From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Return-Path: Date: Mon, 26 Sep 2016 23:08:02 +1000 From: Gavin Shan To: Bjorn Helgaas Cc: Gavin Shan , linux-pci@vger.kernel.org, linuxppc-dev@ozlabs.org, bhelgaas@google.com, mpe@ellerman.id.au Subject: Re: [PATCH 4/4] drivers/pci/hotplug: Support surprise hotplug Reply-To: Gavin Shan References: <1474460130-8316-1-git-send-email-gwshan@linux.vnet.ibm.com> <1474460130-8316-5-git-send-email-gwshan@linux.vnet.ibm.com> <20160921165703.GA17457@localhost> MIME-Version: 1.0 Content-Type: text/plain; charset=us-ascii In-Reply-To: <20160921165703.GA17457@localhost> Message-Id: <20160926130802.GA16718@gwshan> List-ID: On Wed, Sep 21, 2016 at 11:57:03AM -0500, Bjorn Helgaas wrote: >Hi Gavin, > >You don't need my ack for any of these, and I assume you'll merge them >through 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. > >> +static irqreturn_t pnv_php_interrupt(int irq, void *data) >> +{ >> + struct pnv_php_slot *php_slot = data; >> + struct pci_dev *pchild, *pdev = php_slot->pdev; >> + struct eeh_dev *edev; >> + struct eeh_pe *pe; >> + struct pnv_php_event *event; >> + u16 sts, lsts; >> + u8 presence; >> + bool added; >> + unsigned long flags; >> + int ret; >> + >> + pcie_capability_read_word(pdev, PCI_EXP_SLTSTA, &sts); >> + sts &= (PCI_EXP_SLTSTA_PDC | PCI_EXP_SLTSTA_DLLSC); >> + pcie_capability_write_word(pdev, PCI_EXP_SLTSTA, sts); > >I didn't realize that this is some sort of hybrid of native PCIe >hotplug and PowerNV-specific stuff. Wonder if there's any opportunity >to combine with or leverage pciehp. That seems pretty blue-sky >though, since there's so much PowerNV special sauce here. > Bjorn, thanks a lot for your comments. All comments except last one (leverage pciehp) are covered in v2 which wasn't copied to linux-pci@ list to avoid unnecessary traffic. Yeah, the driver is too much PowerNV platform specific things, which makes it hard to be built on top of pciehp. Thanks, Gavin