[PATCH] msi: refactor and move the msi irq_chip into the arch code

It turns out msi_ops was simply not enough to abstract the architecture
specific details of msi.  So I have moved the resposibility of constructing
the struct irq_chip to the architectures, and have two architecture specific
functions arch_setup_msi_irq, and arch_teardown_msi_irq.

For simple architectures those functions can do all of the work.  For
architectures with platform dependencies they can call into the appropriate
platform code.

With this msi.c is finally free of assuming you have an apic, and this
actually takes less code.

The helpers for the architecture specific code are declared in the linux/msi.h
to keep them separate from the msi functions used by drivers in linux/pci.h

Signed-off-by: Eric W. Biederman <ebiederm@xmission.com>
Cc: Ingo Molnar <mingo@elte.hu>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Andi Kleen <ak@suse.de>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Greg KH <greg@kroah.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

2 files changed, 120 insertions, 50 deletions

diff --git a/arch/i386/kernel/io_apic.c b/arch/i386/kernel/io_apic.c
index 100406b453b8..5a1252753dbb 100644
--- a/arch/i386/kernel/io_apic.c
+++ b/arch/i386/kernel/io_apic.c
@@ -32,6 +32,7 @@
 #include <linux/module.h>
 #include <linux/sysdev.h>
 #include <linux/pci.h>
+#include <linux/msi.h>
 
 #include <asm/io.h>
 #include <asm/smp.h>
@@ -2455,11 +2456,8 @@ void destroy_irq(unsigned int irq)
  * MSI mesage composition
  */
 #ifdef CONFIG_PCI_MSI
-static int msi_msg_setup(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg)
+static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg)
 {
-	/* For now always this code always uses physical delivery
-	 * mode.
-	 */
 	int vector;
 	unsigned dest;
 
@@ -2489,34 +2487,71 @@ static int msi_msg_setup(struct pci_dev *pdev, unsigned int irq, struct msi_msg
 	return vector;
 }
 
-static void msi_msg_teardown(unsigned int irq)
-{
-	return;
-}
-
-static void msi_msg_set_affinity(unsigned int irq, cpumask_t mask, struct msi_msg *msg)
+#ifdef CONFIG_SMP
+static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 {
+	struct msi_msg msg;
+	unsigned int dest;
+	cpumask_t tmp;
 	int vector;
-	unsigned dest;
+
+	cpus_and(tmp, mask, cpu_online_map);
+	if (cpus_empty(tmp))
+		tmp = TARGET_CPUS;
 
 	vector = assign_irq_vector(irq);
-	if (vector > 0) {
-		dest = cpu_mask_to_apicid(mask);
+	if (vector < 0)
+		return;
 
-		msg->data &= ~MSI_DATA_VECTOR_MASK;
-		msg->data |= MSI_DATA_VECTOR(vector);
-		msg->address_lo &= ~MSI_ADDR_DEST_ID_MASK;
-		msg->address_lo |= MSI_ADDR_DEST_ID(dest);
-	}
+	dest = cpu_mask_to_apicid(mask);
+
+	read_msi_msg(irq, &msg);
+
+	msg.data &= ~MSI_DATA_VECTOR_MASK;
+	msg.data |= MSI_DATA_VECTOR(vector);
+	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
+	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+
+	write_msi_msg(irq, &msg);
+	set_native_irq_info(irq, mask);
 }
+#endif /* CONFIG_SMP */
 
-struct msi_ops arch_msi_ops = {
-	.needs_64bit_address = 0,
-	.setup = msi_msg_setup,
-	.teardown = msi_msg_teardown,
-	.target = msi_msg_set_affinity,
+/*
+ * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices,
+ * which implement the MSI or MSI-X Capability Structure.
+ */
+static struct irq_chip msi_chip = {
+	.name		= "PCI-MSI",
+	.unmask		= unmask_msi_irq,
+	.mask		= mask_msi_irq,
+	.ack		= ack_ioapic_irq,
+#ifdef CONFIG_SMP
+	.set_affinity	= set_msi_irq_affinity,
+#endif
+	.retrigger	= ioapic_retrigger_irq,
 };
 
+int arch_setup_msi_irq(unsigned int irq, struct pci_dev *dev)
+{
+	struct msi_msg msg;
+	int ret;
+	ret = msi_compose_msg(dev, irq, &msg);
+	if (ret < 0)
+		return ret;
+
+	write_msi_msg(irq, &msg);
+
+	set_irq_chip_and_handler(irq, &msi_chip, handle_edge_irq);
+
+	return 0;
+}
+
+void arch_teardown_msi_irq(unsigned int irq)
+{
+	return;
+}
+
 #endif /* CONFIG_PCI_MSI */
 
 /*
diff --git a/arch/x86_64/kernel/io_apic.c b/arch/x86_64/kernel/io_apic.c
index 31c270fee337..e55028fba942 100644
--- a/arch/x86_64/kernel/io_apic.c
+++ b/arch/x86_64/kernel/io_apic.c
@@ -30,6 +30,7 @@
 #include <linux/mc146818rtc.h>
 #include <linux/acpi.h>
 #include <linux/sysdev.h>
+#include <linux/msi.h>
 #ifdef CONFIG_ACPI
 #include <acpi/acpi_bus.h>
 #endif
@@ -1701,11 +1702,8 @@ void destroy_irq(unsigned int irq)
  * MSI mesage composition
  */
 #ifdef CONFIG_PCI_MSI
-static int msi_msg_setup(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg)
+static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq, struct msi_msg *msg)
 {
-	/* For now always this code always uses physical delivery
-	 * mode.
-	 */
 	int vector;
 	unsigned dest;
 
@@ -1739,39 +1737,76 @@ static int msi_msg_setup(struct pci_dev *pdev, unsigned int irq, struct msi_msg
 	return vector;
 }
 
-static void msi_msg_teardown(unsigned int irq)
-{
-	return;
-}
-
-static void msi_msg_set_affinity(unsigned int irq, cpumask_t mask, struct msi_msg *msg)
+#ifdef CONFIG_SMP
+static void set_msi_irq_affinity(unsigned int irq, cpumask_t mask)
 {
+	struct msi_msg msg;
+	unsigned int dest;
+	cpumask_t tmp;
 	int vector;
-	unsigned dest;
+
+	cpus_and(tmp, mask, cpu_online_map);
+	if (cpus_empty(tmp))
+		tmp = TARGET_CPUS;
+
+	cpus_and(mask, tmp, CPU_MASK_ALL);
 
 	vector = assign_irq_vector(irq, mask);
-	if (vector > 0) {
-		cpumask_t tmp;
+	if (vector < 0)
+		return;
 
-		cpus_clear(tmp);
-		cpu_set(vector >> 8, tmp);
-		dest = cpu_mask_to_apicid(tmp);
+	cpus_clear(tmp);
+	cpu_set(vector >> 8, tmp);
+	dest = cpu_mask_to_apicid(tmp);
 
-		msg->data &= ~MSI_DATA_VECTOR_MASK;
-		msg->data |= MSI_DATA_VECTOR(vector);
-		msg->address_lo &= ~MSI_ADDR_DEST_ID_MASK;
-		msg->address_lo |= MSI_ADDR_DEST_ID(dest);
-	}
+	read_msi_msg(irq, &msg);
+
+	msg.data &= ~MSI_DATA_VECTOR_MASK;
+	msg.data |= MSI_DATA_VECTOR(vector);
+	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
+	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
+
+	write_msi_msg(irq, &msg);
+	set_native_irq_info(irq, mask);
 }
+#endif /* CONFIG_SMP */
 
-struct msi_ops arch_msi_ops = {
-	.needs_64bit_address = 0,
-	.setup = msi_msg_setup,
-	.teardown = msi_msg_teardown,
-	.target = msi_msg_set_affinity,
+/*
+ * IRQ Chip for MSI PCI/PCI-X/PCI-Express Devices,
+ * which implement the MSI or MSI-X Capability Structure.
+ */
+static struct irq_chip msi_chip = {
+	.name		= "PCI-MSI",
+	.unmask		= unmask_msi_irq,
+	.mask		= mask_msi_irq,
+	.ack		= ack_apic_edge,
+#ifdef CONFIG_SMP
+	.set_affinity	= set_msi_irq_affinity,
+#endif
+	.retrigger	= ioapic_retrigger_irq,
 };
 
-#endif
+int arch_setup_msi_irq(unsigned int irq, struct pci_dev *dev)
+{
+	struct msi_msg msg;
+	int ret;
+	ret = msi_compose_msg(dev, irq, &msg);
+	if (ret < 0)
+		return ret;
+
+	write_msi_msg(irq, &msg);
+
+	set_irq_chip_and_handler(irq, &msi_chip, handle_edge_irq);
+
+	return 0;
+}
+
+void arch_teardown_msi_irq(unsigned int irq)
+{
+	return;
+}
+
+#endif /* CONFIG_PCI_MSI */
 
 /*
  * Hypertransport interrupt support