#include <linux/err.h>
#include <linux/export.h>
#include <linux/irq.h>
#include "../pci.h"
#include "msi.h"
int pci_msi_enable = 1;
int pci_msi_ignore_mask;
static int pci_msi_supported(struct pci_dev *dev, int nvec)
{
struct pci_bus *bus;
if (!pci_msi_enable)
return 0;
if (!dev || dev->no_msi)
return 0;
if (nvec < 1)
return 0;
for (bus = dev->bus; bus; bus = bus->parent)
if (bus->bus_flags & PCI_BUS_FLAGS_NO_MSI)
return 0;
return 1;
}
static void pcim_msi_release(void *pcidev)
{
struct pci_dev *dev = pcidev;
dev->is_msi_managed = false;
pci_free_irq_vectors(dev);
}
static int pcim_setup_msi_release(struct pci_dev *dev)
{
int ret;
if (!pci_is_managed(dev) || dev->is_msi_managed)
return 0;
ret = devm_add_action(&dev->dev, pcim_msi_release, dev);
if (!ret)
dev->is_msi_managed = true;
return ret;
}
static int pci_setup_msi_context(struct pci_dev *dev)
{
int ret = msi_setup_device_data(&dev->dev);
if (!ret)
ret = pcim_setup_msi_release(dev);
return ret;
}
void pci_msi_update_mask(struct msi_desc *desc, u32 clear, u32 set)
{
raw_spinlock_t *lock = &to_pci_dev(desc->dev)->msi_lock;
unsigned long flags;
if (!desc->pci.msi_attrib.can_mask)
return;
raw_spin_lock_irqsave(lock, flags);
desc->pci.msi_mask &= ~clear;
desc->pci.msi_mask |= set;
pci_write_config_dword(msi_desc_to_pci_dev(desc), desc->pci.mask_pos,
desc->pci.msi_mask);
raw_spin_unlock_irqrestore(lock, flags);
}
void pci_msi_mask_irq(struct irq_data *data)
{
struct msi_desc *desc = irq_data_get_msi_desc(data);
__pci_msi_mask_desc(desc, BIT(data->irq - desc->irq));
}
EXPORT_SYMBOL_GPL(pci_msi_mask_irq);
void pci_msi_unmask_irq(struct irq_data *data)
{
struct msi_desc *desc = irq_data_get_msi_desc(data);
__pci_msi_unmask_desc(desc, BIT(data->irq - desc->irq));
}
EXPORT_SYMBOL_GPL(pci_msi_unmask_irq);
void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
{
struct pci_dev *dev = msi_desc_to_pci_dev(entry);
BUG_ON(dev->current_state != PCI_D0);
if (entry->pci.msi_attrib.is_msix) {
void __iomem *base = pci_msix_desc_addr(entry);
if (WARN_ON_ONCE(entry->pci.msi_attrib.is_virtual))
return;
msg->address_lo = readl(base + PCI_MSIX_ENTRY_LOWER_ADDR);
msg->address_hi = readl(base + PCI_MSIX_ENTRY_UPPER_ADDR);
msg->data = readl(base + PCI_MSIX_ENTRY_DATA);
} else {
int pos = dev->msi_cap;
u16 data;
pci_read_config_dword(dev, pos + PCI_MSI_ADDRESS_LO,
&msg->address_lo);
if (entry->pci.msi_attrib.is_64) {
pci_read_config_dword(dev, pos + PCI_MSI_ADDRESS_HI,
&msg->address_hi);
pci_read_config_word(dev, pos + PCI_MSI_DATA_64, &data);
} else {
msg->address_hi = 0;
pci_read_config_word(dev, pos + PCI_MSI_DATA_32, &data);
}
msg->data = data;
}
}
static inline void pci_write_msg_msi(struct pci_dev *dev, struct msi_desc *desc,
struct msi_msg *msg)
{
int pos = dev->msi_cap;
u16 msgctl;
pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl);
msgctl &= ~PCI_MSI_FLAGS_QSIZE;
msgctl |= desc->pci.msi_attrib.multiple << 4;
pci_write_config_word(dev, pos + PCI_MSI_FLAGS, msgctl);
pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_LO, msg->address_lo);
if (desc->pci.msi_attrib.is_64) {
pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_HI, msg->address_hi);
pci_write_config_word(dev, pos + PCI_MSI_DATA_64, msg->data);
} else {
pci_write_config_word(dev, pos + PCI_MSI_DATA_32, msg->data);
}
pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl);
}
static inline void pci_write_msg_msix(struct msi_desc *desc, struct msi_msg *msg)
{
void __iomem *base = pci_msix_desc_addr(desc);
u32 ctrl = desc->pci.msix_ctrl;
bool unmasked = !(ctrl & PCI_MSIX_ENTRY_CTRL_MASKBIT);
if (desc->pci.msi_attrib.is_virtual)
return;
if (unmasked)
pci_msix_write_vector_ctrl(desc, ctrl | PCI_MSIX_ENTRY_CTRL_MASKBIT);
writel(msg->address_lo, base + PCI_MSIX_ENTRY_LOWER_ADDR);
writel(msg->address_hi, base + PCI_MSIX_ENTRY_UPPER_ADDR);
writel(msg->data, base + PCI_MSIX_ENTRY_DATA);
if (unmasked)
pci_msix_write_vector_ctrl(desc, ctrl);
readl(base + PCI_MSIX_ENTRY_DATA);
}
void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
{
struct pci_dev *dev = msi_desc_to_pci_dev(entry);
if (dev->current_state != PCI_D0 || pci_dev_is_disconnected(dev)) {
} else if (entry->pci.msi_attrib.is_msix) {
pci_write_msg_msix(entry, msg);
} else {
pci_write_msg_msi(dev, entry, msg);
}
entry->msg = *msg;
if (entry->write_msi_msg)
entry->write_msi_msg(entry, entry->write_msi_msg_data);
}
void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg)
{
struct msi_desc *entry = irq_get_msi_desc(irq);
__pci_write_msi_msg(entry, msg);
}
EXPORT_SYMBOL_GPL(pci_write_msi_msg);
static void pci_intx_for_msi(struct pci_dev *dev, int enable)
{
if (!(dev->dev_flags & PCI_DEV_FLAGS_MSI_INTX_DISABLE_BUG))
pci_intx(dev, enable);
}
static void pci_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);
}
static int msi_setup_msi_desc(struct pci_dev *dev, int nvec,
struct irq_affinity_desc *masks)
{
struct msi_desc desc;
u16 control;
memset(&desc, 0, sizeof(desc));
pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control);
if (dev->dev_flags & PCI_DEV_FLAGS_HAS_MSI_MASKING)
control |= PCI_MSI_FLAGS_MASKBIT;
if (pci_msi_ignore_mask)
control &= ~PCI_MSI_FLAGS_MASKBIT;
desc.nvec_used = nvec;
desc.pci.msi_attrib.is_64 = !!(control & PCI_MSI_FLAGS_64BIT);
desc.pci.msi_attrib.can_mask = !!(control & PCI_MSI_FLAGS_MASKBIT);
desc.pci.msi_attrib.default_irq = dev->irq;
desc.pci.msi_attrib.multi_cap = (control & PCI_MSI_FLAGS_QMASK) >> 1;
desc.pci.msi_attrib.multiple = ilog2(__roundup_pow_of_two(nvec));
desc.affinity = masks;
if (control & PCI_MSI_FLAGS_64BIT)
desc.pci.mask_pos = dev->msi_cap + PCI_MSI_MASK_64;
else
desc.pci.mask_pos = dev->msi_cap + PCI_MSI_MASK_32;
if (desc.pci.msi_attrib.can_mask)
pci_read_config_dword(dev, desc.pci.mask_pos, &desc.pci.msi_mask);
return msi_insert_msi_desc(&dev->dev, &desc);
}
static int msi_verify_entries(struct pci_dev *dev)
{
struct msi_desc *entry;
if (!dev->no_64bit_msi)
return 0;
msi_for_each_desc(entry, &dev->dev, MSI_DESC_ALL) {
if (entry->msg.address_hi) {
pci_err(dev, "arch assigned 64-bit MSI address %#x%08x but device only supports 32 bits\n",
entry->msg.address_hi, entry->msg.address_lo);
break;
}
}
return !entry ? 0 : -EIO;
}
static int msi_capability_init(struct pci_dev *dev, int nvec,
struct irq_affinity *affd)
{
struct irq_affinity_desc *masks = NULL;
struct msi_desc *entry;
int ret;
if (nvec > 1 && !pci_msi_domain_supports(dev, MSI_FLAG_MULTI_PCI_MSI, ALLOW_LEGACY))
return 1;
pci_msi_set_enable(dev, 0);
dev->msi_enabled = 1;
if (affd)
masks = irq_create_affinity_masks(nvec, affd);
msi_lock_descs(&dev->dev);
ret = msi_setup_msi_desc(dev, nvec, masks);
if (ret)
goto fail;
entry = msi_first_desc(&dev->dev, MSI_DESC_ALL);
pci_msi_mask(entry, msi_multi_mask(entry));
ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI);
if (ret)
goto err;
ret = msi_verify_entries(dev);
if (ret)
goto err;
pci_intx_for_msi(dev, 0);
pci_msi_set_enable(dev, 1);
pcibios_free_irq(dev);
dev->irq = entry->irq;
goto unlock;
err:
pci_msi_unmask(entry, msi_multi_mask(entry));
pci_free_msi_irqs(dev);
fail:
dev->msi_enabled = 0;
unlock:
msi_unlock_descs(&dev->dev);
kfree(masks);
return ret;
}
int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec,
struct irq_affinity *affd)
{
int nvec;
int rc;
if (!pci_msi_supported(dev, minvec) || dev->current_state != PCI_D0)
return -EINVAL;
if (dev->msix_enabled) {
pci_info(dev, "can't enable MSI (MSI-X already enabled)\n");
return -EINVAL;
}
if (maxvec < minvec)
return -ERANGE;
if (WARN_ON_ONCE(dev->msi_enabled))
return -EINVAL;
nvec = pci_msi_vec_count(dev);
if (nvec < 0)
return nvec;
if (nvec < minvec)
return -ENOSPC;
if (nvec > maxvec)
nvec = maxvec;
rc = pci_setup_msi_context(dev);
if (rc)
return rc;
if (!pci_setup_msi_device_domain(dev))
return -ENODEV;
for (;;) {
if (affd) {
nvec = irq_calc_affinity_vectors(minvec, nvec, affd);
if (nvec < minvec)
return -ENOSPC;
}
rc = msi_capability_init(dev, nvec, affd);
if (rc == 0)
return nvec;
if (rc < 0)
return rc;
if (rc < minvec)
return -ENOSPC;
nvec = rc;
}
}
int pci_msi_vec_count(struct pci_dev *dev)
{
int ret;
u16 msgctl;
if (!dev->msi_cap)
return -EINVAL;
pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &msgctl);
ret = 1 << ((msgctl & PCI_MSI_FLAGS_QMASK) >> 1);
return ret;
}
EXPORT_SYMBOL(pci_msi_vec_count);
bool __weak arch_restore_msi_irqs(struct pci_dev *dev)
{
return true;
}
void __pci_restore_msi_state(struct pci_dev *dev)
{
struct msi_desc *entry;
u16 control;
if (!dev->msi_enabled)
return;
entry = irq_get_msi_desc(dev->irq);
pci_intx_for_msi(dev, 0);
pci_msi_set_enable(dev, 0);
if (arch_restore_msi_irqs(dev))
__pci_write_msi_msg(entry, &entry->msg);
pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &control);
pci_msi_update_mask(entry, 0, 0);
control &= ~PCI_MSI_FLAGS_QSIZE;
control |= (entry->pci.msi_attrib.multiple << 4) | PCI_MSI_FLAGS_ENABLE;
pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, control);
}
void pci_msi_shutdown(struct pci_dev *dev)
{
struct msi_desc *desc;
if (!pci_msi_enable || !dev || !dev->msi_enabled)
return;
pci_msi_set_enable(dev, 0);
pci_intx_for_msi(dev, 1);
dev->msi_enabled = 0;
desc = msi_first_desc(&dev->dev, MSI_DESC_ALL);
if (!WARN_ON_ONCE(!desc))
pci_msi_unmask(desc, msi_multi_mask(desc));
dev->irq = desc->pci.msi_attrib.default_irq;
pcibios_alloc_irq(dev);
}
static void pci_msix_clear_and_set_ctrl(struct pci_dev *dev, u16 clear, u16 set)
{
u16 ctrl;
pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &ctrl);
ctrl &= ~clear;
ctrl |= set;
pci_write_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, ctrl);
}
static void __iomem *msix_map_region(struct pci_dev *dev,
unsigned int nr_entries)
{
resource_size_t phys_addr;
u32 table_offset;
unsigned long flags;
u8 bir;
pci_read_config_dword(dev, dev->msix_cap + PCI_MSIX_TABLE,
&table_offset);
bir = (u8)(table_offset & PCI_MSIX_TABLE_BIR);
flags = pci_resource_flags(dev, bir);
if (!flags || (flags & IORESOURCE_UNSET))
return NULL;
table_offset &= PCI_MSIX_TABLE_OFFSET;
phys_addr = pci_resource_start(dev, bir) + table_offset;
return ioremap(phys_addr, nr_entries * PCI_MSIX_ENTRY_SIZE);
}
void msix_prepare_msi_desc(struct pci_dev *dev, struct msi_desc *desc)
{
desc->nvec_used = 1;
desc->pci.msi_attrib.is_msix = 1;
desc->pci.msi_attrib.is_64 = 1;
desc->pci.msi_attrib.default_irq = dev->irq;
desc->pci.mask_base = dev->msix_base;
desc->pci.msi_attrib.can_mask = !pci_msi_ignore_mask &&
!desc->pci.msi_attrib.is_virtual;
if (desc->pci.msi_attrib.can_mask) {
void __iomem *addr = pci_msix_desc_addr(desc);
desc->pci.msix_ctrl = readl(addr + PCI_MSIX_ENTRY_VECTOR_CTRL);
}
}
static int msix_setup_msi_descs(struct pci_dev *dev, struct msix_entry *entries,
int nvec, struct irq_affinity_desc *masks)
{
int ret = 0, i, vec_count = pci_msix_vec_count(dev);
struct irq_affinity_desc *curmsk;
struct msi_desc desc;
memset(&desc, 0, sizeof(desc));
for (i = 0, curmsk = masks; i < nvec; i++, curmsk++) {
desc.msi_index = entries ? entries[i].entry : i;
desc.affinity = masks ? curmsk : NULL;
desc.pci.msi_attrib.is_virtual = desc.msi_index >= vec_count;
msix_prepare_msi_desc(dev, &desc);
ret = msi_insert_msi_desc(&dev->dev, &desc);
if (ret)
break;
}
return ret;
}
static void msix_update_entries(struct pci_dev *dev, struct msix_entry *entries)
{
struct msi_desc *desc;
if (entries) {
msi_for_each_desc(desc, &dev->dev, MSI_DESC_ALL) {
entries->vector = desc->irq;
entries++;
}
}
}
static void msix_mask_all(void __iomem *base, int tsize)
{
u32 ctrl = PCI_MSIX_ENTRY_CTRL_MASKBIT;
int i;
if (pci_msi_ignore_mask)
return;
for (i = 0; i < tsize; i++, base += PCI_MSIX_ENTRY_SIZE)
writel(ctrl, base + PCI_MSIX_ENTRY_VECTOR_CTRL);
}
static int msix_setup_interrupts(struct pci_dev *dev, struct msix_entry *entries,
int nvec, struct irq_affinity *affd)
{
struct irq_affinity_desc *masks = NULL;
int ret;
if (affd)
masks = irq_create_affinity_masks(nvec, affd);
msi_lock_descs(&dev->dev);
ret = msix_setup_msi_descs(dev, entries, nvec, masks);
if (ret)
goto out_free;
ret = pci_msi_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX);
if (ret)
goto out_free;
ret = msi_verify_entries(dev);
if (ret)
goto out_free;
msix_update_entries(dev, entries);
goto out_unlock;
out_free:
pci_free_msi_irqs(dev);
out_unlock:
msi_unlock_descs(&dev->dev);
kfree(masks);
return ret;
}
static int msix_capability_init(struct pci_dev *dev, struct msix_entry *entries,
int nvec, struct irq_affinity *affd)
{
int ret, tsize;
u16 control;
pci_msix_clear_and_set_ctrl(dev, 0, PCI_MSIX_FLAGS_MASKALL |
PCI_MSIX_FLAGS_ENABLE);
dev->msix_enabled = 1;
pci_read_config_word(dev, dev->msix_cap + PCI_MSIX_FLAGS, &control);
tsize = msix_table_size(control);
dev->msix_base = msix_map_region(dev, tsize);
if (!dev->msix_base) {
ret = -ENOMEM;
goto out_disable;
}
ret = msix_setup_interrupts(dev, entries, nvec, affd);
if (ret)
goto out_disable;
pci_intx_for_msi(dev, 0);
msix_mask_all(dev->msix_base, tsize);
pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0);
pcibios_free_irq(dev);
return 0;
out_disable:
dev->msix_enabled = 0;
pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE, 0);
return ret;
}
static bool pci_msix_validate_entries(struct pci_dev *dev, struct msix_entry *entries, int nvec)
{
bool nogap;
int i, j;
if (!entries)
return true;
nogap = pci_msi_domain_supports(dev, MSI_FLAG_MSIX_CONTIGUOUS, DENY_LEGACY);
for (i = 0; i < nvec; i++) {
for (j = i + 1; j < nvec; j++) {
if (entries[i].entry == entries[j].entry)
return false;
}
if (nogap && entries[i].entry != i)
return false;
}
return true;
}
int __pci_enable_msix_range(struct pci_dev *dev, struct msix_entry *entries, int minvec,
int maxvec, struct irq_affinity *affd, int flags)
{
int hwsize, rc, nvec = maxvec;
if (maxvec < minvec)
return -ERANGE;
if (dev->msi_enabled) {
pci_info(dev, "can't enable MSI-X (MSI already enabled)\n");
return -EINVAL;
}
if (WARN_ON_ONCE(dev->msix_enabled))
return -EINVAL;
if (!pci_msi_domain_supports(dev, MSI_FLAG_PCI_MSIX, ALLOW_LEGACY))
return -ENOTSUPP;
if (!pci_msi_supported(dev, nvec) || dev->current_state != PCI_D0)
return -EINVAL;
hwsize = pci_msix_vec_count(dev);
if (hwsize < 0)
return hwsize;
if (!pci_msix_validate_entries(dev, entries, nvec))
return -EINVAL;
if (hwsize < nvec) {
if (flags & PCI_IRQ_VIRTUAL)
hwsize = nvec;
else
nvec = hwsize;
}
if (nvec < minvec)
return -ENOSPC;
rc = pci_setup_msi_context(dev);
if (rc)
return rc;
if (!pci_setup_msix_device_domain(dev, hwsize))
return -ENODEV;
for (;;) {
if (affd) {
nvec = irq_calc_affinity_vectors(minvec, nvec, affd);
if (nvec < minvec)
return -ENOSPC;
}
rc = msix_capability_init(dev, entries, nvec, affd);
if (rc == 0)
return nvec;
if (rc < 0)
return rc;
if (rc < minvec)
return -ENOSPC;
nvec = rc;
}
}
void __pci_restore_msix_state(struct pci_dev *dev)
{
struct msi_desc *entry;
bool write_msg;
if (!dev->msix_enabled)
return;
pci_intx_for_msi(dev, 0);
pci_msix_clear_and_set_ctrl(dev, 0,
PCI_MSIX_FLAGS_ENABLE | PCI_MSIX_FLAGS_MASKALL);
write_msg = arch_restore_msi_irqs(dev);
msi_lock_descs(&dev->dev);
msi_for_each_desc(entry, &dev->dev, MSI_DESC_ALL) {
if (write_msg)
__pci_write_msi_msg(entry, &entry->msg);
pci_msix_write_vector_ctrl(entry, entry->pci.msix_ctrl);
}
msi_unlock_descs(&dev->dev);
pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_MASKALL, 0);
}
void pci_msix_shutdown(struct pci_dev *dev)
{
struct msi_desc *desc;
if (!pci_msi_enable || !dev || !dev->msix_enabled)
return;
if (pci_dev_is_disconnected(dev)) {
dev->msix_enabled = 0;
return;
}
msi_for_each_desc(desc, &dev->dev, MSI_DESC_ALL)
pci_msix_mask(desc);
pci_msix_clear_and_set_ctrl(dev, PCI_MSIX_FLAGS_ENABLE, 0);
pci_intx_for_msi(dev, 1);
dev->msix_enabled = 0;
pcibios_alloc_irq(dev);
}
void pci_free_msi_irqs(struct pci_dev *dev)
{
pci_msi_teardown_msi_irqs(dev);
if (dev->msix_base) {
iounmap(dev->msix_base);
dev->msix_base = NULL;
}
}
struct pci_dev *msi_desc_to_pci_dev(struct msi_desc *desc)
{
return to_pci_dev(desc->dev);
}
EXPORT_SYMBOL(msi_desc_to_pci_dev);
void pci_no_msi(void)
{
pci_msi_enable = 0;
}