summaryrefslogtreecommitdiff
path: root/mm/ptdump.c
diff options
context:
space:
mode:
authorMuchun Song <songmuchun@bytedance.com>2022-03-23 00:45:06 +0300
committerLinus Torvalds <torvalds@linux-foundation.org>2022-03-23 01:57:08 +0300
commitd8d55f5616cf3b900a23a72dd24e7b07211e7859 (patch)
tree569325ac86f93106d5329c40e6bb0d5c487d53e5 /mm/ptdump.c
parenta6b40850c442bf996e729e1d441d3dbc37cea171 (diff)
downloadlinux-d8d55f5616cf3b900a23a72dd24e7b07211e7859.tar.xz
mm: sparsemem: use page table lock to protect kernel pmd operations
The init_mm.page_table_lock is used to protect kernel page tables, we can use it to serialize splitting vmemmap PMD mappings instead of mmap write lock, which can increase the concurrency of vmemmap_remap_free(). Actually, It increase the concurrency between allocations of HugeTLB pages. But it is not the only benefit. There are a lot of users of mmap read lock of init_mm. The mmap write lock is holding through vmemmap_remap_free(), removing mmap write lock usage to make it does not affect other users of mmap read lock. It is not making anything worse and always a win to move. Now the kernel page table walker does not hold the page_table_lock when walking pmd entries. There may be consistency issue of a pmd entry, because pmd entry might change from a huge pmd entry to a PTE page table. There is only one user of kernel page table walker, namely ptdump. The ptdump already considers the consistency, which use a local variable to cache the value of pmd entry. But we also need to update ->action to ACTION_CONTINUE to make sure the walker does not walk every pte entry again when concurrent thread has split the huge pmd. Link: https://lkml.kernel.org/r/20211101031651.75851-4-songmuchun@bytedance.com Signed-off-by: Muchun Song <songmuchun@bytedance.com> Cc: Barry Song <song.bao.hua@hisilicon.com> Cc: Bodeddula Balasubramaniam <bodeddub@amazon.com> Cc: Chen Huang <chenhuang5@huawei.com> Cc: David Hildenbrand <david@redhat.com> Cc: Fam Zheng <fam.zheng@bytedance.com> Cc: Jonathan Corbet <corbet@lwn.net> Cc: Matthew Wilcox <willy@infradead.org> Cc: Michal Hocko <mhocko@suse.com> Cc: Mike Kravetz <mike.kravetz@oracle.com> Cc: Oscar Salvador <osalvador@suse.de> Cc: Qi Zheng <zhengqi.arch@bytedance.com> Cc: Xiongchun Duan <duanxiongchun@bytedance.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/ptdump.c')
-rw-r--r--mm/ptdump.c16
1 files changed, 12 insertions, 4 deletions
diff --git a/mm/ptdump.c b/mm/ptdump.c
index da751448d0e4..eea3d28d173c 100644
--- a/mm/ptdump.c
+++ b/mm/ptdump.c
@@ -40,8 +40,10 @@ static int ptdump_pgd_entry(pgd_t *pgd, unsigned long addr,
if (st->effective_prot)
st->effective_prot(st, 0, pgd_val(val));
- if (pgd_leaf(val))
+ if (pgd_leaf(val)) {
st->note_page(st, addr, 0, pgd_val(val));
+ walk->action = ACTION_CONTINUE;
+ }
return 0;
}
@@ -61,8 +63,10 @@ static int ptdump_p4d_entry(p4d_t *p4d, unsigned long addr,
if (st->effective_prot)
st->effective_prot(st, 1, p4d_val(val));
- if (p4d_leaf(val))
+ if (p4d_leaf(val)) {
st->note_page(st, addr, 1, p4d_val(val));
+ walk->action = ACTION_CONTINUE;
+ }
return 0;
}
@@ -82,8 +86,10 @@ static int ptdump_pud_entry(pud_t *pud, unsigned long addr,
if (st->effective_prot)
st->effective_prot(st, 2, pud_val(val));
- if (pud_leaf(val))
+ if (pud_leaf(val)) {
st->note_page(st, addr, 2, pud_val(val));
+ walk->action = ACTION_CONTINUE;
+ }
return 0;
}
@@ -101,8 +107,10 @@ static int ptdump_pmd_entry(pmd_t *pmd, unsigned long addr,
if (st->effective_prot)
st->effective_prot(st, 3, pmd_val(val));
- if (pmd_leaf(val))
+ if (pmd_leaf(val)) {
st->note_page(st, addr, 3, pmd_val(val));
+ walk->action = ACTION_CONTINUE;
+ }
return 0;
}