From: Suren Baghdasaryan <surenb@google•com>
To: akpm@linux-foundation•org
Cc: michel@lespinasse•org, joelaf@google•com, songliubraving@fb•com,
mhocko@suse•com, leewalsh@google•com, david@redhat•com,
peterz@infradead•org, bigeasy@linutronix•de, peterx@redhat•com,
dhowells@redhat•com, linux-mm@kvack•org, edumazet@google•com,
jglisse@google•com, punit.agrawal@bytedance•com, will@kernel•org,
arjunroy@google•com, dave@stgolabs•net, minchan@google•com,
x86@kernel•org, hughd@google•com, willy@infradead•org,
gurua@google•com, mingo@redhat•com,
linux-arm-kernel@lists•infradead.org, rientjes@google•com,
axelrasmussen@google•com, kernel-team@android•com,
soheil@google•com, paulmck@kernel•org, jannh@google•com,
Liam Howlett <Liam.Howlett@oracle•com>,
shakeelb@google•com, luto@kernel•org, gthelen@google•com,
ldufour@linux•ibm.com, surenb@google•com, vbabka@suse•cz,
posk@google•com, lstoakes@gmail•com, peterjung1337@gmail•com,
linuxppc-dev@lists•ozlabs.org, kent.overstreet@linux•dev,
linux-kernel@vger•kernel.org, hannes@cmpxchg•org,
tatashin@google•com, mgorman@techsing ularity.net,
rppt@kernel•org
Subject: [PATCH v2 01/33] maple_tree: Be more cautious about dead nodes
Date: Fri, 27 Jan 2023 11:40:38 -0800 [thread overview]
Message-ID: <20230127194110.533103-2-surenb@google.com> (raw)
In-Reply-To: <20230127194110.533103-1-surenb@google.com>
From: Liam Howlett <Liam.Howlett@oracle•com>
ma_pivots() and ma_data_end() may be called with a dead node. Ensure to
that the node isn't dead before using the returned values.
This is necessary for RCU mode of the maple tree.
Fixes: 54a611b60590 ("Maple Tree: add new data structure")
Signed-off-by: Liam Howlett <Liam.Howlett@oracle•com>
Signed-off-by: Suren Baghdasaryan <surenb@google•com>
---
lib/maple_tree.c | 52 +++++++++++++++++++++++++++++++++++++++---------
1 file changed, 43 insertions(+), 9 deletions(-)
diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index 5e9703189259..e5eeecd14eee 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -537,6 +537,7 @@ static inline bool ma_dead_node(const struct maple_node *node)
return (parent == node);
}
+
/*
* mte_dead_node() - check if the @enode is dead.
* @enode: The encoded maple node
@@ -618,6 +619,8 @@ static inline unsigned int mas_alloc_req(const struct ma_state *mas)
* @node - the maple node
* @type - the node type
*
+ * In the event of a dead node, this array may be %NULL
+ *
* Return: A pointer to the maple node pivots
*/
static inline unsigned long *ma_pivots(struct maple_node *node,
@@ -1089,8 +1092,11 @@ static int mas_ascend(struct ma_state *mas)
a_type = mas_parent_enum(mas, p_enode);
a_node = mte_parent(p_enode);
a_slot = mte_parent_slot(p_enode);
- pivots = ma_pivots(a_node, a_type);
a_enode = mt_mk_node(a_node, a_type);
+ pivots = ma_pivots(a_node, a_type);
+
+ if (unlikely(ma_dead_node(a_node)))
+ return 1;
if (!set_min && a_slot) {
set_min = true;
@@ -1394,6 +1400,9 @@ static inline unsigned char ma_data_end(struct maple_node *node,
{
unsigned char offset;
+ if (!pivots)
+ return 0;
+
if (type == maple_arange_64)
return ma_meta_end(node, type);
@@ -1429,6 +1438,9 @@ static inline unsigned char mas_data_end(struct ma_state *mas)
return ma_meta_end(node, type);
pivots = ma_pivots(node, type);
+ if (unlikely(ma_dead_node(node)))
+ return 0;
+
offset = mt_pivots[type] - 1;
if (likely(!pivots[offset]))
return ma_meta_end(node, type);
@@ -4498,6 +4510,9 @@ static inline int mas_prev_node(struct ma_state *mas, unsigned long min)
node = mas_mn(mas);
slots = ma_slots(node, mt);
pivots = ma_pivots(node, mt);
+ if (unlikely(ma_dead_node(node)))
+ return 1;
+
mas->max = pivots[offset];
if (offset)
mas->min = pivots[offset - 1] + 1;
@@ -4519,6 +4534,9 @@ static inline int mas_prev_node(struct ma_state *mas, unsigned long min)
slots = ma_slots(node, mt);
pivots = ma_pivots(node, mt);
offset = ma_data_end(node, mt, pivots, mas->max);
+ if (unlikely(ma_dead_node(node)))
+ return 1;
+
if (offset)
mas->min = pivots[offset - 1] + 1;
@@ -4567,6 +4585,7 @@ static inline int mas_next_node(struct ma_state *mas, struct maple_node *node,
struct maple_enode *enode;
int level = 0;
unsigned char offset;
+ unsigned char node_end;
enum maple_type mt;
void __rcu **slots;
@@ -4590,7 +4609,11 @@ static inline int mas_next_node(struct ma_state *mas, struct maple_node *node,
node = mas_mn(mas);
mt = mte_node_type(mas->node);
pivots = ma_pivots(node, mt);
- } while (unlikely(offset == ma_data_end(node, mt, pivots, mas->max)));
+ node_end = ma_data_end(node, mt, pivots, mas->max);
+ if (unlikely(ma_dead_node(node)))
+ return 1;
+
+ } while (unlikely(offset == node_end));
slots = ma_slots(node, mt);
pivot = mas_safe_pivot(mas, pivots, ++offset, mt);
@@ -4606,6 +4629,9 @@ static inline int mas_next_node(struct ma_state *mas, struct maple_node *node,
mt = mte_node_type(mas->node);
slots = ma_slots(node, mt);
pivots = ma_pivots(node, mt);
+ if (unlikely(ma_dead_node(node)))
+ return 1;
+
offset = 0;
pivot = pivots[0];
}
@@ -4652,11 +4678,14 @@ static inline void *mas_next_nentry(struct ma_state *mas,
return NULL;
}
- pivots = ma_pivots(node, type);
slots = ma_slots(node, type);
- mas->index = mas_safe_min(mas, pivots, mas->offset);
+ pivots = ma_pivots(node, type);
count = ma_data_end(node, type, pivots, mas->max);
- if (ma_dead_node(node))
+ if (unlikely(ma_dead_node(node)))
+ return NULL;
+
+ mas->index = mas_safe_min(mas, pivots, mas->offset);
+ if (unlikely(ma_dead_node(node)))
return NULL;
if (mas->index > max)
@@ -4810,6 +4839,11 @@ static inline void *mas_prev_nentry(struct ma_state *mas, unsigned long limit,
slots = ma_slots(mn, mt);
pivots = ma_pivots(mn, mt);
+ if (unlikely(ma_dead_node(mn))) {
+ mas_rewalk(mas, index);
+ goto retry;
+ }
+
if (offset == mt_pivots[mt])
pivot = mas->max;
else
@@ -6624,11 +6658,11 @@ static inline void *mas_first_entry(struct ma_state *mas, struct maple_node *mn,
while (likely(!ma_is_leaf(mt))) {
MT_BUG_ON(mas->tree, mte_dead_node(mas->node));
slots = ma_slots(mn, mt);
- pivots = ma_pivots(mn, mt);
- max = pivots[0];
entry = mas_slot(mas, slots, 0);
+ pivots = ma_pivots(mn, mt);
if (unlikely(ma_dead_node(mn)))
return NULL;
+ max = pivots[0];
mas->node = entry;
mn = mas_mn(mas);
mt = mte_node_type(mas->node);
@@ -6648,13 +6682,13 @@ static inline void *mas_first_entry(struct ma_state *mas, struct maple_node *mn,
if (likely(entry))
return entry;
- pivots = ma_pivots(mn, mt);
- mas->index = pivots[0] + 1;
mas->offset = 1;
entry = mas_slot(mas, slots, 1);
+ pivots = ma_pivots(mn, mt);
if (unlikely(ma_dead_node(mn)))
return NULL;
+ mas->index = pivots[0] + 1;
if (mas->index > limit)
goto none;
--
2.39.1
next prev parent reply other threads:[~2023-01-27 19:43 UTC|newest]
Thread overview: 42+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-01-27 19:40 [PATCH v2 00/33] Per-VMA locks Suren Baghdasaryan
2023-01-27 19:40 ` Suren Baghdasaryan [this message]
2023-01-27 19:40 ` [PATCH v2 02/33] maple_tree: Detect dead nodes in mas_start() Suren Baghdasaryan
2023-01-27 19:40 ` [PATCH v2 03/33] maple_tree: Fix freeing of nodes in rcu mode Suren Baghdasaryan
2023-01-27 19:40 ` [PATCH v2 04/33] maple_tree: remove extra smp_wmb() from mas_dead_leaves() Suren Baghdasaryan
2023-01-27 19:40 ` [PATCH v2 05/33] maple_tree: Fix write memory barrier of nodes once dead for RCU mode Suren Baghdasaryan
2023-01-27 19:40 ` [PATCH v2 06/33] maple_tree: Add smp_rmb() to dead node detection Suren Baghdasaryan
2023-01-27 19:40 ` [PATCH v2 07/33] mm: Enable maple tree RCU mode by default Suren Baghdasaryan
2023-01-27 19:40 ` [PATCH v2 08/33] mm: introduce CONFIG_PER_VMA_LOCK Suren Baghdasaryan
2023-01-27 19:40 ` [PATCH v2 09/33] mm: rcu safe VMA freeing Suren Baghdasaryan
2023-01-27 19:40 ` [PATCH v2 10/33] mm: move mmap_lock assert function definitions Suren Baghdasaryan
2023-01-27 19:40 ` [PATCH v2 11/33] mm: add per-VMA lock and helper functions to control it Suren Baghdasaryan
2023-01-27 19:40 ` [PATCH v2 12/33] mm: mark VMA as being written when changing vm_flags Suren Baghdasaryan
2023-01-27 19:40 ` [PATCH v2 13/33] mm/mmap: move VMA locking before vma_adjust_trans_huge call Suren Baghdasaryan
2023-01-27 19:40 ` [PATCH v2 14/33] mm/khugepaged: write-lock VMA while collapsing a huge page Suren Baghdasaryan
2023-01-27 19:40 ` [PATCH v2 15/33] mm/mmap: write-lock VMAs before merging, splitting or expanding them Suren Baghdasaryan
2023-01-27 19:40 ` [PATCH v2 16/33] mm/mmap: write-lock VMA before shrinking or expanding it Suren Baghdasaryan
2023-01-27 19:40 ` [PATCH v2 17/33] mm/mremap: write-lock VMA while remapping it to a new address range Suren Baghdasaryan
2023-01-27 19:40 ` [PATCH v2 18/33] mm: write-lock VMAs before removing them from VMA tree Suren Baghdasaryan
2023-01-27 19:40 ` [PATCH v2 19/33] mm: conditionally write-lock VMA in free_pgtables Suren Baghdasaryan
2023-01-27 19:40 ` [PATCH v2 20/33] mm/mmap: write-lock adjacent VMAs if they can grow into unmapped area Suren Baghdasaryan
2023-01-27 19:40 ` [PATCH v2 21/33] kernel/fork: assert no VMA readers during its destruction Suren Baghdasaryan
2023-01-27 19:40 ` [PATCH v2 22/33] mm/mmap: prevent pagefault handler from racing with mmu_notifier registration Suren Baghdasaryan
2023-01-27 19:41 ` [PATCH v2 23/33] mm: introduce lock_vma_under_rcu to be used from arch-specific code Suren Baghdasaryan
2023-01-27 19:41 ` [PATCH v2 24/33] mm: fall back to mmap_lock if vma->anon_vma is not yet set Suren Baghdasaryan
2023-01-27 19:41 ` [PATCH v2 25/33] mm: add FAULT_FLAG_VMA_LOCK flag Suren Baghdasaryan
2023-01-27 19:41 ` [PATCH v2 26/33] mm: prevent do_swap_page from handling page faults under VMA lock Suren Baghdasaryan
2023-01-27 19:41 ` [PATCH v2 27/33] mm: prevent userfaults to be handled under per-vma lock Suren Baghdasaryan
2023-01-27 19:41 ` [PATCH v2 28/33] mm: introduce per-VMA lock statistics Suren Baghdasaryan
2023-01-27 19:41 ` [PATCH v2 29/33] x86/mm: try VMA lock-based page fault handling first Suren Baghdasaryan
2023-01-27 19:41 ` [PATCH v2 30/33] arm64/mm: " Suren Baghdasaryan
2023-01-27 19:41 ` [PATCH v2 31/33] powerc/mm: " Suren Baghdasaryan
2023-01-27 19:41 ` [PATCH v2 32/33] mm/mmap: free vm_area_struct without call_rcu in exit_mmap Suren Baghdasaryan
2023-01-27 19:41 ` [PATCH v2 33/33] mm: separate vma->lock from vm_area_struct Suren Baghdasaryan
2023-01-27 22:51 ` [PATCH v2 00/33] Per-VMA locks Andrew Morton
2023-01-27 23:26 ` Matthew Wilcox
2023-01-28 0:00 ` Suren Baghdasaryan
2023-02-14 16:47 ` Suren Baghdasaryan
2023-02-15 17:32 ` [External] " Punit Agrawal
2023-02-15 17:39 ` Suren Baghdasaryan
2023-02-28 12:06 ` Punit Agrawal
2023-02-28 18:08 ` 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=20230127194110.533103-2-surenb@google.com \
--to=surenb@google$(echo .)com \
--cc=Liam.Howlett@oracle$(echo .)com \
--cc=akpm@linux-foundation$(echo .)org \
--cc=arjunroy@google$(echo .)com \
--cc=axelrasmussen@google$(echo .)com \
--cc=bigeasy@linutronix$(echo .)de \
--cc=dave@stgolabs$(echo .)net \
--cc=david@redhat$(echo .)com \
--cc=dhowells@redhat$(echo .)com \
--cc=edumazet@google$(echo .)com \
--cc=gthelen@google$(echo .)com \
--cc=gurua@google$(echo .)com \
--cc=hannes@cmpxchg$(echo .)org \
--cc=hughd@google$(echo .)com \
--cc=jannh@google$(echo .)com \
--cc=jglisse@google$(echo .)com \
--cc=joelaf@google$(echo .)com \
--cc=kent.overstreet@linux$(echo .)dev \
--cc=kernel-team@android$(echo .)com \
--cc=ldufour@linux$(echo .)ibm.com \
--cc=leewalsh@google$(echo .)com \
--cc=linux-arm-kernel@lists$(echo .)infradead.org \
--cc=linux-kernel@vger$(echo .)kernel.org \
--cc=linux-mm@kvack$(echo .)org \
--cc=linuxppc-dev@lists$(echo .)ozlabs.org \
--cc=lstoakes@gmail$(echo .)com \
--cc=luto@kernel$(echo .)org \
--cc=mgorman@techsing \
--cc=mhocko@suse$(echo .)com \
--cc=michel@lespinasse$(echo .)org \
--cc=minchan@google$(echo .)com \
--cc=mingo@redhat$(echo .)com \
--cc=paulmck@kernel$(echo .)org \
--cc=peterjung1337@gmail$(echo .)com \
--cc=peterx@redhat$(echo .)com \
--cc=peterz@infradead$(echo .)org \
--cc=posk@google$(echo .)com \
--cc=punit.agrawal@bytedance$(echo .)com \
--cc=rientjes@google$(echo .)com \
--cc=shakeelb@google$(echo .)com \
--cc=soheil@google$(echo .)com \
--cc=songliubraving@fb$(echo .)com \
--cc=tatashin@google$(echo .)com \
--cc=vbabka@suse$(echo .)cz \
--cc=will@kernel$(echo .)org \
--cc=willy@infradead$(echo .)org \
--cc=x86@kernel$(echo .)org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
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