Merge branch 'irq-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip

* 'irq-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip: (96 commits)
  apic, x86: Use BIOS settings for IBS and MCE threshold interrupt LVT offsets
  apic, x86: Check if EILVT APIC registers are available (AMD only)
  x86: ioapic: Call free_irte only if interrupt remapping enabled
  arm: Use ARCH_IRQ_INIT_FLAGS
  genirq, ARM: Fix boot on ARM platforms
  genirq: Fix CONFIG_GENIRQ_NO_DEPRECATED=y build
  x86: Switch sparse_irq allocations to GFP_KERNEL
  genirq: Switch sparse_irq allocator to GFP_KERNEL
  genirq: Make sparse_lock a mutex
  x86: lguest: Use new irq allocator
  genirq: Remove the now unused sparse irq leftovers
  genirq: Sanitize dynamic irq handling
  genirq: Remove arch_init_chip_data()
  x86: xen: Sanitise sparse_irq handling
  x86: Use sane enumeration
  x86: uv: Clean up the direct access to irq_desc
  x86: Make io_apic.c local functions static
  genirq: Remove irq_2_iommu
  x86: Speed up the irq_remapped check in hot pathes
  intr_remap: Simplify the code further
  ...

Fix up trivial conflicts in arch/x86/Kconfig

Documentation/DocBook/genericirq.tmpl

@@ -28,7 +28,7 @@
   </authorgroup>
 
   <copyright>
-   <year>2005-2006</year>
+   <year>2005-2010</year>
    <holder>Thomas Gleixner</holder>
   </copyright>
   <copyright>
@@ -100,6 +100,10 @@
 	  <listitem><para>Edge type</para></listitem>
 	  <listitem><para>Simple type</para></listitem>
 	</itemizedlist>
+	During the implementation we identified another type:
+	<itemizedlist>
+	  <listitem><para>Fast EOI type</para></listitem>
+	</itemizedlist>
 	In the SMP world of the __do_IRQ() super-handler another type
 	was identified:
 	<itemizedlist>
@@ -153,6 +157,7 @@
 	is still available. This leads to a kind of duality for the time
 	being. Over time the new model should be used in more and more
 	architectures, as it enables smaller and cleaner IRQ subsystems.
+	It's deprecated for three years now and about to be removed.
 	</para>
   </chapter>
   <chapter id="bugs">
@@ -217,6 +222,7 @@
 	  <itemizedlist>
 	  <listitem><para>handle_level_irq</para></listitem>
 	  <listitem><para>handle_edge_irq</para></listitem>
+	  <listitem><para>handle_fasteoi_irq</para></listitem>
 	  <listitem><para>handle_simple_irq</para></listitem>
 	  <listitem><para>handle_percpu_irq</para></listitem>
 	  </itemizedlist>
@@ -233,33 +239,33 @@
 		are used by the default flow implementations.
 		The following helper functions are implemented (simplified excerpt):
 		<programlisting>
-default_enable(irq)
+default_enable(struct irq_data *data)
 {
-	desc->chip->unmask(irq);
+	desc->chip->irq_unmask(data);
 }
 
-default_disable(irq)
+default_disable(struct irq_data *data)
 {
-	if (!delay_disable(irq))
-		desc->chip->mask(irq);
+	if (!delay_disable(data))
+		desc->chip->irq_mask(data);
 }
 
-default_ack(irq)
+default_ack(struct irq_data *data)
 {
-	chip->ack(irq);
+	chip->irq_ack(data);
 }
 
-default_mask_ack(irq)
+default_mask_ack(struct irq_data *data)
 {
-	if (chip->mask_ack) {
-		chip->mask_ack(irq);
+	if (chip->irq_mask_ack) {
+		chip->irq_mask_ack(data);
 	} else {
-		chip->mask(irq);
-		chip->ack(irq);
+		chip->irq_mask(data);
+		chip->irq_ack(data);
 	}
 }
 
-noop(irq)
+noop(struct irq_data *data))
 {
 }
 
@@ -278,12 +284,27 @@ noop(irq)
 		<para>
 		The following control flow is implemented (simplified excerpt):
 		<programlisting>
-desc->chip->start();
+desc->chip->irq_mask();
 handle_IRQ_event(desc->action);
-desc->chip->end();
+desc->chip->irq_unmask();
 		</programlisting>
 		</para>
-   	    </sect3>
+	    </sect3>
+	    <sect3 id="Default_FASTEOI_IRQ_flow_handler">
+		<title>Default Fast EOI IRQ flow handler</title>
+		<para>
+		handle_fasteoi_irq provides a generic implementation
+		for interrupts, which only need an EOI at the end of
+		the handler
+		</para>
+		<para>
+		The following control flow is implemented (simplified excerpt):
+		<programlisting>
+handle_IRQ_event(desc->action);
+desc->chip->irq_eoi();
+		</programlisting>
+		</para>
+	    </sect3>
 	    <sect3 id="Default_Edge_IRQ_flow_handler">
 	 	<title>Default Edge IRQ flow handler</title>
 		<para>
@@ -294,20 +315,19 @@ desc->chip->end();
 		The following control flow is implemented (simplified excerpt):
 		<programlisting>
 if (desc->status &amp; running) {
-	desc->chip->hold();
+	desc->chip->irq_mask();
 	desc->status |= pending | masked;
 	return;
 }
-desc->chip->start();
+desc->chip->irq_ack();
 desc->status |= running;
 do {
 	if (desc->status &amp; masked)
-		desc->chip->enable();
+		desc->chip->irq_unmask();
 	desc->status &amp;= ~pending;
 	handle_IRQ_event(desc->action);
 } while (status &amp; pending);
 desc->status &amp;= ~running;
-desc->chip->end();
 		</programlisting>
 		</para>
    	    </sect3>
@@ -342,9 +362,9 @@ handle_IRQ_event(desc->action);
 		<para>
 		The following control flow is implemented (simplified excerpt):
 		<programlisting>
-desc->chip->start();
 handle_IRQ_event(desc->action);
-desc->chip->end();
+if (desc->chip->irq_eoi)
+        desc->chip->irq_eoi();
 		</programlisting>
 		</para>
    	    </sect3>
@@ -375,8 +395,7 @@ desc->chip->end();
 	mechanism. (It's necessary to enable CONFIG_HARDIRQS_SW_RESEND when
 	you want to use the delayed interrupt disable feature and your
 	hardware is not capable of retriggering	an interrupt.)
-	The delayed interrupt disable can be runtime enabled, per interrupt,
-	by setting the IRQ_DELAYED_DISABLE flag in the irq_desc status field.
+	The delayed interrupt disable is not configurable.
 	</para>
 	</sect2>
     </sect1>
@@ -387,13 +406,13 @@ desc->chip->end();
 	contains all the direct chip relevant functions, which
 	can be utilized by the irq flow implementations.
 	  <itemizedlist>
-	  <listitem><para>ack()</para></listitem>
-	  <listitem><para>mask_ack() - Optional, recommended for performance</para></listitem>
-	  <listitem><para>mask()</para></listitem>
-	  <listitem><para>unmask()</para></listitem>
-	  <listitem><para>retrigger() - Optional</para></listitem>
-	  <listitem><para>set_type() - Optional</para></listitem>
-	  <listitem><para>set_wake() - Optional</para></listitem>
+	  <listitem><para>irq_ack()</para></listitem>
+	  <listitem><para>irq_mask_ack() - Optional, recommended for performance</para></listitem>
+	  <listitem><para>irq_mask()</para></listitem>
+	  <listitem><para>irq_unmask()</para></listitem>
+	  <listitem><para>irq_retrigger() - Optional</para></listitem>
+	  <listitem><para>irq_set_type() - Optional</para></listitem>
+	  <listitem><para>irq_set_wake() - Optional</para></listitem>
 	  </itemizedlist>
 	These primitives are strictly intended to mean what they say: ack means
 	ACK, masking means masking of an IRQ line, etc. It is up to the flow
@@ -458,6 +477,7 @@ desc->chip->end();
      <para>
      This chapter contains the autogenerated documentation of the internal functions.
      </para>
+!Ikernel/irq/irqdesc.c
 !Ikernel/irq/handle.c
 !Ikernel/irq/chip.c
   </chapter>

MAINTAINERS

@@ -3241,6 +3241,12 @@ F:	drivers/net/irda/
 F:	include/net/irda/
 F:	net/irda/
 
+IRQ SUBSYSTEM
+M:	Thomas Gleixner <tglx@linutronix.de>
+S:	Maintained
+T:	git git://git.kernel.org/pub/scm/linux/kernel/git/tip/linux-2.6-tip.git irq/core
+F:	kernel/irq/
+
 ISAPNP
 M:	Jaroslav Kysela <perex@perex.cz>
 S:	Maintained

arch/arm/include/asm/hw_irq.h

@@ -24,4 +24,6 @@ void set_irq_flags(unsigned int irq, unsigned int flags);
 #define IRQF_PROBE	(1 << 1)
 #define IRQF_NOAUTOEN	(1 << 2)
 
+#define ARCH_IRQ_INIT_FLAGS	(IRQ_NOREQUEST | IRQ_NOPROBE)
+
 #endif

arch/arm/kernel/irq.c

@@ -154,14 +154,6 @@ void set_irq_flags(unsigned int irq, unsigned int iflags)
 
 void __init init_IRQ(void)
 {
-	struct irq_desc *desc;
-	int irq;
-
-	for (irq = 0; irq < nr_irqs; irq++) {
-		desc = irq_to_desc_alloc_node(irq, 0);
-		desc->status |= IRQ_NOREQUEST | IRQ_NOPROBE;
-	}
-
 	init_arch_irq();
 }
 
@@ -169,7 +161,7 @@ void __init init_IRQ(void)
 int __init arch_probe_nr_irqs(void)
 {
 	nr_irqs = arch_nr_irqs ? arch_nr_irqs : NR_IRQS;
-	return 0;
+	return nr_irqs;
 }
 #endif
 

arch/arm/mach-bcmring/irq.c

@@ -67,21 +67,21 @@ static void bcmring_unmask_irq2(unsigned int irq)
 }
 
 static struct irq_chip bcmring_irq0_chip = {
-	.typename = "ARM-INTC0",
+	.name = "ARM-INTC0",
 	.ack = bcmring_mask_irq0,
 	.mask = bcmring_mask_irq0,	/* mask a specific interrupt, blocking its delivery. */
 	.unmask = bcmring_unmask_irq0,	/* unmaks an interrupt */
 };
 
 static struct irq_chip bcmring_irq1_chip = {
-	.typename = "ARM-INTC1",
+	.name = "ARM-INTC1",
 	.ack = bcmring_mask_irq1,
 	.mask = bcmring_mask_irq1,
 	.unmask = bcmring_unmask_irq1,
 };
 
 static struct irq_chip bcmring_irq2_chip = {
-	.typename = "ARM-SINTC",
+	.name = "ARM-SINTC",
 	.ack = bcmring_mask_irq2,
 	.mask = bcmring_mask_irq2,
 	.unmask = bcmring_unmask_irq2,

arch/arm/mach-iop13xx/msi.c

@@ -164,10 +164,10 @@ static void iop13xx_msi_nop(unsigned int irq)
 static struct irq_chip iop13xx_msi_chip = {
 	.name = "PCI-MSI",
 	.ack = iop13xx_msi_nop,
-	.enable = unmask_msi_irq,
-	.disable = mask_msi_irq,
-	.mask = mask_msi_irq,
-	.unmask = unmask_msi_irq,
+	.irq_enable = unmask_msi_irq,
+	.irq_disable = mask_msi_irq,
+	.irq_mask = mask_msi_irq,
+	.irq_unmask = unmask_msi_irq,
 };
 
 int arch_setup_msi_irq(struct pci_dev *pdev, struct msi_desc *desc)

arch/ia64/kernel/msi_ia64.c

@@ -104,8 +104,8 @@ static int ia64_msi_retrigger_irq(unsigned int irq)
  */
 static struct irq_chip ia64_msi_chip = {
 	.name		= "PCI-MSI",
-	.mask		= mask_msi_irq,
-	.unmask		= unmask_msi_irq,
+	.irq_mask	= mask_msi_irq,
+	.irq_unmask	= unmask_msi_irq,
 	.ack		= ia64_ack_msi_irq,
 #ifdef CONFIG_SMP
 	.set_affinity	= ia64_set_msi_irq_affinity,
@@ -160,8 +160,8 @@ static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 
 static struct irq_chip dmar_msi_type = {
 	.name = "DMAR_MSI",
-	.unmask = dmar_msi_unmask,
-	.mask = dmar_msi_mask,
+	.irq_unmask = dmar_msi_unmask,
+	.irq_mask = dmar_msi_mask,
 	.ack = ia64_ack_msi_irq,
 #ifdef CONFIG_SMP
 	.set_affinity = dmar_msi_set_affinity,

arch/ia64/sn/kernel/msi_sn.c

@@ -228,8 +228,8 @@ static int sn_msi_retrigger_irq(unsigned int irq)
 
 static struct irq_chip sn_msi_chip = {
 	.name		= "PCI-MSI",
-	.mask		= mask_msi_irq,
-	.unmask		= unmask_msi_irq,
+	.irq_mask	= mask_msi_irq,
+	.irq_unmask	= unmask_msi_irq,
 	.ack		= sn_ack_msi_irq,
 #ifdef CONFIG_SMP
 	.set_affinity	= sn_set_msi_irq_affinity,

arch/m32r/kernel/irq.c

@@ -51,7 +51,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
-		seq_printf(p, " %14s", irq_desc[i].chip->typename);
+		seq_printf(p, " %14s", irq_desc[i].chip->name);
 		seq_printf(p, "  %s", action->name);
 
 		for (action=action->next; action; action = action->next)

arch/m32r/platforms/m32104ut/setup.c

@@ -65,7 +65,7 @@ static void shutdown_m32104ut_irq(unsigned int irq)
 
 static struct irq_chip m32104ut_irq_type =
 {
-	.typename = "M32104UT-IRQ",
+	.name = "M32104UT-IRQ",
 	.startup = startup_m32104ut_irq,
 	.shutdown = shutdown_m32104ut_irq,
 	.enable = enable_m32104ut_irq,

arch/m32r/platforms/m32700ut/setup.c

@@ -71,7 +71,7 @@ static void shutdown_m32700ut_irq(unsigned int irq)
 
 static struct irq_chip m32700ut_irq_type =
 {
-	.typename = "M32700UT-IRQ",
+	.name = "M32700UT-IRQ",
 	.startup = startup_m32700ut_irq,
 	.shutdown = shutdown_m32700ut_irq,
 	.enable = enable_m32700ut_irq,
@@ -148,7 +148,7 @@ static void shutdown_m32700ut_pld_irq(unsigned int irq)
 
 static struct irq_chip m32700ut_pld_irq_type =
 {
-	.typename = "M32700UT-PLD-IRQ",
+	.name = "M32700UT-PLD-IRQ",
 	.startup = startup_m32700ut_pld_irq,
 	.shutdown = shutdown_m32700ut_pld_irq,
 	.enable = enable_m32700ut_pld_irq,
@@ -217,7 +217,7 @@ static void shutdown_m32700ut_lanpld_irq(unsigned int irq)
 
 static struct irq_chip m32700ut_lanpld_irq_type =
 {
-	.typename = "M32700UT-PLD-LAN-IRQ",
+	.name = "M32700UT-PLD-LAN-IRQ",
 	.startup = startup_m32700ut_lanpld_irq,
 	.shutdown = shutdown_m32700ut_lanpld_irq,
 	.enable = enable_m32700ut_lanpld_irq,
@@ -286,7 +286,7 @@ static void shutdown_m32700ut_lcdpld_irq(unsigned int irq)
 
 static struct irq_chip m32700ut_lcdpld_irq_type =
 {
-	.typename = "M32700UT-PLD-LCD-IRQ",
+	.name = "M32700UT-PLD-LCD-IRQ",
 	.startup = startup_m32700ut_lcdpld_irq,
 	.shutdown = shutdown_m32700ut_lcdpld_irq,
 	.enable = enable_m32700ut_lcdpld_irq,

arch/m32r/platforms/mappi/setup.c

@@ -65,7 +65,7 @@ static void shutdown_mappi_irq(unsigned int irq)
 
 static struct irq_chip mappi_irq_type =
 {
-	.typename = "MAPPI-IRQ",
+	.name = "MAPPI-IRQ",
 	.startup = startup_mappi_irq,
 	.shutdown = shutdown_mappi_irq,
 	.enable = enable_mappi_irq,

arch/m32r/platforms/mappi2/setup.c

@@ -72,7 +72,7 @@ static void shutdown_mappi2_irq(unsigned int irq)
 
 static struct irq_chip mappi2_irq_type =
 {
-	.typename = "MAPPI2-IRQ",
+	.name = "MAPPI2-IRQ",
 	.startup = startup_mappi2_irq,
 	.shutdown = shutdown_mappi2_irq,
 	.enable = enable_mappi2_irq,

arch/m32r/platforms/mappi3/setup.c

@@ -72,7 +72,7 @@ static void shutdown_mappi3_irq(unsigned int irq)
 
 static struct irq_chip mappi3_irq_type =
 {
-	.typename = "MAPPI3-IRQ",
+	.name = "MAPPI3-IRQ",
 	.startup = startup_mappi3_irq,
 	.shutdown = shutdown_mappi3_irq,
 	.enable = enable_mappi3_irq,

arch/m32r/platforms/oaks32r/setup.c

@@ -63,7 +63,7 @@ static void shutdown_oaks32r_irq(unsigned int irq)
 
 static struct irq_chip oaks32r_irq_type =
 {
-	.typename = "OAKS32R-IRQ",
+	.name = "OAKS32R-IRQ",
 	.startup = startup_oaks32r_irq,
 	.shutdown = shutdown_oaks32r_irq,
 	.enable = enable_oaks32r_irq,

arch/m32r/platforms/opsput/setup.c

@@ -72,7 +72,7 @@ static void shutdown_opsput_irq(unsigned int irq)
 
 static struct irq_chip opsput_irq_type =
 {
-	.typename = "OPSPUT-IRQ",
+	.name = "OPSPUT-IRQ",
 	.startup = startup_opsput_irq,
 	.shutdown = shutdown_opsput_irq,
 	.enable = enable_opsput_irq,
@@ -149,7 +149,7 @@ static void shutdown_opsput_pld_irq(unsigned int irq)
 
 static struct irq_chip opsput_pld_irq_type =
 {
-	.typename = "OPSPUT-PLD-IRQ",
+	.name = "OPSPUT-PLD-IRQ",
 	.startup = startup_opsput_pld_irq,
 	.shutdown = shutdown_opsput_pld_irq,
 	.enable = enable_opsput_pld_irq,
@@ -218,7 +218,7 @@ static void shutdown_opsput_lanpld_irq(unsigned int irq)
 
 static struct irq_chip opsput_lanpld_irq_type =
 {
-	.typename = "OPSPUT-PLD-LAN-IRQ",
+	.name = "OPSPUT-PLD-LAN-IRQ",
 	.startup = startup_opsput_lanpld_irq,
 	.shutdown = shutdown_opsput_lanpld_irq,
 	.enable = enable_opsput_lanpld_irq,

arch/m32r/platforms/usrv/setup.c

@@ -63,7 +63,7 @@ static void shutdown_mappi_irq(unsigned int irq)
 
 static struct irq_chip mappi_irq_type =
 {
-	.typename = "M32700-IRQ",
+	.name = "M32700-IRQ",
 	.startup = startup_mappi_irq,
 	.shutdown = shutdown_mappi_irq,
 	.enable = enable_mappi_irq,
@@ -136,7 +136,7 @@ static void shutdown_m32700ut_pld_irq(unsigned int irq)
 
 static struct irq_chip m32700ut_pld_irq_type =
 {
-	.typename = "USRV-PLD-IRQ",
+	.name = "USRV-PLD-IRQ",
 	.startup = startup_m32700ut_pld_irq,
 	.shutdown = shutdown_m32700ut_pld_irq,
 	.enable = enable_m32700ut_pld_irq,

arch/powerpc/platforms/cell/axon_msi.c

@@ -310,9 +310,9 @@ static void axon_msi_teardown_msi_irqs(struct pci_dev *dev)
 }
 
 static struct irq_chip msic_irq_chip = {
-	.mask		= mask_msi_irq,
-	.unmask		= unmask_msi_irq,
-	.shutdown	= unmask_msi_irq,
+	.irq_mask	= mask_msi_irq,
+	.irq_unmask	= unmask_msi_irq,
+	.irq_shutdown	= mask_msi_irq,
 	.name		= "AXON-MSI",
 };
 

arch/powerpc/platforms/pseries/xics.c

@@ -243,7 +243,7 @@ static unsigned int xics_startup(unsigned int virq)
 	 * at that level, so we do it here by hand.
 	 */
 	if (irq_to_desc(virq)->msi_desc)
-		unmask_msi_irq(virq);
+		unmask_msi_irq(irq_get_irq_data(virq));
 
 	/* unmask it */
 	xics_unmask_irq(virq);

arch/powerpc/sysdev/fsl_msi.c

@@ -51,8 +51,8 @@ static void fsl_msi_end_irq(unsigned int virq)
 }
 
 static struct irq_chip fsl_msi_chip = {
-	.mask		= mask_msi_irq,
-	.unmask		= unmask_msi_irq,
+	.irq_mask	= mask_msi_irq,
+	.irq_unmask	= unmask_msi_irq,
 	.ack		= fsl_msi_end_irq,
 	.name		= "FSL-MSI",
 };

arch/powerpc/sysdev/mpic_pasemi_msi.c

@@ -39,24 +39,24 @@
 static struct mpic *msi_mpic;
 
 
-static void mpic_pasemi_msi_mask_irq(unsigned int irq)
+static void mpic_pasemi_msi_mask_irq(struct irq_data *data)
 {
-	pr_debug("mpic_pasemi_msi_mask_irq %d\n", irq);
-	mask_msi_irq(irq);
-	mpic_mask_irq(irq);
+	pr_debug("mpic_pasemi_msi_mask_irq %d\n", data->irq);
+	mask_msi_irq(data);
+	mpic_mask_irq(data->irq);
 }
 
-static void mpic_pasemi_msi_unmask_irq(unsigned int irq)
+static void mpic_pasemi_msi_unmask_irq(struct irq_data *data)
 {
-	pr_debug("mpic_pasemi_msi_unmask_irq %d\n", irq);
-	mpic_unmask_irq(irq);
-	unmask_msi_irq(irq);
+	pr_debug("mpic_pasemi_msi_unmask_irq %d\n", data->irq);
+	mpic_unmask_irq(data->irq);
+	unmask_msi_irq(data);
 }
 
 static struct irq_chip mpic_pasemi_msi_chip = {
-	.shutdown	= mpic_pasemi_msi_mask_irq,
-	.mask		= mpic_pasemi_msi_mask_irq,
-	.unmask		= mpic_pasemi_msi_unmask_irq,
+	.irq_shutdown	= mpic_pasemi_msi_mask_irq,
+	.irq_mask	= mpic_pasemi_msi_mask_irq,
+	.irq_unmask	= mpic_pasemi_msi_unmask_irq,
 	.eoi		= mpic_end_irq,
 	.set_type	= mpic_set_irq_type,
 	.set_affinity	= mpic_set_affinity,

arch/powerpc/sysdev/mpic_u3msi.c

@@ -23,22 +23,22 @@
 /* A bit ugly, can we get this from the pci_dev somehow? */
 static struct mpic *msi_mpic;
 
-static void mpic_u3msi_mask_irq(unsigned int irq)
+static void mpic_u3msi_mask_irq(struct irq_data *data)
 {
-	mask_msi_irq(irq);
-	mpic_mask_irq(irq);
+	mask_msi_irq(data);
+	mpic_mask_irq(data->irq);
 }
 
-static void mpic_u3msi_unmask_irq(unsigned int irq)
+static void mpic_u3msi_unmask_irq(struct irq_data *data)
 {
-	mpic_unmask_irq(irq);
-	unmask_msi_irq(irq);
+	mpic_unmask_irq(data->irq);
+	unmask_msi_irq(data);
 }
 
 static struct irq_chip mpic_u3msi_chip = {
-	.shutdown	= mpic_u3msi_mask_irq,
-	.mask		= mpic_u3msi_mask_irq,
-	.unmask		= mpic_u3msi_unmask_irq,
+	.irq_shutdown	= mpic_u3msi_mask_irq,
+	.irq_mask	= mpic_u3msi_mask_irq,
+	.irq_unmask	= mpic_u3msi_unmask_irq,
 	.eoi		= mpic_end_irq,
 	.set_type	= mpic_set_irq_type,
 	.set_affinity	= mpic_set_affinity,

arch/sh/kernel/irq.c

@@ -290,7 +290,7 @@ void __init init_IRQ(void)
 int __init arch_probe_nr_irqs(void)
 {
 	nr_irqs = sh_mv.mv_nr_irqs;
-	return 0;
+	return NR_IRQS_LEGACY;
 }
 #endif
 

arch/sparc/kernel/pci_msi.c

@@ -114,10 +114,10 @@ static void free_msi(struct pci_pbm_info *pbm, int msi_num)
 
 static struct irq_chip msi_irq = {
 	.name		= "PCI-MSI",
-	.mask		= mask_msi_irq,
-	.unmask		= unmask_msi_irq,
-	.enable		= unmask_msi_irq,
-	.disable	= mask_msi_irq,
+	.irq_mask	= mask_msi_irq,
+	.irq_unmask	= unmask_msi_irq,
+	.irq_enable	= unmask_msi_irq,
+	.irq_disable	= mask_msi_irq,
 	/* XXX affinity XXX */
 };
 

arch/tile/kernel/irq.c

@@ -208,7 +208,7 @@ static void tile_irq_chip_eoi(unsigned int irq)
 }
 
 static struct irq_chip tile_irq_chip = {
-	.typename = "tile_irq_chip",
+	.name = "tile_irq_chip",
 	.ack = tile_irq_chip_ack,
 	.eoi = tile_irq_chip_eoi,
 	.mask = tile_irq_chip_mask,
@@ -288,7 +288,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
-		seq_printf(p, " %14s", irq_desc[i].chip->typename);
+		seq_printf(p, " %14s", irq_desc[i].chip->name);
 		seq_printf(p, "  %s", action->name);
 
 		for (action = action->next; action; action = action->next)

arch/um/kernel/irq.c

@@ -46,7 +46,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
-		seq_printf(p, " %14s", irq_desc[i].chip->typename);
+		seq_printf(p, " %14s", irq_desc[i].chip->name);
 		seq_printf(p, "  %s", action->name);
 
 		for (action=action->next; action; action = action->next)
@@ -369,7 +369,7 @@ static void dummy(unsigned int irq)
 
 /* This is used for everything else than the timer. */
 static struct irq_chip normal_irq_type = {
-	.typename = "SIGIO",
+	.name = "SIGIO",
 	.release = free_irq_by_irq_and_dev,
 	.disable = dummy,
 	.enable = dummy,
@@ -378,7 +378,7 @@ static struct irq_chip normal_irq_type = {
 };
 
 static struct irq_chip SIGVTALRM_irq_type = {
-	.typename = "SIGVTALRM",
+	.name = "SIGVTALRM",
 	.release = free_irq_by_irq_and_dev,
 	.shutdown = dummy, /* never called */
 	.disable = dummy,

arch/x86/Kconfig

@@ -63,6 +63,10 @@ config X86
 	select HAVE_USER_RETURN_NOTIFIER
 	select HAVE_ARCH_JUMP_LABEL
 	select HAVE_TEXT_POKE_SMP
+	select HAVE_GENERIC_HARDIRQS
+	select HAVE_SPARSE_IRQ
+	select GENERIC_IRQ_PROBE
+	select GENERIC_PENDING_IRQ if SMP
 
 config INSTRUCTION_DECODER
 	def_bool (KPROBES || PERF_EVENTS)
@@ -204,20 +208,6 @@ config HAVE_INTEL_TXT
 	def_bool y
 	depends on EXPERIMENTAL && DMAR && ACPI
 
-# Use the generic interrupt handling code in kernel/irq/:
-config GENERIC_HARDIRQS
-	def_bool y
-
-config GENERIC_HARDIRQS_NO__DO_IRQ
-       def_bool y
-
-config GENERIC_IRQ_PROBE
-	def_bool y
-
-config GENERIC_PENDING_IRQ
-	def_bool y
-	depends on GENERIC_HARDIRQS && SMP
-
 config USE_GENERIC_SMP_HELPERS
 	def_bool y
 	depends on SMP
@@ -300,23 +290,6 @@ config X86_X2APIC
 
 	  If you don't know what to do here, say N.
 
-config SPARSE_IRQ
-	bool "Support sparse irq numbering"
-	depends on PCI_MSI || HT_IRQ
-	---help---
-	  This enables support for sparse irqs. This is useful for distro
-	  kernels that want to define a high CONFIG_NR_CPUS value but still
-	  want to have low kernel memory footprint on smaller machines.
-
-	  ( Sparse IRQs can also be beneficial on NUMA boxes, as they spread
-	    out the irq_desc[] array in a more NUMA-friendly way. )
-
-	  If you don't know what to do here, say N.
-
-config NUMA_IRQ_DESC
-	def_bool y
-	depends on SPARSE_IRQ && NUMA
-
 config X86_MPPARSE
 	bool "Enable MPS table" if ACPI
 	default y

arch/x86/include/asm/apic.h

@@ -252,9 +252,7 @@ static inline int apic_is_clustered_box(void)
 }
 #endif
 
-extern u8 setup_APIC_eilvt_mce(u8 vector, u8 msg_type, u8 mask);
-extern u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask);
-
+extern int setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask);
 
 #else /* !CONFIG_X86_LOCAL_APIC */
 static inline void lapic_shutdown(void) { }

arch/x86/include/asm/apicdef.h

@@ -131,6 +131,7 @@
 #define APIC_EILVTn(n)	(0x500 + 0x10 * n)
 #define		APIC_EILVT_NR_AMD_K8	1	/* # of extended interrupts */
 #define		APIC_EILVT_NR_AMD_10H	4
+#define		APIC_EILVT_NR_MAX	APIC_EILVT_NR_AMD_10H
 #define		APIC_EILVT_LVTOFF(x)	(((x) >> 4) & 0xF)
 #define		APIC_EILVT_MSG_FIX	0x0
 #define		APIC_EILVT_MSG_SMI	0x2

arch/x86/include/asm/hpet.h

@@ -74,10 +74,12 @@ extern void hpet_disable(void);
 extern unsigned int hpet_readl(unsigned int a);
 extern void force_hpet_resume(void);
 
-extern void hpet_msi_unmask(unsigned int irq);
-extern void hpet_msi_mask(unsigned int irq);
-extern void hpet_msi_write(unsigned int irq, struct msi_msg *msg);
-extern void hpet_msi_read(unsigned int irq, struct msi_msg *msg);
+struct irq_data;
+extern void hpet_msi_unmask(struct irq_data *data);
+extern void hpet_msi_mask(struct irq_data *data);
+struct hpet_dev;
+extern void hpet_msi_write(struct hpet_dev *hdev, struct msi_msg *msg);
+extern void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg);
 
 #ifdef CONFIG_PCI_MSI
 extern int arch_setup_hpet_msi(unsigned int irq, unsigned int id);

arch/x86/include/asm/hw_irq.h

@@ -78,6 +78,13 @@ static inline void set_io_apic_irq_attr(struct io_apic_irq_attr *irq_attr,
 	irq_attr->polarity	= polarity;
 }
 
+struct irq_2_iommu {
+	struct intel_iommu *iommu;
+	u16 irte_index;
+	u16 sub_handle;
+	u8  irte_mask;
+};
+
 /*
  * This is performance-critical, we want to do it O(1)
  *
@@ -89,15 +96,17 @@ struct irq_cfg {
 	cpumask_var_t		old_domain;
 	u8			vector;
 	u8			move_in_progress : 1;
+#ifdef CONFIG_INTR_REMAP
+	struct irq_2_iommu	irq_2_iommu;
+#endif
 };
 
-extern struct irq_cfg *irq_cfg(unsigned int);
 extern int assign_irq_vector(int, struct irq_cfg *, const struct cpumask *);
 extern void send_cleanup_vector(struct irq_cfg *);
 
-struct irq_desc;
-extern unsigned int set_desc_affinity(struct irq_desc *, const struct cpumask *,
-				      unsigned int *dest_id);
+struct irq_data;
+int __ioapic_set_affinity(struct irq_data *, const struct cpumask *,
+			  unsigned int *dest_id);
 extern int IO_APIC_get_PCI_irq_vector(int bus, int devfn, int pin, struct io_apic_irq_attr *irq_attr);
 extern void setup_ioapic_dest(void);
 

arch/x86/include/asm/i8259.h

@@ -55,6 +55,8 @@ extern struct irq_chip i8259A_chip;
 struct legacy_pic {
 	int nr_legacy_irqs;
 	struct irq_chip *chip;
+	void (*mask)(unsigned int irq);
+	void (*unmask)(unsigned int irq);
 	void (*mask_all)(void);
 	void (*restore_mask)(void);
 	void (*init)(int auto_eoi);

arch/x86/include/asm/io_apic.h

@@ -170,12 +170,6 @@ extern int restore_IO_APIC_setup(struct IO_APIC_route_entry **ioapic_entries);
 
 extern void probe_nr_irqs_gsi(void);
 
-extern int setup_ioapic_entry(int apic, int irq,
-			      struct IO_APIC_route_entry *entry,
-			      unsigned int destination, int trigger,
-			      int polarity, int vector, int pin);
-extern void ioapic_write_entry(int apic, int pin,
-			       struct IO_APIC_route_entry e);
 extern void setup_ioapic_ids_from_mpc(void);
 
 struct mp_ioapic_gsi{

arch/x86/include/asm/irq_remapping.h

@@ -24,10 +24,18 @@ static inline void prepare_irte(struct irte *irte, int vector,
 	irte->dest_id = IRTE_DEST(dest);
 	irte->redir_hint = 1;
 }
+static inline bool irq_remapped(struct irq_cfg *cfg)
+{
+	return cfg->irq_2_iommu.iommu != NULL;
+}
 #else
 static void prepare_irte(struct irte *irte, int vector, unsigned int dest)
 {
 }
+static inline bool irq_remapped(struct irq_cfg *cfg)
+{
+	return false;
+}
 #endif
 
 #endif	/* _ASM_X86_IRQ_REMAPPING_H */

arch/x86/kernel/apb_timer.c

@@ -231,34 +231,6 @@ static void apbt_restart_clocksource(struct clocksource *cs)
 	apbt_start_counter(phy_cs_timer_id);
 }
 
-/* Setup IRQ routing via IOAPIC */
-#ifdef CONFIG_SMP
-static void apbt_setup_irq(struct apbt_dev *adev)
-{
-	struct irq_chip *chip;
-	struct irq_desc *desc;
-
-	/* timer0 irq has been setup early */
-	if (adev->irq == 0)
-		return;
-	desc = irq_to_desc(adev->irq);
-	chip = get_irq_chip(adev->irq);
-	disable_irq(adev->irq);
-	desc->status |= IRQ_MOVE_PCNTXT;
-	irq_set_affinity(adev->irq, cpumask_of(adev->cpu));
-	/* APB timer irqs are set up as mp_irqs, timer is edge triggerred */
-	set_irq_chip_and_handler_name(adev->irq, chip, handle_edge_irq, "edge");
-	enable_irq(adev->irq);
-	if (system_state == SYSTEM_BOOTING)
-		if (request_irq(adev->irq, apbt_interrupt_handler,
-				IRQF_TIMER | IRQF_DISABLED | IRQF_NOBALANCING,
-				adev->name, adev)) {
-			printk(KERN_ERR "Failed request IRQ for APBT%d\n",
-			       adev->num);
-		}
-}
-#endif
-
 static void apbt_enable_int(int n)
 {
 	unsigned long ctrl = apbt_readl(n, APBTMR_N_CONTROL);
@@ -334,6 +306,27 @@ static int __init apbt_clockevent_register(void)
 }
 
 #ifdef CONFIG_SMP
+
+static void apbt_setup_irq(struct apbt_dev *adev)
+{
+	/* timer0 irq has been setup early */
+	if (adev->irq == 0)
+		return;
+
+	if (system_state == SYSTEM_BOOTING) {
+		irq_modify_status(adev->irq, 0, IRQ_MOVE_PCNTXT);
+		/* APB timer irqs are set up as mp_irqs, timer is edge type */
+		__set_irq_handler(adev->irq, handle_edge_irq, 0, "edge");
+		if (request_irq(adev->irq, apbt_interrupt_handler,
+				IRQF_TIMER | IRQF_DISABLED | IRQF_NOBALANCING,
+				adev->name, adev)) {
+			printk(KERN_ERR "Failed request IRQ for APBT%d\n",
+			       adev->num);
+		}
+	} else
+		enable_irq(adev->irq);
+}
+
 /* Should be called with per cpu */
 void apbt_setup_secondary_clock(void)
 {
@@ -389,10 +382,11 @@ static int apbt_cpuhp_notify(struct notifier_block *n,
 
 	switch (action & 0xf) {
 	case CPU_DEAD:
+		disable_irq(adev->irq);
 		apbt_disable_int(cpu);
-		if (system_state == SYSTEM_RUNNING)
+		if (system_state == SYSTEM_RUNNING) {
 			pr_debug("skipping APBT CPU %lu offline\n", cpu);
-		else if (adev) {
+		} else if (adev) {
 			pr_debug("APBT clockevent for cpu %lu offline\n", cpu);
 			free_irq(adev->irq, adev);
 		}

arch/x86/kernel/apic/apic.c

@@ -52,6 +52,7 @@
 #include <asm/mce.h>
 #include <asm/kvm_para.h>
 #include <asm/tsc.h>
+#include <asm/atomic.h>
 
 unsigned int num_processors;
 
@@ -370,38 +371,87 @@ static void __setup_APIC_LVTT(unsigned int clocks, int oneshot, int irqen)
 }
 
 /*
- * Setup extended LVT, AMD specific (K8, family 10h)
+ * Setup extended LVT, AMD specific
  *
- * Vector mappings are hard coded. On K8 only offset 0 (APIC500) and
- * MCE interrupts are supported. Thus MCE offset must be set to 0.
+ * Software should use the LVT offsets the BIOS provides.  The offsets
+ * are determined by the subsystems using it like those for MCE
+ * threshold or IBS.  On K8 only offset 0 (APIC500) and MCE interrupts
+ * are supported. Beginning with family 10h at least 4 offsets are
+ * available.
  *
- * If mask=1, the LVT entry does not generate interrupts while mask=0
- * enables the vector. See also the BKDGs.
+ * Since the offsets must be consistent for all cores, we keep track
+ * of the LVT offsets in software and reserve the offset for the same
+ * vector also to be used on other cores. An offset is freed by
+ * setting the entry to APIC_EILVT_MASKED.
+ *
+ * If the BIOS is right, there should be no conflicts. Otherwise a
+ * "[Firmware Bug]: ..." error message is generated. However, if
+ * software does not properly determines the offsets, it is not
+ * necessarily a BIOS bug.
  */
 
-#define APIC_EILVT_LVTOFF_MCE 0
-#define APIC_EILVT_LVTOFF_IBS 1
+static atomic_t eilvt_offsets[APIC_EILVT_NR_MAX];
 
-static void setup_APIC_eilvt(u8 lvt_off, u8 vector, u8 msg_type, u8 mask)
+static inline int eilvt_entry_is_changeable(unsigned int old, unsigned int new)
 {
-	unsigned long reg = (lvt_off << 4) + APIC_EILVTn(0);
-	unsigned int  v   = (mask << 16) | (msg_type << 8) | vector;
-
-	apic_write(reg, v);
+	return (old & APIC_EILVT_MASKED)
+		|| (new == APIC_EILVT_MASKED)
+		|| ((new & ~APIC_EILVT_MASKED) == old);
 }
 
-u8 setup_APIC_eilvt_mce(u8 vector, u8 msg_type, u8 mask)
+static unsigned int reserve_eilvt_offset(int offset, unsigned int new)
 {
-	setup_APIC_eilvt(APIC_EILVT_LVTOFF_MCE, vector, msg_type, mask);
-	return APIC_EILVT_LVTOFF_MCE;
+	unsigned int rsvd;			/* 0: uninitialized */
+
+	if (offset >= APIC_EILVT_NR_MAX)
+		return ~0;
+
+	rsvd = atomic_read(&eilvt_offsets[offset]) & ~APIC_EILVT_MASKED;
+	do {
+		if (rsvd &&
+		    !eilvt_entry_is_changeable(rsvd, new))
+			/* may not change if vectors are different */
+			return rsvd;
+		rsvd = atomic_cmpxchg(&eilvt_offsets[offset], rsvd, new);
+	} while (rsvd != new);
+
+	return new;
 }
 
-u8 setup_APIC_eilvt_ibs(u8 vector, u8 msg_type, u8 mask)
+/*
+ * If mask=1, the LVT entry does not generate interrupts while mask=0
+ * enables the vector. See also the BKDGs.
+ */
+
+int setup_APIC_eilvt(u8 offset, u8 vector, u8 msg_type, u8 mask)
 {
-	setup_APIC_eilvt(APIC_EILVT_LVTOFF_IBS, vector, msg_type, mask);
-	return APIC_EILVT_LVTOFF_IBS;
+	unsigned long reg = APIC_EILVTn(offset);
+	unsigned int new, old, reserved;
+
+	new = (mask << 16) | (msg_type << 8) | vector;
+	old = apic_read(reg);
+	reserved = reserve_eilvt_offset(offset, new);
+
+	if (reserved != new) {
+		pr_err(FW_BUG "cpu %d, try to setup vector 0x%x, but "
+		       "vector 0x%x was already reserved by another core, "
+		       "APIC%lX=0x%x\n",
+		       smp_processor_id(), new, reserved, reg, old);
+		return -EINVAL;
+	}
+
+	if (!eilvt_entry_is_changeable(old, new)) {
+		pr_err(FW_BUG "cpu %d, try to setup vector 0x%x but "
+		       "register already in use, APIC%lX=0x%x\n",
+		       smp_processor_id(), new, reg, old);
+		return -EBUSY;
+	}
+
+	apic_write(reg, new);
+
+	return 0;
 }
-EXPORT_SYMBOL_GPL(setup_APIC_eilvt_ibs);
+EXPORT_SYMBOL_GPL(setup_APIC_eilvt);
 
 /*
  * Program the next event, relative to now

arch/x86/kernel/apic/io_apic.c

@@ -131,13 +131,9 @@ struct irq_pin_list {
 	struct irq_pin_list *next;
 };
 
-static struct irq_pin_list *get_one_free_irq_2_pin(int node)
+static struct irq_pin_list *alloc_irq_pin_list(int node)
 {
-	struct irq_pin_list *pin;
-
-	pin = kzalloc_node(sizeof(*pin), GFP_ATOMIC, node);
-
-	return pin;
+	return kzalloc_node(sizeof(struct irq_pin_list), GFP_KERNEL, node);
 }
 
 /* irq_cfg is indexed by the sum of all RTEs in all I/O APICs. */
@@ -150,10 +146,7 @@ static struct irq_cfg irq_cfgx[NR_IRQS];
 int __init arch_early_irq_init(void)
 {
 	struct irq_cfg *cfg;
-	struct irq_desc *desc;
-	int count;
-	int node;
-	int i;
+	int count, node, i;
 
 	if (!legacy_pic->nr_legacy_irqs) {
 		nr_irqs_gsi = 0;
@@ -164,11 +157,13 @@ int __init arch_early_irq_init(void)
 	count = ARRAY_SIZE(irq_cfgx);
 	node = cpu_to_node(0);
 
+	/* Make sure the legacy interrupts are marked in the bitmap */
+	irq_reserve_irqs(0, legacy_pic->nr_legacy_irqs);
+
 	for (i = 0; i < count; i++) {
-		desc = irq_to_desc(i);
-		desc->chip_data = &cfg[i];
-		zalloc_cpumask_var_node(&cfg[i].domain, GFP_NOWAIT, node);
-		zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_NOWAIT, node);
+		set_irq_chip_data(i, &cfg[i]);
+		zalloc_cpumask_var_node(&cfg[i].domain, GFP_KERNEL, node);
+		zalloc_cpumask_var_node(&cfg[i].old_domain, GFP_KERNEL, node);
 		/*
 		 * For legacy IRQ's, start with assigning irq0 to irq15 to
 		 * IRQ0_VECTOR to IRQ15_VECTOR on cpu 0.
@@ -183,170 +178,88 @@ int __init arch_early_irq_init(void)
 }
 
 #ifdef CONFIG_SPARSE_IRQ
-struct irq_cfg *irq_cfg(unsigned int irq)
+static struct irq_cfg *irq_cfg(unsigned int irq)
 {
-	struct irq_cfg *cfg = NULL;
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-	if (desc)
-		cfg = desc->chip_data;
-
-	return cfg;
+	return get_irq_chip_data(irq);
 }
 
-static struct irq_cfg *get_one_free_irq_cfg(int node)
+static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node)
 {
 	struct irq_cfg *cfg;
 
-	cfg = kzalloc_node(sizeof(*cfg), GFP_ATOMIC, node);
-	if (cfg) {
-		if (!zalloc_cpumask_var_node(&cfg->domain, GFP_ATOMIC, node)) {
-			kfree(cfg);
-			cfg = NULL;
-		} else if (!zalloc_cpumask_var_node(&cfg->old_domain,
-							  GFP_ATOMIC, node)) {
-			free_cpumask_var(cfg->domain);
-			kfree(cfg);
-			cfg = NULL;
-		}
-	}
-
+	cfg = kzalloc_node(sizeof(*cfg), GFP_KERNEL, node);
+	if (!cfg)
+		return NULL;
+	if (!zalloc_cpumask_var_node(&cfg->domain, GFP_KERNEL, node))
+		goto out_cfg;
+	if (!zalloc_cpumask_var_node(&cfg->old_domain, GFP_KERNEL, node))
+		goto out_domain;
 	return cfg;
+out_domain:
+	free_cpumask_var(cfg->domain);
+out_cfg:
+	kfree(cfg);
+	return NULL;
 }
 
-int arch_init_chip_data(struct irq_desc *desc, int node)
-{
-	struct irq_cfg *cfg;
-
-	cfg = desc->chip_data;
-	if (!cfg) {
-		desc->chip_data = get_one_free_irq_cfg(node);
-		if (!desc->chip_data) {
-			printk(KERN_ERR "can not alloc irq_cfg\n");
-			BUG_ON(1);
-		}
-	}
-
-	return 0;
-}
-
-/* for move_irq_desc */
-static void
-init_copy_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg, int node)
+static void free_irq_cfg(unsigned int at, struct irq_cfg *cfg)
 {
-	struct irq_pin_list *old_entry, *head, *tail, *entry;
-
-	cfg->irq_2_pin = NULL;
-	old_entry = old_cfg->irq_2_pin;
-	if (!old_entry)
-		return;
-
-	entry = get_one_free_irq_2_pin(node);
-	if (!entry)
+	if (!cfg)
 		return;
+	set_irq_chip_data(at, NULL);
+	free_cpumask_var(cfg->domain);
+	free_cpumask_var(cfg->old_domain);
+	kfree(cfg);
+}
 
-	entry->apic	= old_entry->apic;
-	entry->pin	= old_entry->pin;
-	head		= entry;
-	tail		= entry;
-	old_entry	= old_entry->next;
-	while (old_entry) {
-		entry = get_one_free_irq_2_pin(node);
-		if (!entry) {
-			entry = head;
-			while (entry) {
-				head = entry->next;
-				kfree(entry);
-				entry = head;
-			}
-			/* still use the old one */
-			return;
-		}
-		entry->apic	= old_entry->apic;
-		entry->pin	= old_entry->pin;
-		tail->next	= entry;
-		tail		= entry;
-		old_entry	= old_entry->next;
-	}
+#else
 
-	tail->next = NULL;
-	cfg->irq_2_pin = head;
+struct irq_cfg *irq_cfg(unsigned int irq)
+{
+	return irq < nr_irqs ? irq_cfgx + irq : NULL;
 }
 
-static void free_irq_2_pin(struct irq_cfg *old_cfg, struct irq_cfg *cfg)
+static struct irq_cfg *alloc_irq_cfg(unsigned int irq, int node)
 {
-	struct irq_pin_list *entry, *next;
-
-	if (old_cfg->irq_2_pin == cfg->irq_2_pin)
-		return;
+	return irq_cfgx + irq;
+}
 
-	entry = old_cfg->irq_2_pin;
+static inline void free_irq_cfg(unsigned int at, struct irq_cfg *cfg) { }
 
-	while (entry) {
-		next = entry->next;
-		kfree(entry);
-		entry = next;
-	}
-	old_cfg->irq_2_pin = NULL;
-}
+#endif
 
-void arch_init_copy_chip_data(struct irq_desc *old_desc,
-				 struct irq_desc *desc, int node)
+static struct irq_cfg *alloc_irq_and_cfg_at(unsigned int at, int node)
 {
+	int res = irq_alloc_desc_at(at, node);
 	struct irq_cfg *cfg;
-	struct irq_cfg *old_cfg;
-
-	cfg = get_one_free_irq_cfg(node);
 
-	if (!cfg)
-		return;
-
-	desc->chip_data = cfg;
-
-	old_cfg = old_desc->chip_data;
-
-	cfg->vector = old_cfg->vector;
-	cfg->move_in_progress = old_cfg->move_in_progress;
-	cpumask_copy(cfg->domain, old_cfg->domain);
-	cpumask_copy(cfg->old_domain, old_cfg->old_domain);
-
-	init_copy_irq_2_pin(old_cfg, cfg, node);
-}
+	if (res < 0) {
+		if (res != -EEXIST)
+			return NULL;
+		cfg = get_irq_chip_data(at);
+		if (cfg)
+			return cfg;
+	}
 
-static void free_irq_cfg(struct irq_cfg *cfg)
-{
-	free_cpumask_var(cfg->domain);
-	free_cpumask_var(cfg->old_domain);
-	kfree(cfg);
+	cfg = alloc_irq_cfg(at, node);
+	if (cfg)
+		set_irq_chip_data(at, cfg);
+	else
+		irq_free_desc(at);
+	return cfg;
 }
 
-void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc)
+static int alloc_irq_from(unsigned int from, int node)
 {
-	struct irq_cfg *old_cfg, *cfg;
-
-	old_cfg = old_desc->chip_data;
-	cfg = desc->chip_data;
-
-	if (old_cfg == cfg)
-		return;
-
-	if (old_cfg) {
-		free_irq_2_pin(old_cfg, cfg);
-		free_irq_cfg(old_cfg);
-		old_desc->chip_data = NULL;
-	}
+	return irq_alloc_desc_from(from, node);
 }
-/* end for move_irq_desc */
 
-#else
-struct irq_cfg *irq_cfg(unsigned int irq)
+static void free_irq_at(unsigned int at, struct irq_cfg *cfg)
 {
-	return irq < nr_irqs ? irq_cfgx + irq : NULL;
+	free_irq_cfg(at, cfg);
+	irq_free_desc(at);
 }
 
-#endif
-
 struct io_apic {
 	unsigned int index;
 	unsigned int unused[3];
@@ -451,7 +364,7 @@ __ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
 	io_apic_write(apic, 0x10 + 2*pin, eu.w1);
 }
 
-void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
+static void ioapic_write_entry(int apic, int pin, struct IO_APIC_route_entry e)
 {
 	unsigned long flags;
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
@@ -481,7 +394,7 @@ static void ioapic_mask_entry(int apic, int pin)
  * fast in the common case, and fast for shared ISA-space IRQs.
  */
 static int
-add_pin_to_irq_node_nopanic(struct irq_cfg *cfg, int node, int apic, int pin)
+__add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
 {
 	struct irq_pin_list **last, *entry;
 
@@ -493,7 +406,7 @@ add_pin_to_irq_node_nopanic(struct irq_cfg *cfg, int node, int apic, int pin)
 		last = &entry->next;
 	}
 
-	entry = get_one_free_irq_2_pin(node);
+	entry = alloc_irq_pin_list(node);
 	if (!entry) {
 		printk(KERN_ERR "can not alloc irq_pin_list (%d,%d,%d)\n",
 				node, apic, pin);
@@ -508,7 +421,7 @@ add_pin_to_irq_node_nopanic(struct irq_cfg *cfg, int node, int apic, int pin)
 
 static void add_pin_to_irq_node(struct irq_cfg *cfg, int node, int apic, int pin)
 {
-	if (add_pin_to_irq_node_nopanic(cfg, node, apic, pin))
+	if (__add_pin_to_irq_node(cfg, node, apic, pin))
 		panic("IO-APIC: failed to add irq-pin. Can not proceed\n");
 }
 
@@ -571,11 +484,6 @@ static void __unmask_and_level_IO_APIC_irq(struct irq_pin_list *entry)
 			     IO_APIC_REDIR_LEVEL_TRIGGER, NULL);
 }
 
-static void __unmask_IO_APIC_irq(struct irq_cfg *cfg)
-{
-	io_apic_modify_irq(cfg, ~IO_APIC_REDIR_MASKED, 0, NULL);
-}
-
 static void io_apic_sync(struct irq_pin_list *entry)
 {
 	/*
@@ -587,44 +495,37 @@ static void io_apic_sync(struct irq_pin_list *entry)
 	readl(&io_apic->data);
 }
 
-static void __mask_IO_APIC_irq(struct irq_cfg *cfg)
+static void mask_ioapic(struct irq_cfg *cfg)
 {
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	io_apic_modify_irq(cfg, ~0, IO_APIC_REDIR_MASKED, &io_apic_sync);
+	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-static void mask_IO_APIC_irq_desc(struct irq_desc *desc)
+static void mask_ioapic_irq(struct irq_data *data)
 {
-	struct irq_cfg *cfg = desc->chip_data;
-	unsigned long flags;
-
-	BUG_ON(!cfg);
+	mask_ioapic(data->chip_data);
+}
 
-	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	__mask_IO_APIC_irq(cfg);
-	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
+static void __unmask_ioapic(struct irq_cfg *cfg)
+{
+	io_apic_modify_irq(cfg, ~IO_APIC_REDIR_MASKED, 0, NULL);
 }
 
-static void unmask_IO_APIC_irq_desc(struct irq_desc *desc)
+static void unmask_ioapic(struct irq_cfg *cfg)
 {
-	struct irq_cfg *cfg = desc->chip_data;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	__unmask_IO_APIC_irq(cfg);
+	__unmask_ioapic(cfg);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-static void mask_IO_APIC_irq(unsigned int irq)
+static void unmask_ioapic_irq(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	mask_IO_APIC_irq_desc(desc);
-}
-static void unmask_IO_APIC_irq(unsigned int irq)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	unmask_IO_APIC_irq_desc(desc);
+	unmask_ioapic(data->chip_data);
 }
 
 static void clear_IO_APIC_pin(unsigned int apic, unsigned int pin)
@@ -694,14 +595,14 @@ struct IO_APIC_route_entry **alloc_ioapic_entries(void)
 	struct IO_APIC_route_entry **ioapic_entries;
 
 	ioapic_entries = kzalloc(sizeof(*ioapic_entries) * nr_ioapics,
-				GFP_ATOMIC);
+				GFP_KERNEL);
 	if (!ioapic_entries)
 		return 0;
 
 	for (apic = 0; apic < nr_ioapics; apic++) {
 		ioapic_entries[apic] =
 			kzalloc(sizeof(struct IO_APIC_route_entry) *
-				nr_ioapic_registers[apic], GFP_ATOMIC);
+				nr_ioapic_registers[apic], GFP_KERNEL);
 		if (!ioapic_entries[apic])
 			goto nomem;
 	}
@@ -1259,7 +1160,6 @@ void __setup_vector_irq(int cpu)
 	/* Initialize vector_irq on a new cpu */
 	int irq, vector;
 	struct irq_cfg *cfg;
-	struct irq_desc *desc;
 
 	/*
 	 * vector_lock will make sure that we don't run into irq vector
@@ -1268,9 +1168,10 @@ void __setup_vector_irq(int cpu)
 	 */
 	raw_spin_lock(&vector_lock);
 	/* Mark the inuse vectors */
-	for_each_irq_desc(irq, desc) {
-		cfg = desc->chip_data;
-
+	for_each_active_irq(irq) {
+		cfg = get_irq_chip_data(irq);
+		if (!cfg)
+			continue;
 		/*
 		 * If it is a legacy IRQ handled by the legacy PIC, this cpu
 		 * will be part of the irq_cfg's domain.
@@ -1327,17 +1228,17 @@ static inline int IO_APIC_irq_trigger(int irq)
 }
 #endif
 
-static void ioapic_register_intr(int irq, struct irq_desc *desc, unsigned long trigger)
+static void ioapic_register_intr(unsigned int irq, unsigned long trigger)
 {
 
 	if ((trigger == IOAPIC_AUTO && IO_APIC_irq_trigger(irq)) ||
 	    trigger == IOAPIC_LEVEL)
-		desc->status |= IRQ_LEVEL;
+		irq_set_status_flags(irq, IRQ_LEVEL);
 	else
-		desc->status &= ~IRQ_LEVEL;
+		irq_clear_status_flags(irq, IRQ_LEVEL);
 
-	if (irq_remapped(irq)) {
-		desc->status |= IRQ_MOVE_PCNTXT;
+	if (irq_remapped(get_irq_chip_data(irq))) {
+		irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
 		if (trigger)
 			set_irq_chip_and_handler_name(irq, &ir_ioapic_chip,
 						      handle_fasteoi_irq,
@@ -1358,10 +1259,10 @@ static void ioapic_register_intr(int irq, struct irq_desc *desc, unsigned long t
 					      handle_edge_irq, "edge");
 }
 
-int setup_ioapic_entry(int apic_id, int irq,
-		       struct IO_APIC_route_entry *entry,
-		       unsigned int destination, int trigger,
-		       int polarity, int vector, int pin)
+static int setup_ioapic_entry(int apic_id, int irq,
+			      struct IO_APIC_route_entry *entry,
+			      unsigned int destination, int trigger,
+			      int polarity, int vector, int pin)
 {
 	/*
 	 * add it to the IO-APIC irq-routing table:
@@ -1417,18 +1318,14 @@ int setup_ioapic_entry(int apic_id, int irq,
 	return 0;
 }
 
-static void setup_IO_APIC_irq(int apic_id, int pin, unsigned int irq, struct irq_desc *desc,
-			      int trigger, int polarity)
+static void setup_ioapic_irq(int apic_id, int pin, unsigned int irq,
+			     struct irq_cfg *cfg, int trigger, int polarity)
 {
-	struct irq_cfg *cfg;
 	struct IO_APIC_route_entry entry;
 	unsigned int dest;
 
 	if (!IO_APIC_IRQ(irq))
 		return;
-
-	cfg = desc->chip_data;
-
 	/*
 	 * For legacy irqs, cfg->domain starts with cpu 0 for legacy
 	 * controllers like 8259. Now that IO-APIC can handle this irq, update
@@ -1457,9 +1354,9 @@ static void setup_IO_APIC_irq(int apic_id, int pin, unsigned int irq, struct irq
 		return;
 	}
 
-	ioapic_register_intr(irq, desc, trigger);
+	ioapic_register_intr(irq, trigger);
 	if (irq < legacy_pic->nr_legacy_irqs)
-		legacy_pic->chip->mask(irq);
+		legacy_pic->mask(irq);
 
 	ioapic_write_entry(apic_id, pin, entry);
 }
@@ -1470,11 +1367,9 @@ static struct {
 
 static void __init setup_IO_APIC_irqs(void)
 {
-	int apic_id, pin, idx, irq;
-	int notcon = 0;
-	struct irq_desc *desc;
-	struct irq_cfg *cfg;
+	int apic_id, pin, idx, irq, notcon = 0;
 	int node = cpu_to_node(0);
+	struct irq_cfg *cfg;
 
 	apic_printk(APIC_VERBOSE, KERN_DEBUG "init IO_APIC IRQs\n");
 
@@ -1511,19 +1406,17 @@ static void __init setup_IO_APIC_irqs(void)
 				apic->multi_timer_check(apic_id, irq))
 			continue;
 
-		desc = irq_to_desc_alloc_node(irq, node);
-		if (!desc) {
-			printk(KERN_INFO "can not get irq_desc for %d\n", irq);
+		cfg = alloc_irq_and_cfg_at(irq, node);
+		if (!cfg)
 			continue;
-		}
-		cfg = desc->chip_data;
+
 		add_pin_to_irq_node(cfg, node, apic_id, pin);
 		/*
 		 * don't mark it in pin_programmed, so later acpi could
 		 * set it correctly when irq < 16
 		 */
-		setup_IO_APIC_irq(apic_id, pin, irq, desc,
-				irq_trigger(idx), irq_polarity(idx));
+		setup_ioapic_irq(apic_id, pin, irq, cfg, irq_trigger(idx),
+				  irq_polarity(idx));
 	}
 
 	if (notcon)
@@ -1538,9 +1431,7 @@ static void __init setup_IO_APIC_irqs(void)
  */
 void setup_IO_APIC_irq_extra(u32 gsi)
 {
-	int apic_id = 0, pin, idx, irq;
-	int node = cpu_to_node(0);
-	struct irq_desc *desc;
+	int apic_id = 0, pin, idx, irq, node = cpu_to_node(0);
 	struct irq_cfg *cfg;
 
 	/*
@@ -1556,18 +1447,15 @@ void setup_IO_APIC_irq_extra(u32 gsi)
 		return;
 
 	irq = pin_2_irq(idx, apic_id, pin);
-#ifdef CONFIG_SPARSE_IRQ
-	desc = irq_to_desc(irq);
-	if (desc)
+
+	/* Only handle the non legacy irqs on secondary ioapics */
+	if (apic_id == 0 || irq < NR_IRQS_LEGACY)
 		return;
-#endif
-	desc = irq_to_desc_alloc_node(irq, node);
-	if (!desc) {
-		printk(KERN_INFO "can not get irq_desc for %d\n", irq);
+
+	cfg = alloc_irq_and_cfg_at(irq, node);
+	if (!cfg)
 		return;
-	}
 
-	cfg = desc->chip_data;
 	add_pin_to_irq_node(cfg, node, apic_id, pin);
 
 	if (test_bit(pin, mp_ioapic_routing[apic_id].pin_programmed)) {
@@ -1577,7 +1465,7 @@ void setup_IO_APIC_irq_extra(u32 gsi)
 	}
 	set_bit(pin, mp_ioapic_routing[apic_id].pin_programmed);
 
-	setup_IO_APIC_irq(apic_id, pin, irq, desc,
+	setup_ioapic_irq(apic_id, pin, irq, cfg,
 			irq_trigger(idx), irq_polarity(idx));
 }
 
@@ -1628,7 +1516,6 @@ __apicdebuginit(void) print_IO_APIC(void)
 	union IO_APIC_reg_03 reg_03;
 	unsigned long flags;
 	struct irq_cfg *cfg;
-	struct irq_desc *desc;
 	unsigned int irq;
 
 	printk(KERN_DEBUG "number of MP IRQ sources: %d.\n", mp_irq_entries);
@@ -1715,10 +1602,10 @@ __apicdebuginit(void) print_IO_APIC(void)
 	}
 	}
 	printk(KERN_DEBUG "IRQ to pin mappings:\n");
-	for_each_irq_desc(irq, desc) {
+	for_each_active_irq(irq) {
 		struct irq_pin_list *entry;
 
-		cfg = desc->chip_data;
+		cfg = get_irq_chip_data(irq);
 		if (!cfg)
 			continue;
 		entry = cfg->irq_2_pin;
@@ -2225,29 +2112,26 @@ static int __init timer_irq_works(void)
  * an edge even if it isn't on the 8259A...
  */
 
-static unsigned int startup_ioapic_irq(unsigned int irq)
+static unsigned int startup_ioapic_irq(struct irq_data *data)
 {
-	int was_pending = 0;
+	int was_pending = 0, irq = data->irq;
 	unsigned long flags;
-	struct irq_cfg *cfg;
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	if (irq < legacy_pic->nr_legacy_irqs) {
-		legacy_pic->chip->mask(irq);
+		legacy_pic->mask(irq);
 		if (legacy_pic->irq_pending(irq))
 			was_pending = 1;
 	}
-	cfg = irq_cfg(irq);
-	__unmask_IO_APIC_irq(cfg);
+	__unmask_ioapic(data->chip_data);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 
 	return was_pending;
 }
 
-static int ioapic_retrigger_irq(unsigned int irq)
+static int ioapic_retrigger_irq(struct irq_data *data)
 {
-
-	struct irq_cfg *cfg = irq_cfg(irq);
+	struct irq_cfg *cfg = data->chip_data;
 	unsigned long flags;
 
 	raw_spin_lock_irqsave(&vector_lock, flags);
@@ -2298,7 +2182,7 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq
 		 * With interrupt-remapping, destination information comes
 		 * from interrupt-remapping table entry.
 		 */
-		if (!irq_remapped(irq))
+		if (!irq_remapped(cfg))
 			io_apic_write(apic, 0x11 + pin*2, dest);
 		reg = io_apic_read(apic, 0x10 + pin*2);
 		reg &= ~IO_APIC_REDIR_VECTOR_MASK;
@@ -2308,65 +2192,46 @@ static void __target_IO_APIC_irq(unsigned int irq, unsigned int dest, struct irq
 }
 
 /*
- * Either sets desc->affinity to a valid value, and returns
+ * Either sets data->affinity to a valid value, and returns
  * ->cpu_mask_to_apicid of that in dest_id, or returns -1 and
- * leaves desc->affinity untouched.
+ * leaves data->affinity untouched.
  */
-unsigned int
-set_desc_affinity(struct irq_desc *desc, const struct cpumask *mask,
-		  unsigned int *dest_id)
+int __ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
+			  unsigned int *dest_id)
 {
-	struct irq_cfg *cfg;
-	unsigned int irq;
+	struct irq_cfg *cfg = data->chip_data;
 
 	if (!cpumask_intersects(mask, cpu_online_mask))
 		return -1;
 
-	irq = desc->irq;
-	cfg = desc->chip_data;
-	if (assign_irq_vector(irq, cfg, mask))
+	if (assign_irq_vector(data->irq, data->chip_data, mask))
 		return -1;
 
-	cpumask_copy(desc->affinity, mask);
+	cpumask_copy(data->affinity, mask);
 
-	*dest_id = apic->cpu_mask_to_apicid_and(desc->affinity, cfg->domain);
+	*dest_id = apic->cpu_mask_to_apicid_and(mask, cfg->domain);
 	return 0;
 }
 
 static int
-set_ioapic_affinity_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
+ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
+		    bool force)
 {
-	struct irq_cfg *cfg;
+	unsigned int dest, irq = data->irq;
 	unsigned long flags;
-	unsigned int dest;
-	unsigned int irq;
-	int ret = -1;
-
-	irq = desc->irq;
-	cfg = desc->chip_data;
+	int ret;
 
 	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	ret = set_desc_affinity(desc, mask, &dest);
+	ret = __ioapic_set_affinity(data, mask, &dest);
 	if (!ret) {
 		/* Only the high 8 bits are valid. */
 		dest = SET_APIC_LOGICAL_ID(dest);
-		__target_IO_APIC_irq(irq, dest, cfg);
+		__target_IO_APIC_irq(irq, dest, data->chip_data);
 	}
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
-
 	return ret;
 }
 
-static int
-set_ioapic_affinity_irq(unsigned int irq, const struct cpumask *mask)
-{
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-
-	return set_ioapic_affinity_irq_desc(desc, mask);
-}
-
 #ifdef CONFIG_INTR_REMAP
 
 /*
@@ -2381,24 +2246,21 @@ set_ioapic_affinity_irq(unsigned int irq, const struct cpumask *mask)
  * the interrupt-remapping table entry.
  */
 static int
-migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
+ir_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
+		       bool force)
 {
-	struct irq_cfg *cfg;
+	struct irq_cfg *cfg = data->chip_data;
+	unsigned int dest, irq = data->irq;
 	struct irte irte;
-	unsigned int dest;
-	unsigned int irq;
-	int ret = -1;
 
 	if (!cpumask_intersects(mask, cpu_online_mask))
-		return ret;
+		return -EINVAL;
 
-	irq = desc->irq;
 	if (get_irte(irq, &irte))
-		return ret;
+		return -EBUSY;
 
-	cfg = desc->chip_data;
 	if (assign_irq_vector(irq, cfg, mask))
-		return ret;
+		return -EBUSY;
 
 	dest = apic->cpu_mask_to_apicid_and(cfg->domain, mask);
 
@@ -2413,29 +2275,14 @@ migrate_ioapic_irq_desc(struct irq_desc *desc, const struct cpumask *mask)
 	if (cfg->move_in_progress)
 		send_cleanup_vector(cfg);
 
-	cpumask_copy(desc->affinity, mask);
-
+	cpumask_copy(data->affinity, mask);
 	return 0;
 }
 
-/*
- * Migrates the IRQ destination in the process context.
- */
-static int set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
-					    const struct cpumask *mask)
-{
-	return migrate_ioapic_irq_desc(desc, mask);
-}
-static int set_ir_ioapic_affinity_irq(unsigned int irq,
-				       const struct cpumask *mask)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	return set_ir_ioapic_affinity_irq_desc(desc, mask);
-}
 #else
-static inline int set_ir_ioapic_affinity_irq_desc(struct irq_desc *desc,
-						   const struct cpumask *mask)
+static inline int
+ir_ioapic_set_affinity(struct irq_data *data, const struct cpumask *mask,
+		       bool force)
 {
 	return 0;
 }
@@ -2497,10 +2344,8 @@ unlock:
 	irq_exit();
 }
 
-static void __irq_complete_move(struct irq_desc **descp, unsigned vector)
+static void __irq_complete_move(struct irq_cfg *cfg, unsigned vector)
 {
-	struct irq_desc *desc = *descp;
-	struct irq_cfg *cfg = desc->chip_data;
 	unsigned me;
 
 	if (likely(!cfg->move_in_progress))
@@ -2512,31 +2357,28 @@ static void __irq_complete_move(struct irq_desc **descp, unsigned vector)
 		send_cleanup_vector(cfg);
 }
 
-static void irq_complete_move(struct irq_desc **descp)
+static void irq_complete_move(struct irq_cfg *cfg)
 {
-	__irq_complete_move(descp, ~get_irq_regs()->orig_ax);
+	__irq_complete_move(cfg, ~get_irq_regs()->orig_ax);
 }
 
 void irq_force_complete_move(int irq)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg = desc->chip_data;
+	struct irq_cfg *cfg = get_irq_chip_data(irq);
 
 	if (!cfg)
 		return;
 
-	__irq_complete_move(&desc, cfg->vector);
+	__irq_complete_move(cfg, cfg->vector);
 }
 #else
-static inline void irq_complete_move(struct irq_desc **descp) {}
+static inline void irq_complete_move(struct irq_cfg *cfg) { }
 #endif
 
-static void ack_apic_edge(unsigned int irq)
+static void ack_apic_edge(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	irq_complete_move(&desc);
-	move_native_irq(irq);
+	irq_complete_move(data->chip_data);
+	move_native_irq(data->irq);
 	ack_APIC_irq();
 }
 
@@ -2558,10 +2400,12 @@ atomic_t irq_mis_count;
  * Otherwise, we simulate the EOI message manually by changing the trigger
  * mode to edge and then back to level, with RTE being masked during this.
 */
-static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
+static void eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
 {
 	struct irq_pin_list *entry;
+	unsigned long flags;
 
+	raw_spin_lock_irqsave(&ioapic_lock, flags);
 	for_each_irq_pin(entry, cfg->irq_2_pin) {
 		if (mp_ioapics[entry->apic].apicver >= 0x20) {
 			/*
@@ -2570,7 +2414,7 @@ static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
 			 * intr-remapping table entry. Hence for the io-apic
 			 * EOI we use the pin number.
 			 */
-			if (irq_remapped(irq))
+			if (irq_remapped(cfg))
 				io_apic_eoi(entry->apic, entry->pin);
 			else
 				io_apic_eoi(entry->apic, cfg->vector);
@@ -2579,36 +2423,22 @@ static void __eoi_ioapic_irq(unsigned int irq, struct irq_cfg *cfg)
 			__unmask_and_level_IO_APIC_irq(entry);
 		}
 	}
-}
-
-static void eoi_ioapic_irq(struct irq_desc *desc)
-{
-	struct irq_cfg *cfg;
-	unsigned long flags;
-	unsigned int irq;
-
-	irq = desc->irq;
-	cfg = desc->chip_data;
-
-	raw_spin_lock_irqsave(&ioapic_lock, flags);
-	__eoi_ioapic_irq(irq, cfg);
 	raw_spin_unlock_irqrestore(&ioapic_lock, flags);
 }
 
-static void ack_apic_level(unsigned int irq)
+static void ack_apic_level(struct irq_data *data)
 {
+	struct irq_cfg *cfg = data->chip_data;
+	int i, do_unmask_irq = 0, irq = data->irq;
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long v;
-	int i;
-	struct irq_cfg *cfg;
-	int do_unmask_irq = 0;
 
-	irq_complete_move(&desc);
+	irq_complete_move(cfg);
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	/* If we are moving the irq we need to mask it */
 	if (unlikely(desc->status & IRQ_MOVE_PENDING)) {
 		do_unmask_irq = 1;
-		mask_IO_APIC_irq_desc(desc);
+		mask_ioapic(cfg);
 	}
 #endif
 
@@ -2644,7 +2474,6 @@ static void ack_apic_level(unsigned int irq)
 	 * we use the above logic (mask+edge followed by unmask+level) from
 	 * Manfred Spraul to clear the remote IRR.
 	 */
-	cfg = desc->chip_data;
 	i = cfg->vector;
 	v = apic_read(APIC_TMR + ((i & ~0x1f) >> 1));
 
@@ -2664,7 +2493,7 @@ static void ack_apic_level(unsigned int irq)
 	if (!(v & (1 << (i & 0x1f)))) {
 		atomic_inc(&irq_mis_count);
 
-		eoi_ioapic_irq(desc);
+		eoi_ioapic_irq(irq, cfg);
 	}
 
 	/* Now we can move and renable the irq */
@@ -2695,61 +2524,57 @@ static void ack_apic_level(unsigned int irq)
 		 * accurate and is causing problems then it is a hardware bug
 		 * and you can go talk to the chipset vendor about it.
 		 */
-		cfg = desc->chip_data;
 		if (!io_apic_level_ack_pending(cfg))
 			move_masked_irq(irq);
-		unmask_IO_APIC_irq_desc(desc);
+		unmask_ioapic(cfg);
 	}
 }
 
 #ifdef CONFIG_INTR_REMAP
-static void ir_ack_apic_edge(unsigned int irq)
+static void ir_ack_apic_edge(struct irq_data *data)
 {
 	ack_APIC_irq();
 }
 
-static void ir_ack_apic_level(unsigned int irq)
+static void ir_ack_apic_level(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-
 	ack_APIC_irq();
-	eoi_ioapic_irq(desc);
+	eoi_ioapic_irq(data->irq, data->chip_data);
 }
 #endif /* CONFIG_INTR_REMAP */
 
 static struct irq_chip ioapic_chip __read_mostly = {
-	.name		= "IO-APIC",
-	.startup	= startup_ioapic_irq,
-	.mask		= mask_IO_APIC_irq,
-	.unmask		= unmask_IO_APIC_irq,
-	.ack		= ack_apic_edge,
-	.eoi		= ack_apic_level,
+	.name			= "IO-APIC",
+	.irq_startup		= startup_ioapic_irq,
+	.irq_mask		= mask_ioapic_irq,
+	.irq_unmask		= unmask_ioapic_irq,
+	.irq_ack		= ack_apic_edge,
+	.irq_eoi		= ack_apic_level,
 #ifdef CONFIG_SMP
-	.set_affinity	= set_ioapic_affinity_irq,
+	.irq_set_affinity	= ioapic_set_affinity,
 #endif
-	.retrigger	= ioapic_retrigger_irq,
+	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
 static struct irq_chip ir_ioapic_chip __read_mostly = {
-	.name		= "IR-IO-APIC",
-	.startup	= startup_ioapic_irq,
-	.mask		= mask_IO_APIC_irq,
-	.unmask		= unmask_IO_APIC_irq,
+	.name			= "IR-IO-APIC",
+	.irq_startup		= startup_ioapic_irq,
+	.irq_mask		= mask_ioapic_irq,
+	.irq_unmask		= unmask_ioapic_irq,
 #ifdef CONFIG_INTR_REMAP
-	.ack		= ir_ack_apic_edge,
-	.eoi		= ir_ack_apic_level,
+	.irq_ack		= ir_ack_apic_edge,
+	.irq_eoi		= ir_ack_apic_level,
 #ifdef CONFIG_SMP
-	.set_affinity	= set_ir_ioapic_affinity_irq,
+	.irq_set_affinity	= ir_ioapic_set_affinity,
 #endif
 #endif
-	.retrigger	= ioapic_retrigger_irq,
+	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
 static inline void init_IO_APIC_traps(void)
 {
-	int irq;
-	struct irq_desc *desc;
 	struct irq_cfg *cfg;
+	unsigned int irq;
 
 	/*
 	 * NOTE! The local APIC isn't very good at handling
@@ -2762,8 +2587,8 @@ static inline void init_IO_APIC_traps(void)
 	 * Also, we've got to be careful not to trash gate
 	 * 0x80, because int 0x80 is hm, kind of importantish. ;)
 	 */
-	for_each_irq_desc(irq, desc) {
-		cfg = desc->chip_data;
+	for_each_active_irq(irq) {
+		cfg = get_irq_chip_data(irq);
 		if (IO_APIC_IRQ(irq) && cfg && !cfg->vector) {
 			/*
 			 * Hmm.. We don't have an entry for this,
@@ -2774,7 +2599,7 @@ static inline void init_IO_APIC_traps(void)
 				legacy_pic->make_irq(irq);
 			else
 				/* Strange. Oh, well.. */
-				desc->chip = &no_irq_chip;
+				set_irq_chip(irq, &no_irq_chip);
 		}
 	}
 }
@@ -2783,7 +2608,7 @@ static inline void init_IO_APIC_traps(void)
  * The local APIC irq-chip implementation:
  */
 
-static void mask_lapic_irq(unsigned int irq)
+static void mask_lapic_irq(struct irq_data *data)
 {
 	unsigned long v;
 
@@ -2791,7 +2616,7 @@ static void mask_lapic_irq(unsigned int irq)
 	apic_write(APIC_LVT0, v | APIC_LVT_MASKED);
 }
 
-static void unmask_lapic_irq(unsigned int irq)
+static void unmask_lapic_irq(struct irq_data *data)
 {
 	unsigned long v;
 
@@ -2799,21 +2624,21 @@ static void unmask_lapic_irq(unsigned int irq)
 	apic_write(APIC_LVT0, v & ~APIC_LVT_MASKED);
 }
 
-static void ack_lapic_irq(unsigned int irq)
+static void ack_lapic_irq(struct irq_data *data)
 {
 	ack_APIC_irq();
 }
 
 static struct irq_chip lapic_chip __read_mostly = {
 	.name		= "local-APIC",
-	.mask		= mask_lapic_irq,
-	.unmask		= unmask_lapic_irq,
-	.ack		= ack_lapic_irq,
+	.irq_mask	= mask_lapic_irq,
+	.irq_unmask	= unmask_lapic_irq,
+	.irq_ack	= ack_lapic_irq,
 };
 
-static void lapic_register_intr(int irq, struct irq_desc *desc)
+static void lapic_register_intr(int irq)
 {
-	desc->status &= ~IRQ_LEVEL;
+	irq_clear_status_flags(irq, IRQ_LEVEL);
 	set_irq_chip_and_handler_name(irq, &lapic_chip, handle_edge_irq,
 				      "edge");
 }
@@ -2916,8 +2741,7 @@ int timer_through_8259 __initdata;
  */
 static inline void __init check_timer(void)
 {
-	struct irq_desc *desc = irq_to_desc(0);
-	struct irq_cfg *cfg = desc->chip_data;
+	struct irq_cfg *cfg = get_irq_chip_data(0);
 	int node = cpu_to_node(0);
 	int apic1, pin1, apic2, pin2;
 	unsigned long flags;
@@ -2928,7 +2752,7 @@ static inline void __init check_timer(void)
 	/*
 	 * get/set the timer IRQ vector:
 	 */
-	legacy_pic->chip->mask(0);
+	legacy_pic->mask(0);
 	assign_irq_vector(0, cfg, apic->target_cpus());
 
 	/*
@@ -2987,7 +2811,7 @@ static inline void __init check_timer(void)
 			add_pin_to_irq_node(cfg, node, apic1, pin1);
 			setup_timer_IRQ0_pin(apic1, pin1, cfg->vector);
 		} else {
-			/* for edge trigger, setup_IO_APIC_irq already
+			/* for edge trigger, setup_ioapic_irq already
 			 * leave it unmasked.
 			 * so only need to unmask if it is level-trigger
 			 * do we really have level trigger timer?
@@ -2995,12 +2819,12 @@ static inline void __init check_timer(void)
 			int idx;
 			idx = find_irq_entry(apic1, pin1, mp_INT);
 			if (idx != -1 && irq_trigger(idx))
-				unmask_IO_APIC_irq_desc(desc);
+				unmask_ioapic(cfg);
 		}
 		if (timer_irq_works()) {
 			if (nmi_watchdog == NMI_IO_APIC) {
 				setup_nmi();
-				legacy_pic->chip->unmask(0);
+				legacy_pic->unmask(0);
 			}
 			if (disable_timer_pin_1 > 0)
 				clear_IO_APIC_pin(0, pin1);
@@ -3023,14 +2847,14 @@ static inline void __init check_timer(void)
 		 */
 		replace_pin_at_irq_node(cfg, node, apic1, pin1, apic2, pin2);
 		setup_timer_IRQ0_pin(apic2, pin2, cfg->vector);
-		legacy_pic->chip->unmask(0);
+		legacy_pic->unmask(0);
 		if (timer_irq_works()) {
 			apic_printk(APIC_QUIET, KERN_INFO "....... works.\n");
 			timer_through_8259 = 1;
 			if (nmi_watchdog == NMI_IO_APIC) {
-				legacy_pic->chip->mask(0);
+				legacy_pic->mask(0);
 				setup_nmi();
-				legacy_pic->chip->unmask(0);
+				legacy_pic->unmask(0);
 			}
 			goto out;
 		}
@@ -3038,7 +2862,7 @@ static inline void __init check_timer(void)
 		 * Cleanup, just in case ...
 		 */
 		local_irq_disable();
-		legacy_pic->chip->mask(0);
+		legacy_pic->mask(0);
 		clear_IO_APIC_pin(apic2, pin2);
 		apic_printk(APIC_QUIET, KERN_INFO "....... failed.\n");
 	}
@@ -3055,16 +2879,16 @@ static inline void __init check_timer(void)
 	apic_printk(APIC_QUIET, KERN_INFO
 		    "...trying to set up timer as Virtual Wire IRQ...\n");
 
-	lapic_register_intr(0, desc);
+	lapic_register_intr(0);
 	apic_write(APIC_LVT0, APIC_DM_FIXED | cfg->vector);	/* Fixed mode */
-	legacy_pic->chip->unmask(0);
+	legacy_pic->unmask(0);
 
 	if (timer_irq_works()) {
 		apic_printk(APIC_QUIET, KERN_INFO "..... works.\n");
 		goto out;
 	}
 	local_irq_disable();
-	legacy_pic->chip->mask(0);
+	legacy_pic->mask(0);
 	apic_write(APIC_LVT0, APIC_LVT_MASKED | APIC_DM_FIXED | cfg->vector);
 	apic_printk(APIC_QUIET, KERN_INFO "..... failed.\n");
 
@@ -3230,44 +3054,37 @@ device_initcall(ioapic_init_sysfs);
 /*
  * Dynamic irq allocate and deallocation
  */
-unsigned int create_irq_nr(unsigned int irq_want, int node)
+unsigned int create_irq_nr(unsigned int from, int node)
 {
-	/* Allocate an unused irq */
-	unsigned int irq;
-	unsigned int new;
+	struct irq_cfg *cfg;
 	unsigned long flags;
-	struct irq_cfg *cfg_new = NULL;
-	struct irq_desc *desc_new = NULL;
-
-	irq = 0;
-	if (irq_want < nr_irqs_gsi)
-		irq_want = nr_irqs_gsi;
-
-	raw_spin_lock_irqsave(&vector_lock, flags);
-	for (new = irq_want; new < nr_irqs; new++) {
-		desc_new = irq_to_desc_alloc_node(new, node);
-		if (!desc_new) {
-			printk(KERN_INFO "can not get irq_desc for %d\n", new);
-			continue;
-		}
-		cfg_new = desc_new->chip_data;
-
-		if (cfg_new->vector != 0)
-			continue;
+	unsigned int ret = 0;
+	int irq;
 
-		desc_new = move_irq_desc(desc_new, node);
-		cfg_new = desc_new->chip_data;
+	if (from < nr_irqs_gsi)
+		from = nr_irqs_gsi;
 
-		if (__assign_irq_vector(new, cfg_new, apic->target_cpus()) == 0)
-			irq = new;
-		break;
+	irq = alloc_irq_from(from, node);
+	if (irq < 0)
+		return 0;
+	cfg = alloc_irq_cfg(irq, node);
+	if (!cfg) {
+		free_irq_at(irq, NULL);
+		return 0;
 	}
-	raw_spin_unlock_irqrestore(&vector_lock, flags);
 
-	if (irq > 0)
-		dynamic_irq_init_keep_chip_data(irq);
+	raw_spin_lock_irqsave(&vector_lock, flags);
+	if (!__assign_irq_vector(irq, cfg, apic->target_cpus()))
+		ret = irq;
+	raw_spin_unlock_irqrestore(&vector_lock, flags);
 
-	return irq;
+	if (ret) {
+		set_irq_chip_data(irq, cfg);
+		irq_clear_status_flags(irq, IRQ_NOREQUEST);
+	} else {
+		free_irq_at(irq, cfg);
+	}
+	return ret;
 }
 
 int create_irq(void)
@@ -3287,14 +3104,17 @@ int create_irq(void)
 
 void destroy_irq(unsigned int irq)
 {
+	struct irq_cfg *cfg = get_irq_chip_data(irq);
 	unsigned long flags;
 
-	dynamic_irq_cleanup_keep_chip_data(irq);
+	irq_set_status_flags(irq, IRQ_NOREQUEST|IRQ_NOPROBE);
 
-	free_irte(irq);
+	if (intr_remapping_enabled)
+		free_irte(irq);
 	raw_spin_lock_irqsave(&vector_lock, flags);
-	__clear_irq_vector(irq, get_irq_chip_data(irq));
+	__clear_irq_vector(irq, cfg);
 	raw_spin_unlock_irqrestore(&vector_lock, flags);
+	free_irq_at(irq, cfg);
 }
 
 /*
@@ -3318,7 +3138,7 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
 
 	dest = apic->cpu_mask_to_apicid_and(cfg->domain, apic->target_cpus());
 
-	if (irq_remapped(irq)) {
+	if (irq_remapped(get_irq_chip_data(irq))) {
 		struct irte irte;
 		int ir_index;
 		u16 sub_handle;
@@ -3371,26 +3191,24 @@ static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
 }
 
 #ifdef CONFIG_SMP
-static int set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
+static int
+msi_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg;
+	struct irq_cfg *cfg = data->chip_data;
 	struct msi_msg msg;
 	unsigned int dest;
 
-	if (set_desc_affinity(desc, mask, &dest))
+	if (__ioapic_set_affinity(data, mask, &dest))
 		return -1;
 
-	cfg = desc->chip_data;
-
-	get_cached_msi_msg_desc(desc, &msg);
+	__get_cached_msi_msg(data->msi_desc, &msg);
 
 	msg.data &= ~MSI_DATA_VECTOR_MASK;
 	msg.data |= MSI_DATA_VECTOR(cfg->vector);
 	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
-	write_msi_msg_desc(desc, &msg);
+	__write_msi_msg(data->msi_desc, &msg);
 
 	return 0;
 }
@@ -3400,17 +3218,17 @@ static int set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
  * done in the process context using interrupt-remapping hardware.
  */
 static int
-ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
+ir_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
+		    bool force)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg = desc->chip_data;
-	unsigned int dest;
+	struct irq_cfg *cfg = data->chip_data;
+	unsigned int dest, irq = data->irq;
 	struct irte irte;
 
 	if (get_irte(irq, &irte))
 		return -1;
 
-	if (set_desc_affinity(desc, mask, &dest))
+	if (__ioapic_set_affinity(data, mask, &dest))
 		return -1;
 
 	irte.vector = cfg->vector;
@@ -3440,27 +3258,27 @@ ir_set_msi_irq_affinity(unsigned int irq, const struct cpumask *mask)
  * 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,
+	.name			= "PCI-MSI",
+	.irq_unmask		= unmask_msi_irq,
+	.irq_mask		= mask_msi_irq,
+	.irq_ack		= ack_apic_edge,
 #ifdef CONFIG_SMP
-	.set_affinity	= set_msi_irq_affinity,
+	.irq_set_affinity	= msi_set_affinity,
 #endif
-	.retrigger	= ioapic_retrigger_irq,
+	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
 static struct irq_chip msi_ir_chip = {
-	.name		= "IR-PCI-MSI",
-	.unmask		= unmask_msi_irq,
-	.mask		= mask_msi_irq,
+	.name			= "IR-PCI-MSI",
+	.irq_unmask		= unmask_msi_irq,
+	.irq_mask		= mask_msi_irq,
 #ifdef CONFIG_INTR_REMAP
-	.ack		= ir_ack_apic_edge,
+	.irq_ack		= ir_ack_apic_edge,
 #ifdef CONFIG_SMP
-	.set_affinity	= ir_set_msi_irq_affinity,
+	.irq_set_affinity	= ir_msi_set_affinity,
 #endif
 #endif
-	.retrigger	= ioapic_retrigger_irq,
+	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
 /*
@@ -3492,8 +3310,8 @@ static int msi_alloc_irte(struct pci_dev *dev, int irq, int nvec)
 
 static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
 {
-	int ret;
 	struct msi_msg msg;
+	int ret;
 
 	ret = msi_compose_msg(dev, irq, &msg, -1);
 	if (ret < 0)
@@ -3502,12 +3320,8 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
 	set_irq_msi(irq, msidesc);
 	write_msi_msg(irq, &msg);
 
-	if (irq_remapped(irq)) {
-		struct irq_desc *desc = irq_to_desc(irq);
-		/*
-		 * irq migration in process context
-		 */
-		desc->status |= IRQ_MOVE_PCNTXT;
+	if (irq_remapped(get_irq_chip_data(irq))) {
+		irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
 		set_irq_chip_and_handler_name(irq, &msi_ir_chip, handle_edge_irq, "edge");
 	} else
 		set_irq_chip_and_handler_name(irq, &msi_chip, handle_edge_irq, "edge");
@@ -3519,13 +3333,10 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
 
 int arch_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 {
-	unsigned int irq;
-	int ret, sub_handle;
+	int node, ret, sub_handle, index = 0;
+	unsigned int irq, irq_want;
 	struct msi_desc *msidesc;
-	unsigned int irq_want;
 	struct intel_iommu *iommu = NULL;
-	int index = 0;
-	int node;
 
 	/* x86 doesn't support multiple MSI yet */
 	if (type == PCI_CAP_ID_MSI && nvec > 1)
@@ -3585,18 +3396,17 @@ void arch_teardown_msi_irq(unsigned int irq)
 
 #if defined (CONFIG_DMAR) || defined (CONFIG_INTR_REMAP)
 #ifdef CONFIG_SMP
-static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
+static int
+dmar_msi_set_affinity(struct irq_data *data, const struct cpumask *mask,
+		      bool force)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg;
+	struct irq_cfg *cfg = data->chip_data;
+	unsigned int dest, irq = data->irq;
 	struct msi_msg msg;
-	unsigned int dest;
 
-	if (set_desc_affinity(desc, mask, &dest))
+	if (__ioapic_set_affinity(data, mask, &dest))
 		return -1;
 
-	cfg = desc->chip_data;
-
 	dmar_msi_read(irq, &msg);
 
 	msg.data &= ~MSI_DATA_VECTOR_MASK;
@@ -3612,14 +3422,14 @@ static int dmar_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 #endif /* CONFIG_SMP */
 
 static struct irq_chip dmar_msi_type = {
-	.name = "DMAR_MSI",
-	.unmask = dmar_msi_unmask,
-	.mask = dmar_msi_mask,
-	.ack = ack_apic_edge,
+	.name			= "DMAR_MSI",
+	.irq_unmask		= dmar_msi_unmask,
+	.irq_mask		= dmar_msi_mask,
+	.irq_ack		= ack_apic_edge,
 #ifdef CONFIG_SMP
-	.set_affinity = dmar_msi_set_affinity,
+	.irq_set_affinity	= dmar_msi_set_affinity,
 #endif
-	.retrigger = ioapic_retrigger_irq,
+	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
 int arch_setup_dmar_msi(unsigned int irq)
@@ -3640,26 +3450,24 @@ int arch_setup_dmar_msi(unsigned int irq)
 #ifdef CONFIG_HPET_TIMER
 
 #ifdef CONFIG_SMP
-static int hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
+static int hpet_msi_set_affinity(struct irq_data *data,
+				 const struct cpumask *mask, bool force)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg;
+	struct irq_cfg *cfg = data->chip_data;
 	struct msi_msg msg;
 	unsigned int dest;
 
-	if (set_desc_affinity(desc, mask, &dest))
+	if (__ioapic_set_affinity(data, mask, &dest))
 		return -1;
 
-	cfg = desc->chip_data;
-
-	hpet_msi_read(irq, &msg);
+	hpet_msi_read(data->handler_data, &msg);
 
 	msg.data &= ~MSI_DATA_VECTOR_MASK;
 	msg.data |= MSI_DATA_VECTOR(cfg->vector);
 	msg.address_lo &= ~MSI_ADDR_DEST_ID_MASK;
 	msg.address_lo |= MSI_ADDR_DEST_ID(dest);
 
-	hpet_msi_write(irq, &msg);
+	hpet_msi_write(data->handler_data, &msg);
 
 	return 0;
 }
@@ -3667,34 +3475,33 @@ static int hpet_msi_set_affinity(unsigned int irq, const struct cpumask *mask)
 #endif /* CONFIG_SMP */
 
 static struct irq_chip ir_hpet_msi_type = {
-	.name = "IR-HPET_MSI",
-	.unmask = hpet_msi_unmask,
-	.mask = hpet_msi_mask,
+	.name			= "IR-HPET_MSI",
+	.irq_unmask		= hpet_msi_unmask,
+	.irq_mask		= hpet_msi_mask,
 #ifdef CONFIG_INTR_REMAP
-	.ack = ir_ack_apic_edge,
+	.irq_ack		= ir_ack_apic_edge,
 #ifdef CONFIG_SMP
-	.set_affinity = ir_set_msi_irq_affinity,
+	.irq_set_affinity	= ir_msi_set_affinity,
 #endif
 #endif
-	.retrigger = ioapic_retrigger_irq,
+	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
 static struct irq_chip hpet_msi_type = {
 	.name = "HPET_MSI",
-	.unmask = hpet_msi_unmask,
-	.mask = hpet_msi_mask,
-	.ack = ack_apic_edge,
+	.irq_unmask = hpet_msi_unmask,
+	.irq_mask = hpet_msi_mask,
+	.irq_ack = ack_apic_edge,
 #ifdef CONFIG_SMP
-	.set_affinity = hpet_msi_set_affinity,
+	.irq_set_affinity = hpet_msi_set_affinity,
 #endif
-	.retrigger = ioapic_retrigger_irq,
+	.irq_retrigger = ioapic_retrigger_irq,
 };
 
 int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
 {
-	int ret;
 	struct msi_msg msg;
-	struct irq_desc *desc = irq_to_desc(irq);
+	int ret;
 
 	if (intr_remapping_enabled) {
 		struct intel_iommu *iommu = map_hpet_to_ir(id);
@@ -3712,9 +3519,9 @@ int arch_setup_hpet_msi(unsigned int irq, unsigned int id)
 	if (ret < 0)
 		return ret;
 
-	hpet_msi_write(irq, &msg);
-	desc->status |= IRQ_MOVE_PCNTXT;
-	if (irq_remapped(irq))
+	hpet_msi_write(get_irq_data(irq), &msg);
+	irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
+	if (irq_remapped(get_irq_chip_data(irq)))
 		set_irq_chip_and_handler_name(irq, &ir_hpet_msi_type,
 					      handle_edge_irq, "edge");
 	else
@@ -3747,33 +3554,30 @@ static void target_ht_irq(unsigned int irq, unsigned int dest, u8 vector)
 	write_ht_irq_msg(irq, &msg);
 }
 
-static int set_ht_irq_affinity(unsigned int irq, const struct cpumask *mask)
+static int
+ht_set_affinity(struct irq_data *data, const struct cpumask *mask, bool force)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg;
+	struct irq_cfg *cfg = data->chip_data;
 	unsigned int dest;
 
-	if (set_desc_affinity(desc, mask, &dest))
+	if (__ioapic_set_affinity(data, mask, &dest))
 		return -1;
 
-	cfg = desc->chip_data;
-
-	target_ht_irq(irq, dest, cfg->vector);
-
+	target_ht_irq(data->irq, dest, cfg->vector);
 	return 0;
 }
 
 #endif
 
 static struct irq_chip ht_irq_chip = {
-	.name		= "PCI-HT",
-	.mask		= mask_ht_irq,
-	.unmask		= unmask_ht_irq,
-	.ack		= ack_apic_edge,
+	.name			= "PCI-HT",
+	.irq_mask		= mask_ht_irq,
+	.irq_unmask		= unmask_ht_irq,
+	.irq_ack		= ack_apic_edge,
 #ifdef CONFIG_SMP
-	.set_affinity	= set_ht_irq_affinity,
+	.irq_set_affinity	= ht_set_affinity,
 #endif
-	.retrigger	= ioapic_retrigger_irq,
+	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
 int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev)
@@ -3864,14 +3668,13 @@ int __init arch_probe_nr_irqs(void)
 	if (nr < nr_irqs)
 		nr_irqs = nr;
 
-	return 0;
+	return NR_IRQS_LEGACY;
 }
 #endif
 
 static int __io_apic_set_pci_routing(struct device *dev, int irq,
 				struct io_apic_irq_attr *irq_attr)
 {
-	struct irq_desc *desc;
 	struct irq_cfg *cfg;
 	int node;
 	int ioapic, pin;
@@ -3889,11 +3692,9 @@ static int __io_apic_set_pci_routing(struct device *dev, int irq,
 	else
 		node = cpu_to_node(0);
 
-	desc = irq_to_desc_alloc_node(irq, node);
-	if (!desc) {
-		printk(KERN_INFO "can not get irq_desc %d\n", irq);
+	cfg = alloc_irq_and_cfg_at(irq, node);
+	if (!cfg)
 		return 0;
-	}
 
 	pin = irq_attr->ioapic_pin;
 	trigger = irq_attr->trigger;
@@ -3903,15 +3704,14 @@ static int __io_apic_set_pci_routing(struct device *dev, int irq,
 	 * IRQs < 16 are already in the irq_2_pin[] map
 	 */
 	if (irq >= legacy_pic->nr_legacy_irqs) {
-		cfg = desc->chip_data;
-		if (add_pin_to_irq_node_nopanic(cfg, node, ioapic, pin)) {
+		if (__add_pin_to_irq_node(cfg, node, ioapic, pin)) {
 			printk(KERN_INFO "can not add pin %d for irq %d\n",
 				pin, irq);
 			return 0;
 		}
 	}
 
-	setup_IO_APIC_irq(ioapic, pin, irq, desc, trigger, polarity);
+	setup_ioapic_irq(ioapic, pin, irq, cfg, trigger, polarity);
 
 	return 0;
 }
@@ -4104,14 +3904,14 @@ void __init setup_ioapic_dest(void)
 		 */
 		if (desc->status &
 		    (IRQ_NO_BALANCING | IRQ_AFFINITY_SET))
-			mask = desc->affinity;
+			mask = desc->irq_data.affinity;
 		else
 			mask = apic->target_cpus();
 
 		if (intr_remapping_enabled)
-			set_ir_ioapic_affinity_irq_desc(desc, mask);
+			ir_ioapic_set_affinity(&desc->irq_data, mask, false);
 		else
-			set_ioapic_affinity_irq_desc(desc, mask);
+			ioapic_set_affinity(&desc->irq_data, mask, false);
 	}
 
 }
@@ -4295,19 +4095,18 @@ void __init mp_register_ioapic(int id, u32 address, u32 gsi_base)
 void __init pre_init_apic_IRQ0(void)
 {
 	struct irq_cfg *cfg;
-	struct irq_desc *desc;
 
 	printk(KERN_INFO "Early APIC setup for system timer0\n");
 #ifndef CONFIG_SMP
 	phys_cpu_present_map = physid_mask_of_physid(boot_cpu_physical_apicid);
 #endif
-	desc = irq_to_desc_alloc_node(0, 0);
+	/* Make sure the irq descriptor is set up */
+	cfg = alloc_irq_and_cfg_at(0, 0);
 
 	setup_local_APIC();
 
-	cfg = irq_cfg(0);
 	add_pin_to_irq_node(cfg, 0, 0, 0);
 	set_irq_chip_and_handler_name(0, &ioapic_chip, handle_edge_irq, "edge");
 
-	setup_IO_APIC_irq(0, 0, 0, desc, 0, 0);
+	setup_ioapic_irq(0, 0, 0, cfg, 0, 0);
 }

arch/x86/kernel/apic/nmi.c

@@ -178,7 +178,7 @@ int __init check_nmi_watchdog(void)
 error:
 	if (nmi_watchdog == NMI_IO_APIC) {
 		if (!timer_through_8259)
-			legacy_pic->chip->mask(0);
+			legacy_pic->mask(0);
 		on_each_cpu(__acpi_nmi_disable, NULL, 1);
 	}
 

arch/x86/kernel/cpu/mcheck/mce_amd.c

@@ -131,7 +131,8 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 	u32 low = 0, high = 0, address = 0;
 	unsigned int bank, block;
 	struct thresh_restart tr;
-	u8 lvt_off;
+	int lvt_off = -1;
+	u8 offset;
 
 	for (bank = 0; bank < NR_BANKS; ++bank) {
 		for (block = 0; block < NR_BLOCKS; ++block) {
@@ -162,8 +163,28 @@ void mce_amd_feature_init(struct cpuinfo_x86 *c)
 			if (shared_bank[bank] && c->cpu_core_id)
 				break;
 #endif
-			lvt_off = setup_APIC_eilvt_mce(THRESHOLD_APIC_VECTOR,
-						       APIC_EILVT_MSG_FIX, 0);
+			offset = (high & MASK_LVTOFF_HI) >> 20;
+			if (lvt_off < 0) {
+				if (setup_APIC_eilvt(offset,
+						     THRESHOLD_APIC_VECTOR,
+						     APIC_EILVT_MSG_FIX, 0)) {
+					pr_err(FW_BUG "cpu %d, failed to "
+					       "setup threshold interrupt "
+					       "for bank %d, block %d "
+					       "(MSR%08X=0x%x%08x)",
+					       smp_processor_id(), bank, block,
+					       address, high, low);
+					continue;
+				}
+				lvt_off = offset;
+			} else if (lvt_off != offset) {
+				pr_err(FW_BUG "cpu %d, invalid threshold "
+				       "interrupt offset %d for bank %d,"
+				       "block %d (MSR%08X=0x%x%08x)",
+				       smp_processor_id(), lvt_off, bank,
+				       block, address, high, low);
+				continue;
+			}
 
 			high &= ~MASK_LVTOFF_HI;
 			high |= lvt_off << 20;

arch/x86/kernel/hpet.c

@@ -440,9 +440,9 @@ static int hpet_legacy_next_event(unsigned long delta,
 static DEFINE_PER_CPU(struct hpet_dev *, cpu_hpet_dev);
 static struct hpet_dev	*hpet_devs;
 
-void hpet_msi_unmask(unsigned int irq)
+void hpet_msi_unmask(struct irq_data *data)
 {
-	struct hpet_dev *hdev = get_irq_data(irq);
+	struct hpet_dev *hdev = data->handler_data;
 	unsigned int cfg;
 
 	/* unmask it */
@@ -451,10 +451,10 @@ void hpet_msi_unmask(unsigned int irq)
 	hpet_writel(cfg, HPET_Tn_CFG(hdev->num));
 }
 
-void hpet_msi_mask(unsigned int irq)
+void hpet_msi_mask(struct irq_data *data)
 {
+	struct hpet_dev *hdev = data->handler_data;
 	unsigned int cfg;
-	struct hpet_dev *hdev = get_irq_data(irq);
 
 	/* mask it */
 	cfg = hpet_readl(HPET_Tn_CFG(hdev->num));
@@ -462,18 +462,14 @@ void hpet_msi_mask(unsigned int irq)
 	hpet_writel(cfg, HPET_Tn_CFG(hdev->num));
 }
 
-void hpet_msi_write(unsigned int irq, struct msi_msg *msg)
+void hpet_msi_write(struct hpet_dev *hdev, struct msi_msg *msg)
 {
-	struct hpet_dev *hdev = get_irq_data(irq);
-
 	hpet_writel(msg->data, HPET_Tn_ROUTE(hdev->num));
 	hpet_writel(msg->address_lo, HPET_Tn_ROUTE(hdev->num) + 4);
 }
 
-void hpet_msi_read(unsigned int irq, struct msi_msg *msg)
+void hpet_msi_read(struct hpet_dev *hdev, struct msi_msg *msg)
 {
-	struct hpet_dev *hdev = get_irq_data(irq);
-
 	msg->data = hpet_readl(HPET_Tn_ROUTE(hdev->num));
 	msg->address_lo = hpet_readl(HPET_Tn_ROUTE(hdev->num) + 4);
 	msg->address_hi = 0;

arch/x86/kernel/i8259.c

@@ -29,24 +29,10 @@
  * plus some generic x86 specific things if generic specifics makes
  * any sense at all.
  */
+static void init_8259A(int auto_eoi);
 
 static int i8259A_auto_eoi;
 DEFINE_RAW_SPINLOCK(i8259A_lock);
-static void mask_and_ack_8259A(unsigned int);
-static void mask_8259A(void);
-static void unmask_8259A(void);
-static void disable_8259A_irq(unsigned int irq);
-static void enable_8259A_irq(unsigned int irq);
-static void init_8259A(int auto_eoi);
-static int i8259A_irq_pending(unsigned int irq);
-
-struct irq_chip i8259A_chip = {
-	.name		= "XT-PIC",
-	.mask		= disable_8259A_irq,
-	.disable	= disable_8259A_irq,
-	.unmask		= enable_8259A_irq,
-	.mask_ack	= mask_and_ack_8259A,
-};
 
 /*
  * 8259A PIC functions to handle ISA devices:
@@ -68,7 +54,7 @@ unsigned int cached_irq_mask = 0xffff;
  */
 unsigned long io_apic_irqs;
 
-static void disable_8259A_irq(unsigned int irq)
+static void mask_8259A_irq(unsigned int irq)
 {
 	unsigned int mask = 1 << irq;
 	unsigned long flags;
@@ -82,7 +68,12 @@ static void disable_8259A_irq(unsigned int irq)
 	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 }
 
-static void enable_8259A_irq(unsigned int irq)
+static void disable_8259A_irq(struct irq_data *data)
+{
+	mask_8259A_irq(data->irq);
+}
+
+static void unmask_8259A_irq(unsigned int irq)
 {
 	unsigned int mask = ~(1 << irq);
 	unsigned long flags;
@@ -96,6 +87,11 @@ static void enable_8259A_irq(unsigned int irq)
 	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 }
 
+static void enable_8259A_irq(struct irq_data *data)
+{
+	unmask_8259A_irq(data->irq);
+}
+
 static int i8259A_irq_pending(unsigned int irq)
 {
 	unsigned int mask = 1<<irq;
@@ -117,7 +113,7 @@ static void make_8259A_irq(unsigned int irq)
 	disable_irq_nosync(irq);
 	io_apic_irqs &= ~(1<<irq);
 	set_irq_chip_and_handler_name(irq, &i8259A_chip, handle_level_irq,
-				      "XT");
+				      i8259A_chip.name);
 	enable_irq(irq);
 }
 
@@ -150,8 +146,9 @@ static inline int i8259A_irq_real(unsigned int irq)
  * first, _then_ send the EOI, and the order of EOI
  * to the two 8259s is important!
  */
-static void mask_and_ack_8259A(unsigned int irq)
+static void mask_and_ack_8259A(struct irq_data *data)
 {
+	unsigned int irq = data->irq;
 	unsigned int irqmask = 1 << irq;
 	unsigned long flags;
 
@@ -223,6 +220,14 @@ spurious_8259A_irq:
 	}
 }
 
+struct irq_chip i8259A_chip = {
+	.name		= "XT-PIC",
+	.irq_mask	= disable_8259A_irq,
+	.irq_disable	= disable_8259A_irq,
+	.irq_unmask	= enable_8259A_irq,
+	.irq_mask_ack	= mask_and_ack_8259A,
+};
+
 static char irq_trigger[2];
 /**
  * ELCR registers (0x4d0, 0x4d1) control edge/level of IRQ
@@ -342,9 +347,9 @@ static void init_8259A(int auto_eoi)
 		 * In AEOI mode we just have to mask the interrupt
 		 * when acking.
 		 */
-		i8259A_chip.mask_ack = disable_8259A_irq;
+		i8259A_chip.irq_mask_ack = disable_8259A_irq;
 	else
-		i8259A_chip.mask_ack = mask_and_ack_8259A;
+		i8259A_chip.irq_mask_ack = mask_and_ack_8259A;
 
 	udelay(100);		/* wait for 8259A to initialize */
 
@@ -363,14 +368,6 @@ static void init_8259A(int auto_eoi)
 static void legacy_pic_noop(void) { };
 static void legacy_pic_uint_noop(unsigned int unused) { };
 static void legacy_pic_int_noop(int unused) { };
-
-static struct irq_chip dummy_pic_chip  = {
-	.name = "dummy pic",
-	.mask = legacy_pic_uint_noop,
-	.unmask = legacy_pic_uint_noop,
-	.disable = legacy_pic_uint_noop,
-	.mask_ack = legacy_pic_uint_noop,
-};
 static int legacy_pic_irq_pending_noop(unsigned int irq)
 {
 	return 0;
@@ -378,7 +375,9 @@ static int legacy_pic_irq_pending_noop(unsigned int irq)
 
 struct legacy_pic null_legacy_pic = {
 	.nr_legacy_irqs = 0,
-	.chip = &dummy_pic_chip,
+	.chip = &dummy_irq_chip,
+	.mask = legacy_pic_uint_noop,
+	.unmask = legacy_pic_uint_noop,
 	.mask_all = legacy_pic_noop,
 	.restore_mask = legacy_pic_noop,
 	.init = legacy_pic_int_noop,
@@ -389,7 +388,9 @@ struct legacy_pic null_legacy_pic = {
 struct legacy_pic default_legacy_pic = {
 	.nr_legacy_irqs = NR_IRQS_LEGACY,
 	.chip  = &i8259A_chip,
-	.mask_all  = mask_8259A,
+	.mask = mask_8259A_irq,
+	.unmask = unmask_8259A_irq,
+	.mask_all = mask_8259A,
 	.restore_mask = unmask_8259A,
 	.init = init_8259A,
 	.irq_pending = i8259A_irq_pending,

arch/x86/kernel/irq.c

@@ -159,7 +159,7 @@ int show_interrupts(struct seq_file *p, void *v)
 	seq_printf(p, "%*d: ", prec, i);
 	for_each_online_cpu(j)
 		seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
-	seq_printf(p, " %8s", desc->chip->name);
+	seq_printf(p, " %8s", desc->irq_data.chip->name);
 	seq_printf(p, "-%-8s", desc->name);
 
 	if (action) {
@@ -282,6 +282,7 @@ void fixup_irqs(void)
 	unsigned int irq, vector;
 	static int warned;
 	struct irq_desc *desc;
+	struct irq_data *data;
 
 	for_each_irq_desc(irq, desc) {
 		int break_affinity = 0;
@@ -296,7 +297,8 @@ void fixup_irqs(void)
 		/* interrupt's are disabled at this point */
 		raw_spin_lock(&desc->lock);
 
-		affinity = desc->affinity;
+		data = &desc->irq_data;
+		affinity = data->affinity;
 		if (!irq_has_action(irq) ||
 		    cpumask_equal(affinity, cpu_online_mask)) {
 			raw_spin_unlock(&desc->lock);
@@ -315,16 +317,16 @@ void fixup_irqs(void)
 			affinity = cpu_all_mask;
 		}
 
-		if (!(desc->status & IRQ_MOVE_PCNTXT) && desc->chip->mask)
-			desc->chip->mask(irq);
+		if (!(desc->status & IRQ_MOVE_PCNTXT) && data->chip->irq_mask)
+			data->chip->irq_mask(data);
 
-		if (desc->chip->set_affinity)
-			desc->chip->set_affinity(irq, affinity);
+		if (data->chip->irq_set_affinity)
+			data->chip->irq_set_affinity(data, affinity, true);
 		else if (!(warned++))
 			set_affinity = 0;
 
-		if (!(desc->status & IRQ_MOVE_PCNTXT) && desc->chip->unmask)
-			desc->chip->unmask(irq);
+		if (!(desc->status & IRQ_MOVE_PCNTXT) && data->chip->irq_unmask)
+			data->chip->irq_unmask(data);
 
 		raw_spin_unlock(&desc->lock);
 
@@ -355,10 +357,10 @@ void fixup_irqs(void)
 		if (irr  & (1 << (vector % 32))) {
 			irq = __get_cpu_var(vector_irq)[vector];
 
-			desc = irq_to_desc(irq);
+			data = irq_get_irq_data(irq);
 			raw_spin_lock(&desc->lock);
-			if (desc->chip->retrigger)
-				desc->chip->retrigger(irq);
+			if (data->chip->irq_retrigger)
+				data->chip->irq_retrigger(data);
 			raw_spin_unlock(&desc->lock);
 		}
 	}

arch/x86/kernel/irqinit.c

@@ -100,6 +100,8 @@ int vector_used_by_percpu_irq(unsigned int vector)
 
 void __init init_ISA_irqs(void)
 {
+	struct irq_chip *chip = legacy_pic->chip;
+	const char *name = chip->name;
 	int i;
 
 #if defined(CONFIG_X86_64) || defined(CONFIG_X86_LOCAL_APIC)
@@ -107,19 +109,8 @@ void __init init_ISA_irqs(void)
 #endif
 	legacy_pic->init(0);
 
-	/*
-	 * 16 old-style INTA-cycle interrupts:
-	 */
-	for (i = 0; i < legacy_pic->nr_legacy_irqs; i++) {
-		struct irq_desc *desc = irq_to_desc(i);
-
-		desc->status = IRQ_DISABLED;
-		desc->action = NULL;
-		desc->depth = 1;
-
-		set_irq_chip_and_handler_name(i, &i8259A_chip,
-					      handle_level_irq, "XT");
-	}
+	for (i = 0; i < legacy_pic->nr_legacy_irqs; i++)
+		set_irq_chip_and_handler_name(i, chip, handle_level_irq, name);
 }
 
 void __init init_IRQ(void)

arch/x86/kernel/smpboot.c

@@ -323,9 +323,9 @@ notrace static void __cpuinit start_secondary(void *unused)
 	check_tsc_sync_target();
 
 	if (nmi_watchdog == NMI_IO_APIC) {
-		legacy_pic->chip->mask(0);
+		legacy_pic->mask(0);
 		enable_NMI_through_LVT0();
-		legacy_pic->chip->unmask(0);
+		legacy_pic->unmask(0);
 	}
 
 	/* This must be done before setting cpu_online_mask */

arch/x86/kernel/uv_irq.c

@@ -28,34 +28,21 @@ struct uv_irq_2_mmr_pnode{
 static spinlock_t		uv_irq_lock;
 static struct rb_root		uv_irq_root;
 
-static int uv_set_irq_affinity(unsigned int, const struct cpumask *);
+static int uv_set_irq_affinity(struct irq_data *, const struct cpumask *, bool);
 
-static void uv_noop(unsigned int irq)
-{
-}
-
-static unsigned int uv_noop_ret(unsigned int irq)
-{
-	return 0;
-}
+static void uv_noop(struct irq_data *data) { }
 
-static void uv_ack_apic(unsigned int irq)
+static void uv_ack_apic(struct irq_data *data)
 {
 	ack_APIC_irq();
 }
 
 static struct irq_chip uv_irq_chip = {
-	.name		= "UV-CORE",
-	.startup	= uv_noop_ret,
-	.shutdown	= uv_noop,
-	.enable		= uv_noop,
-	.disable	= uv_noop,
-	.ack		= uv_noop,
-	.mask		= uv_noop,
-	.unmask		= uv_noop,
-	.eoi		= uv_ack_apic,
-	.end		= uv_noop,
-	.set_affinity	= uv_set_irq_affinity,
+	.name			= "UV-CORE",
+	.irq_mask		= uv_noop,
+	.irq_unmask		= uv_noop,
+	.irq_eoi		= uv_ack_apic,
+	.irq_set_affinity	= uv_set_irq_affinity,
 };
 
 /*
@@ -144,26 +131,22 @@ arch_enable_uv_irq(char *irq_name, unsigned int irq, int cpu, int mmr_blade,
 		       unsigned long mmr_offset, int limit)
 {
 	const struct cpumask *eligible_cpu = cpumask_of(cpu);
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg;
-	int mmr_pnode;
+	struct irq_cfg *cfg = get_irq_chip_data(irq);
 	unsigned long mmr_value;
 	struct uv_IO_APIC_route_entry *entry;
-	int err;
+	int mmr_pnode, err;
 
 	BUILD_BUG_ON(sizeof(struct uv_IO_APIC_route_entry) !=
 			sizeof(unsigned long));
 
-	cfg = irq_cfg(irq);
-
 	err = assign_irq_vector(irq, cfg, eligible_cpu);
 	if (err != 0)
 		return err;
 
 	if (limit == UV_AFFINITY_CPU)
-		desc->status |= IRQ_NO_BALANCING;
+		irq_set_status_flags(irq, IRQ_NO_BALANCING);
 	else
-		desc->status |= IRQ_MOVE_PCNTXT;
+		irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
 
 	set_irq_chip_and_handler_name(irq, &uv_irq_chip, handle_percpu_irq,
 				      irq_name);
@@ -206,17 +189,17 @@ static void arch_disable_uv_irq(int mmr_pnode, unsigned long mmr_offset)
 	uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);
 }
 
-static int uv_set_irq_affinity(unsigned int irq, const struct cpumask *mask)
+static int
+uv_set_irq_affinity(struct irq_data *data, const struct cpumask *mask,
+		    bool force)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	struct irq_cfg *cfg = desc->chip_data;
+	struct irq_cfg *cfg = data->chip_data;
 	unsigned int dest;
-	unsigned long mmr_value;
+	unsigned long mmr_value, mmr_offset;
 	struct uv_IO_APIC_route_entry *entry;
-	unsigned long mmr_offset;
 	int mmr_pnode;
 
-	if (set_desc_affinity(desc, mask, &dest))
+	if (__ioapic_set_affinity(data, mask, &dest))
 		return -1;
 
 	mmr_value = 0;
@@ -231,7 +214,7 @@ static int uv_set_irq_affinity(unsigned int irq, const struct cpumask *mask)
 	entry->dest		= dest;
 
 	/* Get previously stored MMR and pnode of hub sourcing interrupts */
-	if (uv_irq_2_mmr_info(irq, &mmr_offset, &mmr_pnode))
+	if (uv_irq_2_mmr_info(data->irq, &mmr_offset, &mmr_pnode))
 		return -1;
 
 	uv_write_global_mmr64(mmr_pnode, mmr_offset, mmr_value);

arch/x86/kernel/visws_quirks.c

@@ -66,10 +66,7 @@ static void __init visws_time_init(void)
 }
 
 /* Replaces the default init_ISA_irqs in the generic setup */
-static void __init visws_pre_intr_init(void)
-{
-	init_VISWS_APIC_irqs();
-}
+static void __init visws_pre_intr_init(void);
 
 /* Quirk for machine specific memory setup. */
 
@@ -429,67 +426,34 @@ static int is_co_apic(unsigned int irq)
 /*
  * This is the SGI Cobalt (IO-)APIC:
  */
-
-static void enable_cobalt_irq(unsigned int irq)
+static void enable_cobalt_irq(struct irq_data *data)
 {
-	co_apic_set(is_co_apic(irq), irq);
+	co_apic_set(is_co_apic(data->irq), data->irq);
 }
 
-static void disable_cobalt_irq(unsigned int irq)
+static void disable_cobalt_irq(struct irq_data *data)
 {
-	int entry = is_co_apic(irq);
+	int entry = is_co_apic(data->irq);
 
 	co_apic_write(CO_APIC_LO(entry), CO_APIC_MASK);
 	co_apic_read(CO_APIC_LO(entry));
 }
 
-/*
- * "irq" really just serves to identify the device.  Here is where we
- * map this to the Cobalt APIC entry where it's physically wired.
- * This is called via request_irq -> setup_irq -> irq_desc->startup()
- */
-static unsigned int startup_cobalt_irq(unsigned int irq)
+static void ack_cobalt_irq(struct irq_data *data)
 {
 	unsigned long flags;
-	struct irq_desc *desc = irq_to_desc(irq);
 
 	spin_lock_irqsave(&cobalt_lock, flags);
-	if ((desc->status & (IRQ_DISABLED | IRQ_INPROGRESS | IRQ_WAITING)))
-		desc->status &= ~(IRQ_DISABLED | IRQ_INPROGRESS | IRQ_WAITING);
-	enable_cobalt_irq(irq);
-	spin_unlock_irqrestore(&cobalt_lock, flags);
-	return 0;
-}
-
-static void ack_cobalt_irq(unsigned int irq)
-{
-	unsigned long flags;
-
-	spin_lock_irqsave(&cobalt_lock, flags);
-	disable_cobalt_irq(irq);
+	disable_cobalt_irq(data);
 	apic_write(APIC_EOI, APIC_EIO_ACK);
 	spin_unlock_irqrestore(&cobalt_lock, flags);
 }
 
-static void end_cobalt_irq(unsigned int irq)
-{
-	unsigned long flags;
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	spin_lock_irqsave(&cobalt_lock, flags);
-	if (!(desc->status & (IRQ_DISABLED | IRQ_INPROGRESS)))
-		enable_cobalt_irq(irq);
-	spin_unlock_irqrestore(&cobalt_lock, flags);
-}
-
 static struct irq_chip cobalt_irq_type = {
-	.name =		"Cobalt-APIC",
-	.startup =	startup_cobalt_irq,
-	.shutdown =	disable_cobalt_irq,
-	.enable =	enable_cobalt_irq,
-	.disable =	disable_cobalt_irq,
-	.ack =		ack_cobalt_irq,
-	.end =		end_cobalt_irq,
+	.name		= "Cobalt-APIC",
+	.irq_enable	= enable_cobalt_irq,
+	.irq_disable	= disable_cobalt_irq,
+	.irq_ack	= ack_cobalt_irq,
 };
 
 
@@ -503,35 +467,34 @@ static struct irq_chip cobalt_irq_type = {
  * interrupt controller type, and through a special virtual interrupt-
  * controller. Device drivers only see the virtual interrupt sources.
  */
-static unsigned int startup_piix4_master_irq(unsigned int irq)
+static unsigned int startup_piix4_master_irq(struct irq_data *data)
 {
 	legacy_pic->init(0);
-
-	return startup_cobalt_irq(irq);
+	enable_cobalt_irq(data);
 }
 
-static void end_piix4_master_irq(unsigned int irq)
+static void end_piix4_master_irq(struct irq_data *data)
 {
 	unsigned long flags;
 
 	spin_lock_irqsave(&cobalt_lock, flags);
-	enable_cobalt_irq(irq);
+	enable_cobalt_irq(data);
 	spin_unlock_irqrestore(&cobalt_lock, flags);
 }
 
 static struct irq_chip piix4_master_irq_type = {
-	.name =		"PIIX4-master",
-	.startup =	startup_piix4_master_irq,
-	.ack =		ack_cobalt_irq,
-	.end =		end_piix4_master_irq,
+	.name		= "PIIX4-master",
+	.irq_startup	= startup_piix4_master_irq,
+	.irq_ack	= ack_cobalt_irq,
 };
 
+static void pii4_mask(struct irq_data *data) { }
 
 static struct irq_chip piix4_virtual_irq_type = {
-	.name =		"PIIX4-virtual",
+	.name		= "PIIX4-virtual",
+	.mask		= pii4_mask,
 };
 
-
 /*
  * PIIX4-8259 master/virtual functions to handle interrupt requests
  * from legacy devices: floppy, parallel, serial, rtc.
@@ -549,9 +512,8 @@ static struct irq_chip piix4_virtual_irq_type = {
  */
 static irqreturn_t piix4_master_intr(int irq, void *dev_id)
 {
-	int realirq;
-	struct irq_desc *desc;
 	unsigned long flags;
+	int realirq;
 
 	raw_spin_lock_irqsave(&i8259A_lock, flags);
 
@@ -592,18 +554,10 @@ static irqreturn_t piix4_master_intr(int irq, void *dev_id)
 
 	raw_spin_unlock_irqrestore(&i8259A_lock, flags);
 
-	desc = irq_to_desc(realirq);
-
 	/*
 	 * handle this 'virtual interrupt' as a Cobalt one now.
 	 */
-	kstat_incr_irqs_this_cpu(realirq, desc);
-
-	if (likely(desc->action != NULL))
-		handle_IRQ_event(realirq, desc->action);
-
-	if (!(desc->status & IRQ_DISABLED))
-		legacy_pic->chip->unmask(realirq);
+	generic_handle_irq(realirq);
 
 	return IRQ_HANDLED;
 
@@ -624,41 +578,35 @@ static struct irqaction cascade_action = {
 
 static inline void set_piix4_virtual_irq_type(void)
 {
-	piix4_virtual_irq_type.shutdown = i8259A_chip.mask;
 	piix4_virtual_irq_type.enable =	i8259A_chip.unmask;
 	piix4_virtual_irq_type.disable = i8259A_chip.mask;
+	piix4_virtual_irq_type.unmask =	i8259A_chip.unmask;
 }
 
-void init_VISWS_APIC_irqs(void)
+static void __init visws_pre_intr_init(void)
 {
 	int i;
 
-	for (i = 0; i < CO_IRQ_APIC0 + CO_APIC_LAST + 1; i++) {
-		struct irq_desc *desc = irq_to_desc(i);
-
-		desc->status = IRQ_DISABLED;
-		desc->action = 0;
-		desc->depth = 1;
+	set_piix4_virtual_irq_type();
 
-		if (i == 0) {
-			desc->chip = &cobalt_irq_type;
-		}
-		else if (i == CO_IRQ_IDE0) {
-			desc->chip = &cobalt_irq_type;
-		}
-		else if (i == CO_IRQ_IDE1) {
-			desc->chip = &cobalt_irq_type;
-		}
-		else if (i == CO_IRQ_8259) {
-			desc->chip = &piix4_master_irq_type;
-		}
-		else if (i < CO_IRQ_APIC0) {
-			set_piix4_virtual_irq_type();
-			desc->chip = &piix4_virtual_irq_type;
-		}
-		else if (IS_CO_APIC(i)) {
-			desc->chip = &cobalt_irq_type;
-		}
+	for (i = 0; i < CO_IRQ_APIC0 + CO_APIC_LAST + 1; i++) {
+		struct irq_chip *chip = NULL;
+
+		if (i == 0)
+			chip = &cobalt_irq_type;
+		else if (i == CO_IRQ_IDE0)
+			chip = &cobalt_irq_type;
+		else if (i == CO_IRQ_IDE1)
+			>chip = &cobalt_irq_type;
+		else if (i == CO_IRQ_8259)
+			chip = &piix4_master_irq_type;
+		else if (i < CO_IRQ_APIC0)
+			chip = &piix4_virtual_irq_type;
+		else if (IS_CO_APIC(i))
+			chip = &cobalt_irq_type;
+
+		if (chip)
+			set_irq_chip(i, chip);
 	}
 
 	setup_irq(CO_IRQ_8259, &master_action);

arch/x86/lguest/boot.c

@@ -791,22 +791,22 @@ static void lguest_flush_tlb_kernel(void)
  * simple as setting a bit.  We don't actually "ack" interrupts as such, we
  * just mask and unmask them.  I wonder if we should be cleverer?
  */
-static void disable_lguest_irq(unsigned int irq)
+static void disable_lguest_irq(struct irq_data *data)
 {
-	set_bit(irq, lguest_data.blocked_interrupts);
+	set_bit(data->irq, lguest_data.blocked_interrupts);
 }
 
-static void enable_lguest_irq(unsigned int irq)
+static void enable_lguest_irq(struct irq_data *data)
 {
-	clear_bit(irq, lguest_data.blocked_interrupts);
+	clear_bit(data->irq, lguest_data.blocked_interrupts);
 }
 
 /* This structure describes the lguest IRQ controller. */
 static struct irq_chip lguest_irq_controller = {
 	.name		= "lguest",
-	.mask		= disable_lguest_irq,
-	.mask_ack	= disable_lguest_irq,
-	.unmask		= enable_lguest_irq,
+	.irq_mask	= disable_lguest_irq,
+	.irq_mask_ack	= disable_lguest_irq,
+	.irq_unmask	= enable_lguest_irq,
 };
 
 /*
@@ -838,12 +838,12 @@ static void __init lguest_init_IRQ(void)
  * rather than set them in lguest_init_IRQ we are called here every time an
  * lguest device needs an interrupt.
  *
- * FIXME: irq_to_desc_alloc_node() can fail due to lack of memory, we should
+ * FIXME: irq_alloc_desc_at() can fail due to lack of memory, we should
  * pass that up!
  */
 void lguest_setup_irq(unsigned int irq)
 {
-	irq_to_desc_alloc_node(irq, 0);
+	irq_alloc_desc_at(irq, 0);
 	set_irq_chip_and_handler_name(irq, &lguest_irq_controller,
 				      handle_level_irq, "level");
 }

arch/x86/oprofile/op_model_amd.c

@@ -64,15 +64,22 @@ static u64 ibs_op_ctl;
  * IBS cpuid feature detection
  */
 
-#define IBS_CPUID_FEATURES      0x8000001b
+#define IBS_CPUID_FEATURES		0x8000001b
 
 /*
  * Same bit mask as for IBS cpuid feature flags (Fn8000_001B_EAX), but
  * bit 0 is used to indicate the existence of IBS.
  */
-#define IBS_CAPS_AVAIL			(1LL<<0)
-#define IBS_CAPS_RDWROPCNT		(1LL<<3)
-#define IBS_CAPS_OPCNT			(1LL<<4)
+#define IBS_CAPS_AVAIL			(1U<<0)
+#define IBS_CAPS_RDWROPCNT		(1U<<3)
+#define IBS_CAPS_OPCNT			(1U<<4)
+
+/*
+ * IBS APIC setup
+ */
+#define IBSCTL				0x1cc
+#define IBSCTL_LVT_OFFSET_VALID		(1ULL<<8)
+#define IBSCTL_LVT_OFFSET_MASK		0x0F
 
 /*
  * IBS randomization macros
@@ -266,6 +273,74 @@ static void op_amd_stop_ibs(void)
 		wrmsrl(MSR_AMD64_IBSOPCTL, 0);
 }
 
+static inline int eilvt_is_available(int offset)
+{
+	/* check if we may assign a vector */
+	return !setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 1);
+}
+
+static inline int ibs_eilvt_valid(void)
+{
+	u64 val;
+	int offset;
+
+	rdmsrl(MSR_AMD64_IBSCTL, val);
+	if (!(val & IBSCTL_LVT_OFFSET_VALID)) {
+		pr_err(FW_BUG "cpu %d, invalid IBS "
+		       "interrupt offset %d (MSR%08X=0x%016llx)",
+		       smp_processor_id(), offset,
+		       MSR_AMD64_IBSCTL, val);
+		return 0;
+	}
+
+	offset = val & IBSCTL_LVT_OFFSET_MASK;
+
+	if (eilvt_is_available(offset))
+		return !0;
+
+	pr_err(FW_BUG "cpu %d, IBS interrupt offset %d "
+	       "not available (MSR%08X=0x%016llx)",
+	       smp_processor_id(), offset,
+	       MSR_AMD64_IBSCTL, val);
+
+	return 0;
+}
+
+static inline int get_ibs_offset(void)
+{
+	u64 val;
+
+	rdmsrl(MSR_AMD64_IBSCTL, val);
+	if (!(val & IBSCTL_LVT_OFFSET_VALID))
+		return -EINVAL;
+
+	return val & IBSCTL_LVT_OFFSET_MASK;
+}
+
+static void setup_APIC_ibs(void)
+{
+	int offset;
+
+	offset = get_ibs_offset();
+	if (offset < 0)
+		goto failed;
+
+	if (!setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_NMI, 0))
+		return;
+failed:
+	pr_warn("oprofile: IBS APIC setup failed on cpu #%d\n",
+		smp_processor_id());
+}
+
+static void clear_APIC_ibs(void)
+{
+	int offset;
+
+	offset = get_ibs_offset();
+	if (offset >= 0)
+		setup_APIC_eilvt(offset, 0, APIC_EILVT_MSG_FIX, 1);
+}
+
 #ifdef CONFIG_OPROFILE_EVENT_MULTIPLEX
 
 static void op_mux_switch_ctrl(struct op_x86_model_spec const *model,
@@ -376,13 +451,13 @@ static void op_amd_setup_ctrs(struct op_x86_model_spec const *model,
 	}
 
 	if (ibs_caps)
-		setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_NMI, 0);
+		setup_APIC_ibs();
 }
 
 static void op_amd_cpu_shutdown(void)
 {
 	if (ibs_caps)
-		setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1);
+		clear_APIC_ibs();
 }
 
 static int op_amd_check_ctrs(struct pt_regs * const regs,
@@ -445,16 +520,11 @@ static void op_amd_stop(struct op_msrs const * const msrs)
 	op_amd_stop_ibs();
 }
 
-static int __init_ibs_nmi(void)
+static int setup_ibs_ctl(int ibs_eilvt_off)
 {
-#define IBSCTL_LVTOFFSETVAL		(1 << 8)
-#define IBSCTL				0x1cc
 	struct pci_dev *cpu_cfg;
 	int nodes;
 	u32 value = 0;
-	u8 ibs_eilvt_off;
-
-	ibs_eilvt_off = setup_APIC_eilvt_ibs(0, APIC_EILVT_MSG_FIX, 1);
 
 	nodes = 0;
 	cpu_cfg = NULL;
@@ -466,21 +536,60 @@ static int __init_ibs_nmi(void)
 			break;
 		++nodes;
 		pci_write_config_dword(cpu_cfg, IBSCTL, ibs_eilvt_off
-				       | IBSCTL_LVTOFFSETVAL);
+				       | IBSCTL_LVT_OFFSET_VALID);
 		pci_read_config_dword(cpu_cfg, IBSCTL, &value);
-		if (value != (ibs_eilvt_off | IBSCTL_LVTOFFSETVAL)) {
+		if (value != (ibs_eilvt_off | IBSCTL_LVT_OFFSET_VALID)) {
 			pci_dev_put(cpu_cfg);
 			printk(KERN_DEBUG "Failed to setup IBS LVT offset, "
-				"IBSCTL = 0x%08x", value);
-			return 1;
+			       "IBSCTL = 0x%08x\n", value);
+			return -EINVAL;
 		}
 	} while (1);
 
 	if (!nodes) {
-		printk(KERN_DEBUG "No CPU node configured for IBS");
-		return 1;
+		printk(KERN_DEBUG "No CPU node configured for IBS\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+static int force_ibs_eilvt_setup(void)
+{
+	int i;
+	int ret;
+
+	/* find the next free available EILVT entry */
+	for (i = 1; i < 4; i++) {
+		if (!eilvt_is_available(i))
+			continue;
+		ret = setup_ibs_ctl(i);
+		if (ret)
+			return ret;
+		return 0;
 	}
 
+	printk(KERN_DEBUG "No EILVT entry available\n");
+
+	return -EBUSY;
+}
+
+static int __init_ibs_nmi(void)
+{
+	int ret;
+
+	if (ibs_eilvt_valid())
+		return 0;
+
+	ret = force_ibs_eilvt_setup();
+	if (ret)
+		return ret;
+
+	if (!ibs_eilvt_valid())
+		return -EFAULT;
+
+	pr_err(FW_BUG "workaround enabled for IBS LVT offset\n");
+
 	return 0;
 }
 

arch/xtensa/kernel/irq.c

@@ -92,7 +92,7 @@ int show_interrupts(struct seq_file *p, void *v)
 		for_each_online_cpu(j)
 			seq_printf(p, "%10u ", kstat_irqs_cpu(i, j));
 #endif
-		seq_printf(p, " %14s", irq_desc[i].chip->typename);
+		seq_printf(p, " %14s", irq_desc[i].chip->name);
 		seq_printf(p, "  %s", action->name);
 
 		for (action=action->next; action; action = action->next)

drivers/isdn/act2000/act2000.h

@@ -141,9 +141,9 @@ typedef struct irq_data_isa {
 	__u8            rcvhdr[8];
 } irq_data_isa;
 
-typedef union irq_data {
+typedef union act2000_irq_data {
 	irq_data_isa isa;
-} irq_data;
+} act2000_irq_data;
 
 /*
  * Per card driver data
@@ -176,7 +176,7 @@ typedef struct act2000_card {
 	char   *status_buf_read;
 	char   *status_buf_write;
 	char   *status_buf_end;
-	irq_data idat;			/* Data used for IRQ handler        */
+	act2000_irq_data idat;		/* Data used for IRQ handler        */
 	isdn_if interface;		/* Interface to upper layer         */
 	char regname[35];		/* Name used for request_region     */
 } act2000_card;

drivers/isdn/hisax/config.c

@@ -801,6 +801,16 @@ static void closecard(int cardnr)
 	ll_unload(csta);
 }
 
+static irqreturn_t card_irq(int intno, void *dev_id)
+{
+	struct IsdnCardState *cs = dev_id;
+	irqreturn_t ret = cs->irq_func(intno, cs);
+
+	if (ret == IRQ_HANDLED)
+		cs->irq_cnt++;
+	return ret;
+}
+
 static int init_card(struct IsdnCardState *cs)
 {
 	int 	irq_cnt, cnt = 3, ret;
@@ -809,10 +819,10 @@ static int init_card(struct IsdnCardState *cs)
 		ret = cs->cardmsg(cs, CARD_INIT, NULL);
 		return(ret);
 	}
-	irq_cnt = kstat_irqs(cs->irq);
+	irq_cnt = cs->irq_cnt = 0;
 	printk(KERN_INFO "%s: IRQ %d count %d\n", CardType[cs->typ],
 	       cs->irq, irq_cnt);
-	if (request_irq(cs->irq, cs->irq_func, cs->irq_flags, "HiSax", cs)) {
+	if (request_irq(cs->irq, card_irq, cs->irq_flags, "HiSax", cs)) {
 		printk(KERN_WARNING "HiSax: couldn't get interrupt %d\n",
 		       cs->irq);
 		return 1;
@@ -822,8 +832,8 @@ static int init_card(struct IsdnCardState *cs)
 		/* Timeout 10ms */
 		msleep(10);
 		printk(KERN_INFO "%s: IRQ %d count %d\n",
-		       CardType[cs->typ], cs->irq, kstat_irqs(cs->irq));
-		if (kstat_irqs(cs->irq) == irq_cnt) {
+		       CardType[cs->typ], cs->irq, cs->irq_cnt);
+		if (cs->irq_cnt == irq_cnt) {
 			printk(KERN_WARNING
 			       "%s: IRQ(%d) getting no interrupts during init %d\n",
 			       CardType[cs->typ], cs->irq, 4 - cnt);

drivers/isdn/hisax/hisax.h

@@ -959,6 +959,7 @@ struct IsdnCardState {
 	u_long		event;
 	struct work_struct tqueue;
 	struct timer_list dbusytimer;
+	unsigned int	irq_cnt;
 #ifdef ERROR_STATISTIC
 	int		err_crc;
 	int		err_tx;

drivers/mfd/twl4030-irq.c

@@ -78,7 +78,7 @@ struct sih {
 	u8	irq_lines;		/* number of supported irq lines */
 
 	/* SIR ignored -- set interrupt, for testing only */
-	struct irq_data {
+	struct sih_irq_data {
 		u8	isr_offset;
 		u8	imr_offset;
 	} mask[2];
@@ -810,7 +810,7 @@ int twl4030_init_irq(int irq_num, unsigned irq_base, unsigned irq_end)
 	twl4030_irq_chip = dummy_irq_chip;
 	twl4030_irq_chip.name = "twl4030";
 
-	twl4030_sih_irq_chip.ack = dummy_irq_chip.ack;
+	twl4030_sih_irq_chip.irq_ack = dummy_irq_chip.irq_ack;
 
 	for (i = irq_base; i < irq_end; i++) {
 		set_irq_chip_and_handler(i, &twl4030_irq_chip,

drivers/pci/dmar.c

@@ -1221,9 +1221,9 @@ const char *dmar_get_fault_reason(u8 fault_reason, int *fault_type)
 	}
 }
 
-void dmar_msi_unmask(unsigned int irq)
+void dmar_msi_unmask(struct irq_data *data)
 {
-	struct intel_iommu *iommu = get_irq_data(irq);
+	struct intel_iommu *iommu = irq_data_get_irq_data(data);
 	unsigned long flag;
 
 	/* unmask it */
@@ -1234,10 +1234,10 @@ void dmar_msi_unmask(unsigned int irq)
 	spin_unlock_irqrestore(&iommu->register_lock, flag);
 }
 
-void dmar_msi_mask(unsigned int irq)
+void dmar_msi_mask(struct irq_data *data)
 {
 	unsigned long flag;
-	struct intel_iommu *iommu = get_irq_data(irq);
+	struct intel_iommu *iommu = irq_data_get_irq_data(data);
 
 	/* mask it */
 	spin_lock_irqsave(&iommu->register_lock, flag);

drivers/pci/htirq.c

@@ -57,28 +57,22 @@ void fetch_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg)
 	*msg = cfg->msg;
 }
 
-void mask_ht_irq(unsigned int irq)
+void mask_ht_irq(struct irq_data *data)
 {
-	struct ht_irq_cfg *cfg;
-	struct ht_irq_msg msg;
-
-	cfg = get_irq_data(irq);
+	struct ht_irq_cfg *cfg = irq_data_get_irq_data(data);
+	struct ht_irq_msg msg = cfg->msg;
 
-	msg = cfg->msg;
 	msg.address_lo |= 1;
-	write_ht_irq_msg(irq, &msg);
+	write_ht_irq_msg(data->irq, &msg);
 }
 
-void unmask_ht_irq(unsigned int irq)
+void unmask_ht_irq(struct irq_data *data)
 {
-	struct ht_irq_cfg *cfg;
-	struct ht_irq_msg msg;
-
-	cfg = get_irq_data(irq);
+	struct ht_irq_cfg *cfg = irq_data_get_irq_data(data);
+	struct ht_irq_msg msg = cfg->msg;
 
-	msg = cfg->msg;
 	msg.address_lo &= ~1;
-	write_ht_irq_msg(irq, &msg);
+	write_ht_irq_msg(data->irq, &msg);
 }
 
 /**

drivers/pci/intr_remapping.c

@@ -46,109 +46,24 @@ static __init int setup_intremap(char *str)
 }
 early_param("intremap", setup_intremap);
 
-struct irq_2_iommu {
-	struct intel_iommu *iommu;
-	u16 irte_index;
-	u16 sub_handle;
-	u8  irte_mask;
-};
-
-#ifdef CONFIG_GENERIC_HARDIRQS
-static struct irq_2_iommu *get_one_free_irq_2_iommu(int node)
-{
-	struct irq_2_iommu *iommu;
-
-	iommu = kzalloc_node(sizeof(*iommu), GFP_ATOMIC, node);
-	printk(KERN_DEBUG "alloc irq_2_iommu on node %d\n", node);
-
-	return iommu;
-}
-
-static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
-{
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-
-	if (WARN_ON_ONCE(!desc))
-		return NULL;
-
-	return desc->irq_2_iommu;
-}
-
-static struct irq_2_iommu *irq_2_iommu_alloc(unsigned int irq)
-{
-	struct irq_desc *desc;
-	struct irq_2_iommu *irq_iommu;
-
-	desc = irq_to_desc(irq);
-	if (!desc) {
-		printk(KERN_INFO "can not get irq_desc for %d\n", irq);
-		return NULL;
-	}
-
-	irq_iommu = desc->irq_2_iommu;
-
-	if (!irq_iommu)
-		desc->irq_2_iommu = get_one_free_irq_2_iommu(irq_node(irq));
-
-	return desc->irq_2_iommu;
-}
-
-#else /* !CONFIG_SPARSE_IRQ */
-
-static struct irq_2_iommu irq_2_iommuX[NR_IRQS];
-
-static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
-{
-	if (irq < nr_irqs)
-		return &irq_2_iommuX[irq];
-
-	return NULL;
-}
-static struct irq_2_iommu *irq_2_iommu_alloc(unsigned int irq)
-{
-	return irq_2_iommu(irq);
-}
-#endif
-
 static DEFINE_SPINLOCK(irq_2_ir_lock);
 
-static struct irq_2_iommu *valid_irq_2_iommu(unsigned int irq)
-{
-	struct irq_2_iommu *irq_iommu;
-
-	irq_iommu = irq_2_iommu(irq);
-
-	if (!irq_iommu)
-		return NULL;
-
-	if (!irq_iommu->iommu)
-		return NULL;
-
-	return irq_iommu;
-}
-
-int irq_remapped(int irq)
+static struct irq_2_iommu *irq_2_iommu(unsigned int irq)
 {
-	return valid_irq_2_iommu(irq) != NULL;
+	struct irq_cfg *cfg = get_irq_chip_data(irq);
+	return cfg ? &cfg->irq_2_iommu : NULL;
 }
 
 int get_irte(int irq, struct irte *entry)
 {
-	int index;
-	struct irq_2_iommu *irq_iommu;
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
 	unsigned long flags;
+	int index;
 
-	if (!entry)
+	if (!entry || !irq_iommu)
 		return -1;
 
 	spin_lock_irqsave(&irq_2_ir_lock, flags);
-	irq_iommu = valid_irq_2_iommu(irq);
-	if (!irq_iommu) {
-		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-		return -1;
-	}
 
 	index = irq_iommu->irte_index + irq_iommu->sub_handle;
 	*entry = *(irq_iommu->iommu->ir_table->base + index);
@@ -160,20 +75,14 @@ int get_irte(int irq, struct irte *entry)
 int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
 {
 	struct ir_table *table = iommu->ir_table;
-	struct irq_2_iommu *irq_iommu;
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
 	u16 index, start_index;
 	unsigned int mask = 0;
 	unsigned long flags;
 	int i;
 
-	if (!count)
-		return -1;
-
-#ifndef CONFIG_SPARSE_IRQ
-	/* protect irq_2_iommu_alloc later */
-	if (irq >= nr_irqs)
+	if (!count || !irq_iommu)
 		return -1;
-#endif
 
 	/*
 	 * start the IRTE search from index 0.
@@ -214,13 +123,6 @@ int alloc_irte(struct intel_iommu *iommu, int irq, u16 count)
 	for (i = index; i < index + count; i++)
 		table->base[i].present = 1;
 
-	irq_iommu = irq_2_iommu_alloc(irq);
-	if (!irq_iommu) {
-		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-		printk(KERN_ERR "can't allocate irq_2_iommu\n");
-		return -1;
-	}
-
 	irq_iommu->iommu = iommu;
 	irq_iommu->irte_index =  index;
 	irq_iommu->sub_handle = 0;
@@ -244,17 +146,14 @@ static int qi_flush_iec(struct intel_iommu *iommu, int index, int mask)
 
 int map_irq_to_irte_handle(int irq, u16 *sub_handle)
 {
-	int index;
-	struct irq_2_iommu *irq_iommu;
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
 	unsigned long flags;
+	int index;
 
-	spin_lock_irqsave(&irq_2_ir_lock, flags);
-	irq_iommu = valid_irq_2_iommu(irq);
-	if (!irq_iommu) {
-		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+	if (!irq_iommu)
 		return -1;
-	}
 
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
 	*sub_handle = irq_iommu->sub_handle;
 	index = irq_iommu->irte_index;
 	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
@@ -263,18 +162,13 @@ int map_irq_to_irte_handle(int irq, u16 *sub_handle)
 
 int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
 {
-	struct irq_2_iommu *irq_iommu;
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
 	unsigned long flags;
 
-	spin_lock_irqsave(&irq_2_ir_lock, flags);
-
-	irq_iommu = irq_2_iommu_alloc(irq);
-
-	if (!irq_iommu) {
-		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-		printk(KERN_ERR "can't allocate irq_2_iommu\n");
+	if (!irq_iommu)
 		return -1;
-	}
+
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
 
 	irq_iommu->iommu = iommu;
 	irq_iommu->irte_index = index;
@@ -286,43 +180,18 @@ int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index, u16 subhandle)
 	return 0;
 }
 
-int clear_irte_irq(int irq, struct intel_iommu *iommu, u16 index)
-{
-	struct irq_2_iommu *irq_iommu;
-	unsigned long flags;
-
-	spin_lock_irqsave(&irq_2_ir_lock, flags);
-	irq_iommu = valid_irq_2_iommu(irq);
-	if (!irq_iommu) {
-		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-		return -1;
-	}
-
-	irq_iommu->iommu = NULL;
-	irq_iommu->irte_index = 0;
-	irq_iommu->sub_handle = 0;
-	irq_2_iommu(irq)->irte_mask = 0;
-
-	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-
-	return 0;
-}
-
 int modify_irte(int irq, struct irte *irte_modified)
 {
-	int rc;
-	int index;
-	struct irte *irte;
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
 	struct intel_iommu *iommu;
-	struct irq_2_iommu *irq_iommu;
 	unsigned long flags;
+	struct irte *irte;
+	int rc, index;
 
-	spin_lock_irqsave(&irq_2_ir_lock, flags);
-	irq_iommu = valid_irq_2_iommu(irq);
-	if (!irq_iommu) {
-		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+	if (!irq_iommu)
 		return -1;
-	}
+
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
 
 	iommu = irq_iommu->iommu;
 
@@ -339,31 +208,6 @@ int modify_irte(int irq, struct irte *irte_modified)
 	return rc;
 }
 
-int flush_irte(int irq)
-{
-	int rc;
-	int index;
-	struct intel_iommu *iommu;
-	struct irq_2_iommu *irq_iommu;
-	unsigned long flags;
-
-	spin_lock_irqsave(&irq_2_ir_lock, flags);
-	irq_iommu = valid_irq_2_iommu(irq);
-	if (!irq_iommu) {
-		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-		return -1;
-	}
-
-	iommu = irq_iommu->iommu;
-
-	index = irq_iommu->irte_index + irq_iommu->sub_handle;
-
-	rc = qi_flush_iec(iommu, index, irq_iommu->irte_mask);
-	spin_unlock_irqrestore(&irq_2_ir_lock, flags);
-
-	return rc;
-}
-
 struct intel_iommu *map_hpet_to_ir(u8 hpet_id)
 {
 	int i;
@@ -420,16 +264,14 @@ static int clear_entries(struct irq_2_iommu *irq_iommu)
 
 int free_irte(int irq)
 {
-	int rc = 0;
-	struct irq_2_iommu *irq_iommu;
+	struct irq_2_iommu *irq_iommu = irq_2_iommu(irq);
 	unsigned long flags;
+	int rc;
 
-	spin_lock_irqsave(&irq_2_ir_lock, flags);
-	irq_iommu = valid_irq_2_iommu(irq);
-	if (!irq_iommu) {
-		spin_unlock_irqrestore(&irq_2_ir_lock, flags);
+	if (!irq_iommu)
 		return -1;
-	}
+
+	spin_lock_irqsave(&irq_2_ir_lock, flags);
 
 	rc = clear_entries(irq_iommu);
 

drivers/pci/msi.c

@@ -170,33 +170,31 @@ static void msix_mask_irq(struct msi_desc *desc, u32 flag)
 	desc->masked = __msix_mask_irq(desc, flag);
 }
 
-static void msi_set_mask_bit(unsigned irq, u32 flag)
+static void msi_set_mask_bit(struct irq_data *data, u32 flag)
 {
-	struct msi_desc *desc = get_irq_msi(irq);
+	struct msi_desc *desc = irq_data_get_msi(data);
 
 	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;
+		unsigned offset = data->irq - desc->dev->irq;
 		msi_mask_irq(desc, 1 << offset, flag << offset);
 	}
 }
 
-void mask_msi_irq(unsigned int irq)
+void mask_msi_irq(struct irq_data *data)
 {
-	msi_set_mask_bit(irq, 1);
+	msi_set_mask_bit(data, 1);
 }
 
-void unmask_msi_irq(unsigned int irq)
+void unmask_msi_irq(struct irq_data *data)
 {
-	msi_set_mask_bit(irq, 0);
+	msi_set_mask_bit(data, 0);
 }
 
-void read_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
+void __read_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 {
-	struct msi_desc *entry = get_irq_desc_msi(desc);
-
 	BUG_ON(entry->dev->current_state != PCI_D0);
 
 	if (entry->msi_attrib.is_msix) {
@@ -227,15 +225,13 @@ void read_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
 
 void read_msi_msg(unsigned int irq, struct msi_msg *msg)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct msi_desc *entry = get_irq_msi(irq);
 
-	read_msi_msg_desc(desc, msg);
+	__read_msi_msg(entry, msg);
 }
 
-void get_cached_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
+void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 {
-	struct msi_desc *entry = get_irq_desc_msi(desc);
-
 	/* Assert that the cache is valid, assuming that
 	 * valid messages are not all-zeroes. */
 	BUG_ON(!(entry->msg.address_hi | entry->msg.address_lo |
@@ -246,15 +242,13 @@ void get_cached_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
 
 void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct msi_desc *entry = get_irq_msi(irq);
 
-	get_cached_msi_msg_desc(desc, msg);
+	__get_cached_msi_msg(entry, msg);
 }
 
-void write_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
+void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg)
 {
-	struct msi_desc *entry = get_irq_desc_msi(desc);
-
 	if (entry->dev->current_state != PCI_D0) {
 		/* Don't touch the hardware now */
 	} else if (entry->msi_attrib.is_msix) {
@@ -292,9 +286,9 @@ void write_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg)
 
 void write_msi_msg(unsigned int irq, struct msi_msg *msg)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct msi_desc *entry = get_irq_msi(irq);
 
-	write_msi_msg_desc(desc, msg);
+	__write_msi_msg(entry, msg);
 }
 
 static void free_msi_irqs(struct pci_dev *dev)

drivers/xen/events.c

@@ -338,30 +338,29 @@ static void unmask_evtchn(int port)
 
 static int find_unbound_irq(void)
 {
-	int irq;
-	struct irq_desc *desc;
+	struct irq_data *data;
+	int irq, res;
 
 	for (irq = 0; irq < nr_irqs; irq++) {
-		desc = irq_to_desc(irq);
+		data = irq_get_irq_data(irq);
 		/* only 0->15 have init'd desc; handle irq > 16 */
-		if (desc == NULL)
+		if (!data)
 			break;
-		if (desc->chip == &no_irq_chip)
+		if (data->chip == &no_irq_chip)
 			break;
-		if (desc->chip != &xen_dynamic_chip)
+		if (data->chip != &xen_dynamic_chip)
 			continue;
 		if (irq_info[irq].type == IRQT_UNBOUND)
-			break;
+			return irq;
 	}
 
 	if (irq == nr_irqs)
 		panic("No available IRQ to bind to: increase nr_irqs!\n");
 
-	desc = irq_to_desc_alloc_node(irq, 0);
-	if (WARN_ON(desc == NULL))
-		return -1;
+	res = irq_alloc_desc_at(irq, 0);
 
-	dynamic_irq_init_keep_chip_data(irq);
+	if (WARN_ON(res != irq))
+		return -1;
 
 	return irq;
 }
@@ -495,7 +494,7 @@ static void unbind_from_irq(unsigned int irq)
 	if (irq_info[irq].type != IRQT_UNBOUND) {
 		irq_info[irq] = mk_unbound_info();
 
-		dynamic_irq_cleanup(irq);
+		irq_free_desc(irq);
 	}
 
 	spin_unlock(&irq_mapping_update_lock);

include/linux/dmar.h

@@ -106,6 +106,7 @@ struct irte {
 		__u64 high;
 	};
 };
+
 #ifdef CONFIG_INTR_REMAP
 extern int intr_remapping_enabled;
 extern int intr_remapping_supported(void);
@@ -119,11 +120,8 @@ extern int alloc_irte(struct intel_iommu *iommu, int irq, u16 count);
 extern int set_irte_irq(int irq, struct intel_iommu *iommu, u16 index,
    			u16 sub_handle);
 extern int map_irq_to_irte_handle(int irq, u16 *sub_handle);
-extern int clear_irte_irq(int irq, struct intel_iommu *iommu, u16 index);
-extern int flush_irte(int irq);
 extern int free_irte(int irq);
 
-extern int irq_remapped(int irq);
 extern struct intel_iommu *map_dev_to_ir(struct pci_dev *dev);
 extern struct intel_iommu *map_ioapic_to_ir(int apic);
 extern struct intel_iommu *map_hpet_to_ir(u8 id);
@@ -177,7 +175,6 @@ static inline int set_msi_sid(struct irte *irte, struct pci_dev *dev)
 	return 0;
 }
 
-#define irq_remapped(irq)		(0)
 #define enable_intr_remapping(mode)	(-1)
 #define disable_intr_remapping()	(0)
 #define reenable_intr_remapping(mode)	(0)
@@ -187,8 +184,9 @@ static inline int set_msi_sid(struct irte *irte, struct pci_dev *dev)
 /* Can't use the common MSI interrupt functions
  * since DMAR is not a pci device
  */
-extern void dmar_msi_unmask(unsigned int irq);
-extern void dmar_msi_mask(unsigned int irq);
+struct irq_data;
+extern void dmar_msi_unmask(struct irq_data *data);
+extern void dmar_msi_mask(struct irq_data *data);
 extern void dmar_msi_read(int irq, struct msi_msg *msg);
 extern void dmar_msi_write(int irq, struct msi_msg *msg);
 extern int dmar_set_interrupt(struct intel_iommu *iommu);

include/linux/htirq.h

@@ -9,8 +9,9 @@ struct ht_irq_msg {
 /* Helper functions.. */
 void fetch_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg);
 void write_ht_irq_msg(unsigned int irq, struct ht_irq_msg *msg);
-void mask_ht_irq(unsigned int irq);
-void unmask_ht_irq(unsigned int irq);
+struct irq_data;
+void mask_ht_irq(struct irq_data *data);
+void unmask_ht_irq(struct irq_data *data);
 
 /* The arch hook for getting things started */
 int arch_setup_ht_irq(unsigned int irq, struct pci_dev *dev);

include/linux/interrupt.h

@@ -647,11 +647,8 @@ static inline void init_irq_proc(void)
 struct seq_file;
 int show_interrupts(struct seq_file *p, void *v);
 
-struct irq_desc;
-
 extern int early_irq_init(void);
 extern int arch_probe_nr_irqs(void);
 extern int arch_early_irq_init(void);
-extern int arch_init_chip_data(struct irq_desc *desc, int node);
 
 #endif

include/linux/irq.h

@@ -72,6 +72,10 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 #define IRQ_ONESHOT		0x08000000	/* IRQ is not unmasked after hardirq */
 #define IRQ_NESTED_THREAD	0x10000000	/* IRQ is nested into another, no own handler thread */
 
+#define IRQF_MODIFY_MASK	\
+	(IRQ_TYPE_SENSE_MASK | IRQ_NOPROBE | IRQ_NOREQUEST | \
+	 IRQ_NOAUTOEN | IRQ_MOVE_PCNTXT | IRQ_LEVEL)
+
 #ifdef CONFIG_IRQ_PER_CPU
 # define CHECK_IRQ_PER_CPU(var) ((var) & IRQ_PER_CPU)
 # define IRQ_NO_BALANCING_MASK	(IRQ_PER_CPU | IRQ_NO_BALANCING)
@@ -80,36 +84,77 @@ typedef	void (*irq_flow_handler_t)(unsigned int irq,
 # define IRQ_NO_BALANCING_MASK	IRQ_NO_BALANCING
 #endif
 
-struct proc_dir_entry;
 struct msi_desc;
 
+/**
+ * struct irq_data - per irq and irq chip data passed down to chip functions
+ * @irq:		interrupt number
+ * @node:		node index useful for balancing
+ * @chip:		low level interrupt hardware access
+ * @handler_data:	per-IRQ data for the irq_chip methods
+ * @chip_data:		platform-specific per-chip private data for the chip
+ *			methods, to allow shared chip implementations
+ * @msi_desc:		MSI descriptor
+ * @affinity:		IRQ affinity on SMP
+ *
+ * The fields here need to overlay the ones in irq_desc until we
+ * cleaned up the direct references and switched everything over to
+ * irq_data.
+ */
+struct irq_data {
+	unsigned int		irq;
+	unsigned int		node;
+	struct irq_chip		*chip;
+	void			*handler_data;
+	void			*chip_data;
+	struct msi_desc		*msi_desc;
+#ifdef CONFIG_SMP
+	cpumask_var_t		affinity;
+#endif
+};
+
 /**
  * struct irq_chip - hardware interrupt chip descriptor
  *
  * @name:		name for /proc/interrupts
- * @startup:		start up the interrupt (defaults to ->enable if NULL)
- * @shutdown:		shut down the interrupt (defaults to ->disable if NULL)
- * @enable:		enable the interrupt (defaults to chip->unmask if NULL)
- * @disable:		disable the interrupt
- * @ack:		start of a new interrupt
- * @mask:		mask an interrupt source
- * @mask_ack:		ack and mask an interrupt source
- * @unmask:		unmask an interrupt source
- * @eoi:		end of interrupt - chip level
- * @end:		end of interrupt - flow level
- * @set_affinity:	set the CPU affinity on SMP machines
- * @retrigger:		resend an IRQ to the CPU
- * @set_type:		set the flow type (IRQ_TYPE_LEVEL/etc.) of an IRQ
- * @set_wake:		enable/disable power-management wake-on of an IRQ
+ * @startup:		deprecated, replaced by irq_startup
+ * @shutdown:		deprecated, replaced by irq_shutdown
+ * @enable:		deprecated, replaced by irq_enable
+ * @disable:		deprecated, replaced by irq_disable
+ * @ack:		deprecated, replaced by irq_ack
+ * @mask:		deprecated, replaced by irq_mask
+ * @mask_ack:		deprecated, replaced by irq_mask_ack
+ * @unmask:		deprecated, replaced by irq_unmask
+ * @eoi:		deprecated, replaced by irq_eoi
+ * @end:		deprecated, will go away with __do_IRQ()
+ * @set_affinity:	deprecated, replaced by irq_set_affinity
+ * @retrigger:		deprecated, replaced by irq_retrigger
+ * @set_type:		deprecated, replaced by irq_set_type
+ * @set_wake:		deprecated, replaced by irq_wake
+ * @bus_lock:		deprecated, replaced by irq_bus_lock
+ * @bus_sync_unlock:	deprecated, replaced by irq_bus_sync_unlock
  *
- * @bus_lock:		function to lock access to slow bus (i2c) chips
- * @bus_sync_unlock:	function to sync and unlock slow bus (i2c) chips
+ * @irq_startup:	start up the interrupt (defaults to ->enable if NULL)
+ * @irq_shutdown:	shut down the interrupt (defaults to ->disable if NULL)
+ * @irq_enable:		enable the interrupt (defaults to chip->unmask if NULL)
+ * @irq_disable:	disable the interrupt
+ * @irq_ack:		start of a new interrupt
+ * @irq_mask:		mask an interrupt source
+ * @irq_mask_ack:	ack and mask an interrupt source
+ * @irq_unmask:		unmask an interrupt source
+ * @irq_eoi:		end of interrupt
+ * @irq_set_affinity:	set the CPU affinity on SMP machines
+ * @irq_retrigger:	resend an IRQ to the CPU
+ * @irq_set_type:	set the flow type (IRQ_TYPE_LEVEL/etc.) of an IRQ
+ * @irq_set_wake:	enable/disable power-management wake-on of an IRQ
+ * @irq_bus_lock:	function to lock access to slow bus (i2c) chips
+ * @irq_bus_sync_unlock:function to sync and unlock slow bus (i2c) chips
  *
  * @release:		release function solely used by UML
- * @typename:		obsoleted by name, kept as migration helper
  */
 struct irq_chip {
 	const char	*name;
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
 	unsigned int	(*startup)(unsigned int irq);
 	void		(*shutdown)(unsigned int irq);
 	void		(*enable)(unsigned int irq);
@@ -130,154 +175,66 @@ struct irq_chip {
 
 	void		(*bus_lock)(unsigned int irq);
 	void		(*bus_sync_unlock)(unsigned int irq);
+#endif
+	unsigned int	(*irq_startup)(struct irq_data *data);
+	void		(*irq_shutdown)(struct irq_data *data);
+	void		(*irq_enable)(struct irq_data *data);
+	void		(*irq_disable)(struct irq_data *data);
+
+	void		(*irq_ack)(struct irq_data *data);
+	void		(*irq_mask)(struct irq_data *data);
+	void		(*irq_mask_ack)(struct irq_data *data);
+	void		(*irq_unmask)(struct irq_data *data);
+	void		(*irq_eoi)(struct irq_data *data);
+
+	int		(*irq_set_affinity)(struct irq_data *data, const struct cpumask *dest, bool force);
+	int		(*irq_retrigger)(struct irq_data *data);
+	int		(*irq_set_type)(struct irq_data *data, unsigned int flow_type);
+	int		(*irq_set_wake)(struct irq_data *data, unsigned int on);
+
+	void		(*irq_bus_lock)(struct irq_data *data);
+	void		(*irq_bus_sync_unlock)(struct irq_data *data);
 
 	/* Currently used only by UML, might disappear one day.*/
 #ifdef CONFIG_IRQ_RELEASE_METHOD
 	void		(*release)(unsigned int irq, void *dev_id);
 #endif
-	/*
-	 * For compatibility, ->typename is copied into ->name.
-	 * Will disappear.
-	 */
-	const char	*typename;
 };
 
-struct timer_rand_state;
-struct irq_2_iommu;
-/**
- * struct irq_desc - interrupt descriptor
- * @irq:		interrupt number for this descriptor
- * @timer_rand_state:	pointer to timer rand state struct
- * @kstat_irqs:		irq stats per cpu
- * @irq_2_iommu:	iommu with this irq
- * @handle_irq:		highlevel irq-events handler [if NULL, __do_IRQ()]
- * @chip:		low level interrupt hardware access
- * @msi_desc:		MSI descriptor
- * @handler_data:	per-IRQ data for the irq_chip methods
- * @chip_data:		platform-specific per-chip private data for the chip
- *			methods, to allow shared chip implementations
- * @action:		the irq action chain
- * @status:		status information
- * @depth:		disable-depth, for nested irq_disable() calls
- * @wake_depth:		enable depth, for multiple set_irq_wake() callers
- * @irq_count:		stats field to detect stalled irqs
- * @last_unhandled:	aging timer for unhandled count
- * @irqs_unhandled:	stats field for spurious unhandled interrupts
- * @lock:		locking for SMP
- * @affinity:		IRQ affinity on SMP
- * @node:		node index useful for balancing
- * @pending_mask:	pending rebalanced interrupts
- * @threads_active:	number of irqaction threads currently running
- * @wait_for_threads:	wait queue for sync_irq to wait for threaded handlers
- * @dir:		/proc/irq/ procfs entry
- * @name:		flow handler name for /proc/interrupts output
- */
-struct irq_desc {
-	unsigned int		irq;
-	struct timer_rand_state *timer_rand_state;
-	unsigned int            *kstat_irqs;
-#ifdef CONFIG_INTR_REMAP
-	struct irq_2_iommu      *irq_2_iommu;
-#endif
-	irq_flow_handler_t	handle_irq;
-	struct irq_chip		*chip;
-	struct msi_desc		*msi_desc;
-	void			*handler_data;
-	void			*chip_data;
-	struct irqaction	*action;	/* IRQ action list */
-	unsigned int		status;		/* IRQ status */
-
-	unsigned int		depth;		/* nested irq disables */
-	unsigned int		wake_depth;	/* nested wake enables */
-	unsigned int		irq_count;	/* For detecting broken IRQs */
-	unsigned long		last_unhandled;	/* Aging timer for unhandled count */
-	unsigned int		irqs_unhandled;
-	raw_spinlock_t		lock;
-#ifdef CONFIG_SMP
-	cpumask_var_t		affinity;
-	const struct cpumask	*affinity_hint;
-	unsigned int		node;
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-	cpumask_var_t		pending_mask;
-#endif
-#endif
-	atomic_t		threads_active;
-	wait_queue_head_t       wait_for_threads;
-#ifdef CONFIG_PROC_FS
-	struct proc_dir_entry	*dir;
-#endif
-	const char		*name;
-} ____cacheline_internodealigned_in_smp;
+/* This include will go away once we isolated irq_desc usage to core code */
+#include <linux/irqdesc.h>
 
-extern void arch_init_copy_chip_data(struct irq_desc *old_desc,
-					struct irq_desc *desc, int node);
-extern void arch_free_chip_data(struct irq_desc *old_desc, struct irq_desc *desc);
+/*
+ * Pick up the arch-dependent methods:
+ */
+#include <asm/hw_irq.h>
 
-#ifndef CONFIG_SPARSE_IRQ
-extern struct irq_desc irq_desc[NR_IRQS];
+#ifndef NR_IRQS_LEGACY
+# define NR_IRQS_LEGACY 0
 #endif
 
-#ifdef CONFIG_NUMA_IRQ_DESC
-extern struct irq_desc *move_irq_desc(struct irq_desc *old_desc, int node);
-#else
-static inline struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
-{
-	return desc;
-}
+#ifndef ARCH_IRQ_INIT_FLAGS
+# define ARCH_IRQ_INIT_FLAGS	0
 #endif
 
-extern struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node);
-
-/*
- * Pick up the arch-dependent methods:
- */
-#include <asm/hw_irq.h>
+#define IRQ_DEFAULT_INIT_FLAGS	(IRQ_DISABLED | ARCH_IRQ_INIT_FLAGS)
 
+struct irqaction;
 extern int setup_irq(unsigned int irq, struct irqaction *new);
 extern void remove_irq(unsigned int irq, struct irqaction *act);
 
 #ifdef CONFIG_GENERIC_HARDIRQS
 
-#ifdef CONFIG_SMP
-
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-
+#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_PENDING_IRQ)
 void move_native_irq(int irq);
 void move_masked_irq(int irq);
-
-#else /* CONFIG_GENERIC_PENDING_IRQ */
-
-static inline void move_irq(int irq)
-{
-}
-
-static inline void move_native_irq(int irq)
-{
-}
-
-static inline void move_masked_irq(int irq)
-{
-}
-
-#endif /* CONFIG_GENERIC_PENDING_IRQ */
-
-#else /* CONFIG_SMP */
-
-#define move_native_irq(x)
-#define move_masked_irq(x)
-
-#endif /* CONFIG_SMP */
+#else
+static inline void move_native_irq(int irq) { }
+static inline void move_masked_irq(int irq) { }
+#endif
 
 extern int no_irq_affinity;
 
-static inline int irq_balancing_disabled(unsigned int irq)
-{
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-	return desc->status & IRQ_NO_BALANCING_MASK;
-}
-
 /* Handle irq action chains: */
 extern irqreturn_t handle_IRQ_event(unsigned int irq, struct irqaction *action);
 
@@ -293,42 +250,10 @@ extern void handle_percpu_irq(unsigned int irq, struct irq_desc *desc);
 extern void handle_bad_irq(unsigned int irq, struct irq_desc *desc);
 extern void handle_nested_irq(unsigned int irq);
 
-/*
- * Monolithic do_IRQ implementation.
- */
-#ifndef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ
-extern unsigned int __do_IRQ(unsigned int irq);
-#endif
-
-/*
- * Architectures call this to let the generic IRQ layer
- * handle an interrupt. If the descriptor is attached to an
- * irqchip-style controller then we call the ->handle_irq() handler,
- * and it calls __do_IRQ() if it's attached to an irqtype-style controller.
- */
-static inline void generic_handle_irq_desc(unsigned int irq, struct irq_desc *desc)
-{
-#ifdef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ
-	desc->handle_irq(irq, desc);
-#else
-	if (likely(desc->handle_irq))
-		desc->handle_irq(irq, desc);
-	else
-		__do_IRQ(irq);
-#endif
-}
-
-static inline void generic_handle_irq(unsigned int irq)
-{
-	generic_handle_irq_desc(irq, irq_to_desc(irq));
-}
-
 /* Handling of unhandled and spurious interrupts: */
 extern void note_interrupt(unsigned int irq, struct irq_desc *desc,
 			   irqreturn_t action_ret);
 
-/* Resending of interrupts :*/
-void check_irq_resend(struct irq_desc *desc, unsigned int irq);
 
 /* Enable/disable irq debugging output: */
 extern int noirqdebug_setup(char *str);
@@ -351,16 +276,6 @@ extern void
 __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		  const char *name);
 
-/* caller has locked the irq_desc and both params are valid */
-static inline void __set_irq_handler_unlocked(int irq,
-					      irq_flow_handler_t handler)
-{
-	struct irq_desc *desc;
-
-	desc = irq_to_desc(irq);
-	desc->handle_irq = handler;
-}
-
 /*
  * Set a highlevel flow handler for a given IRQ:
  */
@@ -384,141 +299,121 @@ set_irq_chained_handler(unsigned int irq,
 
 extern void set_irq_nested_thread(unsigned int irq, int nest);
 
-extern void set_irq_noprobe(unsigned int irq);
-extern void set_irq_probe(unsigned int irq);
+void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set);
+
+static inline void irq_set_status_flags(unsigned int irq, unsigned long set)
+{
+	irq_modify_status(irq, 0, set);
+}
+
+static inline void irq_clear_status_flags(unsigned int irq, unsigned long clr)
+{
+	irq_modify_status(irq, clr, 0);
+}
+
+static inline void set_irq_noprobe(unsigned int irq)
+{
+	irq_modify_status(irq, 0, IRQ_NOPROBE);
+}
+
+static inline void set_irq_probe(unsigned int irq)
+{
+	irq_modify_status(irq, IRQ_NOPROBE, 0);
+}
 
 /* Handle dynamic irq creation and destruction */
 extern unsigned int create_irq_nr(unsigned int irq_want, int node);
 extern int create_irq(void);
 extern void destroy_irq(unsigned int irq);
 
-/* Test to see if a driver has successfully requested an irq */
-static inline int irq_has_action(unsigned int irq)
+/*
+ * Dynamic irq helper functions. Obsolete. Use irq_alloc_desc* and
+ * irq_free_desc instead.
+ */
+extern void dynamic_irq_cleanup(unsigned int irq);
+static inline void dynamic_irq_init(unsigned int irq)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
-	return desc->action != NULL;
+	dynamic_irq_cleanup(irq);
 }
 
-/* Dynamic irq helper functions */
-extern void dynamic_irq_init(unsigned int irq);
-void dynamic_irq_init_keep_chip_data(unsigned int irq);
-extern void dynamic_irq_cleanup(unsigned int irq);
-void dynamic_irq_cleanup_keep_chip_data(unsigned int irq);
-
 /* Set/get chip/data for an IRQ: */
 extern int set_irq_chip(unsigned int irq, struct irq_chip *chip);
 extern int set_irq_data(unsigned int irq, void *data);
 extern int set_irq_chip_data(unsigned int irq, void *data);
 extern int set_irq_type(unsigned int irq, unsigned int type);
 extern int set_irq_msi(unsigned int irq, struct msi_desc *entry);
+extern struct irq_data *irq_get_irq_data(unsigned int irq);
 
-#define get_irq_chip(irq)	(irq_to_desc(irq)->chip)
-#define get_irq_chip_data(irq)	(irq_to_desc(irq)->chip_data)
-#define get_irq_data(irq)	(irq_to_desc(irq)->handler_data)
-#define get_irq_msi(irq)	(irq_to_desc(irq)->msi_desc)
-
-#define get_irq_desc_chip(desc)		((desc)->chip)
-#define get_irq_desc_chip_data(desc)	((desc)->chip_data)
-#define get_irq_desc_data(desc)		((desc)->handler_data)
-#define get_irq_desc_msi(desc)		((desc)->msi_desc)
-
-#endif /* CONFIG_GENERIC_HARDIRQS */
-
-#endif /* !CONFIG_S390 */
-
-#ifdef CONFIG_SMP
-/**
- * alloc_desc_masks - allocate cpumasks for irq_desc
- * @desc:	pointer to irq_desc struct
- * @node:	node which will be handling the cpumasks
- * @boot:	true if need bootmem
- *
- * Allocates affinity and pending_mask cpumask if required.
- * Returns true if successful (or not required).
- */
-static inline bool alloc_desc_masks(struct irq_desc *desc, int node,
-							bool boot)
+static inline struct irq_chip *get_irq_chip(unsigned int irq)
 {
-	gfp_t gfp = GFP_ATOMIC;
-
-	if (boot)
-		gfp = GFP_NOWAIT;
-
-#ifdef CONFIG_CPUMASK_OFFSTACK
-	if (!alloc_cpumask_var_node(&desc->affinity, gfp, node))
-		return false;
+	struct irq_data *d = irq_get_irq_data(irq);
+	return d ? d->chip : NULL;
+}
 
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-	if (!alloc_cpumask_var_node(&desc->pending_mask, gfp, node)) {
-		free_cpumask_var(desc->affinity);
-		return false;
-	}
-#endif
-#endif
-	return true;
+static inline struct irq_chip *irq_data_get_irq_chip(struct irq_data *d)
+{
+	return d->chip;
 }
 
-static inline void init_desc_masks(struct irq_desc *desc)
+static inline void *get_irq_chip_data(unsigned int irq)
 {
-	cpumask_setall(desc->affinity);
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-	cpumask_clear(desc->pending_mask);
-#endif
+	struct irq_data *d = irq_get_irq_data(irq);
+	return d ? d->chip_data : NULL;
 }
 
-/**
- * init_copy_desc_masks - copy cpumasks for irq_desc
- * @old_desc:	pointer to old irq_desc struct
- * @new_desc:	pointer to new irq_desc struct
- *
- * Insures affinity and pending_masks are copied to new irq_desc.
- * If !CONFIG_CPUMASKS_OFFSTACK the cpumasks are embedded in the
- * irq_desc struct so the copy is redundant.
- */
+static inline void *irq_data_get_irq_chip_data(struct irq_data *d)
+{
+	return d->chip_data;
+}
 
-static inline void init_copy_desc_masks(struct irq_desc *old_desc,
-					struct irq_desc *new_desc)
+static inline void *get_irq_data(unsigned int irq)
 {
-#ifdef CONFIG_CPUMASK_OFFSTACK
-	cpumask_copy(new_desc->affinity, old_desc->affinity);
+	struct irq_data *d = irq_get_irq_data(irq);
+	return d ? d->handler_data : NULL;
+}
 
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-	cpumask_copy(new_desc->pending_mask, old_desc->pending_mask);
-#endif
-#endif
+static inline void *irq_data_get_irq_data(struct irq_data *d)
+{
+	return d->handler_data;
 }
 
-static inline void free_desc_masks(struct irq_desc *old_desc,
-				   struct irq_desc *new_desc)
+static inline struct msi_desc *get_irq_msi(unsigned int irq)
 {
-	free_cpumask_var(old_desc->affinity);
+	struct irq_data *d = irq_get_irq_data(irq);
+	return d ? d->msi_desc : NULL;
+}
 
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-	free_cpumask_var(old_desc->pending_mask);
-#endif
+static inline struct msi_desc *irq_data_get_msi(struct irq_data *d)
+{
+	return d->msi_desc;
 }
 
-#else /* !CONFIG_SMP */
+int irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node);
+void irq_free_descs(unsigned int irq, unsigned int cnt);
+int irq_reserve_irqs(unsigned int from, unsigned int cnt);
 
-static inline bool alloc_desc_masks(struct irq_desc *desc, int node,
-								bool boot)
+static inline int irq_alloc_desc(int node)
 {
-	return true;
+	return irq_alloc_descs(-1, 0, 1, node);
 }
 
-static inline void init_desc_masks(struct irq_desc *desc)
+static inline int irq_alloc_desc_at(unsigned int at, int node)
 {
+	return irq_alloc_descs(at, at, 1, node);
 }
 
-static inline void init_copy_desc_masks(struct irq_desc *old_desc,
-					struct irq_desc *new_desc)
+static inline int irq_alloc_desc_from(unsigned int from, int node)
 {
+	return irq_alloc_descs(-1, from, 1, node);
 }
 
-static inline void free_desc_masks(struct irq_desc *old_desc,
-				   struct irq_desc *new_desc)
+static inline void irq_free_desc(unsigned int irq)
 {
+	irq_free_descs(irq, 1);
 }
-#endif	/* CONFIG_SMP */
+
+#endif /* CONFIG_GENERIC_HARDIRQS */
+
+#endif /* !CONFIG_S390 */
 
 #endif /* _LINUX_IRQ_H */

include/linux/irqdesc.h

@@ -0,0 +1,159 @@
+#ifndef _LINUX_IRQDESC_H
+#define _LINUX_IRQDESC_H
+
+/*
+ * Core internal functions to deal with irq descriptors
+ *
+ * This include will move to kernel/irq once we cleaned up the tree.
+ * For now it's included from <linux/irq.h>
+ */
+
+struct proc_dir_entry;
+struct timer_rand_state;
+/**
+ * struct irq_desc - interrupt descriptor
+ * @irq_data:		per irq and chip data passed down to chip functions
+ * @timer_rand_state:	pointer to timer rand state struct
+ * @kstat_irqs:		irq stats per cpu
+ * @handle_irq:		highlevel irq-events handler [if NULL, __do_IRQ()]
+ * @action:		the irq action chain
+ * @status:		status information
+ * @depth:		disable-depth, for nested irq_disable() calls
+ * @wake_depth:		enable depth, for multiple set_irq_wake() callers
+ * @irq_count:		stats field to detect stalled irqs
+ * @last_unhandled:	aging timer for unhandled count
+ * @irqs_unhandled:	stats field for spurious unhandled interrupts
+ * @lock:		locking for SMP
+ * @pending_mask:	pending rebalanced interrupts
+ * @threads_active:	number of irqaction threads currently running
+ * @wait_for_threads:	wait queue for sync_irq to wait for threaded handlers
+ * @dir:		/proc/irq/ procfs entry
+ * @name:		flow handler name for /proc/interrupts output
+ */
+struct irq_desc {
+
+#ifdef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
+	struct irq_data		irq_data;
+#else
+	/*
+	 * This union will go away, once we fixed the direct access to
+	 * irq_desc all over the place. The direct fields are a 1:1
+	 * overlay of irq_data.
+	 */
+	union {
+		struct irq_data		irq_data;
+		struct {
+			unsigned int		irq;
+			unsigned int		node;
+			struct irq_chip		*chip;
+			void			*handler_data;
+			void			*chip_data;
+			struct msi_desc		*msi_desc;
+#ifdef CONFIG_SMP
+			cpumask_var_t		affinity;
+#endif
+		};
+	};
+#endif
+
+	struct timer_rand_state *timer_rand_state;
+	unsigned int		*kstat_irqs;
+	irq_flow_handler_t	handle_irq;
+	struct irqaction	*action;	/* IRQ action list */
+	unsigned int		status;		/* IRQ status */
+
+	unsigned int		depth;		/* nested irq disables */
+	unsigned int		wake_depth;	/* nested wake enables */
+	unsigned int		irq_count;	/* For detecting broken IRQs */
+	unsigned long		last_unhandled;	/* Aging timer for unhandled count */
+	unsigned int		irqs_unhandled;
+	raw_spinlock_t		lock;
+#ifdef CONFIG_SMP
+	const struct cpumask	*affinity_hint;
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	cpumask_var_t		pending_mask;
+#endif
+#endif
+	atomic_t		threads_active;
+	wait_queue_head_t       wait_for_threads;
+#ifdef CONFIG_PROC_FS
+	struct proc_dir_entry	*dir;
+#endif
+	const char		*name;
+} ____cacheline_internodealigned_in_smp;
+
+#ifndef CONFIG_SPARSE_IRQ
+extern struct irq_desc irq_desc[NR_IRQS];
+#endif
+
+/* Will be removed once the last users in power and sh are gone */
+extern struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node);
+static inline struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
+{
+	return desc;
+}
+
+#ifdef CONFIG_GENERIC_HARDIRQS
+
+#define get_irq_desc_chip(desc)		((desc)->irq_data.chip)
+#define get_irq_desc_chip_data(desc)	((desc)->irq_data.chip_data)
+#define get_irq_desc_data(desc)		((desc)->irq_data.handler_data)
+#define get_irq_desc_msi(desc)		((desc)->irq_data.msi_desc)
+
+/*
+ * Monolithic do_IRQ implementation.
+ */
+#ifndef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ
+extern unsigned int __do_IRQ(unsigned int irq);
+#endif
+
+/*
+ * Architectures call this to let the generic IRQ layer
+ * handle an interrupt. If the descriptor is attached to an
+ * irqchip-style controller then we call the ->handle_irq() handler,
+ * and it calls __do_IRQ() if it's attached to an irqtype-style controller.
+ */
+static inline void generic_handle_irq_desc(unsigned int irq, struct irq_desc *desc)
+{
+#ifdef CONFIG_GENERIC_HARDIRQS_NO__DO_IRQ
+	desc->handle_irq(irq, desc);
+#else
+	if (likely(desc->handle_irq))
+		desc->handle_irq(irq, desc);
+	else
+		__do_IRQ(irq);
+#endif
+}
+
+static inline void generic_handle_irq(unsigned int irq)
+{
+	generic_handle_irq_desc(irq, irq_to_desc(irq));
+}
+
+/* Test to see if a driver has successfully requested an irq */
+static inline int irq_has_action(unsigned int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+	return desc->action != NULL;
+}
+
+static inline int irq_balancing_disabled(unsigned int irq)
+{
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+	return desc->status & IRQ_NO_BALANCING_MASK;
+}
+
+/* caller has locked the irq_desc and both params are valid */
+static inline void __set_irq_handler_unlocked(int irq,
+					      irq_flow_handler_t handler)
+{
+	struct irq_desc *desc;
+
+	desc = irq_to_desc(irq);
+	desc->handle_irq = handler;
+}
+#endif
+
+#endif

include/linux/irqnr.h

@@ -25,6 +25,7 @@
 
 extern int nr_irqs;
 extern struct irq_desc *irq_to_desc(unsigned int irq);
+unsigned int irq_get_next_irq(unsigned int offset);
 
 # define for_each_irq_desc(irq, desc)					\
 	for (irq = 0, desc = irq_to_desc(irq); irq < nr_irqs;		\
@@ -47,6 +48,10 @@ extern struct irq_desc *irq_to_desc(unsigned int irq);
 #define irq_node(irq)	0
 #endif
 
+# define for_each_active_irq(irq)			\
+	for (irq = irq_get_next_irq(0); irq < nr_irqs;	\
+	     irq = irq_get_next_irq(irq + 1))
+
 #endif /* CONFIG_GENERIC_HARDIRQS */
 
 #define for_each_irq_nr(irq)                   \

include/linux/lockdep.h

@@ -435,14 +435,6 @@ do {								\
 
 #endif /* CONFIG_LOCKDEP */
 
-#ifdef CONFIG_GENERIC_HARDIRQS
-extern void early_init_irq_lock_class(void);
-#else
-static inline void early_init_irq_lock_class(void)
-{
-}
-#endif
-
 #ifdef CONFIG_TRACE_IRQFLAGS
 extern void early_boot_irqs_off(void);
 extern void early_boot_irqs_on(void);

include/linux/msi.h

@@ -10,12 +10,13 @@ struct msi_msg {
 };
 
 /* Helper functions */
-struct irq_desc;
-extern void mask_msi_irq(unsigned int irq);
-extern void unmask_msi_irq(unsigned int irq);
-extern void read_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg);
-extern void get_cached_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg);
-extern void write_msi_msg_desc(struct irq_desc *desc, struct msi_msg *msg);
+struct irq_data;
+struct msi_desc;
+extern void mask_msi_irq(struct irq_data *data);
+extern void unmask_msi_irq(struct irq_data *data);
+extern void __read_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
+extern void __get_cached_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
+extern void __write_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
 extern void read_msi_msg(unsigned int irq, struct msi_msg *msg);
 extern void get_cached_msi_msg(unsigned int irq, struct msi_msg *msg);
 extern void write_msi_msg(unsigned int irq, struct msi_msg *msg);

init/Kconfig

@@ -339,6 +339,8 @@ config AUDIT_TREE
 	depends on AUDITSYSCALL
 	select FSNOTIFY
 
+source "kernel/irq/Kconfig"
+
 menu "RCU Subsystem"
 
 choice

init/main.c

@@ -556,7 +556,6 @@ asmlinkage void __init start_kernel(void)
 
 	local_irq_disable();
 	early_boot_irqs_off();
-	early_init_irq_lock_class();
 
 /*
  * Interrupts are still disabled. Do necessary setups, then

kernel/irq/Kconfig

@@ -0,0 +1,53 @@
+config HAVE_GENERIC_HARDIRQS
+	def_bool n
+
+if HAVE_GENERIC_HARDIRQS
+menu "IRQ subsystem"
+#
+# Interrupt subsystem related configuration options
+#
+config GENERIC_HARDIRQS
+       def_bool y
+
+config GENERIC_HARDIRQS_NO__DO_IRQ
+       def_bool y
+
+# Select this to disable the deprecated stuff
+config GENERIC_HARDIRQS_NO_DEPRECATED
+       def_bool n
+
+# Options selectable by the architecture code
+config HAVE_SPARSE_IRQ
+       def_bool n
+
+config GENERIC_IRQ_PROBE
+	def_bool n
+
+config GENERIC_PENDING_IRQ
+	def_bool n
+
+config AUTO_IRQ_AFFINITY
+       def_bool n
+
+config IRQ_PER_CPU
+       def_bool n
+
+config HARDIRQS_SW_RESEND
+       def_bool n
+
+config SPARSE_IRQ
+	bool "Support sparse irq numbering"
+	depends on HAVE_SPARSE_IRQ
+	---help---
+
+	  Sparse irq numbering is useful for distro kernels that want
+	  to define a high CONFIG_NR_CPUS value but still want to have
+	  low kernel memory footprint on smaller machines.
+
+	  ( Sparse irqs can also be beneficial on NUMA boxes, as they spread
+	    out the interrupt descriptors in a more NUMA-friendly way. )
+
+	  If you don't know what to do here, say N.
+
+endmenu
+endif

kernel/irq/Makefile

@@ -1,7 +1,6 @@
 
-obj-y := handle.o manage.o spurious.o resend.o chip.o devres.o
+obj-y := irqdesc.o handle.o manage.o spurious.o resend.o chip.o dummychip.o devres.o
 obj-$(CONFIG_GENERIC_IRQ_PROBE) += autoprobe.o
 obj-$(CONFIG_PROC_FS) += proc.o
 obj-$(CONFIG_GENERIC_PENDING_IRQ) += migration.o
-obj-$(CONFIG_NUMA_IRQ_DESC) += numa_migrate.o
 obj-$(CONFIG_PM_SLEEP) += pm.o

kernel/irq/autoprobe.c

@@ -57,9 +57,10 @@ unsigned long probe_irq_on(void)
 			 * Some chips need to know about probing in
 			 * progress:
 			 */
-			if (desc->chip->set_type)
-				desc->chip->set_type(i, IRQ_TYPE_PROBE);
-			desc->chip->startup(i);
+			if (desc->irq_data.chip->irq_set_type)
+				desc->irq_data.chip->irq_set_type(&desc->irq_data,
+							 IRQ_TYPE_PROBE);
+			desc->irq_data.chip->irq_startup(&desc->irq_data);
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}
@@ -76,7 +77,7 @@ unsigned long probe_irq_on(void)
 		raw_spin_lock_irq(&desc->lock);
 		if (!desc->action && !(desc->status & IRQ_NOPROBE)) {
 			desc->status |= IRQ_AUTODETECT | IRQ_WAITING;
-			if (desc->chip->startup(i))
+			if (desc->irq_data.chip->irq_startup(&desc->irq_data))
 				desc->status |= IRQ_PENDING;
 		}
 		raw_spin_unlock_irq(&desc->lock);
@@ -98,7 +99,7 @@ unsigned long probe_irq_on(void)
 			/* It triggered already - consider it spurious. */
 			if (!(status & IRQ_WAITING)) {
 				desc->status = status & ~IRQ_AUTODETECT;
-				desc->chip->shutdown(i);
+				desc->irq_data.chip->irq_shutdown(&desc->irq_data);
 			} else
 				if (i < 32)
 					mask |= 1 << i;
@@ -137,7 +138,7 @@ unsigned int probe_irq_mask(unsigned long val)
 				mask |= 1 << i;
 
 			desc->status = status & ~IRQ_AUTODETECT;
-			desc->chip->shutdown(i);
+			desc->irq_data.chip->irq_shutdown(&desc->irq_data);
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}
@@ -181,7 +182,7 @@ int probe_irq_off(unsigned long val)
 				nr_of_irqs++;
 			}
 			desc->status = status & ~IRQ_AUTODETECT;
-			desc->chip->shutdown(i);
+			desc->irq_data.chip->irq_shutdown(&desc->irq_data);
 		}
 		raw_spin_unlock_irq(&desc->lock);
 	}

kernel/irq/chip.c

@@ -18,108 +18,6 @@
 
 #include "internals.h"
 
-static void dynamic_irq_init_x(unsigned int irq, bool keep_chip_data)
-{
-	struct irq_desc *desc;
-	unsigned long flags;
-
-	desc = irq_to_desc(irq);
-	if (!desc) {
-		WARN(1, KERN_ERR "Trying to initialize invalid IRQ%d\n", irq);
-		return;
-	}
-
-	/* Ensure we don't have left over values from a previous use of this irq */
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc->status = IRQ_DISABLED;
-	desc->chip = &no_irq_chip;
-	desc->handle_irq = handle_bad_irq;
-	desc->depth = 1;
-	desc->msi_desc = NULL;
-	desc->handler_data = NULL;
-	if (!keep_chip_data)
-		desc->chip_data = NULL;
-	desc->action = NULL;
-	desc->irq_count = 0;
-	desc->irqs_unhandled = 0;
-#ifdef CONFIG_SMP
-	cpumask_setall(desc->affinity);
-#ifdef CONFIG_GENERIC_PENDING_IRQ
-	cpumask_clear(desc->pending_mask);
-#endif
-#endif
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-}
-
-/**
- *	dynamic_irq_init - initialize a dynamically allocated irq
- *	@irq:	irq number to initialize
- */
-void dynamic_irq_init(unsigned int irq)
-{
-	dynamic_irq_init_x(irq, false);
-}
-
-/**
- *	dynamic_irq_init_keep_chip_data - initialize a dynamically allocated irq
- *	@irq:	irq number to initialize
- *
- *	does not set irq_to_desc(irq)->chip_data to NULL
- */
-void dynamic_irq_init_keep_chip_data(unsigned int irq)
-{
-	dynamic_irq_init_x(irq, true);
-}
-
-static void dynamic_irq_cleanup_x(unsigned int irq, bool keep_chip_data)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-	unsigned long flags;
-
-	if (!desc) {
-		WARN(1, KERN_ERR "Trying to cleanup invalid IRQ%d\n", irq);
-		return;
-	}
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	if (desc->action) {
-		raw_spin_unlock_irqrestore(&desc->lock, flags);
-		WARN(1, KERN_ERR "Destroying IRQ%d without calling free_irq\n",
-			irq);
-		return;
-	}
-	desc->msi_desc = NULL;
-	desc->handler_data = NULL;
-	if (!keep_chip_data)
-		desc->chip_data = NULL;
-	desc->handle_irq = handle_bad_irq;
-	desc->chip = &no_irq_chip;
-	desc->name = NULL;
-	clear_kstat_irqs(desc);
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-}
-
-/**
- *	dynamic_irq_cleanup - cleanup a dynamically allocated irq
- *	@irq:	irq number to initialize
- */
-void dynamic_irq_cleanup(unsigned int irq)
-{
-	dynamic_irq_cleanup_x(irq, false);
-}
-
-/**
- *	dynamic_irq_cleanup_keep_chip_data - cleanup a dynamically allocated irq
- *	@irq:	irq number to initialize
- *
- *	does not set irq_to_desc(irq)->chip_data to NULL
- */
-void dynamic_irq_cleanup_keep_chip_data(unsigned int irq)
-{
-	dynamic_irq_cleanup_x(irq, true);
-}
-
-
 /**
  *	set_irq_chip - set the irq chip for an irq
  *	@irq:	irq number
@@ -140,7 +38,7 @@ int set_irq_chip(unsigned int irq, struct irq_chip *chip)
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
 	irq_chip_set_defaults(chip);
-	desc->chip = chip;
+	desc->irq_data.chip = chip;
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 
 	return 0;
@@ -193,7 +91,7 @@ int set_irq_data(unsigned int irq, void *data)
 	}
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc->handler_data = data;
+	desc->irq_data.handler_data = data;
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 	return 0;
 }
@@ -218,7 +116,7 @@ int set_irq_msi(unsigned int irq, struct msi_desc *entry)
 	}
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc->msi_desc = entry;
+	desc->irq_data.msi_desc = entry;
 	if (entry)
 		entry->irq = irq;
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
@@ -243,19 +141,27 @@ int set_irq_chip_data(unsigned int irq, void *data)
 		return -EINVAL;
 	}
 
-	if (!desc->chip) {
+	if (!desc->irq_data.chip) {
 		printk(KERN_ERR "BUG: bad set_irq_chip_data(IRQ#%d)\n", irq);
 		return -EINVAL;
 	}
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc->chip_data = data;
+	desc->irq_data.chip_data = data;
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 
 	return 0;
 }
 EXPORT_SYMBOL(set_irq_chip_data);
 
+struct irq_data *irq_get_irq_data(unsigned int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	return desc ? &desc->irq_data : NULL;
+}
+EXPORT_SYMBOL_GPL(irq_get_irq_data);
+
 /**
  *	set_irq_nested_thread - Set/Reset the IRQ_NESTED_THREAD flag of an irq
  *
@@ -287,93 +193,216 @@ EXPORT_SYMBOL_GPL(set_irq_nested_thread);
 /*
  * default enable function
  */
-static void default_enable(unsigned int irq)
+static void default_enable(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_desc *desc = irq_data_to_desc(data);
 
-	desc->chip->unmask(irq);
+	desc->irq_data.chip->irq_unmask(&desc->irq_data);
 	desc->status &= ~IRQ_MASKED;
 }
 
 /*
  * default disable function
  */
-static void default_disable(unsigned int irq)
+static void default_disable(struct irq_data *data)
 {
 }
 
 /*
  * default startup function
  */
-static unsigned int default_startup(unsigned int irq)
+static unsigned int default_startup(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_desc *desc = irq_data_to_desc(data);
 
-	desc->chip->enable(irq);
+	desc->irq_data.chip->irq_enable(data);
 	return 0;
 }
 
 /*
  * default shutdown function
  */
-static void default_shutdown(unsigned int irq)
+static void default_shutdown(struct irq_data *data)
 {
-	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_desc *desc = irq_data_to_desc(data);
 
-	desc->chip->mask(irq);
+	desc->irq_data.chip->irq_mask(&desc->irq_data);
 	desc->status |= IRQ_MASKED;
 }
 
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
+/* Temporary migration helpers */
+static void compat_irq_mask(struct irq_data *data)
+{
+	data->chip->mask(data->irq);
+}
+
+static void compat_irq_unmask(struct irq_data *data)
+{
+	data->chip->unmask(data->irq);
+}
+
+static void compat_irq_ack(struct irq_data *data)
+{
+	data->chip->ack(data->irq);
+}
+
+static void compat_irq_mask_ack(struct irq_data *data)
+{
+	data->chip->mask_ack(data->irq);
+}
+
+static void compat_irq_eoi(struct irq_data *data)
+{
+	data->chip->eoi(data->irq);
+}
+
+static void compat_irq_enable(struct irq_data *data)
+{
+	data->chip->enable(data->irq);
+}
+
+static void compat_irq_disable(struct irq_data *data)
+{
+	data->chip->disable(data->irq);
+}
+
+static void compat_irq_shutdown(struct irq_data *data)
+{
+	data->chip->shutdown(data->irq);
+}
+
+static unsigned int compat_irq_startup(struct irq_data *data)
+{
+	return data->chip->startup(data->irq);
+}
+
+static int compat_irq_set_affinity(struct irq_data *data,
+				   const struct cpumask *dest, bool force)
+{
+	return data->chip->set_affinity(data->irq, dest);
+}
+
+static int compat_irq_set_type(struct irq_data *data, unsigned int type)
+{
+	return data->chip->set_type(data->irq, type);
+}
+
+static int compat_irq_set_wake(struct irq_data *data, unsigned int on)
+{
+	return data->chip->set_wake(data->irq, on);
+}
+
+static int compat_irq_retrigger(struct irq_data *data)
+{
+	return data->chip->retrigger(data->irq);
+}
+
+static void compat_bus_lock(struct irq_data *data)
+{
+	data->chip->bus_lock(data->irq);
+}
+
+static void compat_bus_sync_unlock(struct irq_data *data)
+{
+	data->chip->bus_sync_unlock(data->irq);
+}
+#endif
+
 /*
  * Fixup enable/disable function pointers
  */
 void irq_chip_set_defaults(struct irq_chip *chip)
 {
-	if (!chip->enable)
-		chip->enable = default_enable;
-	if (!chip->disable)
-		chip->disable = default_disable;
-	if (!chip->startup)
-		chip->startup = default_startup;
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
 	/*
-	 * We use chip->disable, when the user provided its own. When
-	 * we have default_disable set for chip->disable, then we need
+	 * Compat fixup functions need to be before we set the
+	 * defaults for enable/disable/startup/shutdown
+	 */
+	if (chip->enable)
+		chip->irq_enable = compat_irq_enable;
+	if (chip->disable)
+		chip->irq_disable = compat_irq_disable;
+	if (chip->shutdown)
+		chip->irq_shutdown = compat_irq_shutdown;
+	if (chip->startup)
+		chip->irq_startup = compat_irq_startup;
+#endif
+	/*
+	 * The real defaults
+	 */
+	if (!chip->irq_enable)
+		chip->irq_enable = default_enable;
+	if (!chip->irq_disable)
+		chip->irq_disable = default_disable;
+	if (!chip->irq_startup)
+		chip->irq_startup = default_startup;
+	/*
+	 * We use chip->irq_disable, when the user provided its own. When
+	 * we have default_disable set for chip->irq_disable, then we need
 	 * to use default_shutdown, otherwise the irq line is not
 	 * disabled on free_irq():
 	 */
-	if (!chip->shutdown)
-		chip->shutdown = chip->disable != default_disable ?
-			chip->disable : default_shutdown;
-	if (!chip->name)
-		chip->name = chip->typename;
+	if (!chip->irq_shutdown)
+		chip->irq_shutdown = chip->irq_disable != default_disable ?
+			chip->irq_disable : default_shutdown;
+
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
 	if (!chip->end)
 		chip->end = dummy_irq_chip.end;
+
+	/*
+	 * Now fix up the remaining compat handlers
+	 */
+	if (chip->bus_lock)
+		chip->irq_bus_lock = compat_bus_lock;
+	if (chip->bus_sync_unlock)
+		chip->irq_bus_sync_unlock = compat_bus_sync_unlock;
+	if (chip->mask)
+		chip->irq_mask = compat_irq_mask;
+	if (chip->unmask)
+		chip->irq_unmask = compat_irq_unmask;
+	if (chip->ack)
+		chip->irq_ack = compat_irq_ack;
+	if (chip->mask_ack)
+		chip->irq_mask_ack = compat_irq_mask_ack;
+	if (chip->eoi)
+		chip->irq_eoi = compat_irq_eoi;
+	if (chip->set_affinity)
+		chip->irq_set_affinity = compat_irq_set_affinity;
+	if (chip->set_type)
+		chip->irq_set_type = compat_irq_set_type;
+	if (chip->set_wake)
+		chip->irq_set_wake = compat_irq_set_wake;
+	if (chip->retrigger)
+		chip->irq_retrigger = compat_irq_retrigger;
+#endif
 }
 
-static inline void mask_ack_irq(struct irq_desc *desc, int irq)
+static inline void mask_ack_irq(struct irq_desc *desc)
 {
-	if (desc->chip->mask_ack)
-		desc->chip->mask_ack(irq);
+	if (desc->irq_data.chip->irq_mask_ack)
+		desc->irq_data.chip->irq_mask_ack(&desc->irq_data);
 	else {
-		desc->chip->mask(irq);
-		if (desc->chip->ack)
-			desc->chip->ack(irq);
+		desc->irq_data.chip->irq_mask(&desc->irq_data);
+		if (desc->irq_data.chip->irq_ack)
+			desc->irq_data.chip->irq_ack(&desc->irq_data);
 	}
 	desc->status |= IRQ_MASKED;
 }
 
-static inline void mask_irq(struct irq_desc *desc, int irq)
+static inline void mask_irq(struct irq_desc *desc)
 {
-	if (desc->chip->mask) {
-		desc->chip->mask(irq);
+	if (desc->irq_data.chip->irq_mask) {
+		desc->irq_data.chip->irq_mask(&desc->irq_data);
 		desc->status |= IRQ_MASKED;
 	}
 }
 
-static inline void unmask_irq(struct irq_desc *desc, int irq)
+static inline void unmask_irq(struct irq_desc *desc)
 {
-	if (desc->chip->unmask) {
-		desc->chip->unmask(irq);
+	if (desc->irq_data.chip->irq_unmask) {
+		desc->irq_data.chip->irq_unmask(&desc->irq_data);
 		desc->status &= ~IRQ_MASKED;
 	}
 }
@@ -476,7 +505,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 	irqreturn_t action_ret;
 
 	raw_spin_lock(&desc->lock);
-	mask_ack_irq(desc, irq);
+	mask_ack_irq(desc);
 
 	if (unlikely(desc->status & IRQ_INPROGRESS))
 		goto out_unlock;
@@ -502,7 +531,7 @@ handle_level_irq(unsigned int irq, struct irq_desc *desc)
 	desc->status &= ~IRQ_INPROGRESS;
 
 	if (!(desc->status & (IRQ_DISABLED | IRQ_ONESHOT)))
-		unmask_irq(desc, irq);
+		unmask_irq(desc);
 out_unlock:
 	raw_spin_unlock(&desc->lock);
 }
@@ -539,7 +568,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 	action = desc->action;
 	if (unlikely(!action || (desc->status & IRQ_DISABLED))) {
 		desc->status |= IRQ_PENDING;
-		mask_irq(desc, irq);
+		mask_irq(desc);
 		goto out;
 	}
 
@@ -554,7 +583,7 @@ handle_fasteoi_irq(unsigned int irq, struct irq_desc *desc)
 	raw_spin_lock(&desc->lock);
 	desc->status &= ~IRQ_INPROGRESS;
 out:
-	desc->chip->eoi(irq);
+	desc->irq_data.chip->irq_eoi(&desc->irq_data);
 
 	raw_spin_unlock(&desc->lock);
 }
@@ -590,14 +619,13 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 	if (unlikely((desc->status & (IRQ_INPROGRESS | IRQ_DISABLED)) ||
 		    !desc->action)) {
 		desc->status |= (IRQ_PENDING | IRQ_MASKED);
-		mask_ack_irq(desc, irq);
+		mask_ack_irq(desc);
 		goto out_unlock;
 	}
 	kstat_incr_irqs_this_cpu(irq, desc);
 
 	/* Start handling the irq */
-	if (desc->chip->ack)
-		desc->chip->ack(irq);
+	desc->irq_data.chip->irq_ack(&desc->irq_data);
 
 	/* Mark the IRQ currently in progress.*/
 	desc->status |= IRQ_INPROGRESS;
@@ -607,7 +635,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 		irqreturn_t action_ret;
 
 		if (unlikely(!action)) {
-			mask_irq(desc, irq);
+			mask_irq(desc);
 			goto out_unlock;
 		}
 
@@ -619,7 +647,7 @@ handle_edge_irq(unsigned int irq, struct irq_desc *desc)
 		if (unlikely((desc->status &
 			       (IRQ_PENDING | IRQ_MASKED | IRQ_DISABLED)) ==
 			      (IRQ_PENDING | IRQ_MASKED))) {
-			unmask_irq(desc, irq);
+			unmask_irq(desc);
 		}
 
 		desc->status &= ~IRQ_PENDING;
@@ -650,15 +678,15 @@ handle_percpu_irq(unsigned int irq, struct irq_desc *desc)
 
 	kstat_incr_irqs_this_cpu(irq, desc);
 
-	if (desc->chip->ack)
-		desc->chip->ack(irq);
+	if (desc->irq_data.chip->irq_ack)
+		desc->irq_data.chip->irq_ack(&desc->irq_data);
 
 	action_ret = handle_IRQ_event(irq, desc->action);
 	if (!noirqdebug)
 		note_interrupt(irq, desc, action_ret);
 
-	if (desc->chip->eoi)
-		desc->chip->eoi(irq);
+	if (desc->irq_data.chip->irq_eoi)
+		desc->irq_data.chip->irq_eoi(&desc->irq_data);
 }
 
 void
@@ -676,7 +704,7 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 
 	if (!handle)
 		handle = handle_bad_irq;
-	else if (desc->chip == &no_irq_chip) {
+	else if (desc->irq_data.chip == &no_irq_chip) {
 		printk(KERN_WARNING "Trying to install %sinterrupt handler "
 		       "for IRQ%d\n", is_chained ? "chained " : "", irq);
 		/*
@@ -686,16 +714,16 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		 * prevent us to setup the interrupt at all. Switch it to
 		 * dummy_irq_chip for easy transition.
 		 */
-		desc->chip = &dummy_irq_chip;
+		desc->irq_data.chip = &dummy_irq_chip;
 	}
 
-	chip_bus_lock(irq, desc);
+	chip_bus_lock(desc);
 	raw_spin_lock_irqsave(&desc->lock, flags);
 
 	/* Uninstall? */
 	if (handle == handle_bad_irq) {
-		if (desc->chip != &no_irq_chip)
-			mask_ack_irq(desc, irq);
+		if (desc->irq_data.chip != &no_irq_chip)
+			mask_ack_irq(desc);
 		desc->status |= IRQ_DISABLED;
 		desc->depth = 1;
 	}
@@ -706,10 +734,10 @@ __set_irq_handler(unsigned int irq, irq_flow_handler_t handle, int is_chained,
 		desc->status &= ~IRQ_DISABLED;
 		desc->status |= IRQ_NOREQUEST | IRQ_NOPROBE;
 		desc->depth = 0;
-		desc->chip->startup(irq);
+		desc->irq_data.chip->irq_startup(&desc->irq_data);
 	}
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	chip_bus_sync_unlock(irq, desc);
+	chip_bus_sync_unlock(desc);
 }
 EXPORT_SYMBOL_GPL(__set_irq_handler);
 
@@ -729,32 +757,20 @@ set_irq_chip_and_handler_name(unsigned int irq, struct irq_chip *chip,
 	__set_irq_handler(irq, handle, 0, name);
 }
 
-void set_irq_noprobe(unsigned int irq)
+void irq_modify_status(unsigned int irq, unsigned long clr, unsigned long set)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 	unsigned long flags;
 
-	if (!desc) {
-		printk(KERN_ERR "Trying to mark IRQ%d non-probeable\n", irq);
+	if (!desc)
 		return;
-	}
-
-	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc->status |= IRQ_NOPROBE;
-	raw_spin_unlock_irqrestore(&desc->lock, flags);
-}
-
-void set_irq_probe(unsigned int irq)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-	unsigned long flags;
 
-	if (!desc) {
-		printk(KERN_ERR "Trying to mark IRQ%d probeable\n", irq);
-		return;
-	}
+	/* Sanitize flags */
+	set &= IRQF_MODIFY_MASK;
+	clr &= IRQF_MODIFY_MASK;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
-	desc->status &= ~IRQ_NOPROBE;
+	desc->status &= ~clr;
+	desc->status |= set;
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
 }

kernel/irq/dummychip.c

@@ -0,0 +1,68 @@
+/*
+ * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar
+ * Copyright (C) 2005-2006, Thomas Gleixner, Russell King
+ *
+ * This file contains the dummy interrupt chip implementation
+ */
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+
+#include "internals.h"
+
+/*
+ * What should we do if we get a hw irq event on an illegal vector?
+ * Each architecture has to answer this themself.
+ */
+static void ack_bad(struct irq_data *data)
+{
+	struct irq_desc *desc = irq_data_to_desc(data);
+
+	print_irq_desc(data->irq, desc);
+	ack_bad_irq(data->irq);
+}
+
+/*
+ * NOP functions
+ */
+static void noop(struct irq_data *data) { }
+
+static unsigned int noop_ret(struct irq_data *data)
+{
+	return 0;
+}
+
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
+static void compat_noop(unsigned int irq) { }
+#define END_INIT .end = compat_noop
+#else
+#define END_INIT
+#endif
+
+/*
+ * Generic no controller implementation
+ */
+struct irq_chip no_irq_chip = {
+	.name		= "none",
+	.irq_startup	= noop_ret,
+	.irq_shutdown	= noop,
+	.irq_enable	= noop,
+	.irq_disable	= noop,
+	.irq_ack	= ack_bad,
+	END_INIT
+};
+
+/*
+ * Generic dummy implementation which can be used for
+ * real dumb interrupt sources
+ */
+struct irq_chip dummy_irq_chip = {
+	.name		= "dummy",
+	.irq_startup	= noop_ret,
+	.irq_shutdown	= noop,
+	.irq_enable	= noop,
+	.irq_disable	= noop,
+	.irq_ack	= noop,
+	.irq_mask	= noop,
+	.irq_unmask	= noop,
+	END_INIT
+};

kernel/irq/handle.c

@@ -11,24 +11,15 @@
  */
 
 #include <linux/irq.h>
-#include <linux/sched.h>
-#include <linux/slab.h>
-#include <linux/module.h>
 #include <linux/random.h>
+#include <linux/sched.h>
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
-#include <linux/rculist.h>
-#include <linux/hash.h>
-#include <linux/radix-tree.h>
+
 #include <trace/events/irq.h>
 
 #include "internals.h"
 
-/*
- * lockdep: we want to handle all irq_desc locks as a single lock-class:
- */
-struct lock_class_key irq_desc_lock_class;
-
 /**
  * handle_bad_irq - handle spurious and unhandled irqs
  * @irq:       the interrupt number
@@ -43,304 +34,6 @@ void handle_bad_irq(unsigned int irq, struct irq_desc *desc)
 	ack_bad_irq(irq);
 }
 
-#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
-static void __init init_irq_default_affinity(void)
-{
-	alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
-	cpumask_setall(irq_default_affinity);
-}
-#else
-static void __init init_irq_default_affinity(void)
-{
-}
-#endif
-
-/*
- * Linux has a controller-independent interrupt architecture.
- * Every controller has a 'controller-template', that is used
- * by the main code to do the right thing. Each driver-visible
- * interrupt source is transparently wired to the appropriate
- * controller. Thus drivers need not be aware of the
- * interrupt-controller.
- *
- * The code is designed to be easily extended with new/different
- * interrupt controllers, without having to do assembly magic or
- * having to touch the generic code.
- *
- * Controller mappings for all interrupt sources:
- */
-int nr_irqs = NR_IRQS;
-EXPORT_SYMBOL_GPL(nr_irqs);
-
-#ifdef CONFIG_SPARSE_IRQ
-
-static struct irq_desc irq_desc_init = {
-	.irq	    = -1,
-	.status	    = IRQ_DISABLED,
-	.chip	    = &no_irq_chip,
-	.handle_irq = handle_bad_irq,
-	.depth      = 1,
-	.lock       = __RAW_SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
-};
-
-void __ref init_kstat_irqs(struct irq_desc *desc, int node, int nr)
-{
-	void *ptr;
-
-	ptr = kzalloc_node(nr * sizeof(*desc->kstat_irqs),
-			   GFP_ATOMIC, node);
-
-	/*
-	 * don't overwite if can not get new one
-	 * init_copy_kstat_irqs() could still use old one
-	 */
-	if (ptr) {
-		printk(KERN_DEBUG "  alloc kstat_irqs on node %d\n", node);
-		desc->kstat_irqs = ptr;
-	}
-}
-
-static void init_one_irq_desc(int irq, struct irq_desc *desc, int node)
-{
-	memcpy(desc, &irq_desc_init, sizeof(struct irq_desc));
-
-	raw_spin_lock_init(&desc->lock);
-	desc->irq = irq;
-#ifdef CONFIG_SMP
-	desc->node = node;
-#endif
-	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
-	init_kstat_irqs(desc, node, nr_cpu_ids);
-	if (!desc->kstat_irqs) {
-		printk(KERN_ERR "can not alloc kstat_irqs\n");
-		BUG_ON(1);
-	}
-	if (!alloc_desc_masks(desc, node, false)) {
-		printk(KERN_ERR "can not alloc irq_desc cpumasks\n");
-		BUG_ON(1);
-	}
-	init_desc_masks(desc);
-	arch_init_chip_data(desc, node);
-}
-
-/*
- * Protect the sparse_irqs:
- */
-DEFINE_RAW_SPINLOCK(sparse_irq_lock);
-
-static RADIX_TREE(irq_desc_tree, GFP_ATOMIC);
-
-static void set_irq_desc(unsigned int irq, struct irq_desc *desc)
-{
-	radix_tree_insert(&irq_desc_tree, irq, desc);
-}
-
-struct irq_desc *irq_to_desc(unsigned int irq)
-{
-	return radix_tree_lookup(&irq_desc_tree, irq);
-}
-
-void replace_irq_desc(unsigned int irq, struct irq_desc *desc)
-{
-	void **ptr;
-
-	ptr = radix_tree_lookup_slot(&irq_desc_tree, irq);
-	if (ptr)
-		radix_tree_replace_slot(ptr, desc);
-}
-
-static struct irq_desc irq_desc_legacy[NR_IRQS_LEGACY] __cacheline_aligned_in_smp = {
-	[0 ... NR_IRQS_LEGACY-1] = {
-		.irq	    = -1,
-		.status	    = IRQ_DISABLED,
-		.chip	    = &no_irq_chip,
-		.handle_irq = handle_bad_irq,
-		.depth	    = 1,
-		.lock	    = __RAW_SPIN_LOCK_UNLOCKED(irq_desc_init.lock),
-	}
-};
-
-static unsigned int *kstat_irqs_legacy;
-
-int __init early_irq_init(void)
-{
-	struct irq_desc *desc;
-	int legacy_count;
-	int node;
-	int i;
-
-	init_irq_default_affinity();
-
-	 /* initialize nr_irqs based on nr_cpu_ids */
-	arch_probe_nr_irqs();
-	printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d\n", NR_IRQS, nr_irqs);
-
-	desc = irq_desc_legacy;
-	legacy_count = ARRAY_SIZE(irq_desc_legacy);
-	node = first_online_node;
-
-	/* allocate based on nr_cpu_ids */
-	kstat_irqs_legacy = kzalloc_node(NR_IRQS_LEGACY * nr_cpu_ids *
-					  sizeof(int), GFP_NOWAIT, node);
-
-	for (i = 0; i < legacy_count; i++) {
-		desc[i].irq = i;
-#ifdef CONFIG_SMP
-		desc[i].node = node;
-#endif
-		desc[i].kstat_irqs = kstat_irqs_legacy + i * nr_cpu_ids;
-		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
-		alloc_desc_masks(&desc[i], node, true);
-		init_desc_masks(&desc[i]);
-		set_irq_desc(i, &desc[i]);
-	}
-
-	return arch_early_irq_init();
-}
-
-struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node)
-{
-	struct irq_desc *desc;
-	unsigned long flags;
-
-	if (irq >= nr_irqs) {
-		WARN(1, "irq (%d) >= nr_irqs (%d) in irq_to_desc_alloc\n",
-			irq, nr_irqs);
-		return NULL;
-	}
-
-	desc = irq_to_desc(irq);
-	if (desc)
-		return desc;
-
-	raw_spin_lock_irqsave(&sparse_irq_lock, flags);
-
-	/* We have to check it to avoid races with another CPU */
-	desc = irq_to_desc(irq);
-	if (desc)
-		goto out_unlock;
-
-	desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
-
-	printk(KERN_DEBUG "  alloc irq_desc for %d on node %d\n", irq, node);
-	if (!desc) {
-		printk(KERN_ERR "can not alloc irq_desc\n");
-		BUG_ON(1);
-	}
-	init_one_irq_desc(irq, desc, node);
-
-	set_irq_desc(irq, desc);
-
-out_unlock:
-	raw_spin_unlock_irqrestore(&sparse_irq_lock, flags);
-
-	return desc;
-}
-
-#else /* !CONFIG_SPARSE_IRQ */
-
-struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
-	[0 ... NR_IRQS-1] = {
-		.status = IRQ_DISABLED,
-		.chip = &no_irq_chip,
-		.handle_irq = handle_bad_irq,
-		.depth = 1,
-		.lock = __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock),
-	}
-};
-
-static unsigned int kstat_irqs_all[NR_IRQS][NR_CPUS];
-int __init early_irq_init(void)
-{
-	struct irq_desc *desc;
-	int count;
-	int i;
-
-	init_irq_default_affinity();
-
-	printk(KERN_INFO "NR_IRQS:%d\n", NR_IRQS);
-
-	desc = irq_desc;
-	count = ARRAY_SIZE(irq_desc);
-
-	for (i = 0; i < count; i++) {
-		desc[i].irq = i;
-		alloc_desc_masks(&desc[i], 0, true);
-		init_desc_masks(&desc[i]);
-		desc[i].kstat_irqs = kstat_irqs_all[i];
-	}
-	return arch_early_irq_init();
-}
-
-struct irq_desc *irq_to_desc(unsigned int irq)
-{
-	return (irq < NR_IRQS) ? irq_desc + irq : NULL;
-}
-
-struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node)
-{
-	return irq_to_desc(irq);
-}
-#endif /* !CONFIG_SPARSE_IRQ */
-
-void clear_kstat_irqs(struct irq_desc *desc)
-{
-	memset(desc->kstat_irqs, 0, nr_cpu_ids * sizeof(*(desc->kstat_irqs)));
-}
-
-/*
- * What should we do if we get a hw irq event on an illegal vector?
- * Each architecture has to answer this themself.
- */
-static void ack_bad(unsigned int irq)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-
-	print_irq_desc(irq, desc);
-	ack_bad_irq(irq);
-}
-
-/*
- * NOP functions
- */
-static void noop(unsigned int irq)
-{
-}
-
-static unsigned int noop_ret(unsigned int irq)
-{
-	return 0;
-}
-
-/*
- * Generic no controller implementation
- */
-struct irq_chip no_irq_chip = {
-	.name		= "none",
-	.startup	= noop_ret,
-	.shutdown	= noop,
-	.enable		= noop,
-	.disable	= noop,
-	.ack		= ack_bad,
-	.end		= noop,
-};
-
-/*
- * Generic dummy implementation which can be used for
- * real dumb interrupt sources
- */
-struct irq_chip dummy_irq_chip = {
-	.name		= "dummy",
-	.startup	= noop_ret,
-	.shutdown	= noop,
-	.enable		= noop,
-	.disable	= noop,
-	.ack		= noop,
-	.mask		= noop,
-	.unmask		= noop,
-	.end		= noop,
-};
-
 /*
  * Special, empty irq handler:
  */
@@ -457,20 +150,20 @@ unsigned int __do_IRQ(unsigned int irq)
 		/*
 		 * No locking required for CPU-local interrupts:
 		 */
-		if (desc->chip->ack)
-			desc->chip->ack(irq);
+		if (desc->irq_data.chip->ack)
+			desc->irq_data.chip->ack(irq);
 		if (likely(!(desc->status & IRQ_DISABLED))) {
 			action_ret = handle_IRQ_event(irq, desc->action);
 			if (!noirqdebug)
 				note_interrupt(irq, desc, action_ret);
 		}
-		desc->chip->end(irq);
+		desc->irq_data.chip->end(irq);
 		return 1;
 	}
 
 	raw_spin_lock(&desc->lock);
-	if (desc->chip->ack)
-		desc->chip->ack(irq);
+	if (desc->irq_data.chip->ack)
+		desc->irq_data.chip->ack(irq);
 	/*
 	 * REPLAY is when Linux resends an IRQ that was dropped earlier
 	 * WAITING is used by probe to mark irqs that are being tested
@@ -530,27 +223,9 @@ out:
 	 * The ->end() handler has to deal with interrupts which got
 	 * disabled while the handler was running.
 	 */
-	desc->chip->end(irq);
+	desc->irq_data.chip->end(irq);
 	raw_spin_unlock(&desc->lock);
 
 	return 1;
 }
 #endif
-
-void early_init_irq_lock_class(void)
-{
-	struct irq_desc *desc;
-	int i;
-
-	for_each_irq_desc(i, desc) {
-		lockdep_set_class(&desc->lock, &irq_desc_lock_class);
-	}
-}
-
-unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
-{
-	struct irq_desc *desc = irq_to_desc(irq);
-	return desc ? desc->kstat_irqs[cpu] : 0;
-}
-EXPORT_SYMBOL(kstat_irqs_cpu);
-

kernel/irq/internals.h

@@ -1,9 +1,12 @@
 /*
  * IRQ subsystem internal functions and variables:
  */
+#include <linux/irqdesc.h>
 
 extern int noirqdebug;
 
+#define irq_data_to_desc(data)	container_of(data, struct irq_desc, irq_data)
+
 /* Set default functions for irq_chip structures: */
 extern void irq_chip_set_defaults(struct irq_chip *chip);
 
@@ -15,21 +18,19 @@ extern int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 extern void __disable_irq(struct irq_desc *desc, unsigned int irq, bool susp);
 extern void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume);
 
-extern struct lock_class_key irq_desc_lock_class;
 extern void init_kstat_irqs(struct irq_desc *desc, int node, int nr);
-extern void clear_kstat_irqs(struct irq_desc *desc);
-extern raw_spinlock_t sparse_irq_lock;
 
-#ifdef CONFIG_SPARSE_IRQ
-void replace_irq_desc(unsigned int irq, struct irq_desc *desc);
-#endif
+/* Resending of interrupts :*/
+void check_irq_resend(struct irq_desc *desc, unsigned int irq);
 
 #ifdef CONFIG_PROC_FS
 extern void register_irq_proc(unsigned int irq, struct irq_desc *desc);
+extern void unregister_irq_proc(unsigned int irq, struct irq_desc *desc);
 extern void register_handler_proc(unsigned int irq, struct irqaction *action);
 extern void unregister_handler_proc(unsigned int irq, struct irqaction *action);
 #else
 static inline void register_irq_proc(unsigned int irq, struct irq_desc *desc) { }
+static inline void unregister_irq_proc(unsigned int irq, struct irq_desc *desc) { }
 static inline void register_handler_proc(unsigned int irq,
 					 struct irqaction *action) { }
 static inline void unregister_handler_proc(unsigned int irq,
@@ -40,17 +41,27 @@ extern int irq_select_affinity_usr(unsigned int irq);
 
 extern void irq_set_thread_affinity(struct irq_desc *desc);
 
+#ifndef CONFIG_GENERIC_HARDIRQS_NO_DEPRECATED
+static inline void irq_end(unsigned int irq, struct irq_desc *desc)
+{
+	if (desc->irq_data.chip && desc->irq_data.chip->end)
+		desc->irq_data.chip->end(irq);
+}
+#else
+static inline void irq_end(unsigned int irq, struct irq_desc *desc) { }
+#endif
+
 /* Inline functions for support of irq chips on slow busses */
-static inline void chip_bus_lock(unsigned int irq, struct irq_desc *desc)
+static inline void chip_bus_lock(struct irq_desc *desc)
 {
-	if (unlikely(desc->chip->bus_lock))
-		desc->chip->bus_lock(irq);
+	if (unlikely(desc->irq_data.chip->irq_bus_lock))
+		desc->irq_data.chip->irq_bus_lock(&desc->irq_data);
 }
 
-static inline void chip_bus_sync_unlock(unsigned int irq, struct irq_desc *desc)
+static inline void chip_bus_sync_unlock(struct irq_desc *desc)
 {
-	if (unlikely(desc->chip->bus_sync_unlock))
-		desc->chip->bus_sync_unlock(irq);
+	if (unlikely(desc->irq_data.chip->irq_bus_sync_unlock))
+		desc->irq_data.chip->irq_bus_sync_unlock(&desc->irq_data);
 }
 
 /*
@@ -67,8 +78,8 @@ static inline void print_irq_desc(unsigned int irq, struct irq_desc *desc)
 		irq, desc, desc->depth, desc->irq_count, desc->irqs_unhandled);
 	printk("->handle_irq():  %p, ", desc->handle_irq);
 	print_symbol("%s\n", (unsigned long)desc->handle_irq);
-	printk("->chip(): %p, ", desc->chip);
-	print_symbol("%s\n", (unsigned long)desc->chip);
+	printk("->irq_data.chip(): %p, ", desc->irq_data.chip);
+	print_symbol("%s\n", (unsigned long)desc->irq_data.chip);
 	printk("->action(): %p\n", desc->action);
 	if (desc->action) {
 		printk("->action->handler(): %p, ", desc->action->handler);

kernel/irq/irqdesc.c

@@ -0,0 +1,395 @@
+/*
+ * Copyright (C) 1992, 1998-2006 Linus Torvalds, Ingo Molnar
+ * Copyright (C) 2005-2006, Thomas Gleixner, Russell King
+ *
+ * This file contains the interrupt descriptor management code
+ *
+ * Detailed information is available in Documentation/DocBook/genericirq
+ *
+ */
+#include <linux/irq.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/kernel_stat.h>
+#include <linux/radix-tree.h>
+#include <linux/bitmap.h>
+
+#include "internals.h"
+
+/*
+ * lockdep: we want to handle all irq_desc locks as a single lock-class:
+ */
+static struct lock_class_key irq_desc_lock_class;
+
+#if defined(CONFIG_SMP) && defined(CONFIG_GENERIC_HARDIRQS)
+static void __init init_irq_default_affinity(void)
+{
+	alloc_cpumask_var(&irq_default_affinity, GFP_NOWAIT);
+	cpumask_setall(irq_default_affinity);
+}
+#else
+static void __init init_irq_default_affinity(void)
+{
+}
+#endif
+
+#ifdef CONFIG_SMP
+static int alloc_masks(struct irq_desc *desc, gfp_t gfp, int node)
+{
+	if (!zalloc_cpumask_var_node(&desc->irq_data.affinity, gfp, node))
+		return -ENOMEM;
+
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	if (!zalloc_cpumask_var_node(&desc->pending_mask, gfp, node)) {
+		free_cpumask_var(desc->irq_data.affinity);
+		return -ENOMEM;
+	}
+#endif
+	return 0;
+}
+
+static void desc_smp_init(struct irq_desc *desc, int node)
+{
+	desc->irq_data.node = node;
+	cpumask_copy(desc->irq_data.affinity, irq_default_affinity);
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	cpumask_clear(desc->pending_mask);
+#endif
+}
+
+static inline int desc_node(struct irq_desc *desc)
+{
+	return desc->irq_data.node;
+}
+
+#else
+static inline int
+alloc_masks(struct irq_desc *desc, gfp_t gfp, int node) { return 0; }
+static inline void desc_smp_init(struct irq_desc *desc, int node) { }
+static inline int desc_node(struct irq_desc *desc) { return 0; }
+#endif
+
+static void desc_set_defaults(unsigned int irq, struct irq_desc *desc, int node)
+{
+	desc->irq_data.irq = irq;
+	desc->irq_data.chip = &no_irq_chip;
+	desc->irq_data.chip_data = NULL;
+	desc->irq_data.handler_data = NULL;
+	desc->irq_data.msi_desc = NULL;
+	desc->status = IRQ_DEFAULT_INIT_FLAGS;
+	desc->handle_irq = handle_bad_irq;
+	desc->depth = 1;
+	desc->irq_count = 0;
+	desc->irqs_unhandled = 0;
+	desc->name = NULL;
+	memset(desc->kstat_irqs, 0, nr_cpu_ids * sizeof(*(desc->kstat_irqs)));
+	desc_smp_init(desc, node);
+}
+
+int nr_irqs = NR_IRQS;
+EXPORT_SYMBOL_GPL(nr_irqs);
+
+static DEFINE_MUTEX(sparse_irq_lock);
+static DECLARE_BITMAP(allocated_irqs, NR_IRQS);
+
+#ifdef CONFIG_SPARSE_IRQ
+
+static RADIX_TREE(irq_desc_tree, GFP_KERNEL);
+
+static void irq_insert_desc(unsigned int irq, struct irq_desc *desc)
+{
+	radix_tree_insert(&irq_desc_tree, irq, desc);
+}
+
+struct irq_desc *irq_to_desc(unsigned int irq)
+{
+	return radix_tree_lookup(&irq_desc_tree, irq);
+}
+
+static void delete_irq_desc(unsigned int irq)
+{
+	radix_tree_delete(&irq_desc_tree, irq);
+}
+
+#ifdef CONFIG_SMP
+static void free_masks(struct irq_desc *desc)
+{
+#ifdef CONFIG_GENERIC_PENDING_IRQ
+	free_cpumask_var(desc->pending_mask);
+#endif
+	free_cpumask_var(desc->irq_data.affinity);
+}
+#else
+static inline void free_masks(struct irq_desc *desc) { }
+#endif
+
+static struct irq_desc *alloc_desc(int irq, int node)
+{
+	struct irq_desc *desc;
+	gfp_t gfp = GFP_KERNEL;
+
+	desc = kzalloc_node(sizeof(*desc), gfp, node);
+	if (!desc)
+		return NULL;
+	/* allocate based on nr_cpu_ids */
+	desc->kstat_irqs = kzalloc_node(nr_cpu_ids * sizeof(*desc->kstat_irqs),
+					 gfp, node);
+	if (!desc->kstat_irqs)
+		goto err_desc;
+
+	if (alloc_masks(desc, gfp, node))
+		goto err_kstat;
+
+	raw_spin_lock_init(&desc->lock);
+	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
+
+	desc_set_defaults(irq, desc, node);
+
+	return desc;
+
+err_kstat:
+	kfree(desc->kstat_irqs);
+err_desc:
+	kfree(desc);
+	return NULL;
+}
+
+static void free_desc(unsigned int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+
+	unregister_irq_proc(irq, desc);
+
+	mutex_lock(&sparse_irq_lock);
+	delete_irq_desc(irq);
+	mutex_unlock(&sparse_irq_lock);
+
+	free_masks(desc);
+	kfree(desc->kstat_irqs);
+	kfree(desc);
+}
+
+static int alloc_descs(unsigned int start, unsigned int cnt, int node)
+{
+	struct irq_desc *desc;
+	int i;
+
+	for (i = 0; i < cnt; i++) {
+		desc = alloc_desc(start + i, node);
+		if (!desc)
+			goto err;
+		mutex_lock(&sparse_irq_lock);
+		irq_insert_desc(start + i, desc);
+		mutex_unlock(&sparse_irq_lock);
+	}
+	return start;
+
+err:
+	for (i--; i >= 0; i--)
+		free_desc(start + i);
+
+	mutex_lock(&sparse_irq_lock);
+	bitmap_clear(allocated_irqs, start, cnt);
+	mutex_unlock(&sparse_irq_lock);
+	return -ENOMEM;
+}
+
+struct irq_desc * __ref irq_to_desc_alloc_node(unsigned int irq, int node)
+{
+	int res = irq_alloc_descs(irq, irq, 1, node);
+
+	if (res == -EEXIST || res == irq)
+		return irq_to_desc(irq);
+	return NULL;
+}
+
+int __init early_irq_init(void)
+{
+	int i, initcnt, node = first_online_node;
+	struct irq_desc *desc;
+
+	init_irq_default_affinity();
+
+	/* Let arch update nr_irqs and return the nr of preallocated irqs */
+	initcnt = arch_probe_nr_irqs();
+	printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d %d\n", NR_IRQS, nr_irqs, initcnt);
+
+	for (i = 0; i < initcnt; i++) {
+		desc = alloc_desc(i, node);
+		set_bit(i, allocated_irqs);
+		irq_insert_desc(i, desc);
+	}
+	return arch_early_irq_init();
+}
+
+#else /* !CONFIG_SPARSE_IRQ */
+
+struct irq_desc irq_desc[NR_IRQS] __cacheline_aligned_in_smp = {
+	[0 ... NR_IRQS-1] = {
+		.status		= IRQ_DEFAULT_INIT_FLAGS,
+		.handle_irq	= handle_bad_irq,
+		.depth		= 1,
+		.lock		= __RAW_SPIN_LOCK_UNLOCKED(irq_desc->lock),
+	}
+};
+
+static unsigned int kstat_irqs_all[NR_IRQS][NR_CPUS];
+int __init early_irq_init(void)
+{
+	int count, i, node = first_online_node;
+	struct irq_desc *desc;
+
+	init_irq_default_affinity();
+
+	printk(KERN_INFO "NR_IRQS:%d\n", NR_IRQS);
+
+	desc = irq_desc;
+	count = ARRAY_SIZE(irq_desc);
+
+	for (i = 0; i < count; i++) {
+		desc[i].irq_data.irq = i;
+		desc[i].irq_data.chip = &no_irq_chip;
+		desc[i].kstat_irqs = kstat_irqs_all[i];
+		alloc_masks(desc + i, GFP_KERNEL, node);
+		desc_smp_init(desc + i, node);
+		lockdep_set_class(&desc[i].lock, &irq_desc_lock_class);
+	}
+	return arch_early_irq_init();
+}
+
+struct irq_desc *irq_to_desc(unsigned int irq)
+{
+	return (irq < NR_IRQS) ? irq_desc + irq : NULL;
+}
+
+struct irq_desc *irq_to_desc_alloc_node(unsigned int irq, int node)
+{
+	return irq_to_desc(irq);
+}
+
+static void free_desc(unsigned int irq)
+{
+	dynamic_irq_cleanup(irq);
+}
+
+static inline int alloc_descs(unsigned int start, unsigned int cnt, int node)
+{
+	return start;
+}
+#endif /* !CONFIG_SPARSE_IRQ */
+
+/* Dynamic interrupt handling */
+
+/**
+ * irq_free_descs - free irq descriptors
+ * @from:	Start of descriptor range
+ * @cnt:	Number of consecutive irqs to free
+ */
+void irq_free_descs(unsigned int from, unsigned int cnt)
+{
+	int i;
+
+	if (from >= nr_irqs || (from + cnt) > nr_irqs)
+		return;
+
+	for (i = 0; i < cnt; i++)
+		free_desc(from + i);
+
+	mutex_lock(&sparse_irq_lock);
+	bitmap_clear(allocated_irqs, from, cnt);
+	mutex_unlock(&sparse_irq_lock);
+}
+
+/**
+ * irq_alloc_descs - allocate and initialize a range of irq descriptors
+ * @irq:	Allocate for specific irq number if irq >= 0
+ * @from:	Start the search from this irq number
+ * @cnt:	Number of consecutive irqs to allocate.
+ * @node:	Preferred node on which the irq descriptor should be allocated
+ *
+ * Returns the first irq number or error code
+ */
+int __ref
+irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node)
+{
+	int start, ret;
+
+	if (!cnt)
+		return -EINVAL;
+
+	mutex_lock(&sparse_irq_lock);
+
+	start = bitmap_find_next_zero_area(allocated_irqs, nr_irqs, from, cnt, 0);
+	ret = -EEXIST;
+	if (irq >=0 && start != irq)
+		goto err;
+
+	ret = -ENOMEM;
+	if (start >= nr_irqs)
+		goto err;
+
+	bitmap_set(allocated_irqs, start, cnt);
+	mutex_unlock(&sparse_irq_lock);
+	return alloc_descs(start, cnt, node);
+
+err:
+	mutex_unlock(&sparse_irq_lock);
+	return ret;
+}
+
+/**
+ * irq_reserve_irqs - mark irqs allocated
+ * @from:	mark from irq number
+ * @cnt:	number of irqs to mark
+ *
+ * Returns 0 on success or an appropriate error code
+ */
+int irq_reserve_irqs(unsigned int from, unsigned int cnt)
+{
+	unsigned int start;
+	int ret = 0;
+
+	if (!cnt || (from + cnt) > nr_irqs)
+		return -EINVAL;
+
+	mutex_lock(&sparse_irq_lock);
+	start = bitmap_find_next_zero_area(allocated_irqs, nr_irqs, from, cnt, 0);
+	if (start == from)
+		bitmap_set(allocated_irqs, start, cnt);
+	else
+		ret = -EEXIST;
+	mutex_unlock(&sparse_irq_lock);
+	return ret;
+}
+
+/**
+ * irq_get_next_irq - get next allocated irq number
+ * @offset:	where to start the search
+ *
+ * Returns next irq number after offset or nr_irqs if none is found.
+ */
+unsigned int irq_get_next_irq(unsigned int offset)
+{
+	return find_next_bit(allocated_irqs, nr_irqs, offset);
+}
+
+/**
+ * dynamic_irq_cleanup - cleanup a dynamically allocated irq
+ * @irq:	irq number to initialize
+ */
+void dynamic_irq_cleanup(unsigned int irq)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&desc->lock, flags);
+	desc_set_defaults(irq, desc, desc_node(desc));
+	raw_spin_unlock_irqrestore(&desc->lock, flags);
+}
+
+unsigned int kstat_irqs_cpu(unsigned int irq, int cpu)
+{
+	struct irq_desc *desc = irq_to_desc(irq);
+	return desc ? desc->kstat_irqs[cpu] : 0;
+}

kernel/irq/manage.c

@@ -73,8 +73,8 @@ int irq_can_set_affinity(unsigned int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
 
-	if (CHECK_IRQ_PER_CPU(desc->status) || !desc->chip ||
-	    !desc->chip->set_affinity)
+	if (CHECK_IRQ_PER_CPU(desc->status) || !desc->irq_data.chip ||
+	    !desc->irq_data.chip->irq_set_affinity)
 		return 0;
 
 	return 1;
@@ -109,17 +109,18 @@ void irq_set_thread_affinity(struct irq_desc *desc)
 int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_chip *chip = desc->irq_data.chip;
 	unsigned long flags;
 
-	if (!desc->chip->set_affinity)
+	if (!chip->irq_set_affinity)
 		return -EINVAL;
 
 	raw_spin_lock_irqsave(&desc->lock, flags);
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	if (desc->status & IRQ_MOVE_PCNTXT) {
-		if (!desc->chip->set_affinity(irq, cpumask)) {
-			cpumask_copy(desc->affinity, cpumask);
+		if (!chip->irq_set_affinity(&desc->irq_data, cpumask, false)) {
+			cpumask_copy(desc->irq_data.affinity, cpumask);
 			irq_set_thread_affinity(desc);
 		}
 	}
@@ -128,8 +129,8 @@ int irq_set_affinity(unsigned int irq, const struct cpumask *cpumask)
 		cpumask_copy(desc->pending_mask, cpumask);
 	}
 #else
-	if (!desc->chip->set_affinity(irq, cpumask)) {
-		cpumask_copy(desc->affinity, cpumask);
+	if (!chip->irq_set_affinity(&desc->irq_data, cpumask, false)) {
+		cpumask_copy(desc->irq_data.affinity, cpumask);
 		irq_set_thread_affinity(desc);
 	}
 #endif
@@ -168,16 +169,16 @@ static int setup_affinity(unsigned int irq, struct irq_desc *desc)
 	 * one of the targets is online.
 	 */
 	if (desc->status & (IRQ_AFFINITY_SET | IRQ_NO_BALANCING)) {
-		if (cpumask_any_and(desc->affinity, cpu_online_mask)
+		if (cpumask_any_and(desc->irq_data.affinity, cpu_online_mask)
 		    < nr_cpu_ids)
 			goto set_affinity;
 		else
 			desc->status &= ~IRQ_AFFINITY_SET;
 	}
 
-	cpumask_and(desc->affinity, cpu_online_mask, irq_default_affinity);
+	cpumask_and(desc->irq_data.affinity, cpu_online_mask, irq_default_affinity);
 set_affinity:
-	desc->chip->set_affinity(irq, desc->affinity);
+	desc->irq_data.chip->irq_set_affinity(&desc->irq_data, desc->irq_data.affinity, false);
 
 	return 0;
 }
@@ -223,7 +224,7 @@ void __disable_irq(struct irq_desc *desc, unsigned int irq, bool suspend)
 
 	if (!desc->depth++) {
 		desc->status |= IRQ_DISABLED;
-		desc->chip->disable(irq);
+		desc->irq_data.chip->irq_disable(&desc->irq_data);
 	}
 }
 
@@ -246,11 +247,11 @@ void disable_irq_nosync(unsigned int irq)
 	if (!desc)
 		return;
 
-	chip_bus_lock(irq, desc);
+	chip_bus_lock(desc);
 	raw_spin_lock_irqsave(&desc->lock, flags);
 	__disable_irq(desc, irq, false);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	chip_bus_sync_unlock(irq, desc);
+	chip_bus_sync_unlock(desc);
 }
 EXPORT_SYMBOL(disable_irq_nosync);
 
@@ -313,7 +314,7 @@ void __enable_irq(struct irq_desc *desc, unsigned int irq, bool resume)
  *	IRQ line is re-enabled.
  *
  *	This function may be called from IRQ context only when
- *	desc->chip->bus_lock and desc->chip->bus_sync_unlock are NULL !
+ *	desc->irq_data.chip->bus_lock and desc->chip->bus_sync_unlock are NULL !
  */
 void enable_irq(unsigned int irq)
 {
@@ -323,11 +324,11 @@ void enable_irq(unsigned int irq)
 	if (!desc)
 		return;
 
-	chip_bus_lock(irq, desc);
+	chip_bus_lock(desc);
 	raw_spin_lock_irqsave(&desc->lock, flags);
 	__enable_irq(desc, irq, false);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
-	chip_bus_sync_unlock(irq, desc);
+	chip_bus_sync_unlock(desc);
 }
 EXPORT_SYMBOL(enable_irq);
 
@@ -336,8 +337,8 @@ static int set_irq_wake_real(unsigned int irq, unsigned int on)
 	struct irq_desc *desc = irq_to_desc(irq);
 	int ret = -ENXIO;
 
-	if (desc->chip->set_wake)
-		ret = desc->chip->set_wake(irq, on);
+	if (desc->irq_data.chip->irq_set_wake)
+		ret = desc->irq_data.chip->irq_set_wake(&desc->irq_data, on);
 
 	return ret;
 }
@@ -429,12 +430,12 @@ void compat_irq_chip_set_default_handler(struct irq_desc *desc)
 }
 
 int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
-		unsigned long flags)
+		      unsigned long flags)
 {
 	int ret;
-	struct irq_chip *chip = desc->chip;
+	struct irq_chip *chip = desc->irq_data.chip;
 
-	if (!chip || !chip->set_type) {
+	if (!chip || !chip->irq_set_type) {
 		/*
 		 * IRQF_TRIGGER_* but the PIC does not support multiple
 		 * flow-types?
@@ -445,11 +446,11 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 	}
 
 	/* caller masked out all except trigger mode flags */
-	ret = chip->set_type(irq, flags);
+	ret = chip->irq_set_type(&desc->irq_data, flags);
 
 	if (ret)
-		pr_err("setting trigger mode %d for irq %u failed (%pF)\n",
-				(int)flags, irq, chip->set_type);
+		pr_err("setting trigger mode %lu for irq %u failed (%pF)\n",
+		       flags, irq, chip->irq_set_type);
 	else {
 		if (flags & (IRQ_TYPE_LEVEL_LOW | IRQ_TYPE_LEVEL_HIGH))
 			flags |= IRQ_LEVEL;
@@ -457,8 +458,8 @@ int __irq_set_trigger(struct irq_desc *desc, unsigned int irq,
 		desc->status &= ~(IRQ_LEVEL | IRQ_TYPE_SENSE_MASK);
 		desc->status |= flags;
 
-		if (chip != desc->chip)
-			irq_chip_set_defaults(desc->chip);
+		if (chip != desc->irq_data.chip)
+			irq_chip_set_defaults(desc->irq_data.chip);
 	}
 
 	return ret;
@@ -507,7 +508,7 @@ static int irq_wait_for_interrupt(struct irqaction *action)
 static void irq_finalize_oneshot(unsigned int irq, struct irq_desc *desc)
 {
 again:
-	chip_bus_lock(irq, desc);
+	chip_bus_lock(desc);
 	raw_spin_lock_irq(&desc->lock);
 
 	/*
@@ -521,17 +522,17 @@ again:
 	 */
 	if (unlikely(desc->status & IRQ_INPROGRESS)) {
 		raw_spin_unlock_irq(&desc->lock);
-		chip_bus_sync_unlock(irq, desc);
+		chip_bus_sync_unlock(desc);
 		cpu_relax();
 		goto again;
 	}
 
 	if (!(desc->status & IRQ_DISABLED) && (desc->status & IRQ_MASKED)) {
 		desc->status &= ~IRQ_MASKED;
-		desc->chip->unmask(irq);
+		desc->irq_data.chip->irq_unmask(&desc->irq_data);
 	}
 	raw_spin_unlock_irq(&desc->lock);
-	chip_bus_sync_unlock(irq, desc);
+	chip_bus_sync_unlock(desc);
 }
 
 #ifdef CONFIG_SMP
@@ -556,7 +557,7 @@ irq_thread_check_affinity(struct irq_desc *desc, struct irqaction *action)
 	}
 
 	raw_spin_lock_irq(&desc->lock);
-	cpumask_copy(mask, desc->affinity);
+	cpumask_copy(mask, desc->irq_data.affinity);
 	raw_spin_unlock_irq(&desc->lock);
 
 	set_cpus_allowed_ptr(current, mask);
@@ -657,7 +658,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	if (!desc)
 		return -EINVAL;
 
-	if (desc->chip == &no_irq_chip)
+	if (desc->irq_data.chip == &no_irq_chip)
 		return -ENOSYS;
 	/*
 	 * Some drivers like serial.c use request_irq() heavily,
@@ -752,7 +753,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 	}
 
 	if (!shared) {
-		irq_chip_set_defaults(desc->chip);
+		irq_chip_set_defaults(desc->irq_data.chip);
 
 		init_waitqueue_head(&desc->wait_for_threads);
 
@@ -779,7 +780,7 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
 		if (!(desc->status & IRQ_NOAUTOEN)) {
 			desc->depth = 0;
 			desc->status &= ~IRQ_DISABLED;
-			desc->chip->startup(irq);
+			desc->irq_data.chip->irq_startup(&desc->irq_data);
 		} else
 			/* Undo nested disables: */
 			desc->depth = 1;
@@ -912,17 +913,17 @@ static struct irqaction *__free_irq(unsigned int irq, void *dev_id)
 
 	/* Currently used only by UML, might disappear one day: */
 #ifdef CONFIG_IRQ_RELEASE_METHOD
-	if (desc->chip->release)
-		desc->chip->release(irq, dev_id);
+	if (desc->irq_data.chip->release)
+		desc->irq_data.chip->release(irq, dev_id);
 #endif
 
 	/* If this was the last handler, shut down the IRQ line: */
 	if (!desc->action) {
 		desc->status |= IRQ_DISABLED;
-		if (desc->chip->shutdown)
-			desc->chip->shutdown(irq);
+		if (desc->irq_data.chip->irq_shutdown)
+			desc->irq_data.chip->irq_shutdown(&desc->irq_data);
 		else
-			desc->chip->disable(irq);
+			desc->irq_data.chip->irq_disable(&desc->irq_data);
 	}
 
 #ifdef CONFIG_SMP
@@ -997,9 +998,9 @@ void free_irq(unsigned int irq, void *dev_id)
 	if (!desc)
 		return;
 
-	chip_bus_lock(irq, desc);
+	chip_bus_lock(desc);
 	kfree(__free_irq(irq, dev_id));
-	chip_bus_sync_unlock(irq, desc);
+	chip_bus_sync_unlock(desc);
 }
 EXPORT_SYMBOL(free_irq);
 
@@ -1086,9 +1087,9 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
 	action->name = devname;
 	action->dev_id = dev_id;
 
-	chip_bus_lock(irq, desc);
+	chip_bus_lock(desc);
 	retval = __setup_irq(irq, desc, action);
-	chip_bus_sync_unlock(irq, desc);
+	chip_bus_sync_unlock(desc);
 
 	if (retval)
 		kfree(action);

kernel/irq/migration.c

@@ -7,6 +7,7 @@
 void move_masked_irq(int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
+	struct irq_chip *chip = desc->irq_data.chip;
 
 	if (likely(!(desc->status & IRQ_MOVE_PENDING)))
 		return;
@@ -24,7 +25,7 @@ void move_masked_irq(int irq)
 	if (unlikely(cpumask_empty(desc->pending_mask)))
 		return;
 
-	if (!desc->chip->set_affinity)
+	if (!chip->irq_set_affinity)
 		return;
 
 	assert_raw_spin_locked(&desc->lock);
@@ -43,8 +44,9 @@ void move_masked_irq(int irq)
 	 */
 	if (likely(cpumask_any_and(desc->pending_mask, cpu_online_mask)
 		   < nr_cpu_ids))
-		if (!desc->chip->set_affinity(irq, desc->pending_mask)) {
-			cpumask_copy(desc->affinity, desc->pending_mask);
+		if (!chip->irq_set_affinity(&desc->irq_data,
+					    desc->pending_mask, false)) {
+			cpumask_copy(desc->irq_data.affinity, desc->pending_mask);
 			irq_set_thread_affinity(desc);
 		}
 
@@ -61,8 +63,8 @@ void move_native_irq(int irq)
 	if (unlikely(desc->status & IRQ_DISABLED))
 		return;
 
-	desc->chip->mask(irq);
+	desc->irq_data.chip->irq_mask(&desc->irq_data);
 	move_masked_irq(irq);
-	desc->chip->unmask(irq);
+	desc->irq_data.chip->irq_unmask(&desc->irq_data);
 }
 

kernel/irq/numa_migrate.c

@@ -1,120 +0,0 @@
-/*
- * NUMA irq-desc migration code
- *
- * Migrate IRQ data structures (irq_desc, chip_data, etc.) over to
- * the new "home node" of the IRQ.
- */
-
-#include <linux/irq.h>
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/random.h>
-#include <linux/interrupt.h>
-#include <linux/kernel_stat.h>
-
-#include "internals.h"
-
-static void init_copy_kstat_irqs(struct irq_desc *old_desc,
-				 struct irq_desc *desc,
-				 int node, int nr)
-{
-	init_kstat_irqs(desc, node, nr);
-
-	if (desc->kstat_irqs != old_desc->kstat_irqs)
-		memcpy(desc->kstat_irqs, old_desc->kstat_irqs,
-			 nr * sizeof(*desc->kstat_irqs));
-}
-
-static void free_kstat_irqs(struct irq_desc *old_desc, struct irq_desc *desc)
-{
-	if (old_desc->kstat_irqs == desc->kstat_irqs)
-		return;
-
-	kfree(old_desc->kstat_irqs);
-	old_desc->kstat_irqs = NULL;
-}
-
-static bool init_copy_one_irq_desc(int irq, struct irq_desc *old_desc,
-		 struct irq_desc *desc, int node)
-{
-	memcpy(desc, old_desc, sizeof(struct irq_desc));
-	if (!alloc_desc_masks(desc, node, false)) {
-		printk(KERN_ERR "irq %d: can not get new irq_desc cpumask "
-				"for migration.\n", irq);
-		return false;
-	}
-	raw_spin_lock_init(&desc->lock);
-	desc->node = node;
-	lockdep_set_class(&desc->lock, &irq_desc_lock_class);
-	init_copy_kstat_irqs(old_desc, desc, node, nr_cpu_ids);
-	init_copy_desc_masks(old_desc, desc);
-	arch_init_copy_chip_data(old_desc, desc, node);
-	return true;
-}
-
-static void free_one_irq_desc(struct irq_desc *old_desc, struct irq_desc *desc)
-{
-	free_kstat_irqs(old_desc, desc);
-	free_desc_masks(old_desc, desc);
-	arch_free_chip_data(old_desc, desc);
-}
-
-static struct irq_desc *__real_move_irq_desc(struct irq_desc *old_desc,
-						int node)
-{
-	struct irq_desc *desc;
-	unsigned int irq;
-	unsigned long flags;
-
-	irq = old_desc->irq;
-
-	raw_spin_lock_irqsave(&sparse_irq_lock, flags);
-
-	/* We have to check it to avoid races with another CPU */
-	desc = irq_to_desc(irq);
-
-	if (desc && old_desc != desc)
-		goto out_unlock;
-
-	desc = kzalloc_node(sizeof(*desc), GFP_ATOMIC, node);
-	if (!desc) {
-		printk(KERN_ERR "irq %d: can not get new irq_desc "
-				"for migration.\n", irq);
-		/* still use old one */
-		desc = old_desc;
-		goto out_unlock;
-	}
-	if (!init_copy_one_irq_desc(irq, old_desc, desc, node)) {
-		/* still use old one */
-		kfree(desc);
-		desc = old_desc;
-		goto out_unlock;
-	}
-
-	replace_irq_desc(irq, desc);
-	raw_spin_unlock_irqrestore(&sparse_irq_lock, flags);
-
-	/* free the old one */
-	free_one_irq_desc(old_desc, desc);
-	kfree(old_desc);
-
-	return desc;
-
-out_unlock:
-	raw_spin_unlock_irqrestore(&sparse_irq_lock, flags);
-
-	return desc;
-}
-
-struct irq_desc *move_irq_desc(struct irq_desc *desc, int node)
-{
-	/* those static or target node is -1, do not move them */
-	if (desc->irq < NR_IRQS_LEGACY || node == -1)
-		return desc;
-
-	if (desc->node != node)
-		desc = __real_move_irq_desc(desc, node);
-
-	return desc;
-}
-

kernel/irq/proc.c

@@ -21,7 +21,7 @@ static struct proc_dir_entry *root_irq_dir;
 static int irq_affinity_proc_show(struct seq_file *m, void *v)
 {
 	struct irq_desc *desc = irq_to_desc((long)m->private);
-	const struct cpumask *mask = desc->affinity;
+	const struct cpumask *mask = desc->irq_data.affinity;
 
 #ifdef CONFIG_GENERIC_PENDING_IRQ
 	if (desc->status & IRQ_MOVE_PENDING)
@@ -65,7 +65,7 @@ static ssize_t irq_affinity_proc_write(struct file *file,
 	cpumask_var_t new_value;
 	int err;
 
-	if (!irq_to_desc(irq)->chip->set_affinity || no_irq_affinity ||
+	if (!irq_to_desc(irq)->irq_data.chip->irq_set_affinity || no_irq_affinity ||
 	    irq_balancing_disabled(irq))
 		return -EIO;
 
@@ -185,7 +185,7 @@ static int irq_node_proc_show(struct seq_file *m, void *v)
 {
 	struct irq_desc *desc = irq_to_desc((long) m->private);
 
-	seq_printf(m, "%d\n", desc->node);
+	seq_printf(m, "%d\n", desc->irq_data.node);
 	return 0;
 }
 
@@ -269,7 +269,7 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 {
 	char name [MAX_NAMELEN];
 
-	if (!root_irq_dir || (desc->chip == &no_irq_chip) || desc->dir)
+	if (!root_irq_dir || (desc->irq_data.chip == &no_irq_chip) || desc->dir)
 		return;
 
 	memset(name, 0, MAX_NAMELEN);
@@ -297,6 +297,24 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
 			 &irq_spurious_proc_fops, (void *)(long)irq);
 }
 
+void unregister_irq_proc(unsigned int irq, struct irq_desc *desc)
+{
+	char name [MAX_NAMELEN];
+
+	if (!root_irq_dir || !desc->dir)
+		return;
+#ifdef CONFIG_SMP
+	remove_proc_entry("smp_affinity", desc->dir);
+	remove_proc_entry("affinity_hint", desc->dir);
+	remove_proc_entry("node", desc->dir);
+#endif
+	remove_proc_entry("spurious", desc->dir);
+
+	memset(name, 0, MAX_NAMELEN);
+	sprintf(name, "%u", irq);
+	remove_proc_entry(name, root_irq_dir);
+}
+
 #undef MAX_NAMELEN
 
 void unregister_handler_proc(unsigned int irq, struct irqaction *action)

kernel/irq/resend.c

@@ -60,7 +60,7 @@ void check_irq_resend(struct irq_desc *desc, unsigned int irq)
 	/*
 	 * Make sure the interrupt is enabled, before resending it:
 	 */
-	desc->chip->enable(irq);
+	desc->irq_data.chip->irq_enable(&desc->irq_data);
 
 	/*
 	 * We do not resend level type interrupts. Level type
@@ -70,7 +70,8 @@ void check_irq_resend(struct irq_desc *desc, unsigned int irq)
 	if ((status & (IRQ_LEVEL | IRQ_PENDING | IRQ_REPLAY)) == IRQ_PENDING) {
 		desc->status = (status & ~IRQ_PENDING) | IRQ_REPLAY;
 
-		if (!desc->chip->retrigger || !desc->chip->retrigger(irq)) {
+		if (!desc->irq_data.chip->irq_retrigger ||
+		    !desc->irq_data.chip->irq_retrigger(&desc->irq_data)) {
 #ifdef CONFIG_HARDIRQS_SW_RESEND
 			/* Set it pending and activate the softirq: */
 			set_bit(irq, irqs_resend);

kernel/irq/spurious.c

@@ -14,6 +14,8 @@
 #include <linux/moduleparam.h>
 #include <linux/timer.h>
 
+#include "internals.h"
+
 static int irqfixup __read_mostly;
 
 #define POLL_SPURIOUS_IRQ_INTERVAL (HZ/10)
@@ -78,8 +80,8 @@ static int try_one_irq(int irq, struct irq_desc *desc)
 	 * If we did actual work for the real IRQ line we must let the
 	 * IRQ controller clean up too
 	 */
-	if (work && desc->chip && desc->chip->end)
-		desc->chip->end(irq);
+	if (work)
+		irq_end(irq, desc);
 	raw_spin_unlock(&desc->lock);
 
 	return ok;
@@ -254,7 +256,7 @@ void note_interrupt(unsigned int irq, struct irq_desc *desc,
 		printk(KERN_EMERG "Disabling IRQ #%d\n", irq);
 		desc->status |= IRQ_DISABLED | IRQ_SPURIOUS_DISABLED;
 		desc->depth++;
-		desc->chip->disable(irq);
+		desc->irq_data.chip->irq_disable(&desc->irq_data);
 
 		mod_timer(&poll_spurious_irq_timer,
 			  jiffies + POLL_SPURIOUS_IRQ_INTERVAL);

kernel/softirq.c

@@ -910,17 +910,14 @@ int __init __weak early_irq_init(void)
 	return 0;
 }
 
+#ifdef CONFIG_GENERIC_HARDIRQS
 int __init __weak arch_probe_nr_irqs(void)
 {
-	return 0;
+	return NR_IRQS_LEGACY;
 }
 
 int __init __weak arch_early_irq_init(void)
 {
 	return 0;
 }
-
-int __weak arch_init_chip_data(struct irq_desc *desc, int node)
-{
-	return 0;
-}
+#endif