Commit
52650505fbf3a6ab851c801f54e73e76c55ab8da 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>
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)
long highest_rate;
unsigned long ref_rate;
- ref_rate = clk_get_rate(ck_ref_p);
+ ref_rate = ck_ref_p->rate;
highest_rate = -EINVAL;