From: Zi Yan <zi.yan@sent.com>
To: linux-mm@kvack.org, Roman Gushchin <guro@fb.com>
Cc: Rik van Riel <riel@surriel.com>,
"Kirill A . Shutemov" <kirill.shutemov@linux.intel.com>,
Matthew Wilcox <willy@infradead.org>,
Shakeel Butt <shakeelb@google.com>,
Yang Shi <yang.shi@linux.alibaba.com>,
David Nellans <dnellans@nvidia.com>,
linux-kernel@vger.kernel.org, Zi Yan <ziy@nvidia.com>
Subject: [RFC PATCH 09/16] mm: thp: 1GB THP support in try_to_unmap().
Date: Wed, 2 Sep 2020 14:06:21 -0400 [thread overview]
Message-ID: <20200902180628.4052244-10-zi.yan@sent.com> (raw)
In-Reply-To: <20200902180628.4052244-1-zi.yan@sent.com>
From: Zi Yan <ziy@nvidia.com>
Unmap different subpages in different sized THPs properly in the
try_to_unmap() function.
Signed-off-by: Zi Yan <ziy@nvidia.com>
---
mm/migrate.c | 2 +-
mm/rmap.c | 159 +++++++++++++++++++++++++++++++++++++--------------
2 files changed, 116 insertions(+), 45 deletions(-)
diff --git a/mm/migrate.c b/mm/migrate.c
index be0e80b32686..df069a55722e 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -225,7 +225,7 @@ static bool remove_migration_pte(struct page *page, struct vm_area_struct *vma,
#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
/* PMD-mapped THP migration entry */
- if (!pvmw.pte) {
+ if (!pvmw.pte && pvmw.pmd) {
VM_BUG_ON_PAGE(PageHuge(page) || !PageTransCompound(page), page);
remove_migration_pmd(&pvmw, new);
continue;
diff --git a/mm/rmap.c b/mm/rmap.c
index 0bbaaa891b3c..6c788abdb0b9 100644
--- a/mm/rmap.c
+++ b/mm/rmap.c
@@ -1123,6 +1123,7 @@ void do_page_add_anon_rmap(struct page *page,
{
bool compound = flags & RMAP_COMPOUND;
bool first;
+ struct page *head = compound_head(page);
if (unlikely(PageKsm(page)))
lock_page_memcg(page);
@@ -1132,8 +1133,8 @@ void do_page_add_anon_rmap(struct page *page,
if (compound) {
atomic_t *mapcount = NULL;
VM_BUG_ON_PAGE(!PageLocked(page), page);
- VM_BUG_ON_PAGE(!PageTransHuge(page), page);
- if (compound_order(page) == HPAGE_PUD_ORDER) {
+ VM_BUG_ON_PAGE(!PMDPageInPUD(page) && !PageTransHuge(page), page);
+ if (compound_order(head) == HPAGE_PUD_ORDER) {
if (order == HPAGE_PUD_ORDER) {
mapcount = compound_mapcount_ptr(page);
} else if (order == HPAGE_PMD_ORDER) {
@@ -1141,7 +1142,7 @@ void do_page_add_anon_rmap(struct page *page,
mapcount = sub_compound_mapcount_ptr(page, 1);
} else
VM_BUG_ON(1);
- } else if (compound_order(page) == HPAGE_PMD_ORDER) {
+ } else if (compound_order(head) == HPAGE_PMD_ORDER) {
mapcount = compound_mapcount_ptr(page);
} else
VM_BUG_ON(1);
@@ -1151,7 +1152,8 @@ void do_page_add_anon_rmap(struct page *page,
}
if (first) {
- int nr = compound ? thp_nr_pages(page) : 1;
+ /* int nr = compound ? thp_nr_pages(page) : 1; */
+ int nr = 1<<order;
/*
* We use the irq-unsafe __{inc|mod}_zone_page_stat because
* these counters are not modified in interrupt context, and
@@ -1460,10 +1462,13 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
.address = address,
};
pte_t pteval;
- struct page *subpage;
+ pmd_t pmdval;
+ pud_t pudval;
+ struct page *subpage = NULL;
bool ret = true;
struct mmu_notifier_range range;
enum ttu_flags flags = (enum ttu_flags)(long)arg;
+ int order = 0;
/* munlock has nothing to gain from examining un-locked vmas */
if ((flags & TTU_MUNLOCK) && !(vma->vm_flags & VM_LOCKED))
@@ -1473,6 +1478,11 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
is_zone_device_page(page) && !is_device_private_page(page))
return true;
+ if (flags & TTU_SPLIT_HUGE_PUD) {
+ split_huge_pud_address(vma, address,
+ flags & TTU_SPLIT_FREEZE, page);
+ }
+
if (flags & TTU_SPLIT_HUGE_PMD) {
split_huge_pmd_address(vma, address,
flags & TTU_SPLIT_FREEZE, page);
@@ -1505,7 +1515,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
while (page_vma_mapped_walk(&pvmw)) {
#ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
/* PMD-mapped THP migration entry */
- if (!pvmw.pte && (flags & TTU_MIGRATION)) {
+ if (!pvmw.pte && pvmw.pmd && (flags & TTU_MIGRATION)) {
VM_BUG_ON_PAGE(PageHuge(page) || !PageTransCompound(page), page);
set_pmd_migration_entry(&pvmw, page);
@@ -1537,9 +1547,18 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
}
/* Unexpected PMD-mapped THP? */
- VM_BUG_ON_PAGE(!pvmw.pte, page);
- subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
+ if (pvmw.pte) {
+ subpage = page - page_to_pfn(page) + pte_pfn(*pvmw.pte);
+ order = 0;
+ } else if (!pvmw.pte && pvmw.pmd) {
+ subpage = page - page_to_pfn(page) + pmd_pfn(*pvmw.pmd);
+ order = HPAGE_PMD_ORDER;
+ } else if (!pvmw.pte && !pvmw.pmd && pvmw.pud) {
+ subpage = page - page_to_pfn(page) + pud_pfn(*pvmw.pud);
+ order = HPAGE_PUD_ORDER;
+ }
+ VM_BUG_ON(!subpage);
address = pvmw.address;
if (PageHuge(page)) {
@@ -1617,16 +1636,26 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
}
if (!(flags & TTU_IGNORE_ACCESS)) {
- if (ptep_clear_flush_young_notify(vma, address,
- pvmw.pte)) {
- ret = false;
- page_vma_mapped_walk_done(&pvmw);
- break;
+ if ((pvmw.pte &&
+ ptep_clear_flush_young_notify(vma, address, pvmw.pte)) ||
+ ((!pvmw.pte && pvmw.pmd) &&
+ pmdp_clear_flush_young_notify(vma, address, pvmw.pmd)) ||
+ ((!pvmw.pte && !pvmw.pmd && pvmw.pud) &&
+ pudp_clear_flush_young_notify(vma, address, pvmw.pud))
+ ) {
+ ret = false;
+ page_vma_mapped_walk_done(&pvmw);
+ break;
}
}
/* Nuke the page table entry. */
- flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
+ if (pvmw.pte)
+ flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
+ else if (!pvmw.pte && pvmw.pmd)
+ flush_cache_page(vma, address, pmd_pfn(*pvmw.pmd));
+ else if (!pvmw.pte && !pvmw.pmd && pvmw.pud)
+ flush_cache_page(vma, address, pud_pfn(*pvmw.pud));
if (should_defer_flush(mm, flags)) {
/*
* We clear the PTE but do not flush so potentially
@@ -1636,16 +1665,34 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
* transition on a cached TLB entry is written through
* and traps if the PTE is unmapped.
*/
- pteval = ptep_get_and_clear(mm, address, pvmw.pte);
+ if (pvmw.pte) {
+ pteval = ptep_get_and_clear(mm, address, pvmw.pte);
+
+ set_tlb_ubc_flush_pending(mm, pte_dirty(pteval));
+ } else if (!pvmw.pte && pvmw.pmd) {
+ pmdval = pmdp_huge_get_and_clear(mm, address, pvmw.pmd);
- set_tlb_ubc_flush_pending(mm, pte_dirty(pteval));
+ set_tlb_ubc_flush_pending(mm, pmd_dirty(pmdval));
+ } else if (!pvmw.pte && !pvmw.pmd && pvmw.pud) {
+ pudval = pudp_huge_get_and_clear(mm, address, pvmw.pud);
+
+ set_tlb_ubc_flush_pending(mm, pud_dirty(pudval));
+ }
} else {
- pteval = ptep_clear_flush(vma, address, pvmw.pte);
+ if (pvmw.pte)
+ pteval = ptep_clear_flush(vma, address, pvmw.pte);
+ else if (!pvmw.pte && pvmw.pmd)
+ pmdval = pmdp_huge_clear_flush(vma, address, pvmw.pmd);
+ else if (!pvmw.pte && !pvmw.pmd && pvmw.pud)
+ pudval = pudp_huge_clear_flush(vma, address, pvmw.pud);
}
/* Move the dirty bit to the page. Now the pte is gone. */
- if (pte_dirty(pteval))
- set_page_dirty(page);
+ if ((pvmw.pte && pte_dirty(pteval)) ||
+ ((!pvmw.pte && pvmw.pmd) && pmd_dirty(pmdval)) ||
+ ((!pvmw.pte && !pvmw.pmd && pvmw.pud) && pud_dirty(pudval))
+ )
+ set_page_dirty(page);
/* Update high watermark before we lower rss */
update_hiwater_rss(mm);
@@ -1680,35 +1727,59 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
} else if (IS_ENABLED(CONFIG_MIGRATION) &&
(flags & (TTU_MIGRATION|TTU_SPLIT_FREEZE))) {
swp_entry_t entry;
- pte_t swp_pte;
- if (arch_unmap_one(mm, vma, address, pteval) < 0) {
- set_pte_at(mm, address, pvmw.pte, pteval);
- ret = false;
- page_vma_mapped_walk_done(&pvmw);
- break;
- }
+ if (pvmw.pte) {
+ pte_t swp_pte;
- /*
- * Store the pfn of the page in a special migration
- * pte. do_swap_page() will wait until the migration
- * pte is removed and then restart fault handling.
- */
- entry = make_migration_entry(subpage,
- pte_write(pteval));
- swp_pte = swp_entry_to_pte(entry);
- if (pte_soft_dirty(pteval))
- swp_pte = pte_swp_mksoft_dirty(swp_pte);
- if (pte_uffd_wp(pteval))
- swp_pte = pte_swp_mkuffd_wp(swp_pte);
- set_pte_at(mm, address, pvmw.pte, swp_pte);
- /*
- * No need to invalidate here it will synchronize on
- * against the special swap migration pte.
- */
+ if (arch_unmap_one(mm, vma, address, pteval) < 0) {
+ set_pte_at(mm, address, pvmw.pte, pteval);
+ ret = false;
+ page_vma_mapped_walk_done(&pvmw);
+ break;
+ }
+
+ /*
+ * Store the pfn of the page in a special migration
+ * pte. do_swap_page() will wait until the migration
+ * pte is removed and then restart fault handling.
+ */
+ entry = make_migration_entry(subpage,
+ pte_write(pteval));
+ swp_pte = swp_entry_to_pte(entry);
+ if (pte_soft_dirty(pteval))
+ swp_pte = pte_swp_mksoft_dirty(swp_pte);
+ if (pte_uffd_wp(pteval))
+ swp_pte = pte_swp_mkuffd_wp(swp_pte);
+ set_pte_at(mm, address, pvmw.pte, swp_pte);
+ /*
+ * No need to invalidate here it will synchronize on
+ * against the special swap migration pte.
+ */
+ } else if (!pvmw.pte && pvmw.pmd) {
+ pmd_t swp_pmd;
+ /*
+ * Store the pfn of the page in a special migration
+ * pte. do_swap_page() will wait until the migration
+ * pte is removed and then restart fault handling.
+ */
+ entry = make_migration_entry(subpage,
+ pmd_write(pmdval));
+ swp_pmd = swp_entry_to_pmd(entry);
+ if (pmd_soft_dirty(pmdval))
+ swp_pmd = pmd_swp_mksoft_dirty(swp_pmd);
+ set_pmd_at(mm, address, pvmw.pmd, swp_pmd);
+ /*
+ * No need to invalidate here it will synchronize on
+ * against the special swap migration pte.
+ */
+ } else if (!pvmw.pte && !pvmw.pmd && pvmw.pud) {
+ VM_BUG_ON(1);
+ }
} else if (PageAnon(page)) {
swp_entry_t entry = { .val = page_private(subpage) };
pte_t swp_pte;
+
+ VM_BUG_ON(!pvmw.pte);
/*
* Store the swap location in the pte.
* See handle_pte_fault() ...
@@ -1794,7 +1865,7 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma,
*
* See Documentation/vm/mmu_notifier.rst
*/
- page_remove_rmap(subpage, PageHuge(page), 0);
+ page_remove_rmap(subpage, PageHuge(page) || order >= HPAGE_PMD_ORDER, order);
put_page(page);
}
--
2.28.0
next prev parent reply other threads:[~2020-09-02 18:06 UTC|newest]
Thread overview: 82+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-09-02 18:06 [RFC PATCH 00/16] 1GB THP support on x86_64 Zi Yan
2020-09-02 18:06 ` [RFC PATCH 01/16] mm: add pagechain container for storing multiple pages Zi Yan
2020-09-02 20:29 ` Randy Dunlap
2020-09-02 20:48 ` Zi Yan
2020-09-03 3:15 ` Matthew Wilcox
2020-09-07 12:22 ` Kirill A. Shutemov
2020-09-07 15:11 ` Zi Yan
2020-09-09 13:46 ` Kirill A. Shutemov
2020-09-09 14:15 ` Zi Yan
2020-09-02 18:06 ` [RFC PATCH 02/16] mm: thp: 1GB anonymous page implementation Zi Yan
2020-09-02 18:06 ` [RFC PATCH 03/16] mm: proc: add 1GB THP kpageflag Zi Yan
2020-09-09 13:46 ` Kirill A. Shutemov
2020-09-02 18:06 ` [RFC PATCH 04/16] mm: thp: 1GB THP copy on write implementation Zi Yan
2020-09-02 18:06 ` [RFC PATCH 05/16] mm: thp: handling 1GB THP reference bit Zi Yan
2020-09-09 14:09 ` Kirill A. Shutemov
2020-09-09 14:36 ` Zi Yan
2020-09-02 18:06 ` [RFC PATCH 06/16] mm: thp: add 1GB THP split_huge_pud_page() function Zi Yan
2020-09-09 14:18 ` Kirill A. Shutemov
2020-09-09 14:19 ` Zi Yan
2020-09-02 18:06 ` [RFC PATCH 07/16] mm: stats: make smap stats understand PUD THPs Zi Yan
2020-09-02 18:06 ` [RFC PATCH 08/16] mm: page_vma_walk: teach it about PMD-mapped PUD THP Zi Yan
2020-09-02 18:06 ` Zi Yan [this message]
2020-09-02 18:06 ` [RFC PATCH 10/16] mm: thp: split 1GB THPs at page reclaim Zi Yan
2020-09-02 18:06 ` [RFC PATCH 11/16] mm: thp: 1GB THP follow_p*d_page() support Zi Yan
2020-09-02 18:06 ` [RFC PATCH 12/16] mm: support 1GB THP pagemap support Zi Yan
2020-09-02 18:06 ` [RFC PATCH 13/16] mm: thp: add a knob to enable/disable 1GB THPs Zi Yan
2020-09-02 18:06 ` [RFC PATCH 14/16] mm: page_alloc: >=MAX_ORDER pages allocation an deallocation Zi Yan
2020-09-02 18:06 ` [RFC PATCH 15/16] hugetlb: cma: move cma reserve function to cma.c Zi Yan
2020-09-02 18:06 ` [RFC PATCH 16/16] mm: thp: use cma reservation for pud thp allocation Zi Yan
2020-09-02 18:40 ` [RFC PATCH 00/16] 1GB THP support on x86_64 Jason Gunthorpe
2020-09-02 18:45 ` Zi Yan
2020-09-02 18:48 ` Jason Gunthorpe
2020-09-02 19:05 ` Zi Yan
2020-09-02 19:57 ` Jason Gunthorpe
2020-09-02 20:29 ` Zi Yan
2020-09-03 16:40 ` Jason Gunthorpe
2020-09-03 16:55 ` Matthew Wilcox
2020-09-03 17:08 ` Jason Gunthorpe
2020-09-03 7:32 ` Michal Hocko
2020-09-03 16:25 ` Roman Gushchin
2020-09-03 16:50 ` Jason Gunthorpe
2020-09-03 17:01 ` Matthew Wilcox
2020-09-03 17:18 ` Jason Gunthorpe
2020-09-03 20:57 ` Mike Kravetz
2020-09-03 21:06 ` Roman Gushchin
2020-09-04 7:42 ` Michal Hocko
2020-09-04 21:10 ` Roman Gushchin
2020-09-07 7:20 ` Michal Hocko
2020-09-08 15:09 ` Zi Yan
2020-09-08 19:58 ` Roman Gushchin
2020-09-09 4:01 ` John Hubbard
2020-09-09 7:15 ` Michal Hocko
2020-09-03 14:23 ` Kirill A. Shutemov
2020-09-03 16:30 ` Roman Gushchin
2020-09-08 11:57 ` David Hildenbrand
2020-09-08 14:05 ` Zi Yan
2020-09-08 14:22 ` David Hildenbrand
2020-09-08 15:36 ` Zi Yan
2020-09-08 14:27 ` Matthew Wilcox
2020-09-08 15:50 ` Zi Yan
2020-09-09 12:11 ` Jason Gunthorpe
2020-09-09 12:32 ` Matthew Wilcox
2020-09-09 13:14 ` Jason Gunthorpe
2020-09-09 13:27 ` David Hildenbrand
2020-09-10 10:02 ` William Kucharski
2020-09-08 14:35 ` Michal Hocko
2020-09-08 14:41 ` Rik van Riel
2020-09-08 15:02 ` David Hildenbrand
2020-09-09 7:04 ` Michal Hocko
2020-09-09 13:19 ` Rik van Riel
2020-09-09 13:43 ` David Hildenbrand
2020-09-09 13:49 ` Rik van Riel
2020-09-09 13:54 ` David Hildenbrand
2020-09-10 7:32 ` Michal Hocko
2020-09-10 8:27 ` David Hildenbrand
2020-09-10 14:21 ` Zi Yan
2020-09-10 14:34 ` David Hildenbrand
2020-09-10 14:41 ` Zi Yan
2020-09-10 15:15 ` David Hildenbrand
2020-09-10 13:32 ` Rik van Riel
2020-09-10 14:30 ` Zi Yan
2020-09-09 13:59 ` Michal Hocko
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=20200902180628.4052244-10-zi.yan@sent.com \
--to=zi.yan@sent.com \
--cc=dnellans@nvidia.com \
--cc=guro@fb.com \
--cc=kirill.shutemov@linux.intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=riel@surriel.com \
--cc=shakeelb@google.com \
--cc=willy@infradead.org \
--cc=yang.shi@linux.alibaba.com \
--cc=ziy@nvidia.com \
/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).