diff mbox series

[net-next,v2,2/3] mlxsw: core_thermal: Report valid current state during cooling device registration

Message ID c823c4678b6b7afb902c35b3551c81a053afd110.1720447210.git.petrm@nvidia.com (mailing list archive)
State Accepted
Commit a22f3bc80075c10c3835b9ec1c7da17496386904
Delegated to: Netdev Maintainers
Headers show
Series mlxsw: Improvements | expand

Checks

Context Check Description
netdev/series_format success Posting correctly formatted
netdev/tree_selection success Clearly marked for net-next
netdev/ynl success Generated files up to date; no warnings/errors; no diff in generated;
netdev/fixes_present success Fixes tag not required for -next series
netdev/header_inline success No static functions without inline keyword in header files
netdev/build_32bit success Errors and warnings before: 816 this patch: 816
netdev/build_tools success No tools touched, skip
netdev/cc_maintainers success CCed 6 of 6 maintainers
netdev/build_clang success Errors and warnings before: 821 this patch: 821
netdev/verify_signedoff success Signed-off-by tag matches author and committer
netdev/deprecated_api success None detected
netdev/check_selftest success No net selftest shell script
netdev/verify_fixes success No Fixes tag
netdev/build_allmodconfig_warn success Errors and warnings before: 821 this patch: 821
netdev/checkpatch success total: 0 errors, 0 warnings, 0 checks, 121 lines checked
netdev/build_clang_rust success No Rust files in patch. Skipping build
netdev/kdoc success Errors and warnings before: 0 this patch: 0
netdev/source_inline success Was 0 now: 0
netdev/contest success net-next-2024-07-09--21-00 (tests: 693)

Commit Message

Petr Machata July 8, 2024, 2:23 p.m. UTC 
From: Ido Schimmel <idosch@nvidia.com>

Commit 31a0fa0019b0 ("thermal/debugfs: Pass cooling device state to
thermal_debug_cdev_add()") changed the thermal core to read the current
state of the cooling device as part of the cooling device's
registration. This is incompatible with the current implementation of
the cooling device operations in mlxsw, leading to initialization
failure with errors such as:

mlxsw_spectrum 0000:01:00.0: Failed to register cooling device
mlxsw_spectrum 0000:01:00.0: cannot register bus device

The reason for the failure is that when the get current state operation
is invoked the driver tries to derive the index of the cooling device by
walking a per thermal zone array and looking for the matching cooling
device pointer. However, the pointer is returned from the registration
function and therefore only set in the array after the registration.

The issue was later fixed by commit 1af89dedc8a5 ("thermal: core: Do not
fail cdev registration because of invalid initial state") by not failing
the registration of the cooling device if it cannot report a valid
current state during registration, although drivers are responsible for
ensuring that this will not happen.

Therefore, make sure the driver is able to report a valid current state
for the cooling device during registration by passing to the
registration function a per cooling device private data that already has
the cooling device index populated.

While at it, call thermal_cooling_device_unregister() unconditionally
since the function returns immediately if the cooling device pointer is
NULL.

Cc: linux-pm@vger.kernel.org
Reviewed-by: Vadim Pasternak <vadimp@nvidia.com>
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
---

Notes:
    v2:
    - call thermal_cooling_device_unregister() unconditionally and mention
      it in the commit message

 .../ethernet/mellanox/mlxsw/core_thermal.c    | 51 +++++++++----------
 1 file changed, 25 insertions(+), 26 deletions(-)
diff mbox series

Patch

diff --git a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
index 5c511e1a8efa..d61478c0c632 100644
--- a/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
+++ b/drivers/net/ethernet/mellanox/mlxsw/core_thermal.c
@@ -100,6 +100,12 @@  static const struct mlxsw_cooling_states default_cooling_states[] = {
 
 struct mlxsw_thermal;
 
+struct mlxsw_thermal_cooling_device {
+	struct mlxsw_thermal *thermal;
+	struct thermal_cooling_device *cdev;
+	unsigned int idx;
+};
+
 struct mlxsw_thermal_module {
 	struct mlxsw_thermal *parent;
 	struct thermal_zone_device *tzdev;
@@ -123,7 +129,7 @@  struct mlxsw_thermal {
 	const struct mlxsw_bus_info *bus_info;
 	struct thermal_zone_device *tzdev;
 	int polling_delay;
-	struct thermal_cooling_device *cdevs[MLXSW_MFCR_PWMS_MAX];
+	struct mlxsw_thermal_cooling_device cdevs[MLXSW_MFCR_PWMS_MAX];
 	struct thermal_trip trips[MLXSW_THERMAL_NUM_TRIPS];
 	struct mlxsw_cooling_states cooling_states[MLXSW_THERMAL_NUM_TRIPS];
 	struct mlxsw_thermal_area line_cards[];
@@ -147,7 +153,7 @@  static int mlxsw_get_cooling_device_idx(struct mlxsw_thermal *thermal,
 	int i;
 
 	for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++)
-		if (thermal->cdevs[i] == cdev)
+		if (thermal->cdevs[i].cdev == cdev)
 			return i;
 
 	/* Allow mlxsw thermal zone binding to an external cooling device */
@@ -352,17 +358,14 @@  static int mlxsw_thermal_get_cur_state(struct thermal_cooling_device *cdev,
 				       unsigned long *p_state)
 
 {
-	struct mlxsw_thermal *thermal = cdev->devdata;
+	struct mlxsw_thermal_cooling_device *mlxsw_cdev = cdev->devdata;
+	struct mlxsw_thermal *thermal = mlxsw_cdev->thermal;
 	struct device *dev = thermal->bus_info->dev;
 	char mfsc_pl[MLXSW_REG_MFSC_LEN];
-	int err, idx;
 	u8 duty;
+	int err;
 
-	idx = mlxsw_get_cooling_device_idx(thermal, cdev);
-	if (idx < 0)
-		return idx;
-
-	mlxsw_reg_mfsc_pack(mfsc_pl, idx, 0);
+	mlxsw_reg_mfsc_pack(mfsc_pl, mlxsw_cdev->idx, 0);
 	err = mlxsw_reg_query(thermal->core, MLXSW_REG(mfsc), mfsc_pl);
 	if (err) {
 		dev_err(dev, "Failed to query PWM duty\n");
@@ -378,22 +381,19 @@  static int mlxsw_thermal_set_cur_state(struct thermal_cooling_device *cdev,
 				       unsigned long state)
 
 {
-	struct mlxsw_thermal *thermal = cdev->devdata;
+	struct mlxsw_thermal_cooling_device *mlxsw_cdev = cdev->devdata;
+	struct mlxsw_thermal *thermal = mlxsw_cdev->thermal;
 	struct device *dev = thermal->bus_info->dev;
 	char mfsc_pl[MLXSW_REG_MFSC_LEN];
-	int idx;
 	int err;
 
 	if (state > MLXSW_THERMAL_MAX_STATE)
 		return -EINVAL;
 
-	idx = mlxsw_get_cooling_device_idx(thermal, cdev);
-	if (idx < 0)
-		return idx;
-
 	/* Normalize the state to the valid speed range. */
 	state = max_t(unsigned long, MLXSW_THERMAL_MIN_STATE, state);
-	mlxsw_reg_mfsc_pack(mfsc_pl, idx, mlxsw_state_to_duty(state));
+	mlxsw_reg_mfsc_pack(mfsc_pl, mlxsw_cdev->idx,
+			    mlxsw_state_to_duty(state));
 	err = mlxsw_reg_write(thermal->core, MLXSW_REG(mfsc), mfsc_pl);
 	if (err) {
 		dev_err(dev, "Failed to write PWM duty\n");
@@ -753,17 +753,21 @@  int mlxsw_thermal_init(struct mlxsw_core *core,
 	}
 	for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++) {
 		if (pwm_active & BIT(i)) {
+			struct mlxsw_thermal_cooling_device *mlxsw_cdev;
 			struct thermal_cooling_device *cdev;
 
+			mlxsw_cdev = &thermal->cdevs[i];
+			mlxsw_cdev->thermal = thermal;
+			mlxsw_cdev->idx = i;
 			cdev = thermal_cooling_device_register("mlxsw_fan",
-							       thermal,
+							       mlxsw_cdev,
 							       &mlxsw_cooling_ops);
 			if (IS_ERR(cdev)) {
 				err = PTR_ERR(cdev);
 				dev_err(dev, "Failed to register cooling device\n");
 				goto err_thermal_cooling_device_register;
 			}
-			thermal->cdevs[i] = cdev;
+			mlxsw_cdev->cdev = cdev;
 		}
 	}
 
@@ -824,8 +828,7 @@  int mlxsw_thermal_init(struct mlxsw_core *core,
 err_thermal_zone_device_register:
 err_thermal_cooling_device_register:
 	for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++)
-		if (thermal->cdevs[i])
-			thermal_cooling_device_unregister(thermal->cdevs[i]);
+		thermal_cooling_device_unregister(thermal->cdevs[i].cdev);
 err_reg_write:
 err_reg_query:
 	kfree(thermal);
@@ -847,12 +850,8 @@  void mlxsw_thermal_fini(struct mlxsw_thermal *thermal)
 		thermal->tzdev = NULL;
 	}
 
-	for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++) {
-		if (thermal->cdevs[i]) {
-			thermal_cooling_device_unregister(thermal->cdevs[i]);
-			thermal->cdevs[i] = NULL;
-		}
-	}
+	for (i = 0; i < MLXSW_MFCR_PWMS_MAX; i++)
+		thermal_cooling_device_unregister(thermal->cdevs[i].cdev);
 
 	kfree(thermal);
 }