x86/hpet: Enhance HPET IRQ to support hierarchical irqdomains

Signed-off-by: Jiang Liu <jiang.liu@linux.intel.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: David Cohen <david.a.cohen@linux.intel.com>
Cc: Sander Eikelenboom <linux@eikelenboom.it>
Cc: David Vrabel <david.vrabel@citrix.com>
Cc: Tony Luck <tony.luck@intel.com>
Cc: Joerg Roedel <joro@8bytes.org>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Srivatsa S. Bhat <srivatsa.bhat@linux.vnet.ibm.com>
Cc: Bjorn Helgaas <bhelgaas@google.com>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Rafael J. Wysocki <rjw@rjwysocki.net>
Cc: Randy Dunlap <rdunlap@infradead.org>
Cc: Yinghai Lu <yinghai@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Dimitri Sivanich <sivanich@sgi.com>
Cc: Andy Lutomirski <luto@amacapital.net>
Link: http://lkml.kernel.org/r/1428905519-23704-13-git-send-email-jiang.liu@linux.intel.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

3 files changed, 167 insertions, 63 deletions

diff --git a/arch/x86/include/asm/hpet.h b/arch/x86/include/asm/hpet.h
index 36f7125945e3..e87e9faf87a9 100644
--- a/arch/x86/include/asm/hpet.h
+++ b/arch/x86/include/asm/hpet.h
@@ -74,11 +74,16 @@ extern unsigned int hpet_readl(unsigned int a);
 extern void force_hpet_resume(void);
 
 struct irq_data;
+struct hpet_dev;
+struct irq_domain;
+
 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);
+extern struct irq_domain *hpet_create_irq_domain(int hpet_id);
+extern int hpet_assign_irq(struct irq_domain *domain,
+                           struct hpet_dev *dev, int dev_num);
 
 #ifdef CONFIG_PCI_MSI
 extern int default_setup_hpet_msi(unsigned int irq, unsigned int id);
diff --git a/arch/x86/kernel/apic/msi.c b/arch/x86/kernel/apic/msi.c
index 9be7d6d8a579..10d9ae8f2166 100644
--- a/arch/x86/kernel/apic/msi.c
+++ b/arch/x86/kernel/apic/msi.c
@@ -51,6 +51,44 @@ void native_compose_msi_msg(struct pci_dev *pdev,
                 MSI_DATA_VECTOR(cfg->vector);
 }
 
+static void irq_msi_compose_msg(struct irq_data *data, struct msi_msg *msg)
+{
+        struct irq_cfg *cfg = irqd_cfg(data);
+
+        msg->address_hi = MSI_ADDR_BASE_HI;
+
+        if (x2apic_enabled())
+                msg->address_hi |= MSI_ADDR_EXT_DEST_ID(cfg->dest_apicid);
+
+        msg->address_lo =
+                MSI_ADDR_BASE_LO |
+                ((apic->irq_dest_mode == 0) ?
+                        MSI_ADDR_DEST_MODE_PHYSICAL :
+                        MSI_ADDR_DEST_MODE_LOGICAL) |
+                ((apic->irq_delivery_mode != dest_LowestPrio) ?
+                        MSI_ADDR_REDIRECTION_CPU :
+                        MSI_ADDR_REDIRECTION_LOWPRI) |
+                MSI_ADDR_DEST_ID(cfg->dest_apicid);
+
+        msg->data =
+                MSI_DATA_TRIGGER_EDGE |
+                MSI_DATA_LEVEL_ASSERT |
+                ((apic->irq_delivery_mode != dest_LowestPrio) ?
+                        MSI_DATA_DELIVERY_FIXED :
+                        MSI_DATA_DELIVERY_LOWPRI) |
+                MSI_DATA_VECTOR(cfg->vector);
+}
+
+static void msi_update_msg(struct msi_msg *msg, struct irq_data *irq_data)
+{
+        struct irq_cfg *cfg = irqd_cfg(irq_data);
+
+        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(cfg->dest_apicid);
+}
+
 static int msi_compose_msg(struct pci_dev *pdev, unsigned int irq,
                            struct msi_msg *msg, u8 hpet_id)
 {
@@ -239,44 +277,43 @@ void dmar_free_hwirq(int irq)
  * MSI message composition
  */
 #ifdef CONFIG_HPET_TIMER
+static inline int hpet_dev_id(struct irq_domain *domain)
+{
+        return (int)(long)domain->host_data;
+}
 
 static int hpet_msi_set_affinity(struct irq_data *data,
                                  const struct cpumask *mask, bool force)
 {
-        struct irq_cfg *cfg = irqd_cfg(data);
+        struct irq_data *parent = data->parent_data;
         struct msi_msg msg;
-        unsigned int dest;
         int ret;
 
-        ret = apic_set_affinity(data, mask, &dest);
-        if (ret)
-                return ret;
-
-        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(data->handler_data, &msg);
+        ret = parent->chip->irq_set_affinity(parent, mask, force);
+        if (ret >= 0 && ret != IRQ_SET_MASK_OK_DONE) {
+                hpet_msi_read(data->handler_data, &msg);
+                msi_update_msg(&msg, data);
+                hpet_msi_write(data->handler_data, &msg);
+        }
 
-        return IRQ_SET_MASK_OK_NOCOPY;
+        return ret;
 }
 
-static struct irq_chip hpet_msi_type = {
+static struct irq_chip hpet_msi_controller = {
         .name = "HPET_MSI",
         .irq_unmask = hpet_msi_unmask,
         .irq_mask = hpet_msi_mask,
-        .irq_ack = apic_ack_edge,
+        .irq_ack = irq_chip_ack_parent,
         .irq_set_affinity = hpet_msi_set_affinity,
-        .irq_retrigger = apic_retrigger_irq,
+        .irq_retrigger = irq_chip_retrigger_hierarchy,
+        .irq_print_chip = irq_remapping_print_chip,
+        .irq_compose_msi_msg = irq_msi_compose_msg,
         .flags = IRQCHIP_SKIP_SET_WAKE,
 };
 
 int default_setup_hpet_msi(unsigned int irq, unsigned int id)
 {
-        struct irq_chip *chip = &hpet_msi_type;
+        struct irq_chip *chip = &hpet_msi_controller;
         struct msi_msg msg;
         int ret;
 
@@ -291,4 +328,95 @@ int default_setup_hpet_msi(unsigned int irq, unsigned int id)
         irq_set_chip_and_handler_name(irq, chip, handle_edge_irq, "edge");
         return 0;
 }
+
+static int hpet_domain_alloc(struct irq_domain *domain, unsigned int virq,
+                             unsigned int nr_irqs, void *arg)
+{
+        struct irq_alloc_info *info = arg;
+        int ret;
+
+        if (nr_irqs > 1 || !info || info->type != X86_IRQ_ALLOC_TYPE_HPET)
+                return -EINVAL;
+        if (irq_find_mapping(domain, info->hpet_index)) {
+                pr_warn("IRQ for HPET%d already exists.\n", info->hpet_index);
+                return -EEXIST;
+        }
+
+        ret = irq_domain_alloc_irqs_parent(domain, virq, nr_irqs, arg);
+        if (ret >= 0) {
+                irq_set_status_flags(virq, IRQ_MOVE_PCNTXT);
+                irq_domain_set_hwirq_and_chip(domain, virq, info->hpet_index,
+                                              &hpet_msi_controller, NULL);
+                irq_set_handler_data(virq, info->hpet_data);
+                __irq_set_handler(virq, handle_edge_irq, 0, "edge");
+        }
+
+        return ret;
+}
+
+static void hpet_domain_free(struct irq_domain *domain, unsigned int virq,
+                             unsigned int nr_irqs)
+{
+        BUG_ON(nr_irqs > 1);
+        irq_clear_status_flags(virq, IRQ_MOVE_PCNTXT);
+        irq_domain_free_irqs_top(domain, virq, nr_irqs);
+}
+
+static void hpet_domain_activate(struct irq_domain *domain,
+                                struct irq_data *irq_data)
+{
+        struct msi_msg msg;
+
+        BUG_ON(irq_chip_compose_msi_msg(irq_data, &msg));
+        hpet_msi_write(irq_get_handler_data(irq_data->irq), &msg);
+}
+
+static void hpet_domain_deactivate(struct irq_domain *domain,
+                                  struct irq_data *irq_data)
+{
+        struct msi_msg msg;
+
+        memset(&msg, 0, sizeof(msg));
+        hpet_msi_write(irq_get_handler_data(irq_data->irq), &msg);
+}
+
+static struct irq_domain_ops hpet_domain_ops = {
+        .alloc = hpet_domain_alloc,
+        .free = hpet_domain_free,
+        .activate = hpet_domain_activate,
+        .deactivate = hpet_domain_deactivate,
+};
+
+struct irq_domain *hpet_create_irq_domain(int hpet_id)
+{
+        struct irq_domain *parent;
+        struct irq_alloc_info info;
+
+        if (x86_vector_domain == NULL)
+                return NULL;
+
+        init_irq_alloc_info(&info, NULL);
+        info.type = X86_IRQ_ALLOC_TYPE_HPET;
+        info.hpet_id = hpet_id;
+        parent = irq_remapping_get_ir_irq_domain(&info);
+        if (parent == NULL)
+                parent = x86_vector_domain;
+
+        return irq_domain_add_hierarchy(parent, 0, 0, NULL, &hpet_domain_ops,
+                                        (void *)(long)hpet_id);
+}
+
+int hpet_assign_irq(struct irq_domain *domain, struct hpet_dev *dev,
+                    int dev_num)
+{
+        struct irq_alloc_info info;
+
+        init_irq_alloc_info(&info, NULL);
+        info.type = X86_IRQ_ALLOC_TYPE_HPET;
+        info.hpet_data = dev;
+        info.hpet_id = hpet_dev_id(domain);
+        info.hpet_index = dev_num;
+
+        return irq_domain_alloc_irqs(domain, 1, NUMA_NO_NODE, NULL);
+}
 #endif
diff --git a/arch/x86/kernel/hpet.c b/arch/x86/kernel/hpet.c
index ae29554f57ea..e3bc18080052 100644
--- a/arch/x86/kernel/hpet.c
+++ b/arch/x86/kernel/hpet.c
@@ -306,8 +306,6 @@ static void hpet_legacy_clockevent_register(void)
         printk(KERN_DEBUG "hpet clockevent registered\n");
 }
 
-static int hpet_setup_msi_irq(unsigned int irq);
-
 static void hpet_set_mode(enum clock_event_mode mode,
                           struct clock_event_device *evt, int timer)
 {
@@ -358,7 +356,7 @@ static void hpet_set_mode(enum clock_event_mode mode,
                         hpet_enable_legacy_int();
                 } else {
                         struct hpet_dev *hdev = EVT_TO_HPET_DEV(evt);
-                        hpet_setup_msi_irq(hdev->irq);
+                        irq_domain_activate_irq(irq_get_irq_data(hdev->irq));
                         disable_irq(hdev->irq);
                         irq_set_affinity(hdev->irq, cpumask_of(hdev->cpu));
                         enable_irq(hdev->irq);
@@ -424,6 +422,7 @@ 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;
+static struct irq_domain *hpet_domain;
 
 void hpet_msi_unmask(struct irq_data *data)
 {
@@ -474,32 +473,6 @@ static int hpet_msi_next_event(unsigned long delta,
         return hpet_next_event(delta, evt, hdev->num);
 }
 
-static int hpet_setup_msi_irq(unsigned int irq)
-{
-        if (x86_msi.setup_hpet_msi(irq, hpet_blockid)) {
-                irq_domain_free_irqs(irq, 1);
-                return -EINVAL;
-        }
-        return 0;
-}
-
-static int hpet_assign_irq(struct hpet_dev *dev)
-{
-        int irq;
-
-        irq = irq_domain_alloc_irqs(NULL, 1, NUMA_NO_NODE, NULL);
-        if (irq <= 0)
-                return -EINVAL;
-
-        irq_set_handler_data(irq, dev);
-
-        if (hpet_setup_msi_irq(irq))
-                return -EINVAL;
-
-        dev->irq = irq;
-        return 0;
-}
-
 static irqreturn_t hpet_interrupt_handler(int irq, void *data)
 {
         struct hpet_dev *dev = (struct hpet_dev *)data;
@@ -542,9 +515,6 @@ static void init_one_hpet_msi_clockevent(struct hpet_dev *hdev, int cpu)
         if (!(hdev->flags & HPET_DEV_VALID))
                 return;
 
-        if (hpet_setup_msi_irq(hdev->irq))
-                return;
-
         hdev->cpu = cpu;
         per_cpu(cpu_hpet_dev, cpu) = hdev;
         evt->name = hdev->name;
@@ -576,7 +546,7 @@ static void hpet_msi_capability_lookup(unsigned int start_timer)
         unsigned int id;
         unsigned int num_timers;
         unsigned int num_timers_used = 0;
-        int i;
+        int i, irq;
 
         if (hpet_msi_disable)
                 return;
@@ -589,6 +559,10 @@ static void hpet_msi_capability_lookup(unsigned int start_timer)
         num_timers++; /* Value read out starts from 0 */
         hpet_print_config();
 
+        hpet_domain = hpet_create_irq_domain(hpet_blockid);
+        if (!hpet_domain)
+                return;
+
         hpet_devs = kzalloc(sizeof(struct hpet_dev) * num_timers, GFP_KERNEL);
         if (!hpet_devs)
                 return;
@@ -603,15 +577,16 @@ static void hpet_msi_capability_lookup(unsigned int start_timer)
                 if (!(cfg & HPET_TN_FSB_CAP))
                         continue;
 
+                irq = hpet_assign_irq(hpet_domain, hdev, hdev->num);
+                if (irq < 0)
+                        continue;
+
+                sprintf(hdev->name, "hpet%d", i);
+                hdev->num = i;
+                hdev->irq = irq;
                 hdev->flags = 0;
                 if (cfg & HPET_TN_PERIODIC_CAP)
                         hdev->flags |= HPET_DEV_PERI_CAP;
-                hdev->num = i;
-
-                sprintf(hdev->name, "hpet%d", i);
-                if (hpet_assign_irq(hdev))
-                        continue;
-
                 hdev->flags |= HPET_DEV_FSB_CAP;
                 hdev->flags |= HPET_DEV_VALID;
                 num_timers_used++;
@@ -711,10 +686,6 @@ static int hpet_cpuhp_notify(struct notifier_block *n,
 }
 #else
 
-static int hpet_setup_msi_irq(unsigned int irq)
-{
-        return 0;
-}
 static void hpet_msi_capability_lookup(unsigned int start_timer)
 {
         return;