summaryrefslogtreecommitdiffstats
path: root/kernel/irq_work.c
diff options
context:
space:
mode:
authorPeter Zijlstra <peterz@infradead.org>2020-05-26 18:11:02 +0200
committerIngo Molnar <mingo@kernel.org>2020-05-28 10:54:15 +0200
commit4b44a21dd640b692d4e9b12d3e37c24825f90baa (patch)
tree5dea8495f643a9152ce6ada83d8f5f6466f1d898 /kernel/irq_work.c
parentb2a02fc43a1f40ef4eb2fb2b06357382608d4d84 (diff)
downloadlinux-4b44a21dd640b692d4e9b12d3e37c24825f90baa.tar.gz
linux-4b44a21dd640b692d4e9b12d3e37c24825f90baa.tar.bz2
linux-4b44a21dd640b692d4e9b12d3e37c24825f90baa.zip
irq_work, smp: Allow irq_work on call_single_queue
Currently irq_work_queue_on() will issue an unconditional arch_send_call_function_single_ipi() and has the handler do irq_work_run(). This is unfortunate in that it makes the IPI handler look at a second cacheline and it misses the opportunity to avoid the IPI. Instead note that struct irq_work and struct __call_single_data are very similar in layout, so use a few bits in the flags word to encode a type and stick the irq_work on the call_single_queue list. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Signed-off-by: Ingo Molnar <mingo@kernel.org> Link: https://lore.kernel.org/r/20200526161908.011635912@infradead.org
Diffstat (limited to 'kernel/irq_work.c')
-rw-r--r--kernel/irq_work.c53
1 files changed, 29 insertions, 24 deletions
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index 48b5d1b6af4d..eca83965b631 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -31,7 +31,7 @@ static bool irq_work_claim(struct irq_work *work)
{
int oflags;
- oflags = atomic_fetch_or(IRQ_WORK_CLAIMED, &work->flags);
+ oflags = atomic_fetch_or(IRQ_WORK_CLAIMED | CSD_TYPE_IRQ_WORK, &work->flags);
/*
* If the work is already pending, no need to raise the IPI.
* The pairing atomic_fetch_andnot() in irq_work_run() makes sure
@@ -102,8 +102,7 @@ bool irq_work_queue_on(struct irq_work *work, int cpu)
if (cpu != smp_processor_id()) {
/* Arch remote IPI send/receive backend aren't NMI safe */
WARN_ON_ONCE(in_nmi());
- if (llist_add(&work->llnode, &per_cpu(raised_list, cpu)))
- arch_send_call_function_single_ipi(cpu);
+ __smp_call_single_queue(cpu, &work->llnode);
} else {
__irq_work_queue_local(work);
}
@@ -131,6 +130,31 @@ bool irq_work_needs_cpu(void)
return true;
}
+void irq_work_single(void *arg)
+{
+ struct irq_work *work = arg;
+ int flags;
+
+ /*
+ * Clear the PENDING bit, after this point the @work
+ * can be re-used.
+ * Make it immediately visible so that other CPUs trying
+ * to claim that work don't rely on us to handle their data
+ * while we are in the middle of the func.
+ */
+ flags = atomic_fetch_andnot(IRQ_WORK_PENDING, &work->flags);
+
+ lockdep_irq_work_enter(work);
+ work->func(work);
+ lockdep_irq_work_exit(work);
+ /*
+ * Clear the BUSY bit and return to the free state if
+ * no-one else claimed it meanwhile.
+ */
+ flags &= ~IRQ_WORK_PENDING;
+ (void)atomic_cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY);
+}
+
static void irq_work_run_list(struct llist_head *list)
{
struct irq_work *work, *tmp;
@@ -142,27 +166,8 @@ static void irq_work_run_list(struct llist_head *list)
return;
llnode = llist_del_all(list);
- llist_for_each_entry_safe(work, tmp, llnode, llnode) {
- int flags;
- /*
- * Clear the PENDING bit, after this point the @work
- * can be re-used.
- * Make it immediately visible so that other CPUs trying
- * to claim that work don't rely on us to handle their data
- * while we are in the middle of the func.
- */
- flags = atomic_fetch_andnot(IRQ_WORK_PENDING, &work->flags);
-
- lockdep_irq_work_enter(work);
- work->func(work);
- lockdep_irq_work_exit(work);
- /*
- * Clear the BUSY bit and return to the free state if
- * no-one else claimed it meanwhile.
- */
- flags &= ~IRQ_WORK_PENDING;
- (void)atomic_cmpxchg(&work->flags, flags, flags & ~IRQ_WORK_BUSY);
- }
+ llist_for_each_entry_safe(work, tmp, llnode, llnode)
+ irq_work_single(work);
}
/*