From: Muchun Song <songmuchun@bytedance.com>
To: corbet@lwn.net, mike.kravetz@oracle.com, tglx@linutronix.de,
mingo@redhat.com, bp@alien8.de, x86@kernel.org, hpa@zytor.com,
dave.hansen@linux.intel.com, luto@kernel.org,
peterz@infradead.org, viro@zeniv.linux.org.uk,
akpm@linux-foundation.org, paulmck@kernel.org,
mchehab+huawei@kernel.org, pawan.kumar.gupta@linux.intel.com,
rdunlap@infradead.org, oneukum@suse.com,
anshuman.khandual@arm.com, jroedel@suse.de,
almasrymina@google.com, rientjes@google.com, willy@infradead.org,
osalvador@suse.de, mhocko@suse.com
Cc: duanxiongchun@bytedance.com, linux-doc@vger.kernel.org,
linux-kernel@vger.kernel.org, linux-mm@kvack.org,
linux-fsdevel@vger.kernel.org,
Muchun Song <songmuchun@bytedance.com>
Subject: [PATCH v3 09/21] mm/hugetlb: Free the vmemmap pages associated with each hugetlb page
Date: Sun, 8 Nov 2020 22:11:01 +0800 [thread overview]
Message-ID: <20201108141113.65450-10-songmuchun@bytedance.com> (raw)
In-Reply-To: <20201108141113.65450-1-songmuchun@bytedance.com>
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 ++
include/linux/hugetlb.h | 8 ++
include/linux/mm.h | 4 +
mm/hugetlb.c | 166 ++++++++++++++++++++++++++++++++
mm/sparse-vmemmap.c | 31 ++++++
6 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/include/linux/hugetlb.h b/include/linux/hugetlb.h
index d81c262418db..afb9b18771c4 100644
--- a/include/linux/hugetlb.h
+++ b/include/linux/hugetlb.h
@@ -594,6 +594,14 @@ static inline unsigned int blocks_per_huge_page(struct hstate *h)
#include <asm/hugetlb.h>
#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+#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
+
#ifndef VMEMMAP_HPAGE_SHIFT
#define VMEMMAP_HPAGE_SHIFT HPAGE_SHIFT
#endif
diff --git a/include/linux/mm.h b/include/linux/mm.h
index ce429614d1ab..480faca94c23 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -3025,6 +3025,10 @@ static inline void print_vma_addr(char *prefix, unsigned long rip)
}
#endif
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+pmd_t *vmemmap_to_pmd(const void *page);
+#endif
+
void *sparse_buffer_alloc(unsigned long size);
struct page * __populate_section_memmap(unsigned long pfn,
unsigned long nr_pages, int nid, struct vmem_altmap *altmap);
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 5c7be2ee7e15..27f0269aab70 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1293,6 +1293,8 @@ static inline void destroy_compound_gigantic_page(struct page *page,
#endif
#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+#include <linux/bootmem_info.h>
+
/*
* There are 512 struct page structs(8 pages) associated with each 2MB
* hugetlb page. For tail pages, the value of compound_dtor is the same.
@@ -1305,6 +1307,13 @@ static inline void destroy_compound_gigantic_page(struct page *page,
#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); \
+})
+
static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
{
return h->nr_free_vmemmap_pages;
@@ -1424,6 +1433,147 @@ static void __init hugetlb_vmemmap_init(struct hstate *h)
pr_debug("HugeTLB: can free %d vmemmap pages for %s\n",
h->nr_free_vmemmap_pages, h->name);
}
+
+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 int nr_free,
+ 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;
+ unsigned long end = start + (nr_free << PAGE_SHIFT);
+
+ 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_NR * PAGE_SIZE;
+ unsigned long end = addr + vmemmap_pages_size_per_hpage(h);
+ struct page *reuse = NULL;
+
+ addr = start;
+ do {
+ unsigned int nr_pages;
+ pte_t *ptep;
+
+ ptep = pte_offset_kernel(pmd, addr);
+ if (!reuse)
+ reuse = pte_page(ptep[-1]);
+
+ next = vmemmap_hpage_addr_end(addr, end);
+ nr_pages = (next - addr) >> PAGE_SHIFT;
+ __free_huge_page_pte_vmemmap(reuse, ptep, addr, nr_pages,
+ 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 hstate *h, struct page *head,
+ pmd_t *pmd)
+{
+ pgtable_t pgtable;
+ unsigned long start = (unsigned long)head & VMEMMAP_HPAGE_MASK;
+ unsigned long addr = start;
+ unsigned int nr = pgtable_pages_to_prealloc_per_hpage(h);
+
+ while (nr-- && (pgtable = vmemmap_pgtable_withdraw(head))) {
+ VM_BUG_ON(freed_vmemmap_hpage(pgtable));
+ split_vmemmap_pmd(pmd++, page_to_virt(pgtable), addr);
+ addr += VMEMMAP_HPAGE_SIZE;
+ }
+
+ flush_tlb_kernel_range(start, addr);
+}
+
+static 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(head);
+ ptl = vmemmap_pmd_lock(pmd);
+ if (vmemmap_pmd_huge(pmd)) {
+ VM_BUG_ON(!pgtable_pages_to_prealloc_per_hpage(h));
+ split_vmemmap_huge_page(h, 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);
+}
#else
static inline void hugetlb_vmemmap_init(struct hstate *h)
{
@@ -1437,6 +1587,10 @@ static inline int vmemmap_pgtable_prealloc(struct hstate *h, struct page *page)
static inline void vmemmap_pgtable_free(struct hstate *h, struct page *page)
{
}
+
+static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+}
#endif
static void update_and_free_page(struct hstate *h, struct page *page)
@@ -1645,6 +1799,10 @@ 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);
+ /* Must be called before the initialization of @page->lru */
+ vmemmap_pgtable_free(h, page);
+
INIT_LIST_HEAD(&page->lru);
set_compound_page_dtor(page, HUGETLB_PAGE_DTOR);
set_hugetlb_cgroup(page, NULL);
@@ -1897,6 +2055,14 @@ 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/sparse-vmemmap.c b/mm/sparse-vmemmap.c
index 16183d85a7d5..4b35d1655a2f 100644
--- a/mm/sparse-vmemmap.c
+++ b/mm/sparse-vmemmap.c
@@ -263,3 +263,34 @@ struct page * __meminit __populate_section_memmap(unsigned long pfn,
return pfn_to_page(pfn);
}
+
+#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
+/*
+ * Walk a vmemmap address to the pmd it maps.
+ */
+pmd_t *vmemmap_to_pmd(const void *page)
+{
+ unsigned long addr = (unsigned long)page;
+ pgd_t *pgd;
+ p4d_t *p4d;
+ pud_t *pud;
+ pmd_t *pmd;
+
+ if (addr < VMEMMAP_START || addr >= VMEMMAP_END)
+ return NULL;
+
+ pgd = pgd_offset_k(addr);
+ if (pgd_none(*pgd))
+ return NULL;
+ p4d = p4d_offset(pgd, addr);
+ if (p4d_none(*p4d))
+ return NULL;
+ pud = pud_offset(p4d, addr);
+
+ if (pud_none(*pud) || pud_bad(*pud))
+ return NULL;
+ pmd = pmd_offset(pud, addr);
+
+ return pmd;
+}
+#endif
--
2.11.0
next prev parent reply other threads:[~2020-11-08 14:13 UTC|newest]
Thread overview: 54+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-08 14:10 [PATCH v3 00/21] Free some vmemmap pages of hugetlb page Muchun Song
2020-11-08 14:10 ` [PATCH v3 01/21] mm/memory_hotplug: Move bootmem info registration API to bootmem_info.c Muchun Song
2020-11-08 14:10 ` [PATCH v3 02/21] mm/memory_hotplug: Move {get,put}_page_bootmem() " Muchun Song
2020-11-08 14:10 ` [PATCH v3 03/21] mm/hugetlb: Introduce a new config HUGETLB_PAGE_FREE_VMEMMAP Muchun Song
2020-11-09 13:52 ` Oscar Salvador
2020-11-09 14:20 ` [External] " Muchun Song
2020-11-10 19:31 ` Mike Kravetz
2020-11-10 19:50 ` Matthew Wilcox
2020-11-10 20:30 ` Mike Kravetz
2020-11-17 15:35 ` [External] " Muchun Song
2020-11-11 3:28 ` Muchun Song
2020-11-08 14:10 ` [PATCH v3 04/21] mm/hugetlb: Introduce nr_free_vmemmap_pages in the struct hstate Muchun Song
2020-11-09 16:48 ` Oscar Salvador
2020-11-10 2:42 ` [External] " Muchun Song
2020-11-10 19:38 ` Mike Kravetz
2020-11-11 3:22 ` Muchun Song
2020-11-08 14:10 ` [PATCH v3 05/21] mm/hugetlb: Introduce pgtable allocation/freeing helpers Muchun Song
2020-11-09 17:21 ` Oscar Salvador
2020-11-10 3:49 ` [External] " Muchun Song
2020-11-10 5:42 ` Oscar Salvador
2020-11-10 6:08 ` Muchun Song
2020-11-10 6:33 ` Oscar Salvador
2020-11-10 7:10 ` Muchun Song
2020-11-11 0:47 ` Mike Kravetz
2020-11-11 3:41 ` [External] " Muchun Song
2020-11-13 0:35 ` Mike Kravetz
2020-11-13 1:02 ` Mike Kravetz
2020-11-13 4:18 ` Muchun Song
2020-11-08 14:10 ` [PATCH v3 06/21] mm/bootmem_info: Introduce {free,prepare}_vmemmap_page() Muchun Song
2020-11-08 14:10 ` [PATCH v3 07/21] mm/bootmem_info: Combine bootmem info and type into page->freelist Muchun Song
2020-11-08 14:11 ` [PATCH v3 08/21] mm/vmemmap: Initialize page table lock for vmemmap Muchun Song
2020-11-09 18:11 ` Oscar Salvador
2020-11-10 5:17 ` [External] " Muchun Song
2020-11-08 14:11 ` Muchun Song [this message]
2020-11-09 18:51 ` [PATCH v3 09/21] mm/hugetlb: Free the vmemmap pages associated with each hugetlb page Oscar Salvador
2020-11-10 6:40 ` [External] " Muchun Song
2020-11-10 9:48 ` Oscar Salvador
2020-11-10 10:47 ` Muchun Song
2020-11-10 13:52 ` Oscar Salvador
2020-11-10 14:00 ` Muchun Song
2020-11-08 14:11 ` [PATCH v3 10/21] mm/hugetlb: Defer freeing of hugetlb pages Muchun Song
2020-11-08 14:11 ` [PATCH v3 11/21] mm/hugetlb: Allocate the vmemmap pages associated with each hugetlb page Muchun Song
2020-11-08 14:11 ` [PATCH v3 12/21] mm/hugetlb: Introduce remap_huge_page_pmd_vmemmap helper Muchun Song
2020-11-08 14:11 ` [PATCH v3 13/21] mm/hugetlb: Use PG_slab to indicate split pmd Muchun Song
2020-11-08 14:11 ` [PATCH v3 14/21] mm/hugetlb: Support freeing vmemmap pages of gigantic page Muchun Song
2020-11-08 14:11 ` [PATCH v3 15/21] mm/hugetlb: Add a BUILD_BUG_ON to check if struct page size is a power of two Muchun Song
2020-11-08 14:11 ` [PATCH v3 16/21] mm/hugetlb: Set the PageHWPoison to the raw error page Muchun Song
2020-11-08 14:11 ` [PATCH v3 17/21] mm/hugetlb: Flush work when dissolving hugetlb page Muchun Song
2020-11-08 14:11 ` [PATCH v3 18/21] mm/hugetlb: Add a kernel parameter hugetlb_free_vmemmap Muchun Song
2020-11-08 14:11 ` [PATCH v3 19/21] mm/hugetlb: Merge pte to huge pmd only for gigantic page Muchun Song
2020-11-08 14:11 ` [PATCH v3 20/21] mm/hugetlb: Gather discrete indexes of tail page Muchun Song
2020-11-08 14:11 ` [PATCH v3 21/21] mm/hugetlb: Add BUILD_BUG_ON to catch invalid usage of tail struct page Muchun Song
2020-11-10 19:23 ` [PATCH v3 00/21] Free some vmemmap pages of hugetlb page Mike Kravetz
2020-11-11 3:21 ` [External] " Muchun Song
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20201108141113.65450-10-songmuchun@bytedance.com \
--to=songmuchun@bytedance.com \
--cc=akpm@linux-foundation.org \
--cc=almasrymina@google.com \
--cc=anshuman.khandual@arm.com \
--cc=bp@alien8.de \
--cc=corbet@lwn.net \
--cc=dave.hansen@linux.intel.com \
--cc=duanxiongchun@bytedance.com \
--cc=hpa@zytor.com \
--cc=jroedel@suse.de \
--cc=linux-doc@vger.kernel.org \
--cc=linux-fsdevel@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=luto@kernel.org \
--cc=mchehab+huawei@kernel.org \
--cc=mhocko@suse.com \
--cc=mike.kravetz@oracle.com \
--cc=mingo@redhat.com \
--cc=oneukum@suse.com \
--cc=osalvador@suse.de \
--cc=paulmck@kernel.org \
--cc=pawan.kumar.gupta@linux.intel.com \
--cc=peterz@infradead.org \
--cc=rdunlap@infradead.org \
--cc=rientjes@google.com \
--cc=tglx@linutronix.de \
--cc=viro@zeniv.linux.org.uk \
--cc=willy@infradead.org \
--cc=x86@kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).