From: Jerome Glisse <jglisse@redhat.com>
To: Laurent Dufour <ldufour@linux.ibm.com>
Cc: jack@suse.cz, sergey.senozhatsky.work@gmail.com,
peterz@infradead.org, Will Deacon <will.deacon@arm.com>,
mhocko@kernel.org, linux-mm@kvack.org, paulus@samba.org,
Punit Agrawal <punitagrawal@gmail.com>,
hpa@zytor.com, Michel Lespinasse <walken@google.com>,
Alexei Starovoitov <alexei.starovoitov@gmail.com>,
Andrea Arcangeli <aarcange@redhat.com>,
ak@linux.intel.com, Minchan Kim <minchan@kernel.org>,
aneesh.kumar@linux.ibm.com, x86@kernel.org,
Matthew Wilcox <willy@infradead.org>,
Daniel Jordan <daniel.m.jordan@oracle.com>,
Ingo Molnar <mingo@redhat.com>,
David Rientjes <rientjes@google.com>,
paulmck@linux.vnet.ibm.com, Haiyan Song <haiyanx.song@intel.com>,
npiggin@gmail.com, sj38.park@gmail.com, dave@stgolabs.net,
kemi.wang@intel.com, kirill@shutemov.name,
Thomas Gleixner <tglx@linutronix.de>,
zhong jiang <zhongjiang@huawei.com>,
Ganesh Mahendran <opensource.ganesh@gmail.com>,
Yang Shi <yang.shi@linux.alibaba.com>,
Mike Rapoport <rppt@linux.ibm.com>,
linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org,
Sergey Senozhatsky <sergey.senozhatsky@gmail.com>,
vinayak menon <vinayakm.list@gmail.com>,
akpm@linux-foundation.org, Tim Chen <tim.c.chen@linux.intel.com>,
haren@linux.vnet.ibm.com
Subject: Re: [PATCH v12 19/31] mm: protect the RB tree with a sequence lock
Date: Mon, 22 Apr 2019 16:33:51 -0400 [thread overview]
Message-ID: <20190422203350.GJ14666@redhat.com> (raw)
In-Reply-To: <20190416134522.17540-20-ldufour@linux.ibm.com>
On Tue, Apr 16, 2019 at 03:45:10PM +0200, Laurent Dufour wrote:
> Introducing a per mm_struct seqlock, mm_seq field, to protect the changes
> made in the MM RB tree. This allows to walk the RB tree without grabbing
> the mmap_sem, and on the walk is done to double check that sequence counter
> was stable during the walk.
>
> The mm seqlock is held while inserting and removing entries into the MM RB
> tree. Later in this series, it will be check when looking for a VMA
> without holding the mmap_sem.
>
> This is based on the initial work from Peter Zijlstra:
> https://lore.kernel.org/linux-mm/20100104182813.479668508@chello.nl/
>
> Signed-off-by: Laurent Dufour <ldufour@linux.ibm.com>
Reviewed-by: Jérôme Glisse <jglisse@redhat.com>
> ---
> include/linux/mm_types.h | 3 +++
> kernel/fork.c | 3 +++
> mm/init-mm.c | 3 +++
> mm/mmap.c | 48 +++++++++++++++++++++++++++++++---------
> 4 files changed, 46 insertions(+), 11 deletions(-)
>
> diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
> index e78f72eb2576..24b3f8ce9e42 100644
> --- a/include/linux/mm_types.h
> +++ b/include/linux/mm_types.h
> @@ -358,6 +358,9 @@ struct mm_struct {
> struct {
> struct vm_area_struct *mmap; /* list of VMAs */
> struct rb_root mm_rb;
> +#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
> + seqlock_t mm_seq;
> +#endif
> u64 vmacache_seqnum; /* per-thread vmacache */
> #ifdef CONFIG_MMU
> unsigned long (*get_unmapped_area) (struct file *filp,
> diff --git a/kernel/fork.c b/kernel/fork.c
> index 2992d2c95256..3a1739197ebc 100644
> --- a/kernel/fork.c
> +++ b/kernel/fork.c
> @@ -1008,6 +1008,9 @@ static struct mm_struct *mm_init(struct mm_struct *mm, struct task_struct *p,
> mm->mmap = NULL;
> mm->mm_rb = RB_ROOT;
> mm->vmacache_seqnum = 0;
> +#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
> + seqlock_init(&mm->mm_seq);
> +#endif
> atomic_set(&mm->mm_users, 1);
> atomic_set(&mm->mm_count, 1);
> init_rwsem(&mm->mmap_sem);
> diff --git a/mm/init-mm.c b/mm/init-mm.c
> index a787a319211e..69346b883a4e 100644
> --- a/mm/init-mm.c
> +++ b/mm/init-mm.c
> @@ -27,6 +27,9 @@
> */
> struct mm_struct init_mm = {
> .mm_rb = RB_ROOT,
> +#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
> + .mm_seq = __SEQLOCK_UNLOCKED(init_mm.mm_seq),
> +#endif
> .pgd = swapper_pg_dir,
> .mm_users = ATOMIC_INIT(2),
> .mm_count = ATOMIC_INIT(1),
> diff --git a/mm/mmap.c b/mm/mmap.c
> index 13460b38b0fb..f7f6027a7dff 100644
> --- a/mm/mmap.c
> +++ b/mm/mmap.c
> @@ -170,6 +170,24 @@ void unlink_file_vma(struct vm_area_struct *vma)
> }
> }
>
> +#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
> +static inline void mm_write_seqlock(struct mm_struct *mm)
> +{
> + write_seqlock(&mm->mm_seq);
> +}
> +static inline void mm_write_sequnlock(struct mm_struct *mm)
> +{
> + write_sequnlock(&mm->mm_seq);
> +}
> +#else
> +static inline void mm_write_seqlock(struct mm_struct *mm)
> +{
> +}
> +static inline void mm_write_sequnlock(struct mm_struct *mm)
> +{
> +}
> +#endif /* CONFIG_SPECULATIVE_PAGE_FAULT */
> +
> /*
> * Close a vm structure and free it, returning the next.
> */
> @@ -445,26 +463,32 @@ static void vma_gap_update(struct vm_area_struct *vma)
> }
>
> static inline void vma_rb_insert(struct vm_area_struct *vma,
> - struct rb_root *root)
> + struct mm_struct *mm)
> {
> + struct rb_root *root = &mm->mm_rb;
> +
> /* All rb_subtree_gap values must be consistent prior to insertion */
> validate_mm_rb(root, NULL);
>
> rb_insert_augmented(&vma->vm_rb, root, &vma_gap_callbacks);
> }
>
> -static void __vma_rb_erase(struct vm_area_struct *vma, struct rb_root *root)
> +static void __vma_rb_erase(struct vm_area_struct *vma, struct mm_struct *mm)
> {
> + struct rb_root *root = &mm->mm_rb;
> +
> /*
> * Note rb_erase_augmented is a fairly large inline function,
> * so make sure we instantiate it only once with our desired
> * augmented rbtree callbacks.
> */
> + mm_write_seqlock(mm);
> rb_erase_augmented(&vma->vm_rb, root, &vma_gap_callbacks);
> + mm_write_sequnlock(mm); /* wmb */
> }
>
> static __always_inline void vma_rb_erase_ignore(struct vm_area_struct *vma,
> - struct rb_root *root,
> + struct mm_struct *mm,
> struct vm_area_struct *ignore)
> {
> /*
> @@ -472,21 +496,21 @@ static __always_inline void vma_rb_erase_ignore(struct vm_area_struct *vma,
> * with the possible exception of the "next" vma being erased if
> * next->vm_start was reduced.
> */
> - validate_mm_rb(root, ignore);
> + validate_mm_rb(&mm->mm_rb, ignore);
>
> - __vma_rb_erase(vma, root);
> + __vma_rb_erase(vma, mm);
> }
>
> static __always_inline void vma_rb_erase(struct vm_area_struct *vma,
> - struct rb_root *root)
> + struct mm_struct *mm)
> {
> /*
> * All rb_subtree_gap values must be consistent prior to erase,
> * with the possible exception of the vma being erased.
> */
> - validate_mm_rb(root, vma);
> + validate_mm_rb(&mm->mm_rb, vma);
>
> - __vma_rb_erase(vma, root);
> + __vma_rb_erase(vma, mm);
> }
>
> /*
> @@ -601,10 +625,12 @@ void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma,
> * immediately update the gap to the correct value. Finally we
> * rebalance the rbtree after all augmented values have been set.
> */
> + mm_write_seqlock(mm);
> rb_link_node(&vma->vm_rb, rb_parent, rb_link);
> vma->rb_subtree_gap = 0;
> vma_gap_update(vma);
> - vma_rb_insert(vma, &mm->mm_rb);
> + vma_rb_insert(vma, mm);
> + mm_write_sequnlock(mm);
> }
>
> static void __vma_link_file(struct vm_area_struct *vma)
> @@ -680,7 +706,7 @@ static __always_inline void __vma_unlink_common(struct mm_struct *mm,
> {
> struct vm_area_struct *next;
>
> - vma_rb_erase_ignore(vma, &mm->mm_rb, ignore);
> + vma_rb_erase_ignore(vma, mm, ignore);
> next = vma->vm_next;
> if (has_prev)
> prev->vm_next = next;
> @@ -2674,7 +2700,7 @@ detach_vmas_to_be_unmapped(struct mm_struct *mm, struct vm_area_struct *vma,
> insertion_point = (prev ? &prev->vm_next : &mm->mmap);
> vma->vm_prev = NULL;
> do {
> - vma_rb_erase(vma, &mm->mm_rb);
> + vma_rb_erase(vma, mm);
> mm->map_count--;
> tail_vma = vma;
> vma = vma->vm_next;
> --
> 2.21.0
>
next prev parent reply other threads:[~2019-04-22 20:36 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 [this message]
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 ` [PATCH v12 21/31] mm: Introduce find_vma_rcu() Laurent Dufour
2019-04-22 20:57 ` 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=20190422203350.GJ14666@redhat.com \
--to=jglisse@redhat.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=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=kemi.wang@intel.com \
--cc=kirill@shutemov.name \
--cc=ldufour@linux.ibm.com \
--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=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).