linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Michel Lespinasse <michel@lespinasse.org>
To: Linux-MM <linux-mm@kvack.org>,
	Linux-Kernel <linux-kernel@vger.kernel.org>
Cc: Laurent Dufour <ldufour@linux.ibm.com>,
	Peter Zijlstra <peterz@infradead.org>,
	Michal Hocko <mhocko@suse.com>,
	Matthew Wilcox <willy@infradead.org>,
	Rik van Riel <riel@surriel.com>,
	Paul McKenney <paulmck@kernel.org>,
	Andrew Morton <akpm@linux-foundation.org>,
	Suren Baghdasaryan <surenb@google.com>,
	Joel Fernandes <joelaf@google.com>,
	Andy Lutomirski <luto@kernel.org>,
	Michel Lespinasse <michel@lespinasse.org>
Subject: [PATCH 10/29] mm: add per-mm mmap sequence counter for speculative page fault handling.
Date: Fri, 30 Apr 2021 12:52:11 -0700	[thread overview]
Message-ID: <20210430195232.30491-11-michel@lespinasse.org> (raw)
In-Reply-To: <20210430195232.30491-1-michel@lespinasse.org>

The counter's write side is hooked into the existing mmap locking API:
mmap_write_lock() increments the counter to the next (odd) value, and
mmap_write_unlock() increments it again to the next (even) value.

The counter's speculative read side is supposed to be used as follows:

seq = mmap_seq_read_start(mm);
if (seq & 1)
	goto fail;
.... speculative handling here ....
if (!mmap_seq_read_check(mm, seq)
	goto fail;

This API guarantees that, if none of the "fail" tests abort
speculative execution, the speculative code section did not run
concurrently with any mmap writer.

This is very similar to a seqlock, but both the writer and speculative
readers are allowed to block. In the fail case, the speculative reader
does not spin on the sequence counter; instead it should fall back to
a different mechanism such as grabbing the mmap lock read side.

Signed-off-by: Michel Lespinasse <michel@lespinasse.org>
---
 include/linux/mm_types.h  |  4 +++
 include/linux/mmap_lock.h | 58 +++++++++++++++++++++++++++++++++++++--
 2 files changed, 60 insertions(+), 2 deletions(-)

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 6613b26a8894..70882e628908 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -461,6 +461,10 @@ struct mm_struct {
 					     * counters
 					     */
 		struct rw_semaphore mmap_lock;
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+		unsigned long mmap_seq;
+#endif
+
 
 		struct list_head mmlist; /* List of maybe swapped mm's.	These
 					  * are globally strung together off
diff --git a/include/linux/mmap_lock.h b/include/linux/mmap_lock.h
index 8ff276a7560e..8f4eca2d0f43 100644
--- a/include/linux/mmap_lock.h
+++ b/include/linux/mmap_lock.h
@@ -8,8 +8,16 @@
 #include <linux/tracepoint-defs.h>
 #include <linux/types.h>
 
-#define MMAP_LOCK_INITIALIZER(name) \
-	.mmap_lock = __RWSEM_INITIALIZER((name).mmap_lock),
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+#define MMAP_LOCK_SEQ_INITIALIZER(name) \
+	.mmap_seq = 0,
+#else
+#define MMAP_LOCK_SEQ_INITIALIZER(name)
+#endif
+
+#define MMAP_LOCK_INITIALIZER(name)				\
+	.mmap_lock = __RWSEM_INITIALIZER((name).mmap_lock),	\
+	MMAP_LOCK_SEQ_INITIALIZER(name)
 
 DECLARE_TRACEPOINT(mmap_lock_start_locking);
 DECLARE_TRACEPOINT(mmap_lock_acquire_returned);
@@ -63,13 +71,52 @@ static inline void __mmap_lock_trace_released(struct mm_struct *mm, bool write)
 static inline void mmap_init_lock(struct mm_struct *mm)
 {
 	init_rwsem(&mm->mmap_lock);
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+	mm->mmap_seq = 0;
+#endif
 }
 
+static inline void __mmap_seq_write_lock(struct mm_struct *mm)
+{
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+	VM_BUG_ON_MM(mm->mmap_seq & 1, mm);
+	mm->mmap_seq++;
+	smp_wmb();
+#endif
+}
+
+static inline void __mmap_seq_write_unlock(struct mm_struct *mm)
+{
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+	smp_wmb();
+	mm->mmap_seq++;
+	VM_BUG_ON_MM(mm->mmap_seq & 1, mm);
+#endif
+}
+
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+static inline unsigned long mmap_seq_read_start(struct mm_struct *mm)
+{
+	unsigned long seq;
+
+	seq = READ_ONCE(mm->mmap_seq);
+	smp_rmb();
+	return seq;
+}
+
+static inline bool mmap_seq_read_check(struct mm_struct *mm, unsigned long seq)
+{
+	smp_rmb();
+	return seq == READ_ONCE(mm->mmap_seq);
+}
+#endif
+
 static inline void mmap_write_lock(struct mm_struct *mm)
 {
 	__mmap_lock_trace_start_locking(mm, true);
 	down_write(&mm->mmap_lock);
 	__mmap_lock_trace_acquire_returned(mm, true, true);
+	__mmap_seq_write_lock(mm);
 }
 
 static inline void mmap_write_lock_nested(struct mm_struct *mm, int subclass)
@@ -77,6 +124,7 @@ 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);
 	__mmap_lock_trace_acquire_returned(mm, true, true);
+	__mmap_seq_write_lock(mm);
 }
 
 static inline int mmap_write_lock_killable(struct mm_struct *mm)
@@ -86,6 +134,8 @@ static inline int mmap_write_lock_killable(struct mm_struct *mm)
 	__mmap_lock_trace_start_locking(mm, true);
 	error = down_write_killable(&mm->mmap_lock);
 	__mmap_lock_trace_acquire_returned(mm, true, !error);
+	if (likely(!error))
+		__mmap_seq_write_lock(mm);
 	return error;
 }
 
@@ -96,17 +146,21 @@ static inline bool mmap_write_trylock(struct mm_struct *mm)
 	__mmap_lock_trace_start_locking(mm, true);
 	ok = down_write_trylock(&mm->mmap_lock) != 0;
 	__mmap_lock_trace_acquire_returned(mm, true, ok);
+	if (likely(ok))
+		__mmap_seq_write_lock(mm);
 	return ok;
 }
 
 static inline void mmap_write_unlock(struct mm_struct *mm)
 {
+	__mmap_seq_write_unlock(mm);
 	up_write(&mm->mmap_lock);
 	__mmap_lock_trace_released(mm, true);
 }
 
 static inline void mmap_write_downgrade(struct mm_struct *mm)
 {
+	__mmap_seq_write_unlock(mm);
 	downgrade_write(&mm->mmap_lock);
 	__mmap_lock_trace_acquire_returned(mm, false, true);
 }
-- 
2.20.1



  parent reply	other threads:[~2021-04-30 19:52 UTC|newest]

Thread overview: 49+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
     [not found] <20210430195232.30491-1-michel@lespinasse.org>
2021-04-30 19:52 ` [PATCH 01/29] mm: export dump_mm Michel Lespinasse
2021-04-30 19:52 ` [PATCH 02/29] mmap locking API: mmap_lock_is_contended returns a bool Michel Lespinasse
2021-04-30 19:52 ` [PATCH 03/29] mmap locking API: name the return values Michel Lespinasse
2021-04-30 19:52 ` [PATCH 04/29] do_anonymous_page: use update_mmu_tlb() Michel Lespinasse
2021-06-10  0:38   ` Suren Baghdasaryan
2021-04-30 19:52 ` [PATCH 05/29] do_anonymous_page: reduce code duplication Michel Lespinasse
2021-04-30 19:52 ` [PATCH 06/29] mm: introduce CONFIG_SPECULATIVE_PAGE_FAULT Michel Lespinasse
2021-04-30 19:52 ` [PATCH 07/29] x86/mm: define ARCH_SUPPORTS_SPECULATIVE_PAGE_FAULT Michel Lespinasse
2021-04-30 19:52 ` [PATCH 08/29] mm: add FAULT_FLAG_SPECULATIVE flag Michel Lespinasse
2021-06-10  0:58   ` Suren Baghdasaryan
2021-04-30 19:52 ` [PATCH 09/29] mm: add do_handle_mm_fault() Michel Lespinasse
2021-04-30 19:52 ` Michel Lespinasse [this message]
2021-04-30 19:52 ` [PATCH 11/29] mm: rcu safe vma freeing Michel Lespinasse
2021-04-30 19:52 ` [PATCH 12/29] x86/mm: attempt speculative mm faults first Michel Lespinasse
2021-04-30 19:52 ` [PATCH 13/29] mm: add speculative_page_walk_begin() and speculative_page_walk_end() Michel Lespinasse
2021-04-30 19:52 ` [PATCH 14/29] mm: refactor __handle_mm_fault() / handle_pte_fault() Michel Lespinasse
2021-04-30 19:52 ` [PATCH 15/29] mm: implement speculative handling in __handle_mm_fault() Michel Lespinasse
2021-04-30 19:52 ` [PATCH 16/29] mm: add pte_map_lock() and pte_spinlock() Michel Lespinasse
2021-04-30 23:33   ` kernel test robot
2021-04-30 23:45   ` kernel test robot
2021-04-30 19:52 ` [PATCH 17/29] mm: implement speculative handling in do_anonymous_page() Michel Lespinasse
2021-04-30 19:52 ` [PATCH 18/29] mm: enable speculative fault handling through do_anonymous_page() Michel Lespinasse
2021-04-30 19:52 ` [PATCH 19/29] mm: implement speculative handling in do_numa_page() Michel Lespinasse
2021-04-30 19:52 ` [PATCH 20/29] mm: enable speculative fault " Michel Lespinasse
2021-04-30 19:52 ` [PATCH 21/29] mm: implement speculative handling in wp_page_copy() Michel Lespinasse
2021-04-30 19:52 ` [PATCH 22/29] mm: implement and enable speculative fault handling in handle_pte_fault() Michel Lespinasse
2021-04-30 19:52 ` [PATCH 23/29] mm: implement speculative handling in do_swap_page() Michel Lespinasse
2021-04-30 19:52 ` [PATCH 24/29] mm: enable speculative fault handling through do_swap_page() Michel Lespinasse
2021-04-30 19:52 ` [PATCH 25/29] mm: disable speculative faults for single threaded user space Michel Lespinasse
2021-04-30 19:52 ` [PATCH 26/29] mm: disable rcu safe vma freeing " Michel Lespinasse
2021-04-30 19:52 ` [PATCH 27/29] mm: anon spf statistics Michel Lespinasse
2021-04-30 22:52   ` kernel test robot
2021-04-30 19:52 ` [PATCH 28/29] arm64/mm: define ARCH_SUPPORTS_SPECULATIVE_PAGE_FAULT Michel Lespinasse
2021-04-30 19:52 ` [PATCH 29/29] arm64/mm: attempt speculative mm faults first Michel Lespinasse
2021-04-30 19:52 ` [PATCH 30/31] powerpc/mm: define ARCH_SUPPORTS_SPECULATIVE_PAGE_FAULT Michel Lespinasse
2021-04-30 19:52 ` [PATCH 31/31] powerpc/mm: attempt speculative mm faults first Michel Lespinasse
2021-04-30 22:46 ` [PATCH 00/29] Speculative page faults (anon vmas only) Michel Lespinasse
2021-05-03 18:11   ` Michel Lespinasse
2021-05-17 17:57     ` Paul E. McKenney
2021-05-20 22:10       ` Suren Baghdasaryan
2021-05-20 23:08         ` Paul E. McKenney
2021-06-01  7:41         ` Michel Lespinasse
2021-06-01 20:18           ` Paul E. McKenney
2021-06-01 20:23         ` Paul E. McKenney
2021-06-14  7:04         ` Michel Lespinasse
2021-05-01 19:56 ` Theodore Ts'o
2021-05-01 21:19   ` Michel Lespinasse
2021-06-17 13:46 ` David Hildenbrand
2021-07-09 10:41   ` David Hildenbrand

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=20210430195232.30491-11-michel@lespinasse.org \
    --to=michel@lespinasse.org \
    --cc=akpm@linux-foundation.org \
    --cc=joelaf@google.com \
    --cc=ldufour@linux.ibm.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=luto@kernel.org \
    --cc=mhocko@suse.com \
    --cc=paulmck@kernel.org \
    --cc=peterz@infradead.org \
    --cc=riel@surriel.com \
    --cc=surenb@google.com \
    --cc=willy@infradead.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).