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, song.bao.hua@hisilicon.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 v7 10/15] mm/hugetlb: Allocate the vmemmap pages associated with each hugetlb page
Date: Mon, 30 Nov 2020 23:18:33 +0800 [thread overview]
Message-ID: <20201130151838.11208-11-songmuchun@bytedance.com> (raw)
In-Reply-To: <20201130151838.11208-1-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 | 2 ++
mm/hugetlb_vmemmap.c | 90 +++++++++++++++++++++++++++++++++++++++++++++++++---
mm/hugetlb_vmemmap.h | 5 +++
3 files changed, 92 insertions(+), 5 deletions(-)
diff --git a/mm/hugetlb.c b/mm/hugetlb.c
index 5131ae3d2245..ebe35532d432 100644
--- a/mm/hugetlb.c
+++ b/mm/hugetlb.c
@@ -1381,6 +1381,8 @@ 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 |
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index af42fad1f131..a3714db7f400 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -95,6 +95,7 @@
#define pr_fmt(fmt) "HugeTLB vmemmap: " fmt
#include <linux/bootmem_info.h>
+#include <linux/delay.h>
#include "hugetlb_vmemmap.h"
/*
@@ -108,6 +109,8 @@
#define RESERVE_VMEMMAP_NR 2U
#define RESERVE_VMEMMAP_SIZE (RESERVE_VMEMMAP_NR << PAGE_SHIFT)
#define VMEMMAP_TAIL_PAGE_REUSE -1
+#define GFP_VMEMMAP_PAGE \
+ (GFP_KERNEL | __GFP_RETRY_MAYFAIL | __GFP_HIGH)
#ifndef VMEMMAP_HPAGE_SHIFT
#define VMEMMAP_HPAGE_SHIFT HPAGE_SHIFT
@@ -124,6 +127,11 @@
(__boundary - 1 < (end) - 1) ? __boundary : (end); \
})
+typedef void (*vmemmap_remap_pte_func_t)(struct page *reuse, pte_t *pte,
+ unsigned long start, unsigned long end,
+ void *priv);
+
+
static inline unsigned int vmemmap_pages_per_hpage(struct hstate *h)
{
return free_vmemmap_pages_per_hpage(h) + RESERVE_VMEMMAP_NR;
@@ -163,9 +171,40 @@ static pmd_t *vmemmap_to_pmd(unsigned long addr)
return pmd;
}
+static void vmemmap_restore_pte_range(struct page *reuse, pte_t *pte,
+ unsigned long start, unsigned long end,
+ void *priv)
+{
+ pgprot_t pgprot = PAGE_KERNEL;
+ void *from = page_to_virt(reuse);
+ unsigned long addr;
+ struct list_head *pages = priv;
+
+ for (addr = start; addr < end; addr += PAGE_SIZE) {
+ void *to;
+ struct page *page;
+
+ VM_BUG_ON(pte_none(*pte) || pte_page(*pte) != reuse);
+
+ page = list_first_entry(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);
+ set_pte_at(&init_mm, addr, pte++, mk_pte(page, pgprot));
+ }
+}
+
static void vmemmap_reuse_pte_range(struct page *reuse, pte_t *pte,
unsigned long start, unsigned long end,
- struct list_head *vmemmap_pages)
+ void *priv)
{
/*
* Make the tail pages are mapped with read-only to catch
@@ -174,6 +213,7 @@ static void vmemmap_reuse_pte_range(struct page *reuse, pte_t *pte,
pgprot_t pgprot = PAGE_KERNEL_RO;
pte_t entry = mk_pte(reuse, pgprot);
unsigned long addr;
+ struct list_head *pages = priv;
for (addr = start; addr < end; addr += PAGE_SIZE, pte++) {
struct page *page;
@@ -181,14 +221,14 @@ static void vmemmap_reuse_pte_range(struct page *reuse, pte_t *pte,
VM_BUG_ON(pte_none(*pte));
page = pte_page(*pte);
- list_add(&page->lru, vmemmap_pages);
+ list_add(&page->lru, pages);
set_pte_at(&init_mm, addr, pte, entry);
}
}
static void vmemmap_remap_range(unsigned long start, unsigned long end,
- struct list_head *vmemmap_pages)
+ vmemmap_remap_pte_func_t func, void *priv)
{
pmd_t *pmd;
unsigned long next, addr = start;
@@ -208,12 +248,52 @@ static void vmemmap_remap_range(unsigned long start, unsigned long end,
reuse = pte_page(pte[VMEMMAP_TAIL_PAGE_REUSE]);
next = vmemmap_hpage_addr_end(addr, end);
- vmemmap_reuse_pte_range(reuse, pte, addr, next, vmemmap_pages);
+ func(reuse, pte, addr, next, priv);
} 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)
+{
+ unsigned int nr = free_vmemmap_pages_per_hpage(h);
+
+ while (nr--) {
+ struct page *page;
+
+retry:
+ page = alloc_page(GFP_VMEMMAP_PAGE);
+ if (unlikely(!page)) {
+ msleep(100);
+ /*
+ * We should retry infinitely, because we cannot
+ * handle allocation failures. Once we allocate
+ * vmemmap pages successfully, then we can free
+ * a HugeTLB page.
+ */
+ goto retry;
+ }
+ list_add_tail(&page->lru, list);
+ }
+}
+
+void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+ unsigned long start, end;
+ unsigned long vmemmap_addr = (unsigned long)head;
+ LIST_HEAD(vmemmap_pages);
+
+ if (!free_vmemmap_pages_per_hpage(h))
+ return;
+
+ alloc_vmemmap_pages(h, &vmemmap_pages);
+
+ start = vmemmap_addr + RESERVE_VMEMMAP_SIZE;
+ end = vmemmap_addr + vmemmap_pages_size_per_hpage(h);
+ vmemmap_remap_range(start, end, vmemmap_restore_pte_range,
+ &vmemmap_pages);
+}
+
static inline void free_vmemmap_page_list(struct list_head *list)
{
struct page *page, *next;
@@ -235,7 +315,7 @@ void free_huge_page_vmemmap(struct hstate *h, struct page *head)
start = vmemmap_addr + RESERVE_VMEMMAP_SIZE;
end = vmemmap_addr + vmemmap_pages_size_per_hpage(h);
- vmemmap_remap_range(start, end, &vmemmap_pages);
+ vmemmap_remap_range(start, end, vmemmap_reuse_pte_range, &vmemmap_pages);
free_vmemmap_page_list(&vmemmap_pages);
}
diff --git a/mm/hugetlb_vmemmap.h b/mm/hugetlb_vmemmap.h
index 293897b9f1d8..7887095488f4 100644
--- a/mm/hugetlb_vmemmap.h
+++ b/mm/hugetlb_vmemmap.h
@@ -12,6 +12,7 @@
#ifdef CONFIG_HUGETLB_PAGE_FREE_VMEMMAP
void __init hugetlb_vmemmap_init(struct hstate *h);
+void alloc_huge_page_vmemmap(struct hstate *h, struct page *head);
void free_huge_page_vmemmap(struct hstate *h, struct page *head);
static inline unsigned int free_vmemmap_pages_per_hpage(struct hstate *h)
@@ -23,6 +24,10 @@ static inline void hugetlb_vmemmap_init(struct hstate *h)
{
}
+static inline void alloc_huge_page_vmemmap(struct hstate *h, struct page *head)
+{
+}
+
static inline void free_huge_page_vmemmap(struct hstate *h, struct page *head)
{
}
--
2.11.0
next prev parent reply other threads:[~2020-11-30 15:22 UTC|newest]
Thread overview: 49+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-11-30 15:18 [PATCH v7 00/15] Free some vmemmap pages of hugetlb page Muchun Song
2020-11-30 15:18 ` [PATCH v7 01/15] mm/memory_hotplug: Move bootmem info registration API to bootmem_info.c Muchun Song
2020-12-07 12:12 ` David Hildenbrand
2020-11-30 15:18 ` [PATCH v7 02/15] mm/memory_hotplug: Move {get,put}_page_bootmem() " Muchun Song
2020-12-07 12:14 ` David Hildenbrand
2020-12-07 12:16 ` [External] " Muchun Song
2020-11-30 15:18 ` [PATCH v7 03/15] mm/hugetlb: Introduce a new config HUGETLB_PAGE_FREE_VMEMMAP Muchun Song
2020-12-07 12:19 ` David Hildenbrand
2020-12-07 12:42 ` [External] " Muchun Song
2020-12-07 12:47 ` David Hildenbrand
2020-12-07 13:22 ` Muchun Song
2020-11-30 15:18 ` [PATCH v7 04/15] mm/hugetlb: Introduce nr_free_vmemmap_pages in the struct hstate Muchun Song
2020-12-07 12:36 ` David Hildenbrand
2020-12-07 13:11 ` [External] " Muchun Song
2020-12-09 8:54 ` David Hildenbrand
2020-12-09 9:27 ` Muchun Song
2020-11-30 15:18 ` [PATCH v7 05/15] mm/bootmem_info: Introduce {free,prepare}_vmemmap_page() Muchun Song
2020-12-07 12:39 ` David Hildenbrand
2020-12-07 13:23 ` [External] " Muchun Song
2020-12-09 7:36 ` Muchun Song
2020-12-09 8:49 ` David Hildenbrand
2020-12-09 9:25 ` Muchun Song
2020-12-09 9:32 ` David Hildenbrand
2020-12-09 9:43 ` Muchun Song
2020-11-30 15:18 ` [PATCH v7 06/15] mm/hugetlb: Disable freeing vmemmap if struct page size is not power of two Muchun Song
2020-12-09 9:57 ` David Hildenbrand
2020-12-09 10:03 ` [External] " Muchun Song
2020-12-09 10:06 ` David Hildenbrand
2020-12-09 10:10 ` David Hildenbrand
2020-12-09 10:16 ` Muchun Song
2020-12-09 15:13 ` Muchun Song
2020-12-09 15:47 ` David Hildenbrand
2020-12-09 15:50 ` Muchun Song
2020-12-09 10:10 ` Muchun Song
2020-11-30 15:18 ` [PATCH v7 07/15] x86/mm/64: Disable PMD page mapping of vmemmap Muchun Song
2020-11-30 15:18 ` [PATCH v7 08/15] mm/hugetlb: Free the vmemmap pages associated with each hugetlb page Muchun Song
2020-11-30 15:18 ` [PATCH v7 09/15] mm/hugetlb: Defer freeing of HugeTLB pages Muchun Song
2020-11-30 15:18 ` Muchun Song [this message]
2020-11-30 15:18 ` [PATCH v7 11/15] mm/hugetlb: Set the PageHWPoison to the raw error page Muchun Song
2020-11-30 15:18 ` [PATCH v7 12/15] mm/hugetlb: Flush work when dissolving hugetlb page Muchun Song
2020-11-30 15:18 ` [PATCH v7 13/15] mm/hugetlb: Add a kernel parameter hugetlb_free_vmemmap Muchun Song
2020-12-04 0:01 ` Song Bao Hua (Barry Song)
2020-11-30 15:18 ` [PATCH v7 14/15] mm/hugetlb: Gather discrete indexes of tail page Muchun Song
2020-11-30 15:18 ` [PATCH v7 15/15] mm/hugetlb: Add BUILD_BUG_ON to catch invalid usage of tail struct page Muchun Song
2020-12-03 8:35 ` [PATCH v7 00/15] Free some vmemmap pages of hugetlb page Muchun Song
2020-12-03 23:48 ` Mike Kravetz
2020-12-04 3:39 ` [External] " Muchun Song
2020-12-07 18:38 ` Oscar Salvador
2020-12-08 2:26 ` 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=20201130151838.11208-11-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=song.bao.hua@hisilicon.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).