net: phy: aquantia: fix -ETIMEDOUT PHY probe failure when firmware not present

The author of the blamed commit apparently did not notice something
about aqr_wait_reset_complete(): it polls the exact same register -
MDIO_MMD_VEND1:VEND1_GLOBAL_FW_ID - as aqr_firmware_load().

Thus, the entire logic after the introduction of aqr_wait_reset_complete() is
now completely side-stepped, because if aqr_wait_reset_complete()
succeeds, MDIO_MMD_VEND1:VEND1_GLOBAL_FW_ID could have only been a
non-zero value. The handling of the case where the register reads as 0
is dead code, due to the previous -ETIMEDOUT having stopped execution
and returning a fatal error to the caller. We never attempt to load
new firmware if no firmware is present.

Based on static code analysis, I guess we should simply introduce a
switch/case statement based on the return code from aqr_wait_reset_complete(),
to determine whether to load firmware or not. I am not intending to
change the procedure through which the driver determines whether to load
firmware or not, as I am unaware of alternative possibilities.

At the same time, Russell King suggests that if aqr_wait_reset_complete()
is expected to return -ETIMEDOUT as part of normal operation and not
just catastrophic failure, the use of phy_read_mmd_poll_timeout() is
improper, since that has an embedded print inside. Just open-code a
call to read_poll_timeout() to avoid printing -ETIMEDOUT, but continue
printing actual read errors from the MDIO bus.

Fixes: ad649a1fac37 ("net: phy: aquantia: wait for FW reset before checking the vendor ID")
Reported-by: Clark Wang <xiaoning.wang@nxp.com>
Reported-by: Jon Hunter <jonathanh@nvidia.com>
Closes: https://lore.kernel.org/netdev/8ac00a45-ac61-41b4-9f74-d18157b8b6bf@nvidia.com/
Reported-by: Hans-Frieder Vogt <hfdevel@gmx.net>
Closes: https://lore.kernel.org/netdev/c7c1a3ae-be97-4929-8d89-04c8aa870209@gmx.net/
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Tested-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Tested-by: Hans-Frieder Vogt <hfdevel@gmx.net>
Link: https://patch.msgid.link/20240913121230.2620122-1-vladimir.oltean@nxp.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

diff --git a/drivers/net/phy/aquantia/aquantia_firmware.c b/drivers/net/phy/aquantia/aquantia_firmware.c
index 524627a36c6fc2482e60f12ca04198a792c7182a..dac6464b5fe2e36fd8b8b7c6ad3ca976500cff4e 100644 (file)
--- a/drivers/net/phy/aquantia/aquantia_firmware.c
+++ b/drivers/net/phy/aquantia/aquantia_firmware.c
@@ -353,26 +353,32 @@ int aqr_firmware_load(struct phy_device *phydev)
 {
        int ret;
 
-       ret = aqr_wait_reset_complete(phydev);
-       if (ret)
-               return ret;
-
-       /* Check if the firmware is not already loaded by pooling
-        * the current version returned by the PHY. If 0 is returned,
-        * no firmware is loaded.
+       /* Check if the firmware is not already loaded by polling
+        * the current version returned by the PHY.
         */
-       ret = phy_read_mmd(phydev, MDIO_MMD_VEND1, VEND1_GLOBAL_FW_ID);
-       if (ret > 0)
-               goto exit;
-
-       ret = aqr_firmware_load_nvmem(phydev);
-       if (!ret)
-               goto exit;
-
-       ret = aqr_firmware_load_fs(phydev);
-       if (ret)
+       ret = aqr_wait_reset_complete(phydev);
+       switch (ret) {
+       case 0:
+               /* Some firmware is loaded => do nothing */
+               return 0;
+       case -ETIMEDOUT:
+               /* VEND1_GLOBAL_FW_ID still reads 0 after 2 seconds of polling.
+                * We don't have full confidence that no firmware is loaded (in
+                * theory it might just not have loaded yet), but we will
+                * assume that, and load a new image.
+                */
+               ret = aqr_firmware_load_nvmem(phydev);
+               if (!ret)
+                       return ret;
+
+               ret = aqr_firmware_load_fs(phydev);
+               if (ret)
+                       return ret;
+               break;
+       default:
+               /* PHY read error, propagate it to the caller */
                return ret;
+       }
 
-exit:
        return 0;
 }

diff --git a/drivers/net/phy/aquantia/aquantia_main.c b/drivers/net/phy/aquantia/aquantia_main.c
index e982e9ce44a5961005495482e0d7146c625c2e91..57b8b8f400fd4d0cbc24cbd75143e9a94c240d8c 100644 (file)
--- a/drivers/net/phy/aquantia/aquantia_main.c
+++ b/drivers/net/phy/aquantia/aquantia_main.c
@@ -435,6 +435,9 @@ static int aqr107_set_tunable(struct phy_device *phydev,
        }
 }
 
+#define AQR_FW_WAIT_SLEEP_US   20000
+#define AQR_FW_WAIT_TIMEOUT_US 2000000
+
 /* If we configure settings whilst firmware is still initializing the chip,
  * then these settings may be overwritten. Therefore make sure chip
  * initialization has completed. Use presence of the firmware ID as
@@ -444,11 +447,19 @@ static int aqr107_set_tunable(struct phy_device *phydev,
  */
 int aqr_wait_reset_complete(struct phy_device *phydev)
 {
-       int val;
+       int ret, val;
+
+       ret = read_poll_timeout(phy_read_mmd, val, val != 0,
+                               AQR_FW_WAIT_SLEEP_US, AQR_FW_WAIT_TIMEOUT_US,
+                               false, phydev, MDIO_MMD_VEND1,
+                               VEND1_GLOBAL_FW_ID);
+       if (val < 0) {
+               phydev_err(phydev, "Failed to read VEND1_GLOBAL_FW_ID: %pe\n",
+                          ERR_PTR(val));
+               return val;
+       }
 
-       return phy_read_mmd_poll_timeout(phydev, MDIO_MMD_VEND1,
-                                        VEND1_GLOBAL_FW_ID, val, val != 0,
-                                        20000, 2000000, false);
+       return ret;
 }
 
 static void aqr107_chip_info(struct phy_device *phydev)