| Message ID | 1408729424-11433-1-git-send-email-dianders@chromium.org (mailing list archive) |
|---|---|
| State | New, archived |
| Headers | show |
On Fri, Aug 22, 2014 at 10:43:44AM -0700, Doug Anderson wrote: > Having a transfer more than 32 bits is not all that unlikely. Remove > the annotation. > > The unlikely in the IRQ handler can't gain us much. It's not in a > loop, so at most it would save 1 instruction per IRQ, which isn't > much. In fact on the compiler I tested it produced the exact same > code. Remove it too. > > Suggested-by: Dmitry Torokhov <dmitry.torokhov@gmail.com> > Signed-off-by: Doug Anderson <dianders@chromium.org> Applied to for-next, thanks!
diff --git a/drivers/i2c/busses/i2c-rk3x.c b/drivers/i2c/busses/i2c-rk3x.c index 69e1185..b8b2b89 100644 --- a/drivers/i2c/busses/i2c-rk3x.c +++ b/drivers/i2c/busses/i2c-rk3x.c @@ -208,7 +208,7 @@ static void rk3x_i2c_prepare_read(struct rk3x_i2c *i2c) * The hw can read up to 32 bytes at a time. If we need more than one * chunk, send an ACK after the last byte of the current chunk. */ - if (unlikely(len > 32)) { + if (len > 32) { len = 32; con &= ~REG_CON_LASTACK; } else { @@ -399,7 +399,7 @@ static irqreturn_t rk3x_i2c_irq(int irqno, void *dev_id) } /* is there anything left to handle? */ - if (unlikely((ipd & REG_INT_ALL) == 0)) + if ((ipd & REG_INT_ALL) == 0) goto out; switch (i2c->state) {
Having a transfer more than 32 bits is not all that unlikely. Remove the annotation. The unlikely in the IRQ handler can't gain us much. It's not in a loop, so at most it would save 1 instruction per IRQ, which isn't much. In fact on the compiler I tested it produced the exact same code. Remove it too. Suggested-by: Dmitry Torokhov <dmitry.torokhov@gmail.com> Signed-off-by: Doug Anderson <dianders@chromium.org> --- drivers/i2c/busses/i2c-rk3x.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-)