linux-kernel - [PATCH 4/5] nvme-pci: simplify nvme_setup_irqs() via .setup

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]

Date:   Fri, 25 Jan 2019 17:53:46 +0800
From:   Ming Lei <ming.lei@...hat.com>
To:     Christoph Hellwig <hch@....de>, Bjorn Helgaas <helgaas@...nel.org>,
        Thomas Gleixner <tglx@...utronix.de>
Cc:     Jens Axboe <axboe@...nel.dk>, linux-block@...r.kernel.org,
        Sagi Grimberg <sagi@...mberg.me>,
        linux-nvme@...ts.infradead.org, linux-kernel@...r.kernel.org,
        linux-pci@...r.kernel.org, Ming Lei <ming.lei@...hat.com>
Subject: [PATCH 4/5] nvme-pci: simplify nvme_setup_irqs() via .setup_affinity callback

Use the callback of .setup_affinity() to re-caculate number
of queues, and build irqs affinity with help of irq_build_affinity().

Then nvme_setup_irqs() gets simplified a lot.

Signed-off-by: Ming Lei <ming.lei@...hat.com>
---
 drivers/nvme/host/pci.c | 97 ++++++++++++++++++++++++-------------------------
 1 file changed, 48 insertions(+), 49 deletions(-)

diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
index 9bc585415d9b..24496de0a29b 100644
--- a/drivers/nvme/host/pci.c
+++ b/drivers/nvme/host/pci.c
@@ -2078,17 +2078,58 @@ static void nvme_calc_io_queues(struct nvme_dev *dev, unsigned int irq_queues)
 	}
 }
 
+static int nvme_setup_affinity(const struct irq_affinity *affd,
+			       struct irq_affinity_desc *masks,
+			       unsigned int nmasks)
+{
+	struct nvme_dev *dev = affd->priv;
+	int affvecs = nmasks - affd->pre_vectors - affd->post_vectors;
+	int curvec, usedvecs;
+	int i;
+
+	nvme_calc_io_queues(dev, nmasks);
+
+	/* Fill out vectors at the beginning that don't need affinity */
+	for (curvec = 0; curvec < affd->pre_vectors; curvec++)
+		cpumask_copy(&masks[curvec].mask, cpu_possible_mask);
+
+	for (i = 0, usedvecs = 0; i < HCTX_TYPE_POLL; i++) {
+		int this_vecs = dev->io_queues[i];
+		int ret;
+
+		if (!this_vecs)
+			break;
+
+		ret = irq_build_affinity(affd, curvec, this_vecs, curvec,
+					 masks, nmasks);
+		if (ret)
+			return ret;
+
+		curvec += this_vecs;
+		usedvecs += this_vecs;
+	}
+
+	/* Fill out vectors at the end that don't need affinity */
+	curvec = affd->pre_vectors + min(usedvecs, affvecs);
+	for (; curvec < nmasks; curvec++)
+		cpumask_copy(&masks[curvec].mask, cpu_possible_mask);
+
+	/* Mark the managed interrupts */
+	for (i = affd->pre_vectors; i < nmasks - affd->post_vectors; i++)
+		masks[i].is_managed = 1;
+
+	return 0;
+}
+
 static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
 {
 	struct pci_dev *pdev = to_pci_dev(dev->dev);
-	int irq_sets[2];
 	struct irq_affinity affd = {
 		.pre_vectors = 1,
-		.nr_sets = ARRAY_SIZE(irq_sets),
-		.sets = irq_sets,
+		.setup_affinity = nvme_setup_affinity,
+		.priv = dev,
 	};
-	int result = 0;
-	unsigned int irq_queues, this_p_queues;
+	int result, irq_queues, this_p_queues;
 
 	/*
 	 * Poll queues don't need interrupts, but we need at least one IO
@@ -2103,50 +2144,8 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
 	}
 	dev->io_queues[HCTX_TYPE_POLL] = this_p_queues;
 
-	/*
-	 * For irq sets, we have to ask for minvec == maxvec. This passes
-	 * any reduction back to us, so we can adjust our queue counts and
-	 * IRQ vector needs.
-	 */
-	do {
-		nvme_calc_io_queues(dev, irq_queues);
-		irq_sets[0] = dev->io_queues[HCTX_TYPE_DEFAULT];
-		irq_sets[1] = dev->io_queues[HCTX_TYPE_READ];
-		if (!irq_sets[1])
-			affd.nr_sets = 1;
-
-		/*
-		 * If we got a failure and we're down to asking for just
-		 * 1 + 1 queues, just ask for a single vector. We'll share
-		 * that between the single IO queue and the admin queue.
-		 * Otherwise, we assign one independent vector to admin queue.
-		 */
-		if (irq_queues > 1)
-			irq_queues = irq_sets[0] + irq_sets[1] + 1;
-
-		result = pci_alloc_irq_vectors_affinity(pdev, irq_queues,
-				irq_queues,
-				PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd);
-
-		/*
-		 * Need to reduce our vec counts. If we get ENOSPC, the
-		 * platform should support mulitple vecs, we just need
-		 * to decrease our ask. If we get EINVAL, the platform
-		 * likely does not. Back down to ask for just one vector.
-		 */
-		if (result == -ENOSPC) {
-			irq_queues--;
-			if (!irq_queues)
-				return result;
-			continue;
-		} else if (result == -EINVAL) {
-			irq_queues = 1;
-			continue;
-		} else if (result <= 0)
-			return -EIO;
-		break;
-	} while (1);
-
+	result = pci_alloc_irq_vectors_affinity(pdev, 1, irq_queues,
+			PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd);
 	return result;
 }
 
-- 
2.9.5