* 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 <linux/smp.h>
#include <asm/errno.h>
#include <asm/io.h>
-#include <asm/smp.h>
#include "pci.h"
#include "msi.h"
-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 int pci_msi_enable = 1;
-static int last_alloc_vector;
-static int nr_released_vectors;
-static int nr_reserved_vectors = NR_HP_RESERVED_VECTORS;
-static int nr_msix_devices;
-
-#ifndef CONFIG_X86_IO_APIC
-int vector_irq[NR_VECTORS] = { [0 ... NR_VECTORS - 1] = -1};
-u8 irq_vector[NR_IRQ_VECTORS];
-#endif
-static struct msi_ops *msi_ops;
+/* Arch hooks */
-int
-msi_register(struct msi_ops *ops)
+#ifndef arch_msi_check_device
+int arch_msi_check_device(struct pci_dev *dev, int nvec, int type)
{
- msi_ops = ops;
return 0;
}
+#endif
-static void msi_cache_ctor(void *p, kmem_cache_t *cache, unsigned long flags)
+#ifndef arch_setup_msi_irqs
+int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
{
- memset(p, 0, NR_IRQS * sizeof(struct msi_desc));
-}
+ struct msi_desc *entry;
+ int ret;
-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);
- if (!msi_cachep)
- return -ENOMEM;
+ /*
+ * If an architecture wants to support multiple MSI, it needs to
+ * override arch_setup_msi_irqs()
+ */
+ if (type == PCI_CAP_ID_MSI && nvec > 1)
+ return 1;
+
+ list_for_each_entry(entry, &dev->msi_list, list) {
+ ret = arch_setup_msi_irq(dev, entry);
+ if (ret < 0)
+ return ret;
+ if (ret > 0)
+ return -ENOSPC;
+ }
return 0;
}
+#endif
-static void msi_set_mask_bit(unsigned int vector, int flag)
+#ifndef arch_teardown_msi_irqs
+void arch_teardown_msi_irqs(struct pci_dev *dev)
{
struct msi_desc *entry;
- entry = (struct msi_desc *)msi_desc[vector];
- if (!entry || !entry->dev || !entry->mask_base)
- return;
- switch (entry->msi_attrib.type) {
- case PCI_CAP_ID_MSI:
- {
- 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_VECTOR_CTRL_OFFSET;
- writel(flag, entry->mask_base + offset);
- break;
- }
- default:
- break;
+ list_for_each_entry(entry, &dev->msi_list, list) {
+ int i, nvec;
+ if (entry->irq == 0)
+ continue;
+ nvec = 1 << entry->msi_attrib.multiple;
+ for (i = 0; i < nvec; i++)
+ arch_teardown_msi_irq(entry->irq + i);
}
}
+#endif
-#ifdef CONFIG_SMP
-static void set_msi_affinity(unsigned int vector, cpumask_t cpu_mask)
+static void msi_set_enable(struct pci_dev *dev, int pos, int enable)
{
- struct msi_desc *entry;
- u32 address_hi, address_lo;
- unsigned int irq = vector;
- unsigned int dest_cpu = first_cpu(cpu_mask);
-
- entry = (struct msi_desc *)msi_desc[vector];
- if (!entry || !entry->dev)
- return;
-
- switch (entry->msi_attrib.type) {
- case PCI_CAP_ID_MSI:
- {
- int pos = pci_find_capability(entry->dev, PCI_CAP_ID_MSI);
-
- 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);
-
- 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);
- set_native_irq_info(irq, cpu_mask);
- break;
- }
- case PCI_CAP_ID_MSIX:
- {
- 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;
- }
- default:
- break;
- }
-}
-#else
-#define set_msi_affinity NULL
-#endif /* CONFIG_SMP */
+ u16 control;
-static void mask_MSI_irq(unsigned int vector)
-{
- msi_set_mask_bit(vector, 1);
-}
+ BUG_ON(!pos);
-static void unmask_MSI_irq(unsigned int vector)
-{
- msi_set_mask_bit(vector, 0);
+ pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &control);
+ control &= ~PCI_MSI_FLAGS_ENABLE;
+ if (enable)
+ control |= PCI_MSI_FLAGS_ENABLE;
+ pci_write_config_word(dev, pos + PCI_MSI_FLAGS, control);
}
-static unsigned int startup_msi_irq_wo_maskbit(unsigned int vector)
+static void msix_set_enable(struct pci_dev *dev, int enable)
{
- struct msi_desc *entry;
- unsigned long flags;
+ int pos;
+ u16 control;
- spin_lock_irqsave(&msi_lock, flags);
- entry = msi_desc[vector];
- if (!entry || !entry->dev) {
- spin_unlock_irqrestore(&msi_lock, flags);
- return 0;
+ pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+ if (pos) {
+ pci_read_config_word(dev, pos + PCI_MSIX_FLAGS, &control);
+ control &= ~PCI_MSIX_FLAGS_ENABLE;
+ if (enable)
+ control |= PCI_MSIX_FLAGS_ENABLE;
+ pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);
}
- entry->msi_attrib.state = 1; /* Mark it active */
- spin_unlock_irqrestore(&msi_lock, flags);
-
- return 0; /* never anything pending */
}
-static unsigned int startup_msi_irq_w_maskbit(unsigned int vector)
+static inline __attribute_const__ u32 msi_mask(unsigned x)
{
- startup_msi_irq_wo_maskbit(vector);
- unmask_MSI_irq(vector);
- return 0; /* never anything pending */
+ /* Don't shift by >= width of type */
+ if (x >= 5)
+ return 0xffffffff;
+ return (1 << (1 << x)) - 1;
}
-static void shutdown_msi_irq(unsigned int vector)
+static inline __attribute_const__ u32 msi_capable_mask(u16 control)
{
- struct msi_desc *entry;
- unsigned long flags;
-
- spin_lock_irqsave(&msi_lock, flags);
- entry = msi_desc[vector];
- if (entry && entry->dev)
- entry->msi_attrib.state = 0; /* Mark it not active */
- spin_unlock_irqrestore(&msi_lock, flags);
+ return msi_mask((control >> 1) & 7);
}
-static void end_msi_irq_wo_maskbit(unsigned int vector)
+static inline __attribute_const__ u32 msi_enabled_mask(u16 control)
{
- move_native_irq(vector);
- ack_APIC_irq();
+ return msi_mask((control >> 4) & 7);
}
-static void end_msi_irq_w_maskbit(unsigned int vector)
-{
- move_native_irq(vector);
- unmask_MSI_irq(vector);
- ack_APIC_irq();
-}
-
-static void do_nothing(unsigned int vector)
-{
-}
-
-/*
- * 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,
- .enable = unmask_MSI_irq,
- .disable = mask_MSI_irq,
- .ack = mask_MSI_irq,
- .end = end_msi_irq_w_maskbit,
- .set_affinity = set_msi_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,
- .enable = unmask_MSI_irq,
- .disable = mask_MSI_irq,
- .ack = mask_MSI_irq,
- .end = end_msi_irq_w_maskbit,
- .set_affinity = set_msi_affinity
-};
-
/*
- * Interrupt Type for MSI PCI/PCI-X/PCI-Express Devices,
- * which implement the MSI Capability Structure without
- * Mask-and-Pending Bits.
+ * 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.
*/
-static struct hw_interrupt_type msi_irq_wo_maskbit_type = {
- .typename = "PCI-MSI",
- .startup = startup_msi_irq_wo_maskbit,
- .shutdown = shutdown_msi_irq,
- .enable = do_nothing,
- .disable = do_nothing,
- .ack = do_nothing,
- .end = end_msi_irq_wo_maskbit,
- .set_affinity = set_msi_affinity
-};
-
-static int msi_free_vector(struct pci_dev* dev, int vector, int reassign);
-static int assign_msi_vector(void)
+static void msi_mask_irq(struct msi_desc *desc, u32 mask, u32 flag)
{
- static int new_vector_avail = 1;
- int vector;
- unsigned long flags;
+ u32 mask_bits = desc->masked;
- /*
- * 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) {
- int free_vector = 0;
-
- /*
- * 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;
- free_vector = vector;
- if (!msi_desc[vector])
- break;
- else
- continue;
- }
- if (!free_vector) {
- spin_unlock_irqrestore(&msi_lock, flags);
- return -EBUSY;
- }
- vector_irq[free_vector] = -1;
- nr_released_vectors--;
- spin_unlock_irqrestore(&msi_lock, flags);
- if (msi_desc[free_vector] != NULL) {
- struct pci_dev *dev;
- int tail;
-
- /* free all linked vectors before re-assign */
- do {
- spin_lock_irqsave(&msi_lock, flags);
- dev = msi_desc[free_vector]->dev;
- tail = msi_desc[free_vector]->link.tail;
- spin_unlock_irqrestore(&msi_lock, flags);
- msi_free_vector(dev, tail, 1);
- } while (free_vector != tail);
- }
-
- return free_vector;
- }
- vector = assign_irq_vector(AUTO_ASSIGN);
- last_alloc_vector = vector;
- if (vector == LAST_DEVICE_VECTOR)
- new_vector_avail = 0;
+ if (!desc->msi_attrib.maskbit)
+ return;
- spin_unlock_irqrestore(&msi_lock, flags);
- return vector;
+ mask_bits &= ~mask;
+ mask_bits |= flag;
+ pci_write_config_dword(desc->dev, desc->mask_pos, mask_bits);
+ desc->masked = mask_bits;
}
-static int get_new_vector(void)
+/*
+ * This internal function does not flush PCI writes to the device.
+ * All users must ensure that they read from the device before either
+ * assuming that the device state is up to date, or returning out of this
+ * file. This saves a few milliseconds when initialising devices with lots
+ * of MSI-X interrupts.
+ */
+static void msix_mask_irq(struct msi_desc *desc, u32 flag)
{
- int vector = assign_msi_vector();
-
- if (vector > 0)
- set_intr_gate(vector, interrupt[vector]);
-
- return vector;
+ u32 mask_bits = desc->masked;
+ unsigned offset = desc->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE +
+ PCI_MSIX_ENTRY_VECTOR_CTRL_OFFSET;
+ mask_bits &= ~1;
+ mask_bits |= flag;
+ writel(mask_bits, desc->mask_base + offset);
+ desc->masked = mask_bits;
}
-static int msi_init(void)
+static void msi_set_mask_bit(unsigned irq, u32 flag)
{
- static int status = -ENOMEM;
-
- if (!status)
- return status;
-
- if (pci_msi_quirk) {
- pci_msi_enable = 0;
- printk(KERN_WARNING "PCI: MSI quirk detected. MSI disabled.\n");
- status = -EINVAL;
- 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;
- }
+ struct msi_desc *desc = get_irq_msi(irq);
- 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;
- }
-
-#ifndef CONFIG_X86_IO_APIC
- irq_vector[0] = FIRST_DEVICE_VECTOR;
-#endif
-
- if (last_alloc_vector < 0) {
- pci_msi_enable = 0;
- printk(KERN_WARNING "PCI: No interrupt vectors available for MSI\n");
- status = -EBUSY;
- return status;
+ if (desc->msi_attrib.is_msix) {
+ msix_mask_irq(desc, flag);
+ readl(desc->mask_base); /* Flush write to device */
+ } else {
+ unsigned offset = irq - desc->dev->irq;
+ msi_mask_irq(desc, 1 << offset, flag << offset);
}
- vector_irq[last_alloc_vector] = 0;
- nr_released_vectors++;
-
- return status;
}
-static int get_msi_vector(struct pci_dev *dev)
+void mask_msi_irq(unsigned int irq)
{
- return get_new_vector();
+ msi_set_mask_bit(irq, 1);
}
-static struct msi_desc* alloc_msi_entry(void)
+void unmask_msi_irq(unsigned int irq)
{
- struct msi_desc *entry;
-
- entry = kmem_cache_alloc(msi_cachep, SLAB_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;
+ msi_set_mask_bit(irq, 0);
}
-static void attach_msi_entry(struct msi_desc *entry, int vector)
+void read_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
{
- unsigned long flags;
+ struct msi_desc *entry = get_irq_desc_msi(desc);
+ if (entry->msi_attrib.is_msix) {
+ void __iomem *base = entry->mask_base +
+ entry->msi_attrib.entry_nr * PCI_MSIX_ENTRY_SIZE;
- spin_lock_irqsave(&msi_lock, flags);
- msi_desc[vector] = entry;
- spin_unlock_irqrestore(&msi_lock, flags);
-}
-
-static void irq_handler_init(int cap_id, int pos, int mask)
-{
- unsigned long flags;
-
- spin_lock_irqsave(&irq_desc[pos].lock, flags);
- 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;
+ 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);
+ } else {
+ 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, 0), &data);
+ }
+ msg->data = data;
}
- spin_unlock_irqrestore(&irq_desc[pos].lock, flags);
}
-static void enable_msi_mode(struct pci_dev *dev, int pos, int type)
+void read_msi_msg(unsigned int irq, struct msi_msg *msg)
{
- u16 control;
+ struct irq_desc *desc = irq_to_desc(irq);
- 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);
- pci_write_config_word(dev, msi_control_reg(pos), control);
- } else {
- msix_enable(control);
- pci_write_config_word(dev, msi_control_reg(pos), control);
- }
- if (pci_find_capability(dev, PCI_CAP_ID_EXP)) {
- /* PCI Express Endpoint device detected */
- pci_intx(dev, 0); /* disable intx */
- }
+ read_msi_msg_desc(desc, msg);
}
-void disable_msi_mode(struct pci_dev *dev, int pos, int type)
+void write_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
{
- u16 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);
- pci_write_config_word(dev, msi_control_reg(pos), control);
+ struct msi_desc *entry = get_irq_desc_msi(desc);
+ if (entry->msi_attrib.is_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);
} else {
- msix_disable(control);
- pci_write_config_word(dev, msi_control_reg(pos), control);
- }
- if (pci_find_capability(dev, PCI_CAP_ID_EXP)) {
- /* PCI Express Endpoint device detected */
- pci_intx(dev, 1); /* enable intx */
+ struct pci_dev *dev = entry->dev;
+ int pos = entry->msi_attrib.pos;
+ u16 msgctl;
+
+ pci_read_config_word(dev, msi_control_reg(pos), &msgctl);
+ msgctl &= ~PCI_MSI_FLAGS_QSIZE;
+ msgctl |= entry->msi_attrib.multiple << 4;
+ pci_write_config_word(dev, msi_control_reg(pos), msgctl);
+
+ 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);
+ }
}
+ entry->msg = *msg;
}
-static int msi_lookup_vector(struct pci_dev *dev, int type)
+void write_msi_msg(unsigned int irq, struct msi_msg *msg)
{
- int vector;
- 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.type != type ||
- msi_desc[vector]->msi_attrib.default_vector != dev->irq)
- continue;
- spin_unlock_irqrestore(&msi_lock, flags);
- /* This pre-assigned MSI vector for this device
- already exits. Override dev->irq with this vector */
- dev->irq = vector;
- return 0;
- }
- spin_unlock_irqrestore(&msi_lock, flags);
+ struct irq_desc *desc = irq_to_desc(irq);
- return -EACCES;
+ write_msi_msg_desc(desc, msg);
}
-void pci_scan_msi_device(struct pci_dev *dev)
-{
- if (!dev)
- return;
-
- if (pci_find_capability(dev, PCI_CAP_ID_MSIX) > 0)
- nr_msix_devices++;
- else if (pci_find_capability(dev, PCI_CAP_ID_MSI) > 0)
- nr_reserved_vectors++;
-}
+static int msi_free_irqs(struct pci_dev* dev);
-#ifdef CONFIG_PM
-int pci_save_msi_state(struct pci_dev *dev)
+static struct msi_desc *alloc_msi_entry(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;
+ struct msi_desc *desc = kzalloc(sizeof(*desc), GFP_KERNEL);
+ if (!desc)
+ return NULL;
- pci_read_config_word(dev, msi_control_reg(pos), &control);
- if (!(control & PCI_MSI_FLAGS_ENABLE))
- return 0;
+ INIT_LIST_HEAD(&desc->list);
+ desc->dev = dev;
- 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++]);
- 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;
+ return desc;
}
-void pci_restore_msi_state(struct pci_dev *dev)
+static void pci_intx_for_msi(struct pci_dev *dev, int enable)
{
- 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);
+ if (!(dev->dev_flags & PCI_DEV_FLAGS_MSI_INTX_DISABLE_BUG))
+ pci_intx(dev, enable);
}
-int pci_save_msix_state(struct pci_dev *dev)
+static void __pci_restore_msi_state(struct pci_dev *dev)
{
int pos;
- int temp;
- int vector, 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;
+ struct msi_desc *entry;
- /* 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;
+ if (!dev->msi_enabled)
+ return;
- /* save the table */
- temp = dev->irq;
- if (msi_lookup_vector(dev, PCI_CAP_ID_MSIX)) {
- kfree(save_state);
- return -EINVAL;
- }
+ entry = get_irq_msi(dev->irq);
+ pos = entry->msi_attrib.pos;
- 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;
+ pci_intx_for_msi(dev, 0);
+ msi_set_enable(dev, pos, 0);
+ write_msi_msg(dev->irq, &entry->msg);
- disable_msi_mode(dev, pos, PCI_CAP_ID_MSIX);
- save_state->cap_nr = PCI_CAP_ID_MSIX;
- pci_add_saved_cap(dev, save_state);
- return 0;
+ pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &control);
+ msi_mask_irq(entry, msi_capable_mask(control), entry->masked);
+ control &= ~PCI_MSI_FLAGS_QSIZE;
+ control |= (entry->msi_attrib.multiple << 4) | PCI_MSI_FLAGS_ENABLE;
+ pci_write_config_word(dev, pos + PCI_MSI_FLAGS, control);
}
-void pci_restore_msix_state(struct pci_dev *dev)
+static void __pci_restore_msix_state(struct pci_dev *dev)
{
- u16 save;
int pos;
- int vector, head, tail = 0;
- void __iomem *base;
- int j;
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);
+ u16 control;
- pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
- if (pos <= 0)
+ if (!dev->msix_enabled)
return;
+ BUG_ON(list_empty(&dev->msi_list));
+ entry = list_entry(dev->msi_list.next, struct msi_desc, list);
+ pos = entry->msi_attrib.pos;
+ pci_read_config_word(dev, pos + PCI_MSIX_FLAGS, &control);
/* route the table */
- temp = dev->irq;
- if (msi_lookup_vector(dev, PCI_CAP_ID_MSIX))
- return;
- vector = head = dev->irq;
- while (head != tail) {
- entry = msi_desc[vector];
- base = entry->mask_base;
- j = entry->msi_attrib.entry_nr;
-
- writel(entry->address_lo_save,
- base + j * PCI_MSIX_ENTRY_SIZE +
- PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET);
- writel(entry->address_hi_save,
- base + j * PCI_MSIX_ENTRY_SIZE +
- PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET);
- writel(entry->data_save,
- base + j * PCI_MSIX_ENTRY_SIZE +
- PCI_MSIX_ENTRY_DATA_OFFSET);
-
- tail = msi_desc[vector]->link.tail;
- vector = tail;
+ pci_intx_for_msi(dev, 0);
+ control |= PCI_MSIX_FLAGS_ENABLE | PCI_MSIX_FLAGS_MASKALL;
+ pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);
+
+ list_for_each_entry(entry, &dev->msi_list, list) {
+ write_msi_msg(entry->irq, &entry->msg);
+ msix_mask_irq(entry, entry->masked);
}
- dev->irq = temp;
- pci_write_config_word(dev, msi_control_reg(pos), save);
- enable_msi_mode(dev, pos, PCI_CAP_ID_MSIX);
+ control &= ~PCI_MSIX_FLAGS_MASKALL;
+ pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);
}
-#endif
-static int msi_register_init(struct pci_dev *dev, struct msi_desc *entry)
+void pci_restore_msi_state(struct pci_dev *dev)
{
- 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 */
- 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);
- pci_write_config_word(dev,
- msi_data_reg(pos, 1), data);
- } else
- pci_write_config_word(dev,
- msi_data_reg(pos, 0), data);
- if (entry->msi_attrib.maskbit) {
- unsigned int maskbits, temp;
- /* All MSIs are unmasked by default, Mask them all */
- 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;
- pci_write_config_dword(dev,
- msi_mask_bits_reg(pos, is_64bit_address(control)),
- maskbits);
- }
-
- return 0;
+ __pci_restore_msi_state(dev);
+ __pci_restore_msix_state(dev);
}
+EXPORT_SYMBOL_GPL(pci_restore_msi_state);
/**
* 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 device function with a single
- * MSI vector, 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.
- **/
-static int msi_capability_init(struct pci_dev *dev)
+ * 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 pci_dev *dev, int nvec)
{
- int status;
struct msi_desc *entry;
- int pos, vector;
+ int pos, ret;
u16 control;
+ unsigned mask;
pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
+ msi_set_enable(dev, pos, 0); /* Disable MSI during set up */
+
pci_read_config_word(dev, msi_control_reg(pos), &control);
/* MSI Entry Initialization */
- entry = alloc_msi_entry();
+ entry = alloc_msi_entry(dev);
if (!entry)
return -ENOMEM;
- vector = get_msi_vector(dev);
- if (vector < 0) {
- kmem_cache_free(msi_cachep, entry);
- return -EBUSY;
- }
- entry->link.head = vector;
- entry->link.tail = vector;
- entry->msi_attrib.type = PCI_CAP_ID_MSI;
- entry->msi_attrib.state = 0; /* Mark it not active */
+ entry->msi_attrib.is_msix = 0;
+ 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; /* Save IOAPIC IRQ */
- dev->irq = vector;
- entry->dev = dev;
- if (is_mask_bit_support(control)) {
- 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);
+ entry->msi_attrib.default_irq = dev->irq; /* Save IOAPIC IRQ */
+ entry->msi_attrib.pos = pos;
+
+ entry->mask_pos = msi_mask_reg(pos, entry->msi_attrib.is_64);
+ /* All MSIs are unmasked by default, Mask them all */
+ if (entry->msi_attrib.maskbit)
+ pci_read_config_dword(dev, entry->mask_pos, &entry->masked);
+ mask = msi_capable_mask(control);
+ msi_mask_irq(entry, mask, mask);
+
+ list_add_tail(&entry->list, &dev->msi_list);
+
/* Configure MSI capability structure */
- status = msi_register_init(dev, entry);
- if (status != 0) {
- dev->irq = entry->msi_attrib.default_vector;
- kmem_cache_free(msi_cachep, entry);
- return status;
+ ret = arch_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSI);
+ if (ret) {
+ msi_free_irqs(dev);
+ return ret;
}
- attach_msi_entry(entry, vector);
/* Set MSI enabled bits */
- enable_msi_mode(dev, pos, PCI_CAP_ID_MSI);
+ pci_intx_for_msi(dev, 0);
+ msi_set_enable(dev, pos, 1);
+ dev->msi_enabled = 1;
+ dev->irq = entry->irq;
return 0;
}
* @nvec: number of @entries
*
* Setup the MSI-X capability structure of device function with a
- * single MSI-X vector. A return of zero indicates the successful setup of
- * requested MSI-X entries with allocated vectors or non-zero for otherwise.
+ * 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 msix_entry *entries, int nvec)
{
- struct msi_desc *head = NULL, *tail = NULL, *entry = NULL;
- u32 address_hi;
- u32 address_lo;
- u32 data;
- int status;
- int vector, pos, i, j, nr_entries, temp = 0;
+ struct msi_desc *entry;
+ int pos, i, j, nr_entries, ret;
unsigned long phys_addr;
u32 table_offset;
u16 control;
void __iomem *base;
pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+ pci_read_config_word(dev, pos + PCI_MSIX_FLAGS, &control);
+
+ /* Ensure MSI-X is disabled while it is set up */
+ control &= ~PCI_MSIX_FLAGS_ENABLE;
+ pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);
+
/* Request & Map MSI-X table region */
- 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);
if (base == NULL)
return -ENOMEM;
- /* MSI-X Table Initialization */
for (i = 0; i < nvec; i++) {
- entry = alloc_msi_entry();
- if (!entry)
- break;
- vector = get_msi_vector(dev);
- if (vector < 0) {
- kmem_cache_free(msi_cachep, entry);
- break;
+ entry = alloc_msi_entry(dev);
+ if (!entry) {
+ if (!i)
+ iounmap(base);
+ else
+ msi_free_irqs(dev);
+ /* No enough memory. Don't try again */
+ return -ENOMEM;
}
j = entries[i].entry;
- entries[i].vector = vector;
- entry->msi_attrib.type = PCI_CAP_ID_MSIX;
- entry->msi_attrib.state = 0; /* Mark it not active */
+ entry->msi_attrib.is_msix = 1;
+ entry->msi_attrib.is_64 = 1;
entry->msi_attrib.entry_nr = j;
- entry->msi_attrib.maskbit = 1;
- entry->msi_attrib.default_vector = dev->irq;
- entry->dev = dev;
+ entry->msi_attrib.default_irq = dev->irq;
+ entry->msi_attrib.pos = pos;
entry->mask_base = base;
- if (!head) {
- entry->link.head = vector;
- entry->link.tail = vector;
- head = entry;
- } else {
- entry->link.head = temp;
- entry->link.tail = tail->link.tail;
- tail->link.tail = vector;
- head->link.head = vector;
- }
- temp = vector;
- tail = entry;
- /* Replace with MSI-X handler */
- irq_handler_init(PCI_CAP_ID_MSIX, vector, 1);
- /* Configure MSI-X capability structure */
- 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,
- base + j * PCI_MSIX_ENTRY_SIZE +
- PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET);
- writel(data,
- base + j * PCI_MSIX_ENTRY_SIZE +
- PCI_MSIX_ENTRY_DATA_OFFSET);
- attach_msi_entry(entry, vector);
+
+ list_add_tail(&entry->list, &dev->msi_list);
}
- if (i != nvec) {
- i--;
- for (; i >= 0; i--) {
- vector = (entries + i)->vector;
- msi_free_vector(dev, vector, 0);
- (entries + i)->vector = 0;
+
+ ret = arch_setup_msi_irqs(dev, nvec, PCI_CAP_ID_MSIX);
+ if (ret < 0) {
+ /* If we had some success report the number of irqs
+ * we succeeded in setting up. */
+ int avail = 0;
+ list_for_each_entry(entry, &dev->msi_list, list) {
+ if (entry->irq != 0) {
+ avail++;
+ }
}
- return -EBUSY;
+
+ if (avail != 0)
+ ret = avail;
+ }
+
+ if (ret) {
+ msi_free_irqs(dev);
+ return ret;
}
- /* Set MSI-X enabled bits */
- enable_msi_mode(dev, pos, PCI_CAP_ID_MSIX);
+
+ /*
+ * 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.
+ */
+ control |= PCI_MSIX_FLAGS_MASKALL | PCI_MSIX_FLAGS_ENABLE;
+ pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);
+
+ i = 0;
+ list_for_each_entry(entry, &dev->msi_list, list) {
+ entries[i].vector = entry->irq;
+ set_irq_msi(entry->irq, entry);
+ j = entries[i].entry;
+ entry->masked = readl(base + j * PCI_MSIX_ENTRY_SIZE +
+ PCI_MSIX_ENTRY_VECTOR_CTRL_OFFSET);
+ msix_mask_irq(entry, 1);
+ i++;
+ }
+
+ /* Set MSI-X enabled bits and unmask the function */
+ pci_intx_for_msi(dev, 0);
+ dev->msix_enabled = 1;
+
+ control &= ~PCI_MSIX_FLAGS_MASKALL;
+ pci_write_config_word(dev, pos + PCI_MSIX_FLAGS, control);
return 0;
}
/**
- * pci_enable_msi - configure device's MSI capability structure
+ * pci_msi_check_device - check whether MSI may be enabled on a device
* @dev: pointer to the pci_dev data structure of MSI device function
+ * @nvec: how many MSIs have been requested ?
+ * @type: are we checking for MSI or MSI-X ?
*
- * Setup the MSI capability structure of device function with
- * a single MSI vector 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
- * vector or non-zero for otherwise.
+ * Look at global flags, the device itself, and its parent busses
+ * to determine if MSI/-X are supported for the device. If MSI/-X is
+ * supported return 0, else return an error code.
**/
-int pci_enable_msi(struct pci_dev* dev)
+static int pci_msi_check_device(struct pci_dev* dev, int nvec, int type)
{
struct pci_bus *bus;
- int pos, temp, status = -EINVAL;
- u16 control;
+ int ret;
- if (!pci_msi_enable || !dev)
- return status;
-
- if (dev->no_msi)
- return status;
+ /* MSI must be globally enabled and supported by the device */
+ if (!pci_msi_enable || !dev || dev->no_msi)
+ return -EINVAL;
+ /*
+ * You can't ask to have 0 or less MSIs configured.
+ * a) it's stupid ..
+ * b) the list manipulation code assumes nvec >= 1.
+ */
+ if (nvec < 1)
+ return -ERANGE;
+
+ /* 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;
- temp = dev->irq;
+ ret = arch_msi_check_device(dev, nvec, type);
+ if (ret)
+ return ret;
- status = msi_init();
- if (status < 0)
- return status;
+ if (!pci_find_capability(dev, type))
+ return -EINVAL;
+
+ return 0;
+}
+
+/**
+ * pci_enable_msi_block - configure device's MSI capability structure
+ * @dev: device to configure
+ * @nvec: number of interrupts to configure
+ *
+ * Allocate IRQs for a device with the MSI capability.
+ * This function returns a negative errno if an error occurs. If it
+ * is unable to allocate the number of interrupts requested, it returns
+ * the number of interrupts it might be able to allocate. If it successfully
+ * allocates at least the number of interrupts requested, it returns 0 and
+ * updates the @dev's irq member to the lowest new interrupt number; the
+ * other interrupt numbers allocated to this device are consecutive.
+ */
+int pci_enable_msi_block(struct pci_dev *dev, unsigned int nvec)
+{
+ int status, pos, maxvec;
+ u16 msgctl;
pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
if (!pos)
return -EINVAL;
+ pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &msgctl);
+ maxvec = 1 << ((msgctl & PCI_MSI_FLAGS_QMASK) >> 1);
+ if (nvec > maxvec)
+ return maxvec;
- 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);
- 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;
- }
- /* Check whether driver already requested for MSI-X vectors */
- pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
- if (pos > 0 && !msi_lookup_vector(dev, PCI_CAP_ID_MSIX)) {
- printk(KERN_INFO "PCI: %s: Can't enable MSI. "
- "Device already has MSI-X vectors assigned\n",
- pci_name(dev));
- dev->irq = temp;
- return -EINVAL;
- }
- status = msi_capability_init(dev);
- if (!status) {
- if (!pos)
- nr_reserved_vectors--; /* Only MSI capable */
- else if (nr_msix_devices > 0)
- nr_msix_devices--; /* Both MSI and MSI-X capable,
- but choose enabling MSI */
+ status = pci_msi_check_device(dev, nvec, PCI_CAP_ID_MSI);
+ if (status)
+ return status;
+
+ WARN_ON(!!dev->msi_enabled);
+
+ /* Check whether driver already requested MSI-X irqs */
+ if (dev->msix_enabled) {
+ dev_info(&dev->dev, "can't enable MSI "
+ "(MSI-X already enabled)\n");
+ return -EINVAL;
}
+ status = msi_capability_init(dev, nvec);
return status;
}
+EXPORT_SYMBOL(pci_enable_msi_block);
+
+void pci_msi_shutdown(struct pci_dev *dev)
+{
+ struct msi_desc *desc;
+ u32 mask;
+ u16 ctrl;
+ unsigned pos;
+
+ if (!pci_msi_enable || !dev || !dev->msi_enabled)
+ return;
+
+ BUG_ON(list_empty(&dev->msi_list));
+ desc = list_first_entry(&dev->msi_list, struct msi_desc, list);
+ pos = desc->msi_attrib.pos;
+
+ msi_set_enable(dev, pos, 0);
+ pci_intx_for_msi(dev, 1);
+ dev->msi_enabled = 0;
+
+ pci_read_config_word(dev, pos + PCI_MSI_FLAGS, &ctrl);
+ mask = msi_capable_mask(ctrl);
+ msi_mask_irq(desc, mask, ~mask);
+
+ /* Restore dev->irq to its default pin-assertion irq */
+ dev->irq = desc->msi_attrib.default_irq;
+}
void pci_disable_msi(struct pci_dev* dev)
{
struct msi_desc *entry;
- int pos, default_vector;
- u16 control;
- unsigned long flags;
- if (!pci_msi_enable)
- return;
- if (!dev)
+ if (!pci_msi_enable || !dev || !dev->msi_enabled)
return;
- pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
- if (!pos)
- return;
+ pci_msi_shutdown(dev);
- pci_read_config_word(dev, msi_control_reg(pos), &control);
- if (!(control & PCI_MSI_FLAGS_ENABLE))
+ entry = list_entry(dev->msi_list.next, struct msi_desc, list);
+ if (entry->msi_attrib.is_msix)
return;
- spin_lock_irqsave(&msi_lock, flags);
- entry = msi_desc[dev->irq];
- if (!entry || !entry->dev || entry->msi_attrib.type != PCI_CAP_ID_MSI) {
- spin_unlock_irqrestore(&msi_lock, flags);
- return;
- }
- if (entry->msi_attrib.state) {
- spin_unlock_irqrestore(&msi_lock, flags);
- printk(KERN_WARNING "PCI: %s: pci_disable_msi() called without "
- "free_irq() on MSI vector %d\n",
- pci_name(dev), dev->irq);
- BUG_ON(entry->msi_attrib.state > 0);
- } else {
- vector_irq[dev->irq] = 0; /* free it */
- nr_released_vectors++;
- default_vector = entry->msi_attrib.default_vector;
- spin_unlock_irqrestore(&msi_lock, flags);
- /* Restore dev->irq to its default pin-assertion vector */
- dev->irq = default_vector;
- disable_msi_mode(dev, pci_find_capability(dev, PCI_CAP_ID_MSI),
- PCI_CAP_ID_MSI);
- }
+ msi_free_irqs(dev);
}
+EXPORT_SYMBOL(pci_disable_msi);
-static int msi_free_vector(struct pci_dev* dev, int vector, int reassign)
+static int msi_free_irqs(struct pci_dev* dev)
{
- struct msi_desc *entry;
- int head, entry_nr, type;
- void __iomem *base;
- unsigned long flags;
-
- msi_ops->teardown(vector);
+ struct msi_desc *entry, *tmp;
- spin_lock_irqsave(&msi_lock, flags);
- entry = msi_desc[vector];
- 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;
- msi_desc[entry->link.head]->link.tail = entry->link.tail;
- msi_desc[entry->link.tail]->link.head = entry->link.head;
- entry->dev = NULL;
- if (!reassign) {
- vector_irq[vector] = 0;
- nr_released_vectors++;
+ list_for_each_entry(entry, &dev->msi_list, list) {
+ int i, nvec;
+ if (!entry->irq)
+ continue;
+ nvec = 1 << entry->msi_attrib.multiple;
+ for (i = 0; i < nvec; i++)
+ BUG_ON(irq_has_action(entry->irq + i));
}
- msi_desc[vector] = NULL;
- spin_unlock_irqrestore(&msi_lock, flags);
-
- kmem_cache_free(msi_cachep, entry);
-
- if (type == PCI_CAP_ID_MSIX) {
- if (!reassign)
- writel(1, base +
- 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
- iounmap(base);
+
+ arch_teardown_msi_irqs(dev);
+
+ list_for_each_entry_safe(entry, tmp, &dev->msi_list, list) {
+ if (entry->msi_attrib.is_msix) {
+ msix_mask_irq(entry, 1);
+ if (list_is_last(&entry->list, &dev->msi_list))
+ iounmap(entry->mask_base);
}
+ list_del(&entry->list);
+ kfree(entry);
}
return 0;
}
-static int reroute_msix_table(int head, struct msix_entry *entries, int *nvec)
+/**
+ * pci_msix_table_size - return the number of device's MSI-X table entries
+ * @dev: pointer to the pci_dev data structure of MSI-X device function
+ */
+int pci_msix_table_size(struct pci_dev *dev)
{
- int vector = head, tail = 0;
- int i, j = 0, nr_entries = 0;
- void __iomem *base;
- unsigned long flags;
-
- spin_lock_irqsave(&msi_lock, flags);
- while (head != tail) {
- nr_entries++;
- tail = msi_desc[vector]->link.tail;
- if (entries[0].entry == msi_desc[vector]->msi_attrib.entry_nr)
- j = vector;
- vector = tail;
- }
- if (*nvec > nr_entries) {
- spin_unlock_irqrestore(&msi_lock, flags);
- *nvec = nr_entries;
- return -EINVAL;
- }
- vector = ((j > 0) ? j : head);
- for (i = 0; i < *nvec; i++) {
- j = msi_desc[vector]->msi_attrib.entry_nr;
- msi_desc[vector]->msi_attrib.state = 0; /* Mark it not active */
- vector_irq[vector] = -1; /* Mark it busy */
- nr_released_vectors--;
- entries[i].vector = vector;
- if (j != (entries + i)->entry) {
- base = msi_desc[vector]->mask_base;
- msi_desc[vector]->msi_attrib.entry_nr =
- (entries + i)->entry;
- writel( readl(base + j * PCI_MSIX_ENTRY_SIZE +
- PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET), base +
- (entries + i)->entry * PCI_MSIX_ENTRY_SIZE +
- PCI_MSIX_ENTRY_LOWER_ADDR_OFFSET);
- writel( readl(base + j * PCI_MSIX_ENTRY_SIZE +
- PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET), base +
- (entries + i)->entry * PCI_MSIX_ENTRY_SIZE +
- PCI_MSIX_ENTRY_UPPER_ADDR_OFFSET);
- writel( (readl(base + j * PCI_MSIX_ENTRY_SIZE +
- PCI_MSIX_ENTRY_DATA_OFFSET) & 0xff00) | vector,
- base + (entries+i)->entry*PCI_MSIX_ENTRY_SIZE +
- PCI_MSIX_ENTRY_DATA_OFFSET);
- }
- vector = msi_desc[vector]->link.tail;
- }
- spin_unlock_irqrestore(&msi_lock, flags);
+ int pos;
+ u16 control;
- return 0;
+ pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
+ if (!pos)
+ return 0;
+
+ pci_read_config_word(dev, msi_control_reg(pos), &control);
+ return multi_msix_capable(control);
}
/**
* pci_enable_msix - configure device's MSI-X capability structure
* @dev: pointer to the pci_dev data structure of MSI-X device function
* @entries: pointer to an array of MSI-X entries
- * @nvec: number of MSI-X vectors requested for allocation by device driver
+ * @nvec: number of MSI-X irqs requested for allocation by device driver
*
* Setup the MSI-X capability structure of device function with the number
- * of requested vectors upon its software driver call to request for
+ * 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 vectors. A return of < 0 indicates a failure.
+ * 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 vectors available. Driver should use the returned value to re-send
- * its request.
+ * of irqs or MSI-X vectors available. Driver should use the returned value to
+ * re-send its request.
**/
int pci_enable_msix(struct pci_dev* dev, struct msix_entry *entries, int nvec)
{
- struct pci_bus *bus;
- int status, pos, nr_entries, free_vectors;
- int i, j, temp;
- u16 control;
- unsigned long flags;
+ int status, nr_entries;
+ int i, j;
- if (!pci_msi_enable || !dev || !entries)
+ if (!entries)
return -EINVAL;
- if (dev->no_msi)
- return -EINVAL;
-
- for (bus = dev->bus; bus; bus = bus->parent)
- if (bus->bus_flags & PCI_BUS_FLAGS_NO_MSI)
- return -EINVAL;
-
- status = msi_init();
- if (status < 0)
+ status = pci_msi_check_device(dev, nvec, PCI_CAP_ID_MSIX);
+ if (status)
return status;
- pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
- if (!pos)
- return -EINVAL;
-
- pci_read_config_word(dev, msi_control_reg(pos), &control);
- if (control & PCI_MSIX_FLAGS_ENABLE)
- return -EINVAL; /* Already in MSI-X mode */
-
- nr_entries = multi_msix_capable(control);
+ nr_entries = pci_msix_table_size(dev);
if (nvec > nr_entries)
- return -EINVAL;
+ return nr_entries;
/* Check for any invalid entries */
for (i = 0; i < nvec; i++) {
return -EINVAL; /* duplicate entry */
}
}
- temp = dev->irq;
- if (!msi_lookup_vector(dev, PCI_CAP_ID_MSIX)) {
- /* Lookup Sucess */
- nr_entries = nvec;
- /* Reroute MSI-X table */
- if (reroute_msix_table(dev->irq, entries, &nr_entries)) {
- /* #requested > #previous-assigned */
- dev->irq = temp;
- return nr_entries;
- }
- dev->irq = temp;
- enable_msi_mode(dev, pos, PCI_CAP_ID_MSIX);
- return 0;
- }
- /* Check whether driver already requested for MSI vector */
- if (pci_find_capability(dev, PCI_CAP_ID_MSI) > 0 &&
- !msi_lookup_vector(dev, PCI_CAP_ID_MSI)) {
- printk(KERN_INFO "PCI: %s: Can't enable MSI-X. "
- "Device already has an MSI vector assigned\n",
- pci_name(dev));
- dev->irq = temp;
- return -EINVAL;
- }
+ WARN_ON(!!dev->msix_enabled);
- spin_lock_irqsave(&msi_lock, flags);
- /*
- * 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) {
- if (free_vectors > 0)
- return free_vectors;
- else
- return -EBUSY;
+ /* Check whether driver already requested for MSI irq */
+ if (dev->msi_enabled) {
+ dev_info(&dev->dev, "can't enable MSI-X "
+ "(MSI IRQ already assigned)\n");
+ return -EINVAL;
}
-
status = msix_capability_init(dev, entries, nvec);
- if (!status && nr_msix_devices > 0)
- nr_msix_devices--;
-
return status;
}
+EXPORT_SYMBOL(pci_enable_msix);
-void pci_disable_msix(struct pci_dev* dev)
+static void msix_free_all_irqs(struct pci_dev *dev)
{
- int pos, temp;
- u16 control;
-
- if (!pci_msi_enable)
- return;
- if (!dev)
- return;
+ msi_free_irqs(dev);
+}
- pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
- if (!pos)
+void pci_msix_shutdown(struct pci_dev* dev)
+{
+ if (!pci_msi_enable || !dev || !dev->msix_enabled)
return;
- pci_read_config_word(dev, msi_control_reg(pos), &control);
- if (!(control & PCI_MSIX_FLAGS_ENABLE))
+ msix_set_enable(dev, 0);
+ pci_intx_for_msi(dev, 1);
+ dev->msix_enabled = 0;
+}
+void pci_disable_msix(struct pci_dev* dev)
+{
+ if (!pci_msi_enable || !dev || !dev->msix_enabled)
return;
- temp = dev->irq;
- if (!msi_lookup_vector(dev, PCI_CAP_ID_MSIX)) {
- int state, vector, head, tail = 0, warning = 0;
- unsigned long flags;
-
- vector = head = dev->irq;
- spin_lock_irqsave(&msi_lock, flags);
- while (head != tail) {
- state = msi_desc[vector]->msi_attrib.state;
- if (state)
- warning = 1;
- else {
- vector_irq[vector] = 0; /* free it */
- nr_released_vectors++;
- }
- tail = msi_desc[vector]->link.tail;
- vector = tail;
- }
- spin_unlock_irqrestore(&msi_lock, flags);
- if (warning) {
- dev->irq = temp;
- printk(KERN_WARNING "PCI: %s: pci_disable_msix() called without "
- "free_irq() on all MSI-X vectors\n",
- pci_name(dev));
- BUG_ON(warning > 0);
- } else {
- dev->irq = temp;
- disable_msi_mode(dev,
- pci_find_capability(dev, PCI_CAP_ID_MSIX),
- PCI_CAP_ID_MSIX);
+ pci_msix_shutdown(dev);
- }
- }
+ msix_free_all_irqs(dev);
}
+EXPORT_SYMBOL(pci_disable_msix);
/**
- * 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 function
- * is hot-removed. All previous assigned MSI/MSI-X vectors, if
+ * 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)
{
- int state, pos, temp;
- unsigned long flags;
-
if (!pci_msi_enable || !dev)
return;
- temp = dev->irq; /* Save IOAPIC IRQ */
- pos = pci_find_capability(dev, PCI_CAP_ID_MSI);
- if (pos > 0 && !msi_lookup_vector(dev, PCI_CAP_ID_MSI)) {
- spin_lock_irqsave(&msi_lock, flags);
- state = msi_desc[dev->irq]->msi_attrib.state;
- spin_unlock_irqrestore(&msi_lock, flags);
- if (state) {
- printk(KERN_WARNING "PCI: %s: msi_remove_pci_irq_vectors() "
- "called without free_irq() on MSI vector %d\n",
- pci_name(dev), dev->irq);
- BUG_ON(state > 0);
- } else /* Release MSI vector assigned to this device */
- msi_free_vector(dev, dev->irq, 0);
- dev->irq = temp; /* Restore IOAPIC IRQ */
- }
- pos = pci_find_capability(dev, PCI_CAP_ID_MSIX);
- if (pos > 0 && !msi_lookup_vector(dev, PCI_CAP_ID_MSIX)) {
- int vector, head, tail = 0, warning = 0;
- void __iomem *base = NULL;
-
- vector = head = dev->irq;
- while (head != tail) {
- spin_lock_irqsave(&msi_lock, flags);
- state = msi_desc[vector]->msi_attrib.state;
- tail = msi_desc[vector]->link.tail;
- base = msi_desc[vector]->mask_base;
- spin_unlock_irqrestore(&msi_lock, flags);
- if (state)
- warning = 1;
- else if (vector != head) /* Release MSI-X vector */
- msi_free_vector(dev, vector, 0);
- vector = tail;
- }
- 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",
- pci_name(dev));
- BUG_ON(warning > 0);
- }
- dev->irq = temp; /* Restore IOAPIC IRQ */
- }
+ if (dev->msi_enabled)
+ msi_free_irqs(dev);
+
+ if (dev->msix_enabled)
+ msix_free_all_irqs(dev);
}
void pci_no_msi(void)
pci_msi_enable = 0;
}
-EXPORT_SYMBOL(pci_enable_msi);
-EXPORT_SYMBOL(pci_disable_msi);
-EXPORT_SYMBOL(pci_enable_msix);
-EXPORT_SYMBOL(pci_disable_msix);
+/**
+ * pci_msi_enabled - is MSI enabled?
+ *
+ * Returns true if MSI has not been disabled by the command-line option
+ * pci=nomsi.
+ **/
+int pci_msi_enabled(void)
+{
+ return pci_msi_enable;
+}
+EXPORT_SYMBOL(pci_msi_enabled);
+
+void pci_msi_init_pci_dev(struct pci_dev *dev)
+{
+ INIT_LIST_HEAD(&dev->msi_list);
+}