summaryrefslogtreecommitdiffstats
path: root/kernel/irq
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/irq')
-rw-r--r--kernel/irq/affinity.c231
-rw-r--r--kernel/irq/chip.c44
-rw-r--r--kernel/irq/cpuhotplug.c21
-rw-r--r--kernel/irq/debugfs.c1
-rw-r--r--kernel/irq/irqdesc.c18
-rw-r--r--kernel/irq/irqdomain.c30
-rw-r--r--kernel/irq/manage.c57
-rw-r--r--kernel/irq/msi.c5
-rw-r--r--kernel/irq/pm.c20
-rw-r--r--kernel/irq/proc.c56
-rw-r--r--kernel/irq/resend.c2
-rw-r--r--kernel/irq/spurious.c1
12 files changed, 405 insertions, 81 deletions
diff --git a/kernel/irq/affinity.c b/kernel/irq/affinity.c
index 6fef48033f96..4d89ad4fae3b 100644
--- a/kernel/irq/affinity.c
+++ b/kernel/irq/affinity.c
@@ -7,6 +7,7 @@
#include <linux/kernel.h>
#include <linux/slab.h>
#include <linux/cpu.h>
+#include <linux/sort.h>
static void irq_spread_init_one(struct cpumask *irqmsk, struct cpumask *nmsk,
unsigned int cpus_per_vec)
@@ -94,6 +95,155 @@ static int get_nodes_in_cpumask(cpumask_var_t *node_to_cpumask,
return nodes;
}
+struct node_vectors {
+ unsigned id;
+
+ union {
+ unsigned nvectors;
+ unsigned ncpus;
+ };
+};
+
+static int ncpus_cmp_func(const void *l, const void *r)
+{
+ const struct node_vectors *ln = l;
+ const struct node_vectors *rn = r;
+
+ return ln->ncpus - rn->ncpus;
+}
+
+/*
+ * Allocate vector number for each node, so that for each node:
+ *
+ * 1) the allocated number is >= 1
+ *
+ * 2) the allocated numbver is <= active CPU number of this node
+ *
+ * The actual allocated total vectors may be less than @numvecs when
+ * active total CPU number is less than @numvecs.
+ *
+ * Active CPUs means the CPUs in '@cpu_mask AND @node_to_cpumask[]'
+ * for each node.
+ */
+static void alloc_nodes_vectors(unsigned int numvecs,
+ cpumask_var_t *node_to_cpumask,
+ const struct cpumask *cpu_mask,
+ const nodemask_t nodemsk,
+ struct cpumask *nmsk,
+ struct node_vectors *node_vectors)
+{
+ unsigned n, remaining_ncpus = 0;
+
+ for (n = 0; n < nr_node_ids; n++) {
+ node_vectors[n].id = n;
+ node_vectors[n].ncpus = UINT_MAX;
+ }
+
+ for_each_node_mask(n, nodemsk) {
+ unsigned ncpus;
+
+ cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]);
+ ncpus = cpumask_weight(nmsk);
+
+ if (!ncpus)
+ continue;
+ remaining_ncpus += ncpus;
+ node_vectors[n].ncpus = ncpus;
+ }
+
+ numvecs = min_t(unsigned, remaining_ncpus, numvecs);
+
+ sort(node_vectors, nr_node_ids, sizeof(node_vectors[0]),
+ ncpus_cmp_func, NULL);
+
+ /*
+ * Allocate vectors for each node according to the ratio of this
+ * node's nr_cpus to remaining un-assigned ncpus. 'numvecs' is
+ * bigger than number of active numa nodes. Always start the
+ * allocation from the node with minimized nr_cpus.
+ *
+ * This way guarantees that each active node gets allocated at
+ * least one vector, and the theory is simple: over-allocation
+ * is only done when this node is assigned by one vector, so
+ * other nodes will be allocated >= 1 vector, since 'numvecs' is
+ * bigger than number of numa nodes.
+ *
+ * One perfect invariant is that number of allocated vectors for
+ * each node is <= CPU count of this node:
+ *
+ * 1) suppose there are two nodes: A and B
+ * ncpu(X) is CPU count of node X
+ * vecs(X) is the vector count allocated to node X via this
+ * algorithm
+ *
+ * ncpu(A) <= ncpu(B)
+ * ncpu(A) + ncpu(B) = N
+ * vecs(A) + vecs(B) = V
+ *
+ * vecs(A) = max(1, round_down(V * ncpu(A) / N))
+ * vecs(B) = V - vecs(A)
+ *
+ * both N and V are integer, and 2 <= V <= N, suppose
+ * V = N - delta, and 0 <= delta <= N - 2
+ *
+ * 2) obviously vecs(A) <= ncpu(A) because:
+ *
+ * if vecs(A) is 1, then vecs(A) <= ncpu(A) given
+ * ncpu(A) >= 1
+ *
+ * otherwise,
+ * vecs(A) <= V * ncpu(A) / N <= ncpu(A), given V <= N
+ *
+ * 3) prove how vecs(B) <= ncpu(B):
+ *
+ * if round_down(V * ncpu(A) / N) == 0, vecs(B) won't be
+ * over-allocated, so vecs(B) <= ncpu(B),
+ *
+ * otherwise:
+ *
+ * vecs(A) =
+ * round_down(V * ncpu(A) / N) =
+ * round_down((N - delta) * ncpu(A) / N) =
+ * round_down((N * ncpu(A) - delta * ncpu(A)) / N) >=
+ * round_down((N * ncpu(A) - delta * N) / N) =
+ * cpu(A) - delta
+ *
+ * then:
+ *
+ * vecs(A) - V >= ncpu(A) - delta - V
+ * =>
+ * V - vecs(A) <= V + delta - ncpu(A)
+ * =>
+ * vecs(B) <= N - ncpu(A)
+ * =>
+ * vecs(B) <= cpu(B)
+ *
+ * For nodes >= 3, it can be thought as one node and another big
+ * node given that is exactly what this algorithm is implemented,
+ * and we always re-calculate 'remaining_ncpus' & 'numvecs', and
+ * finally for each node X: vecs(X) <= ncpu(X).
+ *
+ */
+ for (n = 0; n < nr_node_ids; n++) {
+ unsigned nvectors, ncpus;
+
+ if (node_vectors[n].ncpus == UINT_MAX)
+ continue;
+
+ WARN_ON_ONCE(numvecs == 0);
+
+ ncpus = node_vectors[n].ncpus;
+ nvectors = max_t(unsigned, 1,
+ numvecs * ncpus / remaining_ncpus);
+ WARN_ON_ONCE(nvectors > ncpus);
+
+ node_vectors[n].nvectors = nvectors;
+
+ remaining_ncpus -= ncpus;
+ numvecs -= nvectors;
+ }
+}
+
static int __irq_build_affinity_masks(unsigned int startvec,
unsigned int numvecs,
unsigned int firstvec,
@@ -102,10 +252,11 @@ static int __irq_build_affinity_masks(unsigned int startvec,
struct cpumask *nmsk,
struct irq_affinity_desc *masks)
{
- unsigned int n, nodes, cpus_per_vec, extra_vecs, done = 0;
+ unsigned int i, n, nodes, cpus_per_vec, extra_vecs, done = 0;
unsigned int last_affv = firstvec + numvecs;
unsigned int curvec = startvec;
nodemask_t nodemsk = NODE_MASK_NONE;
+ struct node_vectors *node_vectors;
if (!cpumask_weight(cpu_mask))
return 0;
@@ -126,42 +277,56 @@ static int __irq_build_affinity_masks(unsigned int startvec,
return numvecs;
}
- for_each_node_mask(n, nodemsk) {
- unsigned int ncpus, v, vecs_to_assign, vecs_per_node;
+ node_vectors = kcalloc(nr_node_ids,
+ sizeof(struct node_vectors),
+ GFP_KERNEL);
+ if (!node_vectors)
+ return -ENOMEM;
- /* Spread the vectors per node */
- vecs_per_node = (numvecs - (curvec - firstvec)) / nodes;
+ /* allocate vector number for each node */
+ alloc_nodes_vectors(numvecs, node_to_cpumask, cpu_mask,
+ nodemsk, nmsk, node_vectors);
- /* Get the cpus on this node which are in the mask */
- cpumask_and(nmsk, cpu_mask, node_to_cpumask[n]);
+ for (i = 0; i < nr_node_ids; i++) {
+ unsigned int ncpus, v;
+ struct node_vectors *nv = &node_vectors[i];
+
+ if (nv->nvectors == UINT_MAX)
+ continue;
- /* Calculate the number of cpus per vector */
+ /* Get the cpus on this node which are in the mask */
+ cpumask_and(nmsk, cpu_mask, node_to_cpumask[nv->id]);
ncpus = cpumask_weight(nmsk);
- vecs_to_assign = min(vecs_per_node, ncpus);
+ if (!ncpus)
+ continue;
+
+ WARN_ON_ONCE(nv->nvectors > ncpus);
/* Account for rounding errors */
- extra_vecs = ncpus - vecs_to_assign * (ncpus / vecs_to_assign);
+ extra_vecs = ncpus - nv->nvectors * (ncpus / nv->nvectors);
- for (v = 0; curvec < last_affv && v < vecs_to_assign;
- curvec++, v++) {
- cpus_per_vec = ncpus / vecs_to_assign;
+ /* Spread allocated vectors on CPUs of the current node */
+ for (v = 0; v < nv->nvectors; v++, curvec++) {
+ cpus_per_vec = ncpus / nv->nvectors;
/* Account for extra vectors to compensate rounding errors */
if (extra_vecs) {
cpus_per_vec++;
--extra_vecs;
}
+
+ /*
+ * wrapping has to be considered given 'startvec'
+ * may start anywhere
+ */
+ if (curvec >= last_affv)
+ curvec = firstvec;
irq_spread_init_one(&masks[curvec].mask, nmsk,
cpus_per_vec);
}
-
- done += v;
- if (done >= numvecs)
- break;
- if (curvec >= last_affv)
- curvec = firstvec;
- --nodes;
+ done += nv->nvectors;
}
+ kfree(node_vectors);
return done;
}
@@ -174,7 +339,7 @@ static int irq_build_affinity_masks(unsigned int startvec, unsigned int numvecs,
unsigned int firstvec,
struct irq_affinity_desc *masks)
{
- unsigned int curvec = startvec, nr_present, nr_others;
+ unsigned int curvec = startvec, nr_present = 0, nr_others = 0;
cpumask_var_t *node_to_cpumask;
cpumask_var_t nmsk, npresmsk;
int ret = -ENOMEM;
@@ -189,15 +354,17 @@ static int irq_build_affinity_masks(unsigned int startvec, unsigned int numvecs,
if (!node_to_cpumask)
goto fail_npresmsk;
- ret = 0;
/* Stabilize the cpumasks */
get_online_cpus();
build_node_to_cpumask(node_to_cpumask);
/* Spread on present CPUs starting from affd->pre_vectors */
- nr_present = __irq_build_affinity_masks(curvec, numvecs,
- firstvec, node_to_cpumask,
- cpu_present_mask, nmsk, masks);
+ ret = __irq_build_affinity_masks(curvec, numvecs, firstvec,
+ node_to_cpumask, cpu_present_mask,
+ nmsk, masks);
+ if (ret < 0)
+ goto fail_build_affinity;
+ nr_present = ret;
/*
* Spread on non present CPUs starting from the next vector to be
@@ -210,12 +377,16 @@ static int irq_build_affinity_masks(unsigned int startvec, unsigned int numvecs,
else
curvec = firstvec + nr_present;
cpumask_andnot(npresmsk, cpu_possible_mask, cpu_present_mask);
- nr_others = __irq_build_affinity_masks(curvec, numvecs,
- firstvec, node_to_cpumask,
- npresmsk, nmsk, masks);
+ ret = __irq_build_affinity_masks(curvec, numvecs, firstvec,
+ node_to_cpumask, npresmsk, nmsk,
+ masks);
+ if (ret >= 0)
+ nr_others = ret;
+
+ fail_build_affinity:
put_online_cpus();
- if (nr_present < numvecs)
+ if (ret >= 0)
WARN_ON(nr_present + nr_others < numvecs);
free_node_to_cpumask(node_to_cpumask);
@@ -225,7 +396,7 @@ static int irq_build_affinity_masks(unsigned int startvec, unsigned int numvecs,
fail_nmsk:
free_cpumask_var(nmsk);
- return ret;
+ return ret < 0 ? ret : 0;
}
static void default_calc_sets(struct irq_affinity *affd, unsigned int affvecs)
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index b76703b2c0af..b3fa2d87d2f3 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -1298,6 +1298,50 @@ EXPORT_SYMBOL_GPL(handle_fasteoi_mask_irq);
#endif /* CONFIG_IRQ_FASTEOI_HIERARCHY_HANDLERS */
/**
+ * irq_chip_set_parent_state - set the state of a parent interrupt.
+ *
+ * @data: Pointer to interrupt specific data
+ * @which: State to be restored (one of IRQCHIP_STATE_*)
+ * @val: Value corresponding to @which
+ *
+ * Conditional success, if the underlying irqchip does not implement it.
+ */
+int irq_chip_set_parent_state(struct irq_data *data,
+ enum irqchip_irq_state which,
+ bool val)
+{
+ data = data->parent_data;
+
+ if (!data || !data->chip->irq_set_irqchip_state)
+ return 0;
+
+ return data->chip->irq_set_irqchip_state(data, which, val);
+}
+EXPORT_SYMBOL_GPL(irq_chip_set_parent_state);
+
+/**
+ * irq_chip_get_parent_state - get the state of a parent interrupt.
+ *
+ * @data: Pointer to interrupt specific data
+ * @which: one of IRQCHIP_STATE_* the caller wants to know
+ * @state: a pointer to a boolean where the state is to be stored
+ *
+ * Conditional success, if the underlying irqchip does not implement it.
+ */
+int irq_chip_get_parent_state(struct irq_data *data,
+ enum irqchip_irq_state which,
+ bool *state)
+{
+ data = data->parent_data;
+
+ if (!data || !data->chip->irq_get_irqchip_state)
+ return 0;
+
+ return data->chip->irq_get_irqchip_state(data, which, state);
+}
+EXPORT_SYMBOL_GPL(irq_chip_get_parent_state);
+
+/**
* irq_chip_enable_parent - Enable the parent interrupt (defaults to unmask if
* NULL)
* @data: Pointer to interrupt specific data
diff --git a/kernel/irq/cpuhotplug.c b/kernel/irq/cpuhotplug.c
index 6c7ca2e983a5..02236b13b359 100644
--- a/kernel/irq/cpuhotplug.c
+++ b/kernel/irq/cpuhotplug.c
@@ -12,6 +12,7 @@
#include <linux/interrupt.h>
#include <linux/ratelimit.h>
#include <linux/irq.h>
+#include <linux/sched/isolation.h>
#include "internals.h"
@@ -171,6 +172,20 @@ void irq_migrate_all_off_this_cpu(void)
}
}
+static bool hk_should_isolate(struct irq_data *data, unsigned int cpu)
+{
+ const struct cpumask *hk_mask;
+
+ if (!housekeeping_enabled(HK_FLAG_MANAGED_IRQ))
+ return false;
+
+ hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ);
+ if (cpumask_subset(irq_data_get_effective_affinity_mask(data), hk_mask))
+ return false;
+
+ return cpumask_test_cpu(cpu, hk_mask);
+}
+
static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu)
{
struct irq_data *data = irq_desc_get_irq_data(desc);
@@ -188,9 +203,11 @@ static void irq_restore_affinity_of_irq(struct irq_desc *desc, unsigned int cpu)
/*
* If the interrupt can only be directed to a single target
* CPU then it is already assigned to a CPU in the affinity
- * mask. No point in trying to move it around.
+ * mask. No point in trying to move it around unless the
+ * isolation mechanism requests to move it to an upcoming
+ * housekeeping CPU.
*/
- if (!irqd_is_single_target(data))
+ if (!irqd_is_single_target(data) || hk_should_isolate(data, cpu))
irq_set_affinity_locked(data, affinity, false);
}
diff --git a/kernel/irq/debugfs.c b/kernel/irq/debugfs.c
index c1eccd4f6520..a949bd39e343 100644
--- a/kernel/irq/debugfs.c
+++ b/kernel/irq/debugfs.c
@@ -114,6 +114,7 @@ static const struct irq_bit_descr irqdata_states[] = {
BIT_MASK_DESCR(IRQD_AFFINITY_MANAGED),
BIT_MASK_DESCR(IRQD_MANAGED_SHUTDOWN),
BIT_MASK_DESCR(IRQD_CAN_RESERVE),
+ BIT_MASK_DESCR(IRQD_MSI_NOMASK_QUIRK),
BIT_MASK_DESCR(IRQD_FORWARDED_TO_VCPU),
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 9484e88dabc2..98a5f10d1900 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -295,6 +295,18 @@ static void irq_sysfs_add(int irq, struct irq_desc *desc)
}
}
+static void irq_sysfs_del(struct irq_desc *desc)
+{
+ /*
+ * If irq_sysfs_init() has not yet been invoked (early boot), then
+ * irq_kobj_base is NULL and the descriptor was never added.
+ * kobject_del() complains about a object with no parent, so make
+ * it conditional.
+ */
+ if (irq_kobj_base)
+ kobject_del(&desc->kobj);
+}
+
static int __init irq_sysfs_init(void)
{
struct irq_desc *desc;
@@ -325,6 +337,7 @@ static struct kobj_type irq_kobj_type = {
};
static void irq_sysfs_add(int irq, struct irq_desc *desc) {}
+static void irq_sysfs_del(struct irq_desc *desc) {}
#endif /* CONFIG_SYSFS */
@@ -438,7 +451,7 @@ static void free_desc(unsigned int irq)
* The sysfs entry must be serialized against a concurrent
* irq_sysfs_init() as well.
*/
- kobject_del(&desc->kobj);
+ irq_sysfs_del(desc);
delete_irq_desc(irq);
/*
@@ -737,7 +750,7 @@ void irq_free_descs(unsigned int from, unsigned int cnt)
EXPORT_SYMBOL_GPL(irq_free_descs);
/**
- * irq_alloc_descs - allocate and initialize a range of irq descriptors
+ * __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.
@@ -878,6 +891,7 @@ __irq_get_desc_lock(unsigned int irq, unsigned long *flags, bool bus,
}
void __irq_put_desc_unlock(struct irq_desc *desc, unsigned long flags, bool bus)
+ __releases(&desc->lock)
{
raw_spin_unlock_irqrestore(&desc->lock, flags);
if (bus)
diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
index 3078d0e48bba..7527e5ef6fe5 100644
--- a/kernel/irq/irqdomain.c
+++ b/kernel/irq/irqdomain.c
@@ -31,7 +31,7 @@ struct irqchip_fwid {
struct fwnode_handle fwnode;
unsigned int type;
char *name;
- void *data;
+ phys_addr_t *pa;
};
#ifdef CONFIG_GENERIC_IRQ_DEBUGFS
@@ -51,7 +51,7 @@ EXPORT_SYMBOL_GPL(irqchip_fwnode_ops);
* @type: Type of irqchip_fwnode. See linux/irqdomain.h
* @name: Optional user provided domain name
* @id: Optional user provided id if name != NULL
- * @data: Optional user-provided data
+ * @pa: Optional user-provided physical address
*
* Allocate a struct irqchip_fwid, and return a poiner to the embedded
* fwnode_handle (or NULL on failure).
@@ -62,7 +62,8 @@ EXPORT_SYMBOL_GPL(irqchip_fwnode_ops);
* domain struct.
*/
struct fwnode_handle *__irq_domain_alloc_fwnode(unsigned int type, int id,
- const char *name, void *data)
+ const char *name,
+ phys_addr_t *pa)
{
struct irqchip_fwid *fwid;
char *n;
@@ -77,7 +78,7 @@ struct fwnode_handle *__irq_domain_alloc_fwnode(unsigned int type, int id,
n = kasprintf(GFP_KERNEL, "%s-%d", name, id);
break;
default:
- n = kasprintf(GFP_KERNEL, "irqchip@%p", data);
+ n = kasprintf(GFP_KERNEL, "irqchip@%pa", pa);
break;
}
@@ -89,7 +90,7 @@ struct fwnode_handle *__irq_domain_alloc_fwnode(unsigned int type, int id,
fwid->type = type;
fwid->name = n;
- fwid->data = data;
+ fwid->pa = pa;
fwid->fwnode.ops = &irqchip_fwnode_ops;
return &fwid->fwnode;
}
@@ -148,6 +149,7 @@ struct irq_domain *__irq_domain_add(struct fwnode_handle *fwnode, int size,
switch (fwid->type) {
case IRQCHIP_FWNODE_NAMED:
case IRQCHIP_FWNODE_NAMED_ID:
+ domain->fwnode = fwnode;
domain->name = kstrdup(fwid->name, GFP_KERNEL);
if (!domain->name) {
kfree(domain);
@@ -985,6 +987,23 @@ const struct irq_domain_ops irq_domain_simple_ops = {
EXPORT_SYMBOL_GPL(irq_domain_simple_ops);
/**
+ * irq_domain_translate_onecell() - Generic translate for direct one cell
+ * bindings
+ */
+int irq_domain_translate_onecell(struct irq_domain *d,
+ struct irq_fwspec *fwspec,
+ unsigned long *out_hwirq,
+ unsigned int *out_type)
+{
+ if (WARN_ON(fwspec->param_count < 1))
+ return -EINVAL;
+ *out_hwirq = fwspec->param[0];
+ *out_type = IRQ_TYPE_NONE;
+ return 0;
+}
+EXPORT_SYMBOL_GPL(irq_domain_translate_onecell);
+
+/**
* irq_domain_translate_twocell() - Generic translate for direct two cell
* bindings
*
@@ -1457,6 +1476,7 @@ int irq_domain_push_irq(struct irq_domain *domain, int virq, void *arg)
if (rv) {
/* Restore the original irq_data. */
*root_irq_data = *child_irq_data;
+ kfree(child_irq_data);
goto error;
}
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index e8f7f179bf77..3089a60ea8f9 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -18,12 +18,13 @@
#include <linux/sched.h>
#include <linux/sched/rt.h>
#include <linux/sched/task.h>
+#include <linux/sched/isolation.h>
#include <uapi/linux/sched/types.h>
#include <linux/task_work.h>
#include "internals.h"
-#ifdef CONFIG_IRQ_FORCED_THREADING
+#if defined(CONFIG_IRQ_FORCED_THREADING) && !defined(CONFIG_PREEMPT_RT)
__read_mostly bool force_irqthreads;
EXPORT_SYMBOL_GPL(force_irqthreads);
@@ -217,7 +218,45 @@ int irq_do_set_affinity(struct irq_data *data, const struct cpumask *mask,
if (!chip || !chip->irq_set_affinity)
return -EINVAL;
- ret = chip->irq_set_affinity(data, mask, force);
+ /*
+ * If this is a managed interrupt and housekeeping is enabled on
+ * it check whether the requested affinity mask intersects with
+ * a housekeeping CPU. If so, then remove the isolated CPUs from
+ * the mask and just keep the housekeeping CPU(s). This prevents
+ * the affinity setter from routing the interrupt to an isolated
+ * CPU to avoid that I/O submitted from a housekeeping CPU causes
+ * interrupts on an isolated one.
+ *
+ * If the masks do not intersect or include online CPU(s) then
+ * keep the requested mask. The isolated target CPUs are only
+ * receiving interrupts when the I/O operation was submitted
+ * directly from them.
+ *
+ * If all housekeeping CPUs in the affinity mask are offline, the
+ * interrupt will be migrated by the CPU hotplug code once a
+ * housekeeping CPU which belongs to the affinity mask comes
+ * online.
+ */
+ if (irqd_affinity_is_managed(data) &&
+ housekeeping_enabled(HK_FLAG_MANAGED_IRQ)) {
+ const struct cpumask *hk_mask, *prog_mask;
+
+ static DEFINE_RAW_SPINLOCK(tmp_mask_lock);
+ static struct cpumask tmp_mask;
+
+ hk_mask = housekeeping_cpumask(HK_FLAG_MANAGED_IRQ);
+
+ raw_spin_lock(&tmp_mask_lock);
+ cpumask_and(&tmp_mask, mask, hk_mask);
+ if (!cpumask_intersects(&tmp_mask, cpu_online_mask))
+ prog_mask = mask;
+ else
+ prog_mask = &tmp_mask;
+ ret = chip->irq_set_affinity(data, prog_mask, force);
+ raw_spin_unlock(&tmp_mask_lock);
+ } else {
+ ret = chip->irq_set_affinity(data, mask, force);
+ }
switch (ret) {
case IRQ_SET_MASK_OK:
case IRQ_SET_MASK_OK_DONE:
@@ -692,6 +731,13 @@ static int set_irq_wake_real(unsigned int irq, unsigned int on)
*
* Wakeup mode lets this IRQ wake the system from sleep
* states like "suspend to RAM".
+ *
+ * Note: irq enable/disable state is completely orthogonal
+ * to the enable/disable state of irq wake. An irq can be
+ * disabled with disable_irq() and still wake the system as
+ * long as the irq has wake enabled. If this does not hold,
+ * then the underlying irq chip and the related driver need
+ * to be investigated.
*/
int irq_set_irq_wake(unsigned int irq, unsigned int on)
{
@@ -1255,8 +1301,7 @@ setup_irq_thread(struct irqaction *new, unsigned int irq, bool secondary)
* the thread dies to avoid that the interrupt code
* references an already freed task_struct.
*/
- get_task_struct(t);
- new->thread = t;
+ new->thread = get_task_struct(t);
/*
* Tell the thread to set its affinity. This is
* important for shared interrupt handlers as we do
@@ -1501,8 +1546,8 @@ __setup_irq(unsigned int irq, struct irq_desc *desc, struct irqaction *new)
* has. The type flags are unreliable as the
* underlying chip implementation can override them.
*/
- pr_err("Threaded irq requested with handler=NULL and !ONESHOT for irq %d\n",
- irq);
+ pr_err("Threaded irq requested with handler=NULL and !ONESHOT for %s (irq %d)\n",
+ new->name, irq);
ret = -EINVAL;
goto out_unlock;
}
diff --git a/kernel/irq/msi.c b/kernel/irq/msi.c
index ad26fbcfbfc8..eb95f6106a1e 100644
--- a/kernel/irq/msi.c
+++ b/kernel/irq/msi.c
@@ -453,8 +453,11 @@ int msi_domain_alloc_irqs(struct irq_domain *domain, struct device *dev,
continue;
irq_data = irq_domain_get_irq_data(domain, desc->irq);
- if (!can_reserve)
+ if (!can_reserve) {
irqd_clr_can_reserve(irq_data);
+ if (domain->flags & IRQ_DOMAIN_MSI_NOMASK_QUIRK)
+ irqd_set_msi_nomask_quirk(irq_data);
+ }
ret = irq_domain_activate_irq(irq_data, can_reserve);
if (ret)
goto cleanup;
diff --git a/kernel/irq/pm.c b/kernel/irq/pm.c
index d6961d3c6f9e..8f557fa1f4fe 100644
--- a/kernel/irq/pm.c
+++ b/kernel/irq/pm.c
@@ -177,6 +177,26 @@ static void resume_irqs(bool want_early)
}
/**
+ * rearm_wake_irq - rearm a wakeup interrupt line after signaling wakeup
+ * @irq: Interrupt to rearm
+ */
+void rearm_wake_irq(unsigned int irq)
+{
+ unsigned long flags;
+ struct irq_desc *desc = irq_get_desc_buslock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
+
+ if (!desc || !(desc->istate & IRQS_SUSPENDED) ||
+ !irqd_is_wakeup_set(&desc->irq_data))
+ return;
+
+ desc->istate &= ~IRQS_SUSPENDED;
+ irqd_set(&desc->irq_data, IRQD_WAKEUP_ARMED);
+ __enable_irq(desc);
+
+ irq_put_desc_busunlock(desc, flags);
+}
+
+/**
* irq_pm_syscore_ops - enable interrupt lines early
*
* Enable all interrupt lines with %IRQF_EARLY_RESUME set.
diff --git a/kernel/irq/proc.c b/kernel/irq/proc.c
index da9addb8d655..9e5783d98033 100644
--- a/kernel/irq/proc.c
+++ b/kernel/irq/proc.c
@@ -100,10 +100,6 @@ static int irq_affinity_hint_proc_show(struct seq_file *m, void *v)
return 0;
}
-#ifndef is_affinity_mask_valid
-#define is_affinity_mask_valid(val) 1
-#endif
-
int no_irq_affinity;
static int irq_affinity_proc_show(struct seq_file *m, void *v)
{
@@ -136,11 +132,6 @@ static ssize_t write_irq_affinity(int type, struct file *file,
if (err)
goto free_cpumask;
- if (!is_affinity_mask_valid(new_value)) {
- err = -EINVAL;
- goto free_cpumask;
- }
-
/*
* Do not allow disabling IRQs completely - it's a too easy
* way to make the system unusable accidentally :-) At least
@@ -185,20 +176,20 @@ static int irq_affinity_list_proc_open(struct inode *inode, struct file *file)
return single_open(file, irq_affinity_list_proc_show, PDE_DATA(inode));
}
-static const struct file_operations irq_affinity_proc_fops = {
- .open = irq_affinity_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
- .write = irq_affinity_proc_write,
+static const struct proc_ops irq_affinity_proc_ops = {
+ .proc_open = irq_affinity_proc_open,
+ .proc_read = seq_read,
+ .proc_lseek = seq_lseek,
+ .proc_release = single_release,
+ .proc_write = irq_affinity_proc_write,
};
-static const struct file_operations irq_affinity_list_proc_fops = {
- .open = irq_affinity_list_proc_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
- .write = irq_affinity_list_proc_write,
+static const struct proc_ops irq_affinity_list_proc_ops = {
+ .proc_open = irq_affinity_list_proc_open,
+ .proc_read = seq_read,
+ .proc_lseek = seq_lseek,
+ .proc_release = single_release,
+ .proc_write = irq_affinity_list_proc_write,
};
#ifdef CONFIG_GENERIC_IRQ_EFFECTIVE_AFF_MASK
@@ -232,11 +223,6 @@ static ssize_t default_affinity_write(struct file *file,
if (err)
goto out;
- if (!is_affinity_mask_valid(new_value)) {
- err = -EINVAL;
- goto out;
- }
-
/*
* Do not allow disabling IRQs completely - it's a too easy
* way to make the system unusable accidentally :-) At least
@@ -260,12 +246,12 @@ static int default_affinity_open(struct inode *inode, struct file *file)
return single_open(file, default_affinity_show, PDE_DATA(inode));
}
-static const struct file_operations default_affinity_proc_fops = {
- .open = default_affinity_open,
- .read = seq_read,
- .llseek = seq_lseek,
- .release = single_release,
- .write = default_affinity_write,
+static const struct proc_ops default_affinity_proc_ops = {
+ .proc_open = default_affinity_open,
+ .proc_read = seq_read,
+ .proc_lseek = seq_lseek,
+ .proc_release = single_release,
+ .proc_write = default_affinity_write,
};
static int irq_node_proc_show(struct seq_file *m, void *v)
@@ -356,7 +342,7 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
#ifdef CONFIG_SMP
/* create /proc/irq/<irq>/smp_affinity */
proc_create_data("smp_affinity", 0644, desc->dir,
- &irq_affinity_proc_fops, irqp);
+ &irq_affinity_proc_ops, irqp);
/* create /proc/irq/<irq>/affinity_hint */
proc_create_single_data("affinity_hint", 0444, desc->dir,
@@ -364,7 +350,7 @@ void register_irq_proc(unsigned int irq, struct irq_desc *desc)
/* create /proc/irq/<irq>/smp_affinity_list */
proc_create_data("smp_affinity_list", 0644, desc->dir,
- &irq_affinity_list_proc_fops, irqp);
+ &irq_affinity_list_proc_ops, irqp);
proc_create_single_data("node", 0444, desc->dir, irq_node_proc_show,
irqp);
@@ -415,7 +401,7 @@ static void register_default_affinity_proc(void)
{
#ifdef CONFIG_SMP
proc_create("irq/default_smp_affinity", 0644, NULL,
- &default_affinity_proc_fops);
+ &default_affinity_proc_ops);
#endif
}
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index 95414ad3506a..98c04ca5fa43 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -36,6 +36,8 @@ static void resend_irqs(unsigned long arg)
irq = find_first_bit(irqs_resend, nr_irqs);
clear_bit(irq, irqs_resend);
desc = irq_to_desc(irq);
+ if (!desc)
+ continue;
local_irq_disable();
desc->handle_irq(desc);
local_irq_enable();
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index 2ed97a7c9b2a..f865e5f4d382 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -34,6 +34,7 @@ static atomic_t irq_poll_active;
* true and let the handler run.
*/
bool irq_wait_for_poll(struct irq_desc *desc)
+ __must_hold(&desc->lock)
{
if (WARN_ONCE(irq_poll_cpu == smp_processor_id(),
"irq poll in progress on cpu %d for irq %d\n",
OpenPOWER on IntegriCloud