Linux-mm Archive on lore.kernel.org
 help / color / Atom feed
From: Qian Cai <cai@lca.pw>
To: akpm@linux-foundation.org
Cc: jgg@ziepe.ca, paulmck@kernel.org, linux-mm@kvack.org,
	linux-kernel@vger.kernel.org, Qian Cai <cai@lca.pw>
Subject: [PATCH] mm/mmu_notifier: silence PROVE_RCU_LIST warnings
Date: Tue, 17 Mar 2020 13:56:40 -0400
Message-ID: <20200317175640.2047-1-cai@lca.pw> (raw)

It is safe to traverse mm->notifier_subscriptions->list either under
SRCU read lock or mm->notifier_subscriptions->lock using
hlist_for_each_entry_rcu(). Silence the PROVE_RCU_LIST false positives,
for example,

 WARNING: suspicious RCU usage
 -----------------------------
 mm/mmu_notifier.c:484 RCU-list traversed in non-reader section!!

 other info that might help us debug this:

 rcu_scheduler_active = 2, debug_locks = 1
 3 locks held by libvirtd/802:
  #0: ffff9321e3f58148 (&mm->mmap_sem#2){++++}, at: do_mprotect_pkey+0xe1/0x3e0
  #1: ffffffff91ae6160 (mmu_notifier_invalidate_range_start){+.+.}, at: change_p4d_range+0x5fa/0x800
  #2: ffffffff91ae6e08 (srcu){....}, at: __mmu_notifier_invalidate_range_start+0x178/0x460

 stack backtrace:
 CPU: 7 PID: 802 Comm: libvirtd Tainted: G          I       5.6.0-rc6-next-20200317+ #2
 Hardware name: HP ProLiant BL460c Gen8, BIOS I31 11/02/2014
 Call Trace:
  dump_stack+0xa4/0xfe
  lockdep_rcu_suspicious+0xeb/0xf5
  __mmu_notifier_invalidate_range_start+0x3ff/0x460
  change_p4d_range+0x746/0x800
  change_protection+0x1df/0x300
  mprotect_fixup+0x245/0x3e0
  do_mprotect_pkey+0x23b/0x3e0
  __x64_sys_mprotect+0x51/0x70
  do_syscall_64+0x91/0xae8
  entry_SYSCALL_64_after_hwframe+0x49/0xb3

Signed-off-by: Qian Cai <cai@lca.pw>
---
 mm/mmu_notifier.c | 27 ++++++++++++++++++---------
 1 file changed, 18 insertions(+), 9 deletions(-)

diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c
index ef3973a5d34a..06852b896fa6 100644
--- a/mm/mmu_notifier.c
+++ b/mm/mmu_notifier.c
@@ -307,7 +307,8 @@ static void mn_hlist_release(struct mmu_notifier_subscriptions *subscriptions,
 	 * ->release returns.
 	 */
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist)
+	hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist,
+				 srcu_read_lock_held(&srcu))
 		/*
 		 * If ->release runs before mmu_notifier_unregister it must be
 		 * handled, as it's the only way for the driver to flush all
@@ -370,7 +371,8 @@ int __mmu_notifier_clear_flush_young(struct mm_struct *mm,
 
 	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(subscription,
-				 &mm->notifier_subscriptions->list, hlist) {
+				 &mm->notifier_subscriptions->list, hlist,
+				 srcu_read_lock_held(&srcu)) {
 		if (subscription->ops->clear_flush_young)
 			young |= subscription->ops->clear_flush_young(
 				subscription, mm, start, end);
@@ -389,7 +391,8 @@ int __mmu_notifier_clear_young(struct mm_struct *mm,
 
 	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(subscription,
-				 &mm->notifier_subscriptions->list, hlist) {
+				 &mm->notifier_subscriptions->list, hlist,
+				 srcu_read_lock_held(&srcu)) {
 		if (subscription->ops->clear_young)
 			young |= subscription->ops->clear_young(subscription,
 								mm, start, end);
@@ -407,7 +410,8 @@ int __mmu_notifier_test_young(struct mm_struct *mm,
 
 	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(subscription,
-				 &mm->notifier_subscriptions->list, hlist) {
+				 &mm->notifier_subscriptions->list, hlist,
+				 srcu_read_lock_held(&srcu)) {
 		if (subscription->ops->test_young) {
 			young = subscription->ops->test_young(subscription, mm,
 							      address);
@@ -428,7 +432,8 @@ void __mmu_notifier_change_pte(struct mm_struct *mm, unsigned long address,
 
 	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(subscription,
-				 &mm->notifier_subscriptions->list, hlist) {
+				 &mm->notifier_subscriptions->list, hlist,
+				 srcu_read_lock_held(&srcu)) {
 		if (subscription->ops->change_pte)
 			subscription->ops->change_pte(subscription, mm, address,
 						      pte);
@@ -476,7 +481,8 @@ static int mn_hlist_invalidate_range_start(
 	int id;
 
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist) {
+	hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist,
+				 srcu_read_lock_held(&srcu)) {
 		const struct mmu_notifier_ops *ops = subscription->ops;
 
 		if (ops->invalidate_range_start) {
@@ -528,7 +534,8 @@ mn_hlist_invalidate_end(struct mmu_notifier_subscriptions *subscriptions,
 	int id;
 
 	id = srcu_read_lock(&srcu);
-	hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist) {
+	hlist_for_each_entry_rcu(subscription, &subscriptions->list, hlist,
+				 srcu_read_lock_held(&srcu)) {
 		/*
 		 * Call invalidate_range here too to avoid the need for the
 		 * subsystem of having to register an invalidate_range_end
@@ -582,7 +589,8 @@ void __mmu_notifier_invalidate_range(struct mm_struct *mm,
 
 	id = srcu_read_lock(&srcu);
 	hlist_for_each_entry_rcu(subscription,
-				 &mm->notifier_subscriptions->list, hlist) {
+				 &mm->notifier_subscriptions->list, hlist,
+				 srcu_read_lock_held(&srcu)) {
 		if (subscription->ops->invalidate_range)
 			subscription->ops->invalidate_range(subscription, mm,
 							    start, end);
@@ -714,7 +722,8 @@ find_get_mmu_notifier(struct mm_struct *mm, const struct mmu_notifier_ops *ops)
 
 	spin_lock(&mm->notifier_subscriptions->lock);
 	hlist_for_each_entry_rcu(subscription,
-				 &mm->notifier_subscriptions->list, hlist) {
+				 &mm->notifier_subscriptions->list, hlist,
+				 lockdep_is_held(&mm->notifier_subscriptions->lock)) {
 		if (subscription->ops != ops)
 			continue;
 
-- 
2.21.0 (Apple Git-122.2)



             reply index

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-03-17 17:56 Qian Cai [this message]
2020-03-17 18:06 ` Paul E. McKenney
2020-03-18 12:13 ` Jason Gunthorpe

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=20200317175640.2047-1-cai@lca.pw \
    --to=cai@lca.pw \
    --cc=akpm@linux-foundation.org \
    --cc=jgg@ziepe.ca \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=paulmck@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

Linux-mm Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/linux-mm/0 linux-mm/git/0.git

	# If you have public-inbox 1.1+ installed, you may
	# initialize and index your mirror using the following commands:
	public-inbox-init -V2 linux-mm linux-mm/ https://lore.kernel.org/linux-mm \
		linux-mm@kvack.org
	public-inbox-index linux-mm

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kvack.linux-mm


AGPL code for this site: git clone https://public-inbox.org/public-inbox.git