From: Laurent Dufour <ldufour@linux.ibm.com>
To: akpm@linux-foundation.org, mhocko@kernel.org,
peterz@infradead.org, kirill@shutemov.name, ak@linux.intel.com,
dave@stgolabs.net, jack@suse.cz,
Matthew Wilcox <willy@infradead.org>,
aneesh.kumar@linux.ibm.com, benh@kernel.crashing.org,
mpe@ellerman.id.au, paulus@samba.org,
Thomas Gleixner <tglx@linutronix.de>,
Ingo Molnar <mingo@redhat.com>,
hpa@zytor.com, Will Deacon <will.deacon@arm.com>,
Sergey Senozhatsky <sergey.senozhatsky@gmail.com>,
sergey.senozhatsky.work@gmail.com,
Andrea Arcangeli <aarcange@redhat.com>,
Alexei Starovoitov <alexei.starovoitov@gmail.com>,
kemi.wang@intel.com, Daniel Jordan <daniel.m.jordan@oracle.com>,
David Rientjes <rientjes@google.com>,
Jerome Glisse <jglisse@redhat.com>,
Ganesh Mahendran <opensource.ganesh@gmail.com>,
Minchan Kim <minchan@kernel.org>,
Punit Agrawal <punitagrawal@gmail.com>,
vinayak menon <vinayakm.list@gmail.com>,
Yang Shi <yang.shi@linux.alibaba.com>,
zhong jiang <zhongjiang@huawei.com>,
Haiyan Song <haiyanx.song@intel.com>,
Balbir Singh <bsingharora@gmail.com>,
sj38.park@gmail.com, Michel Lespinasse <walken@google.com>,
Mike Rapoport <rppt@linux.ibm.com>
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
haren@linux.vnet.ibm.com, npiggin@gmail.com,
paulmck@linux.vnet.ibm.com, Tim Chen <tim.c.chen@linux.intel.com>,
linuxppc-dev@lists.ozlabs.org, x86@kernel.org
Subject: [PATCH v12 21/31] mm: Introduce find_vma_rcu()
Date: Tue, 16 Apr 2019 15:45:12 +0200 [thread overview]
Message-ID: <20190416134522.17540-22-ldufour@linux.ibm.com> (raw)
In-Reply-To: <20190416134522.17540-1-ldufour@linux.ibm.com>
This allows to search for a VMA structure without holding the mmap_sem.
The search is repeated while the mm seqlock is changing and until we found
a valid VMA.
While under the RCU protection, a reference is taken on the VMA, so the
caller must call put_vma() once it not more need the VMA structure.
At the time a VMA is inserted in the MM RB tree, in vma_rb_insert(), a
reference is taken to the VMA by calling get_vma().
When removing a VMA from the MM RB tree, the VMA is not release immediately
but at the end of the RCU grace period through vm_rcu_put(). This ensures
that the VMA remains allocated until the end the RCU grace period.
Since the vm_file pointer, if valid, is released in put_vma(), there is no
guarantee that the file pointer will be valid on the returned VMA.
Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
---
include/linux/mm_types.h | 1 +
mm/internal.h | 5 ++-
mm/mmap.c | 76 ++++++++++++++++++++++++++++++++++++++--
3 files changed, 78 insertions(+), 4 deletions(-)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6a6159e11a3f..9af6694cb95d 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -287,6 +287,7 @@ struct vm_area_struct {
#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
atomic_t vm_ref_count;
+ struct rcu_head vm_rcu;
#endif
struct rb_node vm_rb;
diff --git a/mm/internal.h b/mm/internal.h
index 302382bed406..1e368e4afe3c 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -55,7 +55,10 @@ static inline void put_vma(struct vm_area_struct *vma)
__free_vma(vma);
}
-#else
+extern struct vm_area_struct *find_vma_rcu(struct mm_struct *mm,
+ unsigned long addr);
+
+#else /* CONFIG_SPECULATIVE_PAGE_FAULT */
static inline void get_vma(struct vm_area_struct *vma)
{
diff --git a/mm/mmap.c b/mm/mmap.c
index c106440dcae7..34bf261dc2c8 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -179,6 +179,18 @@ static inline void mm_write_sequnlock(struct mm_struct *mm)
{
write_sequnlock(&mm->mm_seq);
}
+
+static void __vm_rcu_put(struct rcu_head *head)
+{
+ struct vm_area_struct *vma = container_of(head, struct vm_area_struct,
+ vm_rcu);
+ put_vma(vma);
+}
+static void vm_rcu_put(struct vm_area_struct *vma)
+{
+ VM_BUG_ON_VMA(!RB_EMPTY_NODE(&vma->vm_rb), vma);
+ call_rcu(&vma->vm_rcu, __vm_rcu_put);
+}
#else
static inline void mm_write_seqlock(struct mm_struct *mm)
{
@@ -190,6 +202,8 @@ static inline void mm_write_sequnlock(struct mm_struct *mm)
void __free_vma(struct vm_area_struct *vma)
{
+ if (IS_ENABLED(CONFIG_SPECULATIVE_PAGE_FAULT))
+ VM_BUG_ON_VMA(!RB_EMPTY_NODE(&vma->vm_rb), vma);
mpol_put(vma_policy(vma));
vm_area_free(vma);
}
@@ -197,11 +211,24 @@ void __free_vma(struct vm_area_struct *vma)
/*
* Close a vm structure and free it, returning the next.
*/
-static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
+static struct vm_area_struct *__remove_vma(struct vm_area_struct *vma)
{
struct vm_area_struct *next = vma->vm_next;
might_sleep();
+ if (IS_ENABLED(CONFIG_SPECULATIVE_PAGE_FAULT) &&
+ !RB_EMPTY_NODE(&vma->vm_rb)) {
+ /*
+ * If the VMA is still linked in the RB tree, we must release
+ * that reference by calling put_vma().
+ * This should only happen when called from exit_mmap().
+ * We forcely clear the node to satisfy the chec in
+ * __free_vma(). This is safe since the RB tree is not walked
+ * anymore.
+ */
+ RB_CLEAR_NODE(&vma->vm_rb);
+ put_vma(vma);
+ }
if (vma->vm_ops && vma->vm_ops->close)
vma->vm_ops->close(vma);
if (vma->vm_file)
@@ -211,6 +238,13 @@ static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
return next;
}
+static struct vm_area_struct *remove_vma(struct vm_area_struct *vma)
+{
+ if (IS_ENABLED(CONFIG_SPECULATIVE_PAGE_FAULT))
+ VM_BUG_ON_VMA(!RB_EMPTY_NODE(&vma->vm_rb), vma);
+ return __remove_vma(vma);
+}
+
static int do_brk_flags(unsigned long addr, unsigned long request, unsigned long flags,
struct list_head *uf);
SYSCALL_DEFINE1(brk, unsigned long, brk)
@@ -475,7 +509,7 @@ static inline void vma_rb_insert(struct vm_area_struct *vma,
/* All rb_subtree_gap values must be consistent prior to insertion */
validate_mm_rb(root, NULL);
-
+ get_vma(vma);
rb_insert_augmented(&vma->vm_rb, root, &vma_gap_callbacks);
}
@@ -491,6 +525,14 @@ static void __vma_rb_erase(struct vm_area_struct *vma, struct mm_struct *mm)
mm_write_seqlock(mm);
rb_erase_augmented(&vma->vm_rb, root, &vma_gap_callbacks);
mm_write_sequnlock(mm); /* wmb */
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+ /*
+ * Ensure the removal is complete before clearing the node.
+ * Matched by vma_has_changed()/handle_speculative_fault().
+ */
+ RB_CLEAR_NODE(&vma->vm_rb);
+ vm_rcu_put(vma);
+#endif
}
static __always_inline void vma_rb_erase_ignore(struct vm_area_struct *vma,
@@ -2331,6 +2373,34 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr)
EXPORT_SYMBOL(find_vma);
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+/*
+ * Like find_vma() but under the protection of RCU and the mm sequence counter.
+ * The vma returned has to be relaesed by the caller through the call to
+ * put_vma()
+ */
+struct vm_area_struct *find_vma_rcu(struct mm_struct *mm, unsigned long addr)
+{
+ struct vm_area_struct *vma = NULL;
+ unsigned int seq;
+
+ do {
+ if (vma)
+ put_vma(vma);
+
+ seq = read_seqbegin(&mm->mm_seq);
+
+ rcu_read_lock();
+ vma = find_vma(mm, addr);
+ if (vma)
+ get_vma(vma);
+ rcu_read_unlock();
+ } while (read_seqretry(&mm->mm_seq, seq));
+
+ return vma;
+}
+#endif
+
/*
* Same as find_vma, but also return a pointer to the previous VMA in *pprev.
*/
@@ -3231,7 +3301,7 @@ void exit_mmap(struct mm_struct *mm)
while (vma) {
if (vma->vm_flags & VM_ACCOUNT)
nr_accounted += vma_pages(vma);
- vma = remove_vma(vma);
+ vma = __remove_vma(vma);
}
vm_unacct_memory(nr_accounted);
}
--
2.21.0
next prev parent reply other threads:[~2019-04-16 13:46 UTC|newest]
Thread overview: 98+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-04-16 13:44 [PATCH v12 00/31] Speculative page faults Laurent Dufour
2019-04-16 13:44 ` [PATCH v12 01/31] mm: introduce CONFIG_SPECULATIVE_PAGE_FAULT Laurent Dufour
2019-04-18 21:47 ` Jerome Glisse
2019-04-23 15:21 ` Laurent Dufour
2019-04-16 13:44 ` [PATCH v12 02/31] x86/mm: define ARCH_SUPPORTS_SPECULATIVE_PAGE_FAULT Laurent Dufour
2019-04-18 21:48 ` Jerome Glisse
2019-04-16 13:44 ` [PATCH v12 03/31] powerpc/mm: set ARCH_SUPPORTS_SPECULATIVE_PAGE_FAULT Laurent Dufour
2019-04-18 21:49 ` Jerome Glisse
2019-04-16 13:44 ` [PATCH v12 04/31] arm64/mm: define ARCH_SUPPORTS_SPECULATIVE_PAGE_FAULT Laurent Dufour
2019-04-16 14:27 ` Mark Rutland
2019-04-16 14:31 ` Laurent Dufour
2019-04-16 14:41 ` Mark Rutland
2019-04-18 21:51 ` Jerome Glisse
2019-04-23 15:36 ` Laurent Dufour
2019-04-23 16:19 ` Mark Rutland
2019-04-24 10:34 ` Laurent Dufour
2019-04-16 13:44 ` [PATCH v12 05/31] mm: prepare for FAULT_FLAG_SPECULATIVE Laurent Dufour
2019-04-18 22:04 ` Jerome Glisse
2019-04-23 15:45 ` Laurent Dufour
2019-04-16 13:44 ` [PATCH v12 06/31] mm: introduce pte_spinlock " Laurent Dufour
2019-04-18 22:05 ` Jerome Glisse
2019-04-16 13:44 ` [PATCH v12 07/31] mm: make pte_unmap_same compatible with SPF Laurent Dufour
2019-04-18 22:10 ` Jerome Glisse
2019-04-23 15:43 ` Matthew Wilcox
2019-04-23 15:47 ` Laurent Dufour
2019-04-16 13:44 ` [PATCH v12 08/31] mm: introduce INIT_VMA() Laurent Dufour
2019-04-18 22:22 ` Jerome Glisse
2019-04-16 13:45 ` [PATCH v12 09/31] mm: VMA sequence count Laurent Dufour
2019-04-18 22:48 ` Jerome Glisse
2019-04-19 15:45 ` Laurent Dufour
2019-04-22 15:51 ` Jerome Glisse
2019-04-16 13:45 ` [PATCH v12 10/31] mm: protect VMA modifications using " Laurent Dufour
2019-04-22 19:43 ` Jerome Glisse
2019-04-16 13:45 ` [PATCH v12 11/31] mm: protect mremap() against SPF hanlder Laurent Dufour
2019-04-22 19:51 ` Jerome Glisse
2019-04-23 15:51 ` Laurent Dufour
2019-04-16 13:45 ` [PATCH v12 12/31] mm: protect SPF handler against anon_vma changes Laurent Dufour
2019-04-22 19:53 ` Jerome Glisse
2019-04-16 13:45 ` [PATCH v12 13/31] mm: cache some VMA fields in the vm_fault structure Laurent Dufour
2019-04-22 20:06 ` Jerome Glisse
2019-04-16 13:45 ` [PATCH v12 14/31] mm/migrate: Pass vm_fault pointer to migrate_misplaced_page() Laurent Dufour
2019-04-22 20:09 ` Jerome Glisse
2019-04-16 13:45 ` [PATCH v12 15/31] mm: introduce __lru_cache_add_active_or_unevictable Laurent Dufour
2019-04-22 20:11 ` Jerome Glisse
2019-04-16 13:45 ` [PATCH v12 16/31] mm: introduce __vm_normal_page() Laurent Dufour
2019-04-22 20:15 ` Jerome Glisse
2019-04-16 13:45 ` [PATCH v12 17/31] mm: introduce __page_add_new_anon_rmap() Laurent Dufour
2019-04-22 20:18 ` Jerome Glisse
2019-04-16 13:45 ` [PATCH v12 18/31] mm: protect against PTE changes done by dup_mmap() Laurent Dufour
2019-04-22 20:32 ` Jerome Glisse
2019-04-24 10:33 ` Laurent Dufour
2019-04-16 13:45 ` [PATCH v12 19/31] mm: protect the RB tree with a sequence lock Laurent Dufour
2019-04-22 20:33 ` Jerome Glisse
2019-04-16 13:45 ` [PATCH v12 20/31] mm: introduce vma reference counter Laurent Dufour
2019-04-22 20:36 ` Jerome Glisse
2019-04-24 14:26 ` Laurent Dufour
2019-04-16 13:45 ` Laurent Dufour [this message]
2019-04-22 20:57 ` [PATCH v12 21/31] mm: Introduce find_vma_rcu() Jerome Glisse
2019-04-24 14:39 ` Laurent Dufour
2019-04-23 9:27 ` Peter Zijlstra
2019-04-23 18:13 ` Davidlohr Bueso
2019-04-24 7:57 ` Laurent Dufour
2019-04-16 13:45 ` [PATCH v12 22/31] mm: provide speculative fault infrastructure Laurent Dufour
2019-04-22 21:26 ` Jerome Glisse
2019-04-24 14:56 ` Laurent Dufour
2019-04-24 15:13 ` Jerome Glisse
2019-04-16 13:45 ` [PATCH v12 23/31] mm: don't do swap readahead during speculative page fault Laurent Dufour
2019-04-22 21:36 ` Jerome Glisse
2019-04-24 14:57 ` Laurent Dufour
2019-04-16 13:45 ` [PATCH v12 24/31] mm: adding speculative page fault failure trace events Laurent Dufour
2019-04-16 13:45 ` [PATCH v12 25/31] perf: add a speculative page fault sw event Laurent Dufour
2019-04-16 13:45 ` [PATCH v12 26/31] perf tools: add support for the SPF perf event Laurent Dufour
2019-04-16 13:45 ` [PATCH v12 27/31] mm: add speculative page fault vmstats Laurent Dufour
2019-04-16 13:45 ` [PATCH v12 28/31] x86/mm: add speculative pagefault handling Laurent Dufour
2019-04-16 13:45 ` [PATCH v12 29/31] powerpc/mm: add speculative page fault Laurent Dufour
2019-04-16 13:45 ` [PATCH v12 30/31] arm64/mm: " Laurent Dufour
2019-04-16 13:45 ` [PATCH v12 31/31] mm: Add a speculative page fault switch in sysctl Laurent Dufour
2019-04-22 21:29 ` [PATCH v12 00/31] Speculative page faults Michel Lespinasse
2019-04-23 9:38 ` Peter Zijlstra
2019-04-24 7:33 ` Laurent Dufour
2019-04-27 1:53 ` Michel Lespinasse
2019-04-23 10:47 ` Michal Hocko
2019-04-23 12:41 ` Matthew Wilcox
2019-04-23 12:48 ` Peter Zijlstra
2019-04-23 13:42 ` Michal Hocko
2019-04-24 18:01 ` Laurent Dufour
2019-04-27 6:00 ` Michel Lespinasse
2019-04-23 11:35 ` Anshuman Khandual
2019-06-06 6:51 ` Haiyan Song
2019-06-14 8:37 ` Laurent Dufour
2019-06-14 8:44 ` Laurent Dufour
2019-06-20 8:19 ` Haiyan Song
2020-07-06 9:25 ` Chinwen Chang
2020-07-06 12:27 ` Laurent Dufour
2020-07-07 5:31 ` Chinwen Chang
2020-12-14 2:03 ` Joel Fernandes
2020-12-14 9:36 ` Laurent Dufour
2020-12-14 18:10 ` Joel Fernandes
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=20190416134522.17540-22-ldufour@linux.ibm.com \
--to=ldufour@linux.ibm.com \
--cc=aarcange@redhat.com \
--cc=ak@linux.intel.com \
--cc=akpm@linux-foundation.org \
--cc=alexei.starovoitov@gmail.com \
--cc=aneesh.kumar@linux.ibm.com \
--cc=benh@kernel.crashing.org \
--cc=bsingharora@gmail.com \
--cc=daniel.m.jordan@oracle.com \
--cc=dave@stgolabs.net \
--cc=haiyanx.song@intel.com \
--cc=haren@linux.vnet.ibm.com \
--cc=hpa@zytor.com \
--cc=jack@suse.cz \
--cc=jglisse@redhat.com \
--cc=kemi.wang@intel.com \
--cc=kirill@shutemov.name \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=mhocko@kernel.org \
--cc=minchan@kernel.org \
--cc=mingo@redhat.com \
--cc=mpe@ellerman.id.au \
--cc=npiggin@gmail.com \
--cc=opensource.ganesh@gmail.com \
--cc=paulmck@linux.vnet.ibm.com \
--cc=paulus@samba.org \
--cc=peterz@infradead.org \
--cc=punitagrawal@gmail.com \
--cc=rientjes@google.com \
--cc=rppt@linux.ibm.com \
--cc=sergey.senozhatsky.work@gmail.com \
--cc=sergey.senozhatsky@gmail.com \
--cc=sj38.park@gmail.com \
--cc=tglx@linutronix.de \
--cc=tim.c.chen@linux.intel.com \
--cc=vinayakm.list@gmail.com \
--cc=walken@google.com \
--cc=will.deacon@arm.com \
--cc=willy@infradead.org \
--cc=x86@kernel.org \
--cc=yang.shi@linux.alibaba.com \
--cc=zhongjiang@huawei.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).