lkml.org 
[lkml]   [2020]   [Nov]   [13]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
Patch in this message
/
From
Subject[PATCH v4 09/21] mm/hugetlb: Free the vmemmap pages associated with each hugetlb page
Date
When we allocate a hugetlb page from the buddy, we should free the
unused vmemmap pages associated with it. We can do that in the
prep_new_huge_page().

Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
arch/x86/include/asm/hugetlb.h | 9 ++
arch/x86/include/asm/pgtable_64_types.h | 8 ++
mm/hugetlb.c | 16 +++
mm/hugetlb_vmemmap.c | 188 ++++++++++++++++++++++++++++++++
mm/hugetlb_vmemmap.h | 5 +
5 files changed, 226 insertions(+)

diff --git a/arch/x86/include/asm/hugetlb.h b/arch/x86/include/asm/hugetlb.h
index 1721b1aadeb1..c601fe042832 100644
--- a/arch/x86/include/asm/hugetlb.h
+++ b/arch/x86/include/asm/hugetlb.h
@@ -4,6 +4,15 @@

#include <asm/page.h>
#include <asm-generic/hugetlb.h>
+#include <asm/pgtable.h>
+
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+#define vmemmap_pmd_huge vmemmap_pmd_huge
+static inline bool vmemmap_pmd_huge(pmd_t *pmd)
+{
+ return pmd_large(*pmd);
+}
+#endif

#define hugepages_supported() boot_cpu_has(X86_FEATURE_PSE)

diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
index 52e5f5f2240d..bedbd2e7d06c 100644
--- a/arch/x86/include/asm/pgtable_64_types.h
+++ b/arch/x86/include/asm/pgtable_64_types.h
@@ -139,6 +139,14 @@ extern unsigned int ptrs_per_p4d;
# define VMEMMAP_START __VMEMMAP_BASE_L4
#endif /* CONFIG_DYNAMIC_MEMORY_LAYOUT */

+/*
+ * VMEMMAP_SIZE - allows the whole linear region to be covered by
+ * a struct page array.
+ */
+#define VMEMMAP_SIZE (1UL << (__VIRTUAL_MASK_SHIFT - PAGE_SHIFT - \
+ 1 + ilog2(sizeof(struct page))))
+#define VMEMMAP_END (VMEMMAP_START + VMEMMAP_SIZE)
+
#define VMALLOC_END (VMALLOC_START + (VMALLOC_SIZE_TB << 40) - 1)

#define MODULES_VADDR (__START_KERNEL_map + KERNEL_IMAGE_SIZE)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index f88032c24667..a0ce6f33a717 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1499,6 +1499,14 @@ void free_huge_page(struct page *page)

static void prep_new_huge_page(struct hstate *h, struct page *page, int nid)
{
+ free_huge_page_vmemmap(h, page);
+ /*
+ * Because we store preallocated pages on @page->lru,
+ * vmemmap_pgtable_free() must be called before the
+ * initialization of @page->lru in INIT_LIST_HEAD().
+ */
+ vmemmap_pgtable_free(page);
+
INIT_LIST_HEAD(&page->lru);
set_compound_page_dtor(page, HUGETLB_PAGE_DTOR);
set_hugetlb_cgroup(page, NULL);
@@ -1751,6 +1759,14 @@ static struct page *alloc_fresh_huge_page(struct hstate *h,
if (!page)
return NULL;

+ if (vmemmap_pgtable_prealloc(h, page)) {
+ if (hstate_is_gigantic(h))
+ free_gigantic_page(page, huge_page_order(h));
+ else
+ put_page(page);
+ return NULL;
+ }
+
if (hstate_is_gigantic(h))
prep_compound_gigantic_page(page, huge_page_order(h));
prep_new_huge_page(h, page, page_to_nid(page));
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 332c131c01a8..937562a15f1e 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -74,6 +74,7 @@
#include <linux/pagewalk.h>
#include <linux/mmzone.h>
#include <linux/list.h>
+#include <linux/bootmem_info.h>
#include <asm/pgalloc.h>
#include "hugetlb_vmemmap.h"

@@ -86,6 +87,8 @@
* reserve at least 2 pages as vmemmap areas.
*/
#define RESERVE_VMEMMAP_NR 2U
+#define RESERVE_VMEMMAP_SIZE (RESERVE_VMEMMAP_NR << PAGE_SHIFT)
+#define TAIL_PAGE_REUSE -1

#ifndef VMEMMAP_HPAGE_SHIFT
#define VMEMMAP_HPAGE_SHIFT HPAGE_SHIFT
@@ -97,6 +100,21 @@

#define page_huge_pte(page) ((page)->pmd_huge_pte)

+#define vmemmap_hpage_addr_end(addr, end) \
+({ \
+ unsigned long __boundary; \
+ __boundary = ((addr) + VMEMMAP_HPAGE_SIZE) & VMEMMAP_HPAGE_MASK; \
+ (__boundary - 1 < (end) - 1) ? __boundary : (end); \
+})
+
+#ifndef vmemmap_pmd_huge
+#define vmemmap_pmd_huge vmemmap_pmd_huge
+static inline bool vmemmap_pmd_huge(pmd_t *pmd)
+{
+ return pmd_huge(*pmd);
+}
+#endif
+
static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
{
return h->nr_free_vmemmap_pages;
@@ -158,6 +176,176 @@ int vmemmap_pgtable_prealloc(struct hstate *h, struct page *page)
return -ENOMEM;
}

+/*
+ * Walk a vmemmap address to the pmd it maps.
+ */
+static pmd_t *vmemmap_to_pmd(unsigned long page)
+{
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+
+ if (page < VMEMMAP_START || page >= VMEMMAP_END)
+ return NULL;
+
+ pgd = pgd_offset_k(page);
+ if (pgd_none(*pgd))
+ return NULL;
+ p4d = p4d_offset(pgd, page);
+ if (p4d_none(*p4d))
+ return NULL;
+ pud = pud_offset(p4d, page);
+
+ if (pud_none(*pud) || pud_bad(*pud))
+ return NULL;
+ pmd = pmd_offset(pud, page);
+
+ return pmd;
+}
+
+static inline spinlock_t *vmemmap_pmd_lock(pmd_t *pmd)
+{
+ return pmd_lock(&init_mm, pmd);
+}
+
+static inline int freed_vmemmap_hpage(struct page *page)
+{
+ return atomic_read(&page->_mapcount) + 1;
+}
+
+static inline int freed_vmemmap_hpage_inc(struct page *page)
+{
+ return atomic_inc_return_relaxed(&page->_mapcount) + 1;
+}
+
+static inline int freed_vmemmap_hpage_dec(struct page *page)
+{
+ return atomic_dec_return_relaxed(&page->_mapcount) + 1;
+}
+
+static inline void free_vmemmap_page_list(struct list_head *list)
+{
+ struct page *page, *next;
+
+ list_for_each_entry_safe(page, next, list, lru) {
+ list_del(&page->lru);
+ free_vmemmap_page(page);
+ }
+}
+
+static void __free_huge_page_pte_vmemmap(struct page *reuse, pte_t *ptep,
+ unsigned long start,
+ unsigned long end,
+ struct list_head *free_pages)
+{
+ /* Make the tail pages are mapped read-only. */
+ pgprot_t pgprot = PAGE_KERNEL_RO;
+ pte_t entry = mk_pte(reuse, pgprot);
+ unsigned long addr;
+
+ for (addr = start; addr < end; addr += PAGE_SIZE, ptep++) {
+ struct page *page;
+ pte_t old = *ptep;
+
+ VM_WARN_ON(!pte_present(old));
+ page = pte_page(old);
+ list_add(&page->lru, free_pages);
+
+ set_pte_at(&init_mm, addr, ptep, entry);
+ }
+}
+
+static void __free_huge_page_pmd_vmemmap(struct hstate *h, pmd_t *pmd,
+ unsigned long addr,
+ struct list_head *free_pages)
+{
+ unsigned long next;
+ unsigned long start = addr + RESERVE_VMEMMAP_SIZE;
+ unsigned long end = addr + vmemmap_pages_size_per_hpage(h);
+ struct page *reuse = NULL;
+
+ addr = start;
+ do {
+ pte_t *ptep;
+
+ ptep = pte_offset_kernel(pmd, addr);
+ if (!reuse)
+ reuse = pte_page(ptep[TAIL_PAGE_REUSE]);
+
+ next = vmemmap_hpage_addr_end(addr, end);
+ __free_huge_page_pte_vmemmap(reuse, ptep, addr, next,
+ free_pages);
+ } while (pmd++, addr = next, addr != end);
+
+ flush_tlb_kernel_range(start, end);
+}
+
+static void split_vmemmap_pmd(pmd_t *pmd, pte_t *pte_p, unsigned long addr)
+{
+ int i;
+ pgprot_t pgprot = PAGE_KERNEL;
+ struct mm_struct *mm = &init_mm;
+ struct page *page;
+ pmd_t old_pmd, _pmd;
+
+ old_pmd = READ_ONCE(*pmd);
+ page = pmd_page(old_pmd);
+ pmd_populate_kernel(mm, &_pmd, pte_p);
+
+ for (i = 0; i < VMEMMAP_HPAGE_NR; i++, addr += PAGE_SIZE) {
+ pte_t entry, *pte;
+
+ entry = mk_pte(page + i, pgprot);
+ pte = pte_offset_kernel(&_pmd, addr);
+ VM_BUG_ON(!pte_none(*pte));
+ set_pte_at(mm, addr, pte, entry);
+ }
+
+ /* make pte visible before pmd */
+ smp_wmb();
+ pmd_populate_kernel(mm, pmd, pte_p);
+}
+
+static void split_vmemmap_huge_page(struct page *head, pmd_t *pmd)
+{
+ struct page *pte_page, *t_page;
+ unsigned long start = (unsigned long)head & VMEMMAP_HPAGE_MASK;
+ unsigned long addr = start;
+
+ list_for_each_entry_safe(pte_page, t_page, &head->lru, lru) {
+ list_del(&pte_page->lru);
+ VM_BUG_ON(freed_vmemmap_hpage(pte_page));
+ split_vmemmap_pmd(pmd++, page_to_virt(pte_page), addr);
+ addr += VMEMMAP_HPAGE_SIZE;
+ }
+
+ flush_tlb_kernel_range(start, addr);
+}
+
+void free_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+ pmd_t *pmd;
+ spinlock_t *ptl;
+ LIST_HEAD(free_pages);
+
+ if (!free_vmemmap_pages_per_hpage(h))
+ return;
+
+ pmd = vmemmap_to_pmd((unsigned long)head);
+ BUG_ON(!pmd);
+
+ ptl = vmemmap_pmd_lock(pmd);
+ if (vmemmap_pmd_huge(pmd))
+ split_vmemmap_huge_page(head, pmd);
+
+ __free_huge_page_pmd_vmemmap(h, pmd, (unsigned long)head, &free_pages);
+ freed_vmemmap_hpage_inc(pmd_page(*pmd));
+ spin_unlock(ptl);
+
+ free_vmemmap_page_list(&free_pages);
+}
+
void __init hugetlb_vmemmap_init(struct hstate *h)
{
unsigned int order = huge_page_order(h);
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index 2a72d2f62411..fb8b77659ed5 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -15,6 +15,7 @@
void __init hugetlb_vmemmap_init(struct hstate *h);
int vmemmap_pgtable_prealloc(struct hstate *h, struct page *page);
void vmemmap_pgtable_free(struct page *page);
+void free_huge_page_vmemmap(struct hstate *h, struct page *head);
#else
static inline void hugetlb_vmemmap_init(struct hstate *h)
{
@@ -28,5 +29,9 @@ static inline int vmemmap_pgtable_prealloc(struct hstate *h, struct page *page)
static inline void vmemmap_pgtable_free(struct page *page)
{
}
+
+static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+}
#endif /* CONFIG_HUGETLB_PAGE_FREE_VMEMMAP */
#endif /* _LINUX_HUGETLB_VMEMMAP_H */
--
2.11.0
\
 
 \ /
  Last update: 2020-11-13 12:19    [W:0.240 / U:0.340 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site