genirq/core: Introduce struct irq_affinity_desc
The interrupt affinity management uses straight cpumask pointers to convey
the automatically assigned affinity masks for managed interrupts. The core
interrupt descriptor allocation also decides based on the pointer being non
NULL whether an interrupt is managed or not.
Devices which use managed interrupts usually have two classes of
interrupts:
- Interrupts for multiple device queues
- Interrupts for general device management
Currently both classes are treated the same way, i.e. as managed
interrupts. The general interrupts get the default affinity mask assigned
while the device queue interrupts are spread out over the possible CPUs.
Treating the general interrupts as managed is both a limitation and under
certain circumstances a bug. Assume the following situation:
default_irq_affinity = 4..7
So if CPUs 4-7 are offlined, then the core code will shut down the device
management interrupts because the last CPU in their affinity mask went
offline.
It's also a limitation because it's desired to allow manual placement of
the general device interrupts for various reasons. If they are marked
managed then the interrupt affinity setting from both user and kernel space
is disabled.
To remedy that situation it's required to convey more information than the
cpumasks through various interfaces related to interrupt descriptor
allocation.
Instead of adding yet another argument, create a new data structure
'irq_affinity_desc' which for now just contains the cpumask. This struct
can be expanded to convey auxilliary information in the next step.
No functional change, just preparatory work.
[ tglx: Simplified logic and clarified changelog ]
Suggested-by: Thomas Gleixner <tglx@linutronix.de>
Suggested-by: Bjorn Helgaas <bhelgaas@google.com>
Signed-off-by: Dou Liyang <douliyangs@gmail.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-pci@vger.kernel.org
Cc: kashyap.desai@broadcom.com
Cc: shivasharan.srikanteshwara@broadcom.com
Cc: sumit.saxena@broadcom.com
Cc: ming.lei@redhat.com
Cc: hch@lst.de
Cc: douliyang1@huawei.com
Link: https://lkml.kernel.org/r/20181204155122.6327-2-douliyangs@gmail.com
diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
index ca397ff..c44b7844 100644
--- a/include/linux/interrupt.h
+++ b/include/linux/interrupt.h
@@ -257,6 +257,14 @@ struct irq_affinity {
int *sets;
};
+/**
+ * struct irq_affinity_desc - Interrupt affinity descriptor
+ * @mask: cpumask to hold the affinity assignment
+ */
+struct irq_affinity_desc {
+ struct cpumask mask;
+};
+
#if defined(CONFIG_SMP)
extern cpumask_var_t irq_default_affinity;
@@ -303,7 +311,9 @@ extern int irq_set_affinity_hint(unsigned int irq, const struct cpumask *m);
extern int
irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify);
-struct cpumask *irq_create_affinity_masks(int nvec, const struct irq_affinity *affd);
+struct irq_affinity_desc *
+irq_create_affinity_masks(int nvec, const struct irq_affinity *affd);
+
int irq_calc_affinity_vectors(int minvec, int maxvec, const struct irq_affinity *affd);
#else /* CONFIG_SMP */
@@ -337,7 +347,7 @@ irq_set_affinity_notifier(unsigned int irq, struct irq_affinity_notify *notify)
return 0;
}
-static inline struct cpumask *
+static inline struct irq_affinity_desc *
irq_create_affinity_masks(int nvec, const struct irq_affinity *affd)
{
return NULL;
diff --git a/include/linux/irq.h b/include/linux/irq.h
index c9bffda..def2b2a 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -27,6 +27,7 @@
struct seq_file;
struct module;
struct msi_msg;
+struct irq_affinity_desc;
enum irqchip_irq_state;
/*
@@ -834,11 +835,12 @@ struct cpumask *irq_data_get_effective_affinity_mask(struct irq_data *d)
unsigned int arch_dynirq_lower_bound(unsigned int from);
int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
- struct module *owner, const struct cpumask *affinity);
+ struct module *owner,
+ const struct irq_affinity_desc *affinity);
int __devm_irq_alloc_descs(struct device *dev, int irq, unsigned int from,
unsigned int cnt, int node, struct module *owner,
- const struct cpumask *affinity);
+ const struct irq_affinity_desc *affinity);
/* use macros to avoid needing export.h for THIS_MODULE */
#define irq_alloc_descs(irq, from, cnt, node) \
diff --git a/include/linux/irqdomain.h b/include/linux/irqdomain.h
index 068aa46..35965f4 100644
--- a/include/linux/irqdomain.h
+++ b/include/linux/irqdomain.h
@@ -43,6 +43,7 @@ struct irq_chip;
struct irq_data;
struct cpumask;
struct seq_file;
+struct irq_affinity_desc;
/* Number of irqs reserved for a legacy isa controller */
#define NUM_ISA_INTERRUPTS 16
@@ -266,7 +267,7 @@ extern bool irq_domain_check_msi_remap(void);
extern void irq_set_default_host(struct irq_domain *host);
extern int irq_domain_alloc_descs(int virq, unsigned int nr_irqs,
irq_hw_number_t hwirq, int node,
- const struct cpumask *affinity);
+ const struct irq_affinity_desc *affinity);
static inline struct fwnode_handle *of_node_to_fwnode(struct device_node *node)
{
@@ -449,7 +450,8 @@ static inline struct irq_domain *irq_domain_add_hierarchy(struct irq_domain *par
extern int __irq_domain_alloc_irqs(struct irq_domain *domain, int irq_base,
unsigned int nr_irqs, int node, void *arg,
- bool realloc, const struct cpumask *affinity);
+ bool realloc,
+ const struct irq_affinity_desc *affinity);
extern void irq_domain_free_irqs(unsigned int virq, unsigned int nr_irqs);
extern int irq_domain_activate_irq(struct irq_data *irq_data, bool early);
extern void irq_domain_deactivate_irq(struct irq_data *irq_data);
diff --git a/include/linux/msi.h b/include/linux/msi.h
index eb213b8..784fb52 100644
--- a/include/linux/msi.h
+++ b/include/linux/msi.h
@@ -76,7 +76,7 @@ struct msi_desc {
unsigned int nvec_used;
struct device *dev;
struct msi_msg msg;
- struct cpumask *affinity;
+ struct irq_affinity_desc *affinity;
union {
/* PCI MSI/X specific data */
@@ -138,7 +138,7 @@ static inline void pci_write_msi_msg(unsigned int irq, struct msi_msg *msg)
#endif /* CONFIG_PCI_MSI */
struct msi_desc *alloc_msi_entry(struct device *dev, int nvec,
- const struct cpumask *affinity);
+ const struct irq_affinity_desc *affinity);
void free_msi_entry(struct msi_desc *entry);
void __pci_read_msi_msg(struct msi_desc *entry, struct msi_msg *msg);
void __pci_write_msi_msg(struct msi_desc *entry, struct msi_msg *msg);