Bjorn Helgaas <helg...@kernel.org> writes: > Hi Gavin, > > You don't need my ack for any of these, and I assume you'll merge them > through the powerpc tree.
Thanks Bjorn, I wasn't sure if you wanted to ack it or not. I'll take the whole series via the powerpc tree. > Minor comments below, feel free to ignore them. > > On Wed, Sep 21, 2016 at 10:15:30PM +1000, Gavin Shan wrote: >> ... >> @@ -536,9 +565,16 @@ static struct pnv_php_slot *pnv_php_alloc_slot(struct >> device_node *dn) >> if (unlikely(!php_slot)) >> return NULL; >> >> + php_slot->event = kzalloc(sizeof(struct pnv_php_event), GFP_KERNEL); >> + if (unlikely(!php_slot->event)) { >> + kfree(php_slot); >> + return NULL; >> + } > > Since you *always* allocate the event when allocating the php_slot, > making the event a member of php_slot (instead of keeping a pointer to > it) would simplify your memory management a bit. > It seems to be the style in this file to use "unlikely" liberally, but > I really doubt there's any performance consideration in this code. To > me it adds more clutter than usefulness. Agreed on both counts. Gavin can you do another spin with those changes, thanks. cheers