From: Andrii Nakryiko <andrii.nakryiko@gmail.com>
To: Suren Baghdasaryan <surenb@google.com>
Cc: akpm@linux-foundation.org, peterz@infradead.org,
linux-kernel@vger.kernel.org, linux-mm@kvack.org
Subject: Re: [RFC 1/1] mm: introduce mmap_lock_speculation_{start|end}
Date: Thu, 8 Aug 2024 13:18:46 -0700 [thread overview]
Message-ID: <CAEf4BzaocU-CQsFZ=s5gDM6XQ0Foss_HroFsPUesBn=qgJCprg@mail.gmail.com> (raw)
In-Reply-To: <20240807182325.2585582-1-surenb@google.com>
On Wed, Aug 7, 2024 at 11:23 AM Suren Baghdasaryan <surenb@google.com> wrote:
>
> Add helper functions to speculatively perform operations without
> read-locking mmap_lock, expecting that mmap_lock will not be
> write-locked and mm is not modified from under us.
>
> Signed-off-by: Suren Baghdasaryan <surenb@google.com>
> Suggested-by: Peter Zijlstra <peterz@infradead.org>
> Cc: Andrii Nakryiko <andrii.nakryiko@gmail.com>
> ---
This change makes sense and makes mm's seq a bit more useful and
meaningful. I've also tested it locally with uprobe stress-test, and
it seems to work great, I haven't run into any problems with a
multi-hour stress test run so far. Thanks!
Acked-by: Andrii Nakryiko <andrii@kernel.org>
> Discussion [1] follow-up. If proves to be useful can be included in that
> patchset. Based on mm-unstable.
>
> [1] https://lore.kernel.org/all/20240730134605.GO33588@noisy.programming.kicks-ass.net/
>
> include/linux/mm_types.h | 3 +++
> include/linux/mmap_lock.h | 53 +++++++++++++++++++++++++++++++--------
> kernel/fork.c | 3 ---
> 3 files changed, 46 insertions(+), 13 deletions(-)
>
> diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
> index 003619fab20e..a426e6ced604 100644
> --- a/include/linux/mm_types.h
> +++ b/include/linux/mm_types.h
> @@ -887,6 +887,9 @@ struct mm_struct {
> * Roughly speaking, incrementing the sequence number is
> * equivalent to releasing locks on VMAs; reading the sequence
> * number can be part of taking a read lock on a VMA.
> + * Incremented every time mmap_lock is write-locked/unlocked.
> + * Initialized to 0, therefore odd values indicate mmap_lock
> + * is write-locked and even values that it's released.
> *
> * Can be modified under write mmap_lock using RELEASE
> * semantics.
> diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
> index de9dc20b01ba..5410ce741d75 100644
> --- a/include/linux/mmap_lock.h
> +++ b/include/linux/mmap_lock.h
> @@ -71,15 +71,12 @@ static inline void mmap_assert_write_locked(const struct mm_struct *mm)
> }
>
> #ifdef CONFIG_PER_VMA_LOCK
> -/*
> - * Drop all currently-held per-VMA locks.
> - * This is called from the mmap_lock implementation directly before releasing
> - * a write-locked mmap_lock (or downgrading it to read-locked).
> - * This should normally NOT be called manually from other places.
> - * If you want to call this manually anyway, keep in mind that this will release
> - * *all* VMA write locks, including ones from further up the stack.
> - */
> -static inline void vma_end_write_all(struct mm_struct *mm)
> +static inline void init_mm_lock_seq(struct mm_struct *mm)
> +{
> + mm->mm_lock_seq = 0;
> +}
> +
> +static inline void inc_mm_lock_seq(struct mm_struct *mm)
> {
> mmap_assert_write_locked(mm);
> /*
> @@ -91,19 +88,52 @@ static inline void vma_end_write_all(struct mm_struct *mm)
> */
> smp_store_release(&mm->mm_lock_seq, mm->mm_lock_seq + 1);
> }
> +
> +static inline bool mmap_lock_speculation_start(struct mm_struct *mm, int *seq)
> +{
> + /* Pairs with RELEASE semantics in inc_mm_lock_seq(). */
> + *seq = smp_load_acquire(&mm->mm_lock_seq);
> + /* Allow speculation if mmap_lock is not write-locked */
> + return (*seq & 1) == 0;
> +}
> +
> +static inline bool mmap_lock_speculation_end(struct mm_struct *mm, int seq)
> +{
> + /* Pairs with RELEASE semantics in inc_mm_lock_seq(). */
> + return seq == smp_load_acquire(&mm->mm_lock_seq);
> +}
> +
> #else
> -static inline void vma_end_write_all(struct mm_struct *mm) {}
> +static inline void init_mm_lock_seq(struct mm_struct *mm) {}
> +static inline void inc_mm_lock_seq(struct mm_struct *mm) {}
> +static inline bool mmap_lock_speculation_start(struct mm_struct *mm, int *seq) { return false; }
> +static inline bool mmap_lock_speculation_end(struct mm_struct *mm, int seq) { return false; }
> #endif
>
> +/*
> + * Drop all currently-held per-VMA locks.
> + * This is called from the mmap_lock implementation directly before releasing
> + * a write-locked mmap_lock (or downgrading it to read-locked).
> + * This should normally NOT be called manually from other places.
> + * If you want to call this manually anyway, keep in mind that this will release
> + * *all* VMA write locks, including ones from further up the stack.
> + */
> +static inline void vma_end_write_all(struct mm_struct *mm)
> +{
> + inc_mm_lock_seq(mm);
> +}
> +
> static inline void mmap_init_lock(struct mm_struct *mm)
> {
> init_rwsem(&mm->mmap_lock);
> + init_mm_lock_seq(mm);
> }
>
> static inline void mmap_write_lock(struct mm_struct *mm)
> {
> __mmap_lock_trace_start_locking(mm, true);
> down_write(&mm->mmap_lock);
> + inc_mm_lock_seq(mm);
> __mmap_lock_trace_acquire_returned(mm, true, true);
> }
>
> @@ -111,6 +141,7 @@ static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass)
> {
> __mmap_lock_trace_start_locking(mm, true);
> down_write_nested(&mm->mmap_lock, subclass);
> + inc_mm_lock_seq(mm);
> __mmap_lock_trace_acquire_returned(mm, true, true);
> }
>
> @@ -120,6 +151,8 @@ static inline int mmap_write_lock_killable(struct mm_struct *mm)
>
> __mmap_lock_trace_start_locking(mm, true);
> ret = down_write_killable(&mm->mmap_lock);
> + if (!ret)
> + inc_mm_lock_seq(mm);
> __mmap_lock_trace_acquire_returned(mm, true, ret == 0);
> return ret;
> }
> diff --git a/kernel/fork.c b/kernel/fork.c
> index 3d590e51ce84..73e37af8a24d 100644
> --- a/kernel/fork.c
> +++ b/kernel/fork.c
> @@ -1259,9 +1259,6 @@ 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
> - mm->mm_lock_seq = 0;
> -#endif
> mm_pgtables_bytes_init(mm);
> mm->map_count = 0;
> mm->locked_vm = 0;
>
> base-commit: 98808d08fc0f78ee638e0c0a88020fbbaf581ec6
> --
> 2.46.0.rc2.264.g509ed76dc8-goog
>
next parent reply other threads:[~2024-08-08 20:19 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20240807182325.2585582-1-surenb@google.com>
2024-08-08 20:18 ` Andrii Nakryiko [this message]
2024-08-08 21:02 ` Suren Baghdasaryan
2024-08-08 21:11 ` Andrii Nakryiko
2024-08-08 21:42 ` Jann Horn
2024-08-08 22:05 ` Andrii Nakryiko
2024-08-08 22:16 ` Jann Horn
2024-08-08 22:36 ` Andrii Nakryiko
2024-08-08 23:26 ` Suren Baghdasaryan
2024-08-09 15:20 ` Jann Horn
2024-08-09 16:39 ` Andrii Nakryiko
2024-08-09 16:55 ` 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='CAEf4BzaocU-CQsFZ=s5gDM6XQ0Foss_HroFsPUesBn=qgJCprg@mail.gmail.com' \
--to=andrii.nakryiko@gmail.com \
--cc=akpm@linux-foundation.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=peterz@infradead.org \
--cc=surenb@google.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