From: Yishai Hadas <yishaih@nvidia.com>
To: <alex.williamson@redhat.com>, <bhelgaas@google.com>,
<jgg@nvidia.com>, <saeedm@nvidia.com>
Cc: <linux-pci@vger.kernel.org>, <kvm@vger.kernel.org>,
<netdev@vger.kernel.org>, <kuba@kernel.org>, <leonro@nvidia.com>,
<kwankhede@nvidia.com>, <mgurtovoy@nvidia.com>,
<yishaih@nvidia.com>, <maorg@nvidia.com>, <ashok.raj@intel.com>,
<kevin.tian@intel.com>, <shameerali.kolothum.thodi@huawei.com>
Subject: [PATCH V7 mlx5-next 14/15] vfio/mlx5: Use its own PCI reset_done error handler
Date: Mon, 7 Feb 2022 19:22:15 +0200 [thread overview]
Message-ID: <20220207172216.206415-15-yishaih@nvidia.com> (raw)
In-Reply-To: <20220207172216.206415-1-yishaih@nvidia.com>
Register its own handler for pci_error_handlers.reset_done and update
state accordingly.
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
drivers/vfio/pci/mlx5/main.c | 57 ++++++++++++++++++++++++++++++++++--
1 file changed, 55 insertions(+), 2 deletions(-)
diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c
index acd205bcff70..63a889210ef3 100644
--- a/drivers/vfio/pci/mlx5/main.c
+++ b/drivers/vfio/pci/mlx5/main.c
@@ -28,9 +28,12 @@
struct mlx5vf_pci_core_device {
struct vfio_pci_core_device core_device;
u8 migrate_cap:1;
+ u8 deferred_reset:1;
/* protect migration state */
struct mutex state_mutex;
enum vfio_device_mig_state mig_state;
+ /* protect the reset_done flow */
+ spinlock_t reset_lock;
u16 vhca_id;
struct mlx5_vf_migration_file *resuming_migf;
struct mlx5_vf_migration_file *saving_migf;
@@ -437,6 +440,25 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
return ERR_PTR(-EINVAL);
}
+/*
+ * This function is called in all state_mutex unlock cases to
+ * handle a 'deferred_reset' if exists.
+ */
+static void mlx5vf_state_mutex_unlock(struct mlx5vf_pci_core_device *mvdev)
+{
+again:
+ spin_lock(&mvdev->reset_lock);
+ if (mvdev->deferred_reset) {
+ mvdev->deferred_reset = false;
+ spin_unlock(&mvdev->reset_lock);
+ mvdev->mig_state = VFIO_DEVICE_STATE_RUNNING;
+ mlx5vf_disable_fds(mvdev);
+ goto again;
+ }
+ mutex_unlock(&mvdev->state_mutex);
+ spin_unlock(&mvdev->reset_lock);
+}
+
static struct file *
mlx5vf_pci_set_device_state(struct vfio_device *vdev,
enum vfio_device_mig_state new_state)
@@ -465,7 +487,7 @@ mlx5vf_pci_set_device_state(struct vfio_device *vdev,
break;
}
}
- mutex_unlock(&mvdev->state_mutex);
+ mlx5vf_state_mutex_unlock(mvdev);
return res;
}
@@ -477,10 +499,34 @@ static int mlx5vf_pci_get_device_state(struct vfio_device *vdev,
mutex_lock(&mvdev->state_mutex);
*curr_state = mvdev->mig_state;
- mutex_unlock(&mvdev->state_mutex);
+ mlx5vf_state_mutex_unlock(mvdev);
return 0;
}
+static void mlx5vf_pci_aer_reset_done(struct pci_dev *pdev)
+{
+ struct mlx5vf_pci_core_device *mvdev = dev_get_drvdata(&pdev->dev);
+
+ if (!mvdev->migrate_cap)
+ return;
+
+ /*
+ * As the higher VFIO layers are holding locks across reset and using
+ * those same locks with the mm_lock we need to prevent ABBA deadlock
+ * with the state_mutex and mm_lock.
+ * In case the state_mutex was taken already we defer the cleanup work
+ * to the unlock flow of the other running context.
+ */
+ spin_lock(&mvdev->reset_lock);
+ mvdev->deferred_reset = true;
+ if (!mutex_trylock(&mvdev->state_mutex)) {
+ spin_unlock(&mvdev->reset_lock);
+ return;
+ }
+ spin_unlock(&mvdev->reset_lock);
+ mlx5vf_state_mutex_unlock(mvdev);
+}
+
static int mlx5vf_pci_open_device(struct vfio_device *core_vdev)
{
struct mlx5vf_pci_core_device *mvdev = container_of(
@@ -562,6 +608,7 @@ static int mlx5vf_pci_probe(struct pci_dev *pdev,
VFIO_MIGRATION_STOP_COPY |
VFIO_MIGRATION_P2P;
mutex_init(&mvdev->state_mutex);
+ spin_lock_init(&mvdev->reset_lock);
}
mlx5_vf_put_core_dev(mdev);
}
@@ -596,11 +643,17 @@ static const struct pci_device_id mlx5vf_pci_table[] = {
MODULE_DEVICE_TABLE(pci, mlx5vf_pci_table);
+static const struct pci_error_handlers mlx5vf_err_handlers = {
+ .reset_done = mlx5vf_pci_aer_reset_done,
+ .error_detected = vfio_pci_core_aer_err_detected,
+};
+
static struct pci_driver mlx5vf_pci_driver = {
.name = KBUILD_MODNAME,
.id_table = mlx5vf_pci_table,
.probe = mlx5vf_pci_probe,
.remove = mlx5vf_pci_remove,
+ .err_handler = &mlx5vf_err_handlers,
};
static void __exit mlx5vf_pci_cleanup(void)
--
2.18.1
next prev parent reply other threads:[~2022-02-07 17:33 UTC|newest]
Thread overview: 50+ messages / expand[flat|nested] mbox.gz Atom feed top
2022-02-07 17:22 [PATCH V7 mlx5-next 00/15] Add mlx5 live migration driver and v2 migration protocol Yishai Hadas
2022-02-07 17:22 ` [PATCH V7 mlx5-next 01/15] PCI/IOV: Add pci_iov_vf_id() to get VF index Yishai Hadas
2022-02-07 17:22 ` [PATCH V7 mlx5-next 02/15] net/mlx5: Reuse exported virtfn index function call Yishai Hadas
2022-02-07 17:22 ` [PATCH V7 mlx5-next 03/15] net/mlx5: Disable SRIOV before PF removal Yishai Hadas
2022-02-07 17:22 ` [PATCH V7 mlx5-next 04/15] PCI/IOV: Add pci_iov_get_pf_drvdata() to allow VF reaching the drvdata of a PF Yishai Hadas
2022-02-07 17:22 ` [PATCH V7 mlx5-next 05/15] net/mlx5: Expose APIs to get/put the mlx5 core device Yishai Hadas
2022-02-07 17:22 ` [PATCH V7 mlx5-next 06/15] net/mlx5: Introduce migration bits and structures Yishai Hadas
2022-02-07 17:22 ` [PATCH V7 mlx5-next 07/15] vfio: Have the core code decode the VFIO_DEVICE_FEATURE ioctl Yishai Hadas
2022-02-07 17:22 ` [PATCH V7 mlx5-next 08/15] vfio: Define device migration protocol v2 Yishai Hadas
2022-02-09 0:07 ` Alex Williamson
2022-02-09 2:36 ` Jason Gunthorpe
2022-02-15 10:41 ` Tian, Kevin
2022-02-15 16:04 ` Jason Gunthorpe
2022-02-15 23:32 ` Alex Williamson
2022-02-16 1:17 ` Jason Gunthorpe
2022-02-16 3:17 ` Tian, Kevin
2022-02-16 12:14 ` Jason Gunthorpe
2022-02-17 2:29 ` Tian, Kevin
2022-02-15 10:58 ` Tian, Kevin
2022-02-15 13:13 ` Jason Gunthorpe
2022-02-15 8:04 ` Tian, Kevin
2022-02-15 15:33 ` Jason Gunthorpe
2022-02-16 3:04 ` Tian, Kevin
2022-02-07 17:22 ` [PATCH V7 mlx5-next 09/15] vfio: Extend the device migration protocol with RUNNING_P2P Yishai Hadas
2022-02-15 10:18 ` Tian, Kevin
2022-02-15 15:56 ` Jason Gunthorpe
2022-02-16 2:52 ` Tian, Kevin
2022-02-16 12:11 ` Jason Gunthorpe
2022-02-07 17:22 ` [PATCH V7 mlx5-next 10/15] vfio: Remove migration protocol v1 documentation Yishai Hadas
2022-02-11 11:03 ` Cornelia Huck
2022-02-07 17:22 ` [PATCH V7 mlx5-next 11/15] vfio/mlx5: Expose migration commands over mlx5 device Yishai Hadas
2022-02-07 17:22 ` [PATCH V7 mlx5-next 12/15] vfio/mlx5: Implement vfio_pci driver for mlx5 devices Yishai Hadas
2022-02-09 0:07 ` Alex Williamson
2022-02-07 17:22 ` [PATCH V7 mlx5-next 13/15] vfio/pci: Expose vfio_pci_core_aer_err_detected() Yishai Hadas
2022-02-07 17:22 ` Yishai Hadas [this message]
2022-02-09 0:08 ` [PATCH V7 mlx5-next 14/15] vfio/mlx5: Use its own PCI reset_done error handler Alex Williamson
2022-02-09 2:39 ` Jason Gunthorpe
2022-02-10 16:48 ` Alex Williamson
2022-02-10 17:27 ` Jason Gunthorpe
2022-02-07 17:22 ` [PATCH V7 mlx5-next 15/15] vfio: Extend the device migration protocol with PRE_COPY Yishai Hadas
2022-02-17 17:15 ` Alex Williamson
2022-02-18 0:03 ` Jason Gunthorpe
2022-02-18 8:01 ` Tian, Kevin
2022-02-18 14:06 ` Jason Gunthorpe
2022-02-22 1:43 ` Tian, Kevin
2022-02-22 15:50 ` Jason Gunthorpe
2022-02-23 0:40 ` Tian, Kevin
2022-02-23 0:44 ` Jason Gunthorpe
2022-02-23 1:46 ` Tian, Kevin
2022-02-18 8:11 ` [PATCH V7 mlx5-next 00/15] Add mlx5 live migration driver and v2 migration protocol Tarun Gupta (SW-GPU)
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=20220207172216.206415-15-yishaih@nvidia.com \
--to=yishaih@nvidia.com \
--cc=alex.williamson@redhat.com \
--cc=ashok.raj@intel.com \
--cc=bhelgaas@google.com \
--cc=jgg@nvidia.com \
--cc=kevin.tian@intel.com \
--cc=kuba@kernel.org \
--cc=kvm@vger.kernel.org \
--cc=kwankhede@nvidia.com \
--cc=leonro@nvidia.com \
--cc=linux-pci@vger.kernel.org \
--cc=maorg@nvidia.com \
--cc=mgurtovoy@nvidia.com \
--cc=netdev@vger.kernel.org \
--cc=saeedm@nvidia.com \
--cc=shameerali.kolothum.thodi@huawei.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
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;
as well as URLs for NNTP newsgroup(s).