scsi: ufs: Fix a race between the interrupt handler and the reset handler

Prevent that both the interrupt handler and the reset handler try to
complete a request at the same time. This patch is the result of an
analysis of the following crash:

Unable to handle kernel NULL pointer dereference at virtual address 0000000000000120
CPU: 0 PID: 0 Comm: swapper/0 Tainted: G           OE     5.10.107-android13-4-00051-g1e48e8970cca-ab8664745 #1
pc : ufshcd_release_scsi_cmd+0x30/0x46c
lr : __ufshcd_transfer_req_compl+0x4fc/0x9c0
Call trace:
 ufshcd_release_scsi_cmd+0x30/0x46c
 __ufshcd_transfer_req_compl+0x4fc/0x9c0
 ufshcd_poll+0xf0/0x208
 ufshcd_sl_intr+0xb8/0xf0
 ufshcd_intr+0x168/0x2f4
 __handle_irq_event_percpu+0xa0/0x30c
 handle_irq_event+0x84/0x178
 handle_fasteoi_irq+0x150/0x2e8
 __handle_domain_irq+0x114/0x1e4
 gic_handle_irq.31846+0x58/0x300
 el1_irq+0xe4/0x1c0
 cpuidle_enter_state+0x3ac/0x8c4
 do_idle+0x2fc/0x55c
 cpu_startup_entry+0x84/0x90
 kernel_init+0x0/0x310
 start_kernel+0x0/0x608
 start_kernel+0x4ec/0x608

Link: https://lore.kernel.org/r/20220613214442.212466-4-bvanassche@acm.org
Reviewed-by: Stanley Chu <stanley.chu@mediatek.com>
Reviewed-by: Adrian Hunter <adrian.hunter@intel.com>
Signed-off-by: Bart Van Assche <bvanassche@acm.org>
Signed-off-by: Martin K. Petersen <martin.petersen@oracle.com>

diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
index 8789147760aebaea99cf6e6c6d470976204ecd2e..ce86d1b790c058ba6ac579d14e69258bf4b51a16 100644 (file)
--- a/drivers/ufs/core/ufshcd.c
+++ b/drivers/ufs/core/ufshcd.c
@@ -6968,14 +6968,14 @@ int ufshcd_exec_raw_upiu_cmd(struct ufs_hba *hba,
 }
 
 /**
- * ufshcd_eh_device_reset_handler - device reset handler registered to
- *                                    scsi layer.
+ * ufshcd_eh_device_reset_handler() - Reset a single logical unit.
  * @cmd: SCSI command pointer
  *
  * Returns SUCCESS/FAILED
  */
 static int ufshcd_eh_device_reset_handler(struct scsi_cmnd *cmd)
 {
+       unsigned long flags, pending_reqs = 0, not_cleared = 0;
        struct Scsi_Host *host;
        struct ufs_hba *hba;
        u32 pos;
@@ -6994,14 +6994,24 @@ static int ufshcd_eh_device_reset_handler(struct scsi_cmnd *cmd)
        }
 
        /* clear the commands that were pending for corresponding LUN */
-       for_each_set_bit(pos, &hba->outstanding_reqs, hba->nutrs) {
-               if (hba->lrb[pos].lun == lun) {
-                       err = ufshcd_clear_cmds(hba, 1U << pos);
-                       if (err)
-                               break;
-                       __ufshcd_transfer_req_compl(hba, 1U << pos);
-               }
+       spin_lock_irqsave(&hba->outstanding_lock, flags);
+       for_each_set_bit(pos, &hba->outstanding_reqs, hba->nutrs)
+               if (hba->lrb[pos].lun == lun)
+                       __set_bit(pos, &pending_reqs);
+       hba->outstanding_reqs &= ~pending_reqs;
+       spin_unlock_irqrestore(&hba->outstanding_lock, flags);
+
+       if (ufshcd_clear_cmds(hba, pending_reqs) < 0) {
+               spin_lock_irqsave(&hba->outstanding_lock, flags);
+               not_cleared = pending_reqs &
+                       ufshcd_readl(hba, REG_UTP_TRANSFER_REQ_DOOR_BELL);
+               hba->outstanding_reqs |= not_cleared;
+               spin_unlock_irqrestore(&hba->outstanding_lock, flags);
+
+               dev_err(hba->dev, "%s: failed to clear requests %#lx\n",
+                       __func__, not_cleared);
        }
+       __ufshcd_transfer_req_compl(hba, pending_reqs & ~not_cleared);
 
 out:
        hba->req_abort_count = 0;