 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Internal HugeTLB definitions.
+ *
+ * Copyright (C) 2025 KylinSoft Corporation.
+ * Author: Geliang Tang <geliang@kernel.org>
+ */
+
+#ifndef _LINUX_HUGETLB_INTERNAL_H
+#define _LINUX_HUGETLB_INTERNAL_H
+
+#include <linux/hugetlb.h>
+#include <linux/hugetlb_cgroup.h>
+
+/*
+ * Check if the hstate represents gigantic pages but gigantic page
+ * runtime support is not available. This is a common condition used to
+ * skip operations that cannot be performed on gigantic pages when runtime
+ * support is disabled.
+ */
+static inline bool hstate_is_gigantic_no_runtime(struct hstate *h)
+{
+ return hstate_is_gigantic(h) && !gigantic_page_runtime_supported();
+}
+
+/*
+ * common helper functions for hstate_next_node_to_{alloc|free}.
+ * We may have allocated or freed a huge page based on a different
+ * nodes_allowed previously, so h->next_node_to_{alloc|free} might
+ * be outside of *nodes_allowed. Ensure that we use an allowed
+ * node for alloc or free.
+ */
+static inline int next_node_allowed(int nid, nodemask_t *nodes_allowed)
+{
+ nid = next_node_in(nid, *nodes_allowed);
+ VM_BUG_ON(nid >= MAX_NUMNODES);
+
+ return nid;
+}
+
+static inline int get_valid_node_allowed(int nid, nodemask_t *nodes_allowed)
+{
+ if (!node_isset(nid, *nodes_allowed))
+ nid = next_node_allowed(nid, nodes_allowed);
+ return nid;
+}
+
+/*
+ * returns the previously saved node ["this node"] from which to
+ * allocate a persistent huge page for the pool and advance the
+ * next node from which to allocate, handling wrap at end of node
+ * mask.
+ */
+static inline int hstate_next_node_to_alloc(int *next_node,
+ nodemask_t *nodes_allowed)
+{
+ int nid;
+
+ VM_BUG_ON(!nodes_allowed);
+
+ nid = get_valid_node_allowed(*next_node, nodes_allowed);
+ *next_node = next_node_allowed(nid, nodes_allowed);
+
+ return nid;
+}
+
+/*
+ * helper for remove_pool_hugetlb_folio() - return the previously saved
+ * node ["this node"] from which to free a huge page. Advance the
+ * next node id whether or not we find a free huge page to free so
+ * that the next attempt to free addresses the next node.
+ */
+static inline int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed)
+{
+ int nid;
+
+ VM_BUG_ON(!nodes_allowed);
+
+ nid = get_valid_node_allowed(h->next_nid_to_free, nodes_allowed);
+ h->next_nid_to_free = next_node_allowed(nid, nodes_allowed);
+
+ return nid;
+}
+
+#define for_each_node_mask_to_alloc(next_node, nr_nodes, node, mask) \
+ for (nr_nodes = nodes_weight(*mask); \
+ nr_nodes > 0 && \
+ ((node = hstate_next_node_to_alloc(next_node, mask)) || 1); \
+ nr_nodes--)
+
+#define for_each_node_mask_to_free(hs, nr_nodes, node, mask) \
+ for (nr_nodes = nodes_weight(*mask); \
+ nr_nodes > 0 && \
+ ((node = hstate_next_node_to_free(hs, mask)) || 1); \
+ nr_nodes--)
+
+extern void remove_hugetlb_folio(struct hstate *h, struct folio *folio,
+ bool adjust_surplus);
+extern void add_hugetlb_folio(struct hstate *h, struct folio *folio,
+ bool adjust_surplus);
+extern void init_new_hugetlb_folio(struct folio *folio);
+extern void prep_and_add_allocated_folios(struct hstate *h,
+ struct list_head *folio_list);
+extern ssize_t __nr_hugepages_store_common(bool obey_mempolicy,
+ struct hstate *h, int nid,
+ unsigned long count, size_t len);
+
+extern void hugetlb_sysfs_init(void) __init;
+
+#endif /* _LINUX_HUGETLB_INTERNAL_H */
diff --git a/mm/hugetlb_sysfs.c b/mm/hugetlb_sysfs.c
new file mode 100644
index 000000000000..a681be311664
--- /dev/null
+++ b/mm/hugetlb_sysfs.c
@@ -0,0 +1,632 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * HugeTLB sysfs interfaces.
+ *
+ * Copyright (C) 2025 KylinSoft Corporation.
+ * Author: Geliang Tang <geliang@kernel.org>
+ */
+
+#include <linux/swap.h>
+#include <linux/page_owner.h>
+#include <linux/page-isolation.h>
+
+#include "hugetlb_vmemmap.h"
+#include "hugetlb_internal.h"
+
+static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst,
+ struct list_head *src_list)
+{
+ long rc;
+ struct folio *folio, *next;
+ LIST_HEAD(dst_list);
+ LIST_HEAD(ret_list);
+
+ rc = hugetlb_vmemmap_restore_folios(src, src_list, &ret_list);
+ list_splice_init(&ret_list, src_list);
+
+ /*
+ * Taking target hstate mutex synchronizes with set_max_huge_pages.
+ * Without the mutex, pages added to target hstate could be marked
+ * as surplus.
+ *
+ * Note that we already hold src->resize_lock. To prevent deadlock,
+ * use the convention of always taking larger size hstate mutex first.
+ */
+ mutex_lock(&dst->resize_lock);
+
+ list_for_each_entry_safe(folio, next, src_list, lru) {
+ int i;
+ bool cma;
+
+ if (folio_test_hugetlb_vmemmap_optimized(folio))
+ continue;
+
+ cma = folio_test_hugetlb_cma(folio);
+
+ list_del(&folio->lru);
+
+ split_page_owner(&folio->page, huge_page_order(src), huge_page_order(dst));
+ pgalloc_tag_split(folio, huge_page_order(src), huge_page_order(dst));
+
+ for (i = 0; i < pages_per_huge_page(src); i += pages_per_huge_page(dst)) {
+ struct page *page = folio_page(folio, i);
+ /* Careful: see __split_huge_page_tail() */
+ struct folio *new_folio = (struct folio *)page;
+
+ clear_compound_head(page);
+ prep_compound_page(page, dst->order);
+
+ new_folio->mapping = NULL;
+ init_new_hugetlb_folio(new_folio);
+ /* Copy the CMA flag so that it is freed correctly */
+ if (cma)
+ folio_set_hugetlb_cma(new_folio);
+ list_add(&new_folio->lru, &dst_list);
+ }
+ }
+
+ prep_and_add_allocated_folios(dst, &dst_list);
+
+ mutex_unlock(&dst->resize_lock);
+
+ return rc;
+}
+
+static long demote_pool_huge_page(struct hstate *src, nodemask_t *nodes_allowed,
+ unsigned long nr_to_demote)
+ __must_hold(&hugetlb_lock)
+{
+ int nr_nodes, node;
+ struct hstate *dst;
+ long rc = 0;
+ long nr_demoted = 0;
+
+ lockdep_assert_held(&hugetlb_lock);
+
+ /* We should never get here if no demote order */
+ if (!src->demote_order) {
+ pr_warn("HugeTLB: NULL demote order passed to demote_pool_huge_page.\n");
+ return -EINVAL; /* internal error */
+ }
+ dst = size_to_hstate(PAGE_SIZE << src->demote_order);
+
+ for_each_node_mask_to_free(src, nr_nodes, node, nodes_allowed) {
+ LIST_HEAD(list);
+ struct folio *folio, *next;
+
+ list_for_each_entry_safe(folio, next, &src->hugepage_freelists[node], lru) {
+ if (folio_test_hwpoison(folio))
+ continue;
+
+ remove_hugetlb_folio(src, folio, false);
+ list_add(&folio->lru, &list);
+
+ if (++nr_demoted == nr_to_demote)
+ break;
+ }
+
+ spin_unlock_irq(&hugetlb_lock);
+
+ rc = demote_free_hugetlb_folios(src, dst, &list);
+
+ spin_lock_irq(&hugetlb_lock);
+
+ list_for_each_entry_safe(folio, next, &list, lru) {
+ list_del(&folio->lru);
+ add_hugetlb_folio(src, folio, false);
+
+ nr_demoted--;
+ }
+
+ if (rc < 0 || nr_demoted == nr_to_demote)
+ break;
+ }
+
+ /*
+ * Not absolutely necessary, but for consistency update max_huge_pages
+ * based on pool changes for the demoted page.
+ */
+ src->max_huge_pages -= nr_demoted;
+ dst->max_huge_pages += nr_demoted << (huge_page_order(src) - huge_page_order(dst));
+
+ if (rc < 0)
+ return rc;
+
+ if (nr_demoted)
+ return nr_demoted;
+ /*
+ * Only way to get here is if all pages on free lists are poisoned.
+ * Return -EBUSY so that caller will not retry.
+ */
+ return -EBUSY;
+}
+
+#define HSTATE_ATTR_RO(_name) \
+ static struct kobj_attribute _name##_attr = __ATTR_RO(_name)
+
+#define HSTATE_ATTR_WO(_name) \
+ static struct kobj_attribute _name##_attr = __ATTR_WO(_name)
+
+#define HSTATE_ATTR(_name) \
+ static struct kobj_attribute _name##_attr = __ATTR_RW(_name)
+
+static struct kobject *hugepages_kobj;
+static struct kobject *hstate_kobjs[HUGE_MAX_HSTATE];
+
+static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp);
+
+static struct hstate *kobj_to_hstate(struct kobject *kobj, int *nidp)
+{
+ int i;
+
+ for (i = 0; i < HUGE_MAX_HSTATE; i++)
+ if (hstate_kobjs[i] == kobj) {
+ if (nidp)
+ *nidp = NUMA_NO_NODE;
+ return &hstates[i];
+ }
+
+ return kobj_to_node_hstate(kobj, nidp);
+}
+
+static ssize_t nr_hugepages_show_common(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct hstate *h;
+ unsigned long nr_huge_pages;
+ int nid;
+
+ h = kobj_to_hstate(kobj, &nid);
+ if (nid == NUMA_NO_NODE)
+ nr_huge_pages = h->nr_huge_pages;
+ else
+ nr_huge_pages = h->nr_huge_pages_node[nid];
+
+ return sysfs_emit(buf, "%lu\n", nr_huge_pages);
+}
+
+static ssize_t nr_hugepages_store_common(bool obey_mempolicy,
+ struct kobject *kobj, const char *buf,
+ size_t len)
+{
+ struct hstate *h;
+ unsigned long count;
+ int nid;
+ int err;
+
+ err = kstrtoul(buf, 10, &count);
+ if (err)
+ return err;
+
+ h = kobj_to_hstate(kobj, &nid);
+ return __nr_hugepages_store_common(obey_mempolicy, h, nid, count, len);
+}
+
+static ssize_t nr_hugepages_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return nr_hugepages_show_common(kobj, attr, buf);
+}
+
+static ssize_t nr_hugepages_store(struct kobject *kobj,
+ struct kobj_attribute *attr, const char *buf, size_t len)
+{
+ return nr_hugepages_store_common(false, kobj, buf, len);
+}
+HSTATE_ATTR(nr_hugepages);
+
+#ifdef CONFIG_NUMA
+
+/*
+ * hstate attribute for optionally mempolicy-based constraint on persistent
+ * huge page alloc/free.
+ */
+static ssize_t nr_hugepages_mempolicy_show(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ char *buf)
+{
+ return nr_hugepages_show_common(kobj, attr, buf);
+}
+
+static ssize_t nr_hugepages_mempolicy_store(struct kobject *kobj,
+ struct kobj_attribute *attr, const char *buf, size_t len)
+{
+ return nr_hugepages_store_common(true, kobj, buf, len);
+}
+HSTATE_ATTR(nr_hugepages_mempolicy);
+#endif
+
+
+static ssize_t nr_overcommit_hugepages_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct hstate *h = kobj_to_hstate(kobj, NULL);
+ return sysfs_emit(buf, "%lu\n", h->nr_overcommit_huge_pages);
+}
+
+static ssize_t nr_overcommit_hugepages_store(struct kobject *kobj,
+ struct kobj_attribute *attr, const char *buf, size_t count)
+{
+ int err;
+ unsigned long input;
+ struct hstate *h = kobj_to_hstate(kobj, NULL);
+
+ if (hstate_is_gigantic_no_runtime(h))
+ return -EINVAL;
+
+ err = kstrtoul(buf, 10, &input);
+ if (err)
+ return err;
+
+ spin_lock_irq(&hugetlb_lock);
+ h->nr_overcommit_huge_pages = input;
+ spin_unlock_irq(&hugetlb_lock);
+
+ return count;
+}
+HSTATE_ATTR(nr_overcommit_hugepages);
+
+static ssize_t free_hugepages_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct hstate *h;
+ unsigned long free_huge_pages;
+ int nid;
+
+ h = kobj_to_hstate(kobj, &nid);
+ if (nid == NUMA_NO_NODE)
+ free_huge_pages = h->free_huge_pages;
+ else
+ free_huge_pages = h->free_huge_pages_node[nid];
+
+ return sysfs_emit(buf, "%lu\n", free_huge_pages);
+}
+HSTATE_ATTR_RO(free_hugepages);
+
+static ssize_t resv_hugepages_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct hstate *h = kobj_to_hstate(kobj, NULL);
+ return sysfs_emit(buf, "%lu\n", h->resv_huge_pages);
+}
+HSTATE_ATTR_RO(resv_hugepages);
+
+static ssize_t surplus_hugepages_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct hstate *h;
+ unsigned long surplus_huge_pages;
+ int nid;
+
+ h = kobj_to_hstate(kobj, &nid);
+ if (nid == NUMA_NO_NODE)
+ surplus_huge_pages = h->surplus_huge_pages;
+ else
+ surplus_huge_pages = h->surplus_huge_pages_node[nid];
+
+ return sysfs_emit(buf, "%lu\n", surplus_huge_pages);
+}
+HSTATE_ATTR_RO(surplus_hugepages);
+
+static ssize_t demote_store(struct kobject *kobj,
+ struct kobj_attribute *attr, const char *buf, size_t len)
+{
+ unsigned long nr_demote;
+ unsigned long nr_available;
+ nodemask_t nodes_allowed, *n_mask;
+ struct hstate *h;
+ int err;
+ int nid;
+
+ err = kstrtoul(buf, 10, &nr_demote);
+ if (err)
+ return err;
+ h = kobj_to_hstate(kobj, &nid);
+
+ if (nid != NUMA_NO_NODE) {
+ init_nodemask_of_node(&nodes_allowed, nid);
+ n_mask = &nodes_allowed;
+ } else {
+ n_mask = &node_states[N_MEMORY];
+ }
+
+ /* Synchronize with other sysfs operations modifying huge pages */
+ mutex_lock(&h->resize_lock);
+ spin_lock_irq(&hugetlb_lock);
+
+ while (nr_demote) {
+ long rc;
+
+ /*
+ * Check for available pages to demote each time thorough the
+ * loop as demote_pool_huge_page will drop hugetlb_lock.
+ */
+ if (nid != NUMA_NO_NODE)
+ nr_available = h->free_huge_pages_node[nid];
+ else
+ nr_available = h->free_huge_pages;
+ nr_available -= h->resv_huge_pages;
+ if (!nr_available)
+ break;
+
+ rc = demote_pool_huge_page(h, n_mask, nr_demote);
+ if (rc < 0) {
+ err = rc;
+ break;
+ }
+
+ nr_demote -= rc;
+ }
+
+ spin_unlock_irq(&hugetlb_lock);
+ mutex_unlock(&h->resize_lock);
+
+ if (err)
+ return err;
+ return len;
+}
+HSTATE_ATTR_WO(demote);
+
+static ssize_t demote_size_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ struct hstate *h = kobj_to_hstate(kobj, NULL);
+ unsigned long demote_size = (PAGE_SIZE << h->demote_order) / SZ_1K;
+
+ return sysfs_emit(buf, "%lukB\n", demote_size);
+}
+
+static ssize_t demote_size_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ struct hstate *h, *demote_hstate;
+ unsigned long demote_size;
+ unsigned int demote_order;
+
+ demote_size = (unsigned long)memparse(buf, NULL);
+
+ demote_hstate = size_to_hstate(demote_size);
+ if (!demote_hstate)
+ return -EINVAL;
+ demote_order = demote_hstate->order;
+ if (demote_order < HUGETLB_PAGE_ORDER)
+ return -EINVAL;
+
+ /* demote order must be smaller than hstate order */
+ h = kobj_to_hstate(kobj, NULL);
+ if (demote_order >= h->order)
+ return -EINVAL;
+
+ /* resize_lock synchronizes access to demote size and writes */
+ mutex_lock(&h->resize_lock);
+ h->demote_order = demote_order;
+ mutex_unlock(&h->resize_lock);
+
+ return count;
+}
+HSTATE_ATTR(demote_size);
+
+static struct attribute *hstate_attrs[] = {
+ &nr_hugepages_attr.attr,
+ &nr_overcommit_hugepages_attr.attr,
+ &free_hugepages_attr.attr,
+ &resv_hugepages_attr.attr,
+ &surplus_hugepages_attr.attr,
+#ifdef CONFIG_NUMA
+ &nr_hugepages_mempolicy_attr.attr,
+#endif
+ NULL,
+};
+
+static const struct attribute_group hstate_attr_group = {
+ .attrs = hstate_attrs,
+};
+
+static struct attribute *hstate_demote_attrs[] = {
+ &demote_size_attr.attr,
+ &demote_attr.attr,
+ NULL,
+};
+
+static const struct attribute_group hstate_demote_attr_group = {
+ .attrs = hstate_demote_attrs,
+};
+
+static int hugetlb_sysfs_add_hstate(struct hstate *h, struct kobject *parent,
+ struct kobject **hstate_kobjs,
+ const struct attribute_group *hstate_attr_group)
+{
+ int retval;
+ int hi = hstate_index(h);
+
+ hstate_kobjs[hi] = kobject_create_and_add(h->name, parent);
+ if (!hstate_kobjs[hi])
+ return -ENOMEM;
+
+ retval = sysfs_create_group(hstate_kobjs[hi], hstate_attr_group);
+ if (retval) {
+ kobject_put(hstate_kobjs[hi]);
+ hstate_kobjs[hi] = NULL;
+ return retval;
+ }
+
+ if (h->demote_order) {
+ retval = sysfs_create_group(hstate_kobjs[hi],
+ &hstate_demote_attr_group);
+ if (retval) {
+ pr_warn("HugeTLB unable to create demote interfaces for %s\n", h->name);
+ sysfs_remove_group(hstate_kobjs[hi], hstate_attr_group);
+ kobject_put(hstate_kobjs[hi]);
+ hstate_kobjs[hi] = NULL;
+ return retval;
+ }
+ }
+
+ return 0;
+}
+
+#ifdef CONFIG_NUMA
+static bool hugetlb_sysfs_initialized __ro_after_init;
+
+/*
+ * node_hstate/s - associate per node hstate attributes, via their kobjects,
+ * with node devices in node_devices[] using a parallel array. The array
+ * index of a node device or _hstate == node id.
+ * This is here to avoid any static dependency of the node device driver, in
+ * the base kernel, on the hugetlb module.
+ */
+struct node_hstate {
+ struct kobject *hugepages_kobj;
+ struct kobject *hstate_kobjs[HUGE_MAX_HSTATE];
+};
+static struct node_hstate node_hstates[MAX_NUMNODES];
+
+/*
+ * A subset of global hstate attributes for node devices
+ */
+static struct attribute *per_node_hstate_attrs[] = {
+ &nr_hugepages_attr.attr,
+ &free_hugepages_attr.attr,
+ &surplus_hugepages_attr.attr,
+ NULL,
+};
+
+static const struct attribute_group per_node_hstate_attr_group = {
+ .attrs = per_node_hstate_attrs,
+};
+
+/*
+ * kobj_to_node_hstate - lookup global hstate for node device hstate attr kobj.
+ * Returns node id via non-NULL nidp.
+ */
+static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp)
+{
+ int nid;
+
+ for (nid = 0; nid < nr_node_ids; nid++) {
+ struct node_hstate *nhs = &node_hstates[nid];
+ int i;
+ for (i = 0; i < HUGE_MAX_HSTATE; i++)
+ if (nhs->hstate_kobjs[i] == kobj) {
+ if (nidp)
+ *nidp = nid;
+ return &hstates[i];
+ }
+ }
+
+ BUG();
+ return NULL;
+}
+
+/*
+ * Unregister hstate attributes from a single node device.
+ * No-op if no hstate attributes attached.
+ */
+void hugetlb_unregister_node(struct node *node)
+{
+ struct hstate *h;
+ struct node_hstate *nhs = &node_hstates[node->dev.id];
+
+ if (!nhs->hugepages_kobj)
+ return; /* no hstate attributes */
+
+ for_each_hstate(h) {
+ int idx = hstate_index(h);
+ struct kobject *hstate_kobj = nhs->hstate_kobjs[idx];
+
+ if (!hstate_kobj)
+ continue;
+ if (h->demote_order)
+ sysfs_remove_group(hstate_kobj, &hstate_demote_attr_group);
+ sysfs_remove_group(hstate_kobj, &per_node_hstate_attr_group);
+ kobject_put(hstate_kobj);
+ nhs->hstate_kobjs[idx] = NULL;
+ }
+
+ kobject_put(nhs->hugepages_kobj);
+ nhs->hugepages_kobj = NULL;
+}
+
+
+/*
+ * Register hstate attributes for a single node device.
+ * No-op if attributes already registered.
+ */
+void hugetlb_register_node(struct node *node)
+{
+ struct hstate *h;
+ struct node_hstate *nhs = &node_hstates[node->dev.id];
+ int err;
+
+ if (!hugetlb_sysfs_initialized)
+ return;
+
+ if (nhs->hugepages_kobj)
+ return; /* already allocated */
+
+ nhs->hugepages_kobj = kobject_create_and_add("hugepages",
+ &node->dev.kobj);
+ if (!nhs->hugepages_kobj)
+ return;
+
+ for_each_hstate(h) {
+ err = hugetlb_sysfs_add_hstate(h, nhs->hugepages_kobj,
+ nhs->hstate_kobjs,
+ &per_node_hstate_attr_group);
+ if (err) {
+ pr_err("HugeTLB: Unable to add hstate %s for node %d\n",
+ h->name, node->dev.id);
+ hugetlb_unregister_node(node);
+ break;
+ }
+ }
+}
+
+/*
+ * hugetlb init time: register hstate attributes for all registered node
+ * devices of nodes that have memory. All on-line nodes should have
+ * registered their associated device by this time.
+ */
+static void __init hugetlb_register_all_nodes(void)
+{
+ int nid;
+
+ for_each_online_node(nid)
+ hugetlb_register_node(node_devices[nid]);
+}
+#else /* !CONFIG_NUMA */
+
+static struct hstate *kobj_to_node_hstate(struct kobject *kobj, int *nidp)
+{
+ BUG();
+ if (nidp)
+ *nidp = -1;
+ return NULL;
+}
+
+static void hugetlb_register_all_nodes(void) { }
+
+#endif
+
+void __init hugetlb_sysfs_init(void)
+{
+ struct hstate *h;
+ int err;
+
+ hugepages_kobj = kobject_create_and_add("hugepages", mm_kobj);
+ if (!hugepages_kobj)
+ return;
+
+ for_each_hstate(h) {
+ err = hugetlb_sysfs_add_hstate(h, hugepages_kobj,
+ hstate_kobjs, &hstate_attr_group);
+ if (err)
+ pr_err("HugeTLB: Unable to add hstate %s\n", h->name);
+ }
+
+#ifdef CONFIG_NUMA
+ hugetlb_sysfs_initialized = true;
+#endif
+ hugetlb_register_all_nodes();
+}
--
2.43.0
^ permalink raw reply related [flat|nested] 8+ messages in thread* [PATCH 2/2] mm/hugetlb: extract sysctl into hugetlb_sysctl.c
2025-11-03 8:22 [PATCH 0/2] mm/hugetlb: refactor sysfs/sysctl interfaces Hui Zhu
2025-11-03 8:22 ` [PATCH 1/2] mm/hugetlb: extract sysfs into hugetlb_sysfs.c Hui Zhu
@ 2025-11-03 8:22 ` Hui Zhu
2025-11-04 4:43 ` [PATCH 0/2] mm/hugetlb: refactor sysfs/sysctl interfaces SeongJae Park
2 siblings, 0 replies; 8+ messages in thread
From: Hui Zhu @ 2025-11-03 8:22 UTC (permalink / raw)
To: Andrew Morton, Muchun Song, Oscar Salvador, David Hildenbrand,
linux-kernel, linux-mm
Cc: Hui Zhu, Geliang Tang
From: Hui Zhu <zhuhui@kylinos.cn>
Following the extraction of sysfs code, this patch moves the sysctl
interface implementation into a dedicated file to further improve code
organization and maintainability of the hugetlb subsystem.
The following components are moved to mm/hugetlb_sysctl.c:
- proc_hugetlb_doulongvec_minmax()
- hugetlb_sysctl_handler_common()
- hugetlb_sysctl_handler()
- hugetlb_mempolicy_sysctl_handler() (CONFIG_NUMA)
- hugetlb_overcommit_handler()
- hugetlb_table[] sysctl table definition
- hugetlb_sysctl_init()
The hugetlb_internal.h header file is updated to declare the sysctl
initialization function with proper #ifdef guards for configurations
without CONFIG_SYSCTL support.
The Makefile is updated to compile hugetlb_sysctl.o when CONFIG_HUGETLBFS
is enabled. This refactoring reduces the size of hugetlb.c and logically
separates the sysctl interface from core hugetlb management code.
No functional changes are introduced; all code is moved as-is from
hugetlb.c with consistent formatting.
Signed-off-by: Geliang Tang <geliang@kernel.org>
Signed-off-by: Hui Zhu <zhuhui@kylinos.cn>
---
mm/Makefile | 2 +-
mm/hugetlb.c | 132 ----------------------------------------
mm/hugetlb_internal.h | 6 ++
mm/hugetlb_sysctl.c | 136 ++++++++++++++++++++++++++++++++++++++++++
4 files changed, 143 insertions(+), 133 deletions(-)
create mode 100644 mm/hugetlb_sysctl.c
diff --git a/mm/Makefile b/mm/Makefile
index b9edfce6c202..00ceb2418b64 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -78,7 +78,7 @@ endif
obj-$(CONFIG_SWAP) += page_io.o swap_state.o swapfile.o
obj-$(CONFIG_ZSWAP) += zswap.o
obj-$(CONFIG_HAS_DMA) += dmapool.o
-obj-$(CONFIG_HUGETLBFS) += hugetlb.o hugetlb_sysfs.o
+obj-$(CONFIG_HUGETLBFS) += hugetlb.o hugetlb_sysfs.o hugetlb_sysctl.o
ifdef CONFIG_CMA
obj-$(CONFIG_HUGETLBFS) += hugetlb_cma.o
endif
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 1fc24f7e63ac..ee2df563550e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -7,7 +7,6 @@
#include <linux/init.h>
#include <linux/mm.h>
#include <linux/seq_file.h>
-#include <linux/sysctl.h>
#include <linux/highmem.h>
#include <linux/mmu_notifier.h>
#include <linux/nodemask.h>
@@ -3983,12 +3982,6 @@ ssize_t __nr_hugepages_store_common(bool obey_mempolicy,
return err ? err : len;
}
-#ifdef CONFIG_SYSCTL
-static void hugetlb_sysctl_init(void);
-#else
-static inline void hugetlb_sysctl_init(void) { }
-#endif
-
static int __init hugetlb_init(void)
{
int i;
@@ -4421,131 +4414,6 @@ static unsigned int allowed_mems_nr(struct hstate *h)
return nr;
}
-#ifdef CONFIG_SYSCTL
-static int proc_hugetlb_doulongvec_minmax(const struct ctl_table *table, int write,
- void *buffer, size_t *length,
- loff_t *ppos, unsigned long *out)
-{
- struct ctl_table dup_table;
-
- /*
- * In order to avoid races with __do_proc_doulongvec_minmax(), we
- * can duplicate the @table and alter the duplicate of it.
- */
- dup_table = *table;
- dup_table.data = out;
-
- return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos);
-}
-
-static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
- const struct ctl_table *table, int write,
- void *buffer, size_t *length, loff_t *ppos)
-{
- struct hstate *h = &default_hstate;
- unsigned long tmp = h->max_huge_pages;
- int ret;
-
- if (!hugepages_supported())
- return -EOPNOTSUPP;
-
- ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
- &tmp);
- if (ret)
- goto out;
-
- if (write)
- ret = __nr_hugepages_store_common(obey_mempolicy, h,
- NUMA_NO_NODE, tmp, *length);
-out:
- return ret;
-}
-
-static int hugetlb_sysctl_handler(const struct ctl_table *table, int write,
- void *buffer, size_t *length, loff_t *ppos)
-{
-
- return hugetlb_sysctl_handler_common(false, table, write,
- buffer, length, ppos);
-}
-
-#ifdef CONFIG_NUMA
-static int hugetlb_mempolicy_sysctl_handler(const struct ctl_table *table, int write,
- void *buffer, size_t *length, loff_t *ppos)
-{
- return hugetlb_sysctl_handler_common(true, table, write,
- buffer, length, ppos);
-}
-#endif /* CONFIG_NUMA */
-
-static int hugetlb_overcommit_handler(const struct ctl_table *table, int write,
- void *buffer, size_t *length, loff_t *ppos)
-{
- struct hstate *h = &default_hstate;
- unsigned long tmp;
- int ret;
-
- if (!hugepages_supported())
- return -EOPNOTSUPP;
-
- tmp = h->nr_overcommit_huge_pages;
-
- if (write && hstate_is_gigantic_no_runtime(h))
- return -EINVAL;
-
- ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
- &tmp);
- if (ret)
- goto out;
-
- if (write) {
- spin_lock_irq(&hugetlb_lock);
- h->nr_overcommit_huge_pages = tmp;
- spin_unlock_irq(&hugetlb_lock);
- }
-out:
- return ret;
-}
-
-static const struct ctl_table hugetlb_table[] = {
- {
- .procname = "nr_hugepages",
- .data = NULL,
- .maxlen = sizeof(unsigned long),
- .mode = 0644,
- .proc_handler = hugetlb_sysctl_handler,
- },
-#ifdef CONFIG_NUMA
- {
- .procname = "nr_hugepages_mempolicy",
- .data = NULL,
- .maxlen = sizeof(unsigned long),
- .mode = 0644,
- .proc_handler = &hugetlb_mempolicy_sysctl_handler,
- },
-#endif
- {
- .procname = "hugetlb_shm_group",
- .data = &sysctl_hugetlb_shm_group,
- .maxlen = sizeof(gid_t),
- .mode = 0644,
- .proc_handler = proc_dointvec,
- },
- {
- .procname = "nr_overcommit_hugepages",
- .data = NULL,
- .maxlen = sizeof(unsigned long),
- .mode = 0644,
- .proc_handler = hugetlb_overcommit_handler,
- },
-};
-
-static void __init hugetlb_sysctl_init(void)
-{
- register_sysctl_init("vm", hugetlb_table);
-}
-#endif /* CONFIG_SYSCTL */
-
void hugetlb_report_meminfo(struct seq_file *m)
{
struct hstate *h;
diff --git a/mm/hugetlb_internal.h b/mm/hugetlb_internal.h
index 63ab13cfb072..8c303d666fd8 100644
--- a/mm/hugetlb_internal.h
+++ b/mm/hugetlb_internal.h
@@ -107,4 +107,10 @@ extern ssize_t __nr_hugepages_store_common(bool obey_mempolicy,
extern void hugetlb_sysfs_init(void) __init;
+#ifdef CONFIG_SYSCTL
+extern void hugetlb_sysctl_init(void);
+#else
+static inline void hugetlb_sysctl_init(void) { }
+#endif
+
#endif /* _LINUX_HUGETLB_INTERNAL_H */
diff --git a/mm/hugetlb_sysctl.c b/mm/hugetlb_sysctl.c
new file mode 100644
index 000000000000..53443bb4f0bc
--- /dev/null
+++ b/mm/hugetlb_sysctl.c
@@ -0,0 +1,136 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * HugeTLB sysfs interfaces.
+ *
+ * Copyright (C) 2025 KylinSoft Corporation.
+ * Author: Hui Zhu <zhuhui@kylinos.cn>
+ */
+
+#include <linux/sysctl.h>
+
+#include "hugetlb_internal.h"
+
+#ifdef CONFIG_SYSCTL
+static int proc_hugetlb_doulongvec_minmax(const struct ctl_table *table, int write,
+ void *buffer, size_t *length,
+ loff_t *ppos, unsigned long *out)
+{
+ struct ctl_table dup_table;
+
+ /*
+ * In order to avoid races with __do_proc_doulongvec_minmax(), we
+ * can duplicate the @table and alter the duplicate of it.
+ */
+ dup_table = *table;
+ dup_table.data = out;
+
+ return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos);
+}
+
+static int hugetlb_sysctl_handler_common(bool obey_mempolicy,
+ const struct ctl_table *table, int write,
+ void *buffer, size_t *length, loff_t *ppos)
+{
+ struct hstate *h = &default_hstate;
+ unsigned long tmp = h->max_huge_pages;
+ int ret;
+
+ if (!hugepages_supported())
+ return -EOPNOTSUPP;
+
+ ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
+ &tmp);
+ if (ret)
+ goto out;
+
+ if (write)
+ ret = __nr_hugepages_store_common(obey_mempolicy, h,
+ NUMA_NO_NODE, tmp, *length);
+out:
+ return ret;
+}
+
+static int hugetlb_sysctl_handler(const struct ctl_table *table, int write,
+ void *buffer, size_t *length, loff_t *ppos)
+{
+
+ return hugetlb_sysctl_handler_common(false, table, write,
+ buffer, length, ppos);
+}
+
+#ifdef CONFIG_NUMA
+static int hugetlb_mempolicy_sysctl_handler(const struct ctl_table *table, int write,
+ void *buffer, size_t *length, loff_t *ppos)
+{
+ return hugetlb_sysctl_handler_common(true, table, write,
+ buffer, length, ppos);
+}
+#endif /* CONFIG_NUMA */
+
+static int hugetlb_overcommit_handler(const struct ctl_table *table, int write,
+ void *buffer, size_t *length, loff_t *ppos)
+{
+ struct hstate *h = &default_hstate;
+ unsigned long tmp;
+ int ret;
+
+ if (!hugepages_supported())
+ return -EOPNOTSUPP;
+
+ tmp = h->nr_overcommit_huge_pages;
+
+ if (write && hstate_is_gigantic_no_runtime(h))
+ return -EINVAL;
+
+ ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos,
+ &tmp);
+ if (ret)
+ goto out;
+
+ if (write) {
+ spin_lock_irq(&hugetlb_lock);
+ h->nr_overcommit_huge_pages = tmp;
+ spin_unlock_irq(&hugetlb_lock);
+ }
+out:
+ return ret;
+}
+
+static const struct ctl_table hugetlb_table[] = {
+ {
+ .procname = "nr_hugepages",
+ .data = NULL,
+ .maxlen = sizeof(unsigned long),
+ .mode = 0644,
+ .proc_handler = hugetlb_sysctl_handler,
+ },
+#ifdef CONFIG_NUMA
+ {
+ .procname = "nr_hugepages_mempolicy",
+ .data = NULL,
+ .maxlen = sizeof(unsigned long),
+ .mode = 0644,
+ .proc_handler = &hugetlb_mempolicy_sysctl_handler,
+ },
+#endif
+ {
+ .procname = "hugetlb_shm_group",
+ .data = &sysctl_hugetlb_shm_group,
+ .maxlen = sizeof(gid_t),
+ .mode = 0644,
+ .proc_handler = proc_dointvec,
+ },
+ {
+ .procname = "nr_overcommit_hugepages",
+ .data = NULL,
+ .maxlen = sizeof(unsigned long),
+ .mode = 0644,
+ .proc_handler = hugetlb_overcommit_handler,
+ },
+};
+
+void __init hugetlb_sysctl_init(void)
+{
+ register_sysctl_init("vm", hugetlb_table);
+}
+#endif /* CONFIG_SYSCTL */
--
2.43.0
^ permalink raw reply related [flat|nested] 8+ messages in thread