* Copyright (C) Tom Long Nguyen (tom.l.nguyen@intel.com)
*/
+#include <linux/err.h>
#include <linux/mm.h>
#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 <linux/proc_fs.h>
+#include <linux/msi.h>
#include <asm/errno.h>
#include <asm/io.h>
#include <asm/smp.h>
+#include "pci.h"
#include "msi.h"
-static spinlock_t msi_lock = SPIN_LOCK_UNLOCKED;
+static DEFINE_SPINLOCK(msi_lock);
static struct msi_desc* msi_desc[NR_IRQS] = { [0 ... NR_IRQS-1] = NULL };
-static kmem_cache_t* msi_cachep;
+static struct kmem_cache* msi_cachep;
-static int pci_msi_enable = 1;
-static int last_alloc_vector = 0;
-static int nr_released_vectors = 0;
-static int nr_reserved_vectors = NR_HP_RESERVED_VECTORS;
-static int nr_msix_devices = 0;
-
-#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 void msi_cache_ctor(void *p, kmem_cache_t *cache, unsigned long flags)
-{
- memset(p, 0, NR_IRQS * sizeof(struct msi_desc));
-}
+static int pci_msi_enable = 0;
static int msi_cache_init(void)
{
- msi_cachep = kmem_cache_create("msi_cache",
- NR_IRQS * sizeof(struct msi_desc),
- 0, SLAB_HWCACHE_ALIGN, msi_cache_ctor, NULL);
+ msi_cachep = kmem_cache_create("msi_cache", sizeof(struct msi_desc),
+ 0, SLAB_HWCACHE_ALIGN, NULL, NULL);
if (!msi_cachep)
return -ENOMEM;
return 0;
}
-static void msi_set_mask_bit(unsigned int vector, int flag)
+void msix_flush_writes(unsigned int irq)
{
struct msi_desc *entry;
- entry = (struct msi_desc *)msi_desc[vector];
- if (!entry || !entry->dev || !entry->mask_base)
- return;
+ entry = msi_desc[irq];
+ BUG_ON(!entry || !entry->dev);
switch (entry->msi_attrib.type) {
case PCI_CAP_ID_MSI:
- {
- int pos;
- unsigned int mask_bits;
-
- pos = entry->mask_base;
- entry->dev->bus->ops->read(entry->dev->bus, entry->dev->devfn,
- pos, 4, &mask_bits);
- mask_bits &= ~(1);
- mask_bits |= flag;
- entry->dev->bus->ops->write(entry->dev->bus, entry->dev->devfn,
- pos, 4, mask_bits);
+ /* nothing to do */
break;
- }
case PCI_CAP_ID_MSIX:
{
int offset = entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
PCI_MSIX_ENTRY_VECTOR_CTRL_OFFSET;
- writel(flag, entry->mask_base + offset);
+ readl(entry->mask_base + offset);
break;
}
default:
+ BUG();
break;
}
}
-#ifdef CONFIG_SMP
-static void set_msi_affinity(unsigned int vector, cpumask_t cpu_mask)
+static void msi_set_mask_bit(unsigned int irq, int flag)
{
struct msi_desc *entry;
- struct msg_address address;
-
- entry = (struct msi_desc *)msi_desc[vector];
- if (!entry || !entry->dev)
- return;
+ entry = msi_desc[irq];
+ BUG_ON(!entry || !entry->dev);
switch (entry->msi_attrib.type) {
case PCI_CAP_ID_MSI:
- {
- int pos;
-
- if (!(pos = pci_find_capability(entry->dev, PCI_CAP_ID_MSI)))
- return;
-
- entry->dev->bus->ops->read(entry->dev->bus, entry->dev->devfn,
- msi_lower_address_reg(pos), 4,
- &address.lo_address.value);
- address.lo_address.value &= MSI_ADDRESS_DEST_ID_MASK;
- address.lo_address.value |= (cpu_mask_to_apicid(cpu_mask) <<
- MSI_TARGET_CPU_SHIFT);
- entry->msi_attrib.current_cpu = cpu_mask_to_apicid(cpu_mask);
- entry->dev->bus->ops->write(entry->dev->bus, entry->dev->devfn,
- msi_lower_address_reg(pos), 4,
- address.lo_address.value);
+ if (entry->msi_attrib.maskbit) {
+ int pos;
+ u32 mask_bits;
+
+ pos = (long)entry->mask_base;
+ pci_read_config_dword(entry->dev, pos, &mask_bits);
+ mask_bits &= ~(1);
+ mask_bits |= flag;
+ pci_write_config_dword(entry->dev, pos, mask_bits);
+ }
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_mask_to_apicid(cpu_mask) <<
- MSI_TARGET_CPU_SHIFT);
- entry->msi_attrib.current_cpu = cpu_mask_to_apicid(cpu_mask);
- writel(address.lo_address.value, entry->mask_base + offset);
+ PCI_MSIX_ENTRY_VECTOR_CTRL_OFFSET;
+ writel(flag, entry->mask_base + offset);
break;
}
default:
+ BUG();
break;
}
}
-#ifdef CONFIG_IRQBALANCE
-static inline void move_msi(int vector)
+void read_msi_msg(unsigned int irq, struct msi_msg *msg)
{
- if (!cpus_empty(pending_irq_balance_cpumask[vector])) {
- set_msi_affinity(vector, pending_irq_balance_cpumask[vector]);
- cpus_clear(pending_irq_balance_cpumask[vector]);
+ struct msi_desc *entry = get_irq_data(irq);
+ switch(entry->msi_attrib.type) {
+ case PCI_CAP_ID_MSI:
+ {
+ struct pci_dev *dev = entry->dev;
+ int pos = entry->msi_attrib.pos;
+ u16 data;
+
+ pci_read_config_dword(dev, msi_lower_address_reg(pos),
+ &msg->address_lo);
+ if (entry->msi_attrib.is_64) {
+ pci_read_config_dword(dev, msi_upper_address_reg(pos),
+ &msg->address_hi);
+ pci_read_config_word(dev, msi_data_reg(pos, 1), &data);
+ } else {
+ msg->address_hi = 0;
+ pci_read_config_word(dev, msi_data_reg(pos, 1), &data);
+ }
+ msg->data = data;
+ break;
}
-}
-#endif /* CONFIG_IRQBALANCE */
-#endif /* CONFIG_SMP */
-
-static void mask_MSI_irq(unsigned int vector)
-{
- msi_set_mask_bit(vector, 1);
-}
-
-static void unmask_MSI_irq(unsigned int vector)
-{
- msi_set_mask_bit(vector, 0);
-}
-
-static unsigned int startup_msi_irq_wo_maskbit(unsigned int vector)
-{
- return 0; /* never anything pending */
-}
-
-static void pci_disable_msi(unsigned int vector);
-static void shutdown_msi_irq(unsigned int vector)
-{
- pci_disable_msi(vector);
-}
-
-#define shutdown_msi_irq_wo_maskbit shutdown_msi_irq
-static void enable_msi_irq_wo_maskbit(unsigned int vector) {}
-static void disable_msi_irq_wo_maskbit(unsigned int vector) {}
-static void ack_msi_irq_wo_maskbit(unsigned int vector) {}
-static void end_msi_irq_wo_maskbit(unsigned int vector)
-{
- move_msi(vector);
- ack_APIC_irq();
-}
+ case PCI_CAP_ID_MSIX:
+ {
+ void __iomem *base;
+ base = entry->mask_base +
+ entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;
-static unsigned int startup_msi_irq_w_maskbit(unsigned int vector)
-{
- unmask_MSI_irq(vector);
- return 0; /* never anything pending */
+ msg->address_lo = readl(base + PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET);
+ msg->address_hi = readl(base + PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET);
+ msg->data = readl(base + PCI_MSIX_ENTRY_DATA_OFFSET);
+ break;
+ }
+ default:
+ BUG();
+ }
}
-#define shutdown_msi_irq_w_maskbit shutdown_msi_irq
-#define enable_msi_irq_w_maskbit unmask_MSI_irq
-#define disable_msi_irq_w_maskbit mask_MSI_irq
-#define ack_msi_irq_w_maskbit mask_MSI_irq
-
-static void end_msi_irq_w_maskbit(unsigned int vector)
+void write_msi_msg(unsigned int irq, struct msi_msg *msg)
{
- move_msi(vector);
- unmask_MSI_irq(vector);
- ack_APIC_irq();
+ struct msi_desc *entry = get_irq_data(irq);
+ switch (entry->msi_attrib.type) {
+ case PCI_CAP_ID_MSI:
+ {
+ struct pci_dev *dev = entry->dev;
+ int pos = entry->msi_attrib.pos;
+
+ pci_write_config_dword(dev, msi_lower_address_reg(pos),
+ msg->address_lo);
+ if (entry->msi_attrib.is_64) {
+ pci_write_config_dword(dev, msi_upper_address_reg(pos),
+ msg->address_hi);
+ pci_write_config_word(dev, msi_data_reg(pos, 1),
+ msg->data);
+ } else {
+ pci_write_config_word(dev, msi_data_reg(pos, 0),
+ msg->data);
+ }
+ break;
+ }
+ case PCI_CAP_ID_MSIX:
+ {
+ void __iomem *base;
+ base = entry->mask_base +
+ entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;
+
+ writel(msg->address_lo,
+ base + PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET);
+ writel(msg->address_hi,
+ base + PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET);
+ writel(msg->data, base + PCI_MSIX_ENTRY_DATA_OFFSET);
+ break;
+ }
+ default:
+ BUG();
+ }
}
-/*
- * Interrupt Type for MSI-X PCI/PCI-X/PCI-Express Devices,
- * which implement the MSI-X Capability Structure.
- */
-static struct hw_interrupt_type msix_irq_type = {
- .typename = "PCI MSI-X",
- .startup = startup_msi_irq_w_maskbit,
- .shutdown = shutdown_msi_irq_w_maskbit,
- .enable = enable_msi_irq_w_maskbit,
- .disable = disable_msi_irq_w_maskbit,
- .ack = ack_msi_irq_w_maskbit,
- .end = end_msi_irq_w_maskbit,
- .set_affinity = set_msi_irq_affinity
-};
-
-/*
- * Interrupt Type for MSI PCI/PCI-X/PCI-Express Devices,
- * which implement the MSI Capability Structure with
- * Mask-and-Pending Bits.
- */
-static struct hw_interrupt_type msi_irq_w_maskbit_type = {
- .typename = "PCI MSI",
- .startup = startup_msi_irq_w_maskbit,
- .shutdown = shutdown_msi_irq_w_maskbit,
- .enable = enable_msi_irq_w_maskbit,
- .disable = disable_msi_irq_w_maskbit,
- .ack = ack_msi_irq_w_maskbit,
- .end = end_msi_irq_w_maskbit,
- .set_affinity = set_msi_irq_affinity
-};
-
-/*
- * Interrupt Type for MSI PCI/PCI-X/PCI-Express Devices,
- * which implement the MSI Capability Structure without
- * Mask-and-Pending Bits.
- */
-static struct hw_interrupt_type msi_irq_wo_maskbit_type = {
- .typename = "PCI MSI",
- .startup = startup_msi_irq_wo_maskbit,
- .shutdown = shutdown_msi_irq_wo_maskbit,
- .enable = enable_msi_irq_wo_maskbit,
- .disable = disable_msi_irq_wo_maskbit,
- .ack = ack_msi_irq_wo_maskbit,
- .end = end_msi_irq_wo_maskbit,
- .set_affinity = set_msi_irq_affinity
-};
-
-static void msi_data_init(struct msg_data *msi_data,
- unsigned int vector)
+void mask_msi_irq(unsigned int irq)
{
- 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;
+ msi_set_mask_bit(irq, 1);
}
-static void msi_address_init(struct msg_address *msi_address)
+void unmask_msi_irq(unsigned int irq)
{
- unsigned int dest_id;
-
- 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_DEST_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 |= (MSI_TARGET_CPU << MSI_TARGET_CPU_SHIFT);
+ msi_set_mask_bit(irq, 0);
}
-static int assign_msi_vector(void)
+void disable_msi_irq(unsigned int irq)
{
- static int new_vector_avail = 1;
- int vector;
- unsigned long flags;
-
- /*
- * msi_lock is provided to ensure that successful allocation of MSI
- * vector is assigned unique among drivers.
- */
- spin_lock_irqsave(&msi_lock, flags);
-
- if (!new_vector_avail) {
- /*
- * vector_irq[] = -1 indicates that this specific vector is:
- * - assigned for MSI (since MSI have no associated IRQ) or
- * - assigned for legacy if less than 16, or
- * - having no corresponding 1:1 vector-to-IOxAPIC IRQ mapping
- * vector_irq[] = 0 indicates that this vector, previously
- * assigned for MSI, is freed by hotplug removed operations.
- * This vector will be reused for any subsequent hotplug added
- * operations.
- * vector_irq[] > 0 indicates that this vector is assigned for
- * IOxAPIC IRQs. This vector and its value provides a 1-to-1
- * vector-to-IOxAPIC IRQ mapping.
- */
- for (vector = FIRST_DEVICE_VECTOR; vector < NR_IRQS; vector++) {
- if (vector_irq[vector] != 0)
- continue;
- vector_irq[vector] = -1;
- nr_released_vectors--;
- spin_unlock_irqrestore(&msi_lock, flags);
- return vector;
- }
- spin_unlock_irqrestore(&msi_lock, flags);
- return -EBUSY;
- }
- vector = assign_irq_vector(AUTO_ASSIGN);
- last_alloc_vector = vector;
- if (vector == LAST_DEVICE_VECTOR)
- new_vector_avail = 0;
-
- spin_unlock_irqrestore(&msi_lock, flags);
- return vector;
+ msi_set_mask_bit(irq, 1);
+ msix_flush_writes(irq);
}
-static int get_new_vector(void)
+void enable_msi_irq(unsigned int irq)
{
- int vector;
-
- if ((vector = assign_msi_vector()) > 0)
- set_intr_gate(vector, interrupt[vector]);
-
- return vector;
+ msi_set_mask_bit(irq, 0);
+ msix_flush_writes(irq);
}
-
+static int msi_free_irq(struct pci_dev* dev, int irq);
static int msi_init(void)
{
static int status = -ENOMEM;
if (!status)
return status;
- if ((status = msi_cache_init()) < 0) {
+ if (pci_msi_quirk) {
pci_msi_enable = 0;
- printk(KERN_INFO "WARNING: MSI INIT FAILURE\n");
+ printk(KERN_WARNING "PCI: MSI quirk detected. MSI disabled.\n");
+ status = -EINVAL;
return status;
}
- printk(KERN_INFO "MSI INIT SUCCESS\n");
- return status;
-}
+ status = msi_cache_init();
+ if (status < 0) {
+ pci_msi_enable = 0;
+ printk(KERN_WARNING "PCI: MSI cache init failed\n");
+ return status;
+ }
-static int get_msi_vector(struct pci_dev *dev)
-{
- return get_new_vector();
+ return status;
}
static struct msi_desc* alloc_msi_entry(void)
{
struct msi_desc *entry;
- entry = (struct msi_desc*) kmem_cache_alloc(msi_cachep, SLAB_KERNEL);
+ entry = kmem_cache_zalloc(msi_cachep, GFP_KERNEL);
if (!entry)
return NULL;
- memset(entry, 0, sizeof(struct msi_desc));
entry->link.tail = entry->link.head = 0; /* single message */
entry->dev = NULL;
return entry;
}
-static void attach_msi_entry(struct msi_desc *entry, int vector)
+static void attach_msi_entry(struct msi_desc *entry, int irq)
{
unsigned long flags;
spin_lock_irqsave(&msi_lock, flags);
- msi_desc[vector] = entry;
+ msi_desc[irq] = entry;
spin_unlock_irqrestore(&msi_lock, flags);
}
-static void irq_handler_init(int cap_id, int pos, int mask)
+static int create_msi_irq(void)
{
- spin_lock(&irq_desc[pos].lock);
- if (cap_id == PCI_CAP_ID_MSIX)
- irq_desc[pos].handler = &msix_irq_type;
- else {
- if (!mask)
- irq_desc[pos].handler = &msi_irq_wo_maskbit_type;
- else
- irq_desc[pos].handler = &msi_irq_w_maskbit_type;
+ struct msi_desc *entry;
+ int irq;
+
+ entry = alloc_msi_entry();
+ if (!entry)
+ return -ENOMEM;
+
+ irq = create_irq();
+ if (irq < 0) {
+ kmem_cache_free(msi_cachep, entry);
+ return -EBUSY;
}
- spin_unlock(&irq_desc[pos].lock);
+
+ set_irq_data(irq, entry);
+
+ return irq;
+}
+
+static void destroy_msi_irq(unsigned int irq)
+{
+ struct msi_desc *entry;
+
+ entry = get_irq_data(irq);
+ set_irq_chip(irq, NULL);
+ set_irq_data(irq, NULL);
+ destroy_irq(irq);
+ kmem_cache_free(msi_cachep, entry);
}
static void enable_msi_mode(struct pci_dev *dev, int pos, int type)
{
- u32 control;
+ u16 control;
- dev->bus->ops->read(dev->bus, dev->devfn,
- msi_control_reg(pos), 2, &control);
+ pci_read_config_word(dev, msi_control_reg(pos), &control);
if (type == PCI_CAP_ID_MSI) {
/* Set enabled bits to single MSI & enable MSI_enable bit */
msi_enable(control, 1);
- dev->bus->ops->write(dev->bus, dev->devfn,
- msi_control_reg(pos), 2, control);
+ pci_write_config_word(dev, msi_control_reg(pos), control);
+ dev->msi_enabled = 1;
} else {
msix_enable(control);
- dev->bus->ops->write(dev->bus, dev->devfn,
- msi_control_reg(pos), 2, control);
- }
- if (pci_find_capability(dev, PCI_CAP_ID_EXP)) {
- /* PCI Express Endpoint device detected */
- u32 cmd;
- dev->bus->ops->read(dev->bus, dev->devfn, PCI_COMMAND, 2, &cmd);
- cmd |= PCI_COMMAND_INTX_DISABLE;
- dev->bus->ops->write(dev->bus, dev->devfn, PCI_COMMAND, 2, cmd);
+ pci_write_config_word(dev, msi_control_reg(pos), control);
+ dev->msix_enabled = 1;
}
+
+ pci_intx(dev, 0); /* disable intx */
}
-static void disable_msi_mode(struct pci_dev *dev, int pos, int type)
+void disable_msi_mode(struct pci_dev *dev, int pos, int type)
{
- u32 control;
+ u16 control;
- dev->bus->ops->read(dev->bus, dev->devfn,
- msi_control_reg(pos), 2, &control);
+ pci_read_config_word(dev, msi_control_reg(pos), &control);
if (type == PCI_CAP_ID_MSI) {
/* Set enabled bits to single MSI & enable MSI_enable bit */
msi_disable(control);
- dev->bus->ops->write(dev->bus, dev->devfn,
- msi_control_reg(pos), 2, control);
+ pci_write_config_word(dev, msi_control_reg(pos), control);
+ dev->msi_enabled = 0;
} else {
msix_disable(control);
- dev->bus->ops->write(dev->bus, dev->devfn,
- msi_control_reg(pos), 2, control);
- }
- if (pci_find_capability(dev, PCI_CAP_ID_EXP)) {
- /* PCI Express Endpoint device detected */
- u32 cmd;
- dev->bus->ops->read(dev->bus, dev->devfn, PCI_COMMAND, 2, &cmd);
- cmd &= ~PCI_COMMAND_INTX_DISABLE;
- dev->bus->ops->write(dev->bus, dev->devfn, PCI_COMMAND, 2, cmd);
+ pci_write_config_word(dev, msi_control_reg(pos), control);
+ dev->msix_enabled = 0;
}
+
+ pci_intx(dev, 1); /* enable intx */
}
-static int msi_lookup_vector(struct pci_dev *dev)
+static int msi_lookup_irq(struct pci_dev *dev, int type)
{
- int vector;
+ int irq;
unsigned long flags;
spin_lock_irqsave(&msi_lock, flags);
- for (vector = FIRST_DEVICE_VECTOR; vector < NR_IRQS; vector++) {
- if (!msi_desc[vector] || msi_desc[vector]->dev != dev ||
- msi_desc[vector]->msi_attrib.entry_nr ||
- msi_desc[vector]->msi_attrib.default_vector != dev->irq)
- continue; /* not entry 0, skip */
+ for (irq = 0; irq < NR_IRQS; irq++) {
+ if (!msi_desc[irq] || msi_desc[irq]->dev != dev ||
+ msi_desc[irq]->msi_attrib.type != type ||
+ msi_desc[irq]->msi_attrib.default_irq != dev->irq)
+ continue;
spin_unlock_irqrestore(&msi_lock, flags);
- /* This pre-assigned entry-0 MSI vector for this device
- already exits. Override dev->irq with this vector */
- dev->irq = vector;
+ /* This pre-assigned MSI irq for this device
+ already exits. Override dev->irq with this irq */
+ dev->irq = irq;
return 0;
}
spin_unlock_irqrestore(&msi_lock, flags);
{
if (!dev)
return;
+}
+
+#ifdef CONFIG_PM
+int pci_save_msi_state(struct pci_dev *dev)
+{
+ int pos, i = 0;
+ u16 control;
+ struct pci_cap_saved_state *save_state;
+ u32 *cap;
+
+ pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
+ if (pos <= 0 || dev->no_msi)
+ return 0;
+
+ pci_read_config_word(dev, msi_control_reg(pos), &control);
+ if (!(control & PCI_MSI_FLAGS_ENABLE))
+ return 0;
+
+ save_state = kzalloc(sizeof(struct pci_cap_saved_state) + sizeof(u32) * 5,
+ GFP_KERNEL);
+ if (!save_state) {
+ printk(KERN_ERR "Out of memory in pci_save_msi_state\n");
+ return -ENOMEM;
+ }
+ cap = &save_state->data[0];
+
+ pci_read_config_dword(dev, pos, &cap[i++]);
+ control = cap[0] >> 16;
+ pci_read_config_dword(dev, pos + PCI_MSI_ADDRESS_LO, &cap[i++]);
+ if (control & PCI_MSI_FLAGS_64BIT) {
+ pci_read_config_dword(dev, pos + PCI_MSI_ADDRESS_HI, &cap[i++]);
+ pci_read_config_dword(dev, pos + PCI_MSI_DATA_64, &cap[i++]);
+ } else
+ 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++]);
+ save_state->cap_nr = PCI_CAP_ID_MSI;
+ pci_add_saved_cap(dev, save_state);
+ return 0;
+}
+
+void pci_restore_msi_state(struct pci_dev *dev)
+{
+ int i = 0, pos;
+ u16 control;
+ struct pci_cap_saved_state *save_state;
+ u32 *cap;
+
+ save_state = pci_find_saved_cap(dev, PCI_CAP_ID_MSI);
+ pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
+ if (!save_state || pos <= 0)
+ return;
+ cap = &save_state->data[0];
+
+ control = cap[i++] >> 16;
+ pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_LO, cap[i++]);
+ if (control & PCI_MSI_FLAGS_64BIT) {
+ pci_write_config_dword(dev, pos + PCI_MSI_ADDRESS_HI, cap[i++]);
+ pci_write_config_dword(dev, pos + PCI_MSI_DATA_64, cap[i++]);
+ } else
+ pci_write_config_dword(dev, pos + PCI_MSI_DATA_32, cap[i++]);
+ if (control & PCI_MSI_FLAGS_MASKBIT)
+ pci_write_config_dword(dev, pos + PCI_MSI_MASK_BIT, cap[i++]);
+ pci_write_config_word(dev, pos + PCI_MSI_FLAGS, control);
+ enable_msi_mode(dev, pos, PCI_CAP_ID_MSI);
+ pci_remove_saved_cap(save_state);
+ kfree(save_state);
+}
+
+int pci_save_msix_state(struct pci_dev *dev)
+{
+ int pos;
+ int temp;
+ int irq, head, tail = 0;
+ u16 control;
+ struct pci_cap_saved_state *save_state;
+
+ pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+ 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;
+ save_state = kzalloc(sizeof(struct pci_cap_saved_state) + sizeof(u16),
+ GFP_KERNEL);
+ if (!save_state) {
+ printk(KERN_ERR "Out of memory in pci_save_msix_state\n");
+ return -ENOMEM;
+ }
+ *((u16 *)&save_state->data[0]) = control;
+
+ /* save the table */
+ temp = dev->irq;
+ if (msi_lookup_irq(dev, PCI_CAP_ID_MSIX)) {
+ kfree(save_state);
+ return -EINVAL;
+ }
+
+ irq = head = dev->irq;
+ while (head != tail) {
+ struct msi_desc *entry;
+
+ entry = msi_desc[irq];
+ read_msi_msg(irq, &entry->msg_save);
+
+ tail = msi_desc[irq]->link.tail;
+ irq = tail;
+ }
+ dev->irq = temp;
+
+ save_state->cap_nr = PCI_CAP_ID_MSIX;
+ pci_add_saved_cap(dev, save_state);
+ return 0;
+}
+
+void pci_restore_msix_state(struct pci_dev *dev)
+{
+ u16 save;
+ int pos;
+ int irq, head, tail = 0;
+ struct msi_desc *entry;
+ int temp;
+ struct pci_cap_saved_state *save_state;
+
+ save_state = pci_find_saved_cap(dev, PCI_CAP_ID_MSIX);
+ if (!save_state)
+ return;
+ save = *((u16 *)&save_state->data[0]);
+ pci_remove_saved_cap(save_state);
+ kfree(save_state);
+
+ pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+ if (pos <= 0)
+ return;
- if (pci_find_capability(dev, PCI_CAP_ID_MSIX) > 0) {
- nr_reserved_vectors++;
- nr_msix_devices++;
- } else if (pci_find_capability(dev, PCI_CAP_ID_MSI) > 0)
- nr_reserved_vectors++;
+ /* route the table */
+ temp = dev->irq;
+ if (msi_lookup_irq(dev, PCI_CAP_ID_MSIX))
+ return;
+ irq = head = dev->irq;
+ while (head != tail) {
+ entry = msi_desc[irq];
+ write_msi_msg(irq, &entry->msg_save);
+
+ tail = msi_desc[irq]->link.tail;
+ irq = tail;
+ }
+ dev->irq = temp;
+
+ pci_write_config_word(dev, msi_control_reg(pos), save);
+ enable_msi_mode(dev, pos, PCI_CAP_ID_MSIX);
}
+#endif
/**
* msi_capability_init - configure device's MSI capability structure
* @dev: pointer to the pci_dev data structure of MSI device function
*
- * Setup the MSI capability structure of device funtion with a single
- * MSI vector, regardless of device function is capable of handling
+ * Setup the MSI capability structure of device function with a single
+ * MSI irq, regardless of device function is capable of handling
* multiple messages. A return of zero indicates the successful setup
- * of an entry zero with the new MSI vector or non-zero for otherwise.
+ * of an entry zero with the new MSI irq or non-zero for otherwise.
**/
static int msi_capability_init(struct pci_dev *dev)
{
+ int status;
struct msi_desc *entry;
- struct msg_address address;
- struct msg_data data;
- int pos, vector;
- u32 control;
+ int pos, irq;
+ u16 control;
pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
- if (!pos)
- return -EINVAL;
-
- dev->bus->ops->read(dev->bus, dev->devfn, msi_control_reg(pos),
- 2, &control);
- if (control & PCI_MSI_FLAGS_ENABLE)
- return 0;
-
- if (!msi_lookup_vector(dev)) {
- /* Lookup Sucess */
- enable_msi_mode(dev, pos, PCI_CAP_ID_MSI);
- return 0;
- }
+ pci_read_config_word(dev, msi_control_reg(pos), &control);
/* MSI Entry Initialization */
- if (!(entry = alloc_msi_entry()))
- return -ENOMEM;
+ irq = create_msi_irq();
+ if (irq < 0)
+ return irq;
- if ((vector = get_msi_vector(dev)) < 0) {
- kmem_cache_free(msi_cachep, entry);
- return -EBUSY;
- }
+ entry = get_irq_data(irq);
+ entry->link.head = irq;
+ entry->link.tail = irq;
entry->msi_attrib.type = PCI_CAP_ID_MSI;
+ entry->msi_attrib.is_64 = is_64bit_address(control);
entry->msi_attrib.entry_nr = 0;
entry->msi_attrib.maskbit = is_mask_bit_support(control);
- entry->msi_attrib.default_vector = dev->irq;
- dev->irq = vector; /* save default pre-assigned ioapic vector */
- entry->dev = dev;
+ entry->msi_attrib.default_irq = dev->irq; /* Save IOAPIC IRQ */
+ entry->msi_attrib.pos = pos;
if (is_mask_bit_support(control)) {
- entry->mask_base = msi_mask_bits_reg(pos,
+ entry->mask_base = (void __iomem *)(long)msi_mask_bits_reg(pos,
is_64bit_address(control));
}
- /* Replace with MSI handler */
- irq_handler_init(PCI_CAP_ID_MSI, vector, entry->msi_attrib.maskbit);
- /* 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);
- dev->bus->ops->write(dev->bus, dev->devfn, msi_lower_address_reg(pos),
- 4, address.lo_address.value);
- if (is_64bit_address(control)) {
- dev->bus->ops->write(dev->bus, dev->devfn,
- msi_upper_address_reg(pos), 4, address.hi_address);
- dev->bus->ops->write(dev->bus, dev->devfn,
- msi_data_reg(pos, 1), 2, *((u32*)&data));
- } else
- dev->bus->ops->write(dev->bus, dev->devfn,
- msi_data_reg(pos, 0), 2, *((u32*)&data));
+ entry->dev = dev;
if (entry->msi_attrib.maskbit) {
unsigned int maskbits, temp;
/* All MSIs are unmasked by default, Mask them all */
- dev->bus->ops->read(dev->bus, dev->devfn,
- msi_mask_bits_reg(pos, is_64bit_address(control)), 4,
+ pci_read_config_dword(dev,
+ msi_mask_bits_reg(pos, is_64bit_address(control)),
&maskbits);
temp = (1 << multi_msi_capable(control));
temp = ((temp - 1) & ~temp);
maskbits |= temp;
- dev->bus->ops->write(dev->bus, dev->devfn,
- msi_mask_bits_reg(pos, is_64bit_address(control)), 4,
+ pci_write_config_dword(dev,
+ msi_mask_bits_reg(pos, is_64bit_address(control)),
maskbits);
}
- attach_msi_entry(entry, vector);
+ /* Configure MSI capability structure */
+ status = arch_setup_msi_irq(irq, dev);
+ if (status < 0) {
+ destroy_msi_irq(irq);
+ return status;
+ }
+
+ attach_msi_entry(entry, irq);
/* Set MSI enabled bits */
enable_msi_mode(dev, pos, PCI_CAP_ID_MSI);
+ dev->irq = irq;
return 0;
}
/**
* 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 funtion with a
- * single MSI-X vector. A return of zero indicates the successful setup
- * of an entry zero with the new MSI-X vector or non-zero for otherwise.
- * To request for additional MSI-X vectors, the device drivers are
- * required to utilize the following supported APIs:
- * 1) msi_alloc_vectors(...) for requesting one or more MSI-X vectors
- * 2) msi_free_vectors(...) for releasing one or more MSI-X vectors
- * back to PCI subsystem before calling free_irq(...)
+ * 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 pci_dev *dev)
-{
- struct msi_desc *entry;
- struct msg_address address;
- struct msg_data data;
- int vector = 0, pos, dev_msi_cap;
- u32 phys_addr, table_offset;
- u32 control;
+static int msix_capability_init(struct pci_dev *dev,
+ struct msix_entry *entries, int nvec)
+{
+ struct msi_desc *head = NULL, *tail = NULL, *entry = NULL;
+ int status;
+ int irq, pos, i, j, nr_entries, temp = 0;
+ unsigned long phys_addr;
+ u32 table_offset;
+ u16 control;
u8 bir;
- void *base;
+ void __iomem *base;
pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
- if (!pos)
- return -EINVAL;
-
/* Request & Map MSI-X table region */
- dev->bus->ops->read(dev->bus, dev->devfn, msi_control_reg(pos), 2,
- &control);
- if (control & PCI_MSIX_FLAGS_ENABLE)
- return 0;
+ pci_read_config_word(dev, msi_control_reg(pos), &control);
+ nr_entries = multi_msix_capable(control);
- if (!msi_lookup_vector(dev)) {
- /* Lookup Sucess */
- enable_msi_mode(dev, pos, PCI_CAP_ID_MSIX);
- return 0;
- }
-
- dev_msi_cap = multi_msix_capable(control);
- dev->bus->ops->read(dev->bus, dev->devfn,
- msix_table_offset_reg(pos), 4, &table_offset);
+ pci_read_config_dword(dev, msix_table_offset_reg(pos), &table_offset);
bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK);
- phys_addr = pci_resource_start (dev, bir);
- phys_addr += (u32)(table_offset & ~PCI_MSIX_FLAGS_BIRMASK);
- if (!request_mem_region(phys_addr,
- dev_msi_cap * PCI_MSIX_ENTRY_SIZE,
- "MSI-X iomap Failure"))
- return -ENOMEM;
- base = ioremap_nocache(phys_addr, dev_msi_cap * PCI_MSIX_ENTRY_SIZE);
+ table_offset &= ~PCI_MSIX_FLAGS_BIRMASK;
+ phys_addr = pci_resource_start (dev, bir) + table_offset;
+ base = ioremap_nocache(phys_addr, nr_entries * PCI_MSIX_ENTRY_SIZE);
if (base == NULL)
- goto free_region;
- /* MSI Entry Initialization */
- entry = alloc_msi_entry();
- if (!entry)
- goto free_iomap;
- if ((vector = get_msi_vector(dev)) < 0)
- goto free_entry;
+ return -ENOMEM;
- entry->msi_attrib.type = PCI_CAP_ID_MSIX;
- entry->msi_attrib.entry_nr = 0;
- entry->msi_attrib.maskbit = 1;
- entry->msi_attrib.default_vector = dev->irq;
- dev->irq = vector; /* save default pre-assigned ioapic vector */
- entry->dev = dev;
- entry->mask_base = (unsigned long)base;
- /* Replace with MSI 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, base + PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET);
- writel(address.hi_address, base + PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET);
- writel(*(u32*)&data, base + PCI_MSIX_ENTRY_DATA_OFFSET);
- /* Initialize all entries from 1 up to 0 */
- for (pos = 1; pos < dev_msi_cap; pos++) {
- writel(0, base + pos * PCI_MSIX_ENTRY_SIZE +
- PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET);
- writel(0, base + pos * PCI_MSIX_ENTRY_SIZE +
- PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET);
- writel(0, base + pos * PCI_MSIX_ENTRY_SIZE +
- PCI_MSIX_ENTRY_DATA_OFFSET);
- }
- attach_msi_entry(entry, vector);
- /* Set MSI enabled bits */
+ /* MSI-X Table Initialization */
+ for (i = 0; i < nvec; i++) {
+ irq = create_msi_irq();
+ if (irq < 0)
+ break;
+
+ entry = get_irq_data(irq);
+ j = entries[i].entry;
+ entries[i].vector = irq;
+ entry->msi_attrib.type = PCI_CAP_ID_MSIX;
+ entry->msi_attrib.is_64 = 1;
+ entry->msi_attrib.entry_nr = j;
+ entry->msi_attrib.maskbit = 1;
+ entry->msi_attrib.default_irq = dev->irq;
+ entry->msi_attrib.pos = pos;
+ entry->dev = dev;
+ entry->mask_base = base;
+ if (!head) {
+ entry->link.head = irq;
+ entry->link.tail = irq;
+ head = entry;
+ } else {
+ entry->link.head = temp;
+ entry->link.tail = tail->link.tail;
+ tail->link.tail = irq;
+ head->link.head = irq;
+ }
+ temp = irq;
+ tail = entry;
+ /* Configure MSI-X capability structure */
+ status = arch_setup_msi_irq(irq, dev);
+ if (status < 0) {
+ destroy_msi_irq(irq);
+ break;
+ }
+
+ attach_msi_entry(entry, irq);
+ }
+ if (i != nvec) {
+ int avail = i - 1;
+ i--;
+ for (; i >= 0; i--) {
+ irq = (entries + i)->vector;
+ msi_free_irq(dev, irq);
+ (entries + i)->vector = 0;
+ }
+ /* If we had some success report the number of irqs
+ * we succeeded in setting up.
+ */
+ if (avail <= 0)
+ avail = -EBUSY;
+ return avail;
+ }
+ /* Set MSI-X enabled bits */
enable_msi_mode(dev, pos, PCI_CAP_ID_MSIX);
return 0;
+}
-free_entry:
- kmem_cache_free(msi_cachep, entry);
-free_iomap:
- iounmap(base);
-free_region:
- release_mem_region(phys_addr, dev_msi_cap * PCI_MSIX_ENTRY_SIZE);
+/**
+ * pci_msi_supported - check whether MSI may be enabled on device
+ * @dev: pointer to the pci_dev data structure of MSI device function
+ *
+ * Look at global flags, the device itself, and its parent busses
+ * to return 0 if MSI are supported for the device.
+ **/
+static
+int pci_msi_supported(struct pci_dev * dev)
+{
+ struct pci_bus *bus;
- return ((vector < 0) ? -EBUSY : -ENOMEM);
+ /* MSI must be globally enabled and supported by the device */
+ if (!pci_msi_enable || !dev || dev->no_msi)
+ return -EINVAL;
+
+ /* Any bridge which does NOT route MSI transactions from it's
+ * secondary bus to it's primary bus must set NO_MSI flag on
+ * the secondary pci_bus.
+ * We expect only arch-specific PCI host bus controller driver
+ * or quirks for specific PCI bridges to be setting NO_MSI.
+ */
+ 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(X) capability structure
- * @dev: pointer to the pci_dev data structure of MSI(X) device function
+ * pci_enable_msi - configure device's MSI capability structure
+ * @dev: pointer to the pci_dev data structure of MSI device function
*
- * Setup the MSI/MSI-X capability structure of device function with
- * a single MSI(X) vector upon its software driver call to request for
- * MSI(X) mode enabled on its hardware device function. A return of zero
- * indicates the successful setup of an entry zero with the new MSI(X)
- * vector or non-zero for otherwise.
+ * Setup the MSI capability structure of device function with
+ * a single MSI irq upon its software driver call to request for
+ * MSI mode enabled on its hardware device function. A return of zero
+ * indicates the successful setup of an entry zero with the new MSI
+ * irq or non-zero for otherwise.
**/
int pci_enable_msi(struct pci_dev* dev)
{
- int status = -EINVAL;
+ int pos, temp, status;
- if (!pci_msi_enable || !dev)
- return status;
+ if (pci_msi_supported(dev) < 0)
+ return -EINVAL;
- if (msi_init() < 0)
- return -ENOMEM;
+ temp = dev->irq;
- if ((status = msix_capability_init(dev)) == -EINVAL)
- status = msi_capability_init(dev);
- if (!status)
- nr_reserved_vectors--;
+ status = msi_init();
+ if (status < 0)
+ return status;
+
+ pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
+ if (!pos)
+ return -EINVAL;
+
+ WARN_ON(!msi_lookup_irq(dev, PCI_CAP_ID_MSI));
+ /* Check whether driver already requested for MSI-X irqs */
+ pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+ if (pos > 0 && !msi_lookup_irq(dev, PCI_CAP_ID_MSIX)) {
+ printk(KERN_INFO "PCI: %s: Can't enable MSI. "
+ "Device already has MSI-X irq assigned\n",
+ pci_name(dev));
+ dev->irq = temp;
+ return -EINVAL;
+ }
+ status = msi_capability_init(dev);
return status;
}
-static int msi_free_vector(struct pci_dev* dev, int vector);
-static void pci_disable_msi(unsigned int vector)
+void pci_disable_msi(struct pci_dev* dev)
{
- int head, tail, type, default_vector;
struct msi_desc *entry;
- struct pci_dev *dev;
+ int pos, default_irq;
+ u16 control;
unsigned long flags;
- spin_lock_irqsave(&msi_lock, flags);
- entry = msi_desc[vector];
- if (!entry || !entry->dev) {
- spin_unlock_irqrestore(&msi_lock, flags);
+ if (!pci_msi_enable)
+ return;
+ if (!dev)
return;
- }
- dev = entry->dev;
- type = entry->msi_attrib.type;
- head = entry->link.head;
- tail = entry->link.tail;
- default_vector = entry->msi_attrib.default_vector;
- spin_unlock_irqrestore(&msi_lock, flags);
- disable_msi_mode(dev, pci_find_capability(dev, type), type);
- /* Restore dev->irq to its default pin-assertion vector */
- dev->irq = default_vector;
- if (type == PCI_CAP_ID_MSIX && head != tail) {
- /* Bad driver, which do not call msi_free_vectors before exit.
- We must do a cleanup here */
- while (1) {
- spin_lock_irqsave(&msi_lock, flags);
- entry = msi_desc[vector];
- head = entry->link.head;
- tail = entry->link.tail;
- spin_unlock_irqrestore(&msi_lock, flags);
- if (tail == head)
- break;
- if (msi_free_vector(dev, entry->link.tail))
- break;
- }
- }
-}
+ pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
+ if (!pos)
+ return;
-static int msi_alloc_vector(struct pci_dev* dev, int head)
-{
- struct msi_desc *entry;
- struct msg_address address;
- struct msg_data data;
- int i, offset, pos, dev_msi_cap, vector;
- u32 low_address, control;
- unsigned long base = 0L;
- unsigned long flags;
+ pci_read_config_word(dev, msi_control_reg(pos), &control);
+ if (!(control & PCI_MSI_FLAGS_ENABLE))
+ return;
+
+ disable_msi_mode(dev, pos, PCI_CAP_ID_MSI);
spin_lock_irqsave(&msi_lock, flags);
entry = msi_desc[dev->irq];
- if (!entry) {
+ if (!entry || !entry->dev || entry->msi_attrib.type != PCI_CAP_ID_MSI) {
spin_unlock_irqrestore(&msi_lock, flags);
- return -EINVAL;
+ return;
}
- base = entry->mask_base;
- spin_unlock_irqrestore(&msi_lock, flags);
-
- pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
- dev->bus->ops->read(dev->bus, dev->devfn, msi_control_reg(pos),
- 2, &control);
- dev_msi_cap = multi_msix_capable(control);
- for (i = 1; i < dev_msi_cap; i++) {
- if (!(low_address = readl(base + i * PCI_MSIX_ENTRY_SIZE)))
- break;
- }
- if (i >= dev_msi_cap)
- return -EINVAL;
-
- /* MSI Entry Initialization */
- if (!(entry = alloc_msi_entry()))
- return -ENOMEM;
+ if (irq_has_action(dev->irq)) {
+ spin_unlock_irqrestore(&msi_lock, flags);
+ printk(KERN_WARNING "PCI: %s: pci_disable_msi() called without "
+ "free_irq() on MSI irq %d\n",
+ pci_name(dev), dev->irq);
+ BUG_ON(irq_has_action(dev->irq));
+ } else {
+ default_irq = entry->msi_attrib.default_irq;
+ spin_unlock_irqrestore(&msi_lock, flags);
+ msi_free_irq(dev, dev->irq);
- if ((vector = get_new_vector()) < 0) {
- kmem_cache_free(msi_cachep, entry);
- return vector;
+ /* Restore dev->irq to its default pin-assertion irq */
+ dev->irq = default_irq;
}
- entry->msi_attrib.type = PCI_CAP_ID_MSIX;
- entry->msi_attrib.entry_nr = i;
- entry->msi_attrib.maskbit = 1;
- entry->dev = dev;
- entry->link.head = head;
- entry->mask_base = base;
- 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);
- offset = entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;
- writel(address.lo_address.value, base + offset +
- PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET);
- writel(address.hi_address, base + offset +
- PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET);
- writel(*(u32*)&data, base + offset + PCI_MSIX_ENTRY_DATA_OFFSET);
- writel(1, base + offset + PCI_MSIX_ENTRY_VECTOR_CTRL_OFFSET);
- attach_msi_entry(entry, vector);
-
- return vector;
-}
-
-static int msi_free_vector(struct pci_dev* dev, int vector)
+}
+
+static int msi_free_irq(struct pci_dev* dev, int irq)
{
struct msi_desc *entry;
- int entry_nr, type;
- unsigned long base = 0L;
+ int head, entry_nr, type;
+ void __iomem *base;
unsigned long flags;
+ arch_teardown_msi_irq(irq);
+
spin_lock_irqsave(&msi_lock, flags);
- entry = msi_desc[vector];
+ entry = msi_desc[irq];
if (!entry || entry->dev != dev) {
spin_unlock_irqrestore(&msi_lock, flags);
return -EINVAL;
}
type = entry->msi_attrib.type;
entry_nr = entry->msi_attrib.entry_nr;
+ head = entry->link.head;
base = entry->mask_base;
- if (entry->link.tail != entry->link.head) {
- msi_desc[entry->link.head]->link.tail = entry->link.tail;
- if (entry->link.tail)
- msi_desc[entry->link.tail]->link.head = entry->link.head;
- }
+ msi_desc[entry->link.head]->link.tail = entry->link.tail;
+ msi_desc[entry->link.tail]->link.head = entry->link.head;
entry->dev = NULL;
- vector_irq[vector] = 0;
- nr_released_vectors++;
- msi_desc[vector] = NULL;
+ msi_desc[irq] = NULL;
spin_unlock_irqrestore(&msi_lock, flags);
- kmem_cache_free(msi_cachep, entry);
+ destroy_msi_irq(irq);
+
if (type == PCI_CAP_ID_MSIX) {
- int offset;
+ writel(1, base + entry_nr * PCI_MSIX_ENTRY_SIZE +
+ PCI_MSIX_ENTRY_VECTOR_CTRL_OFFSET);
- offset = entry_nr * PCI_MSIX_ENTRY_SIZE;
- writel(1, base + offset + PCI_MSIX_ENTRY_VECTOR_CTRL_OFFSET);
- writel(0, base + offset + PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET);
+ if (head == irq)
+ iounmap(base);
}
return 0;
}
/**
- * msi_alloc_vectors - allocate additional MSI-X vectors
+ * pci_enable_msix - configure device's MSI-X capability structure
* @dev: pointer to the pci_dev data structure of MSI-X device function
- * @vector: pointer to an array of new allocated MSI-X vectors
- * @nvec: number of MSI-X vectors requested for allocation by device driver
+ * @entries: pointer to an array of MSI-X entries
+ * @nvec: number of MSI-X irqs requested for allocation by device driver
*
- * Allocate additional MSI-X vectors requested by device driver. A
- * return of zero indicates the successful setup of MSI-X capability
- * structure with new allocated MSI-X vectors or non-zero for otherwise.
+ * Setup the MSI-X capability structure of device function with the number
+ * of requested irqs upon its software driver call to request for
+ * MSI-X mode enabled on its hardware device function. A return of zero
+ * indicates the successful configuration of MSI-X capability structure
+ * with new allocated MSI-X irqs. A return of < 0 indicates a failure.
+ * Or a return of > 0 indicates that driver request is exceeding the number
+ * of irqs available. Driver should use the returned value to re-send
+ * its request.
**/
-int msi_alloc_vectors(struct pci_dev* dev, int *vector, int nvec)
+int pci_enable_msix(struct pci_dev* dev, struct msix_entry *entries, int nvec)
{
- struct msi_desc *entry;
- int i, head, pos, vec, free_vectors, alloc_vectors;
- int *vectors = (int *)vector;
- u32 control;
- unsigned long flags;
+ int status, pos, nr_entries;
+ int i, j, temp;
+ u16 control;
- if (!pci_msi_enable || !dev)
+ if (!entries || pci_msi_supported(dev) < 0)
return -EINVAL;
- if (!(pos = pci_find_capability(dev, PCI_CAP_ID_MSIX)))
- return -EINVAL;
+ status = msi_init();
+ if (status < 0)
+ return status;
- dev->bus->ops->read(dev->bus, dev->devfn, msi_control_reg(pos), 2, &control);
- if (nvec > multi_msix_capable(control))
- return -EINVAL;
+ pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+ if (!pos)
+ return -EINVAL;
- spin_lock_irqsave(&msi_lock, flags);
- entry = msi_desc[dev->irq];
- if (!entry || entry->dev != dev || /* legal call */
- entry->msi_attrib.type != PCI_CAP_ID_MSIX || /* must be MSI-X */
- entry->link.head != entry->link.tail) { /* already multi */
- spin_unlock_irqrestore(&msi_lock, flags);
+ pci_read_config_word(dev, msi_control_reg(pos), &control);
+ nr_entries = multi_msix_capable(control);
+ if (nvec > nr_entries)
return -EINVAL;
- }
- /*
- * msi_lock is provided to ensure that enough vectors resources are
- * available before granting.
- */
- free_vectors = pci_vector_resources(last_alloc_vector,
- nr_released_vectors);
- /* Ensure that each MSI/MSI-X device has one vector reserved by
- default to avoid any MSI-X driver to take all available
- resources */
- free_vectors -= nr_reserved_vectors;
- /* Find the average of free vectors among MSI-X devices */
- if (nr_msix_devices > 0)
- free_vectors /= nr_msix_devices;
- spin_unlock_irqrestore(&msi_lock, flags);
- if (nvec > free_vectors)
- return -EBUSY;
-
- alloc_vectors = 0;
- head = dev->irq;
+ /* Check for any invalid entries */
for (i = 0; i < nvec; i++) {
- if ((vec = msi_alloc_vector(dev, head)) < 0)
- break;
- *(vectors + i) = vec;
- head = vec;
- alloc_vectors++;
- }
- if (alloc_vectors != nvec) {
- for (i = 0; i < alloc_vectors; i++) {
- vec = *(vectors + i);
- msi_free_vector(dev, vec);
+ if (entries[i].entry >= nr_entries)
+ return -EINVAL; /* invalid entry */
+ for (j = i + 1; j < nvec; j++) {
+ if (entries[i].entry == entries[j].entry)
+ return -EINVAL; /* duplicate entry */
}
- spin_lock_irqsave(&msi_lock, flags);
- msi_desc[dev->irq]->link.tail = msi_desc[dev->irq]->link.head;
- spin_unlock_irqrestore(&msi_lock, flags);
- return -EBUSY;
}
- if (nr_msix_devices > 0)
- nr_msix_devices--;
-
- return 0;
+ temp = dev->irq;
+ WARN_ON(!msi_lookup_irq(dev, PCI_CAP_ID_MSIX));
+
+ /* Check whether driver already requested for MSI irq */
+ if (pci_find_capability(dev, PCI_CAP_ID_MSI) > 0 &&
+ !msi_lookup_irq(dev, PCI_CAP_ID_MSI)) {
+ printk(KERN_INFO "PCI: %s: Can't enable MSI-X. "
+ "Device already has an MSI irq assigned\n",
+ pci_name(dev));
+ dev->irq = temp;
+ return -EINVAL;
+ }
+ status = msix_capability_init(dev, entries, nvec);
+ return status;
}
-/**
- * msi_free_vectors - reclaim MSI-X vectors to unused state
- * @dev: pointer to the pci_dev data structure of MSI-X device function
- * @vector: pointer to an array of released MSI-X vectors
- * @nvec: number of MSI-X vectors requested for release by device driver
- *
- * Reclaim MSI-X vectors released by device driver to unused state,
- * which may be used later on. A return of zero indicates the
- * success or non-zero for otherwise. Device driver should call this
- * before calling function free_irq.
- **/
-int msi_free_vectors(struct pci_dev* dev, int *vector, int nvec)
+void pci_disable_msix(struct pci_dev* dev)
{
- struct msi_desc *entry;
- int i;
- unsigned long flags;
+ int pos, temp;
+ u16 control;
if (!pci_msi_enable)
- return -EINVAL;
+ return;
+ if (!dev)
+ return;
- spin_lock_irqsave(&msi_lock, flags);
- entry = msi_desc[dev->irq];
- if (!entry || entry->dev != dev ||
- entry->msi_attrib.type != PCI_CAP_ID_MSIX ||
- entry->link.head == entry->link.tail) { /* Nothing to free */
- spin_unlock_irqrestore(&msi_lock, flags);
- return -EINVAL;
- }
- spin_unlock_irqrestore(&msi_lock, flags);
+ pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+ if (!pos)
+ return;
- for (i = 0; i < nvec; i++) {
- if (*(vector + i) == dev->irq)
- continue;/* Don't free entry 0 if mistaken by driver */
- msi_free_vector(dev, *(vector + i));
- }
+ pci_read_config_word(dev, msi_control_reg(pos), &control);
+ if (!(control & PCI_MSIX_FLAGS_ENABLE))
+ return;
- return 0;
+ disable_msi_mode(dev, pos, PCI_CAP_ID_MSIX);
+
+ temp = dev->irq;
+ if (!msi_lookup_irq(dev, PCI_CAP_ID_MSIX)) {
+ int irq, head, tail = 0, warning = 0;
+ unsigned long flags;
+
+ irq = head = dev->irq;
+ dev->irq = temp; /* Restore pin IRQ */
+ while (head != tail) {
+ spin_lock_irqsave(&msi_lock, flags);
+ tail = msi_desc[irq]->link.tail;
+ spin_unlock_irqrestore(&msi_lock, flags);
+ if (irq_has_action(irq))
+ warning = 1;
+ else if (irq != head) /* Release MSI-X irq */
+ msi_free_irq(dev, irq);
+ irq = tail;
+ }
+ msi_free_irq(dev, irq);
+ if (warning) {
+ printk(KERN_WARNING "PCI: %s: pci_disable_msix() called without "
+ "free_irq() on all MSI-X irqs\n",
+ pci_name(dev));
+ BUG_ON(warning > 0);
+ }
+ }
}
/**
- * msi_remove_pci_irq_vectors - reclaim MSI(X) vectors to unused state
+ * msi_remove_pci_irq_vectors - reclaim MSI(X) irqs to unused state
* @dev: pointer to the pci_dev data structure of MSI(X) device function
*
- * Being called during hotplug remove, from which the device funciton
- * is hot-removed. All previous assigned MSI/MSI-X vectors, if
+ * Being called during hotplug remove, from which the device function
+ * is hot-removed. All previous assigned MSI/MSI-X irqs, if
* allocated for this device function, are reclaimed to unused state,
* which may be used later on.
**/
void msi_remove_pci_irq_vectors(struct pci_dev* dev)
{
- struct msi_desc *entry;
- int type, temp;
+ int pos, temp;
unsigned long flags;
if (!pci_msi_enable || !dev)
return;
- if (!pci_find_capability(dev, PCI_CAP_ID_MSI)) {
- if (!pci_find_capability(dev, PCI_CAP_ID_MSIX))
- return;
- }
- temp = dev->irq;
- if (msi_lookup_vector(dev))
- return;
-
- spin_lock_irqsave(&msi_lock, flags);
- entry = msi_desc[dev->irq];
- if (!entry || entry->dev != dev) {
- spin_unlock_irqrestore(&msi_lock, flags);
- return;
- }
- type = entry->msi_attrib.type;
- spin_unlock_irqrestore(&msi_lock, flags);
-
- msi_free_vector(dev, dev->irq);
- if (type == PCI_CAP_ID_MSIX) {
- int i, pos, dev_msi_cap;
- u32 phys_addr, table_offset;
- u32 control;
- u8 bir;
-
- pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
- dev->bus->ops->read(dev->bus, dev->devfn, msi_control_reg(pos), 2, &control);
- dev_msi_cap = multi_msix_capable(control);
- dev->bus->ops->read(dev->bus, dev->devfn,
- msix_table_offset_reg(pos), 4, &table_offset);
- bir = (u8)(table_offset & PCI_MSIX_FLAGS_BIRMASK);
- phys_addr = pci_resource_start (dev, bir);
- phys_addr += (u32)(table_offset & ~PCI_MSIX_FLAGS_BIRMASK);
- for (i = FIRST_DEVICE_VECTOR; i < NR_IRQS; i++) {
+ temp = dev->irq; /* Save IOAPIC IRQ */
+ pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
+ if (pos > 0 && !msi_lookup_irq(dev, PCI_CAP_ID_MSI)) {
+ if (irq_has_action(dev->irq)) {
+ printk(KERN_WARNING "PCI: %s: msi_remove_pci_irq_vectors() "
+ "called without free_irq() on MSI irq %d\n",
+ pci_name(dev), dev->irq);
+ BUG_ON(irq_has_action(dev->irq));
+ } else /* Release MSI irq assigned to this device */
+ msi_free_irq(dev, dev->irq);
+ dev->irq = temp; /* Restore IOAPIC IRQ */
+ }
+ pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+ if (pos > 0 && !msi_lookup_irq(dev, PCI_CAP_ID_MSIX)) {
+ int irq, head, tail = 0, warning = 0;
+ void __iomem *base = NULL;
+
+ irq = head = dev->irq;
+ while (head != tail) {
spin_lock_irqsave(&msi_lock, flags);
- if (!msi_desc[i] || msi_desc[i]->dev != dev) {
- spin_unlock_irqrestore(&msi_lock, flags);
- continue;
- }
+ tail = msi_desc[irq]->link.tail;
+ base = msi_desc[irq]->mask_base;
spin_unlock_irqrestore(&msi_lock, flags);
- msi_free_vector(dev, i);
+ if (irq_has_action(irq))
+ warning = 1;
+ else if (irq != head) /* Release MSI-X irq */
+ msi_free_irq(dev, irq);
+ irq = tail;
+ }
+ msi_free_irq(dev, irq);
+ if (warning) {
+ iounmap(base);
+ printk(KERN_WARNING "PCI: %s: msi_remove_pci_irq_vectors() "
+ "called without free_irq() on all MSI-X irqs\n",
+ pci_name(dev));
+ BUG_ON(warning > 0);
}
- writel(1, entry->mask_base + PCI_MSIX_ENTRY_VECTOR_CTRL_OFFSET);
- iounmap((void*)entry->mask_base);
- release_mem_region(phys_addr, dev_msi_cap * PCI_MSIX_ENTRY_SIZE);
+ dev->irq = temp; /* Restore IOAPIC IRQ */
}
- dev->irq = temp;
- nr_reserved_vectors++;
+}
+
+void pci_no_msi(void)
+{
+ pci_msi_enable = 0;
+}
+void pci_yes_msi(void)
+{
+ pci_msi_enable = 1;
}
EXPORT_SYMBOL(pci_enable_msi);
-EXPORT_SYMBOL(msi_alloc_vectors);
-EXPORT_SYMBOL(msi_free_vectors);
+EXPORT_SYMBOL(pci_disable_msi);
+EXPORT_SYMBOL(pci_enable_msix);
+EXPORT_SYMBOL(pci_disable_msix);