From: Suren Baghdasaryan <surenb@google.com>
To: akpm@linux-foundation.org
Cc: michel@lespinasse.org, jglisse@google.com, mhocko@suse.com,
vbabka@suse.cz, hannes@cmpxchg.org, mgorman@suse.de,
dave@stgolabs.net, willy@infradead.org, liam.howlett@oracle.com,
peterz@infradead.org, ldufour@linux.ibm.com,
laurent.dufour@fr.ibm.com, paulmck@kernel.org, luto@kernel.org,
songliubraving@fb.com, peterx@redhat.com, david@redhat.com,
dhowells@redhat.com, hughd@google.com, bigeasy@linutronix.de,
kent.overstreet@linux.dev, rientjes@google.com,
axelrasmussen@google.com, joelaf@google.com, minchan@google.com,
surenb@google.com, kernel-team@android.com, linux-mm@kvack.org,
linux-arm-kernel@lists.infradead.org,
linuxppc-dev@lists.ozlabs.org, x86@kernel.org,
linux-kernel@vger.kernel.org
Subject: [RFC PATCH RESEND 05/28] mm: add per-VMA lock and helper functions to control it
Date: Thu, 1 Sep 2022 10:34:53 -0700 [thread overview]
Message-ID: <20220901173516.702122-6-surenb@google.com> (raw)
In-Reply-To: <20220901173516.702122-1-surenb@google.com>
Introduce a per-VMA rw_semaphore to be used during page fault handling
instead of mmap_lock. Because there are cases when multiple VMAs need
to be exclusively locked during VMA tree modifications, instead of the
usual lock/unlock patter we mark a VMA as locked by taking per-VMA lock
exclusively and setting vma->lock_seq to the current mm->lock_seq. When
mmap_write_lock holder is done with all modifications and drops mmap_lock,
it will increment mm->lock_seq, effectively unlocking all VMAs marked as
locked.
Signed-off-by: Suren Baghdasaryan <surenb@google.com>
---
include/linux/mm.h | 78 +++++++++++++++++++++++++++++++++++++++
include/linux/mm_types.h | 7 ++++
include/linux/mmap_lock.h | 13 +++++++
kernel/fork.c | 4 ++
mm/init-mm.c | 3 ++
5 files changed, 105 insertions(+)
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 7d322a979455..476bf936c5f0 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -611,6 +611,83 @@ struct vm_operations_struct {
unsigned long addr);
};
+#ifdef CONFIG_PER_VMA_LOCK
+static inline void vma_init_lock(struct vm_area_struct *vma)
+{
+ init_rwsem(&vma->lock);
+ vma->vm_lock_seq = -1;
+}
+
+static inline void vma_mark_locked(struct vm_area_struct *vma)
+{
+ int mm_lock_seq;
+
+ mmap_assert_write_locked(vma->vm_mm);
+
+ /*
+ * current task is holding mmap_write_lock, both vma->vm_lock_seq and
+ * mm->mm_lock_seq can't be concurrently modified.
+ */
+ mm_lock_seq = READ_ONCE(vma->vm_mm->mm_lock_seq);
+ if (vma->vm_lock_seq == mm_lock_seq)
+ return;
+
+ down_write(&vma->lock);
+ vma->vm_lock_seq = mm_lock_seq;
+ up_write(&vma->lock);
+}
+
+static inline bool vma_read_trylock(struct vm_area_struct *vma)
+{
+ if (unlikely(down_read_trylock(&vma->lock) == 0))
+ return false;
+
+ /*
+ * Overflow might produce false locked result but it's not critical.
+ * False unlocked result is critical but is impossible because we
+ * modify and check vma->vm_lock_seq under vma->lock protection and
+ * mm->mm_lock_seq modification invalidates all existing locks.
+ */
+ if (vma->vm_lock_seq == READ_ONCE(vma->vm_mm->mm_lock_seq)) {
+ up_read(&vma->lock);
+ return false;
+ }
+ return true;
+}
+
+static inline void vma_read_unlock(struct vm_area_struct *vma)
+{
+ up_read(&vma->lock);
+}
+
+static inline void vma_assert_locked(struct vm_area_struct *vma)
+{
+ lockdep_assert_held(&vma->lock);
+ VM_BUG_ON_VMA(!rwsem_is_locked(&vma->lock), vma);
+}
+
+static inline void vma_assert_write_locked(struct vm_area_struct *vma, int pos)
+{
+ mmap_assert_write_locked(vma->vm_mm);
+ /*
+ * current task is holding mmap_write_lock, both vma->vm_lock_seq and
+ * mm->mm_lock_seq can't be concurrently modified.
+ */
+ VM_BUG_ON_VMA(vma->vm_lock_seq != READ_ONCE(vma->vm_mm->mm_lock_seq), vma);
+}
+
+#else /* CONFIG_PER_VMA_LOCK */
+
+static inline void vma_init_lock(struct vm_area_struct *vma) {}
+static inline void vma_mark_locked(struct vm_area_struct *vma) {}
+static inline bool vma_read_trylock(struct vm_area_struct *vma)
+ { return false; }
+static inline void vma_read_unlock(struct vm_area_struct *vma) {}
+static inline void vma_assert_locked(struct vm_area_struct *vma) {}
+static inline void vma_assert_write_locked(struct vm_area_struct *vma, int pos) {}
+
+#endif /* CONFIG_PER_VMA_LOCK */
+
static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm)
{
static const struct vm_operations_struct dummy_vm_ops = {};
@@ -619,6 +696,7 @@ static inline void vma_init(struct vm_area_struct *vma, struct mm_struct *mm)
vma->vm_mm = mm;
vma->vm_ops = &dummy_vm_ops;
INIT_LIST_HEAD(&vma->anon_vma_chain);
+ vma_init_lock(vma);
}
static inline void vma_set_anonymous(struct vm_area_struct *vma)
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index bed25ef7c994..6a03f59c1e78 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -486,6 +486,10 @@ struct vm_area_struct {
struct mempolicy *vm_policy; /* NUMA policy for the VMA */
#endif
struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
+#ifdef CONFIG_PER_VMA_LOCK
+ struct rw_semaphore lock;
+ int vm_lock_seq;
+#endif
} __randomize_layout;
struct kioctx_table;
@@ -567,6 +571,9 @@ struct mm_struct {
* init_mm.mmlist, and are protected
* by mmlist_lock
*/
+#ifdef CONFIG_PER_VMA_LOCK
+ int mm_lock_seq;
+#endif
unsigned long hiwater_rss; /* High-watermark of RSS usage */
diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
index e49ba91bb1f0..a391ae226564 100644
--- a/include/linux/mmap_lock.h
+++ b/include/linux/mmap_lock.h
@@ -72,6 +72,17 @@ static inline void mmap_assert_write_locked(struct mm_struct *mm)
VM_BUG_ON_MM(!rwsem_is_locked(&mm->mmap_lock), mm);
}
+#ifdef CONFIG_PER_VMA_LOCK
+static inline void vma_mark_unlocked_all(struct mm_struct *mm)
+{
+ mmap_assert_write_locked(mm);
+ /* No races during update due to exclusive mmap_lock being held */
+ WRITE_ONCE(mm->mm_lock_seq, mm->mm_lock_seq + 1);
+}
+#else
+static inline void vma_mark_unlocked_all(struct mm_struct *mm) {}
+#endif
+
static inline void mmap_init_lock(struct mm_struct *mm)
{
init_rwsem(&mm->mmap_lock);
@@ -114,12 +125,14 @@ static inline bool mmap_write_trylock(struct mm_struct *mm)
static inline void mmap_write_unlock(struct mm_struct *mm)
{
__mmap_lock_trace_released(mm, true);
+ vma_mark_unlocked_all(mm);
up_write(&mm->mmap_lock);
}
static inline void mmap_write_downgrade(struct mm_struct *mm)
{
__mmap_lock_trace_acquire_returned(mm, false, true);
+ vma_mark_unlocked_all(mm);
downgrade_write(&mm->mmap_lock);
}
diff --git a/kernel/fork.c b/kernel/fork.c
index 614872438393..bfab31ecd11e 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -475,6 +475,7 @@ struct vm_area_struct *vm_area_dup(struct vm_area_struct *orig)
*/
*new = data_race(*orig);
INIT_LIST_HEAD(&new->anon_vma_chain);
+ vma_init_lock(new);
new->vm_next = new->vm_prev = NULL;
dup_anon_vma_name(orig, new);
}
@@ -1130,6 +1131,9 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
seqcount_init(&mm->write_protect_seq);
mmap_init_lock(mm);
INIT_LIST_HEAD(&mm->mmlist);
+#ifdef CONFIG_PER_VMA_LOCK
+ WRITE_ONCE(mm->mm_lock_seq, 0);
+#endif
mm_pgtables_bytes_init(mm);
mm->map_count = 0;
mm->locked_vm = 0;
diff --git a/mm/init-mm.c b/mm/init-mm.c
index fbe7844d0912..8399f90d631c 100644
--- a/mm/init-mm.c
+++ b/mm/init-mm.c
@@ -37,6 +37,9 @@ struct mm_struct init_mm = {
.page_table_lock = __SPIN_LOCK_UNLOCKED(init_mm.page_table_lock),
.arg_lock = __SPIN_LOCK_UNLOCKED(init_mm.arg_lock),
.mmlist = LIST_HEAD_INIT(init_mm.mmlist),
+#ifdef CONFIG_PER_VMA_LOCK
+ .mm_lock_seq = 0,
+#endif
.user_ns = &init_user_ns,
.cpu_bitmap = CPU_BITS_NONE,
#ifdef CONFIG_IOMMU_SVA
--
2.37.2.789.g6183377224-goog
_______________________________________________
linux-arm-kernel mailing list
linux-arm-kernel@lists.infradead.org
http://lists.infradead.org/mailman/listinfo/linux-arm-kernel
next prev parent reply other threads:[~2022-09-01 18:10 UTC|newest]
Thread overview: 91+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-09-01 17:34 [RFC PATCH RESEND 00/28] per-VMA locks proposal Suren Baghdasaryan
2022-09-01 17:34 ` [RFC PATCH RESEND 01/28] mm: introduce CONFIG_PER_VMA_LOCK Suren Baghdasaryan
2022-09-01 17:34 ` [RFC PATCH RESEND 02/28] mm: rcu safe VMA freeing Suren Baghdasaryan
2022-09-01 17:34 ` [RFC PATCH RESEND 03/28] mm: introduce __find_vma to be used without mmap_lock protection Suren Baghdasaryan
2022-09-01 20:22 ` Kent Overstreet
2022-09-01 23:18 ` Suren Baghdasaryan
2022-09-01 17:34 ` [RFC PATCH RESEND 04/28] mm: move mmap_lock assert function definitions Suren Baghdasaryan
2022-09-01 20:24 ` Kent Overstreet
2022-09-01 20:51 ` Liam Howlett
2022-09-01 23:21 ` Suren Baghdasaryan
2022-09-02 6:23 ` Sebastian Andrzej Siewior
2022-09-02 17:46 ` Suren Baghdasaryan
2022-09-01 17:34 ` Suren Baghdasaryan [this message]
2022-09-06 13:46 ` [RFC PATCH RESEND 05/28] mm: add per-VMA lock and helper functions to control it Laurent Dufour
2022-09-06 17:24 ` Suren Baghdasaryan
2022-09-01 17:34 ` [RFC PATCH RESEND 06/28] mm: mark VMA as locked whenever vma->vm_flags are modified Suren Baghdasaryan
2022-09-06 14:26 ` Laurent Dufour
2022-09-06 19:00 ` Suren Baghdasaryan
2022-09-06 20:00 ` Liam Howlett
2022-09-06 20:13 ` Suren Baghdasaryan
2022-09-01 17:34 ` [RFC PATCH RESEND 07/28] kernel/fork: mark VMAs as locked before copying pages during fork Suren Baghdasaryan
2022-09-06 14:37 ` Laurent Dufour
2022-09-08 23:57 ` Suren Baghdasaryan
2022-09-09 13:27 ` Laurent Dufour
2022-09-09 16:29 ` Suren Baghdasaryan
2022-09-01 17:34 ` [RFC PATCH RESEND 08/28] mm/khugepaged: mark VMA as locked while collapsing a hugepage Suren Baghdasaryan
2022-09-06 14:43 ` Laurent Dufour
2022-09-09 0:15 ` Suren Baghdasaryan
2022-09-01 17:34 ` [RFC PATCH RESEND 09/28] mm/mempolicy: mark VMA as locked when changing protection policy Suren Baghdasaryan
2022-09-06 14:47 ` Laurent Dufour
2022-09-09 0:27 ` Suren Baghdasaryan
2022-09-01 17:34 ` [RFC PATCH RESEND 10/28] mm/mmap: mark VMAs as locked in vma_adjust Suren Baghdasaryan
2022-09-06 15:35 ` Laurent Dufour
2022-09-09 0:51 ` Suren Baghdasaryan
2022-09-09 15:52 ` Laurent Dufour
2022-09-01 17:34 ` [RFC PATCH RESEND 11/28] mm/mmap: mark VMAs as locked before merging or splitting them Suren Baghdasaryan
2022-09-06 15:44 ` Laurent Dufour
2022-09-01 17:35 ` [RFC PATCH RESEND 12/28] mm/mremap: mark VMA as locked while remapping it to a new address range Suren Baghdasaryan
2022-09-06 16:09 ` Laurent Dufour
2022-09-01 17:35 ` [RFC PATCH RESEND 13/28] mm: conditionally mark VMA as locked in free_pgtables and unmap_page_range Suren Baghdasaryan
2022-09-09 10:33 ` Laurent Dufour
2022-09-09 16:43 ` Suren Baghdasaryan
2022-09-01 17:35 ` [RFC PATCH RESEND 14/28] mm: mark VMAs as locked before isolating them Suren Baghdasaryan
2022-09-09 13:35 ` Laurent Dufour
2022-09-09 16:28 ` Suren Baghdasaryan
2022-09-01 17:35 ` [RFC PATCH RESEND 15/28] mm/mmap: mark adjacent VMAs as locked if they can grow into unmapped area Suren Baghdasaryan
2022-09-09 13:43 ` Laurent Dufour
2022-09-09 16:25 ` Suren Baghdasaryan
2022-09-01 17:35 ` [RFC PATCH RESEND 16/28] kernel/fork: assert no VMA readers during its destruction Suren Baghdasaryan
2022-09-09 13:56 ` Laurent Dufour
2022-09-09 16:19 ` Suren Baghdasaryan
2022-09-01 17:35 ` [RFC PATCH RESEND 17/28] mm/mmap: prevent pagefault handler from racing with mmu_notifier registration Suren Baghdasaryan
2022-09-09 14:20 ` Laurent Dufour
2022-09-09 16:12 ` Suren Baghdasaryan
2022-09-01 17:35 ` [RFC PATCH RESEND 18/28] mm: add FAULT_FLAG_VMA_LOCK flag Suren Baghdasaryan
2022-09-09 14:26 ` Laurent Dufour
2022-09-01 17:35 ` [RFC PATCH RESEND 19/28] mm: disallow do_swap_page to handle page faults under VMA lock Suren Baghdasaryan
2022-09-06 19:39 ` Peter Xu
2022-09-06 20:08 ` Suren Baghdasaryan
2022-09-06 20:22 ` Peter Xu
2022-09-07 0:58 ` Suren Baghdasaryan
2022-09-09 14:26 ` Laurent Dufour
2022-09-01 17:35 ` [RFC PATCH RESEND 20/28] mm: introduce per-VMA lock statistics Suren Baghdasaryan
2022-09-09 14:28 ` Laurent Dufour
2022-09-09 16:11 ` Suren Baghdasaryan
2022-09-01 17:35 ` [RFC PATCH RESEND 21/28] mm: introduce find_and_lock_anon_vma to be used from arch-specific code Suren Baghdasaryan
2022-09-09 14:38 ` Laurent Dufour
2022-09-09 16:10 ` Suren Baghdasaryan
2022-09-01 17:35 ` [RFC PATCH RESEND 22/28] x86/mm: try VMA lock-based page fault handling first Suren Baghdasaryan
2022-09-01 17:35 ` [RFC PATCH RESEND 23/28] x86/mm: define ARCH_SUPPORTS_PER_VMA_LOCK Suren Baghdasaryan
2022-09-01 20:20 ` Kent Overstreet
2022-09-01 23:17 ` Suren Baghdasaryan
2022-09-01 17:35 ` [RFC PATCH RESEND 24/28] arm64/mm: try VMA lock-based page fault handling first Suren Baghdasaryan
2022-09-01 17:35 ` [RFC PATCH RESEND 25/28] arm64/mm: define ARCH_SUPPORTS_PER_VMA_LOCK Suren Baghdasaryan
2022-09-01 17:35 ` [RFC PATCH RESEND 26/28] powerc/mm: try VMA lock-based page fault handling first Suren Baghdasaryan
2022-09-01 17:35 ` [RFC PATCH RESEND 27/28] powerpc/mm: define ARCH_SUPPORTS_PER_VMA_LOCK Suren Baghdasaryan
2022-09-01 17:35 ` [RFC PATCH RESEND 28/28] kernel/fork: throttle call_rcu() calls in vm_area_free Suren Baghdasaryan
2022-09-09 15:19 ` Laurent Dufour
2022-09-09 16:02 ` Suren Baghdasaryan
2022-09-09 16:14 ` Laurent Dufour
2022-09-01 20:58 ` [RFC PATCH RESEND 00/28] per-VMA locks proposal Kent Overstreet
2022-09-01 23:26 ` Suren Baghdasaryan
2022-09-11 9:35 ` Vlastimil Babka
2022-09-28 2:28 ` Suren Baghdasaryan
2022-09-29 11:18 ` Vlastimil Babka
2022-09-02 7:42 ` Peter Zijlstra
2022-09-02 14:45 ` Suren Baghdasaryan
2022-09-05 12:32 ` Michal Hocko
2022-09-05 18:32 ` Suren Baghdasaryan
2022-09-05 20:35 ` Kent Overstreet
2022-09-06 15:46 ` Suren Baghdasaryan
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=20220901173516.702122-6-surenb@google.com \
--to=surenb@google.com \
--cc=akpm@linux-foundation.org \
--cc=axelrasmussen@google.com \
--cc=bigeasy@linutronix.de \
--cc=dave@stgolabs.net \
--cc=david@redhat.com \
--cc=dhowells@redhat.com \
--cc=hannes@cmpxchg.org \
--cc=hughd@google.com \
--cc=jglisse@google.com \
--cc=joelaf@google.com \
--cc=kent.overstreet@linux.dev \
--cc=kernel-team@android.com \
--cc=laurent.dufour@fr.ibm.com \
--cc=ldufour@linux.ibm.com \
--cc=liam.howlett@oracle.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=luto@kernel.org \
--cc=mgorman@suse.de \
--cc=mhocko@suse.com \
--cc=michel@lespinasse.org \
--cc=minchan@google.com \
--cc=paulmck@kernel.org \
--cc=peterx@redhat.com \
--cc=peterz@infradead.org \
--cc=rientjes@google.com \
--cc=songliubraving@fb.com \
--cc=vbabka@suse.cz \
--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).