#include <linux/irq.h>
#include <linux/interrupt.h>
#include <linux/init.h>
-#include <linux/config.h>
#include <linux/ioport.h>
#include <linux/smp_lock.h>
#include <linux/pci.h>
#include "pci.h"
#include "msi.h"
-#define MSI_TARGET_CPU first_cpu(cpu_online_map)
-
static DEFINE_SPINLOCK(msi_lock);
static struct msi_desc* msi_desc[NR_IRQS] = { [0 ... NR_IRQS-1] = NULL };
static kmem_cache_t* msi_cachep;
#ifndef CONFIG_X86_IO_APIC
int vector_irq[NR_VECTORS] = { [0 ... NR_VECTORS - 1] = -1};
-u8 irq_vector[NR_IRQ_VECTORS] = { FIRST_DEVICE_VECTOR , 0 };
#endif
+static struct msi_ops *msi_ops;
+
+int
+msi_register(struct msi_ops *ops)
+{
+ msi_ops = ops;
+ return 0;
+}
+
static void msi_cache_ctor(void *p, kmem_cache_t *cache, unsigned long flags)
{
- memset(p, 0, NR_IRQS * sizeof(struct msi_desc));
+ memset(p, 0, sizeof(struct msi_desc));
}
static int msi_cache_init(void)
{
msi_cachep = kmem_cache_create("msi_cache",
- NR_IRQS * sizeof(struct msi_desc),
+ sizeof(struct msi_desc),
0, SLAB_HWCACHE_ALIGN, msi_cache_ctor, NULL);
if (!msi_cachep)
return -ENOMEM;
static void set_msi_affinity(unsigned int vector, cpumask_t cpu_mask)
{
struct msi_desc *entry;
- struct msg_address address;
+ u32 address_hi, address_lo;
unsigned int irq = vector;
unsigned int dest_cpu = first_cpu(cpu_mask);
if (!pos)
return;
+ pci_read_config_dword(entry->dev, msi_upper_address_reg(pos),
+ &address_hi);
pci_read_config_dword(entry->dev, msi_lower_address_reg(pos),
- &address.lo_address.value);
- address.lo_address.value &= MSI_ADDRESS_DEST_ID_MASK;
- address.lo_address.value |= (cpu_physical_id(dest_cpu) <<
- MSI_TARGET_CPU_SHIFT);
- entry->msi_attrib.current_cpu = cpu_physical_id(dest_cpu);
+ &address_lo);
+
+ msi_ops->target(vector, dest_cpu, &address_hi, &address_lo);
+
+ pci_write_config_dword(entry->dev, msi_upper_address_reg(pos),
+ address_hi);
pci_write_config_dword(entry->dev, msi_lower_address_reg(pos),
- address.lo_address.value);
+ address_lo);
set_native_irq_info(irq, cpu_mask);
break;
}
case PCI_CAP_ID_MSIX:
{
- int offset = entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
- PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET;
-
- address.lo_address.value = readl(entry->mask_base + offset);
- address.lo_address.value &= MSI_ADDRESS_DEST_ID_MASK;
- address.lo_address.value |= (cpu_physical_id(dest_cpu) <<
- MSI_TARGET_CPU_SHIFT);
- entry->msi_attrib.current_cpu = cpu_physical_id(dest_cpu);
- writel(address.lo_address.value, entry->mask_base + offset);
+ int offset_hi =
+ entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
+ PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET;
+ int offset_lo =
+ entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
+ PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET;
+
+ address_hi = readl(entry->mask_base + offset_hi);
+ address_lo = readl(entry->mask_base + offset_lo);
+
+ msi_ops->target(vector, dest_cpu, &address_hi, &address_lo);
+
+ writel(address_hi, entry->mask_base + offset_hi);
+ writel(address_lo, entry->mask_base + offset_lo);
set_native_irq_info(irq, cpu_mask);
break;
}
.set_affinity = set_msi_affinity
};
-static void msi_data_init(struct msg_data *msi_data,
- unsigned int vector)
-{
- memset(msi_data, 0, sizeof(struct msg_data));
- msi_data->vector = (u8)vector;
- msi_data->delivery_mode = MSI_DELIVERY_MODE;
- msi_data->level = MSI_LEVEL_MODE;
- msi_data->trigger = MSI_TRIGGER_MODE;
-}
-
-static void msi_address_init(struct msg_address *msi_address)
-{
- unsigned int dest_id;
- unsigned long dest_phys_id = cpu_physical_id(MSI_TARGET_CPU);
-
- memset(msi_address, 0, sizeof(struct msg_address));
- msi_address->hi_address = (u32)0;
- dest_id = (MSI_ADDRESS_HEADER << MSI_ADDRESS_HEADER_SHIFT);
- msi_address->lo_address.u.dest_mode = MSI_PHYSICAL_MODE;
- msi_address->lo_address.u.redirection_hint = MSI_REDIRECTION_HINT_MODE;
- msi_address->lo_address.u.dest_id = dest_id;
- msi_address->lo_address.value |= (dest_phys_id << MSI_TARGET_CPU_SHIFT);
-}
-
static int msi_free_vector(struct pci_dev* dev, int vector, int reassign);
static int assign_msi_vector(void)
{
return status;
}
+ status = msi_arch_init();
+ if (status < 0) {
+ pci_msi_enable = 0;
+ printk(KERN_WARNING
+ "PCI: MSI arch init failed. MSI disabled.\n");
+ return status;
+ }
+
+ if (! msi_ops) {
+ printk(KERN_WARNING
+ "PCI: MSI ops not registered. MSI disabled.\n");
+ status = -EINVAL;
+ return status;
+ }
+
+ last_alloc_vector = assign_irq_vector(AUTO_ASSIGN);
status = msi_cache_init();
if (status < 0) {
pci_msi_enable = 0;
printk(KERN_WARNING "PCI: MSI cache init failed\n");
return status;
}
- last_alloc_vector = assign_irq_vector(AUTO_ASSIGN);
+
if (last_alloc_vector < 0) {
pci_msi_enable = 0;
printk(KERN_WARNING "PCI: No interrupt vectors available for MSI\n");
spin_lock_irqsave(&irq_desc[pos].lock, flags);
if (cap_id == PCI_CAP_ID_MSIX)
- irq_desc[pos].handler = &msix_irq_type;
+ irq_desc[pos].chip = &msix_irq_type;
else {
if (!mask)
- irq_desc[pos].handler = &msi_irq_wo_maskbit_type;
+ irq_desc[pos].chip = &msi_irq_wo_maskbit_type;
else
- irq_desc[pos].handler = &msi_irq_w_maskbit_type;
+ irq_desc[pos].chip = &msi_irq_w_maskbit_type;
}
spin_unlock_irqrestore(&irq_desc[pos].lock, flags);
}
/* Set enabled bits to single MSI & enable MSI_enable bit */
msi_enable(control, 1);
pci_write_config_word(dev, msi_control_reg(pos), control);
+ dev->msi_enabled = 1;
} else {
msix_enable(control);
pci_write_config_word(dev, msi_control_reg(pos), control);
+ dev->msix_enabled = 1;
}
if (pci_find_capability(dev, PCI_CAP_ID_EXP)) {
/* PCI Express Endpoint device detected */
/* Set enabled bits to single MSI & enable MSI_enable bit */
msi_disable(control);
pci_write_config_word(dev, msi_control_reg(pos), control);
+ dev->msi_enabled = 0;
} else {
msix_disable(control);
pci_write_config_word(dev, msi_control_reg(pos), control);
+ dev->msix_enabled = 0;
}
if (pci_find_capability(dev, PCI_CAP_ID_EXP)) {
/* PCI Express Endpoint device detected */
pci_read_config_dword(dev, pos + PCI_MSI_DATA_32, &cap[i++]);
if (control & PCI_MSI_FLAGS_MASKBIT)
pci_read_config_dword(dev, pos + PCI_MSI_MASK_BIT, &cap[i++]);
- disable_msi_mode(dev, pos, PCI_CAP_ID_MSI);
save_state->cap_nr = PCI_CAP_ID_MSI;
pci_add_saved_cap(dev, save_state);
return 0;
int pci_save_msix_state(struct pci_dev *dev)
{
int pos;
+ int temp;
+ int vector, head, tail = 0;
u16 control;
struct pci_cap_saved_state *save_state;
if (pos <= 0 || dev->no_msi)
return 0;
+ /* save the capability */
pci_read_config_word(dev, msi_control_reg(pos), &control);
if (!(control & PCI_MSIX_FLAGS_ENABLE))
return 0;
}
*((u16 *)&save_state->data[0]) = control;
- disable_msi_mode(dev, pos, PCI_CAP_ID_MSIX);
+ /* save the table */
+ temp = dev->irq;
+ if (msi_lookup_vector(dev, PCI_CAP_ID_MSIX)) {
+ kfree(save_state);
+ return -EINVAL;
+ }
+
+ vector = head = dev->irq;
+ while (head != tail) {
+ int j;
+ void __iomem *base;
+ struct msi_desc *entry;
+
+ entry = msi_desc[vector];
+ base = entry->mask_base;
+ j = entry->msi_attrib.entry_nr;
+
+ entry->address_lo_save =
+ readl(base + j * PCI_MSIX_ENTRY_SIZE +
+ PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET);
+ entry->address_hi_save =
+ readl(base + j * PCI_MSIX_ENTRY_SIZE +
+ PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET);
+ entry->data_save =
+ readl(base + j * PCI_MSIX_ENTRY_SIZE +
+ PCI_MSIX_ENTRY_DATA_OFFSET);
+
+ tail = msi_desc[vector]->link.tail;
+ vector = tail;
+ }
+ dev->irq = temp;
+
save_state->cap_nr = PCI_CAP_ID_MSIX;
pci_add_saved_cap(dev, save_state);
return 0;
int vector, head, tail = 0;
void __iomem *base;
int j;
- struct msg_address address;
- struct msg_data data;
struct msi_desc *entry;
int temp;
struct pci_cap_saved_state *save_state;
base = entry->mask_base;
j = entry->msi_attrib.entry_nr;
- msi_address_init(&address);
- msi_data_init(&data, vector);
-
- address.lo_address.value &= MSI_ADDRESS_DEST_ID_MASK;
- address.lo_address.value |= entry->msi_attrib.current_cpu <<
- MSI_TARGET_CPU_SHIFT;
-
- writel(address.lo_address.value,
+ writel(entry->address_lo_save,
base + j * PCI_MSIX_ENTRY_SIZE +
PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET);
- writel(address.hi_address,
+ writel(entry->address_hi_save,
base + j * PCI_MSIX_ENTRY_SIZE +
PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET);
- writel(*(u32*)&data,
+ writel(entry->data_save,
base + j * PCI_MSIX_ENTRY_SIZE +
PCI_MSIX_ENTRY_DATA_OFFSET);
}
#endif
-static void msi_register_init(struct pci_dev *dev, struct msi_desc *entry)
+static int msi_register_init(struct pci_dev *dev, struct msi_desc *entry)
{
- struct msg_address address;
- struct msg_data data;
+ int status;
+ u32 address_hi;
+ u32 address_lo;
+ u32 data;
int pos, vector = dev->irq;
u16 control;
pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
pci_read_config_word(dev, msi_control_reg(pos), &control);
+
/* Configure MSI capability structure */
- msi_address_init(&address);
- msi_data_init(&data, vector);
- entry->msi_attrib.current_cpu = ((address.lo_address.u.dest_id >>
- MSI_TARGET_CPU_SHIFT) & MSI_TARGET_CPU_MASK);
- pci_write_config_dword(dev, msi_lower_address_reg(pos),
- address.lo_address.value);
+ status = msi_ops->setup(dev, vector, &address_hi, &address_lo, &data);
+ if (status < 0)
+ return status;
+
+ pci_write_config_dword(dev, msi_lower_address_reg(pos), address_lo);
if (is_64bit_address(control)) {
pci_write_config_dword(dev,
- msi_upper_address_reg(pos), address.hi_address);
+ msi_upper_address_reg(pos), address_hi);
pci_write_config_word(dev,
- msi_data_reg(pos, 1), *((u32*)&data));
+ msi_data_reg(pos, 1), data);
} else
pci_write_config_word(dev,
- msi_data_reg(pos, 0), *((u32*)&data));
+ msi_data_reg(pos, 0), data);
if (entry->msi_attrib.maskbit) {
unsigned int maskbits, temp;
/* All MSIs are unmasked by default, Mask them all */
msi_mask_bits_reg(pos, is_64bit_address(control)),
maskbits);
}
+
+ return 0;
}
/**
**/
static int msi_capability_init(struct pci_dev *dev)
{
+ int status;
struct msi_desc *entry;
int pos, vector;
u16 control;
/* Replace with MSI handler */
irq_handler_init(PCI_CAP_ID_MSI, vector, entry->msi_attrib.maskbit);
/* Configure MSI capability structure */
- msi_register_init(dev, entry);
+ status = msi_register_init(dev, entry);
+ if (status != 0) {
+ dev->irq = entry->msi_attrib.default_vector;
+ kmem_cache_free(msi_cachep, entry);
+ return status;
+ }
attach_msi_entry(entry, vector);
/* Set MSI enabled bits */
struct msix_entry *entries, int nvec)
{
struct msi_desc *head = NULL, *tail = NULL, *entry = NULL;
- struct msg_address address;
- struct msg_data data;
+ u32 address_hi;
+ u32 address_lo;
+ u32 data;
+ int status;
int vector, pos, i, j, nr_entries, temp = 0;
unsigned long phys_addr;
u32 table_offset;
/* Replace with MSI-X handler */
irq_handler_init(PCI_CAP_ID_MSIX, vector, 1);
/* Configure MSI-X capability structure */
- msi_address_init(&address);
- msi_data_init(&data, vector);
- entry->msi_attrib.current_cpu =
- ((address.lo_address.u.dest_id >>
- MSI_TARGET_CPU_SHIFT) & MSI_TARGET_CPU_MASK);
- writel(address.lo_address.value,
+ status = msi_ops->setup(dev, vector,
+ &address_hi,
+ &address_lo,
+ &data);
+ if (status < 0)
+ break;
+
+ writel(address_lo,
base + j * PCI_MSIX_ENTRY_SIZE +
PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET);
- writel(address.hi_address,
+ writel(address_hi,
base + j * PCI_MSIX_ENTRY_SIZE +
PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET);
- writel(*(u32*)&data,
+ writel(data,
base + j * PCI_MSIX_ENTRY_SIZE +
PCI_MSIX_ENTRY_DATA_OFFSET);
attach_msi_entry(entry, vector);
return 0;
}
+/**
+ * pci_msi_supported - check whether MSI may be enabled on device
+ * @dev: pointer to the pci_dev data structure of MSI device function
+ *
+ * MSI must be globally enabled and supported by the device and its root
+ * bus. But, the root bus is not easy to find since some architectures
+ * have virtual busses on top of the PCI hierarchy (for instance the
+ * hypertransport bus), while the actual bus where MSI must be supported
+ * is below. So we test the MSI flag on all parent busses and assume
+ * that no quirk will ever set the NO_MSI flag on a non-root bus.
+ **/
+static
+int pci_msi_supported(struct pci_dev * dev)
+{
+ struct pci_bus *bus;
+
+ if (!pci_msi_enable || !dev || dev->no_msi)
+ return -EINVAL;
+
+ /* check MSI flags of all parent busses */
+ for (bus = dev->bus; bus; bus = bus->parent)
+ if (bus->bus_flags & PCI_BUS_FLAGS_NO_MSI)
+ return -EINVAL;
+
+ return 0;
+}
+
/**
* pci_enable_msi - configure device's MSI capability structure
* @dev: pointer to the pci_dev data structure of MSI device function
**/
int pci_enable_msi(struct pci_dev* dev)
{
- int pos, temp, status = -EINVAL;
+ int pos, temp, status;
u16 control;
- if (!pci_msi_enable || !dev)
- return status;
-
- if (dev->no_msi)
- return status;
-
- if (dev->bus->bus_flags & PCI_BUS_FLAGS_NO_MSI)
+ if (pci_msi_supported(dev) < 0)
return -EINVAL;
temp = dev->irq;
if (!pos)
return -EINVAL;
- pci_read_config_word(dev, msi_control_reg(pos), &control);
- if (control & PCI_MSI_FLAGS_ENABLE)
- return 0; /* Already in MSI mode */
-
if (!msi_lookup_vector(dev, PCI_CAP_ID_MSI)) {
/* Lookup Sucess */
unsigned long flags;
+ pci_read_config_word(dev, msi_control_reg(pos), &control);
+ if (control & PCI_MSI_FLAGS_ENABLE)
+ return 0; /* Already in MSI mode */
spin_lock_irqsave(&msi_lock, flags);
if (!vector_irq[dev->irq]) {
msi_desc[dev->irq]->msi_attrib.state = 0;
vector_irq[dev->irq] = -1;
nr_released_vectors--;
spin_unlock_irqrestore(&msi_lock, flags);
- msi_register_init(dev, msi_desc[dev->irq]);
- enable_msi_mode(dev, pos, PCI_CAP_ID_MSI);
- return 0;
+ status = msi_register_init(dev, msi_desc[dev->irq]);
+ if (status == 0)
+ enable_msi_mode(dev, pos, PCI_CAP_ID_MSI);
+ return status;
}
spin_unlock_irqrestore(&msi_lock, flags);
dev->irq = temp;
void __iomem *base;
unsigned long flags;
+ msi_ops->teardown(vector);
+
spin_lock_irqsave(&msi_lock, flags);
entry = msi_desc[vector];
if (!entry || entry->dev != dev) {
entry_nr * PCI_MSIX_ENTRY_SIZE +
PCI_MSIX_ENTRY_VECTOR_CTRL_OFFSET);
- if (head == vector) {
- /*
- * Detect last MSI-X vector to be released.
- * Release the MSI-X memory-mapped table.
- */
-#if 0
- int pos, nr_entries;
- unsigned long phys_addr;
- u32 table_offset;
- u16 control;
- u8 bir;
-
- pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
- pci_read_config_word(dev, msi_control_reg(pos),
- &control);
- nr_entries = multi_msix_capable(control);
- pci_read_config_dword(dev, msix_table_offset_reg(pos),
- &table_offset);
- bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK);
- table_offset &= ~PCI_MSIX_FLAGS_BIRMASK;
- phys_addr = pci_resource_start(dev, bir) + table_offset;
-/*
- * FIXME! and what did you want to do with phys_addr?
- */
-#endif
+ if (head == vector)
iounmap(base);
- }
}
return 0;
u16 control;
unsigned long flags;
- if (!pci_msi_enable || !dev || !entries)
+ if (!entries || pci_msi_supported(dev) < 0)
return -EINVAL;
status = msi_init();
}
msi_free_vector(dev, vector, 0);
if (warning) {
- /* Force to release the MSI-X memory-mapped table */
-#if 0
- unsigned long phys_addr;
- u32 table_offset;
- u16 control;
- u8 bir;
-
- pci_read_config_word(dev, msi_control_reg(pos),
- &control);
- pci_read_config_dword(dev, msix_table_offset_reg(pos),
- &table_offset);
- bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK);
- table_offset &= ~PCI_MSIX_FLAGS_BIRMASK;
- phys_addr = pci_resource_start(dev, bir) + table_offset;
-/*
- * FIXME! and what did you want to do with phys_addr?
- */
-#endif
iounmap(base);
printk(KERN_WARNING "PCI: %s: msi_remove_pci_irq_vectors() "
"called without free_irq() on all MSI-X vectors\n",