scsi: hisi_sas: Fix the conflict between dev gone and host reset

[ Upstream commit d2fc401e47529d9ffd2673a5395d56002e31ad98 ]

There is a possible conflict when a device is removed and host reset occurs
concurrently.

The reason is that then the device is notified as gone, we try to clear the
ITCT, which is notified via an interrupt. The dev gone function pends on
this event with a completion, which is completed when the ITCT interrupt
occurs.

But host reset will disable all interrupts, the wait_for_completion() may
wait indefinitely.

This patch adds an semaphore to synchronise this two processes. The
semaphore is taken by the host reset as the basis of synchronising.

Signed-off-by: Xiaofei Tan <tanxiaofei@huawei.com>
Signed-off-by: John Garry <john.garry@huawei.com>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>
Signed-off-by: Sasha Levin <alexander.levin@microsoft.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/drivers/scsi/hisi_sas/hisi_sas.h b/drivers/scsi/hisi_sas/hisi_sas.h
index 7052a5d45f7f98fddcaf9adc16df764df888f060..78e5a9254143f40629a05dd3387af6491623a11e 100644 (file)
--- a/drivers/scsi/hisi_sas/hisi_sas.h
+++ b/drivers/scsi/hisi_sas/hisi_sas.h
@@ -277,6 +277,7 @@ struct hisi_hba {
 
        int n_phy;
        spinlock_t lock;
+       struct semaphore sem;
 
        struct timer_list timer;
        struct workqueue_struct *wq;

diff --git a/drivers/scsi/hisi_sas/hisi_sas_main.c b/drivers/scsi/hisi_sas/hisi_sas_main.c
index 6f562974f8f6b44829ac5dda778a6baccde819fa..bfbd2fb7e69eb9d63429f81947e066b282b831ff 100644 (file)
--- a/drivers/scsi/hisi_sas/hisi_sas_main.c
+++ b/drivers/scsi/hisi_sas/hisi_sas_main.c
@@ -914,7 +914,9 @@ static void hisi_sas_dev_gone(struct domain_device *device)
 
                hisi_sas_dereg_device(hisi_hba, device);
 
+               down(&hisi_hba->sem);
                hisi_hba->hw->clear_itct(hisi_hba, sas_dev);
+               up(&hisi_hba->sem);
                device->lldd_dev = NULL;
        }
 
@@ -1364,6 +1366,7 @@ static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
        if (test_and_set_bit(HISI_SAS_RESET_BIT, &hisi_hba->flags))
                return -1;
 
+       down(&hisi_hba->sem);
        dev_info(dev, "controller resetting...\n");
        old_state = hisi_hba->hw->get_phys_state(hisi_hba);
 
@@ -1378,6 +1381,7 @@ static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
        if (rc) {
                dev_warn(dev, "controller reset failed (%d)\n", rc);
                clear_bit(HISI_SAS_REJECT_CMD_BIT, &hisi_hba->flags);
+               up(&hisi_hba->sem);
                scsi_unblock_requests(shost);
                goto out;
        }
@@ -1388,6 +1392,7 @@ static int hisi_sas_controller_reset(struct hisi_hba *hisi_hba)
        hisi_hba->hw->phys_init(hisi_hba);
        msleep(1000);
        hisi_sas_refresh_port_id(hisi_hba);
+       up(&hisi_hba->sem);
 
        if (hisi_hba->reject_stp_links_msk)
                hisi_sas_terminate_stp_reject(hisi_hba);
@@ -2016,6 +2021,7 @@ int hisi_sas_alloc(struct hisi_hba *hisi_hba, struct Scsi_Host *shost)
        struct device *dev = hisi_hba->dev;
        int i, s, max_command_entries = hisi_hba->hw->max_command_entries;
 
+       sema_init(&hisi_hba->sem, 1);
        spin_lock_init(&hisi_hba->lock);
        for (i = 0; i < hisi_hba->n_phy; i++) {
                hisi_sas_phy_init(hisi_hba, i);