OMAP1 clock: fix for "BUG: spinlock lockup on CPU#0"

Commit 52650505fb caused clock initialization
to fail on OMAP1 with "BUG: spinlock lockup on CPU#0" -- this is because
omap1_select_table_rate() and omap1_round_to_table_rate() call clk_get_rate()
with the clockfw spinlock held.  Fix by accessing the rate directly from
the internal clock framework functions.

Thanks to Tony Lindgren <tony@atomide.com> for reporting and testing the fix.

Signed-off-by: Paul Walmsley <paul@pwsan.com>
Cc: Tony Lindgren <tony@atomide.com>
This commit is contained in:
Paul Walmsley 2010-01-19 17:30:55 -07:00
parent ecbb065947
commit af022fafa8
1 changed files with 3 additions and 3 deletions

View File

@ -214,8 +214,8 @@ int omap1_select_table_rate(struct clk *clk, unsigned long rate)
struct mpu_rate * ptr;
unsigned long dpll1_rate, ref_rate;
dpll1_rate = clk_get_rate(ck_dpll1_p);
ref_rate = clk_get_rate(ck_ref_p);
dpll1_rate = ck_dpll1_p->rate;
ref_rate = ck_ref_p->rate;
for (ptr = omap1_rate_table; ptr->rate; ptr++) {
if (ptr->xtal != ref_rate)
@ -306,7 +306,7 @@ long omap1_round_to_table_rate(struct clk *clk, unsigned long rate)
long highest_rate;
unsigned long ref_rate;
ref_rate = clk_get_rate(ck_ref_p);
ref_rate = ck_ref_p->rate;
highest_rate = -EINVAL;