summaryrefslogtreecommitdiffstats
path: root/mm/huge_memory.c
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2024-09-21 16:29:05 +0200
committerLinus Torvalds <torvalds@linux-foundation.org>2024-09-21 16:29:05 +0200
commit617a814f14b8914271f7a70366d72c6196d17663 (patch)
tree31d32f73bef107862101ded103a76b314cea3705 /mm/huge_memory.c
parentMerge tag 'for-linux-6.12-ofs1' of git://git.kernel.org/pub/scm/linux/kernel/... (diff)
parentzram: free secondary algorithms names (diff)
downloadlinux-617a814f14b8914271f7a70366d72c6196d17663.tar.xz
linux-617a814f14b8914271f7a70366d72c6196d17663.zip
Merge tag 'mm-stable-2024-09-20-02-31' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm
Pull MM updates from Andrew Morton: "Along with the usual shower of singleton patches, notable patch series in this pull request are: - "Align kvrealloc() with krealloc()" from Danilo Krummrich. Adds consistency to the APIs and behaviour of these two core allocation functions. This also simplifies/enables Rustification. - "Some cleanups for shmem" from Baolin Wang. No functional changes - mode code reuse, better function naming, logic simplifications. - "mm: some small page fault cleanups" from Josef Bacik. No functional changes - code cleanups only. - "Various memory tiering fixes" from Zi Yan. A small fix and a little cleanup. - "mm/swap: remove boilerplate" from Yu Zhao. Code cleanups and simplifications and .text shrinkage. - "Kernel stack usage histogram" from Pasha Tatashin and Shakeel Butt. This is a feature, it adds new feilds to /proc/vmstat such as $ grep kstack /proc/vmstat kstack_1k 3 kstack_2k 188 kstack_4k 11391 kstack_8k 243 kstack_16k 0 which tells us that 11391 processes used 4k of stack while none at all used 16k. Useful for some system tuning things, but partivularly useful for "the dynamic kernel stack project". - "kmemleak: support for percpu memory leak detect" from Pavel Tikhomirov. Teaches kmemleak to detect leaksage of percpu memory. - "mm: memcg: page counters optimizations" from Roman Gushchin. "3 independent small optimizations of page counters". - "mm: split PTE/PMD PT table Kconfig cleanups+clarifications" from David Hildenbrand. Improves PTE/PMD splitlock detection, makes powerpc/8xx work correctly by design rather than by accident. - "mm: remove arch_make_page_accessible()" from David Hildenbrand. Some folio conversions which make arch_make_page_accessible() unneeded. - "mm, memcg: cg2 memory{.swap,}.peak write handlers" fro David Finkel. Cleans up and fixes our handling of the resetting of the cgroup/process peak-memory-use detector. - "Make core VMA operations internal and testable" from Lorenzo Stoakes. Rationalizaion and encapsulation of the VMA manipulation APIs. With a view to better enable testing of the VMA functions, even from a userspace-only harness. - "mm: zswap: fixes for global shrinker" from Takero Funaki. Fix issues in the zswap global shrinker, resulting in improved performance. - "mm: print the promo watermark in zoneinfo" from Kaiyang Zhao. Fill in some missing info in /proc/zoneinfo. - "mm: replace follow_page() by folio_walk" from David Hildenbrand. Code cleanups and rationalizations (conversion to folio_walk()) resulting in the removal of follow_page(). - "improving dynamic zswap shrinker protection scheme" from Nhat Pham. Some tuning to improve zswap's dynamic shrinker. Significant reductions in swapin and improvements in performance are shown. - "mm: Fix several issues with unaccepted memory" from Kirill Shutemov. Improvements to the new unaccepted memory feature, - "mm/mprotect: Fix dax puds" from Peter Xu. Implements mprotect on DAX PUDs. This was missing, although nobody seems to have notied yet. - "Introduce a store type enum for the Maple tree" from Sidhartha Kumar. Cleanups and modest performance improvements for the maple tree library code. - "memcg: further decouple v1 code from v2" from Shakeel Butt. Move more cgroup v1 remnants away from the v2 memcg code. - "memcg: initiate deprecation of v1 features" from Shakeel Butt. Adds various warnings telling users that memcg v1 features are deprecated. - "mm: swap: mTHP swap allocator base on swap cluster order" from Chris Li. Greatly improves the success rate of the mTHP swap allocation. - "mm: introduce numa_memblks" from Mike Rapoport. Moves various disparate per-arch implementations of numa_memblk code into generic code. - "mm: batch free swaps for zap_pte_range()" from Barry Song. Greatly improves the performance of munmap() of swap-filled ptes. - "support large folio swap-out and swap-in for shmem" from Baolin Wang. With this series we no longer split shmem large folios into simgle-page folios when swapping out shmem. - "mm/hugetlb: alloc/free gigantic folios" from Yu Zhao. Nice performance improvements and code reductions for gigantic folios. - "support shmem mTHP collapse" from Baolin Wang. Adds support for khugepaged's collapsing of shmem mTHP folios. - "mm: Optimize mseal checks" from Pedro Falcato. Fixes an mprotect() performance regression due to the addition of mseal(). - "Increase the number of bits available in page_type" from Matthew Wilcox. Increases the number of bits available in page_type! - "Simplify the page flags a little" from Matthew Wilcox. Many legacy page flags are now folio flags, so the page-based flags and their accessors/mutators can be removed. - "mm: store zero pages to be swapped out in a bitmap" from Usama Arif. An optimization which permits us to avoid writing/reading zero-filled zswap pages to backing store. - "Avoid MAP_FIXED gap exposure" from Liam Howlett. Fixes a race window which occurs when a MAP_FIXED operqtion is occurring during an unrelated vma tree walk. - "mm: remove vma_merge()" from Lorenzo Stoakes. Major rotorooting of the vma_merge() functionality, making ot cleaner, more testable and better tested. - "misc fixups for DAMON {self,kunit} tests" from SeongJae Park. Minor fixups of DAMON selftests and kunit tests. - "mm: memory_hotplug: improve do_migrate_range()" from Kefeng Wang. Code cleanups and folio conversions. - "Shmem mTHP controls and stats improvements" from Ryan Roberts. Cleanups for shmem controls and stats. - "mm: count the number of anonymous THPs per size" from Barry Song. Expose additional anon THP stats to userspace for improved tuning. - "mm: finish isolate/putback_lru_page()" from Kefeng Wang: more folio conversions and removal of now-unused page-based APIs. - "replace per-quota region priorities histogram buffer with per-context one" from SeongJae Park. DAMON histogram rationalization. - "Docs/damon: update GitHub repo URLs and maintainer-profile" from SeongJae Park. DAMON documentation updates. - "mm/vdpa: correct misuse of non-direct-reclaim __GFP_NOFAIL and improve related doc and warn" from Jason Wang: fixes usage of page allocator __GFP_NOFAIL and GFP_ATOMIC flags. - "mm: split underused THPs" from Yu Zhao. Improve THP=always policy. This was overprovisioning THPs in sparsely accessed memory areas. - "zram: introduce custom comp backends API" frm Sergey Senozhatsky. Add support for zram run-time compression algorithm tuning. - "mm: Care about shadow stack guard gap when getting an unmapped area" from Mark Brown. Fix up the various arch_get_unmapped_area() implementations to better respect guard areas. - "Improve mem_cgroup_iter()" from Kinsey Ho. Improve the reliability of mem_cgroup_iter() and various code cleanups. - "mm: Support huge pfnmaps" from Peter Xu. Extends the usage of huge pfnmap support. - "resource: Fix region_intersects() vs add_memory_driver_managed()" from Huang Ying. Fix a bug in region_intersects() for systems with CXL memory. - "mm: hwpoison: two more poison recovery" from Kefeng Wang. Teaches a couple more code paths to correctly recover from the encountering of poisoned memry. - "mm: enable large folios swap-in support" from Barry Song. Support the swapin of mTHP memory into appropriately-sized folios, rather than into single-page folios" * tag 'mm-stable-2024-09-20-02-31' of git://git.kernel.org/pub/scm/linux/kernel/git/akpm/mm: (416 commits) zram: free secondary algorithms names uprobes: turn xol_area->pages[2] into xol_area->page uprobes: introduce the global struct vm_special_mapping xol_mapping Revert "uprobes: use vm_special_mapping close() functionality" mm: support large folios swap-in for sync io devices mm: add nr argument in mem_cgroup_swapin_uncharge_swap() helper to support large folios mm: fix swap_read_folio_zeromap() for large folios with partial zeromap mm/debug_vm_pgtable: Use pxdp_get() for accessing page table entries set_memory: add __must_check to generic stubs mm/vma: return the exact errno in vms_gather_munmap_vmas() memcg: cleanup with !CONFIG_MEMCG_V1 mm/show_mem.c: report alloc tags in human readable units mm: support poison recovery from copy_present_page() mm: support poison recovery from do_cow_fault() resource, kunit: add test case for region_intersects() resource: make alloc_free_mem_region() works for iomem_resource mm: z3fold: deprecate CONFIG_Z3FOLD vfio/pci: implement huge_fault support mm/arm64: support large pfn mappings mm/x86: support large pfn mappings ...
Diffstat (limited to 'mm/huge_memory.c')
-rw-r--r--mm/huge_memory.c589
1 files changed, 471 insertions, 118 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index b71f744d360c..0580ac9e47b9 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -40,6 +40,7 @@
#include <linux/memory-tiers.h>
#include <linux/compat.h>
#include <linux/pgalloc_tag.h>
+#include <linux/pagewalk.h>
#include <asm/tlb.h>
#include <asm/pgalloc.h>
@@ -73,6 +74,7 @@ static unsigned long deferred_split_count(struct shrinker *shrink,
struct shrink_control *sc);
static unsigned long deferred_split_scan(struct shrinker *shrink,
struct shrink_control *sc);
+static bool split_underused_thp = true;
static atomic_t huge_zero_refcount;
struct folio *huge_zero_folio __read_mostly;
@@ -80,6 +82,7 @@ unsigned long huge_zero_pfn __read_mostly = ~0UL;
unsigned long huge_anon_orders_always __read_mostly;
unsigned long huge_anon_orders_madvise __read_mostly;
unsigned long huge_anon_orders_inherit __read_mostly;
+static bool anon_orders_configured __initdata;
unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
unsigned long vm_flags,
@@ -94,8 +97,8 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
/* Check the intersection of requested and supported orders. */
if (vma_is_anonymous(vma))
supported_orders = THP_ORDERS_ALL_ANON;
- else if (vma_is_dax(vma))
- supported_orders = THP_ORDERS_ALL_FILE_DAX;
+ else if (vma_is_special_huge(vma))
+ supported_orders = THP_ORDERS_ALL_SPECIAL;
else
supported_orders = THP_ORDERS_ALL_FILE_DEFAULT;
@@ -159,15 +162,10 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
* Must be done before hugepage flags check since shmem has its
* own flags.
*/
- if (!in_pf && shmem_file(vma->vm_file)) {
- bool global_huge = shmem_is_huge(file_inode(vma->vm_file), vma->vm_pgoff,
- !enforce_sysfs, vma->vm_mm, vm_flags);
-
- if (!vma_is_anon_shmem(vma))
- return global_huge ? orders : 0;
+ if (!in_pf && shmem_file(vma->vm_file))
return shmem_allowable_huge_orders(file_inode(vma->vm_file),
- vma, vma->vm_pgoff, global_huge);
- }
+ vma, vma->vm_pgoff, 0,
+ !enforce_sysfs);
if (!vma_is_anonymous(vma)) {
/*
@@ -445,6 +443,27 @@ static ssize_t hpage_pmd_size_show(struct kobject *kobj,
static struct kobj_attribute hpage_pmd_size_attr =
__ATTR_RO(hpage_pmd_size);
+static ssize_t split_underused_thp_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ return sysfs_emit(buf, "%d\n", split_underused_thp);
+}
+
+static ssize_t split_underused_thp_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
+{
+ int err = kstrtobool(buf, &split_underused_thp);
+
+ if (err < 0)
+ return err;
+
+ return count;
+}
+
+static struct kobj_attribute split_underused_thp_attr = __ATTR(
+ shrink_underused, 0644, split_underused_thp_show, split_underused_thp_store);
+
static struct attribute *hugepage_attr[] = {
&enabled_attr.attr,
&defrag_attr.attr,
@@ -453,6 +472,7 @@ static struct attribute *hugepage_attr[] = {
#ifdef CONFIG_SHMEM
&shmem_enabled_attr.attr,
#endif
+ &split_underused_thp_attr.attr,
NULL,
};
@@ -465,8 +485,8 @@ static void thpsize_release(struct kobject *kobj);
static DEFINE_SPINLOCK(huge_anon_orders_lock);
static LIST_HEAD(thpsize_list);
-static ssize_t thpsize_enabled_show(struct kobject *kobj,
- struct kobj_attribute *attr, char *buf)
+static ssize_t anon_enabled_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
{
int order = to_thpsize(kobj)->order;
const char *output;
@@ -483,9 +503,9 @@ static ssize_t thpsize_enabled_show(struct kobject *kobj,
return sysfs_emit(buf, "%s\n", output);
}
-static ssize_t thpsize_enabled_store(struct kobject *kobj,
- struct kobj_attribute *attr,
- const char *buf, size_t count)
+static ssize_t anon_enabled_store(struct kobject *kobj,
+ struct kobj_attribute *attr,
+ const char *buf, size_t count)
{
int order = to_thpsize(kobj)->order;
ssize_t ret = count;
@@ -527,19 +547,35 @@ static ssize_t thpsize_enabled_store(struct kobject *kobj,
return ret;
}
-static struct kobj_attribute thpsize_enabled_attr =
- __ATTR(enabled, 0644, thpsize_enabled_show, thpsize_enabled_store);
+static struct kobj_attribute anon_enabled_attr =
+ __ATTR(enabled, 0644, anon_enabled_show, anon_enabled_store);
+
+static struct attribute *anon_ctrl_attrs[] = {
+ &anon_enabled_attr.attr,
+ NULL,
+};
+
+static const struct attribute_group anon_ctrl_attr_grp = {
+ .attrs = anon_ctrl_attrs,
+};
-static struct attribute *thpsize_attrs[] = {
- &thpsize_enabled_attr.attr,
+static struct attribute *file_ctrl_attrs[] = {
#ifdef CONFIG_SHMEM
&thpsize_shmem_enabled_attr.attr,
#endif
NULL,
};
-static const struct attribute_group thpsize_attr_group = {
- .attrs = thpsize_attrs,
+static const struct attribute_group file_ctrl_attr_grp = {
+ .attrs = file_ctrl_attrs,
+};
+
+static struct attribute *any_ctrl_attrs[] = {
+ NULL,
+};
+
+static const struct attribute_group any_ctrl_attr_grp = {
+ .attrs = any_ctrl_attrs,
};
static const struct kobj_type thpsize_ktype = {
@@ -578,64 +614,136 @@ DEFINE_MTHP_STAT_ATTR(anon_fault_fallback, MTHP_STAT_ANON_FAULT_FALLBACK);
DEFINE_MTHP_STAT_ATTR(anon_fault_fallback_charge, MTHP_STAT_ANON_FAULT_FALLBACK_CHARGE);
DEFINE_MTHP_STAT_ATTR(swpout, MTHP_STAT_SWPOUT);
DEFINE_MTHP_STAT_ATTR(swpout_fallback, MTHP_STAT_SWPOUT_FALLBACK);
+#ifdef CONFIG_SHMEM
DEFINE_MTHP_STAT_ATTR(shmem_alloc, MTHP_STAT_SHMEM_ALLOC);
DEFINE_MTHP_STAT_ATTR(shmem_fallback, MTHP_STAT_SHMEM_FALLBACK);
DEFINE_MTHP_STAT_ATTR(shmem_fallback_charge, MTHP_STAT_SHMEM_FALLBACK_CHARGE);
+#endif
DEFINE_MTHP_STAT_ATTR(split, MTHP_STAT_SPLIT);
DEFINE_MTHP_STAT_ATTR(split_failed, MTHP_STAT_SPLIT_FAILED);
DEFINE_MTHP_STAT_ATTR(split_deferred, MTHP_STAT_SPLIT_DEFERRED);
+DEFINE_MTHP_STAT_ATTR(nr_anon, MTHP_STAT_NR_ANON);
+DEFINE_MTHP_STAT_ATTR(nr_anon_partially_mapped, MTHP_STAT_NR_ANON_PARTIALLY_MAPPED);
-static struct attribute *stats_attrs[] = {
+static struct attribute *anon_stats_attrs[] = {
&anon_fault_alloc_attr.attr,
&anon_fault_fallback_attr.attr,
&anon_fault_fallback_charge_attr.attr,
+#ifndef CONFIG_SHMEM
&swpout_attr.attr,
&swpout_fallback_attr.attr,
+#endif
+ &split_deferred_attr.attr,
+ &nr_anon_attr.attr,
+ &nr_anon_partially_mapped_attr.attr,
+ NULL,
+};
+
+static struct attribute_group anon_stats_attr_grp = {
+ .name = "stats",
+ .attrs = anon_stats_attrs,
+};
+
+static struct attribute *file_stats_attrs[] = {
+#ifdef CONFIG_SHMEM
&shmem_alloc_attr.attr,
&shmem_fallback_attr.attr,
&shmem_fallback_charge_attr.attr,
+#endif
+ NULL,
+};
+
+static struct attribute_group file_stats_attr_grp = {
+ .name = "stats",
+ .attrs = file_stats_attrs,
+};
+
+static struct attribute *any_stats_attrs[] = {
+#ifdef CONFIG_SHMEM
+ &swpout_attr.attr,
+ &swpout_fallback_attr.attr,
+#endif
&split_attr.attr,
&split_failed_attr.attr,
- &split_deferred_attr.attr,
NULL,
};
-static struct attribute_group stats_attr_group = {
+static struct attribute_group any_stats_attr_grp = {
.name = "stats",
- .attrs = stats_attrs,
+ .attrs = any_stats_attrs,
};
+static int sysfs_add_group(struct kobject *kobj,
+ const struct attribute_group *grp)
+{
+ int ret = -ENOENT;
+
+ /*
+ * If the group is named, try to merge first, assuming the subdirectory
+ * was already created. This avoids the warning emitted by
+ * sysfs_create_group() if the directory already exists.
+ */
+ if (grp->name)
+ ret = sysfs_merge_group(kobj, grp);
+ if (ret)
+ ret = sysfs_create_group(kobj, grp);
+
+ return ret;
+}
+
static struct thpsize *thpsize_create(int order, struct kobject *parent)
{
unsigned long size = (PAGE_SIZE << order) / SZ_1K;
struct thpsize *thpsize;
- int ret;
+ int ret = -ENOMEM;
thpsize = kzalloc(sizeof(*thpsize), GFP_KERNEL);
if (!thpsize)
- return ERR_PTR(-ENOMEM);
+ goto err;
+
+ thpsize->order = order;
ret = kobject_init_and_add(&thpsize->kobj, &thpsize_ktype, parent,
"hugepages-%lukB", size);
if (ret) {
kfree(thpsize);
- return ERR_PTR(ret);
+ goto err;
}
- ret = sysfs_create_group(&thpsize->kobj, &thpsize_attr_group);
- if (ret) {
- kobject_put(&thpsize->kobj);
- return ERR_PTR(ret);
+
+ ret = sysfs_add_group(&thpsize->kobj, &any_ctrl_attr_grp);
+ if (ret)
+ goto err_put;
+
+ ret = sysfs_add_group(&thpsize->kobj, &any_stats_attr_grp);
+ if (ret)
+ goto err_put;
+
+ if (BIT(order) & THP_ORDERS_ALL_ANON) {
+ ret = sysfs_add_group(&thpsize->kobj, &anon_ctrl_attr_grp);
+ if (ret)
+ goto err_put;
+
+ ret = sysfs_add_group(&thpsize->kobj, &anon_stats_attr_grp);
+ if (ret)
+ goto err_put;
}
- ret = sysfs_create_group(&thpsize->kobj, &stats_attr_group);
- if (ret) {
- kobject_put(&thpsize->kobj);
- return ERR_PTR(ret);
+ if (BIT(order) & THP_ORDERS_ALL_FILE_DEFAULT) {
+ ret = sysfs_add_group(&thpsize->kobj, &file_ctrl_attr_grp);
+ if (ret)
+ goto err_put;
+
+ ret = sysfs_add_group(&thpsize->kobj, &file_stats_attr_grp);
+ if (ret)
+ goto err_put;
}
- thpsize->order = order;
return thpsize;
+err_put:
+ kobject_put(&thpsize->kobj);
+err:
+ return ERR_PTR(ret);
}
static void thpsize_release(struct kobject *kobj)
@@ -655,7 +763,8 @@ static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj)
* disable all other sizes. powerpc's PMD_ORDER isn't a compile-time
* constant so we have to do this here.
*/
- huge_anon_orders_inherit = BIT(PMD_ORDER);
+ if (!anon_orders_configured)
+ huge_anon_orders_inherit = BIT(PMD_ORDER);
*hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj);
if (unlikely(!*hugepage_kobj)) {
@@ -675,7 +784,7 @@ static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj)
goto remove_hp_group;
}
- orders = THP_ORDERS_ALL_ANON;
+ orders = THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE_DEFAULT;
order = highest_order(orders);
while (orders) {
thpsize = thpsize_create(order, *hugepage_kobj);
@@ -840,6 +949,100 @@ out:
}
__setup("transparent_hugepage=", setup_transparent_hugepage);
+static inline int get_order_from_str(const char *size_str)
+{
+ unsigned long size;
+ char *endptr;
+ int order;
+
+ size = memparse(size_str, &endptr);
+
+ if (!is_power_of_2(size))
+ goto err;
+ order = get_order(size);
+ if (BIT(order) & ~THP_ORDERS_ALL_ANON)
+ goto err;
+
+ return order;
+err:
+ pr_err("invalid size %s in thp_anon boot parameter\n", size_str);
+ return -EINVAL;
+}
+
+static char str_dup[PAGE_SIZE] __initdata;
+static int __init setup_thp_anon(char *str)
+{
+ char *token, *range, *policy, *subtoken;
+ unsigned long always, inherit, madvise;
+ char *start_size, *end_size;
+ int start, end, nr;
+ char *p;
+
+ if (!str || strlen(str) + 1 > PAGE_SIZE)
+ goto err;
+ strcpy(str_dup, str);
+
+ always = huge_anon_orders_always;
+ madvise = huge_anon_orders_madvise;
+ inherit = huge_anon_orders_inherit;
+ p = str_dup;
+ while ((token = strsep(&p, ";")) != NULL) {
+ range = strsep(&token, ":");
+ policy = token;
+
+ if (!policy)
+ goto err;
+
+ while ((subtoken = strsep(&range, ",")) != NULL) {
+ if (strchr(subtoken, '-')) {
+ start_size = strsep(&subtoken, "-");
+ end_size = subtoken;
+
+ start = get_order_from_str(start_size);
+ end = get_order_from_str(end_size);
+ } else {
+ start = end = get_order_from_str(subtoken);
+ }
+
+ if (start < 0 || end < 0 || start > end)
+ goto err;
+
+ nr = end - start + 1;
+ if (!strcmp(policy, "always")) {
+ bitmap_set(&always, start, nr);
+ bitmap_clear(&inherit, start, nr);
+ bitmap_clear(&madvise, start, nr);
+ } else if (!strcmp(policy, "madvise")) {
+ bitmap_set(&madvise, start, nr);
+ bitmap_clear(&inherit, start, nr);
+ bitmap_clear(&always, start, nr);
+ } else if (!strcmp(policy, "inherit")) {
+ bitmap_set(&inherit, start, nr);
+ bitmap_clear(&madvise, start, nr);
+ bitmap_clear(&always, start, nr);
+ } else if (!strcmp(policy, "never")) {
+ bitmap_clear(&inherit, start, nr);
+ bitmap_clear(&madvise, start, nr);
+ bitmap_clear(&always, start, nr);
+ } else {
+ pr_err("invalid policy %s in thp_anon boot parameter\n", policy);
+ goto err;
+ }
+ }
+ }
+
+ huge_anon_orders_always = always;
+ huge_anon_orders_madvise = madvise;
+ huge_anon_orders_inherit = inherit;
+ anon_orders_configured = true;
+ return 1;
+
+err:
+ pr_warn("thp_anon=%s: error parsing string, ignoring setting\n", str);
+ return 0;
+}
+__setup("thp_anon=", setup_thp_anon);
+
pmd_t maybe_pmd_mkwrite(pmd_t pmd, struct vm_area_struct *vma)
{
if (likely(vma->vm_flags & VM_WRITE))
@@ -1009,6 +1212,7 @@ static vm_fault_t __do_huge_pmd_anonymous_page(struct vm_fault *vmf,
update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
add_mm_counter(vma->vm_mm, MM_ANONPAGES, HPAGE_PMD_NR);
mm_inc_nr_ptes(vma->vm_mm);
+ deferred_split_folio(folio, false);
spin_unlock(vmf->ptl);
count_vm_event(THP_FAULT_ALLOC);
count_mthp_stat(HPAGE_PMD_ORDER, MTHP_STAT_ANON_FAULT_ALLOC);
@@ -1168,6 +1372,8 @@ static void insert_pfn_pmd(struct vm_area_struct *vma, unsigned long addr,
entry = pmd_mkhuge(pfn_t_pmd(pfn, prot));
if (pfn_t_devmap(pfn))
entry = pmd_mkdevmap(entry);
+ else
+ entry = pmd_mkspecial(entry);
if (write) {
entry = pmd_mkyoung(pmd_mkdirty(entry));
entry = maybe_pmd_mkwrite(entry, vma);
@@ -1251,10 +1457,8 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
ptl = pud_lock(mm, pud);
if (!pud_none(*pud)) {
if (write) {
- if (pud_pfn(*pud) != pfn_t_to_pfn(pfn)) {
- WARN_ON_ONCE(!is_huge_zero_pud(*pud));
+ if (WARN_ON_ONCE(pud_pfn(*pud) != pfn_t_to_pfn(pfn)))
goto out_unlock;
- }
entry = pud_mkyoung(*pud);
entry = maybe_pud_mkwrite(pud_mkdirty(entry), vma);
if (pudp_set_access_flags(vma, addr, pud, entry, 1))
@@ -1266,6 +1470,8 @@ static void insert_pfn_pud(struct vm_area_struct *vma, unsigned long addr,
entry = pud_mkhuge(pfn_t_pud(pfn, prot));
if (pfn_t_devmap(pfn))
entry = pud_mkdevmap(entry);
+ else
+ entry = pud_mkspecial(entry);
if (write) {
entry = pud_mkyoung(pud_mkdirty(entry));
entry = maybe_pud_mkwrite(entry, vma);
@@ -1379,6 +1585,24 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm,
pgtable_t pgtable = NULL;
int ret = -ENOMEM;
+ pmd = pmdp_get_lockless(src_pmd);
+ if (unlikely(pmd_special(pmd))) {
+ dst_ptl = pmd_lock(dst_mm, dst_pmd);
+ src_ptl = pmd_lockptr(src_mm, src_pmd);
+ spin_lock_nested(src_ptl, SINGLE_DEPTH_NESTING);
+ /*
+ * No need to recheck the pmd, it can't change with write
+ * mmap lock held here.
+ *
+ * Meanwhile, making sure it's not a CoW VMA with writable
+ * mapping, otherwise it means either the anon page wrongly
+ * applied special bit, or we made the PRIVATE mapping be
+ * able to wrongly write to the backend MMIO.
+ */
+ VM_WARN_ON_ONCE(is_cow_mapping(src_vma->vm_flags) && pmd_write(pmd));
+ goto set_pmd;
+ }
+
/* Skip if can be re-fill on fault */
if (!vma_is_anonymous(dst_vma))
return 0;
@@ -1460,7 +1684,9 @@ out_zero_page:
pmdp_set_wrprotect(src_mm, addr, src_pmd);
if (!userfaultfd_wp(dst_vma))
pmd = pmd_clear_uffd_wp(pmd);
- pmd = pmd_mkold(pmd_wrprotect(pmd));
+ pmd = pmd_wrprotect(pmd);
+set_pmd:
+ pmd = pmd_mkold(pmd);
set_pmd_at(dst_mm, addr, dst_pmd, pmd);
ret = 0;
@@ -1503,20 +1729,14 @@ int copy_huge_pud(struct mm_struct *dst_mm, struct mm_struct *src_mm,
goto out_unlock;
/*
- * When page table lock is held, the huge zero pud should not be
- * under splitting since we don't split the page itself, only pud to
- * a page table.
- */
- if (is_huge_zero_pud(pud)) {
- /* No huge zero pud yet */
- }
-
- /*
* TODO: once we support anonymous pages, use
* folio_try_dup_anon_rmap_*() and split if duplicating fails.
*/
- pudp_set_wrprotect(src_mm, addr, src_pud);
- pud = pud_mkold(pud_wrprotect(pud));
+ if (is_cow_mapping(vma->vm_flags) && pud_write(pud)) {
+ pudp_set_wrprotect(src_mm, addr, src_pud);
+ pud = pud_wrprotect(pud);
+ }
+ pud = pud_mkold(pud);
set_pud_at(dst_mm, addr, dst_pud, pud);
ret = 0;
@@ -1675,22 +1895,23 @@ static inline bool can_change_pmd_writable(struct vm_area_struct *vma,
vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
{
struct vm_area_struct *vma = vmf->vma;
- pmd_t oldpmd = vmf->orig_pmd;
- pmd_t pmd;
struct folio *folio;
unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
int nid = NUMA_NO_NODE;
- int target_nid, last_cpupid = (-1 & LAST_CPUPID_MASK);
+ int target_nid, last_cpupid;
+ pmd_t pmd, old_pmd;
bool writable = false;
int flags = 0;
vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
- if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) {
+ old_pmd = pmdp_get(vmf->pmd);
+
+ if (unlikely(!pmd_same(old_pmd, vmf->orig_pmd))) {
spin_unlock(vmf->ptl);
return 0;
}
- pmd = pmd_modify(oldpmd, vma->vm_page_prot);
+ pmd = pmd_modify(old_pmd, vma->vm_page_prot);
/*
* Detect now whether the PMD could be writable; this information
@@ -1705,18 +1926,10 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
if (!folio)
goto out_map;
- /* See similar comment in do_numa_page for explanation */
- if (!writable)
- flags |= TNF_NO_GROUP;
-
nid = folio_nid(folio);
- /*
- * For memory tiering mode, cpupid of slow memory page is used
- * to record page access time. So use default value.
- */
- if (node_is_toptier(nid))
- last_cpupid = folio_last_cpupid(folio);
- target_nid = numa_migrate_prep(folio, vmf, haddr, nid, &flags);
+
+ target_nid = numa_migrate_check(folio, vmf, haddr, &flags, writable,
+ &last_cpupid);
if (target_nid == NUMA_NO_NODE)
goto out_map;
if (migrate_misplaced_folio_prepare(folio, vma, target_nid)) {
@@ -1736,13 +1949,13 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
flags |= TNF_MIGRATE_FAIL;
vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
- if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) {
+ if (unlikely(!pmd_same(pmdp_get(vmf->pmd), vmf->orig_pmd))) {
spin_unlock(vmf->ptl);
return 0;
}
out_map:
/* Restore the PMD */
- pmd = pmd_modify(oldpmd, vma->vm_page_prot);
+ pmd = pmd_modify(pmdp_get(vmf->pmd), vma->vm_page_prot);
pmd = pmd_mkyoung(pmd);
if (writable)
pmd = pmd_mkwrite(pmd, vma);
@@ -2064,8 +2277,7 @@ int change_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma,
toptier)
goto unlock;
- if (sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING &&
- !toptier)
+ if (folio_use_access_time(folio))
folio_xchg_access_time(folio,
jiffies_to_msecs(jiffies));
}
@@ -2118,6 +2330,53 @@ unlock:
return ret;
}
+/*
+ * Returns:
+ *
+ * - 0: if pud leaf changed from under us
+ * - 1: if pud can be skipped
+ * - HPAGE_PUD_NR: if pud was successfully processed
+ */
+#ifdef CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD
+int change_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
+ pud_t *pudp, unsigned long addr, pgprot_t newprot,
+ unsigned long cp_flags)
+{
+ struct mm_struct *mm = vma->vm_mm;
+ pud_t oldpud, entry;
+ spinlock_t *ptl;
+
+ tlb_change_page_size(tlb, HPAGE_PUD_SIZE);
+
+ /* NUMA balancing doesn't apply to dax */
+ if (cp_flags & MM_CP_PROT_NUMA)
+ return 1;
+
+ /*
+ * Huge entries on userfault-wp only works with anonymous, while we
+ * don't have anonymous PUDs yet.
+ */
+ if (WARN_ON_ONCE(cp_flags & MM_CP_UFFD_WP_ALL))
+ return 1;
+
+ ptl = __pud_trans_huge_lock(pudp, vma);
+ if (!ptl)
+ return 0;
+
+ /*
+ * Can't clear PUD or it can race with concurrent zapping. See
+ * change_huge_pmd().
+ */
+ oldpud = pudp_invalidate(vma, addr, pudp);
+ entry = pud_modify(oldpud, newprot);
+ set_pud_at(mm, addr, pudp, entry);
+ tlb_flush_pud_range(tlb, addr, HPAGE_PUD_SIZE);
+
+ spin_unlock(ptl);
+ return HPAGE_PUD_NR;
+}
+#endif
+
#ifdef CONFIG_USERFAULTFD
/*
* The PT lock for src_pmd and dst_vma/src_vma (for reading) are locked by
@@ -2297,12 +2556,14 @@ int zap_huge_pud(struct mmu_gather *tlb, struct vm_area_struct *vma,
pud_t *pud, unsigned long addr)
{
spinlock_t *ptl;
+ pud_t orig_pud;
ptl = __pud_trans_huge_lock(pud, vma);
if (!ptl)
return 0;
- pudp_huge_get_and_clear_full(vma, addr, pud, tlb->fullmm);
+ orig_pud = pudp_huge_get_and_clear_full(vma, addr, pud, tlb->fullmm);
+ arch_check_zapped_pud(vma, orig_pud);
tlb_remove_pud_tlb_entry(tlb, pud, addr);
if (vma_is_special_huge(vma)) {
spin_unlock(ptl);
@@ -2346,6 +2607,11 @@ out:
spin_unlock(ptl);
mmu_notifier_invalidate_range_end(&range);
}
+#else
+void __split_huge_pud(struct vm_area_struct *vma, pud_t *pud,
+ unsigned long address)
+{
+}
#endif /* CONFIG_HAVE_ARCH_TRANSPARENT_HUGEPAGE_PUD */
static void __split_huge_zero_page_pmd(struct vm_area_struct *vma,
@@ -2780,7 +3046,7 @@ bool unmap_huge_pmd_locked(struct vm_area_struct *vma, unsigned long addr,
return false;
}
-static void remap_page(struct folio *folio, unsigned long nr)
+static void remap_page(struct folio *folio, unsigned long nr, int flags)
{
int i = 0;
@@ -2788,7 +3054,7 @@ static void remap_page(struct folio *folio, unsigned long nr)
if (!folio_test_anon(folio))
return;
for (;;) {
- remove_migration_ptes(folio, folio, true);
+ remove_migration_ptes(folio, folio, RMP_LOCKED | flags);
i += folio_nr_pages(folio);
if (i >= nr)
break;
@@ -2796,25 +3062,25 @@ static void remap_page(struct folio *folio, unsigned long nr)
}
}
-static void lru_add_page_tail(struct page *head, struct page *tail,
+static void lru_add_page_tail(struct folio *folio, struct page *tail,
struct lruvec *lruvec, struct list_head *list)
{
- VM_BUG_ON_PAGE(!PageHead(head), head);
- VM_BUG_ON_PAGE(PageLRU(tail), head);
+ VM_BUG_ON_FOLIO(!folio_test_large(folio), folio);
+ VM_BUG_ON_FOLIO(PageLRU(tail), folio);
lockdep_assert_held(&lruvec->lru_lock);
if (list) {
/* page reclaim is reclaiming a huge page */
- VM_WARN_ON(PageLRU(head));
+ VM_WARN_ON(folio_test_lru(folio));
get_page(tail);
list_add_tail(&tail->lru, list);
} else {
/* head is still on lru (and we have it frozen) */
- VM_WARN_ON(!PageLRU(head));
- if (PageUnevictable(tail))
+ VM_WARN_ON(!folio_test_lru(folio));
+ if (folio_test_unevictable(folio))
tail->mlock_count = 0;
else
- list_add_tail(&tail->lru, &head->lru);
+ list_add_tail(&tail->lru, &folio->lru);
SetPageLRU(tail);
}
}
@@ -2857,8 +3123,10 @@ static void __split_huge_page_tail(struct folio *folio, int tail,
(1L << PG_workingset) |
(1L << PG_locked) |
(1L << PG_unevictable) |
-#ifdef CONFIG_ARCH_USES_PG_ARCH_X
+#ifdef CONFIG_ARCH_USES_PG_ARCH_2
(1L << PG_arch_2) |
+#endif
+#ifdef CONFIG_ARCH_USES_PG_ARCH_3
(1L << PG_arch_3) |
#endif
(1L << PG_dirty) |
@@ -2913,7 +3181,7 @@ static void __split_huge_page_tail(struct folio *folio, int tail,
* pages to show after the currently processed elements - e.g.
* migrate_pages
*/
- lru_add_page_tail(head, page_tail, lruvec, list);
+ lru_add_page_tail(folio, page_tail, lruvec, list);
}
static void __split_huge_page(struct page *page, struct list_head *list,
@@ -2976,7 +3244,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
/* Caller disabled irqs, so they are still disabled here */
split_page_owner(head, order, new_order);
- pgalloc_tag_split(head, 1 << order);
+ pgalloc_tag_split(folio, order, new_order);
/* See comment in __split_huge_page_tail() */
if (folio_test_anon(folio)) {
@@ -2996,7 +3264,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
if (nr_dropped)
shmem_uncharge(folio->mapping->host, nr_dropped);
- remap_page(folio, nr);
+ remap_page(folio, nr, PageAnon(head) ? RMP_USE_SHARED_ZEROPAGE : 0);
/*
* set page to its compound_head when split to non order-0 pages, so
@@ -3025,7 +3293,7 @@ static void __split_huge_page(struct page *page, struct list_head *list,
}
/* Racy check whether the huge page can be split */
-bool can_split_folio(struct folio *folio, int *pextra_pins)
+bool can_split_folio(struct folio *folio, int caller_pins, int *pextra_pins)
{
int extra_pins;
@@ -3037,7 +3305,8 @@ bool can_split_folio(struct folio *folio, int *pextra_pins)
extra_pins = folio_nr_pages(folio);
if (pextra_pins)
*pextra_pins = extra_pins;
- return folio_mapcount(folio) == folio_ref_count(folio) - extra_pins - 1;
+ return folio_mapcount(folio) == folio_ref_count(folio) - extra_pins -
+ caller_pins;
}
/*
@@ -3094,8 +3363,9 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
struct deferred_split *ds_queue = get_deferred_split_queue(folio);
/* reset xarray order to new order after split */
XA_STATE_ORDER(xas, &folio->mapping->i_pages, folio->index, new_order);
- struct anon_vma *anon_vma = NULL;
+ bool is_anon = folio_test_anon(folio);
struct address_space *mapping = NULL;
+ struct anon_vma *anon_vma = NULL;
int order = folio_order(folio);
int extra_pins, ret;
pgoff_t end;
@@ -3107,7 +3377,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
if (new_order >= folio_order(folio))
return -EINVAL;
- if (folio_test_anon(folio)) {
+ if (is_anon) {
/* order-1 is not supported for anonymous THP. */
if (new_order == 1) {
VM_WARN_ONCE(1, "Cannot split to order-1 folio");
@@ -3147,7 +3417,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
if (folio_test_writeback(folio))
return -EBUSY;
- if (folio_test_anon(folio)) {
+ if (is_anon) {
/*
* The caller does not necessarily hold an mmap_lock that would
* prevent the anon_vma disappearing so we first we take a
@@ -3217,7 +3487,7 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
* Racy check if we can split the page, before unmap_folio() will
* split PMDs
*/
- if (!can_split_folio(folio, &extra_pins)) {
+ if (!can_split_folio(folio, 1, &extra_pins)) {
ret = -EAGAIN;
goto out_unlock;
}
@@ -3243,6 +3513,11 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
if (folio_order(folio) > 1 &&
!list_empty(&folio->_deferred_list)) {
ds_queue->split_queue_len--;
+ if (folio_test_partially_mapped(folio)) {
+ __folio_clear_partially_mapped(folio);
+ mod_mthp_stat(folio_order(folio),
+ MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1);
+ }
/*
* Reinitialize page_deferred_list after removing the
* page from the split_queue, otherwise a subsequent
@@ -3269,6 +3544,10 @@ int split_huge_page_to_list_to_order(struct page *page, struct list_head *list,
}
}
+ if (is_anon) {
+ mod_mthp_stat(order, MTHP_STAT_NR_ANON, -1);
+ mod_mthp_stat(new_order, MTHP_STAT_NR_ANON, 1 << (order - new_order));
+ }
__split_huge_page(page, list, end, new_order);
ret = 0;
} else {
@@ -3277,7 +3556,7 @@ fail:
if (mapping)
xas_unlock(&xas);
local_irq_enable();
- remap_page(folio, folio_nr_pages(folio));
+ remap_page(folio, folio_nr_pages(folio), 0);
ret = -EAGAIN;
}
@@ -3329,12 +3608,18 @@ void __folio_undo_large_rmappable(struct folio *folio)
spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
if (!list_empty(&folio->_deferred_list)) {
ds_queue->split_queue_len--;
+ if (folio_test_partially_mapped(folio)) {
+ __folio_clear_partially_mapped(folio);
+ mod_mthp_stat(folio_order(folio),
+ MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1);
+ }
list_del_init(&folio->_deferred_list);
}
spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
}
-void deferred_split_folio(struct folio *folio)
+/* partially_mapped=false won't clear PG_partially_mapped folio flag */
+void deferred_split_folio(struct folio *folio, bool partially_mapped)
{
struct deferred_split *ds_queue = get_deferred_split_queue(folio);
#ifdef CONFIG_MEMCG
@@ -3349,6 +3634,9 @@ void deferred_split_folio(struct folio *folio)
if (folio_order(folio) <= 1)
return;
+ if (!partially_mapped && !split_underused_thp)
+ return;
+
/*
* The try_to_unmap() in page reclaim path might reach here too,
* this may cause a race condition to corrupt deferred split queue.
@@ -3362,14 +3650,21 @@ void deferred_split_folio(struct folio *folio)
if (folio_test_swapcache(folio))
return;
- if (!list_empty(&folio->_deferred_list))
- return;
-
spin_lock_irqsave(&ds_queue->split_queue_lock, flags);
+ if (partially_mapped) {
+ if (!folio_test_partially_mapped(folio)) {
+ __folio_set_partially_mapped(folio);
+ if (folio_test_pmd_mappable(folio))
+ count_vm_event(THP_DEFERRED_SPLIT_PAGE);
+ count_mthp_stat(folio_order(folio), MTHP_STAT_SPLIT_DEFERRED);
+ mod_mthp_stat(folio_order(folio), MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, 1);
+
+ }
+ } else {
+ /* partially mapped folios cannot become non-partially mapped */
+ VM_WARN_ON_FOLIO(folio_test_partially_mapped(folio), folio);
+ }
if (list_empty(&folio->_deferred_list)) {
- if (folio_test_pmd_mappable(folio))
- count_vm_event(THP_DEFERRED_SPLIT_PAGE);
- count_mthp_stat(folio_order(folio), MTHP_STAT_SPLIT_DEFERRED);
list_add_tail(&folio->_deferred_list, &ds_queue->split_queue);
ds_queue->split_queue_len++;
#ifdef CONFIG_MEMCG
@@ -3394,6 +3689,39 @@ static unsigned long deferred_split_count(struct shrinker *shrink,
return READ_ONCE(ds_queue->split_queue_len);
}
+static bool thp_underused(struct folio *folio)
+{
+ int num_zero_pages = 0, num_filled_pages = 0;
+ void *kaddr;
+ int i;
+
+ if (khugepaged_max_ptes_none == HPAGE_PMD_NR - 1)
+ return false;
+
+ for (i = 0; i < folio_nr_pages(folio); i++) {
+ kaddr = kmap_local_folio(folio, i * PAGE_SIZE);
+ if (!memchr_inv(kaddr, 0, PAGE_SIZE)) {
+ num_zero_pages++;
+ if (num_zero_pages > khugepaged_max_ptes_none) {
+ kunmap_local(kaddr);
+ return true;
+ }
+ } else {
+ /*
+ * Another path for early exit once the number
+ * of non-zero filled pages exceeds threshold.
+ */
+ num_filled_pages++;
+ if (num_filled_pages >= HPAGE_PMD_NR - khugepaged_max_ptes_none) {
+ kunmap_local(kaddr);
+ return false;
+ }
+ }
+ kunmap_local(kaddr);
+ }
+ return false;
+}
+
static unsigned long deferred_split_scan(struct shrinker *shrink,
struct shrink_control *sc)
{
@@ -3417,6 +3745,11 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
list_move(&folio->_deferred_list, &list);
} else {
/* We lost race with folio_put() */
+ if (folio_test_partially_mapped(folio)) {
+ __folio_clear_partially_mapped(folio);
+ mod_mthp_stat(folio_order(folio),
+ MTHP_STAT_NR_ANON_PARTIALLY_MAPPED, -1);
+ }
list_del_init(&folio->_deferred_list);
ds_queue->split_queue_len--;
}
@@ -3426,13 +3759,35 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
spin_unlock_irqrestore(&ds_queue->split_queue_lock, flags);
list_for_each_entry_safe(folio, next, &list, _deferred_list) {
+ bool did_split = false;
+ bool underused = false;
+
+ if (!folio_test_partially_mapped(folio)) {
+ underused = thp_underused(folio);
+ if (!underused)
+ goto next;
+ }
if (!folio_trylock(folio))
goto next;
- /* split_huge_page() removes page from list on success */
- if (!split_folio(folio))
+ if (!split_folio(folio)) {
+ did_split = true;
+ if (underused)
+ count_vm_event(THP_UNDERUSED_SPLIT_PAGE);
split++;
+ }
folio_unlock(folio);
next:
+ /*
+ * split_folio() removes folio from list on success.
+ * Only add back to the queue if folio is partially mapped.
+ * If thp_underused returns false, or if split_folio fails
+ * in the case it was underused, then consider it used and
+ * don't add it back to split_queue.
+ */
+ if (!did_split && !folio_test_partially_mapped(folio)) {
+ list_del_init(&folio->_deferred_list);
+ ds_queue->split_queue_len--;
+ }
folio_put(folio);
}
@@ -3518,16 +3873,11 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
vaddr_start &= PAGE_MASK;
vaddr_end &= PAGE_MASK;
- /* Find the task_struct from pid */
- rcu_read_lock();
- task = find_task_by_vpid(pid);
+ task = find_get_task_by_vpid(pid);
if (!task) {
- rcu_read_unlock();
ret = -ESRCH;
goto out;
}
- get_task_struct(task);
- rcu_read_unlock();
/* Find the mm_struct */
mm = get_task_mm(task);
@@ -3548,7 +3898,7 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
*/
for (addr = vaddr_start; addr < vaddr_end; addr += PAGE_SIZE) {
struct vm_area_struct *vma = vma_lookup(mm, addr);
- struct page *page;
+ struct folio_walk fw;
struct folio *folio;
struct address_space *mapping;
unsigned int target_order = new_order;
@@ -3562,13 +3912,10 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
continue;
}
- /* FOLL_DUMP to ignore special (like zero) pages */
- page = follow_page(vma, addr, FOLL_GET | FOLL_DUMP);
-
- if (IS_ERR_OR_NULL(page))
+ folio = folio_walk_start(&fw, vma, addr, 0);
+ if (!folio)
continue;
- folio = page_folio(page);
if (!is_transparent_hugepage(folio))
goto next;
@@ -3588,11 +3935,13 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
* can be split or not. So skip the check here.
*/
if (!folio_test_private(folio) &&
- !can_split_folio(folio, NULL))
+ !can_split_folio(folio, 0, NULL))
goto next;
if (!folio_trylock(folio))
goto next;
+ folio_get(folio);
+ folio_walk_end(&fw, vma);
if (!folio_test_anon(folio) && folio->mapping != mapping)
goto unlock;
@@ -3603,8 +3952,12 @@ static int split_huge_pages_pid(int pid, unsigned long vaddr_start,
unlock:
folio_unlock(folio);
-next:
folio_put(folio);
+
+ cond_resched();
+ continue;
+next:
+ folio_walk_end(&fw, vma);
cond_resched();
}
mmap_read_unlock(mm);