IB/hfi1: Prevent LNI out of sync by resetting host interface version

When the link is disabled and re-enabled, the host version bit is not
set again, so the firmware behaves as though it’s interacting with an
old driver. This causes LNI to get out of sync. The host version bit
needs to be set at load_8051_firmware() and _dc_start(). Currently, it's
only set at load_8051_firmware().

Create a common function to set the bit with the intent to make the code
more maintainable in the future, set the host version bit at _dc_start()
and modify the 8051 command API to prevent a deadlock as _dc_start() is
already holding the dc8051 lock.

Fixes: 913cc67159bc ("IB/hfi1: Always perform offline transition")
Reviewed-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: Mike Marciniszyn <mike.marciniszyn@intel.com>
Signed-off-by: Sebastian Sanchez <sebastian.sanchez@intel.com>
Signed-off-by: Dennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

1 files changed, 47 insertions, 16 deletions

diff --git a/drivers/infiniband/hw/hfi1/firmware.c b/drivers/infiniband/hw/hfi1/firmware.c
index 9471c4063ebe..dee3c674f33d 100644
--- a/drivers/infiniband/hw/hfi1/firmware.c
+++ b/drivers/infiniband/hw/hfi1/firmware.c
@@ -971,6 +971,46 @@ int wait_fm_ready(struct hfi1_devdata *dd, u32 mstimeout)
 }
 
 /*
+ * Clear all reset bits, releasing the 8051.
+ * Wait for firmware to be ready to accept host requests.
+ * Then, set host version bit.
+ *
+ * This function executes even if the 8051 is in reset mode when
+ * dd->dc_shutdown == 1.
+ *
+ * Expects dd->dc8051_lock to be held.
+ */
+int release_and_wait_ready_8051_firmware(struct hfi1_devdata *dd)
+{
+	int ret;
+
+	lockdep_assert_held(&dd->dc8051_lock);
+	/* clear all reset bits, releasing the 8051 */
+	write_csr(dd, DC_DC8051_CFG_RST, 0ull);
+
+	/*
+	 * Wait for firmware to be ready to accept host
+	 * requests.
+	 */
+	ret = wait_fm_ready(dd, TIMEOUT_8051_START);
+	if (ret) {
+		dd_dev_err(dd, "8051 start timeout, current FW state 0x%x\n",
+			   get_firmware_state(dd));
+		return ret;
+	}
+
+	ret = write_host_interface_version(dd, HOST_INTERFACE_VERSION);
+	if (ret != HCMD_SUCCESS) {
+		dd_dev_err(dd,
+			   "Failed to set host interface version, return 0x%x\n",
+			   ret);
+		return -EIO;
+	}
+
+	return 0;
+}
+
+/*
  * Load the 8051 firmware.
  */
 static int load_8051_firmware(struct hfi1_devdata *dd,
@@ -1035,31 +1075,22 @@ static int load_8051_firmware(struct hfi1_devdata *dd,
 	if (ret)
 		return ret;
 
-	/* clear all reset bits, releasing the 8051 */
-	write_csr(dd, DC_DC8051_CFG_RST, 0ull);
-
 	/*
+	 * Clear all reset bits, releasing the 8051.
 	 * DC reset step 5. Wait for firmware to be ready to accept host
 	 * requests.
+	 * Then, set host version bit.
 	 */
-	ret = wait_fm_ready(dd, TIMEOUT_8051_START);
-	if (ret) { /* timed out */
-		dd_dev_err(dd, "8051 start timeout, current state 0x%x\n",
-			   get_firmware_state(dd));
-		return -ETIMEDOUT;
-	}
+	mutex_lock(&dd->dc8051_lock);
+	ret = release_and_wait_ready_8051_firmware(dd);
+	mutex_unlock(&dd->dc8051_lock);
+	if (ret)
+		return ret;
 
 	read_misc_status(dd, &ver_major, &ver_minor, &ver_patch);
 	dd_dev_info(dd, "8051 firmware version %d.%d.%d\n",
 		    (int)ver_major, (int)ver_minor, (int)ver_patch);
 	dd->dc8051_ver = dc8051_ver(ver_major, ver_minor, ver_patch);
-	ret = write_host_interface_version(dd, HOST_INTERFACE_VERSION);
-	if (ret != HCMD_SUCCESS) {
-		dd_dev_err(dd,
-			   "Failed to set host interface version, return 0x%x\n",
-			   ret);
-		return -EIO;
-	}
 
 	return 0;
 }