Commit 18a04837 authored by Haiyang Zhang's avatar Haiyang Zhang Committed by Jakub Kicinski
Browse files

net: mana: Fix accessing freed irq affinity_hint 



After calling irq_set_affinity_and_hint(), the cpumask pointer is
saved in desc->affinity_hint, and will be used later when reading
/proc/irq/<num>/affinity_hint. So the cpumask variable needs to be
persistent. Otherwise, we are accessing freed memory when reading
the affinity_hint file.

Also, need to clear affinity_hint before free_irq(), otherwise there
is a one-time warning and stack trace during module unloading:

 [  243.948687] WARNING: CPU: 10 PID: 1589 at kernel/irq/manage.c:1913 free_irq+0x318/0x360
 ...
 [  243.948753] Call Trace:
 [  243.948754]  <TASK>
 [  243.948760]  mana_gd_remove_irqs+0x78/0xc0 [mana]
 [  243.948767]  mana_gd_remove+0x3e/0x80 [mana]
 [  243.948773]  pci_device_remove+0x3d/0xb0
 [  243.948778]  device_remove+0x46/0x70
 [  243.948782]  device_release_driver_internal+0x1fe/0x280
 [  243.948785]  driver_detach+0x4e/0xa0
 [  243.948787]  bus_remove_driver+0x70/0xf0
 [  243.948789]  driver_unregister+0x35/0x60
 [  243.948792]  pci_unregister_driver+0x44/0x90
 [  243.948794]  mana_driver_exit+0x14/0x3fe [mana]
 [  243.948800]  __do_sys_delete_module.constprop.0+0x185/0x2f0

To fix the bug, use the persistent mask, cpumask_of(cpu#), and set
affinity_hint to NULL before freeing the IRQ, as required by free_irq().

Cc: stable@vger.kernel.org
Fixes: 71fa6887 ("net: mana: Assign interrupts to CPUs based on NUMA nodes")
Signed-off-by: default avatarHaiyang Zhang <haiyangz@microsoft.com>
Reviewed-by: default avatarMichael Kelley <mikelley@microsoft.com>
Reviewed-by: default avatarLeon Romanovsky <leonro@nvidia.com>
Link: https://lore.kernel.org/r/1675718929-19565-1-git-send-email-haiyangz@microsoft.com


Signed-off-by: default avatarJakub Kicinski <kuba@kernel.org>
parent b1f4fbab

drivers/net/ethernet/microsoft/mana/gdma_main.c

+11 −26
Original line number Diff line number Diff line
@@ -1217,9 +1217,7 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) 
	unsigned int max_queues_per_port = num_online_cpus();

	struct gdma_context *gc = pci_get_drvdata(pdev);

	struct gdma_irq_context *gic;

	unsigned int max_irqs;

	u16 *cpus;

	cpumask_var_t req_mask;

	unsigned int max_irqs, cpu;

	int nvec, irq;

	int err, i = 0, j;
@@ -1240,21 +1238,7 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) 
		goto free_irq_vector;

	}



	if (!zalloc_cpumask_var(&req_mask, GFP_KERNEL)) {

		err = -ENOMEM;

		goto free_irq;

	}



	cpus = kcalloc(nvec, sizeof(*cpus), GFP_KERNEL);

	if (!cpus) {

		err = -ENOMEM;

		goto free_mask;

	}

	for (i = 0; i < nvec; i++)

		cpus[i] = cpumask_local_spread(i, gc->numa_node);



	for (i = 0; i < nvec; i++) {

		cpumask_set_cpu(cpus[i], req_mask);

		gic = &gc->irq_contexts[i];

		gic->handler = NULL;

		gic->arg = NULL;
@@ -1269,17 +1253,16 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) 
		irq = pci_irq_vector(pdev, i);

		if (irq < 0) {

			err = irq;

			goto free_mask;

			goto free_irq;

		}



		err = request_irq(irq, mana_gd_intr, 0, gic->name, gic);

		if (err)

			goto free_mask;

		irq_set_affinity_and_hint(irq, req_mask);

		cpumask_clear(req_mask);

			goto free_irq;



		cpu = cpumask_local_spread(i, gc->numa_node);

		irq_set_affinity_and_hint(irq, cpumask_of(cpu));

	}

	free_cpumask_var(req_mask);

	kfree(cpus);



	err = mana_gd_alloc_res_map(nvec, &gc->msix_resource);

	if (err)
@@ -1290,13 +1273,12 @@ static int mana_gd_setup_irqs(struct pci_dev *pdev) 


	return 0;



free_mask:

	free_cpumask_var(req_mask);

	kfree(cpus);

free_irq:

	for (j = i - 1; j >= 0; j--) {

		irq = pci_irq_vector(pdev, j);

		gic = &gc->irq_contexts[j];



		irq_update_affinity_hint(irq, NULL);

		free_irq(irq, gic);

	}
@@ -1324,6 +1306,9 @@ static void mana_gd_remove_irqs(struct pci_dev *pdev) 
			continue;



		gic = &gc->irq_contexts[i];



		/* Need to clear the hint before free_irq */

		irq_update_affinity_hint(irq, NULL);

		free_irq(irq, gic);

	}