From: Hugh Dickins <hughd@google.com>
To: Andrew Morton <akpm@linux-foundation.org>
Cc: Mike Kravetz <mike.kravetz@oracle.com>,
Mike Rapoport <rppt@kernel.org>,
"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
Matthew Wilcox <willy@infradead.org>,
David Hildenbrand <david@redhat.com>,
Suren Baghdasaryan <surenb@google.com>,
Qi Zheng <zhengqi.arch@bytedance.com>,
Yang Shi <shy828301@gmail.com>,
Mel Gorman <mgorman@techsingularity.net>,
Peter Xu <peterx@redhat.com>,
Peter Zijlstra <peterz@infradead.org>,
Will Deacon <will@kernel.org>, Yu Zhao <yuzhao@google.com>,
Alistair Popple <apopple@nvidia.com>,
Ralph Campbell <rcampbell@nvidia.com>,
Ira Weiny <ira.weiny@intel.com>,
Steven Price <steven.price@arm.com>,
SeongJae Park <sj@kernel.org>,
Naoya Horiguchi <naoya.horiguchi@nec.com>,
Christophe Leroy <christophe.leroy@csgroup.eu>,
Zack Rusin <zackr@vmware.com>, Jason Gunthorpe <jgg@ziepe.ca>,
Axel Rasmussen <axelrasmussen@google.com>,
Anshuman Khandual <anshuman.khandual@arm.com>,
Pasha Tatashin <pasha.tatashin@soleen.com>,
Miaohe Lin <linmiaohe@huawei.com>,
Minchan Kim <minchan@kernel.org>,
Christoph Hellwig <hch@infradead.org>,
Song Liu <song@kernel.org>,
Thomas Hellstrom <thomas.hellstrom@linux.intel.com>,
Russell King <linux@armlinux.org.uk>,
"David S. Miller" <davem@davemloft.net>,
Michael Ellerman <mpe@ellerman.id.au>,
"Aneesh Kumar K.V" <aneesh.kumar@linux.ibm.com>,
Heiko Carstens <hca@linux.ibm.com>,
Christian Borntraeger <borntraeger@linux.ibm.com>,
Claudio Imbrenda <imbrenda@linux.ibm.com>,
Alexander Gordeev <agordeev@linux.ibm.com>,
Jann Horn <jannh@google.com>,
linux-arm-kernel@lists.infradead.org,
sparclinux@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
linux-s390@vger.kernel.org, linux-kernel@vger.kernel.org,
linux-mm@kvack.org
Subject: [PATCH 07/12] s390: add pte_free_defer(), with use of mmdrop_async()
Date: Sun, 28 May 2023 23:22:40 -0700 (PDT) [thread overview]
Message-ID: <6dd63b39-e71f-2e8b-7e0-83e02f3bcb39@google.com> (raw)
In-Reply-To: <35e983f5-7ed3-b310-d949-9ae8b130cdab@google.com>
Add s390-specific pte_free_defer(), to call pte_free() via call_rcu().
pte_free_defer() will be called inside khugepaged's retract_page_tables()
loop, where allocating extra memory cannot be relied upon. This precedes
the generic version to avoid build breakage from incompatible pgtable_t.
This version is more complicated than others: because page_table_free()
needs to know which fragment is being freed, and which mm to link it to.
page_table_free()'s fragment handling is clever, but I could too easily
break it: what's done here in pte_free_defer() and pte_free_now() might
be better integrated with page_table_free()'s cleverness, but not by me!
By the time that page_table_free() gets called via RCU, it's conceivable
that mm would already have been freed: so mmgrab() in pte_free_defer()
and mmdrop() in pte_free_now(). No, that is not a good context to call
mmdrop() from, so make mmdrop_async() public and use that.
Signed-off-by: Hugh Dickins <hughd@google.com>
---
arch/s390/include/asm/pgalloc.h | 4 ++++
arch/s390/mm/pgalloc.c | 34 +++++++++++++++++++++++++++++++++
include/linux/mm_types.h | 2 +-
include/linux/sched/mm.h | 1 +
kernel/fork.c | 2 +-
5 files changed, 41 insertions(+), 2 deletions(-)
diff --git a/arch/s390/include/asm/pgalloc.h b/arch/s390/include/asm/pgalloc.h
index 17eb618f1348..89a9d5ef94f8 100644
--- a/arch/s390/include/asm/pgalloc.h
+++ b/arch/s390/include/asm/pgalloc.h
@@ -143,6 +143,10 @@ static inline void pmd_populate(struct mm_struct *mm,
#define pte_free_kernel(mm, pte) page_table_free(mm, (unsigned long *) pte)
#define pte_free(mm, pte) page_table_free(mm, (unsigned long *) pte)
+/* arch use pte_free_defer() implementation in arch/s390/mm/pgalloc.c */
+#define pte_free_defer pte_free_defer
+void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable);
+
void vmem_map_init(void);
void *vmem_crst_alloc(unsigned long val);
pte_t *vmem_pte_alloc(void);
diff --git a/arch/s390/mm/pgalloc.c b/arch/s390/mm/pgalloc.c
index 66ab68db9842..0129de9addfd 100644
--- a/arch/s390/mm/pgalloc.c
+++ b/arch/s390/mm/pgalloc.c
@@ -346,6 +346,40 @@ void page_table_free(struct mm_struct *mm, unsigned long *table)
__free_page(page);
}
+#ifdef CONFIG_TRANSPARENT_HUGEPAGE
+static void pte_free_now(struct rcu_head *head)
+{
+ struct page *page;
+ unsigned long mm_bit;
+ struct mm_struct *mm;
+ unsigned long *table;
+
+ page = container_of(head, struct page, rcu_head);
+ table = (unsigned long *)page_to_virt(page);
+ mm_bit = (unsigned long)page->pt_mm;
+ /* 4K page has only two 2K fragments, but alignment allows eight */
+ mm = (struct mm_struct *)(mm_bit & ~7);
+ table += PTRS_PER_PTE * (mm_bit & 7);
+ page_table_free(mm, table);
+ mmdrop_async(mm);
+}
+
+void pte_free_defer(struct mm_struct *mm, pgtable_t pgtable)
+{
+ struct page *page;
+ unsigned long mm_bit;
+
+ mmgrab(mm);
+ page = virt_to_page(pgtable);
+ /* Which 2K page table fragment of a 4K page? */
+ mm_bit = ((unsigned long)pgtable & ~PAGE_MASK) /
+ (PTRS_PER_PTE * sizeof(pte_t));
+ mm_bit += (unsigned long)mm;
+ page->pt_mm = (struct mm_struct *)mm_bit;
+ call_rcu(&page->rcu_head, pte_free_now);
+}
+#endif /* CONFIG_TRANSPARENT_HUGEPAGE */
+
void page_table_free_rcu(struct mmu_gather *tlb, unsigned long *table,
unsigned long vmaddr)
{
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 306a3d1a0fa6..1667a1bdb8a8 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -146,7 +146,7 @@ struct page {
pgtable_t pmd_huge_pte; /* protected by page->ptl */
unsigned long _pt_pad_2; /* mapping */
union {
- struct mm_struct *pt_mm; /* x86 pgds only */
+ struct mm_struct *pt_mm; /* x86 pgd, s390 */
atomic_t pt_frag_refcount; /* powerpc */
};
#if ALLOC_SPLIT_PTLOCKS
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 8d89c8c4fac1..a9043d1a0d55 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -41,6 +41,7 @@ static inline void smp_mb__after_mmgrab(void)
smp_mb__after_atomic();
}
+extern void mmdrop_async(struct mm_struct *mm);
extern void __mmdrop(struct mm_struct *mm);
static inline void mmdrop(struct mm_struct *mm)
diff --git a/kernel/fork.c b/kernel/fork.c
index ed4e01daccaa..fa4486b65c56 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -942,7 +942,7 @@ static void mmdrop_async_fn(struct work_struct *work)
__mmdrop(mm);
}
-static void mmdrop_async(struct mm_struct *mm)
+void mmdrop_async(struct mm_struct *mm)
{
if (unlikely(atomic_dec_and_test(&mm->mm_count))) {
INIT_WORK(&mm->async_put_work, mmdrop_async_fn);
--
2.35.3
next prev parent reply other threads:[~2023-05-29 6:22 UTC|newest]
Thread overview: 27+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-05-29 6:11 [PATCH 00/12] mm: free retracted page table by RCU Hugh Dickins
2023-05-29 6:14 ` [PATCH 01/12] mm/pgtable: add rcu_read_lock() and rcu_read_unlock()s Hugh Dickins
2023-05-31 17:06 ` Jann Horn
2023-05-29 6:16 ` [PATCH 02/12] mm/pgtable: add PAE safety to __pte_offset_map() Hugh Dickins
2023-05-29 13:56 ` Matthew Wilcox
2023-05-29 6:17 ` [PATCH 03/12] arm: adjust_pte() use pte_offset_map_nolock() Hugh Dickins
2023-05-29 6:18 ` [PATCH 04/12] powerpc: assert_pte_locked() " Hugh Dickins
2023-05-29 6:20 ` [PATCH 05/12] powerpc: add pte_free_defer() for pgtables sharing page Hugh Dickins
2023-05-29 14:02 ` Matthew Wilcox
2023-05-29 14:36 ` Hugh Dickins
[not found] ` <ZHn6n5eVTsr4Wl8x@ziepe.ca>
[not found] ` <4df4909f-f5dd-6f94-9792-8f2949f542b3@google.com>
[not found] ` <ZH95oobIqN0WO5MK@ziepe.ca>
[not found] ` <ZH+DAxLhIYpTlIFc@x1n>
[not found] ` <ZH+EMp9RuEVOjVNb@ziepe.ca>
2023-06-07 3:49 ` Hugh Dickins
2023-05-29 6:21 ` [PATCH 06/12] sparc: " Hugh Dickins
2023-05-29 6:22 ` Hugh Dickins [this message]
[not found] ` <175ebec8-761-c3f-2d98-6c3bd87161c8@google.com>
2023-06-06 19:40 ` [PATCH 07/12] s390: add pte_free_defer(), with use of mmdrop_async() Gerald Schaefer
2023-06-08 3:35 ` Hugh Dickins
2023-06-08 13:58 ` Jason Gunthorpe
2023-06-08 15:47 ` Gerald Schaefer
[not found] ` <ZH99cLKeALvUCIH8@ziepe.ca>
2023-06-08 2:46 ` Hugh Dickins
2023-05-29 6:23 ` [PATCH 08/12] mm/pgtable: add pte_free_defer() for pgtable as page Hugh Dickins
2023-05-29 6:25 ` [PATCH 09/12] mm/khugepaged: retract_page_tables() without mmap or vma lock Hugh Dickins
2023-05-29 23:26 ` Peter Xu
2023-05-31 0:38 ` Hugh Dickins
2023-05-31 15:34 ` Jann Horn
2023-05-29 6:26 ` [PATCH 10/12] mm/khugepaged: collapse_pte_mapped_thp() with mmap_read_lock() Hugh Dickins
2023-05-31 17:25 ` Jann Horn
2023-05-29 6:28 ` [PATCH 11/12] mm/khugepaged: delete khugepaged_collapse_pte_mapped_thps() Hugh Dickins
2023-05-29 6:30 ` [PATCH 12/12] mm: delete mmap_write_trylock() and vma_try_start_write() Hugh Dickins
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=6dd63b39-e71f-2e8b-7e0-83e02f3bcb39@google.com \
--to=hughd@google.com \
--cc=agordeev@linux.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=aneesh.kumar@linux.ibm.com \
--cc=anshuman.khandual@arm.com \
--cc=apopple@nvidia.com \
--cc=axelrasmussen@google.com \
--cc=borntraeger@linux.ibm.com \
--cc=christophe.leroy@csgroup.eu \
--cc=davem@davemloft.net \
--cc=david@redhat.com \
--cc=hca@linux.ibm.com \
--cc=hch@infradead.org \
--cc=imbrenda@linux.ibm.com \
--cc=ira.weiny@intel.com \
--cc=jannh@google.com \
--cc=jgg@ziepe.ca \
--cc=kirill.shutemov@linux.intel.com \
--cc=linmiaohe@huawei.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-s390@vger.kernel.org \
--cc=linux@armlinux.org.uk \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mgorman@techsingularity.net \
--cc=mike.kravetz@oracle.com \
--cc=minchan@kernel.org \
--cc=mpe@ellerman.id.au \
--cc=naoya.horiguchi@nec.com \
--cc=pasha.tatashin@soleen.com \
--cc=peterx@redhat.com \
--cc=peterz@infradead.org \
--cc=rcampbell@nvidia.com \
--cc=rppt@kernel.org \
--cc=shy828301@gmail.com \
--cc=sj@kernel.org \
--cc=song@kernel.org \
--cc=sparclinux@vger.kernel.org \
--cc=steven.price@arm.com \
--cc=surenb@google.com \
--cc=thomas.hellstrom@linux.intel.com \
--cc=will@kernel.org \
--cc=willy@infradead.org \
--cc=yuzhao@google.com \
--cc=zackr@vmware.com \
--cc=zhengqi.arch@bytedance.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