linux-kernel - [PATCH 5.13 140/151] powerpc/xive: Do not skip CPU-less nodes when creating the IPIs

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <20210816125448.681174462@linuxfoundation.org>
Date:   Mon, 16 Aug 2021 15:02:50 +0200
From:   Greg Kroah-Hartman <gregkh@...uxfoundation.org>
To:     linux-kernel@...r.kernel.org
Cc:     Greg Kroah-Hartman <gregkh@...uxfoundation.org>,
        stable@...r.kernel.org,
        Geetika Moolchandani <Geetika.Moolchandani1@....com>,
        Cédric Le Goater <clg@...d.org>,
        Srikar Dronamraju <srikar@...ux.vnet.ibm.com>,
        Laurent Vivier <lvivier@...hat.com>,
        Michael Ellerman <mpe@...erman.id.au>
Subject: [PATCH 5.13 140/151] powerpc/xive: Do not skip CPU-less nodes when creating the IPIs

From: Cédric Le Goater <clg@...d.org>

commit cbc06f051c524dcfe52ef0d1f30647828e226d30 upstream.

On PowerVM, CPU-less nodes can be populated with hot-plugged CPUs at
runtime. Today, the IPI is not created for such nodes, and hot-plugged
CPUs use a bogus IPI, which leads to soft lockups.

We can not directly allocate and request the IPI on demand because
bringup_up() is called under the IRQ sparse lock. The alternative is
to allocate the IPIs for all possible nodes at startup and to request
the mapping on demand when the first CPU of a node is brought up.

Fixes: 7dcc37b3eff9 ("powerpc/xive: Map one IPI interrupt per node")
Cc: stable@...r.kernel.org # v5.13
Reported-by: Geetika Moolchandani <Geetika.Moolchandani1@....com>
Signed-off-by: Cédric Le Goater <clg@...d.org>
Tested-by: Srikar Dronamraju <srikar@...ux.vnet.ibm.com>
Tested-by: Laurent Vivier <lvivier@...hat.com>
Signed-off-by: Michael Ellerman <mpe@...erman.id.au>
Link: https://lore.kernel.org/r/20210807072057.184698-1-clg@kaod.org
Signed-off-by: Greg Kroah-Hartman <gregkh@...uxfoundation.org>
---
 arch/powerpc/sysdev/xive/common.c |   35 ++++++++++++++++++++++++-----------
 1 file changed, 24 insertions(+), 11 deletions(-)

--- a/arch/powerpc/sysdev/xive/common.c
+++ b/arch/powerpc/sysdev/xive/common.c
@@ -67,6 +67,7 @@ static struct irq_domain *xive_irq_domai
 static struct xive_ipi_desc {
 	unsigned int irq;
 	char name[16];
+	atomic_t started;
 } *xive_ipis;
 
 /*
@@ -1120,7 +1121,7 @@ static const struct irq_domain_ops xive_
 	.alloc  = xive_ipi_irq_domain_alloc,
 };
 
-static int __init xive_request_ipi(void)
+static int __init xive_init_ipis(void)
 {
 	struct fwnode_handle *fwnode;
 	struct irq_domain *ipi_domain;
@@ -1144,10 +1145,6 @@ static int __init xive_request_ipi(void)
 		struct xive_ipi_desc *xid = &xive_ipis[node];
 		struct xive_ipi_alloc_info info = { 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,
@@ -1159,11 +1156,6 @@ static int __init xive_request_ipi(void)
 		xid->irq = ret;
 
 		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);
-
-		WARN(ret < 0, "Failed to request IPI %d: %d\n", xid->irq, ret);
 	}
 
 	return ret;
@@ -1178,6 +1170,22 @@ out:
 	return ret;
 }
 
+static int __init xive_request_ipi(unsigned int cpu)
+{
+	struct xive_ipi_desc *xid = &xive_ipis[early_cpu_to_node(cpu)];
+	int ret;
+
+	if (atomic_inc_return(&xid->started) > 1)
+		return 0;
+
+	ret = request_irq(xid->irq, xive_muxed_ipi_action,
+			  IRQF_PERCPU | IRQF_NO_THREAD,
+			  xid->name, NULL);
+
+	WARN(ret < 0, "Failed to request IPI %d: %d\n", xid->irq, ret);
+	return ret;
+}
+
 static int xive_setup_cpu_ipi(unsigned int cpu)
 {
 	unsigned int xive_ipi_irq = xive_ipi_cpu_to_irq(cpu);
@@ -1192,6 +1200,9 @@ static int xive_setup_cpu_ipi(unsigned i
 	if (xc->hw_ipi != XIVE_BAD_IRQ)
 		return 0;
 
+	/* Register the IPI */
+	xive_request_ipi(cpu);
+
 	/* Grab an IPI from the backend, this will populate xc->hw_ipi */
 	if (xive_ops->get_ipi(cpu, xc))
 		return -EIO;
@@ -1231,6 +1242,8 @@ static void xive_cleanup_cpu_ipi(unsigne
 	if (xc->hw_ipi == XIVE_BAD_IRQ)
 		return;
 
+	/* TODO: clear IPI mapping */
+
 	/* Mask the IPI */
 	xive_do_source_set_mask(&xc->ipi_data, true);
 
@@ -1253,7 +1266,7 @@ void __init xive_smp_probe(void)
 	smp_ops->cause_ipi = xive_cause_ipi;
 
 	/* Register the IPI */
-	xive_request_ipi();
+	xive_init_ipis();
 
 	/* Allocate and setup IPI for the boot CPU */
 	xive_setup_cpu_ipi(smp_processor_id());