Re: [v5,2/3] PCI: mediatek-gen3: Add MediaTek Gen3 driver for MT8192

[Jianjun Wang]

On Mon, 2020-12-21 at 10:18 +0800, Nicolas Boichat wrote:
> On Wed, Dec 2, 2020 at 9:39 PM Jianjun Wang <jianjun.wang@xxxxxxxxxxxx> wrote:
> >
> > MediaTek's PCIe host controller has three generation HWs, the new
> > generation HW is an individual bridge, it supports Gen3 speed and
> > up to 256 MSI interrupt numbers for multi-function devices.
> >
> > Add support for new Gen3 controller which can be found on MT8192.
> >
> > Signed-off-by: Jianjun Wang <jianjun.wang@xxxxxxxxxxxx>
> > Acked-by: Ryder Lee <ryder.lee@xxxxxxxxxxxx>
> 
> FWIW, I looked at Rob and Bjorn's comments on v4, and they seem to
> have been addressed (with one small nit highlighted below).
> 
> > ---
> > This patch dependents on "PCI: Export pci_pio_to_address() for module use"[1]
> > to build as a kernel module.
> >
> > This interface will be used by PCI host drivers for PIO translation,
> > export it to support compiling those drivers as kernel modules.
> >
> > [1]http://lists.infradead.org/pipermail/linux-mediatek/2020-December/019504.html
> > ---
> >  drivers/pci/controller/Kconfig              |   13 +
> >  drivers/pci/controller/Makefile             |    1 +
> >  drivers/pci/controller/pcie-mediatek-gen3.c | 1039 +++++++++++++++++++
> >  3 files changed, 1053 insertions(+)
> >  create mode 100644 drivers/pci/controller/pcie-mediatek-gen3.c
> >
> > [snip]
> > diff --git a/drivers/pci/controller/pcie-mediatek-gen3.c b/drivers/pci/controller/pcie-mediatek-gen3.c
> > new file mode 100644
> > index 000000000000..d30ea734ac0a
> > --- /dev/null
> > +++ b/drivers/pci/controller/pcie-mediatek-gen3.c
> > @@ -0,0 +1,1039 @@
> > [snip]
> > +static int mtk_pcie_set_trans_table(struct mtk_pcie_port *port,
> > +                                   resource_size_t cpu_addr,
> > +                                   resource_size_t pci_addr,
> > +                                   resource_size_t size,
> > +                                   unsigned long type, int num)
> > +{
> > +       void __iomem *table;
> > +       u32 val = 0;
> 
> You don't need to init val to 0.
> 
> > +
> > +       if (num >= PCIE_MAX_TRANS_TABLES) {
> > +               dev_notice(port->dev, "not enough translate table[%d] for addr: %#llx, limited to [%d]\n",
> > +                          num, (unsigned long long) cpu_addr,
> > +                          PCIE_MAX_TRANS_TABLES);
> > +               return -ENODEV;
> > +       }
> > +
> > +       table = port->base + PCIE_TRANS_TABLE_BASE_REG +
> > +               num * PCIE_ATR_TLB_SET_OFFSET;
> > +
> > +       writel(lower_32_bits(cpu_addr) | PCIE_ATR_SIZE(fls(size) - 1), table);
> > +       writel(upper_32_bits(cpu_addr), table + PCIE_ATR_SRC_ADDR_MSB_OFFSET);
> > +       writel(lower_32_bits(pci_addr), table + PCIE_ATR_TRSL_ADDR_LSB_OFFSET);
> > +       writel(upper_32_bits(pci_addr), table + PCIE_ATR_TRSL_ADDR_MSB_OFFSET);
> > +
> > +       if (type == IORESOURCE_IO)
> > +               val = PCIE_ATR_TYPE_IO | PCIE_ATR_TLP_TYPE_IO;
> > +       else
> > +               val = PCIE_ATR_TYPE_MEM | PCIE_ATR_TLP_TYPE_MEM;
> > +
> > +       writel(val, table + PCIE_ATR_TRSL_PARAM_OFFSET);
> > +
> > +       return 0;
> > +}
> > +
> > +static int mtk_pcie_startup_port(struct mtk_pcie_port *port)
> > +{
> > +       struct resource_entry *entry;
> > +       struct pci_host_bridge *host = pci_host_bridge_from_priv(port);
> > +       unsigned int table_index = 0;
> > +       int err;
> > +       u32 val;
> > +
> > +       /* Set as RC mode */
> > +       val = readl(port->base + PCIE_SETTING_REG);
> > +       val |= PCIE_RC_MODE;
> > +       writel(val, port->base + PCIE_SETTING_REG);
> > +
> > +       /* Set class code */
> > +       val = readl(port->base + PCIE_PCI_IDS_1);
> > +       val &= ~GENMASK(31, 8);
> > +       val |= PCI_CLASS(PCI_CLASS_BRIDGE_PCI << 8);
> > +       writel(val, port->base + PCIE_PCI_IDS_1);
> > +
> > +       /* Assert all reset signals */
> > +       val = readl(port->base + PCIE_RST_CTRL_REG);
> > +       val |= PCIE_MAC_RSTB | PCIE_PHY_RSTB | PCIE_BRG_RSTB | PCIE_PE_RSTB;
> > +       writel(val, port->base + PCIE_RST_CTRL_REG);
> > +
> > +       /* De-assert reset signals */
> > +       val &= ~(PCIE_MAC_RSTB | PCIE_PHY_RSTB | PCIE_BRG_RSTB);
> > +       writel(val, port->base + PCIE_RST_CTRL_REG);
> > +
> > +       /* Delay 100ms to wait the reference clocks become stable */
> > +       usleep_range(100 * 1000, 120 * 1000);
> 
> Any reason not to use msleep(100)?

No special reasons, but it seems the msleep() should be used when the
sleep time is more than 20ms (base on
Documentation/timers/timers-howto.rst).

I will replace to msleep(100) in the next version, thanks for your
review.
> 
> > +
> > +       /* De-assert PERST# signal */
> > +       val &= ~PCIE_PE_RSTB;
> > +       writel(val, port->base + PCIE_RST_CTRL_REG);
> > +
> > +       /* Check if the link is up or not */
> > +       err = readl_poll_timeout(port->base + PCIE_LINK_STATUS_REG, val,
> > +                       !!(val & PCIE_PORT_LINKUP), 20,
> > +                       50 * USEC_PER_MSEC);
> > +       if (err) {
> > +               val = readl(port->base + PCIE_LTSSM_STATUS_REG);
> > +               dev_notice(port->dev, "PCIe link down, ltssm reg val: %#x\n",
> > +                          val);
> > +               return err;
> > +       }
> > +
> > +       /* Set PCIe translation windows */
> > +       resource_list_for_each_entry(entry, &host->windows) {
> > +               struct resource *res = entry->res;
> > +               unsigned long type = resource_type(res);
> > +               resource_size_t cpu_addr;
> > +               resource_size_t pci_addr;
> > +               resource_size_t size;
> > +               const char *range_type;
> > +
> > +               if (type == IORESOURCE_IO) {
> > +                       cpu_addr = pci_pio_to_address(res->start);
> > +                       range_type = "IO";
> > +               } else if (type == IORESOURCE_MEM) {
> > +                       cpu_addr = res->start;
> > +                       range_type = "MEM";
> > +               } else {
> > +                       continue;
> > +               }
> > +
> > +               pci_addr = res->start - entry->offset;
> > +               size = resource_size(res);
> > +               err = mtk_pcie_set_trans_table(port, cpu_addr, pci_addr, size,
> > +                                              type, table_index);
> > +               if (err)
> > +                       return err;
> > +
> > +               dev_dbg(port->dev, "set %s trans window[%d]: cpu_addr = %#llx, pci_addr = %#llx, size = %#llx\n",
> > +                       range_type, table_index, (unsigned long long) cpu_addr,
> > +                       (unsigned long long) pci_addr,
> > +                       (unsigned long long) size);
> > +
> > +               table_index++;
> > +       }
> > +
> > +       return 0;
> > +}
> > +
> > [snip]
> > +static irq_hw_number_t mtk_pcie_msi_get_hwirq(struct msi_domain_info *info,
> > +                                             msi_alloc_info_t *arg)
> > +{
> > +       struct msi_desc *entry = arg->desc;
> > +       struct mtk_pcie_port *port = info->chip_data;
> > +       int hwirq;
> > +
> > +       mutex_lock(&port->lock);
> > +
> > +       hwirq = bitmap_find_free_region(port->msi_irq_in_use, PCIE_MSI_IRQS_NUM,
> > +                                       order_base_2(entry->nvec_used));
> > +       if (hwirq < 0) {
> > +               mutex_unlock(&port->lock);
> > +               return -ENOSPC;
> > +       }
> > +
> > +       mutex_unlock(&port->lock);
> > +
> > +       return hwirq;
> 
> Code is good, but I had to look twice to make sure the mutex is
> unlocked. Is the following marginally better?
> 
> hwirq = ...;
> 
> mutex_unlock(&port->lock);
> 
> if (hwirq < 0)
>    return -ENOSPC;
> 
> return hwirq;

Impressive, I will fix it in the next version, and I think the hwirq can
be returned directly since it will be a negative value if
bitmap_find_free_region is failed. The code will be like the following:

hwirq = ...;

mutex_unlock(&port->lock);

return hwirq;

> 
> > +}
> > +
> > [snip]
> > +static void mtk_pcie_msi_handler(struct irq_desc *desc)
> > +{
> > +       struct mtk_pcie_msi *msi_info = irq_desc_get_handler_data(desc);
> > +       struct irq_chip *irqchip = irq_desc_get_chip(desc);
> > +       unsigned long msi_enable, msi_status;
> > +       unsigned int virq;
> > +       irq_hw_number_t bit, hwirq;
> > +
> > +       chained_irq_enter(irqchip, desc);
> > +
> > +       msi_enable = readl(msi_info->base + PCIE_MSI_ENABLE_OFFSET);
> > +       while ((msi_status = readl(msi_info->base + PCIE_MSI_STATUS_OFFSET))) {
> > +               msi_status &= msi_enable;
> 
> I don't know much about MSI, but what happens if you have a bit that
> is set in PCIE_MSI_STATUS_OFFSET register, but not in msi_enable?

If the bit that in PCIE_MSI_STATUS_OFFSET register is set but not in
msi_enable, it must be an abnormal usage of MSI or something goes wrong,
it should be ignored in case we can not find the corresponding handler.

> Sounds like you'll just spin-loop forever without acknowledging the
> interrupt.

The interrupt will be acknowledged in the irq_ack callback of
mtk_msi_irq_chip, which belongs to the msi_domain.

> 
> > +               for_each_set_bit(bit, &msi_status, PCIE_MSI_IRQS_PER_SET) {
> > +                       hwirq = bit + msi_info->index * PCIE_MSI_IRQS_PER_SET;
> > +                       virq = irq_find_mapping(msi_info->domain, hwirq);
> > +                       generic_handle_irq(virq);
> > +               }
> > +       }
> > +
> > +       chained_irq_exit(irqchip, desc);
> > +}
> > +
> > [snip]
> > +static int __maybe_unused mtk_pcie_suspend_noirq(struct device *dev)
> > +{
> > +       struct mtk_pcie_port *port = dev_get_drvdata(dev);
> > +       int err;
> > +       u32 val;
> > +
> > +       /* Trigger link to L2 state */
> > +       err = mtk_pcie_turn_off_link(port);
> > +       if (err) {
> > +               dev_notice(port->dev, "can not enter L2 state\n");
> 
> Rob suggested dev_error here.
> 
> (and IMHO, or lot of the other dev_notice above should probably get dev_error)

I will replace to dev_err, thanks for your review.
> 
> > +               return err;
> > +       }
> > +
> > +       /* Pull down the PERST# pin */
> > +       val = readl(port->base + PCIE_RST_CTRL_REG);
> > +       val |= PCIE_PE_RSTB;
> > +       writel(val, port->base + PCIE_RST_CTRL_REG);
> > +
> > +       dev_dbg(port->dev, "enter L2 state success");
> > +
> > +       clk_bulk_disable_unprepare(port->num_clks, port->clks);
> > +
> > +       phy_power_off(port->phy);
> > +
> > +       return 0;
> > +}
> > +
> > [snip]
> 
> _______________________________________________
> Linux-mediatek mailing list
> Linux-mediatek@xxxxxxxxxxxxxxxxxxx
> http://lists.infradead.org/mailman/listinfo/linux-mediatek