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 11/21] mm/hugetlb: Allocate the vmemmap pages associated with each hugetlb page
Date: Sun, 8 Nov 2020 22:11:03 +0800 [thread overview]
Message-ID: <20201108141113.65450-12-songmuchun@bytedance.com> (raw)
In-Reply-To: <20201108141113.65450-1-songmuchun@bytedance.com>
When we free a hugetlb page to the buddy, we should allocate the vmemmap
pages associated with it. We can do that in the __free_hugepage().
Signed-off-by: Muchun Song <songmuchun@bytedance.com>
---
mm/hugetlb.c | 110 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++-
1 file changed, 109 insertions(+), 1 deletion(-)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index ded7f0fbde35..8295911fe76e 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1307,6 +1307,8 @@ static void __free_hugepage(struct hstate *h, struct page *page);
* reserve at least 2 pages as vmemmap areas.
*/
#define RESERVE_VMEMMAP_NR 2U
+#define RESERVE_VMEMMAP_SIZE (RESERVE_VMEMMAP_NR << PAGE_SHIFT)
+#define GFP_VMEMMAP_PAGE (GFP_KERNEL | __GFP_NOFAIL | __GFP_MEMALLOC)
#define page_huge_pte(page) ((page)->pmd_huge_pte)
@@ -1490,7 +1492,7 @@ static void __free_huge_page_pmd_vmemmap(struct hstate *h, pmd_t *pmd,
struct list_head *free_pages)
{
unsigned long next;
- unsigned long start = addr + RESERVE_VMEMMAP_NR * PAGE_SIZE;
+ unsigned long start = addr + RESERVE_VMEMMAP_SIZE;
unsigned long end = addr + vmemmap_pages_size_per_hpage(h);
struct page *reuse = NULL;
@@ -1578,6 +1580,106 @@ static void free_huge_page_vmemmap(struct hstate *h, struct page *head)
free_vmemmap_page_list(&free_pages);
}
+static void __remap_huge_page_pte_vmemmap(struct page *reuse, pte_t *ptep,
+ unsigned long start,
+ unsigned int nr_remap,
+ struct list_head *remap_pages)
+{
+ pgprot_t pgprot = PAGE_KERNEL;
+ void *from = (void *)page_private(reuse);
+ unsigned long addr, end = start + (nr_remap << PAGE_SHIFT);
+
+ for (addr = start; addr < end; addr += PAGE_SIZE) {
+ void *to;
+ struct page *page;
+ pte_t entry, old = *ptep;
+
+ page = list_first_entry_or_null(remap_pages, struct page, lru);
+ list_del(&page->lru);
+ to = page_to_virt(page);
+ copy_page(to, from);
+
+ /*
+ * Make sure that any data that writes to the @to is made
+ * visible to the physical page.
+ */
+ flush_kernel_vmap_range(to, PAGE_SIZE);
+
+ prepare_vmemmap_page(page);
+
+ entry = mk_pte(page, pgprot);
+ set_pte_at(&init_mm, addr, ptep++, entry);
+
+ VM_BUG_ON(!pte_present(old) || pte_page(old) != reuse);
+ }
+}
+
+static void __remap_huge_page_pmd_vmemmap(struct hstate *h, pmd_t *pmd,
+ unsigned long addr,
+ struct list_head *remap_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]);
+ set_page_private(reuse, addr - PAGE_SIZE);
+ }
+
+ next = vmemmap_hpage_addr_end(addr, end);
+ nr_pages = (next - addr) >> PAGE_SHIFT;
+ __remap_huge_page_pte_vmemmap(reuse, ptep, addr, nr_pages,
+ remap_pages);
+ } while (pmd++, addr = next, addr != end);
+
+ flush_tlb_kernel_range(start, end);
+}
+
+static inline void alloc_vmemmap_pages(struct hstate *h, struct list_head *list)
+{
+ int i;
+
+ for (i = 0; i < free_vmemmap_pages_per_hpage(h); i++) {
+ struct page *page;
+
+ /* This should not fail */
+ page = alloc_page(GFP_VMEMMAP_PAGE);
+ list_add_tail(&page->lru, list);
+ }
+}
+
+static void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+ pmd_t *pmd;
+ spinlock_t *ptl;
+ LIST_HEAD(remap_pages);
+
+ if (!free_vmemmap_pages_per_hpage(h))
+ return;
+
+ alloc_vmemmap_pages(h, &remap_pages);
+
+ pmd = vmemmap_to_pmd(head);
+ ptl = vmemmap_pmd_lock(pmd);
+ __remap_huge_page_pmd_vmemmap(h, pmd, (unsigned long)head,
+ &remap_pages);
+ if (!freed_vmemmap_hpage_dec(pmd_page(*pmd))) {
+ /*
+ * Todo:
+ * Merge pte to huge pmd if it has ever been split.
+ */
+ }
+ spin_unlock(ptl);
+}
+
/*
* As update_and_free_page() is be called from a non-task context(and hold
* hugetlb_lock), we can defer the actual freeing in a workqueue to prevent
@@ -1653,6 +1755,10 @@ static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
{
}
+static inline void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+}
+
static inline void __update_and_free_page(struct hstate *h, struct page *page)
{
__free_hugepage(h, page);
@@ -1685,6 +1791,8 @@ static void __free_hugepage(struct hstate *h, struct page *page)
{
int i;
+ alloc_huge_page_vmemmap(h, page);
+
for (i = 0; i < pages_per_huge_page(h); i++) {
page[i].flags &= ~(1 << PG_locked | 1 << PG_error |
1 << PG_referenced | 1 << PG_dirty |
--
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 ` [PATCH v3 09/21] mm/hugetlb: Free the vmemmap pages associated with each hugetlb page Muchun Song
2020-11-09 18:51 ` 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 ` Muchun Song [this message]
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=20201108141113.65450-12-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).