summaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorRyan Roberts <ryan.roberts@arm.com>2023-12-07 19:12:04 +0300
committerAndrew Morton <akpm@linux-foundation.org>2023-12-21 01:48:12 +0300
commit3485b88390b0af9e05dc2c3f57e9936f41e159a0 (patch)
tree023201bcd36dff0107643d203289c09e9879baef /mm
parent372cbd4d5a0665bf7e181c72f5e40e1bf59b0b08 (diff)
downloadlinux-3485b88390b0af9e05dc2c3f57e9936f41e159a0.tar.xz
mm: thp: introduce multi-size THP sysfs interface
In preparation for adding support for anonymous multi-size THP, introduce new sysfs structure that will be used to control the new behaviours. A new directory is added under transparent_hugepage for each supported THP size, and contains an `enabled` file, which can be set to "inherit" (to inherit the global setting), "always", "madvise" or "never". For now, the kernel still only supports PMD-sized anonymous THP, so only 1 directory is populated. The first half of the change converts transhuge_vma_suitable() and hugepage_vma_check() so that they take a bitfield of orders for which the user wants to determine support, and the functions filter out all the orders that can't be supported, given the current sysfs configuration and the VMA dimensions. The resulting functions are renamed to thp_vma_suitable_orders() and thp_vma_allowable_orders() respectively. Convenience functions that take a single, unencoded order and return a boolean are also defined as thp_vma_suitable_order() and thp_vma_allowable_order(). The second half of the change implements the new sysfs interface. It has been done so that each supported THP size has a `struct thpsize`, which describes the relevant metadata and is itself a kobject. This is pretty minimal for now, but should make it easy to add new per-thpsize files to the interface if needed in future (e.g. per-size defrag). Rather than keep the `enabled` state directly in the struct thpsize, I've elected to directly encode it into huge_anon_orders_[always|madvise|inherit] bitfields since this reduces the amount of work required in thp_vma_allowable_orders() which is called for every page fault. See Documentation/admin-guide/mm/transhuge.rst, as modified by this commit, for details of how the new sysfs interface works. [ryan.roberts@arm.com: fix build warning when CONFIG_SYSFS is disabled] Link: https://lkml.kernel.org/r/20231211125320.3997543-1-ryan.roberts@arm.com Link: https://lkml.kernel.org/r/20231207161211.2374093-4-ryan.roberts@arm.com Signed-off-by: Ryan Roberts <ryan.roberts@arm.com> Reviewed-by: Barry Song <v-songbaohua@oppo.com> Tested-by: Kefeng Wang <wangkefeng.wang@huawei.com> Tested-by: John Hubbard <jhubbard@nvidia.com> Acked-by: David Hildenbrand <david@redhat.com> Cc: Alistair Popple <apopple@nvidia.com> Cc: Anshuman Khandual <anshuman.khandual@arm.com> Cc: Catalin Marinas <catalin.marinas@arm.com> Cc: David Rientjes <rientjes@google.com> Cc: "Huang, Ying" <ying.huang@intel.com> Cc: Hugh Dickins <hughd@google.com> Cc: Itaru Kitayama <itaru.kitayama@gmail.com> Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com> Cc: Luis Chamberlain <mcgrof@kernel.org> Cc: Matthew Wilcox (Oracle) <willy@infradead.org> Cc: Vlastimil Babka <vbabka@suse.cz> Cc: Yang Shi <shy828301@gmail.com> Cc: Yin Fengwei <fengwei.yin@intel.com> Cc: Yu Zhao <yuzhao@google.com> Cc: Zi Yan <ziy@nvidia.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/huge_memory.c231
-rw-r--r--mm/khugepaged.c20
-rw-r--r--mm/memory.c6
-rw-r--r--mm/page_vma_mapped.c3
4 files changed, 221 insertions, 39 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c
index c848ea97ab02..387b030c7f15 100644
--- a/mm/huge_memory.c
+++ b/mm/huge_memory.c
@@ -74,12 +74,23 @@ static unsigned long deferred_split_scan(struct shrinker *shrink,
static atomic_t huge_zero_refcount;
struct page *huge_zero_page __read_mostly;
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;
+
+unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
+ unsigned long vm_flags, bool smaps,
+ bool in_pf, bool enforce_sysfs,
+ unsigned long orders)
+{
+ /* Check the intersection of requested and supported orders. */
+ orders &= vma_is_anonymous(vma) ?
+ THP_ORDERS_ALL_ANON : THP_ORDERS_ALL_FILE;
+ if (!orders)
+ return 0;
-bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags,
- bool smaps, bool in_pf, bool enforce_sysfs)
-{
if (!vma->vm_mm) /* vdso */
- return false;
+ return 0;
/*
* Explicitly disabled through madvise or prctl, or some
@@ -88,16 +99,16 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags,
* */
if ((vm_flags & VM_NOHUGEPAGE) ||
test_bit(MMF_DISABLE_THP, &vma->vm_mm->flags))
- return false;
+ return 0;
/*
* If the hardware/firmware marked hugepage support disabled.
*/
if (transparent_hugepage_flags & (1 << TRANSPARENT_HUGEPAGE_UNSUPPORTED))
- return false;
+ return 0;
/* khugepaged doesn't collapse DAX vma, but page fault is fine. */
if (vma_is_dax(vma))
- return in_pf;
+ return in_pf ? orders : 0;
/*
* khugepaged special VMA and hugetlb VMA.
@@ -105,17 +116,29 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags,
* VM_MIXEDMAP set.
*/
if (!in_pf && !smaps && (vm_flags & VM_NO_KHUGEPAGED))
- return false;
+ return 0;
/*
- * Check alignment for file vma and size for both file and anon vma.
+ * Check alignment for file vma and size for both file and anon vma by
+ * filtering out the unsuitable orders.
*
* Skip the check for page fault. Huge fault does the check in fault
- * handlers. And this check is not suitable for huge PUD fault.
+ * handlers.
*/
- if (!in_pf &&
- !transhuge_vma_suitable(vma, (vma->vm_end - HPAGE_PMD_SIZE)))
- return false;
+ if (!in_pf) {
+ int order = highest_order(orders);
+ unsigned long addr;
+
+ while (orders) {
+ addr = vma->vm_end - (PAGE_SIZE << order);
+ if (thp_vma_suitable_order(vma, addr, order))
+ break;
+ order = next_order(&orders, order);
+ }
+
+ if (!orders)
+ return 0;
+ }
/*
* Enabled via shmem mount options or sysfs settings.
@@ -124,29 +147,33 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags,
*/
if (!in_pf && shmem_file(vma->vm_file))
return shmem_is_huge(file_inode(vma->vm_file), vma->vm_pgoff,
- !enforce_sysfs, vma->vm_mm, vm_flags);
-
- /* Enforce sysfs THP requirements as necessary */
- if (enforce_sysfs &&
- (!hugepage_flags_enabled() || (!(vm_flags & VM_HUGEPAGE) &&
- !hugepage_flags_always())))
- return false;
+ !enforce_sysfs, vma->vm_mm, vm_flags)
+ ? orders : 0;
if (!vma_is_anonymous(vma)) {
/*
+ * Enforce sysfs THP requirements as necessary. Anonymous vmas
+ * were already handled in thp_vma_allowable_orders().
+ */
+ if (enforce_sysfs &&
+ (!hugepage_global_enabled() || (!(vm_flags & VM_HUGEPAGE) &&
+ !hugepage_global_always())))
+ return 0;
+
+ /*
* Trust that ->huge_fault() handlers know what they are doing
* in fault path.
*/
if (((in_pf || smaps)) && vma->vm_ops->huge_fault)
- return true;
+ return orders;
/* Only regular file is valid in collapse path */
if (((!in_pf || smaps)) && file_thp_enabled(vma))
- return true;
- return false;
+ return orders;
+ return 0;
}
if (vma_is_temporary_stack(vma))
- return false;
+ return 0;
/*
* THPeligible bit of smaps should show 1 for proper VMAs even
@@ -156,9 +183,9 @@ bool hugepage_vma_check(struct vm_area_struct *vma, unsigned long vm_flags,
* the first page fault.
*/
if (!vma->anon_vma)
- return (smaps || in_pf);
+ return (smaps || in_pf) ? orders : 0;
- return true;
+ return orders;
}
static bool get_huge_zero_page(void)
@@ -412,9 +439,136 @@ static const struct attribute_group hugepage_attr_group = {
.attrs = hugepage_attr,
};
+static void hugepage_exit_sysfs(struct kobject *hugepage_kobj);
+static void thpsize_release(struct kobject *kobj);
+static DEFINE_SPINLOCK(huge_anon_orders_lock);
+static LIST_HEAD(thpsize_list);
+
+struct thpsize {
+ struct kobject kobj;
+ struct list_head node;
+ int order;
+};
+
+#define to_thpsize(kobj) container_of(kobj, struct thpsize, kobj)
+
+static ssize_t thpsize_enabled_show(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+{
+ int order = to_thpsize(kobj)->order;
+ const char *output;
+
+ if (test_bit(order, &huge_anon_orders_always))
+ output = "[always] inherit madvise never";
+ else if (test_bit(order, &huge_anon_orders_inherit))
+ output = "always [inherit] madvise never";
+ else if (test_bit(order, &huge_anon_orders_madvise))
+ output = "always inherit [madvise] never";
+ else
+ output = "always inherit madvise [never]";
+
+ 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)
+{
+ int order = to_thpsize(kobj)->order;
+ ssize_t ret = count;
+
+ if (sysfs_streq(buf, "always")) {
+ spin_lock(&huge_anon_orders_lock);
+ clear_bit(order, &huge_anon_orders_inherit);
+ clear_bit(order, &huge_anon_orders_madvise);
+ set_bit(order, &huge_anon_orders_always);
+ spin_unlock(&huge_anon_orders_lock);
+ } else if (sysfs_streq(buf, "inherit")) {
+ spin_lock(&huge_anon_orders_lock);
+ clear_bit(order, &huge_anon_orders_always);
+ clear_bit(order, &huge_anon_orders_madvise);
+ set_bit(order, &huge_anon_orders_inherit);
+ spin_unlock(&huge_anon_orders_lock);
+ } else if (sysfs_streq(buf, "madvise")) {
+ spin_lock(&huge_anon_orders_lock);
+ clear_bit(order, &huge_anon_orders_always);
+ clear_bit(order, &huge_anon_orders_inherit);
+ set_bit(order, &huge_anon_orders_madvise);
+ spin_unlock(&huge_anon_orders_lock);
+ } else if (sysfs_streq(buf, "never")) {
+ spin_lock(&huge_anon_orders_lock);
+ clear_bit(order, &huge_anon_orders_always);
+ clear_bit(order, &huge_anon_orders_inherit);
+ clear_bit(order, &huge_anon_orders_madvise);
+ spin_unlock(&huge_anon_orders_lock);
+ } else
+ ret = -EINVAL;
+
+ return ret;
+}
+
+static struct kobj_attribute thpsize_enabled_attr =
+ __ATTR(enabled, 0644, thpsize_enabled_show, thpsize_enabled_store);
+
+static struct attribute *thpsize_attrs[] = {
+ &thpsize_enabled_attr.attr,
+ NULL,
+};
+
+static const struct attribute_group thpsize_attr_group = {
+ .attrs = thpsize_attrs,
+};
+
+static const struct kobj_type thpsize_ktype = {
+ .release = &thpsize_release,
+ .sysfs_ops = &kobj_sysfs_ops,
+};
+
+static struct thpsize *thpsize_create(int order, struct kobject *parent)
+{
+ unsigned long size = (PAGE_SIZE << order) / SZ_1K;
+ struct thpsize *thpsize;
+ int ret;
+
+ thpsize = kzalloc(sizeof(*thpsize), GFP_KERNEL);
+ if (!thpsize)
+ return ERR_PTR(-ENOMEM);
+
+ ret = kobject_init_and_add(&thpsize->kobj, &thpsize_ktype, parent,
+ "hugepages-%lukB", size);
+ if (ret) {
+ kfree(thpsize);
+ return ERR_PTR(ret);
+ }
+
+ ret = sysfs_create_group(&thpsize->kobj, &thpsize_attr_group);
+ if (ret) {
+ kobject_put(&thpsize->kobj);
+ return ERR_PTR(ret);
+ }
+
+ thpsize->order = order;
+ return thpsize;
+}
+
+static void thpsize_release(struct kobject *kobj)
+{
+ kfree(to_thpsize(kobj));
+}
+
static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj)
{
int err;
+ struct thpsize *thpsize;
+ unsigned long orders;
+ int order;
+
+ /*
+ * Default to setting PMD-sized THP to inherit the global setting and
+ * 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);
*hugepage_kobj = kobject_create_and_add("transparent_hugepage", mm_kobj);
if (unlikely(!*hugepage_kobj)) {
@@ -434,8 +588,24 @@ static int __init hugepage_init_sysfs(struct kobject **hugepage_kobj)
goto remove_hp_group;
}
+ orders = THP_ORDERS_ALL_ANON;
+ order = highest_order(orders);
+ while (orders) {
+ thpsize = thpsize_create(order, *hugepage_kobj);
+ if (IS_ERR(thpsize)) {
+ pr_err("failed to create thpsize for order %d\n", order);
+ err = PTR_ERR(thpsize);
+ goto remove_all;
+ }
+ list_add(&thpsize->node, &thpsize_list);
+ order = next_order(&orders, order);
+ }
+
return 0;
+remove_all:
+ hugepage_exit_sysfs(*hugepage_kobj);
+ return err;
remove_hp_group:
sysfs_remove_group(*hugepage_kobj, &hugepage_attr_group);
delete_obj:
@@ -445,6 +615,13 @@ delete_obj:
static void __init hugepage_exit_sysfs(struct kobject *hugepage_kobj)
{
+ struct thpsize *thpsize, *tmp;
+
+ list_for_each_entry_safe(thpsize, tmp, &thpsize_list, node) {
+ list_del(&thpsize->node);
+ kobject_put(&thpsize->kobj);
+ }
+
sysfs_remove_group(hugepage_kobj, &khugepaged_attr_group);
sysfs_remove_group(hugepage_kobj, &hugepage_attr_group);
kobject_put(hugepage_kobj);
@@ -811,7 +988,7 @@ vm_fault_t do_huge_pmd_anonymous_page(struct vm_fault *vmf)
struct folio *folio;
unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
- if (!transhuge_vma_suitable(vma, haddr))
+ if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER))
return VM_FAULT_FALLBACK;
if (unlikely(anon_vma_prepare(vma)))
return VM_FAULT_OOM;
diff --git a/mm/khugepaged.c b/mm/khugepaged.c
index 064654717843..d72aecd3624a 100644
--- a/mm/khugepaged.c
+++ b/mm/khugepaged.c
@@ -446,7 +446,8 @@ void khugepaged_enter_vma(struct vm_area_struct *vma,
{
if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) &&
hugepage_flags_enabled()) {
- if (hugepage_vma_check(vma, vm_flags, false, false, true))
+ if (thp_vma_allowable_order(vma, vm_flags, false, false, true,
+ PMD_ORDER))
__khugepaged_enter(vma->vm_mm);
}
}
@@ -922,16 +923,16 @@ static int hugepage_vma_revalidate(struct mm_struct *mm, unsigned long address,
if (!vma)
return SCAN_VMA_NULL;
- if (!transhuge_vma_suitable(vma, address))
+ if (!thp_vma_suitable_order(vma, address, PMD_ORDER))
return SCAN_ADDRESS_RANGE;
- if (!hugepage_vma_check(vma, vma->vm_flags, false, false,
- cc->is_khugepaged))
+ if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false,
+ cc->is_khugepaged, PMD_ORDER))
return SCAN_VMA_CHECK;
/*
* Anon VMA expected, the address may be unmapped then
* remapped to file after khugepaged reaquired the mmap_lock.
*
- * hugepage_vma_check may return true for qualified file
+ * thp_vma_allowable_order may return true for qualified file
* vmas.
*/
if (expect_anon && (!(*vmap)->anon_vma || !vma_is_anonymous(*vmap)))
@@ -1503,7 +1504,8 @@ int collapse_pte_mapped_thp(struct mm_struct *mm, unsigned long addr,
* and map it by a PMD, regardless of sysfs THP settings. As such, let's
* analogously elide sysfs THP settings here.
*/
- if (!hugepage_vma_check(vma, vma->vm_flags, false, false, false))
+ if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false, false,
+ PMD_ORDER))
return SCAN_VMA_CHECK;
/* Keep pmd pgtable for uffd-wp; see comment in retract_page_tables() */
@@ -2368,7 +2370,8 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result,
progress++;
break;
}
- if (!hugepage_vma_check(vma, vma->vm_flags, false, false, true)) {
+ if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false,
+ true, PMD_ORDER)) {
skip:
progress++;
continue;
@@ -2705,7 +2708,8 @@ int madvise_collapse(struct vm_area_struct *vma, struct vm_area_struct **prev,
*prev = vma;
- if (!hugepage_vma_check(vma, vma->vm_flags, false, false, false))
+ if (!thp_vma_allowable_order(vma, vma->vm_flags, false, false, false,
+ PMD_ORDER))
return -EINVAL;
cc = kmalloc(sizeof(*cc), GFP_KERNEL);
diff --git a/mm/memory.c b/mm/memory.c
index 99582b188ed2..8ab2d994d997 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -4322,7 +4322,7 @@ vm_fault_t do_set_pmd(struct vm_fault *vmf, struct page *page)
pmd_t entry;
vm_fault_t ret = VM_FAULT_FALLBACK;
- if (!transhuge_vma_suitable(vma, haddr))
+ if (!thp_vma_suitable_order(vma, haddr, PMD_ORDER))
return ret;
page = compound_head(page);
@@ -5116,7 +5116,7 @@ static vm_fault_t __handle_mm_fault(struct vm_area_struct *vma,
return VM_FAULT_OOM;
retry_pud:
if (pud_none(*vmf.pud) &&
- hugepage_vma_check(vma, vm_flags, false, true, true)) {
+ thp_vma_allowable_order(vma, vm_flags, false, true, true, PUD_ORDER)) {
ret = create_huge_pud(&vmf);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
@@ -5150,7 +5150,7 @@ retry_pud:
goto retry_pud;
if (pmd_none(*vmf.pmd) &&
- hugepage_vma_check(vma, vm_flags, false, true, true)) {
+ thp_vma_allowable_order(vma, vm_flags, false, true, true, PMD_ORDER)) {
ret = create_huge_pmd(&vmf);
if (!(ret & VM_FAULT_FALLBACK))
return ret;
diff --git a/mm/page_vma_mapped.c b/mm/page_vma_mapped.c
index e0b368e545ed..74d2de15fb5e 100644
--- a/mm/page_vma_mapped.c
+++ b/mm/page_vma_mapped.c
@@ -268,7 +268,8 @@ restart:
* cleared *pmd but not decremented compound_mapcount().
*/
if ((pvmw->flags & PVMW_SYNC) &&
- transhuge_vma_suitable(vma, pvmw->address) &&
+ thp_vma_suitable_order(vma, pvmw->address,
+ PMD_ORDER) &&
(pvmw->nr_pages >= HPAGE_PMD_NR)) {
spinlock_t *ptl = pmd_lock(mm, pvmw->pmd);