> -----Original Message-----
> From: linux-pci-ow...@vger.kernel.org [mailto:linux-pci-ow...@vger.kernel.org]
> On Behalf Of Yijing Wang
> Sent: Saturday, July 26, 2014 8:39 AM
> To: linux-ker...@vger.kernel.org
> Cc: Xinwei Hu; Wuyun; Bjorn Helgaas; linux-...@vger.kernel.org;
> paul.mu...@huawei.com; James E.J. Bottomley; Marc Zyngier; linux-arm-
> ker...@lists.infradead.org; Russell King; linux-a...@vger.kernel.org; Basu
> Arnab-B45036; virtualization@lists.linux-foundation.org; Hanjun Guo; Yijing
> Wang
> Subject: [RFC PATCH 09/11] PCI/MSI: refactor PCI MSI driver
>
> Use struct msi_ops to hook PCI MSI operations,
> and use struct msi_irqs to refactor PCI MSI drvier.
>
> Signed-off-by: Yijing Wang <wangyij...@huawei.com>
> ---
> drivers/pci/msi.c | 351
> ++++++++++++++++++++++++++++++---------------------
> include/linux/msi.h | 14 +-
> include/linux/pci.h | 11 +-
> 3 files changed, 222 insertions(+), 154 deletions(-)
>
> diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c
> index 41c33da..f0c5989 100644
> --- a/drivers/pci/msi.c
> +++ b/drivers/pci/msi.c
> @@ -29,8 +29,9 @@ static int pci_msi_enable = 1;
>
> /* Arch hooks */
>
> -int __weak arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc)
> +int __weak arch_setup_msi_irq(struct msi_irqs *msi, struct msi_desc *desc)
> {
> + struct pci_dev *dev = msi->data; //TO BE DONE: rework msi_chip to
> support
> Non-PCI
> struct msi_chip *chip = dev->bus->msi;
> int err;
>
> @@ -56,8 +57,9 @@ void __weak arch_teardown_msi_irq(unsigned int irq)
> chip->teardown_irq(chip, irq);
> }
>
> -int __weak arch_msi_check_device(struct pci_dev *dev, int nvec, int type)
> +int __weak arch_msi_check_device(struct msi_irqs *msi, int nvec, int type)
> {
> + struct pci_dev *dev = msi->data; //TO BE DONE: rework msi_chip to
> support
> Non-PCI
> struct msi_chip *chip = dev->bus->msi;
>
> if (!chip || !chip->check_device)
> @@ -66,7 +68,7 @@ int __weak arch_msi_check_device(struct pci_dev *dev, int
> nvec, int type)
> return chip->check_device(chip, dev, nvec, type);
> }
>
> -int __weak arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
> +int __weak arch_setup_msi_irqs(struct msi_irqs *msi, int nvec, int type)
> {
> struct msi_desc *entry;
> int ret;
> @@ -78,8 +80,8 @@ int __weak arch_setup_msi_irqs(struct pci_dev *dev, int
> nvec,
> int type)
> if (type == MSI_TYPE && nvec > 1)
> return 1;
>
> - list_for_each_entry(entry, &dev->msi_list, list) {
> - ret = arch_setup_msi_irq(dev, entry);
> + list_for_each_entry(entry, &msi->msi_list, list) {
> + ret = arch_setup_msi_irq(msi, entry);
> if (ret < 0)
> return ret;
> if (ret > 0)
> @@ -93,11 +95,11 @@ int __weak arch_setup_msi_irqs(struct pci_dev *dev, int
> nvec, int type)
> * We have a default implementation available as a separate non-weak
> * function, as it is used by the Xen x86 PCI code
> */
> -void default_teardown_msi_irqs(struct pci_dev *dev)
> +void default_teardown_msi_irqs(struct msi_irqs *msi)
> {
> struct msi_desc *entry;
>
> - list_for_each_entry(entry, &dev->msi_list, list) {
> + list_for_each_entry(entry, &msi->msi_list, list) {
> int i, nvec;
> if (entry->irq == 0)
> continue;
> @@ -110,22 +112,22 @@ void default_teardown_msi_irqs(struct pci_dev *dev)
> }
> }
>
> -void __weak arch_teardown_msi_irqs(struct pci_dev *dev)
> +void __weak arch_teardown_msi_irqs(struct msi_irqs *msi)
> {
> - return default_teardown_msi_irqs(dev);
> + return default_teardown_msi_irqs(msi);
> }
>
> -static void default_restore_msi_irq(struct pci_dev *dev, int irq)
> +static void default_restore_msi_irq(struct msi_irqs *msi, int irq)
> {
> struct msi_desc *entry;
>
> entry = NULL;
> - if (dev->msix_enabled) {
> - list_for_each_entry(entry, &dev->msi_list, list) {
> + if (msi->msix_enabled) {
> + list_for_each_entry(entry, &msi->msi_list, list) {
> if (irq == entry->irq)
> break;
> }
> - } else if (pci_dev_msi_enabled(dev, MSI_TYPE)) {
> + } else if (msi->msi_enabled) {
> entry = irq_get_msi_desc(irq);
> }
>
> @@ -133,20 +135,9 @@ static void default_restore_msi_irq(struct pci_dev *dev,
> int irq)
> write_msi_msg(irq, &entry->msg);
> }
>
> -void __weak arch_restore_msi_irqs(struct pci_dev *dev)
> +void __weak arch_restore_msi_irqs(struct msi_irqs *msi)
> {
> - return default_restore_msi_irqs(dev);
> -}
> -
> -static void msi_set_enable(struct pci_dev *dev, int enable)
> -{
> - u16 control;
> -
> - pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control);
> - control &= ~PCI_MSI_FLAGS_ENABLE;
> - if (enable)
> - control |= PCI_MSI_FLAGS_ENABLE;
> - pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control);
> + return default_restore_msi_irqs(msi);
> }
>
> static void msix_clear_and_set_ctrl(struct pci_dev *dev, u16 clear, u16 set)
> @@ -159,6 +150,25 @@ static void msix_clear_and_set_ctrl(struct pci_dev *dev,
> u16 clear, u16 set)
> pci_write_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, ctrl);
> }
>
> +static void msi_set_enable(struct msi_irqs *msi, int enable, int type)
> +{
> + u16 control;
> + struct pci_dev *dev = msi->data;
> +
> + if (type == MSI_TYPE) {
> + pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS,
> &control);
> + control &= ~PCI_MSI_FLAGS_ENABLE;
> + if (enable)
> + control |= PCI_MSI_FLAGS_ENABLE;
> + pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS,
> control);
> + } else if (type == MSIX_TYPE) {
> + if (enable)
> + msix_clear_and_set_ctrl(dev, 0, PCI_MSIX_FLAGS_ENABLE);
> + else
> + msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
> + }
> +}
> +
> static inline __attribute_const__ u32 msi_mask(unsigned x)
> {
> /* Don't shift by >= width of type */
> @@ -175,6 +185,7 @@ static inline __attribute_const__ u32 msi_mask(unsigned x)
> */
> u32 default_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
> {
> + struct pci_dev *dev = desc->msi->data;
> u32 mask_bits = desc->masked;
>
> if (!desc->msi_attrib.maskbit)
> @@ -182,7 +193,7 @@ u32 default_msi_mask_irq(struct msi_desc *desc, u32 mask,
> u32 flag)
>
> mask_bits &= ~mask;
> mask_bits |= flag;
> - pci_write_config_dword(desc->dev, desc->mask_pos, mask_bits);
> + pci_write_config_dword(dev, desc->mask_pos, mask_bits);
>
> return mask_bits;
> }
> @@ -250,18 +261,30 @@ void unmask_msi_irq(struct irq_data *data)
> msi_set_mask_bit(data, 0);
> }
>
> -void default_restore_msi_irqs(struct pci_dev *dev)
> +static void msix_set_all_mask(struct msi_irqs *msi, int flag)
> +{
> + struct pci_dev *dev = msi->data;
> +
> + if (flag)
> + msix_clear_and_set_ctrl(dev, 0, PCI_MSIX_FLAGS_MASKALL);
> + else
> + msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0);
> +}
> +
> +void default_restore_msi_irqs(struct msi_irqs *msi)
> {
> struct msi_desc *entry;
>
> - list_for_each_entry(entry, &dev->msi_list, list) {
> - default_restore_msi_irq(dev, entry->irq);
> + list_for_each_entry(entry, &msi->msi_list, list) {
> + default_restore_msi_irq(msi, entry->irq);
> }
> }
>
> void __read_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
> {
> - BUG_ON(entry->dev->current_state != PCI_D0);
> + struct pci_dev *dev = entry->msi->data;
> +
> + BUG_ON(dev->current_state != PCI_D0);
>
> if (entry->msi_attrib.is_msix) {
> void __iomem *base = entry->mask_base +
> @@ -271,7 +294,6 @@ void __read_msi_msg(struct msi_desc *entry, struct msi_msg
> *msg)
> msg->address_hi = readl(base + PCI_MSIX_ENTRY_UPPER_ADDR);
> msg->data = readl(base + PCI_MSIX_ENTRY_DATA);
> } else {
> - struct pci_dev *dev = entry->dev;
> int pos = dev->msi_cap;
> u16 data;
>
> @@ -315,7 +337,9 @@ void get_cached_msi_msg(unsigned int irq, struct msi_msg
> *msg)
>
> void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
> {
> - if (entry->dev->current_state != PCI_D0) {
> + struct pci_dev *dev = entry->msi->data;
> +
> + if (dev->current_state != PCI_D0) {
> /* Don't touch the hardware now */
> } else if (entry->msi_attrib.is_msix) {
> void __iomem *base;
> @@ -326,7 +350,6 @@ void __write_msi_msg(struct msi_desc *entry, struct
> msi_msg
> *msg)
> writel(msg->address_hi, base + PCI_MSIX_ENTRY_UPPER_ADDR);
> writel(msg->data, base + PCI_MSIX_ENTRY_DATA);
> } else {
> - struct pci_dev *dev = entry->dev;
> int pos = dev->msi_cap;
> u16 msgctl;
>
> @@ -357,14 +380,34 @@ void write_msi_msg(unsigned int irq, struct msi_msg
> *msg)
> __write_msi_msg(entry, msg);
> }
>
> -static void free_msi_irqs(struct pci_dev *dev)
> +static void free_msi_sysfs(struct pci_dev *dev)
> {
> - struct msi_desc *entry, *tmp;
> struct attribute **msi_attrs;
> struct device_attribute *dev_attr;
> int count = 0;
>
> - list_for_each_entry(entry, &dev->msi_list, list) {
> + if (dev->msi_irq_groups) {
> + sysfs_remove_groups(&dev->dev.kobj, dev->msi_irq_groups);
> + msi_attrs = dev->msi_irq_groups[0]->attrs;
> + while (msi_attrs[count]) {
> + dev_attr = container_of(msi_attrs[count],
> + struct device_attribute, attr);
> + kfree(dev_attr->attr.name);
> + kfree(dev_attr);
> + ++count;
> + }
> + kfree(msi_attrs);
> + kfree(dev->msi_irq_groups[0]);
> + kfree(dev->msi_irq_groups);
> + dev->msi_irq_groups = NULL;
> + }
> +}
> +
> +static void free_msi_irqs(struct msi_irqs *msi)
> +{
> + struct msi_desc *entry, *tmp;
> +
> + list_for_each_entry(entry, &msi->msi_list, list) {
> int i, nvec;
> if (!entry->irq)
> continue;
> @@ -376,11 +419,11 @@ static void free_msi_irqs(struct pci_dev *dev)
> BUG_ON(irq_has_action(entry->irq + i));
> }
>
> - arch_teardown_msi_irqs(dev);
> + arch_teardown_msi_irqs(msi);
>
> - list_for_each_entry_safe(entry, tmp, &dev->msi_list, list) {
> + list_for_each_entry_safe(entry, tmp, &msi->msi_list, list) {
> if (entry->msi_attrib.is_msix) {
> - if (list_is_last(&entry->list, &dev->msi_list))
> + if (list_is_last(&entry->list, &msi->msi_list))
> iounmap(entry->mask_base);
> }
>
> @@ -398,38 +441,24 @@ static void free_msi_irqs(struct pci_dev *dev)
> list_del(&entry->list);
> kfree(entry);
> }
> -
> - if (dev->msi_irq_groups) {
> - sysfs_remove_groups(&dev->dev.kobj, dev->msi_irq_groups);
> - msi_attrs = dev->msi_irq_groups[0]->attrs;
> - while (msi_attrs[count]) {
> - dev_attr = container_of(msi_attrs[count],
> - struct device_attribute, attr);
> - kfree(dev_attr->attr.name);
> - kfree(dev_attr);
> - ++count;
> - }
> - kfree(msi_attrs);
> - kfree(dev->msi_irq_groups[0]);
> - kfree(dev->msi_irq_groups);
> - dev->msi_irq_groups = NULL;
> - }
> }
>
> -static struct msi_desc *alloc_msi_entry(struct pci_dev *dev)
> +static struct msi_desc *alloc_msi_entry(struct msi_irqs *msi)
> {
> struct msi_desc *desc = kzalloc(sizeof(*desc), GFP_KERNEL);
> if (!desc)
> return NULL;
>
> INIT_LIST_HEAD(&desc->list);
> - desc->dev = dev;
> + desc->msi = msi;
>
> return desc;
> }
>
> -static void pci_intx_for_msi(struct pci_dev *dev, int enable)
> +static void pci_intx_for_msi(struct msi_irqs *msi, int enable)
> {
> + struct pci_dev *dev = msi->data;
> +
> if (!(dev->dev_flags & PCI_DEV_FLAGS_MSI_INTX_DISABLE_BUG))
> pci_intx(dev, enable);
> }
> @@ -444,9 +473,9 @@ static void __pci_restore_msi_state(struct pci_dev *dev)
>
> entry = irq_get_msi_desc(dev->irq);
>
> - pci_intx_for_msi(dev, 0);
> - msi_set_enable(dev, 0);
> - arch_restore_msi_irqs(dev);
> + pci_intx_for_msi(dev->msi, 0);
> + msi_set_enable(dev->msi, 0, MSI_TYPE);
> + arch_restore_msi_irqs(dev->msi);
>
> pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control);
> msi_mask_irq(entry, msi_mask(entry->msi_attrib.multi_cap),
> @@ -459,22 +488,21 @@ static void __pci_restore_msi_state(struct pci_dev *dev)
> static void __pci_restore_msix_state(struct pci_dev *dev)
> {
> struct msi_desc *entry;
> + struct msi_irqs *msi = dev->msi;
>
> - if (!dev->msix_enabled)
> + if (!pci_dev_msi_enabled(dev, MSIX_TYPE))
> return;
> - BUG_ON(list_empty(&dev->msi_list));
> + BUG_ON(list_empty(&msi->msi_list));
>
> /* route the table */
> - pci_intx_for_msi(dev, 0);
> - msix_clear_and_set_ctrl(dev, 0,
> - PCI_MSIX_FLAGS_ENABLE | PCI_MSIX_FLAGS_MASKALL);
> -
> - arch_restore_msi_irqs(dev);
> - list_for_each_entry(entry, &dev->msi_list, list) {
> + pci_intx_for_msi(msi, 0);
> + msi_set_enable(msi, 1, MSIX_TYPE);
> + msix_set_all_mask(msi, 1);
> + arch_restore_msi_irqs(msi);
> + list_for_each_entry(entry, &msi->msi_list, list)
> msix_mask_irq(entry, entry->masked);
> - }
>
> - msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0);
> + msix_set_all_mask(msi, 0);
> }
>
> void pci_restore_msi_state(struct pci_dev *dev)
> @@ -516,7 +544,7 @@ static int populate_msi_sysfs(struct pci_dev *pdev)
> int count = 0;
>
> /* Determine how many msi entries we have */
> - list_for_each_entry(entry, &pdev->msi_list, list) {
> + list_for_each_entry(entry, &pdev->msi->msi_list, list) {
> ++num_msi;
> }
> if (!num_msi)
> @@ -526,7 +554,7 @@ static int populate_msi_sysfs(struct pci_dev *pdev)
> msi_attrs = kzalloc(sizeof(void *) * (num_msi + 1), GFP_KERNEL);
> if (!msi_attrs)
> return -ENOMEM;
> - list_for_each_entry(entry, &pdev->msi_list, list) {
> + list_for_each_entry(entry, &pdev->msi->msi_list, list) {
> msi_dev_attr = kzalloc(sizeof(*msi_dev_attr), GFP_KERNEL);
> if (!msi_dev_attr)
> goto error_attrs;
> @@ -578,13 +606,14 @@ error_attrs:
> return ret;
> }
>
> -static struct msi_desc *msi_setup_entry(struct pci_dev *dev)
> +static struct msi_desc *msi_setup_entry(struct msi_irqs *msi)
> {
> u16 control;
> struct msi_desc *entry;
> + struct pci_dev *dev = msi->data;
>
> /* MSI Entry Initialization */
> - entry = alloc_msi_entry(dev);
> + entry = alloc_msi_entry(msi);
> if (!entry)
> return NULL;
>
> @@ -620,15 +649,15 @@ static struct msi_desc *msi_setup_entry(struct pci_dev
> *dev)
> * an error, and a positive return value indicates the number of interrupts
> * which could have been allocated.
> */
> -static int msi_capability_init(struct pci_dev *dev, int nvec)
> +static int msi_capability_init(struct msi_irqs *msi, int nvec)
> {
> struct msi_desc *entry;
> int ret;
> unsigned mask;
>
> - msi_set_enable(dev, 0); /* Disable MSI during set up */
> + msi_set_enable(msi, 0, MSI_TYPE); /* Disable MSI during set up */
>
> - entry = msi_setup_entry(dev);
> + entry = msi_setup_entry(msi);
> if (!entry)
> return -ENOMEM;
>
> @@ -636,21 +665,23 @@ static int msi_capability_init(struct pci_dev *dev, int
> nvec)
> mask = msi_mask(entry->msi_attrib.multi_cap);
> msi_mask_irq(entry, mask, mask);
>
> - list_add_tail(&entry->list, &dev->msi_list);
> + list_add_tail(&entry->list, &msi->msi_list);
>
> /* Configure MSI capability structure */
> - ret = arch_setup_msi_irqs(dev, nvec, MSI_TYPE);
> - if (ret) {
> - msi_mask_irq(entry, mask, ~mask);
> - free_msi_irqs(dev);
> - return ret;
> - }
> + ret = arch_setup_msi_irqs(msi, nvec, MSI_TYPE);
> + if (ret)
> + goto err;
>
> /* Set MSI enabled bits */
> - pci_intx_for_msi(dev, 0);
> - msi_set_enable(dev, 1);
> - dev->msi_enabled = 1;
> + pci_intx_for_msi(msi, 0);
> + msi_set_enable(msi, 1, MSI_TYPE);
> + msi->msi_enabled = 1;
> return 0;
> +
> +err:
> + msi_mask_irq(entry, mask, ~mask);
> + free_msi_irqs(msi);
> + return ret;
> }
>
> static void __iomem *msix_map_region(struct pci_dev *dev, unsigned
> nr_entries)
> @@ -668,19 +699,20 @@ static void __iomem *msix_map_region(struct pci_dev
> *dev,
> unsigned nr_entries)
> return ioremap_nocache(phys_addr, nr_entries * PCI_MSIX_ENTRY_SIZE);
> }
>
> -static int msix_setup_entries(struct pci_dev *dev, void __iomem *base,
> +static int msix_setup_entries(struct msi_irqs *msi, void __iomem *base,
> struct msix_entry *entries, int nvec)
> {
> struct msi_desc *entry;
> int i, offset;
> + struct pci_dev *dev = msi->data;
>
> for (i = 0; i < nvec; i++) {
> - entry = alloc_msi_entry(dev);
> + entry = alloc_msi_entry(msi);
> if (!entry) {
> if (!i)
> iounmap(base);
> else
> - free_msi_irqs(dev);
> + free_msi_irqs(msi);
> /* No enough memory. Don't try again */
> return -ENOMEM;
> }
> @@ -688,7 +720,6 @@ static int msix_setup_entries(struct pci_dev *dev, void
> __iomem *base,
> entry->msi_attrib.is_msix = 1;
> entry->msi_attrib.is_64 = 1;
> entry->msi_attrib.entry_nr = entries[i].entry;
> - entry->msi_attrib.default_irq = dev->irq;
> entry->mask_base = base;
>
> msix_clear_and_set_ctrl(dev, 0,
> @@ -700,19 +731,19 @@ static int msix_setup_entries(struct pci_dev *dev, void
> __iomem *base,
> msix_clear_and_set_ctrl(dev,
> PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE,
> 0);
>
> - list_add_tail(&entry->list, &dev->msi_list);
> + list_add_tail(&entry->list, &msi->msi_list);
> }
>
> return 0;
> }
>
> -static void msix_program_entries(struct pci_dev *dev,
> +static void msix_program_entries(struct msi_irqs *msi,
> struct msix_entry *entries)
> {
> struct msi_desc *entry;
> int i = 0;
>
> - list_for_each_entry(entry, &dev->msi_list, list) {
> + list_for_each_entry(entry, &msi->msi_list, list) {
> entries[i].vector = entry->irq;
> irq_set_msi_desc(entry->irq, entry);
> i++;
> @@ -729,19 +760,19 @@ static void msix_program_entries(struct pci_dev *dev,
> * single MSI-X irq. A return of zero indicates the successful setup of
> * requested MSI-X entries with allocated irqs or non-zero for otherwise.
> **/
> -static int msix_capability_init(struct pci_dev *dev, void __iomem *base,
> +static int msix_capability_init(struct msi_irqs *msi, void __iomem *base,
> struct msix_entry *entries, int nvec)
> {
> int ret;
>
> /* Ensure MSI-X is disabled while it is set up */
> - msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
> + msi_set_enable(msi, 0, MSIX_TYPE);
>
> - ret = msix_setup_entries(dev, base, entries, nvec);
> + ret = msix_setup_entries(msi, base, entries, nvec);
> if (ret)
> return ret;
>
> - ret = arch_setup_msi_irqs(dev, nvec, MSIX_TYPE);
> + ret = arch_setup_msi_irqs(msi, nvec, MSIX_TYPE);
> if (ret)
> goto out_avail;
>
> @@ -750,13 +781,13 @@ static int msix_capability_init(struct pci_dev *dev,
> void
> __iomem *base,
> * MSI-X registers. We need to mask all the vectors to prevent
> * interrupts coming in before they're fully set up.
> */
> - msix_program_entries(dev, entries);
> + msix_program_entries(msi, entries);
>
> /* Set MSI-X enabled bits and unmask the function */
> - pci_intx_for_msi(dev, 0);
> - dev->msix_enabled = 1;
> + pci_intx_for_msi(msi, 0);
> + msi->msix_enabled = 1;
>
> - msix_clear_and_set_ctrl(dev, 0, PCI_MSIX_FLAGS_ENABLE);
> + msi_set_enable(msi, 1, MSIX_TYPE);
>
> return 0;
>
> @@ -769,7 +800,7 @@ out_avail:
> struct msi_desc *entry;
> int avail = 0;
>
> - list_for_each_entry(entry, &dev->msi_list, list) {
> + list_for_each_entry(entry, &msi->msi_list, list) {
> if (entry->irq != 0)
> avail++;
> }
> @@ -777,7 +808,7 @@ out_avail:
> ret = avail;
> }
>
> - free_msi_irqs(dev);
> + free_msi_irqs(msi);
>
> return ret;
> }
> @@ -820,7 +851,7 @@ static int pci_msi_check_device(struct pci_dev *dev, int
> nvec, int type)
> if (bus->bus_flags & PCI_BUS_FLAGS_NO_MSI)
> return -EINVAL;
>
> - ret = arch_msi_check_device(dev, nvec, type);
> + ret = arch_msi_check_device(dev->msi, nvec, type);
> if (ret)
> return ret;
>
> @@ -861,12 +892,12 @@ void pci_msi_shutdown(struct pci_dev *dev)
> !pci_dev_msi_enabled(dev, MSI_TYPE))
> return;
>
> - BUG_ON(list_empty(&dev->msi_list));
> - desc = list_first_entry(&dev->msi_list, struct msi_desc, list);
> + BUG_ON(list_empty(&dev->msi->msi_list));
> + desc = list_first_entry(&dev->msi->msi_list, struct msi_desc, list);
>
> - msi_set_enable(dev, 0);
> - pci_intx_for_msi(dev, 1);
> - dev->msi_enabled = 0;
> + msi_set_enable(dev->msi, 0, MSI_TYPE);
> + pci_intx_for_msi(dev->msi, 1);
> + dev->msi->msi_enabled = 0;
>
> /* Return the device with MSI unmasked as initial states */
> mask = msi_mask(desc->msi_attrib.multi_cap);
> @@ -884,7 +915,8 @@ void pci_disable_msi(struct pci_dev *dev)
> return;
>
> pci_msi_shutdown(dev);
> - free_msi_irqs(dev);
> + free_msi_irqs(dev->msi);
> + free_msi_sysfs(dev);
> }
> EXPORT_SYMBOL(pci_disable_msi);
>
> @@ -930,9 +962,10 @@ int pci_enable_msix(struct pci_dev *dev, struct
> msix_entry
> *entries, int nvec)
> void __iomem *base;
> u16 control;
>
> - if (!entries || !dev->msix_cap || dev->current_state != PCI_D0)
> + if (!entries || !dev->msix_cap || !dev->msi
> + || dev->current_state != PCI_D0)
> return -EINVAL;
> -
> +
> status = pci_msi_check_device(dev, nvec, MSIX_TYPE);
> if (status)
> return status;
> @@ -952,7 +985,7 @@ int pci_enable_msix(struct pci_dev *dev, struct msix_entry
> *entries, int nvec)
> return -EINVAL; /* duplicate entry */
> }
> }
> - WARN_ON(!!dev->msix_enabled);
> + WARN_ON(!!pci_dev_msi_enabled(dev, MSIX_TYPE));
>
> /* Check whether driver already requested for MSI irq */
> if (pci_dev_msi_enabled(dev, MSI_TYPE)) {
> @@ -966,13 +999,13 @@ int pci_enable_msix(struct pci_dev *dev, struct
> msix_entry
> *entries, int nvec)
> if (!base)
> return -ENOMEM;
>
> - status = msix_capability_init(dev, base, entries, nvec);
> + status = msix_capability_init(dev->msi, base, entries, nvec);
> if (!status) {
> ret = populate_msi_sysfs(dev);
> if (ret) {
> - dev->msix_enabled = 0;
> - pci_intx_for_msi(dev, 1);
> - free_msi_irqs(dev);
> + dev->msi->msix_enabled = 0;
> + pci_intx_for_msi(dev->msi, 1);
> + free_msi_irqs(dev->msi);
> }
> }
> return status;
> @@ -983,18 +1016,18 @@ void pci_msix_shutdown(struct pci_dev *dev)
> {
> struct msi_desc *entry;
>
> - if (!pci_msi_enable || !dev || !dev->msix_enabled)
> + if (!pci_msi_enable || !dev || !pci_dev_msi_enabled(dev, MSIX_TYPE))
> return;
>
> /* Return the device with MSI-X masked as initial states */
> - list_for_each_entry(entry, &dev->msi_list, list) {
> + list_for_each_entry(entry, &dev->msi->msi_list, list) {
> /* Keep cached states to be restored */
> arch_msix_mask_irq(entry, 1);
> }
>
> - msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
> - pci_intx_for_msi(dev, 1);
> - dev->msix_enabled = 0;
> + msi_set_enable(dev->msi, 0, MSIX_TYPE);
> + pci_intx_for_msi(dev->msi, 1);
> + dev->msi->msix_enabled = 0;
> }
>
> void pci_disable_msix(struct pci_dev *dev)
> @@ -1004,7 +1037,8 @@ void pci_disable_msix(struct pci_dev *dev)
> return;
>
> pci_msix_shutdown(dev);
> - free_msi_irqs(dev);
> + free_msi_irqs(dev->msi);
> + free_msi_sysfs(dev);
> }
> EXPORT_SYMBOL(pci_disable_msix);
>
> @@ -1025,21 +1059,52 @@ int pci_msi_enabled(void)
> }
> EXPORT_SYMBOL(pci_msi_enabled);
>
> -void pci_msi_init_pci_dev(struct pci_dev *dev)
> +static struct msi_ops pci_msi = {
> + .msi_set_enable = msi_set_enable,
> + .msi_setup_entry = msi_setup_entry,
> + .msix_setup_entries = msix_setup_entries,
> + .msi_mask_irq = default_msi_mask_irq,
> + .msix_mask_irq = default_msix_mask_irq,
> + .msi_read_message = __read_msi_msg,
> + .msi_write_message = __write_msi_msg,
> + .msi_set_intx = pci_intx_for_msi,
> +};
Ahh, want to be sure I am understanding this correctly. So if I have a non-pci
driver "xyz" which wants to use separate ops then I need to have a all these
functions in that driver. Something like driver/xyz/msi.c
Thanks
-Bharat
> +
> +struct msi_irqs *alloc_msi_irqs(void *data, struct msi_ops *ops)
> {
> - INIT_LIST_HEAD(&dev->msi_list);
> + struct msi_irqs *msi;
> +
> + msi = kzalloc(sizeof(struct msi_irqs), GFP_KERNEL);
> + if (!msi)
> + return NULL;
>
> + INIT_LIST_HEAD(&msi->msi_list);
> + msi->data = data;
> + msi->ops = ops;
> + return msi;
> +}
> +
> +void pci_msi_init_pci_dev(struct pci_dev *dev)
> +{
> /* Disable the msi hardware to avoid screaming interrupts
> * during boot. This is the power on reset default so
> * usually this should be a noop.
> */
> dev->msi_cap = pci_find_capability(dev, PCI_CAP_ID_MSI);
> - if (dev->msi_cap)
> - msi_set_enable(dev, 0);
> -
> dev->msix_cap = pci_find_capability(dev, PCI_CAP_ID_MSIX);
> - if (dev->msix_cap)
> - msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
> +
> + if (dev->msi_cap || dev->msix_cap) {
> + dev->msi = alloc_msi_irqs(dev, &pci_msi);
> + if (!dev->msi)
> + return;
> +
> + dev->msi->node = dev_to_node(&dev->dev);
> + if (dev->msi_cap)
> + msi_set_enable(dev->msi, 0, MSI_TYPE);
> +
> + if (dev->msix_cap)
> + msi_set_enable(dev->msi, 0, MSIX_TYPE);
> + }
> }
>
> /**
> @@ -1060,13 +1125,13 @@ int pci_enable_msi_range(struct pci_dev *dev, int
> minvec, int maxvec)
> int rc;
> struct msi_desc *entry;
>
> - if (dev->current_state != PCI_D0)
> + if (dev->current_state != PCI_D0 || !dev->msi)
> return -EINVAL;
>
> - WARN_ON(!!dev->msi_enabled);
> + WARN_ON(!!pci_dev_msi_enabled(dev, MSI_TYPE));
>
> /* Check whether driver already requested MSI-X irqs */
> - if (dev->msix_enabled) {
> + if (pci_dev_msi_enabled(dev, MSIX_TYPE)) {
> dev_info(&dev->dev,
> "can't enable MSI (MSI-X already enabled)\n");
> return -EINVAL;
> @@ -1095,7 +1160,7 @@ int pci_enable_msi_range(struct pci_dev *dev, int
> minvec,
> int maxvec)
> } while (rc);
>
> do {
> - rc = msi_capability_init(dev, nvec);
> + rc = msi_capability_init(dev->msi, nvec);
> if (rc < 0) {
> return rc;
> } else if (rc > 0) {
> @@ -1107,14 +1172,14 @@ int pci_enable_msi_range(struct pci_dev *dev, int
> minvec, int maxvec)
>
> rc = populate_msi_sysfs(dev);
> if (rc) {
> - msi_set_enable(dev, 0);
> - pci_intx_for_msi(dev, 1);
> - dev->msi_enabled = 0;
> - free_msi_irqs(dev);
> + msi_set_enable(dev->msi, 0, MSI_TYPE);
> + pci_intx_for_msi(dev->msi, 1);
> + dev->msi->msi_enabled = 0;
> + free_msi_irqs(dev->msi);
> return rc;
> }
>
> - entry = list_entry(dev->msi_list.next, struct msi_desc, list);
> + entry = list_entry(dev->msi->msi_list.next, struct msi_desc, list);
> dev->irq = entry->irq;
> return nvec;
> }
> @@ -1158,3 +1223,5 @@ int pci_enable_msix_range(struct pci_dev *dev, struct
> msix_entry *entries,
> return nvec;
> }
> EXPORT_SYMBOL(pci_enable_msix_range);
> +
> +
> diff --git a/include/linux/msi.h b/include/linux/msi.h
> index 5a672d3..fc8f3e8 100644
> --- a/include/linux/msi.h
> +++ b/include/linux/msi.h
> @@ -83,15 +83,15 @@ struct msi_desc {
> * implemented as weak symbols so that they /can/ be overriden by
> * architecture specific code if needed.
> */
> -int arch_setup_msi_irq(struct pci_dev *dev, struct msi_desc *desc);
> +int arch_setup_msi_irq(struct msi_irqs *msi, struct msi_desc *desc);
> void arch_teardown_msi_irq(unsigned int irq);
> -int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type);
> -void arch_teardown_msi_irqs(struct pci_dev *dev);
> -int arch_msi_check_device(struct pci_dev* dev, int nvec, int type);
> -void arch_restore_msi_irqs(struct pci_dev *dev);
> +int arch_setup_msi_irqs(struct msi_irqs *msi, int nvec, int type);
> +void arch_teardown_msi_irqs(struct msi_irqs *msi);
> +int arch_msi_check_device(struct msi_irqs *msi, int nvec, int type);
> +void arch_restore_msi_irqs(struct msi_irqs *msi);
>
> -void default_teardown_msi_irqs(struct pci_dev *dev);
> -void default_restore_msi_irqs(struct pci_dev *dev);
> +void default_teardown_msi_irqs(struct msi_irqs *msi);
> +void default_restore_msi_irqs(struct msi_irqs *msi);
> u32 default_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag);
> u32 default_msix_mask_irq(struct msi_desc *desc, u32 flag);
>
> diff --git a/include/linux/pci.h b/include/linux/pci.h
> index c7bca1c..d7126fc 100644
> --- a/include/linux/pci.h
> +++ b/include/linux/pci.h
> @@ -334,8 +334,6 @@ struct pci_dev {
> unsigned int block_cfg_access:1; /* config space access is
> blocked */
> unsigned int broken_parity_status:1; /* Device generates false
> positive
> parity */
> unsigned int irq_reroute_variant:2; /* device needs IRQ rerouting
> variant */
> - unsigned int msi_enabled:1;
> - unsigned int msix_enabled:1;
> unsigned int ari_enabled:1; /* ARI forwarding */
> unsigned int is_managed:1;
> unsigned int needs_freset:1; /* Dev requires fundamental reset */
> @@ -358,7 +356,7 @@ struct pci_dev {
> struct bin_attribute *res_attr[DEVICE_COUNT_RESOURCE]; /* sysfs file for
> resources */
> struct bin_attribute *res_attr_wc[DEVICE_COUNT_RESOURCE]; /* sysfs file
> for WC mapping of resources */
> #ifdef CONFIG_PCI_MSI
> - struct list_head msi_list;
> + struct msi_irqs *msi;
> const struct attribute_group **msi_irq_groups;
> #endif
> struct pci_vpd *vpd;
> @@ -510,11 +508,14 @@ static inline struct pci_dev *pci_upstream_bridge(struct
> pci_dev *dev)
> static inline bool pci_dev_msi_enabled(struct pci_dev *pci_dev, int type)
> {
> bool enabled = 0;
> +
> + if (!pci_dev->msi)
> + return false;
>
> if (type & MSI_TYPE)
> - enabled |= pci_dev->msi_enabled;
> + enabled |= pci_dev->msi->msi_enabled;
> if (type & MSIX_TYPE)
> - enabled |= pci_dev->msix_enabled;
> + enabled |= pci_dev->msi->msix_enabled;
>
> return enabled;
> }
> --
> 1.7.1
>
> --
> To unsubscribe from this list: send the line "unsubscribe linux-pci" in
> the body of a message to majord...@vger.kernel.org
> More majordomo info at http://vger.kernel.org/majordomo-info.html
_______________________________________________
Virtualization mailing list
Virtualization@lists.linux-foundation.org
https://lists.linuxfoundation.org/mailman/listinfo/virtualization
