Re: [PATCH] amd-pstate: Fix amd_pstate mode switch

From: Rafael J. Wysocki
Date: Thu Mar 30 2023 - 14:19:49 EST


On Thu, Mar 30, 2023 at 4:13 PM Wyes Karny <wyes.karny@xxxxxxx> wrote:
>
> amd_pstate mode can be changed by writing the mode name to the `status`
> sysfs. But some combinations are not working. Fix this issue by taking
> care of the edge cases.
>
> Before the fix the mode change combination test fails:
>
> #./pst_test.sh
> Test passed: from: disable, to
> Test passed: from: disable, to disable
> Test failed: 1, From mode: disable, to mode: passive
> Test failed: 1, From mode: disable, to mode: active
> Test failed: 1, From mode: passive, to mode: active
> Test passed: from: passive, to disable
> Test failed: 1, From mode: passive, to mode: passive
> Test failed: 1, From mode: passive, to mode: active
> Test failed: 1, From mode: active, to mode: active
> Test passed: from: active, to disable
> Test failed: 1, From mode: active, to mode: passive
> Test failed: 1, From mode: active, to mode: active
>
> After the fix test passes:
>
> #./pst_test.sh
> Test passed: from: disable, to
> Test passed: from: disable, to disable
> Test passed: from: disable, to passive
> Test passed: from: disable, to active
> Test passed: from: passive, to active
> Test passed: from: passive, to disable
> Test passed: from: passive, to passive
> Test passed: from: passive, to active
> Test passed: from: active, to active
> Test passed: from: active, to disable
> Test passed: from: active, to passive
> Test passed: from: active, to active
>
> Fixes: abd61c08ef349 ("cpufreq: amd-pstate: add driver working mode switch support")
>
> Acked-by: Huang Rui <ray.huang@xxxxxxx>
> Reviewed-by: Alexey Kardashevskiy <aik@xxxxxxx>
> Signed-off-by: Wyes Karny <wyes.karny@xxxxxxx>
>
> Cc: "Rafael J. Wysocki" <rafael@xxxxxxxxxx>
> Cc: Viresh Kumar <viresh.kumar@xxxxxxxxxx>
> Cc: Mario Limonciello <mario.limonciello@xxxxxxx>
> Cc: Perry Yuan <Perry.Yuan@xxxxxxx>

This is all fine, but you need to tell me how it interacts with the
amd-pstate changes in linux-next.

Does it affect the code in linux-next at all or is it only for 6.3-rc?

> ---
> drivers/cpufreq/amd-pstate.c | 18 ++++++++----------
> 1 file changed, 8 insertions(+), 10 deletions(-)
>
> diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
> index 73c7643b2697..8dd46fad151e 100644
> --- a/drivers/cpufreq/amd-pstate.c
> +++ b/drivers/cpufreq/amd-pstate.c
> @@ -840,22 +840,20 @@ static int amd_pstate_update_status(const char *buf, size_t size)
>
> switch(mode_idx) {
> case AMD_PSTATE_DISABLE:
> - if (!current_pstate_driver)
> - return -EINVAL;
> - if (cppc_state == AMD_PSTATE_ACTIVE)
> - return -EBUSY;
> - cpufreq_unregister_driver(current_pstate_driver);
> - amd_pstate_driver_cleanup();
> + if (current_pstate_driver) {
> + cpufreq_unregister_driver(current_pstate_driver);
> + amd_pstate_driver_cleanup();
> + }
> break;
> case AMD_PSTATE_PASSIVE:
> if (current_pstate_driver) {
> if (current_pstate_driver == &amd_pstate_driver)
> return 0;
> cpufreq_unregister_driver(current_pstate_driver);
> - cppc_state = AMD_PSTATE_PASSIVE;
> - current_pstate_driver = &amd_pstate_driver;
> }
>
> + current_pstate_driver = &amd_pstate_driver;
> + cppc_state = AMD_PSTATE_PASSIVE;
> ret = cpufreq_register_driver(current_pstate_driver);
> break;
> case AMD_PSTATE_ACTIVE:
> @@ -863,10 +861,10 @@ static int amd_pstate_update_status(const char *buf, size_t size)
> if (current_pstate_driver == &amd_pstate_epp_driver)
> return 0;
> cpufreq_unregister_driver(current_pstate_driver);
> - current_pstate_driver = &amd_pstate_epp_driver;
> - cppc_state = AMD_PSTATE_ACTIVE;
> }
>
> + current_pstate_driver = &amd_pstate_epp_driver;
> + cppc_state = AMD_PSTATE_ACTIVE;
> ret = cpufreq_register_driver(current_pstate_driver);
> break;
> default:
> --
> 2.34.1
>