lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <20231027223651.36047-4-brett.creeley@amd.com>
Date:   Fri, 27 Oct 2023 15:36:51 -0700
From:   Brett Creeley <brett.creeley@....com>
To:     <jgg@...pe.ca>, <yishaih@...dia.com>,
        <shameerali.kolothum.thodi@...wei.com>, <kevin.tian@...el.com>,
        <alex.williamson@...hat.com>, <dan.carpenter@...aro.org>
CC:     <kvm@...r.kernel.org>, <linux-kernel@...r.kernel.org>,
        <brett.creeley@....com>, <shannon.nelson@....com>
Subject: [PATCH v3 vfio 3/3] pds/vfio: Fix possible sleep while in atomic context

The driver could possibly sleep while in atomic context resulting
in the following call trace while CONFIG_DEBUG_ATOMIC_SLEEP=y is
set:

BUG: sleeping function called from invalid context at kernel/locking/mutex.c:283
in_atomic(): 1, irqs_disabled(): 0, non_block: 0, pid: 2817, name: bash
preempt_count: 1, expected: 0
RCU nest depth: 0, expected: 0
Call Trace:
 <TASK>
 dump_stack_lvl+0x36/0x50
 __might_resched+0x123/0x170
 mutex_lock+0x1e/0x50
 pds_vfio_put_lm_file+0x1e/0xa0 [pds_vfio_pci]
 pds_vfio_put_save_file+0x19/0x30 [pds_vfio_pci]
 pds_vfio_state_mutex_unlock+0x2e/0x80 [pds_vfio_pci]
 pci_reset_function+0x4b/0x70
 reset_store+0x5b/0xa0
 kernfs_fop_write_iter+0x137/0x1d0
 vfs_write+0x2de/0x410
 ksys_write+0x5d/0xd0
 do_syscall_64+0x3b/0x90
 entry_SYSCALL_64_after_hwframe+0x6e/0xd8

This can happen if pds_vfio_put_restore_file() and/or
pds_vfio_put_save_file() grab the mutex_lock(&lm_file->lock)
while the spin_lock(&pds_vfio->reset_lock) is held, which can
happen during while calling pds_vfio_state_mutex_unlock().

Fix this by changing the reset_lock to reset_mutex so there are no such
conerns. Also, make sure to destroy the reset_mutex in the driver specific
VFIO device release function.

Reported-by: Dan Carpenter <dan.carpenter@...aro.org>
Closes: https://lore.kernel.org/kvm/1f9bc27b-3de9-4891-9687-ba2820c1b390@moroto.mountain/
Signed-off-by: Brett Creeley <brett.creeley@....com>
Reviewed-by: Shannon Nelson <shannon.nelson@....com>
---
 drivers/vfio/pci/pds/pci_drv.c  |  4 ++--
 drivers/vfio/pci/pds/vfio_dev.c | 15 ++++++++-------
 drivers/vfio/pci/pds/vfio_dev.h |  2 +-
 3 files changed, 11 insertions(+), 10 deletions(-)

diff --git a/drivers/vfio/pci/pds/pci_drv.c b/drivers/vfio/pci/pds/pci_drv.c
index ab4b5958e413..caffa1a2cf59 100644
--- a/drivers/vfio/pci/pds/pci_drv.c
+++ b/drivers/vfio/pci/pds/pci_drv.c
@@ -55,10 +55,10 @@ static void pds_vfio_recovery(struct pds_vfio_pci_device *pds_vfio)
 	 * VFIO_DEVICE_STATE_RUNNING.
 	 */
 	if (deferred_reset_needed) {
-		spin_lock(&pds_vfio->reset_lock);
+		mutex_lock(&pds_vfio->reset_mutex);
 		pds_vfio->deferred_reset = true;
 		pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_ERROR;
-		spin_unlock(&pds_vfio->reset_lock);
+		mutex_unlock(&pds_vfio->reset_mutex);
 	}
 }
 
diff --git a/drivers/vfio/pci/pds/vfio_dev.c b/drivers/vfio/pci/pds/vfio_dev.c
index 306b1c25f016..4c351c59d05a 100644
--- a/drivers/vfio/pci/pds/vfio_dev.c
+++ b/drivers/vfio/pci/pds/vfio_dev.c
@@ -29,7 +29,7 @@ struct pds_vfio_pci_device *pds_vfio_pci_drvdata(struct pci_dev *pdev)
 void pds_vfio_state_mutex_unlock(struct pds_vfio_pci_device *pds_vfio)
 {
 again:
-	spin_lock(&pds_vfio->reset_lock);
+	mutex_lock(&pds_vfio->reset_mutex);
 	if (pds_vfio->deferred_reset) {
 		pds_vfio->deferred_reset = false;
 		if (pds_vfio->state == VFIO_DEVICE_STATE_ERROR) {
@@ -39,23 +39,23 @@ void pds_vfio_state_mutex_unlock(struct pds_vfio_pci_device *pds_vfio)
 		}
 		pds_vfio->state = pds_vfio->deferred_reset_state;
 		pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_RUNNING;
-		spin_unlock(&pds_vfio->reset_lock);
+		mutex_unlock(&pds_vfio->reset_mutex);
 		goto again;
 	}
 	mutex_unlock(&pds_vfio->state_mutex);
-	spin_unlock(&pds_vfio->reset_lock);
+	mutex_unlock(&pds_vfio->reset_mutex);
 }
 
 void pds_vfio_reset(struct pds_vfio_pci_device *pds_vfio)
 {
-	spin_lock(&pds_vfio->reset_lock);
+	mutex_lock(&pds_vfio->reset_mutex);
 	pds_vfio->deferred_reset = true;
 	pds_vfio->deferred_reset_state = VFIO_DEVICE_STATE_RUNNING;
 	if (!mutex_trylock(&pds_vfio->state_mutex)) {
-		spin_unlock(&pds_vfio->reset_lock);
+		mutex_unlock(&pds_vfio->reset_mutex);
 		return;
 	}
-	spin_unlock(&pds_vfio->reset_lock);
+	mutex_unlock(&pds_vfio->reset_mutex);
 	pds_vfio_state_mutex_unlock(pds_vfio);
 }
 
@@ -156,7 +156,7 @@ static int pds_vfio_init_device(struct vfio_device *vdev)
 	pds_vfio->vf_id = vf_id;
 
 	mutex_init(&pds_vfio->state_mutex);
-	spin_lock_init(&pds_vfio->reset_lock);
+	mutex_init(&pds_vfio->reset_mutex);
 
 	vdev->migration_flags = VFIO_MIGRATION_STOP_COPY | VFIO_MIGRATION_P2P;
 	vdev->mig_ops = &pds_vfio_lm_ops;
@@ -178,6 +178,7 @@ static void pds_vfio_release_device(struct vfio_device *vdev)
 			     vfio_coredev.vdev);
 
 	mutex_destroy(&pds_vfio->state_mutex);
+	mutex_destroy(&pds_vfio->reset_mutex);
 	vfio_pci_core_release_dev(vdev);
 }
 
diff --git a/drivers/vfio/pci/pds/vfio_dev.h b/drivers/vfio/pci/pds/vfio_dev.h
index b8f2d667608f..e7b01080a1ec 100644
--- a/drivers/vfio/pci/pds/vfio_dev.h
+++ b/drivers/vfio/pci/pds/vfio_dev.h
@@ -18,7 +18,7 @@ struct pds_vfio_pci_device {
 	struct pds_vfio_dirty dirty;
 	struct mutex state_mutex; /* protect migration state */
 	enum vfio_device_mig_state state;
-	spinlock_t reset_lock; /* protect reset_done flow */
+	struct mutex reset_mutex; /* protect reset_done flow */
 	u8 deferred_reset;
 	enum vfio_device_mig_state deferred_reset_state;
 	struct notifier_block nb;
-- 
2.17.1

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ