@@ -85,6 +85,7 @@ struct clk {
unsigned long min_rate;
unsigned long max_rate;
struct hlist_node clks_node;
+ struct kref ref;
};
/*** locking ***/
@@ -2590,7 +2591,7 @@ fail_out:
EXPORT_SYMBOL_GPL(clk_register);
/* Free memory allocated for a clock. */
-static void __clk_release(struct kref *ref)
+static void __clk_core_release(struct kref *ref)
{
struct clk_core *core = container_of(ref, struct clk_core, ref);
int i = core->num_parents;
@@ -2606,6 +2607,18 @@ static void __clk_release(struct kref *ref)
kfree(core);
}
+static void __clk_release(struct kref *ref)
+{
+ struct clk *clk = container_of(ref, struct clk, ref);
+
+ hlist_del(&clk->clks_node);
+ if (clk->min_rate > clk->core->req_rate ||
+ clk->max_rate < clk->core->req_rate)
+ clk_core_set_rate_nolock(clk->core, clk->core->req_rate);
+
+ kfree(clk);
+}
+
/*
* Empty clk_ops for unregistered clocks. These are used temporarily
* after clk_unregister() was called on a clock and until last clock
@@ -2684,7 +2697,7 @@ void clk_unregister(struct clk *clk)
if (clk->core->prepare_count)
pr_warn("%s: unregistering prepared clock: %s\n",
__func__, clk->core->name);
- kref_put(&clk->core->ref, __clk_release);
+ kref_put(&clk->core->ref, __clk_core_release);
clk_prepare_unlock();
}
@@ -2759,12 +2772,14 @@ int __clk_get(struct clk *clk)
return 0;
kref_get(&core->ref);
+ kref_get(&clk->ref);
}
return 1;
}
void __clk_put(struct clk *clk)
{
+ struct clk_core *core;
struct module *owner;
if (!clk || WARN_ON_ONCE(IS_ERR(clk)))
@@ -2772,19 +2787,15 @@ void __clk_put(struct clk *clk)
clk_prepare_lock();
- hlist_del(&clk->clks_node);
- if (clk->min_rate > clk->core->req_rate ||
- clk->max_rate < clk->core->req_rate)
- clk_core_set_rate_nolock(clk->core, clk->core->req_rate);
+ core = clk->core;
+ owner = core->owner;
- owner = clk->core->owner;
- kref_put(&clk->core->ref, __clk_release);
+ kref_put(&clk->ref, __clk_release);
+ kref_put(&core->ref, __clk_core_release);
clk_prepare_unlock();
module_put(owner);
-
- kfree(clk);
}
/*** clk rate change notifiers ***/
With the split into struct clk and struct clk_core, clocks lost the ability for nested __clk_get clkdev calls. While it stays possible to call __clk_get, the first call to (__)clk_put will clear the struct clk, making subsequent clk_put calls run into a NULL pointer dereference. One prime example of this sits in the generic power domain code, where it is possible to add the clocks both by name and by passing in a struct clk via pm_clk_add_clk(). __pm_clk_add() in turn then calls __clk_get to increase the refcount, so that the original code can put the clock again. A possible call-path looks like clk = of_clk_get(); pm_clk_add_clk(dev, clk); clk_put(clk); with pm_clk_add_clk() => __pm_clk_add() then calling __clk_get on the clk and later clk_put when the pm clock list gets destroyed, thus creating a NULL pointer deref, as the struct clk doesn't exist anymore. So add a separate refcounting for struct clk instances and only clean up once the refcount reaches zero. This makes it possible again to hand off a clock reference to common code without needing to track it further. Signed-off-by: Heiko Stuebner <heiko@sntech.de> --- While it may be nice to do the actual handling of the clock references only in the calling code, in this current use case it would create a big additional overhead. It looks like this so called synchronous reset on power-domain state- changes, requiring device clocks to be turned on, is not that uncommon or rockchip-specific. For this Kevin requested that we read the clocks from the actual consumer devices and not double-list them in the power-domain node as well. So when expecting pm_clk_add_clk() to work, the current powerdomain code can simply do when adding a device to a domain in rockchip_pd_attach_dev(): while ((clk = of_clk_get(dev->of_node, i++)) && !IS_ERR(clk)) { dev_dbg(dev, "adding clock '%pC' to list of PM clocks\n", clk); error = pm_clk_add_clk(dev, clk); clk_put(clk); } The clock gets handed off to the generic pm clock handling and thus clk_put in there. On the other hand when only the rockchip power-domain code is expected to get and put the clock, we would require a lot of new overhead, as now the code would also need to track which devices got added to what domain and also all clock-references until the device gets detached again. So this would essentially duplicate a big part of what the genpd-code does (per-domain device-list and per-device clock-list). As this seems to be not uncommon, future powerdomain drivers might need that too and would also need to duplicate that handling. When allowing multiple __clk_get and __clk_put calls on the other hand, the overhead for the regular case comes down to one atomic_inc, atomic_sub_and_test and the function call to the new separate release function ;-) . changes in v2: removed double parentheses found by Stephen Boyd drivers/clk/clk.c | 31 +++++++++++++++++++++---------- 1 file changed, 21 insertions(+), 10 deletions(-)