Stable Archive on lore.kernel.org
 help / color / Atom feed
From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>,
	John Hubbard <jhubbard@nvidia.com>,
	Sasha Levin <sashal@kernel.org>,
	linux-nfs@vger.kernel.org
Subject: [PATCH AUTOSEL 4.19 40/68] NFSv4: Fix a potential sleep while atomic in nfs4_do_reclaim()
Date: Tue, 13 Aug 2019 22:15:18 -0400
Message-ID: <20190814021548.16001-40-sashal@kernel.org> (raw)
In-Reply-To: <20190814021548.16001-1-sashal@kernel.org>

From: Trond Myklebust <trond.myklebust@hammerspace.com>

[ Upstream commit c77e22834ae9a11891cb613bd9a551be1b94f2bc ]

John Hubbard reports seeing the following stack trace:

nfs4_do_reclaim
   rcu_read_lock /* we are now in_atomic() and must not sleep */
       nfs4_purge_state_owners
           nfs4_free_state_owner
               nfs4_destroy_seqid_counter
                   rpc_destroy_wait_queue
                       cancel_delayed_work_sync
                           __cancel_work_timer
                               __flush_work
                                   start_flush_work
                                       might_sleep:
                                        (kernel/workqueue.c:2975: BUG)

The solution is to separate out the freeing of the state owners
from nfs4_purge_state_owners(), and perform that outside the atomic
context.

Reported-by: John Hubbard <jhubbard@nvidia.com>
Fixes: 0aaaf5c424c7f ("NFS: Cache state owners after files are closed")
Signed-off-by: Trond Myklebust <trond.myklebust@hammerspace.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 fs/nfs/nfs4_fs.h    |  3 ++-
 fs/nfs/nfs4client.c |  5 ++++-
 fs/nfs/nfs4state.c  | 27 ++++++++++++++++++++++-----
 3 files changed, 28 insertions(+), 7 deletions(-)

diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 63287d911c088..5b61520dce888 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -469,7 +469,8 @@ static inline void nfs4_schedule_session_recovery(struct nfs4_session *session,
 
 extern struct nfs4_state_owner *nfs4_get_state_owner(struct nfs_server *, struct rpc_cred *, gfp_t);
 extern void nfs4_put_state_owner(struct nfs4_state_owner *);
-extern void nfs4_purge_state_owners(struct nfs_server *);
+extern void nfs4_purge_state_owners(struct nfs_server *, struct list_head *);
+extern void nfs4_free_state_owners(struct list_head *head);
 extern struct nfs4_state * nfs4_get_open_state(struct inode *, struct nfs4_state_owner *);
 extern void nfs4_put_open_state(struct nfs4_state *);
 extern void nfs4_close_state(struct nfs4_state *, fmode_t);
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 8f53455c47653..86991bcfbeb12 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -754,9 +754,12 @@ int nfs41_walk_client_list(struct nfs_client *new,
 
 static void nfs4_destroy_server(struct nfs_server *server)
 {
+	LIST_HEAD(freeme);
+
 	nfs_server_return_all_delegations(server);
 	unset_pnfs_layoutdriver(server);
-	nfs4_purge_state_owners(server);
+	nfs4_purge_state_owners(server, &freeme);
+	nfs4_free_state_owners(&freeme);
 }
 
 /*
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index 3ba2087469ac8..c36ef75f2054b 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -628,24 +628,39 @@ void nfs4_put_state_owner(struct nfs4_state_owner *sp)
 /**
  * nfs4_purge_state_owners - Release all cached state owners
  * @server: nfs_server with cached state owners to release
+ * @head: resulting list of state owners
  *
  * Called at umount time.  Remaining state owners will be on
  * the LRU with ref count of zero.
+ * Note that the state owners are not freed, but are added
+ * to the list @head, which can later be used as an argument
+ * to nfs4_free_state_owners.
  */
-void nfs4_purge_state_owners(struct nfs_server *server)
+void nfs4_purge_state_owners(struct nfs_server *server, struct list_head *head)
 {
 	struct nfs_client *clp = server->nfs_client;
 	struct nfs4_state_owner *sp, *tmp;
-	LIST_HEAD(doomed);
 
 	spin_lock(&clp->cl_lock);
 	list_for_each_entry_safe(sp, tmp, &server->state_owners_lru, so_lru) {
-		list_move(&sp->so_lru, &doomed);
+		list_move(&sp->so_lru, head);
 		nfs4_remove_state_owner_locked(sp);
 	}
 	spin_unlock(&clp->cl_lock);
+}
 
-	list_for_each_entry_safe(sp, tmp, &doomed, so_lru) {
+/**
+ * nfs4_purge_state_owners - Release all cached state owners
+ * @head: resulting list of state owners
+ *
+ * Frees a list of state owners that was generated by
+ * nfs4_purge_state_owners
+ */
+void nfs4_free_state_owners(struct list_head *head)
+{
+	struct nfs4_state_owner *sp, *tmp;
+
+	list_for_each_entry_safe(sp, tmp, head, so_lru) {
 		list_del(&sp->so_lru);
 		nfs4_free_state_owner(sp);
 	}
@@ -1843,12 +1858,13 @@ static int nfs4_do_reclaim(struct nfs_client *clp, const struct nfs4_state_recov
 	struct nfs4_state_owner *sp;
 	struct nfs_server *server;
 	struct rb_node *pos;
+	LIST_HEAD(freeme);
 	int status = 0;
 
 restart:
 	rcu_read_lock();
 	list_for_each_entry_rcu(server, &clp->cl_superblocks, client_link) {
-		nfs4_purge_state_owners(server);
+		nfs4_purge_state_owners(server, &freeme);
 		spin_lock(&clp->cl_lock);
 		for (pos = rb_first(&server->state_owners);
 		     pos != NULL;
@@ -1877,6 +1893,7 @@ static int nfs4_do_reclaim(struct nfs_client *clp, const struct nfs4_state_recov
 		spin_unlock(&clp->cl_lock);
 	}
 	rcu_read_unlock();
+	nfs4_free_state_owners(&freeme);
 	return 0;
 }
 
-- 
2.20.1


  parent reply index

Thread overview: 69+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-08-14  2:14 [PATCH AUTOSEL 4.19 01/68] iio: adc: max9611: Fix misuse of GENMASK macro Sasha Levin
2019-08-14  2:14 ` [PATCH AUTOSEL 4.19 02/68] iio: cros_ec_accel_legacy: Fix incorrect channel setting Sasha Levin
2019-08-14  2:14 ` [PATCH AUTOSEL 4.19 03/68] HID: Add 044f:b320 ThrustMaster, Inc. 2 in 1 DT Sasha Levin
2019-08-14  2:14 ` [PATCH AUTOSEL 4.19 04/68] MIPS: kernel: only use i8253 clocksource with periodic clockevent Sasha Levin
2019-08-14  2:14 ` [PATCH AUTOSEL 4.19 05/68] mips: fix cacheinfo Sasha Levin
2019-08-14  2:14 ` [PATCH AUTOSEL 4.19 06/68] netfilter: ebtables: fix a memory leak bug in compat Sasha Levin
2019-08-14  2:14 ` [PATCH AUTOSEL 4.19 07/68] ASoC: dapm: Fix handling of custom_stop_condition on DAPM graph walks Sasha Levin
2019-08-14  2:14 ` [PATCH AUTOSEL 4.19 08/68] selftests/bpf: fix sendmsg6_prog on s390 Sasha Levin
2019-08-14  2:14 ` [PATCH AUTOSEL 4.19 09/68] bonding: Force slave speed check after link state recovery for 802.3ad Sasha Levin
2019-08-14  2:14 ` [PATCH AUTOSEL 4.19 10/68] net: mvpp2: Don't check for 3 consecutive Idle frames for 10G links Sasha Levin
2019-08-14  2:14 ` [PATCH AUTOSEL 4.19 11/68] selftests: forwarding: gre_multipath: Enable IPv4 forwarding Sasha Levin
2019-08-14  2:14 ` [PATCH AUTOSEL 4.19 12/68] selftests: forwarding: gre_multipath: Fix flower filters Sasha Levin
2019-08-14  2:14 ` [PATCH AUTOSEL 4.19 13/68] can: dev: call netif_carrier_off() in register_candev() Sasha Levin
2019-08-14  2:14 ` [PATCH AUTOSEL 4.19 14/68] can: mcp251x: add error check when wq alloc failed Sasha Levin
2019-08-14  2:14 ` [PATCH AUTOSEL 4.19 15/68] can: gw: Fix error path of cgw_module_init Sasha Levin
2019-08-14  2:14 ` [PATCH AUTOSEL 4.19 16/68] ASoC: Fail card instantiation if DAI format setup fails Sasha Levin
2019-08-14  2:14 ` [PATCH AUTOSEL 4.19 17/68] st21nfca_connectivity_event_received: null check the allocation Sasha Levin
2019-08-14  2:14 ` [PATCH AUTOSEL 4.19 18/68] st_nci_hci_connectivity_event_received: " Sasha Levin
2019-08-14  2:14 ` [PATCH AUTOSEL 4.19 19/68] ASoC: rockchip: Fix mono capture Sasha Levin
2019-08-14  2:14 ` [PATCH AUTOSEL 4.19 20/68] ASoC: ti: davinci-mcasp: Correct slot_width posed constraint Sasha Levin
2019-08-14  2:14 ` [PATCH AUTOSEL 4.19 21/68] net: usb: qmi_wwan: Add the BroadMobi BM818 card Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 22/68] qed: RDMA - Fix the hw_ver returned in device attributes Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 23/68] isdn: mISDN: hfcsusb: Fix possible null-pointer dereferences in start_isoc_chain() Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 24/68] mac80211_hwsim: Fix possible null-pointer dereferences in hwsim_dump_radio_nl() Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 25/68] netfilter: ipset: Actually allow destination MAC address for hash:ip,mac sets too Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 26/68] netfilter: ipset: Copy the right MAC address in bitmap:ip,mac and hash:ip,mac sets Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 27/68] netfilter: ipset: Fix rename concurrency with listing Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 28/68] netfilter: ebtables: also count base chain policies Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 29/68] rxrpc: Fix potential deadlock Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 30/68] rxrpc: Fix the lack of notification when sendmsg() fails on a DATA packet Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 31/68] driver core: Fix use-after-free and double free on glue directory Sasha Levin
2019-08-14  7:36   ` Greg Kroah-Hartman
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 32/68] isdn: hfcsusb: Fix mISDN driver crash caused by transfer buffer on the stack Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 33/68] net: phy: phy_led_triggers: Fix a possible null-pointer dereference in phy_led_trigger_change_speed() Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 34/68] perf bench numa: Fix cpu0 binding Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 35/68] Input: kbtab - sanity check for endpoint type Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 36/68] net: usb: pegasus: fix improper read if get_registers() fail Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 37/68] can: sja1000: force the string buffer NULL-terminated Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 38/68] can: peak_usb: " Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 39/68] net/ethernet/qlogic/qed: " Sasha Levin
2019-08-14  2:15 ` Sasha Levin [this message]
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 41/68] NFS: Fix regression whereby fscache errors are appearing on 'nofsc' mounts Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 42/68] HID: quirks: Set the INCREMENT_USAGE_ON_DUPLICATE quirk on Saitek X52 Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 43/68] HID: holtek: test for sanity of intfdata Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 44/68] HID: input: fix a4tech horizontal wheel custom usage Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 45/68] drm/rockchip: Suspend DP late Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 46/68] SMB3: Fix potential memory leak when processing compound chain Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 47/68] SMB3: Kernel oops mounting a encryptData share with CONFIG_DEBUG_VIRTUAL Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 48/68] HID: hiddev: avoid opening a disconnected device Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 49/68] HID: hiddev: do cleanup in failure of opening a device Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 50/68] s390: put _stext and _etext into .text section Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 51/68] Input: iforce - add sanity checks Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 52/68] net: cxgb3_main: Fix a resource leak in a error path in 'init_one()' Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 53/68] net: stmmac: Fix issues when number of Queues >= 4 Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 54/68] net: stmmac: tc: Do not return a fragment entry Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 55/68] net: hisilicon: make hip04_tx_reclaim non-reentrant Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 56/68] net: hisilicon: fix hip04-xmit never return TX_BUSY Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 57/68] net: hisilicon: Fix dma_map_single failed on arm64 Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 58/68] libata: have ata_scsi_rw_xlat() fail invalid passthrough requests Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 59/68] libata: add SG safety checks in SFF pio transfers Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 60/68] x86/lib/cpu: Address missing prototypes warning Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 61/68] drm/vmwgfx: fix memory leak when too many retries have occurred Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 62/68] block, bfq: handle NULL return value by bfq_init_rq() Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 63/68] perf ftrace: Fix failure to set cpumask when only one cpu is present Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 64/68] perf cpumap: Fix writing to illegal memory in handling cpumap mask Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 65/68] perf pmu-events: Fix missing "cpu_clk_unhalted.core" event Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 66/68] KVM: arm64: Don't write junk to sysregs on reset Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 67/68] KVM: arm: Don't write junk to CP15 registers " Sasha Levin
2019-08-14  2:15 ` [PATCH AUTOSEL 4.19 68/68] selftests: kvm: Adding config fragments Sasha Levin

Reply instructions:

You may reply publically 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=20190814021548.16001-40-sashal@kernel.org \
    --to=sashal@kernel.org \
    --cc=jhubbard@nvidia.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-nfs@vger.kernel.org \
    --cc=stable@vger.kernel.org \
    --cc=trond.myklebust@hammerspace.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

Stable Archive on lore.kernel.org

Archives are clonable:
	git clone --mirror https://lore.kernel.org/stable/0 stable/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 stable stable/ https://lore.kernel.org/stable \
		stable@vger.kernel.org
	public-inbox-index stable

Example config snippet for mirrors

Newsgroup available over NNTP:
	nntp://nntp.lore.kernel.org/org.kernel.vger.stable


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