> -----Original Message----- > From: linux-pci-owner@xxxxxxxxxxxxxxx [mailto:linux-pci-owner@xxxxxxxxxxxxxxx] > On Behalf Of Yijing Wang > Sent: Saturday, July 26, 2014 8:39 AM > To: linux-kernel@xxxxxxxxxxxxxxx > Cc: Xinwei Hu; Wuyun; Bjorn Helgaas; linux-pci@xxxxxxxxxxxxxxx; > Paul.Mundt@xxxxxxxxxx; James E.J. Bottomley; Marc Zyngier; linux-arm- > kernel@xxxxxxxxxxxxxxxxxxx; Russell King; linux-arch@xxxxxxxxxxxxxxx; Basu > Arnab-B45036; virtualization@xxxxxxxxxxxxxxxxxxxxxxxxxx; Hanjun Guo; Yijing Wang > Subject: [RFC PATCH 10/11] PCI/MSI: Split the generic MSI code into new file > > MSI interrupt will not only used in PCI device, more > and more Non-PCI device also want to use MSI. ARM > GIC v3 spec says in ARM platform with GIC v3 controller, > Non-PCI device can also be design to support MSI to > simplify interrupt wires, for the existing Non-PCI > device, consolidator is designed and used to translate > legacy interrupt to MSI. So for support Non-PCI MSI > device, generic MSI driver is needed. Split the generic > MSI code into new location, drivers/msi/msi.c. Then > MSI driver does not depend PCI anymore. > > Signed-off-by: Yijing Wang <wangyijing@xxxxxxxxxx> > --- > drivers/Kconfig | 1 + > drivers/Makefile | 1 + > drivers/msi/Kconfig | 8 + > drivers/msi/Makefile | 1 + > drivers/msi/msi.c | 540 ++++++++++++++++++++++++++++++++++++++++++++++++++ > drivers/pci/Kconfig | 6 +- > drivers/pci/msi.c | 500 ++++------------------------------------------- > include/linux/msi.h | 31 +++- > 8 files changed, 617 insertions(+), 471 deletions(-) > create mode 100644 drivers/msi/Kconfig > create mode 100644 drivers/msi/Makefile > create mode 100644 drivers/msi/msi.c > > diff --git a/drivers/Kconfig b/drivers/Kconfig > index 0e87a34..4d05749 100644 > --- a/drivers/Kconfig > +++ b/drivers/Kconfig > @@ -176,4 +176,5 @@ source "drivers/powercap/Kconfig" > > source "drivers/mcb/Kconfig" > > +source "drivers/msi/Kconfig" > endmenu > diff --git a/drivers/Makefile b/drivers/Makefile > index f98b50d..47ae3d1 100644 > --- a/drivers/Makefile > +++ b/drivers/Makefile > @@ -158,3 +158,4 @@ obj-$(CONFIG_NTB) += ntb/ > obj-$(CONFIG_FMC) += fmc/ > obj-$(CONFIG_POWERCAP) += powercap/ > obj-$(CONFIG_MCB) += mcb/ > +obj-$(CONFIG_MSI) += msi/ > diff --git a/drivers/msi/Kconfig b/drivers/msi/Kconfig > new file mode 100644 > index 0000000..739bd13 > --- /dev/null > +++ b/drivers/msi/Kconfig > @@ -0,0 +1,8 @@ > +config MSI > + bool "Message Signaled Interrupts (MSI and MSI-X)" > + default y > + help > + This allows device drivers to use generic MSI(Message > + Signaled Interrupt). Message Signaled Interrupts enable > + a device to generate an interrupt using an inbound Memory > + Write to a specific target address. > diff --git a/drivers/msi/Makefile b/drivers/msi/Makefile > new file mode 100644 > index 0000000..39cb026 > --- /dev/null > +++ b/drivers/msi/Makefile > @@ -0,0 +1 @@ > +obj-$(CONFIG_MSI) += msi.o > diff --git a/drivers/msi/msi.c b/drivers/msi/msi.c > new file mode 100644 > index 0000000..3fbd539 > --- /dev/null > +++ b/drivers/msi/msi.c > @@ -0,0 +1,540 @@ > +/* > + * File: msi.c > + * Purpose: Message Signaled Interrupt (MSI) > + * > + * Copyright (C) 2014 Huawei Ltd. > + * Copyright (C) Yijing Wang <wangyijing@xxxxxxxxxx> > + */ > +#include <linux/err.h> > +#include <linux/mm.h> > +#include <linux/irq.h> > +#include <linux/interrupt.h> > +#include <linux/export.h> > +#include <linux/ioport.h> > +#include <linux/proc_fs.h> > +#include <linux/msi.h> > +#include <linux/smp.h> > +#include <linux/errno.h> > +#include <linux/io.h> > +#include <linux/slab.h> > +#include <linux/device.h> > +#include <linux/pci.h> > + > +/* Arch hooks */ > + > +int __weak arch_setup_msi_irq(struct msi_irqs *msi, struct msi_desc *desc) > +{ > + struct pci_dev *dev = msi->data; > + struct msi_chip *chip = dev->bus->msi; //TO BE DONE: rework msi_chip to > support Non-PCI MSI > + int err; > + > + if (!chip || !chip->setup_irq) > + return -EINVAL; > + > + err = chip->setup_irq(chip, dev, desc); > + if (err < 0) > + return err; > + > + irq_set_chip_data(desc->irq, chip); > + return 0; > +} > + > +void __weak arch_teardown_msi_irq(unsigned int irq) > +{ > + struct msi_chip *chip = irq_get_chip_data(irq); > + > + if (!chip || !chip->teardown_irq) > + return; > + > + chip->teardown_irq(chip, irq); > +} > + > +int __weak arch_msi_check_device(struct msi_irqs *msi, int nvec, int type) > +{ > + struct pci_dev *dev = msi->data; > + struct msi_chip *chip = dev->bus->msi; //TO BE DONE: rework msi_chip to > support Non-PCI MSI > + > + if (!chip || !chip->check_device) > + return 0; > + > + return chip->check_device(chip, dev, nvec, type); > +} > + > +int __weak arch_setup_msi_irqs(struct msi_irqs *msi, int nvec, int type) > +{ > + struct msi_desc *entry; > + int ret; > + > + /* > + * If an architecture wants to support multiple MSI, it needs to > + * override arch_setup_msi_irqs() > + */ > + if (type == MSI_TYPE && nvec > 1) > + return 1; > + > + list_for_each_entry(entry, &msi->msi_list, list) { > + ret = arch_setup_msi_irq(msi, entry); > + if (ret < 0) > + return ret; > + if (ret > 0) > + return -ENOSPC; > + } > + return 0; > +} > + > + > +void __weak arch_teardown_msi_irqs(struct msi_irqs *msi) > +{ > + return default_teardown_msi_irqs(msi); > +} > + > +/* > + * 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 msi_irqs *msi) > +{ > + struct msi_desc *entry; > + > + list_for_each_entry(entry, &msi->msi_list, list) { > + int i, nvec; > + if (entry->irq == 0) > + continue; > + if (entry->nvec_used) > + nvec = entry->nvec_used; > + else > + nvec = 1 << entry->msi_attrib.multiple; > + for (i = 0; i < nvec; i++) > + arch_teardown_msi_irq(entry->irq + i); > + } > +} > + > +static void default_restore_msi_irq(struct msi_irqs *msi, int irq) > +{ > + struct msi_desc *entry; > + > + entry = NULL; > + if (msi->msix_enabled) { > + list_for_each_entry(entry, &msi->msi_list, list) { > + if (irq == entry->irq) > + break; > + } > + } else if (msi->msi_enabled) { > + entry = irq_get_msi_desc(irq); > + } > + > + if (entry) > + write_msi_msg(irq, &entry->msg); > +} > + > +void default_restore_msi_irqs(struct msi_irqs *msi) > +{ > + struct msi_desc *entry; > + > + list_for_each_entry(entry, &msi->msi_list, list) { > + default_restore_msi_irq(msi, entry->irq); > + } > +} > + > +void __weak arch_restore_msi_irqs(struct msi_irqs *msi) > +{ > + return default_restore_msi_irqs(msi); > +} > + > +u32 default_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) > +{ > + struct msi_irqs *msi = desc->msi; > + > + if (!msi || !msi->ops || !msi->ops->msi_mask_irq) > + return desc->masked; > + return msi->ops->msi_mask_irq(desc, mask, flag); > +} > + > +__weak u32 arch_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) > +{ > + return default_msi_mask_irq(desc, mask, flag); > +} > + > +void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) > +{ > + desc->masked = arch_msi_mask_irq(desc, mask, flag); > +} > + > +u32 default_msix_mask_irq(struct msi_desc *desc, u32 flag) > +{ > + struct msi_irqs *msi = desc->msi; > + > + if (!msi || !msi->ops || !msi->ops->msix_mask_irq) > + return desc->masked; > + > + return msi->ops->msix_mask_irq(desc, flag); > +} > + > +__weak u32 arch_msix_mask_irq(struct msi_desc *desc, u32 flag) > +{ > + return default_msix_mask_irq(desc, flag); > +} > + > +void msix_mask_irq(struct msi_desc *desc, u32 flag) > +{ > + desc->masked = arch_msix_mask_irq(desc, flag); > +} > + > +static void msi_set_mask_bit(struct irq_data *data, u32 flag) > +{ > + struct msi_desc *desc = irq_data_get_msi(data); > + > + if (desc->msi_attrib.is_msix) { > + msix_mask_irq(desc, flag); > + readl(desc->mask_base); /* Flush write to device */ > + } else { > + unsigned offset = data->irq - desc->irq; > + msi_mask_irq(desc, 1 << offset, flag << offset); > + } > +} > + > +void mask_msi_irq(struct irq_data *data) > +{ > + msi_set_mask_bit(data, 1); > +} > + > +void unmask_msi_irq(struct irq_data *data) > +{ > + msi_set_mask_bit(data, 0); > +} > + > +void msi_set_enable(struct msi_irqs *msi, int enable, int type) > +{ > + if (!msi || !msi->ops || !msi->ops->msi_set_enable) > + return; > + msi->ops->msi_set_enable(msi, enable, type); > +} > +EXPORT_SYMBOL(msi_set_enable); > + > +void __read_msi_msg(struct msi_desc *entry, struct msi_msg *msg) > +{ > + struct msi_irqs *msi = entry->msi; > + > + if (!msi || !msi->ops || !msi->ops->msi_read_message) > + return; > + msi->ops->msi_read_message(entry, msg); > +} > + > +void read_msi_msg(unsigned int irq, struct msi_msg *msg) > +{ > + struct msi_desc *entry = irq_get_msi_desc(irq); > + > + __read_msi_msg(entry, msg); > +} > + > +void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg) > +{ > + /* Assert that the cache is valid, assuming that > + * valid messages are not all-zeroes. */ > + BUG_ON(!(entry->msg.address_hi | entry->msg.address_lo | > + entry->msg.data)); > + > + *msg = entry->msg; > +} > + > +void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg) > +{ > + struct msi_desc *entry = irq_get_msi_desc(irq); > + > + __get_cached_msi_msg(entry, msg); > +} > + > +void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg) > +{ > + struct msi_irqs *msi = entry->msi; > + > + if (!msi || !msi->ops || !msi->ops->msi_write_message) > + return; > + msi->ops->msi_write_message(entry, msg); > +} > + > +void write_msi_msg(unsigned int irq, struct msi_msg *msg) > +{ > + struct msi_desc *entry = irq_get_msi_desc(irq); > + > + __write_msi_msg(entry, msg); > +} > + > +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; > + if (entry->nvec_used) > + nvec = entry->nvec_used; > + else > + nvec = 1 << entry->msi_attrib.multiple; > + for (i = 0; i < nvec; i++) > + BUG_ON(irq_has_action(entry->irq + i)); > + } > + > + arch_teardown_msi_irqs(msi); > + > + list_for_each_entry_safe(entry, tmp, &msi->msi_list, list) { > + if (entry->msi_attrib.is_msix) { > + if (list_is_last(&entry->list, &msi->msi_list)) > + iounmap(entry->mask_base); > + } > + > + /* > + * Its possible that we get into this path > + * When populate_msi_sysfs fails, which means the entries > + * were not registered with sysfs. In that case don't > + * unregister them. > + */ > + if (entry->kobj.parent) { > + kobject_del(&entry->kobj); > + kobject_put(&entry->kobj); > + } > + > + list_del(&entry->list); > + kfree(entry); > + } > +} > +EXPORT_SYMBOL(free_msi_irqs); > + > +struct msi_irqs *alloc_msi_irqs(void *data, struct msi_ops *ops) > +{ > + 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; > +} > +EXPORT_SYMBOL(alloc_msi_irqs); > + > +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->msi = msi; > + > + return desc; > +} > +EXPORT_SYMBOL(alloc_msi_entry); > + > +static void msi_set_intx(struct msi_irqs *msi, int flag) > +{ > + if (!msi || !msi->ops || !msi->ops->msi_set_intx) > + return; > + msi->ops->msi_set_intx(msi, flag); > +} > + > +void msi_shutdown(struct msi_irqs *msi) > +{ > + u32 mask; > + struct msi_desc *desc; > + > + if (!msi || !msi->msi_enabled) > + return; > + > + BUG_ON(list_empty(&msi->msi_list)); > + > + desc = list_first_entry(&msi->msi_list, struct msi_desc, list); > + msi_set_enable(msi, 0, MSI_TYPE); > + msi_set_intx(msi, 1); > + msi->msi_enabled = 0; > + > + mask = msi_mask(desc->msi_attrib.multi_cap); > + arch_msi_mask_irq(desc, mask, ~mask); > +} > + > +void msix_shutdown(struct msi_irqs *msi) > +{ > + struct msi_desc *entry; > + > + if (!msi || !msi->msix_enabled) > + return; > + > + list_for_each_entry(entry, &msi->msi_list, list) > + arch_msix_mask_irq(entry, 1); > + > + msi_set_enable(msi, 0, MSIX_TYPE); > + msi_set_intx(msi, 1); > + msi->msix_enabled = 0; > +} > + > +static struct msi_desc * msi_setup_entry(struct msi_irqs *msi) > +{ > + struct msi_desc *entry; > + > + entry = alloc_msi_entry(msi); > + if (!entry) > + return NULL; > + > + entry->msi_attrib.is_msix = 0; > + entry->msi_attrib.entry_nr = 0; > + > + if (!msi->ops || !msi->ops->msi_setup_entry) { > + kfree(entry); > + return NULL; > + } Can we move this check at the start of the function? > + > + msi->ops->msi_setup_entry(msi, entry); > + return entry; > +} > + > +static int msix_setup_entries(struct msi_irqs *msi, void __iomem *base, > + struct msix_entry *entries, int nvec) > +{ > + struct msi_desc *entry; > + int i; > + > + for (i = 0; i < nvec; i++) { > + entry = alloc_msi_entry(msi); > + if (!entry) { > + if (!i) > + iounmap(base); > + else > + free_msi_irqs(msi); > + /* No enough memory. Don't try again */ > + return -ENOMEM; > + } > + > + entry->msi_attrib.is_msix = 1; > + entry->msi_attrib.is_64 = 1; > + entry->msi_attrib.entry_nr = entries[i].entry; > + entry->mask_base = base; > + > + list_add_tail(&entry->list, &msi->msi_list); > + } > + > + if (msi->ops && msi->ops->msix_setup_entries) > + return msi->ops->msix_setup_entries(msi, entries); > + > + return 0; > +} > + > +/** > + * msi_capability_init - configure device's MSI capability structure > + * @msi: pointer to the msi_irqs data structure of MSI device function > + * @nvec: number of interrupts to allocate > + * > + * Setup the MSI capability structure of the device with the requested > + * number of interrupts. A return value of zero indicates the successful > + * setup of an entry with the new MSI irq. A negative return value indicates > + * an error, and a positive return value indicates the number of interrupts > + * which could have been allocated. > + */ > +int msi_capability_init(struct msi_irqs *msi, int nvec) > +{ > + struct msi_desc *entry; > + int ret; > + unsigned mask; > + > + msi_set_enable(msi, 0, MSI_TYPE); /* Disable MSI during set up */ > + > + /* MSI Entry Initialization */ > + entry = msi_setup_entry(msi); > + if (!entry) > + return -ENOMEM; > + > + /* All MSIs are unmasked by default, Mask them all */ Will this be true for non-pci devices as well? Thanks -Bharat > + mask = msi_mask(entry->msi_attrib.multi_cap); > + msi_mask_irq(entry, mask, mask); > + > + /* Configure MSI capability structure */ > + ret = arch_setup_msi_irqs(msi, nvec, MSI_TYPE); > + if (ret) > + goto err; > + > + /* Set MSI enabled bits */ > + msi_set_intx(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 msix_program_entries(struct msi_irqs *msi, > + struct msix_entry *entries) > +{ > + struct msi_desc *entry; > + int i = 0; > + > + list_for_each_entry(entry, &msi->msi_list, list) { > + entries[i].vector = entry->irq; > + irq_set_msi_desc(entry->irq, entry); > + i++; > + } > +} > + > +/** > + * msix_capability_init - configure device's MSI-X capability > + * @dev: pointer to the pci_dev data structure of MSI-X device function > + * @entries: pointer to an array of struct msix_entry entries > + * @nvec: number of @entries > + * > + * Setup the MSI-X capability structure of device function with a > + * 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. > + **/ > +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 */ > + msi_set_enable(msi, 0, MSIX_TYPE); > + > + ret = msix_setup_entries(msi, base, entries, nvec); > + if (ret) > + return ret; > + > + ret = arch_setup_msi_irqs(msi, nvec, MSIX_TYPE); > + if (ret) > + goto out_avail; > + > + msix_program_entries(msi, entries); > + > + /* Set MSI-X enabled bits and unmask the function */ > + msi_set_intx(msi, 0); > + msi->msix_enabled = 1; > + > + msi_set_enable(msi, 1, MSIX_TYPE); > + > + return 0; > + > +out_avail: > + if (ret < 0) { > + /* > + * If we had some success, report the number of irqs > + * we succeeded in setting up. > + */ > + struct msi_desc *entry; > + int avail = 0; > + > + list_for_each_entry(entry, &msi->msi_list, list) { > + if (entry->irq != 0) > + avail++; > + } > + if (avail != 0) > + ret = avail; > + } > + > + free_msi_irqs(msi); > + > + return ret; > +} > + > diff --git a/drivers/pci/Kconfig b/drivers/pci/Kconfig > index 893503f..1a10488 100644 > --- a/drivers/pci/Kconfig > +++ b/drivers/pci/Kconfig > @@ -2,10 +2,10 @@ > # PCI configuration > # > config PCI_MSI > - bool "Message Signaled Interrupts (MSI and MSI-X)" > - depends on PCI > + bool "PCI Message Signaled Interrupts (MSI and MSI-X)" > + depends on PCI && MSI > help > - This allows device drivers to enable MSI (Message Signaled > + This allows PCI device drivers to enable MSI (Message Signaled > Interrupts). Message Signaled Interrupts enable a device to > generate an interrupt using an inbound Memory Write on its > PCI bus instead of asserting a device IRQ pin. > diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c > index f0c5989..df7223c 100644 > --- a/drivers/pci/msi.c > +++ b/drivers/pci/msi.c > @@ -26,121 +26,8 @@ static int pci_msi_enable = 1; > > #define msix_table_size(flags) ((flags & PCI_MSIX_FLAGS_QSIZE) + 1) > > - > -/* Arch hooks */ > - > -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; > - > - if (!chip || !chip->setup_irq) > - return -EINVAL; > - > - err = chip->setup_irq(chip, dev, desc); > - if (err < 0) > - return err; > - > - irq_set_chip_data(desc->irq, chip); > - > - return 0; > -} > - > -void __weak arch_teardown_msi_irq(unsigned int irq) > -{ > - struct msi_chip *chip = irq_get_chip_data(irq); > - > - if (!chip || !chip->teardown_irq) > - return; > - > - chip->teardown_irq(chip, irq); > -} > - > -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) > - return 0; > - > - return chip->check_device(chip, dev, nvec, type); > -} > - > -int __weak arch_setup_msi_irqs(struct msi_irqs *msi, int nvec, int type) > -{ > - struct msi_desc *entry; > - int ret; > - > - /* > - * If an architecture wants to support multiple MSI, it needs to > - * override arch_setup_msi_irqs() > - */ > - if (type == MSI_TYPE && nvec > 1) > - return 1; > - > - list_for_each_entry(entry, &msi->msi_list, list) { > - ret = arch_setup_msi_irq(msi, entry); > - if (ret < 0) > - return ret; > - if (ret > 0) > - return -ENOSPC; > - } > - > - return 0; > -} > - > -/* > - * 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 msi_irqs *msi) > -{ > - struct msi_desc *entry; > - > - list_for_each_entry(entry, &msi->msi_list, list) { > - int i, nvec; > - if (entry->irq == 0) > - continue; > - if (entry->nvec_used) > - nvec = entry->nvec_used; > - else > - nvec = 1 << entry->msi_attrib.multiple; > - for (i = 0; i < nvec; i++) > - arch_teardown_msi_irq(entry->irq + i); > - } > -} > - > -void __weak arch_teardown_msi_irqs(struct msi_irqs *msi) > -{ > - return default_teardown_msi_irqs(msi); > -} > - > -static void default_restore_msi_irq(struct msi_irqs *msi, int irq) > -{ > - struct msi_desc *entry; > - > - entry = NULL; > - if (msi->msix_enabled) { > - list_for_each_entry(entry, &msi->msi_list, list) { > - if (irq == entry->irq) > - break; > - } > - } else if (msi->msi_enabled) { > - entry = irq_get_msi_desc(irq); > - } > - > - if (entry) > - write_msi_msg(irq, &entry->msg); > -} > - > -void __weak arch_restore_msi_irqs(struct msi_irqs *msi) > -{ > - return default_restore_msi_irqs(msi); > -} > - > -static void msix_clear_and_set_ctrl(struct pci_dev *dev, u16 clear, u16 set) > +static void msix_clear_and_set_ctrl(struct pci_dev *dev, > + u16 clear, u16 set) > { > u16 ctrl; > > @@ -150,7 +37,7 @@ 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) > +static void pci_msi_set_enable(struct msi_irqs *msi, int enable, int type) > { > u16 control; > struct pci_dev *dev = msi->data; > @@ -169,21 +56,13 @@ static void msi_set_enable(struct msi_irqs *msi, int > enable, int type) > } > } > > -static inline __attribute_const__ u32 msi_mask(unsigned x) > -{ > - /* Don't shift by >= width of type */ > - if (x >= 5) > - return 0xffffffff; > - return (1 << (1 << x)) - 1; > -} > - > /* > * PCI 2.3 does not specify mask bits for each MSI interrupt. Attempting to > * mask all MSI interrupts by clearing the MSI enable bit does not work > * reliably as devices without an INTx disable bit will then generate a > * level IRQ which will never be cleared. > */ > -u32 default_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) > +u32 pci_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) > { > struct pci_dev *dev = desc->msi->data; > u32 mask_bits = desc->masked; > @@ -198,16 +77,6 @@ u32 default_msi_mask_irq(struct msi_desc *desc, u32 mask, > u32 flag) > return mask_bits; > } > > -__weak u32 arch_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) > -{ > - return default_msi_mask_irq(desc, mask, flag); > -} > - > -static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag) > -{ > - desc->masked = arch_msi_mask_irq(desc, mask, flag); > -} > - > /* > * This internal function does not flush PCI writes to the device. > * All users must ensure that they read from the device before either > @@ -215,7 +84,7 @@ static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 > flag) > * file. This saves a few milliseconds when initialising devices with lots > * of MSI-X interrupts. > */ > -u32 default_msix_mask_irq(struct msi_desc *desc, u32 flag) > +u32 pci_msix_mask_irq(struct msi_desc *desc, u32 flag) > { > u32 mask_bits = desc->masked; > unsigned offset = desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE + > @@ -228,40 +97,7 @@ u32 default_msix_mask_irq(struct msi_desc *desc, u32 flag) > return mask_bits; > } > > -__weak u32 arch_msix_mask_irq(struct msi_desc *desc, u32 flag) > -{ > - return default_msix_mask_irq(desc, flag); > -} > - > -static void msix_mask_irq(struct msi_desc *desc, u32 flag) > -{ > - desc->masked = arch_msix_mask_irq(desc, flag); > -} > - > -static void msi_set_mask_bit(struct irq_data *data, u32 flag) > -{ > - struct msi_desc *desc = irq_data_get_msi(data); > - > - if (desc->msi_attrib.is_msix) { > - msix_mask_irq(desc, flag); > - readl(desc->mask_base); /* Flush write to device */ > - } else { > - unsigned offset = data->irq - desc->irq; > - msi_mask_irq(desc, 1 << offset, flag << offset); > - } > -} > - > -void mask_msi_irq(struct irq_data *data) > -{ > - msi_set_mask_bit(data, 1); > -} > - > -void unmask_msi_irq(struct irq_data *data) > -{ > - msi_set_mask_bit(data, 0); > -} > - > -static void msix_set_all_mask(struct msi_irqs *msi, int flag) > +static void pci_msix_set_all_mask(struct msi_irqs *msi, int flag) > { > struct pci_dev *dev = msi->data; > > @@ -271,16 +107,7 @@ static void msix_set_all_mask(struct msi_irqs *msi, int > flag) > 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, &msi->msi_list, list) { > - default_restore_msi_irq(msi, entry->irq); > - } > -} > - > -void __read_msi_msg(struct msi_desc *entry, struct msi_msg *msg) > +void pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg) > { > struct pci_dev *dev = entry->msi->data; > > @@ -311,31 +138,7 @@ void __read_msi_msg(struct msi_desc *entry, struct msi_msg > *msg) > } > } > > -void read_msi_msg(unsigned int irq, struct msi_msg *msg) > -{ > - struct msi_desc *entry = irq_get_msi_desc(irq); > - > - __read_msi_msg(entry, msg); > -} > - > -void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg) > -{ > - /* Assert that the cache is valid, assuming that > - * valid messages are not all-zeroes. */ > - BUG_ON(!(entry->msg.address_hi | entry->msg.address_lo | > - entry->msg.data)); > - > - *msg = entry->msg; > -} > - > -void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg) > -{ > - struct msi_desc *entry = irq_get_msi_desc(irq); > - > - __get_cached_msi_msg(entry, msg); > -} > - > -void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg) > +void pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg) > { > struct pci_dev *dev = entry->msi->data; > > @@ -373,13 +176,6 @@ void __write_msi_msg(struct msi_desc *entry, struct msi_msg > *msg) > entry->msg = *msg; > } > > -void write_msi_msg(unsigned int irq, struct msi_msg *msg) > -{ > - struct msi_desc *entry = irq_get_msi_desc(irq); > - > - __write_msi_msg(entry, msg); > -} > - > static void free_msi_sysfs(struct pci_dev *dev) > { > struct attribute **msi_attrs; > @@ -403,58 +199,6 @@ static void free_msi_sysfs(struct pci_dev *dev) > } > } > > -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; > - if (entry->nvec_used) > - nvec = entry->nvec_used; > - else > - nvec = 1 << entry->msi_attrib.multiple; > - for (i = 0; i < nvec; i++) > - BUG_ON(irq_has_action(entry->irq + i)); > - } > - > - arch_teardown_msi_irqs(msi); > - > - list_for_each_entry_safe(entry, tmp, &msi->msi_list, list) { > - if (entry->msi_attrib.is_msix) { > - if (list_is_last(&entry->list, &msi->msi_list)) > - iounmap(entry->mask_base); > - } > - > - /* > - * Its possible that we get into this path > - * When populate_msi_sysfs fails, which means the entries > - * were not registered with sysfs. In that case don't > - * unregister them. > - */ > - if (entry->kobj.parent) { > - kobject_del(&entry->kobj); > - kobject_put(&entry->kobj); > - } > - > - list_del(&entry->list); > - kfree(entry); > - } > -} > - > -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->msi = msi; > - > - return desc; > -} > - > static void pci_intx_for_msi(struct msi_irqs *msi, int enable) > { > struct pci_dev *dev = msi->data; > @@ -474,7 +218,7 @@ static void __pci_restore_msi_state(struct pci_dev *dev) > entry = irq_get_msi_desc(dev->irq); > > pci_intx_for_msi(dev->msi, 0); > - msi_set_enable(dev->msi, 0, MSI_TYPE); > + pci_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); > @@ -496,13 +240,13 @@ static void __pci_restore_msix_state(struct pci_dev *dev) > > /* route the table */ > pci_intx_for_msi(msi, 0); > - msi_set_enable(msi, 1, MSIX_TYPE); > - msix_set_all_mask(msi, 1); > + pci_msi_set_enable(msi, 1, MSIX_TYPE); > + pci_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_set_all_mask(msi, 0); > + pci_msix_set_all_mask(msi, 0); > } > > void pci_restore_msi_state(struct pci_dev *dev) > @@ -606,22 +350,16 @@ error_attrs: > return ret; > } > > -static struct msi_desc *msi_setup_entry(struct msi_irqs *msi) > +static struct msi_desc *pci_msi_setup_entry(struct msi_irqs *msi, > + struct msi_desc *entry) > { > u16 control; > - struct msi_desc *entry; > struct pci_dev *dev = msi->data; > > /* MSI Entry Initialization */ > - entry = alloc_msi_entry(msi); > - if (!entry) > - return NULL; > - > pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control); > > - entry->msi_attrib.is_msix = 0; > entry->msi_attrib.is_64 = !!(control & PCI_MSI_FLAGS_64BIT); > - entry->msi_attrib.entry_nr = 0; > entry->msi_attrib.maskbit = !!(control & PCI_MSI_FLAGS_MASKBIT); > entry->msi_attrib.default_irq = dev->irq; /* Save IOAPIC IRQ */ > entry->msi_attrib.multi_cap = (control & PCI_MSI_FLAGS_QMASK) >> 1; > @@ -638,52 +376,6 @@ static struct msi_desc *msi_setup_entry(struct msi_irqs > *msi) > return entry; > } > > -/** > - * msi_capability_init - configure device's MSI capability structure > - * @dev: pointer to the pci_dev data structure of MSI device function > - * @nvec: number of interrupts to allocate > - * > - * Setup the MSI capability structure of the device with the requested > - * number of interrupts. A return value of zero indicates the successful > - * setup of an entry with the new MSI irq. A negative return value indicates > - * an error, and a positive return value indicates the number of interrupts > - * which could have been allocated. > - */ > -static int msi_capability_init(struct msi_irqs *msi, int nvec) > -{ > - struct msi_desc *entry; > - int ret; > - unsigned mask; > - > - msi_set_enable(msi, 0, MSI_TYPE); /* Disable MSI during set up */ > - > - entry = msi_setup_entry(msi); > - if (!entry) > - return -ENOMEM; > - > - /* All MSIs are unmasked by default, Mask them all */ > - mask = msi_mask(entry->msi_attrib.multi_cap); > - msi_mask_irq(entry, mask, mask); > - > - list_add_tail(&entry->list, &msi->msi_list); > - > - /* Configure MSI capability structure */ > - ret = arch_setup_msi_irqs(msi, nvec, MSI_TYPE); > - if (ret) > - goto err; > - > - /* Set MSI enabled bits */ > - 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) > { > resource_size_t phys_addr; > @@ -699,28 +391,19 @@ 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 msi_irqs *msi, void __iomem *base, > - struct msix_entry *entries, int nvec) > +static int pci_msix_setup_entries(struct msi_irqs *msi, struct msix_entry > *entries) > { > + int offset, i = 0; > struct msi_desc *entry; > - int i, offset; > struct pci_dev *dev = msi->data; > > - for (i = 0; i < nvec; i++) { > - entry = alloc_msi_entry(msi); > - if (!entry) { > - if (!i) > - iounmap(base); > - else > - free_msi_irqs(msi); > - /* No enough memory. Don't try again */ > - return -ENOMEM; > - } > > - entry->msi_attrib.is_msix = 1; > - entry->msi_attrib.is_64 = 1; > - entry->msi_attrib.entry_nr = entries[i].entry; > - entry->mask_base = base; > + list_for_each_entry(entry, &msi->msi_list, list) { > + /* > + * Some devices require MSI-X to be enabled before we can touch the > + * MSI-X registers. We need to mask all the vectors to prevent > + * interrupts coming in before they're fully set up. > + */ > > msix_clear_and_set_ctrl(dev, 0, > PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE); > @@ -730,87 +413,10 @@ static int msix_setup_entries(struct msi_irqs *msi, void > __iomem *base, > msix_mask_irq(entry, 1); > msix_clear_and_set_ctrl(dev, > PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE, 0); > - > - list_add_tail(&entry->list, &msi->msi_list); > - } > - > - return 0; > -} > - > -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, &msi->msi_list, list) { > - entries[i].vector = entry->irq; > - irq_set_msi_desc(entry->irq, entry); > i++; > } > -} > - > -/** > - * msix_capability_init - configure device's MSI-X capability > - * @dev: pointer to the pci_dev data structure of MSI-X device function > - * @entries: pointer to an array of struct msix_entry entries > - * @nvec: number of @entries > - * > - * Setup the MSI-X capability structure of device function with a > - * 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 msi_irqs *msi, void __iomem *base, > - struct msix_entry *entries, int nvec) > -{ > - int ret; > - > - /* Ensure MSI-X is disabled while it is set up */ > - msi_set_enable(msi, 0, MSIX_TYPE); > - > - ret = msix_setup_entries(msi, base, entries, nvec); > - if (ret) > - return ret; > - > - ret = arch_setup_msi_irqs(msi, nvec, MSIX_TYPE); > - if (ret) > - goto out_avail; > - > - /* > - * Some devices require MSI-X to be enabled before we can touch the > - * MSI-X registers. We need to mask all the vectors to prevent > - * interrupts coming in before they're fully set up. > - */ > - msix_program_entries(msi, entries); > - > - /* Set MSI-X enabled bits and unmask the function */ > - pci_intx_for_msi(msi, 0); > - msi->msix_enabled = 1; > - > - msi_set_enable(msi, 1, MSIX_TYPE); > > return 0; > - > -out_avail: > - if (ret < 0) { > - /* > - * If we had some success, report the number of irqs > - * we succeeded in setting up. > - */ > - struct msi_desc *entry; > - int avail = 0; > - > - list_for_each_entry(entry, &msi->msi_list, list) { > - if (entry->irq != 0) > - avail++; > - } > - if (avail != 0) > - ret = avail; > - } > - > - free_msi_irqs(msi); > - > - return ret; > } > > /** > @@ -886,25 +492,14 @@ EXPORT_SYMBOL(pci_msi_vec_count); > void pci_msi_shutdown(struct pci_dev *dev) > { > struct msi_desc *desc; > - u32 mask; > > if (!pci_msi_enable || !dev || > !pci_dev_msi_enabled(dev, MSI_TYPE)) > return; > > - BUG_ON(list_empty(&dev->msi->msi_list)); > - desc = list_first_entry(&dev->msi->msi_list, struct msi_desc, list); > - > - 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); > - /* Keep cached state to be restored */ > - arch_msi_mask_irq(desc, mask, ~mask); > - > + msi_shutdown(dev->msi); > /* Restore dev->irq to its default pin-assertion irq */ > + desc = list_first_entry(&dev->msi->msi_list, struct msi_desc, list); > dev->irq = desc->msi_attrib.default_irq; > } > > @@ -1014,20 +609,10 @@ EXPORT_SYMBOL(pci_enable_msix); > > void pci_msix_shutdown(struct pci_dev *dev) > { > - struct msi_desc *entry; > - > - if (!pci_msi_enable || !dev || !pci_dev_msi_enabled(dev, MSIX_TYPE)) > + if (!pci_msi_enable || !dev) > return; > > - /* Return the device with MSI-X masked as initial states */ > - list_for_each_entry(entry, &dev->msi->msi_list, list) { > - /* Keep cached states to be restored */ > - arch_msix_mask_irq(entry, 1); > - } > - > - msi_set_enable(dev->msi, 0, MSIX_TYPE); > - pci_intx_for_msi(dev->msi, 1); > - dev->msi->msix_enabled = 0; > + msix_shutdown(dev->msi); > } > > void pci_disable_msix(struct pci_dev *dev) > @@ -1060,30 +645,16 @@ int pci_msi_enabled(void) > EXPORT_SYMBOL(pci_msi_enabled); > > 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_enable = pci_msi_set_enable, > + .msi_setup_entry = pci_msi_setup_entry, > + .msix_setup_entries = pci_msix_setup_entries, > + .msi_mask_irq = pci_msi_mask_irq, > + .msix_mask_irq = pci_msix_mask_irq, > + .msi_read_message = pci_read_msi_msg, > + .msi_write_message = pci_write_msi_msg, > .msi_set_intx = pci_intx_for_msi, > }; > > -struct msi_irqs *alloc_msi_irqs(void *data, struct msi_ops *ops) > -{ > - 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 > @@ -1100,10 +671,10 @@ void pci_msi_init_pci_dev(struct pci_dev *dev) > > dev->msi->node = dev_to_node(&dev->dev); > if (dev->msi_cap) > - msi_set_enable(dev->msi, 0, MSI_TYPE); > + pci_msi_set_enable(dev->msi, 0, MSI_TYPE); > > if (dev->msix_cap) > - msi_set_enable(dev->msi, 0, MSIX_TYPE); > + pci_msi_set_enable(dev->msi, 0, MSIX_TYPE); > } > } > > @@ -1224,4 +795,3 @@ int pci_enable_msix_range(struct pci_dev *dev, struct > msix_entry *entries, > } > EXPORT_SYMBOL(pci_enable_msix_range); > > - > diff --git a/include/linux/msi.h b/include/linux/msi.h > index fc8f3e8..87ed0dd 100644 > --- a/include/linux/msi.h > +++ b/include/linux/msi.h > @@ -28,9 +28,9 @@ struct msix_entry { > > struct msi_ops { > void (*msi_set_enable)(struct msi_irqs *msi, int enable, int type); > - struct msi_desc *(*msi_setup_entry)(struct msi_irqs *msi); > - int (*msix_setup_entries)(struct msi_irqs *msi, void __iomem *base, > - struct msix_entry *entries, int nvec); > + struct msi_desc *(*msi_setup_entry)(struct msi_irqs *msi, > + struct msi_desc *entry); > + int (*msix_setup_entries)(struct msi_irqs *msi, struct msix_entry > *entries); > u32 (*msi_mask_irq)(struct msi_desc *desc, u32 mask, u32 flag); > u32 (*msix_mask_irq)(struct msi_desc *desc, u32 flag); > void (*msi_read_message)(struct msi_desc *desc, struct msi_msg *msg); > @@ -49,6 +49,18 @@ void __write_msi_msg(struct msi_desc *entry, struct msi_msg > *msg); > void read_msi_msg(unsigned int irq, struct msi_msg *msg); > void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg); > void write_msi_msg(unsigned int irq, struct msi_msg *msg); > +struct msi_desc *alloc_msi_entry(struct msi_irqs *msi); > +void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag); > +void msix_mask_irq(struct msi_desc *desc, u32 flag); > +void msi_set_enable(struct msi_irqs *msi, int enable, int type); > + > +struct msi_irqs *alloc_msi_irqs(void *data, struct msi_ops *ops); > + > +void free_msi_irqs(struct msi_irqs *msi); > + > +int msi_capability_init(struct msi_irqs *msi, int nvec); > +int msix_capability_init(struct msi_irqs *msi, void __iomem *base, > + struct msix_entry *entries, int nvec); > > struct msi_desc { > struct { > @@ -89,12 +101,17 @@ 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); > +u32 arch_msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag); > +u32 arch_msix_mask_irq(struct msi_desc *desc, u32 flag); > > 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); > > +void msi_shutdown(struct msi_irqs *msi); > +void msix_shutdown(struct msi_irqs *msi); > + > #define MSI_TYPE 0x01 > #define MSIX_TYPE 0x02 > > @@ -111,4 +128,12 @@ struct msi_chip { > int nvec, int type); > }; > > +static inline __attribute_const__ u32 msi_mask(unsigned x) > +{ > + /* Don't shift by >= width of type */ > + if (x >= 5) > + return 0xffffffff; > + return (1 << (1 << x)) - 1; > +} > + > #endif /* LINUX_MSI_H */ > -- > 1.7.1 > > -- > To unsubscribe from this list: send the line "unsubscribe linux-pci" in > the body of a message to majordomo@xxxxxxxxxxxxxxx > More majordomo info at http://vger.kernel.org/majordomo-info.html -- To unsubscribe from this list: send the line "unsubscribe linux-pci" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html
