From: Suren Baghdasaryan <surenb@google.com>
To: akpm@linux-foundation.org
Cc: michel@lespinasse.org, jglisse@google.com, mhocko@suse.com,
vbabka@suse.cz, hannes@cmpxchg.org, mgorman@techsingularity.net,
dave@stgolabs.net, willy@infradead.org, liam.howlett@oracle.com,
peterz@infradead.org, ldufour@linux.ibm.com, paulmck@kernel.org,
mingo@redhat.com, will@kernel.org, luto@kernel.org,
songliubraving@fb.com, peterx@redhat.com, david@redhat.com,
dhowells@redhat.com, hughd@google.com, bigeasy@linutronix.de,
kent.overstreet@linux.dev, punit.agrawal@bytedance.com,
lstoakes@gmail.com, peterjung1337@gmail.com,
rientjes@google.com, chriscli@google.com,
axelrasmussen@google.com, joelaf@google.com, minchan@google.com,
rppt@kernel.org, jannh@google.com, shakeelb@google.com,
tatashin@google.com, edumazet@google.com, gthelen@google.com,
gurua@google.com, arjunroy@google.com, soheil@google.com,
leewalsh@google.com, posk@google.com,
michalechner92@googlemail.com, linux-mm@kvack.org,
linux-arm-kernel@lists.infradead.org,
linuxppc-dev@lists.ozlabs.org, x86@kernel.org,
linux-kernel@vger.kernel.org, kernel-team@android.com,
Liam Howlett <Liam.Howlett@oracle.com>,
Suren Baghdasaryan <surenb@google.com>
Subject: [PATCH v4 03/33] maple_tree: Fix freeing of nodes in rcu mode
Date: Mon, 27 Feb 2023 09:36:02 -0800 [thread overview]
Message-ID: <20230227173632.3292573-4-surenb@google.com> (raw)
In-Reply-To: <20230227173632.3292573-1-surenb@google.com>
From: Liam Howlett <Liam.Howlett@oracle.com>
The walk to destroy the nodes was not always setting the node type and
would result in a destroy method potentially using the values as nodes.
Avoid this by setting the correct node types. This is necessary for the
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 | 73 ++++++++++++++++++++++++++++++++++++++++--------
1 file changed, 62 insertions(+), 11 deletions(-)
diff --git a/lib/maple_tree.c b/lib/maple_tree.c
index 089cd76ec379..44d6ce30b28e 100644
--- a/lib/maple_tree.c
+++ b/lib/maple_tree.c
@@ -902,6 +902,44 @@ static inline void ma_set_meta(struct maple_node *mn, enum maple_type mt,
meta->end = end;
}
+/*
+ * mas_clear_meta() - clear the metadata information of a node, if it exists
+ * @mas: The maple state
+ * @mn: The maple node
+ * @mt: The maple node type
+ * @offset: The offset of the highest sub-gap in this node.
+ * @end: The end of the data in this node.
+ */
+static inline void mas_clear_meta(struct ma_state *mas, struct maple_node *mn,
+ enum maple_type mt)
+{
+ struct maple_metadata *meta;
+ unsigned long *pivots;
+ void __rcu **slots;
+ void *next;
+
+ switch (mt) {
+ case maple_range_64:
+ pivots = mn->mr64.pivot;
+ if (unlikely(pivots[MAPLE_RANGE64_SLOTS - 2])) {
+ slots = mn->mr64.slot;
+ next = mas_slot_locked(mas, slots,
+ MAPLE_RANGE64_SLOTS - 1);
+ if (unlikely((mte_to_node(next) && mte_node_type(next))))
+ return; /* The last slot is a node, no metadata */
+ }
+ fallthrough;
+ case maple_arange_64:
+ meta = ma_meta(mn, mt);
+ break;
+ default:
+ return;
+ }
+
+ meta->gap = 0;
+ meta->end = 0;
+}
+
/*
* ma_meta_end() - Get the data end of a node from the metadata
* @mn: The maple node
@@ -5455,20 +5493,22 @@ static inline int mas_rev_alloc(struct ma_state *mas, unsigned long min,
* mas_dead_leaves() - Mark all leaves of a node as dead.
* @mas: The maple state
* @slots: Pointer to the slot array
+ * @type: The maple node type
*
* Must hold the write lock.
*
* Return: The number of leaves marked as dead.
*/
static inline
-unsigned char mas_dead_leaves(struct ma_state *mas, void __rcu **slots)
+unsigned char mas_dead_leaves(struct ma_state *mas, void __rcu **slots,
+ enum maple_type mt)
{
struct maple_node *node;
enum maple_type type;
void *entry;
int offset;
- for (offset = 0; offset < mt_slot_count(mas->node); offset++) {
+ for (offset = 0; offset < mt_slots[mt]; offset++) {
entry = mas_slot_locked(mas, slots, offset);
type = mte_node_type(entry);
node = mte_to_node(entry);
@@ -5487,14 +5527,13 @@ unsigned char mas_dead_leaves(struct ma_state *mas, void __rcu **slots)
static void __rcu **mas_dead_walk(struct ma_state *mas, unsigned char offset)
{
- struct maple_node *node, *next;
+ struct maple_node *next;
void __rcu **slots = NULL;
next = mas_mn(mas);
do {
- mas->node = ma_enode_ptr(next);
- node = mas_mn(mas);
- slots = ma_slots(node, node->type);
+ mas->node = mt_mk_node(next, next->type);
+ slots = ma_slots(next, next->type);
next = mas_slot_locked(mas, slots, offset);
offset = 0;
} while (!ma_is_leaf(next->type));
@@ -5558,11 +5597,14 @@ static inline void __rcu **mas_destroy_descend(struct ma_state *mas,
node = mas_mn(mas);
slots = ma_slots(node, mte_node_type(mas->node));
next = mas_slot_locked(mas, slots, 0);
- if ((mte_dead_node(next)))
+ if ((mte_dead_node(next))) {
+ mte_to_node(next)->type = mte_node_type(next);
next = mas_slot_locked(mas, slots, 1);
+ }
mte_set_node_dead(mas->node);
node->type = mte_node_type(mas->node);
+ mas_clear_meta(mas, node, node->type);
node->piv_parent = prev;
node->parent_slot = offset;
offset = 0;
@@ -5582,13 +5624,18 @@ static void mt_destroy_walk(struct maple_enode *enode, unsigned char ma_flags,
MA_STATE(mas, &mt, 0, 0);
- if (mte_is_leaf(enode))
+ mas.node = enode;
+ if (mte_is_leaf(enode)) {
+ node->type = mte_node_type(enode);
goto free_leaf;
+ }
+ ma_flags &= ~MT_FLAGS_LOCK_MASK;
mt_init_flags(&mt, ma_flags);
mas_lock(&mas);
- mas.node = start = enode;
+ mte_to_node(enode)->ma_flags = ma_flags;
+ start = enode;
slots = mas_destroy_descend(&mas, start, 0);
node = mas_mn(&mas);
do {
@@ -5596,7 +5643,8 @@ static void mt_destroy_walk(struct maple_enode *enode, unsigned char ma_flags,
unsigned char offset;
struct maple_enode *parent, *tmp;
- node->slot_len = mas_dead_leaves(&mas, slots);
+ node->type = mte_node_type(mas.node);
+ node->slot_len = mas_dead_leaves(&mas, slots, node->type);
if (free)
mt_free_bulk(node->slot_len, slots);
offset = node->parent_slot + 1;
@@ -5620,7 +5668,8 @@ static void mt_destroy_walk(struct maple_enode *enode, unsigned char ma_flags,
} while (start != mas.node);
node = mas_mn(&mas);
- node->slot_len = mas_dead_leaves(&mas, slots);
+ node->type = mte_node_type(mas.node);
+ node->slot_len = mas_dead_leaves(&mas, slots, node->type);
if (free)
mt_free_bulk(node->slot_len, slots);
@@ -5630,6 +5679,8 @@ static void mt_destroy_walk(struct maple_enode *enode, unsigned char ma_flags,
free_leaf:
if (free)
mt_free_rcu(&node->rcu);
+ else
+ mas_clear_meta(&mas, node, node->type);
}
/*
--
2.39.2.722.g9855ee24e9-goog
next prev parent reply other threads:[~2023-02-27 17:36 UTC|newest]
Thread overview: 72+ messages / expand[flat|nested] mbox.gz Atom feed top
2023-02-27 17:35 [PATCH v4 00/33] Per-VMA locks Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 01/33] maple_tree: Be more cautious about dead nodes Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 02/33] maple_tree: Detect dead nodes in mas_start() Suren Baghdasaryan
2023-02-27 17:36 ` Suren Baghdasaryan [this message]
2023-02-27 17:36 ` [PATCH v4 04/33] maple_tree: remove extra smp_wmb() from mas_dead_leaves() Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 05/33] maple_tree: Fix write memory barrier of nodes once dead for RCU mode Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 06/33] maple_tree: Add smp_rmb() to dead node detection Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 07/33] maple_tree: Add RCU lock checking to rcu callback functions Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 08/33] mm: Enable maple tree RCU mode by default Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 09/33] mm: introduce CONFIG_PER_VMA_LOCK Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 10/33] mm: rcu safe VMA freeing Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 11/33] mm: move mmap_lock assert function definitions Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 12/33] mm: add per-VMA lock and helper functions to control it Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 13/33] mm: mark VMA as being written when changing vm_flags Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 14/33] mm/mmap: move vma_prepare before vma_adjust_trans_huge Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 15/33] mm/khugepaged: write-lock VMA while collapsing a huge page Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 16/33] mm/mmap: write-lock VMAs in vma_prepare before modifying them Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 17/33] mm/mremap: write-lock VMA while remapping it to a new address range Suren Baghdasaryan
2023-03-01 7:01 ` Hyeonggon Yoo
2023-02-27 17:36 ` [PATCH v4 18/33] mm: write-lock VMAs before removing them from VMA tree Suren Baghdasaryan
2023-03-01 7:43 ` Hyeonggon Yoo
2023-03-01 7:56 ` Hyeonggon Yoo
2023-03-01 18:34 ` Suren Baghdasaryan
2023-03-01 18:42 ` Suren Baghdasaryan
2023-03-02 0:53 ` Hyeonggon Yoo
2023-03-02 2:21 ` Suren Baghdasaryan
2023-03-01 19:07 ` Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 19/33] mm: conditionally write-lock VMA in free_pgtables Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 20/33] kernel/fork: assert no VMA readers during its destruction Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 21/33] mm/mmap: prevent pagefault handler from racing with mmu_notifier registration Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 22/33] mm: introduce vma detached flag Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 23/33] mm: introduce lock_vma_under_rcu to be used from arch-specific code Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 24/33] mm: fall back to mmap_lock if vma->anon_vma is not yet set Suren Baghdasaryan
2023-03-01 9:54 ` Hyeonggon Yoo
2023-02-27 17:36 ` [PATCH v4 25/33] mm: add FAULT_FLAG_VMA_LOCK flag Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 26/33] mm: prevent do_swap_page from handling page faults under VMA lock Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 27/33] mm: prevent userfaults to be handled under per-vma lock Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 28/33] mm: introduce per-VMA lock statistics Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 29/33] x86/mm: try VMA lock-based page fault handling first Suren Baghdasaryan
2023-06-29 14:40 ` Jiri Slaby
2023-06-29 15:30 ` Suren Baghdasaryan
2023-06-30 6:35 ` Jiri Slaby
2023-06-30 8:28 ` Jiri Slaby
2023-06-30 8:43 ` Jiri Slaby
2023-06-30 17:40 ` Suren Baghdasaryan
2023-07-03 10:47 ` Jiri Slaby
2023-07-03 13:52 ` Holger Hoffstätte
2023-07-03 14:45 ` Suren Baghdasaryan
2023-07-03 15:24 ` Suren Baghdasaryan
2023-07-03 18:28 ` Suren Baghdasaryan
2023-07-05 22:15 ` Suren Baghdasaryan
2023-07-05 22:37 ` Holger Hoffstätte
2023-07-05 22:55 ` Suren Baghdasaryan
2023-07-06 14:27 ` Holger Hoffstätte
2023-07-06 16:11 ` Suren Baghdasaryan
2023-07-07 2:23 ` Suren Baghdasaryan
2023-07-07 4:40 ` Suren Baghdasaryan
2023-07-11 6:20 ` Jiri Slaby
2023-06-29 17:06 ` Linux regression tracking #adding (Thorsten Leemhuis)
2023-07-03 9:58 ` Linux regression tracking (Thorsten Leemhuis)
2023-02-27 17:36 ` [PATCH v4 30/33] arm64/mm: " Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 31/33] powerc/mm: " Suren Baghdasaryan
2023-03-06 15:42 ` [PATCH] powerpc/mm: fix mmap_lock bad unlock Laurent Dufour
2023-03-06 20:25 ` [PATCH v4 31/33] powerc/mm: try VMA lock-based page fault handling first Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 32/33] mm/mmap: free vm_area_struct without call_rcu in exit_mmap Suren Baghdasaryan
2023-02-27 17:36 ` [PATCH v4 33/33] mm: separate vma->lock from vm_area_struct Suren Baghdasaryan
2023-07-11 10:35 ` [PATCH v4 00/33] Per-VMA locks Leon Romanovsky
2023-07-11 10:39 ` Vlastimil Babka
2023-07-11 11:01 ` Leon Romanovsky
2023-07-11 11:09 ` Leon Romanovsky
2023-07-11 16:35 ` Suren Baghdasaryan
2023-07-11 17:14 ` Leon Romanovsky
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=20230227173632.3292573-4-surenb@google.com \
--to=surenb@google.com \
--cc=akpm@linux-foundation.org \
--cc=arjunroy@google.com \
--cc=axelrasmussen@google.com \
--cc=bigeasy@linutronix.de \
--cc=chriscli@google.com \
--cc=dave@stgolabs.net \
--cc=david@redhat.com \
--cc=dhowells@redhat.com \
--cc=edumazet@google.com \
--cc=gthelen@google.com \
--cc=gurua@google.com \
--cc=hannes@cmpxchg.org \
--cc=hughd@google.com \
--cc=jannh@google.com \
--cc=jglisse@google.com \
--cc=joelaf@google.com \
--cc=kent.overstreet@linux.dev \
--cc=kernel-team@android.com \
--cc=ldufour@linux.ibm.com \
--cc=leewalsh@google.com \
--cc=liam.howlett@oracle.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=lstoakes@gmail.com \
--cc=luto@kernel.org \
--cc=mgorman@techsingularity.net \
--cc=mhocko@suse.com \
--cc=michalechner92@googlemail.com \
--cc=michel@lespinasse.org \
--cc=minchan@google.com \
--cc=mingo@redhat.com \
--cc=paulmck@kernel.org \
--cc=peterjung1337@gmail.com \
--cc=peterx@redhat.com \
--cc=peterz@infradead.org \
--cc=posk@google.com \
--cc=punit.agrawal@bytedance.com \
--cc=rientjes@google.com \
--cc=rppt@kernel.org \
--cc=shakeelb@google.com \
--cc=soheil@google.com \
--cc=songliubraving@fb.com \
--cc=tatashin@google.com \
--cc=vbabka@suse.cz \
--cc=will@kernel.org \
--cc=willy@infradead.org \
--cc=x86@kernel.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