LKML Archive on lore.kernel.org
help / color / mirror / Atom feed
From: Laurent Dufour <ldufour@linux.vnet.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>,
	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>,
	Andrea Arcangeli <aarcange@redhat.com>,
	Alexei Starovoitov <alexei.starovoitov@gmail.com>,
	kemi.wang@intel.com, sergey.senozhatsky.work@gmail.com,
	Daniel Jordan <daniel.m.jordan@oracle.com>,
	David Rientjes <rientjes@google.com>,
	Jerome Glisse <jglisse@redhat.com>,
	Ganesh Mahendran <opensource.ganesh@gmail.com>
Cc: linux-kernel@vger.kernel.org, linux-mm@kvack.org,
	haren@linux.vnet.ibm.com, khandual@linux.vnet.ibm.com,
	npiggin@gmail.com, bsingharora@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 v10 08/25] mm: VMA sequence count
Date: Tue, 17 Apr 2018 16:33:14 +0200	[thread overview]
Message-ID: <1523975611-15978-9-git-send-email-ldufour@linux.vnet.ibm.com> (raw)
In-Reply-To: <1523975611-15978-1-git-send-email-ldufour@linux.vnet.ibm.com>

From: Peter Zijlstra <peterz@infradead.org>

Wrap the VMA modifications (vma_adjust/unmap_page_range) with sequence
counts such that we can easily test if a VMA is changed.

The unmap_page_range() one allows us to make assumptions about
page-tables; when we find the seqcount hasn't changed we can assume
page-tables are still valid.

The flip side is that we cannot distinguish between a vma_adjust() and
the unmap_page_range() -- where with the former we could have
re-checked the vma bounds against the address.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>

[Port to 4.12 kernel]
[Build depends on CONFIG_SPECULATIVE_PAGE_FAULT]
[Introduce vm_write_* inline function depending on
 CONFIG_SPECULATIVE_PAGE_FAULT]
[Fix lock dependency between mapping->i_mmap_rwsem and vma->vm_sequence by
 using vm_raw_write* functions]
[Fix a lock dependency warning in mmap_region() when entering the error
 path]
[move sequence initialisation INIT_VMA()]
Signed-off-by: Laurent Dufour <ldufour@linux.vnet.ibm.com>
---
 include/linux/mm.h       | 44 ++++++++++++++++++++++++++++++++++++++++++++
 include/linux/mm_types.h |  3 +++
 mm/memory.c              |  2 ++
 mm/mmap.c                | 31 +++++++++++++++++++++++++++++++
 4 files changed, 80 insertions(+)

diff --git a/include/linux/mm.h b/include/linux/mm.h
index efc1248b82bd..988daf7030c9 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1264,6 +1264,9 @@ struct zap_details {
 static inline void INIT_VMA(struct vm_area_struct *vma)
 {
 	INIT_LIST_HEAD(&vma->anon_vma_chain);
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+	seqcount_init(&vma->vm_sequence);
+#endif
 }
 
 struct page *_vm_normal_page(struct vm_area_struct *vma, unsigned long addr,
@@ -1386,6 +1389,47 @@ static inline void unmap_shared_mapping_range(struct address_space *mapping,
 	unmap_mapping_range(mapping, holebegin, holelen, 0);
 }
 
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+static inline void vm_write_begin(struct vm_area_struct *vma)
+{
+	write_seqcount_begin(&vma->vm_sequence);
+}
+static inline void vm_write_begin_nested(struct vm_area_struct *vma,
+					 int subclass)
+{
+	write_seqcount_begin_nested(&vma->vm_sequence, subclass);
+}
+static inline void vm_write_end(struct vm_area_struct *vma)
+{
+	write_seqcount_end(&vma->vm_sequence);
+}
+static inline void vm_raw_write_begin(struct vm_area_struct *vma)
+{
+	raw_write_seqcount_begin(&vma->vm_sequence);
+}
+static inline void vm_raw_write_end(struct vm_area_struct *vma)
+{
+	raw_write_seqcount_end(&vma->vm_sequence);
+}
+#else
+static inline void vm_write_begin(struct vm_area_struct *vma)
+{
+}
+static inline void vm_write_begin_nested(struct vm_area_struct *vma,
+					 int subclass)
+{
+}
+static inline void vm_write_end(struct vm_area_struct *vma)
+{
+}
+static inline void vm_raw_write_begin(struct vm_area_struct *vma)
+{
+}
+static inline void vm_raw_write_end(struct vm_area_struct *vma)
+{
+}
+#endif /* CONFIG_SPECULATIVE_PAGE_FAULT */
+
 extern int access_process_vm(struct task_struct *tsk, unsigned long addr,
 		void *buf, int len, unsigned int gup_flags);
 extern int access_remote_vm(struct mm_struct *mm, unsigned long addr,
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 21612347d311..db5e9d630e7a 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -335,6 +335,9 @@ struct vm_area_struct {
 	struct mempolicy *vm_policy;	/* NUMA policy for the VMA */
 #endif
 	struct vm_userfaultfd_ctx vm_userfaultfd_ctx;
+#ifdef CONFIG_SPECULATIVE_PAGE_FAULT
+	seqcount_t vm_sequence;
+#endif
 } __randomize_layout;
 
 struct core_thread {
diff --git a/mm/memory.c b/mm/memory.c
index f86efcb8e268..f7fed053df80 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1503,6 +1503,7 @@ void unmap_page_range(struct mmu_gather *tlb,
 	unsigned long next;
 
 	BUG_ON(addr >= end);
+	vm_write_begin(vma);
 	tlb_start_vma(tlb, vma);
 	pgd = pgd_offset(vma->vm_mm, addr);
 	do {
@@ -1512,6 +1513,7 @@ void unmap_page_range(struct mmu_gather *tlb,
 		next = zap_p4d_range(tlb, vma, pgd, addr, next, details);
 	} while (pgd++, addr = next, addr != end);
 	tlb_end_vma(tlb, vma);
+	vm_write_end(vma);
 }
 
 
diff --git a/mm/mmap.c b/mm/mmap.c
index 8bd9ae1dfacc..813e49589ea1 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -692,6 +692,30 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
 	long adjust_next = 0;
 	int remove_next = 0;
 
+	/*
+	 * Why using vm_raw_write*() functions here to avoid lockdep's warning ?
+	 *
+	 * Locked is complaining about a theoretical lock dependency, involving
+	 * 3 locks:
+	 *   mapping->i_mmap_rwsem --> vma->vm_sequence --> fs_reclaim
+	 *
+	 * Here are the major path leading to this dependency :
+	 *  1. __vma_adjust() mmap_sem  -> vm_sequence -> i_mmap_rwsem
+	 *  2. move_vmap() mmap_sem -> vm_sequence -> fs_reclaim
+	 *  3. __alloc_pages_nodemask() fs_reclaim -> i_mmap_rwsem
+	 *  4. unmap_mapping_range() i_mmap_rwsem -> vm_sequence
+	 *
+	 * So there is no way to solve this easily, especially because in
+	 * unmap_mapping_range() the i_mmap_rwsem is grab while the impacted
+	 * VMAs are not yet known.
+	 * However, the way the vm_seq is used is guarantying that we will
+	 * never block on it since we just check for its value and never wait
+	 * for it to move, see vma_has_changed() and handle_speculative_fault().
+	 */
+	vm_raw_write_begin(vma);
+	if (next)
+		vm_raw_write_begin(next);
+
 	if (next && !insert) {
 		struct vm_area_struct *exporter = NULL, *importer = NULL;
 
@@ -902,6 +926,7 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
 			anon_vma_merge(vma, next);
 		mm->map_count--;
 		mpol_put(vma_policy(next));
+		vm_raw_write_end(next);
 		kmem_cache_free(vm_area_cachep, next);
 		/*
 		 * In mprotect's case 6 (see comments on vma_merge),
@@ -916,6 +941,8 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
 			 * "vma->vm_next" gap must be updated.
 			 */
 			next = vma->vm_next;
+			if (next)
+				vm_raw_write_begin(next);
 		} else {
 			/*
 			 * For the scope of the comment "next" and
@@ -962,6 +989,10 @@ int __vma_adjust(struct vm_area_struct *vma, unsigned long start,
 	if (insert && file)
 		uprobe_mmap(insert);
 
+	if (next && next != vma)
+		vm_raw_write_end(next);
+	vm_raw_write_end(vma);
+
 	validate_mm(mm);
 
 	return 0;
-- 
2.7.4

  parent reply	other threads:[~2018-04-17 14:34 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2018-04-17 14:33 [PATCH v10 00/25] Speculative page faults Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 01/25] mm: introduce CONFIG_SPECULATIVE_PAGE_FAULT Laurent Dufour
2018-04-23  5:58   ` Minchan Kim
2018-04-23 15:10     ` Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 02/25] x86/mm: define ARCH_SUPPORTS_SPECULATIVE_PAGE_FAULT Laurent Dufour
2018-05-08 11:04   ` Punit Agrawal
2018-05-14 14:47     ` Laurent Dufour
2018-05-14 15:05       ` Punit Agrawal
2018-04-17 14:33 ` [PATCH v10 03/25] powerpc/mm: set ARCH_SUPPORTS_SPECULATIVE_PAGE_FAULT Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 04/25] mm: prepare for FAULT_FLAG_SPECULATIVE Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 05/25] mm: introduce pte_spinlock " Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 06/25] mm: make pte_unmap_same compatible with SPF Laurent Dufour
2018-04-23  6:31   ` Minchan Kim
2018-04-30 14:07     ` Laurent Dufour
2018-05-01 13:04       ` Minchan Kim
2018-05-10 16:15   ` vinayak menon
2018-05-14 15:09     ` Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 07/25] mm: introduce INIT_VMA() Laurent Dufour
2018-04-17 14:33 ` Laurent Dufour [this message]
2018-04-23  6:42   ` [PATCH v10 08/25] mm: VMA sequence count Minchan Kim
2018-04-30 15:14     ` Laurent Dufour
2018-05-01 13:16       ` Minchan Kim
2018-05-03 14:45         ` Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 09/25] mm: protect VMA modifications using " Laurent Dufour
2018-04-23  7:19   ` Minchan Kim
2018-05-14 15:25     ` Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 10/25] mm: protect mremap() against SPF hanlder Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 11/25] mm: protect SPF handler against anon_vma changes Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 12/25] mm: cache some VMA fields in the vm_fault structure Laurent Dufour
2018-04-23  7:42   ` Minchan Kim
2018-05-03 12:25     ` Laurent Dufour
2018-05-03 15:42       ` Minchan Kim
2018-05-04  9:10         ` Laurent Dufour
2018-05-08 10:56           ` Minchan Kim
2018-04-17 14:33 ` [PATCH v10 13/25] mm/migrate: Pass vm_fault pointer to migrate_misplaced_page() Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 14/25] mm: introduce __lru_cache_add_active_or_unevictable Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 15/25] mm: introduce __vm_normal_page() Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 16/25] mm: introduce __page_add_new_anon_rmap() Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 17/25] mm: protect mm_rb tree with a rwlock Laurent Dufour
2018-04-30 18:47   ` Punit Agrawal
2018-05-02  6:37     ` Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 18/25] mm: provide speculative fault infrastructure Laurent Dufour
2018-05-15 13:09   ` vinayak menon
2018-05-15 14:07     ` Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 19/25] mm: adding speculative page fault failure trace events Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 20/25] perf: add a speculative page fault sw event Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 21/25] perf tools: add support for the SPF perf event Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 22/25] mm: speculative page fault handler return VMA Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 23/25] mm: add speculative page fault vmstats Laurent Dufour
2018-05-16  2:50   ` Ganesh Mahendran
2018-05-16  6:42     ` Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 24/25] x86/mm: add speculative pagefault handling Laurent Dufour
2018-04-30 18:43   ` Punit Agrawal
2018-05-03 14:59     ` Laurent Dufour
2018-04-17 14:33 ` [PATCH v10 25/25] powerpc/mm: add speculative page fault Laurent Dufour
2018-05-02 14:17 ` [PATCH v10 00/25] Speculative page faults Punit Agrawal
2018-05-02 14:45   ` Laurent Dufour

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=1523975611-15978-9-git-send-email-ldufour@linux.vnet.ibm.com \
    --to=ldufour@linux.vnet.ibm.com \
    --cc=aarcange@redhat.com \
    --cc=ak@linux.intel.com \
    --cc=akpm@linux-foundation.org \
    --cc=alexei.starovoitov@gmail.com \
    --cc=benh@kernel.crashing.org \
    --cc=bsingharora@gmail.com \
    --cc=daniel.m.jordan@oracle.com \
    --cc=dave@stgolabs.net \
    --cc=haren@linux.vnet.ibm.com \
    --cc=hpa@zytor.com \
    --cc=jack@suse.cz \
    --cc=jglisse@redhat.com \
    --cc=kemi.wang@intel.com \
    --cc=khandual@linux.vnet.ibm.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=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=rientjes@google.com \
    --cc=sergey.senozhatsky.work@gmail.com \
    --cc=sergey.senozhatsky@gmail.com \
    --cc=tglx@linutronix.de \
    --cc=tim.c.chen@linux.intel.com \
    --cc=will.deacon@arm.com \
    --cc=willy@infradead.org \
    --cc=x86@kernel.org \
    --subject='Re: [PATCH v10 08/25] mm: VMA sequence count' \
    /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

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).