ipistorm [*] can be used to benchmark the raw interrupt rate of an
interrupt controller by measuring the number of IPIs a system can
sustain. When applied to the XIVE interrupt controller of POWER9 and
POWER10 systems, a significant drop of the interrupt rate can be
observed when crossing the second node boundary.
This is due to the fact that a single IPI interrupt is used for all
CPUs of the system. The structure is shared and the cache line updates
impact greatly the traffic between nodes and the overall IPI
performance.
As a workaround, the impact can be reduced by deactivating the IRQ
lockup detector ("noirqdebug") which does a lot of accounting in the
Linux IRQ descriptor structure and is responsible for most of the
performance penalty.
As a fix, this proposal allocates an IPI interrupt per node, to be
shared by all CPUs of that node. It solves the scaling issue, the IRQ
lockup detector still has an impact but the XIVE interrupt rate scales
linearly. It also improves the "noirqdebug" case as showed in the
tables below.
* P9 DD2.2 - 2s * 64 threads
"noirqdebug"
Mint/s Mint/s
chips cpus IPI/sys IPI/chip IPI/chip IPI/sys
--------------------------------------------------------------
1 0-15 4.984023 4.875405 4.996536 5.048892
0-31 10.879164 10.544040 10.757632 11.037859
0-47 15.345301 14.688764 14.926520 15.310053
0-63 17.064907 17.066812 17.613416 17.874511
2 0-79 11.768764 21.650749 22.689120 22.566508
0-95 10.616812 26.878789 28.434703 28.320324
0-111 10.151693 31.397803 31.771773 32.388122
0-127 9.948502 33.139336 34.875716 35.224548
* P10 DD1 - 4s (not homogeneous) 352 threads
"noirqdebug"
Mint/s Mint/s
chips cpus IPI/sys IPI/chip IPI/chip IPI/sys
--------------------------------------------------------------
1 0-15 2.409402 2.364108 2.383303 2.395091
0-31 6.028325 6.046075 6.089999 6.073750
0-47 8.655178 8.644531 8.712830 8.724702
0-63 11.629652 11.735953 12.088203 12.055979
0-79 14.392321 14.729959 14.986701 14.973073
0-95 12.604158 13.004034 17.528748 17.568095
2 0-111 9.767753 13.719831 19.968606 20.024218
0-127 6.744566 16.418854 22.898066 22.995110
0-143 6.005699 19.174421 25.425622 25.417541
0-159 5.649719 21.938836 27.952662 28.059603
0-175 5.441410 24.109484 31.133915 31.127996
3 0-191 5.318341 24.405322 33.999221 33.775354
0-207 5.191382 26.449769 36.050161 35.867307
0-223 5.102790 29.356943 39.544135 39.508169
0-239 5.035295 31.933051 42.135075 42.071975
0-255 4.969209 34.477367 44.655395 44.757074
4 0-271 4.907652 35.887016 47.080545 47.318537
0-287 4.839581 38.076137 50.464307 50.636219
0-303 4.786031 40.881319 53.478684 53.310759
0-319 4.743750 43.448424 56.388102 55.973969
0-335 4.709936 45.623532 59.400930 58.926857
0-351 4.681413 45.646151 62.035804 61.830057
[*] https://github.com/antonblanchard/ipistorm
Signed-off-by: Cédric Le Goater <clg@kaod.org>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210331144514.892250-9-clg@kaod.org
static struct irq_domain *xive_irq_domain;
#ifdef CONFIG_SMP
-/* The IPIs all use the same logical irq number */
-static u32 xive_ipi_irq;
+/* The IPIs use the same logical irq number when on the same chip */
+static struct xive_ipi_desc {
+ unsigned int irq;
+ char name[16];
+} *xive_ipis;
+
+/*
+ * Use early_cpu_to_node() for hot-plugged CPUs
+ */
+static unsigned int xive_ipi_cpu_to_irq(unsigned int cpu)
+{
+ return xive_ipis[early_cpu_to_node(cpu)].irq;
+}
#endif
/* Xive state for each CPU */
{
struct fwnode_handle *fwnode;
struct irq_domain *ipi_domain;
- unsigned int virq;
+ unsigned int node;
int ret = -ENOMEM;
fwnode = irq_domain_alloc_named_fwnode("XIVE-IPI");
if (!fwnode)
goto out;
- ipi_domain = irq_domain_create_linear(fwnode, 1,
+ ipi_domain = irq_domain_create_linear(fwnode, nr_node_ids,
&xive_ipi_irq_domain_ops, NULL);
if (!ipi_domain)
goto out_free_fwnode;
- /* Initialize it */
- virq = irq_create_mapping(ipi_domain, XIVE_IPI_HW_IRQ);
- if (!virq) {
- ret = -EINVAL;
+ xive_ipis = kcalloc(nr_node_ids, sizeof(*xive_ipis), GFP_KERNEL | __GFP_NOFAIL);
+ if (!xive_ipis)
goto out_free_domain;
- }
- xive_ipi_irq = virq;
+ for_each_node(node) {
+ struct xive_ipi_desc *xid = &xive_ipis[node];
+ irq_hw_number_t ipi_hwirq = node;
+
+ /* Skip nodes without CPUs */
+ if (cpumask_empty(cpumask_of_node(node)))
+ continue;
+
+ /*
+ * Map one IPI interrupt per node for all cpus of that node.
+ * Since the HW interrupt number doesn't have any meaning,
+ * simply use the node number.
+ */
+ xid->irq = irq_create_mapping(ipi_domain, ipi_hwirq);
+ if (!xid->irq) {
+ ret = -EINVAL;
+ goto out_free_xive_ipis;
+ }
+
+ snprintf(xid->name, sizeof(xid->name), "IPI-%d", node);
+
+ ret = request_irq(xid->irq, xive_muxed_ipi_action,
+ IRQF_PERCPU | IRQF_NO_THREAD, xid->name, NULL);
- ret = request_irq(virq, xive_muxed_ipi_action,
- IRQF_PERCPU | IRQF_NO_THREAD, "IPI", NULL);
+ WARN(ret < 0, "Failed to request IPI %d: %d\n", xid->irq, ret);
+ }
- WARN(ret < 0, "Failed to request IPI %d: %d\n", virq, ret);
return ret;
+out_free_xive_ipis:
+ kfree(xive_ipis);
out_free_domain:
irq_domain_remove(ipi_domain);
out_free_fwnode:
static int xive_setup_cpu_ipi(unsigned int cpu)
{
+ unsigned int xive_ipi_irq = xive_ipi_cpu_to_irq(cpu);
struct xive_cpu *xc;
int rc;
static void xive_cleanup_cpu_ipi(unsigned int cpu, struct xive_cpu *xc)
{
+ unsigned int xive_ipi_irq = xive_ipi_cpu_to_irq(cpu);
+
/* Disable the IPI and free the IRQ data */
/* Already cleaned up ? */
#ifndef __XIVE_INTERNAL_H
#define __XIVE_INTERNAL_H
-#define XIVE_IPI_HW_IRQ 0 /* interrupt source # for IPIs */
-
/*
* A "disabled" interrupt should never fire, to catch problems
* we set its logical number to this