linux-kernel - [PATCH 2/2] nvme-pci: allow unmanaged interrupts

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: <20240510141459.3207725-2-kbusch@meta.com>
Date: Fri, 10 May 2024 07:14:59 -0700
From: Keith Busch <kbusch@...a.com>
To: <linux-nvme@...ts.infradead.org>, <linux-kernel@...r.kernel.org>
CC: <hch@....de>, <tglx@...utronix.de>, <ming.lei@...hat.com>,
        Keith Busch
	<kbusch@...nel.org>
Subject: [PATCH 2/2] nvme-pci: allow unmanaged interrupts

From: Keith Busch <kbusch@...nel.org>

Some people _really_ want to control their interrupt affinity.

Signed-off-by: Keith Busch <kbusch@...nel.org>
---
 drivers/nvme/host/pci.c | 13 ++++++++++++-
 1 file changed, 12 insertions(+), 1 deletion(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 8e0bb9692685d..4c2799c3f45f5 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -63,6 +63,11 @@ MODULE_PARM_DESC(sgl_threshold,
 		"Use SGLs when average request segment size is larger or equal to "
 		"this size. Use 0 to disable SGLs.");
 
+static bool managed_irqs = true;
+module_param(managed_irqs, bool, 0444);
+MODULE_PARM_DESC(managed_irqs,
+		 "set to false for user controlled irq affinity");
+
 #define NVME_PCI_MIN_QUEUE_SIZE 2
 #define NVME_PCI_MAX_QUEUE_SIZE 4095
 static int io_queue_depth_set(const char *val, const struct kernel_param *kp);
@@ -456,7 +461,7 @@ static void nvme_pci_map_queues(struct blk_mq_tag_set *set)
 		 * affinity), so use the regular blk-mq cpu mapping
 		 */
 		map->queue_offset = qoff;
-		if (i != HCTX_TYPE_POLL && offset)
+		if (managed_irqs && i != HCTX_TYPE_POLL && offset)
 			blk_mq_pci_map_queues(map, to_pci_dev(dev->dev), offset);
 		else
 			blk_mq_map_queues(map);
@@ -2180,6 +2185,9 @@ static void nvme_calc_irq_sets(struct irq_affinity *affd, unsigned int nrirqs)
 	struct nvme_dev *dev = affd->priv;
 	unsigned int nr_read_queues, nr_write_queues = dev->nr_write_queues;
 
+	if (!nrirqs)
+		nrirqs = affd->post_vectors;
+
 	/*
 	 * If there is no interrupt available for queues, ensure that
 	 * the default queue is set to 1. The affinity set size is
@@ -2226,6 +2234,9 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
 	poll_queues = min(dev->nr_poll_queues, nr_io_queues - 1);
 	dev->io_queues[HCTX_TYPE_POLL] = poll_queues;
 
+	if (!managed_irqs)
+		affd.post_vectors = nr_io_queues - poll_queues;
+
 	/*
 	 * Initialize for the single interrupt case, will be updated in
 	 * nvme_calc_irq_sets().
-- 
2.43.0