Skip to contentSkip to conversation

nvme-pci: Set tagset nr_maps just once

PATCH Superseded Keith Busch 3 participants 8 messages Jan 3, 2019 – Jan 4, 2019

Subsystems (2)

v1 of 2 Superseded Latest is v2 →

lore
Share & tools
lore
#0 lore raw

PATCH 1/4 nvme-pci: Set tagset nr_maps just once

The driver overwrites the intermediate nr_map assignments to HCTX_MAX_TYPES, so remove those unnecessary temporary settings.

Signed-off-by Keith Busch <keith.busch at intel.com>
---
 drivers/nvme/host/pci.c | 3 ---
 1 file changed, 3 deletions(-)
drivers/nvme/host/pci.c +0 -3
index 5a0bf6a24d50..98332d0a80f0 100644
@@ -2291,9 +2291,6 @@ static int nvme_dev_add(struct nvme_dev *dev)
 	if (!dev->ctrl.tagset) {
 		dev->tagset.ops = &nvme_mq_ops;
 		dev->tagset.nr_hw_queues = dev->online_queues - 1;
-		dev->tagset.nr_maps = 2; /* default + read */
-		if (dev->io_queues[HCTX_TYPE_POLL])
-			dev->tagset.nr_maps++;
 		dev->tagset.nr_maps = HCTX_MAX_TYPES;
 		dev->tagset.timeout = NVME_IO_TIMEOUT;
 		dev->tagset.numa_node = dev_to_node(dev->dev);
Signature · 1 line
2.14.4
#1 lore raw

PATCH 2/4 nvme-pci: Distribute io queue types after creation

The dev->io_queues types were set based on the results of the nvme set feature "number of queues" and the IRQ allocation. This does not mean that we're going to actually successfully allocate and create those IO queues. A failure there will cause blk-mq to have NULL hctx's because the map's nr_hw_queues accounts for more queues than were actually created.

Adjust the io_queue types after we've created them when we've less than originally desired.

Fixes 3b6592f70ad7b ("nvme: utilize two queue maps, one for reads and one for writes")
Signed-off-by Keith Busch <keith.busch at intel.com>
---
 drivers/nvme/host/pci.c | 46 ++++++++++++++++++++++++++++++++++++++++------
 1 file changed, 40 insertions(+), 6 deletions(-)
drivers/nvme/host/pci.c +40 -6
index 98332d0a80f0..1481bb6d9c42 100644
@@ -1733,6 +1733,30 @@ static int nvme_pci_configure_admin_queue(struct nvme_dev *dev)
 	return result;
 }
 
+static void nvme_distribute_queues(struct nvme_dev *dev, unsigned int io_queues)
+{
+	unsigned int irq_queues, this_p_queues = dev->io_queues[HCTX_TYPE_POLL],
+		     this_w_queues = dev->io_queues[HCTX_TYPE_DEFAULT];
+
+	if (!io_queues) {
+		dev->io_queues[HCTX_TYPE_POLL] = 0;
+		dev->io_queues[HCTX_TYPE_DEFAULT] = 0;
+		dev->io_queues[HCTX_TYPE_READ] = 0;
+		return;
+	}
+
+	if (this_p_queues >= io_queues)
+		this_p_queues = io_queues - 1;
+	irq_queues = io_queues - this_p_queues;
+
+	if (this_w_queues > irq_queues)
+		this_w_queues = irq_queues;
+
+	dev->io_queues[HCTX_TYPE_POLL] = this_p_queues;
+	dev->io_queues[HCTX_TYPE_DEFAULT] = this_w_queues;
+	dev->io_queues[HCTX_TYPE_READ] = irq_queues - this_w_queues;
+}
+
 static int nvme_create_io_queues(struct nvme_dev *dev)
 {
 	unsigned i, max, rw_queues;
@@ -1761,6 +1785,13 @@ static int nvme_create_io_queues(struct nvme_dev *dev)
 			break;
 	}
 
+	/*
+	 * If we've created less than expected io queues, redistribute the
+	 * dev->io_queues[] types accordingly.
+	 */
+	if (dev->online_queues - 1 != dev->max_qid)
+		nvme_distribute_queues(dev, dev->online_queues - 1);
+
 	/*
 	 * Ignore failing Create SQ/CQ commands, we can continue with less
 	 * than the desired amount of queues, and even a controller without
@@ -2185,11 +2216,6 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 	result = max(result - 1, 1);
 	dev->max_qid = result + dev->io_queues[HCTX_TYPE_POLL];
 
-	dev_info(dev->ctrl.device, "%d/%d/%d default/read/poll queues\n",
-					dev->io_queues[HCTX_TYPE_DEFAULT],
-					dev->io_queues[HCTX_TYPE_READ],
-					dev->io_queues[HCTX_TYPE_POLL]);
-
 	/*
 	 * Should investigate if there's a performance win from allocating
 	 * more queues than interrupt vectors; it might allow the submission
@@ -2203,7 +2229,15 @@ static int nvme_setup_io_queues(struct nvme_dev *dev)
 		return result;
 	}
 	set_bit(NVMEQ_ENABLED, &adminq->flags);
-	return nvme_create_io_queues(dev);
+	result = nvme_create_io_queues(dev);
+
+	if (!result)
+		dev_info(dev->ctrl.device, "%d/%d/%d default/read/poll queues\n",
+					dev->io_queues[HCTX_TYPE_DEFAULT],
+					dev->io_queues[HCTX_TYPE_READ],
+					dev->io_queues[HCTX_TYPE_POLL]);
+	return result;
+
 }
 
 static void nvme_del_queue_end(struct request *req, blk_status_t error)
Signature · 1 line
2.14.4
#2 lore raw

PATCH 3/4 pci/irq: Handle vector reduce and retry

In reply to Keith Busch

Adding the nr_sets forced the driver to handle reducing the vector count on allocation failures because the set distributino counts are driver specific. The change to this API is very different to use than before, and introduced new error corner cases that weren't being handled. It is also less efficient since the driver doesn't actually know what a proper vector count it should use since it only sees the error code and can only reduce by one instead of going straight to a possible vector count like PCI is able to do.

Provide a driver specific callback for managed irq set creation so that PCI can take a min and max vectors as before to handle the reduce and retry logic.

Signed-off-by Keith Busch <keith.busch at intel.com>
---
 drivers/pci/msi.c         | 20 ++++++--------------
 include/linux/interrupt.h |  4 ++++
 2 files changed, 10 insertions(+), 14 deletions(-)
drivers/pci/msi.c +6 -14
index 7a1c8a09efa5..b93ac49be18d 100644
@@ -1035,13 +1035,6 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec,
 	if (maxvec < minvec)
 		return -ERANGE;
 
-	/*
-	 * If the caller is passing in sets, we can't support a range of
-	 * vectors. The caller needs to handle that.
-	 */
-	if (affd && affd->nr_sets && minvec != maxvec)
-		return -EINVAL;
-
 	if (WARN_ON_ONCE(dev->msi_enabled))
 		return -EINVAL;
 
@@ -1061,6 +1054,9 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec,
 				return -ENOSPC;
 		}
 
+		if (nvec != maxvec && affd && affd->recalc_sets)
+			affd->recalc_sets((struct irq_affinity *)affd, nvec);
+
 		rc = msi_capability_init(dev, nvec, affd);
 		if (rc == 0)
 			return nvec;
@@ -1093,13 +1089,6 @@ static int __pci_enable_msix_range(struct pci_dev *dev,
 	if (maxvec < minvec)
 		return -ERANGE;
 
-	/*
-	 * If the caller is passing in sets, we can't support a range of
-	 * supported vectors. The caller needs to handle that.
-	 */
-	if (affd && affd->nr_sets && minvec != maxvec)
-		return -EINVAL;
-
 	if (WARN_ON_ONCE(dev->msix_enabled))
 		return -EINVAL;
 
@@ -1110,6 +1099,9 @@ static int __pci_enable_msix_range(struct pci_dev *dev,
 				return -ENOSPC;
 		}
 
+		if (nvec != maxvec && affd && affd->recalc_sets)
+			affd->recalc_sets((struct irq_affinity *)affd, nvec);
+
 		rc = __pci_enable_msix(dev, entries, nvec, affd);
 		if (rc == 0)
 			return nvec;
include/linux/interrupt.h +4 -0
index c672f34235e7..326c9bd05f62 100644
@@ -249,12 +249,16 @@ struct irq_affinity_notify {
  *			the MSI(-X) vector space
  * @nr_sets:		Length of passed in *sets array
  * @sets:		Number of affinitized sets
+ * @recalc_sets:	Recalculate sets original requested allocation failed
+ * @priv:		Driver private data
  */
 struct irq_affinity {
 	int	pre_vectors;
 	int	post_vectors;
 	int	nr_sets;
 	int	*sets;
+	void	(*recalc_sets)(struct irq_affinity *, unsigned int);
+	void	*priv;
 };
 
 /**
Signature · 1 line
2.14.4
#3 lore raw

PATCH 3/4 pci/irq: Handle vector reduce and retry

Hi Keith,

Thanks a lot for jumping on this.

I know I'm a broken record. Please run "git log --oneline drivers/pci/msi.c" and make your subject match.

Quoted 9 lines · Keith Busch

Adding the nr_sets forced the driver to handle reducing the vector count on allocation failures because the set distributino counts are driver specific. The change to this API is very different to use than before, and introduced new error corner cases that weren't being handled. It is also less efficient since the driver doesn't actually know what a proper vector count it should use since it only sees the error code and can only reduce by one instead of going straight to a possible vector count like PCI is able to do.

Quoted 3 lines

Provide a driver specific callback for managed irq set creation so that PCI can take a min and max vectors as before to handle the reduce and retry logic.

s/distributino/distribution/
s/irq/IRQ/

Can you also add some explanation to Documentation/PCI/MSI-HOWTO.txt about the concept of "sets" and how to use nr_sets/sets/recalc_sets/priv?

Quoted 63 lines
Signed-off-by Keith Busch <keith.busch at intel.com>
---
 drivers/pci/msi.c         | 20 ++++++--------------
 include/linux/interrupt.h |  4 ++++
 2 files changed, 10 insertions(+), 14 deletions(-)
drivers/pci/msi.c +6 -14
index 7a1c8a09efa5..b93ac49be18d 100644
@@ -1035,13 +1035,6 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec,
 	if (maxvec < minvec)
 		return -ERANGE;
 
-	/*
-	 * If the caller is passing in sets, we can't support a range of
-	 * vectors. The caller needs to handle that.
-	 */
-	if (affd && affd->nr_sets && minvec != maxvec)
-		return -EINVAL;
-
 	if (WARN_ON_ONCE(dev->msi_enabled))
 		return -EINVAL;
 
@@ -1061,6 +1054,9 @@ static int __pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec,
 				return -ENOSPC;
 		}
 
+		if (nvec != maxvec && affd && affd->recalc_sets)
+			affd->recalc_sets((struct irq_affinity *)affd, nvec);
+
 		rc = msi_capability_init(dev, nvec, affd);
 		if (rc == 0)
 			return nvec;
@@ -1093,13 +1089,6 @@ static int __pci_enable_msix_range(struct pci_dev *dev,
 	if (maxvec < minvec)
 		return -ERANGE;
 
-	/*
-	 * If the caller is passing in sets, we can't support a range of
-	 * supported vectors. The caller needs to handle that.
-	 */
-	if (affd && affd->nr_sets && minvec != maxvec)
-		return -EINVAL;
-
 	if (WARN_ON_ONCE(dev->msix_enabled))
 		return -EINVAL;
 
@@ -1110,6 +1099,9 @@ static int __pci_enable_msix_range(struct pci_dev *dev,
 				return -ENOSPC;
 		}
 
+		if (nvec != maxvec && affd && affd->recalc_sets)
+			affd->recalc_sets((struct irq_affinity *)affd, nvec);
+
 		rc = __pci_enable_msix(dev, entries, nvec, affd);
 		if (rc == 0)
 			return nvec;
include/linux/interrupt.h +0 -0
index c672f34235e7..326c9bd05f62 100644

include/linux/interrupt.h struct irq_affinity_notify { · line 252

Quoted 4 lines
include/linux/interrupt.h +1 -0
@@ -249,12 +249,16 @@ struct irq_affinity_notify {
  *			the MSI(-X) vector space
  * @nr_sets:		Length of passed in *sets array
  * @sets:		Number of affinitized sets
+ * @recalc_sets:	Recalculate sets original requested allocation failed

This sentence is missing something and doesn't parse quite right. "if"? Is "original" superfluous?

Quoted 15 lines
include/linux/interrupt.h +3 -0
+ * @priv:		Driver private data
  */
 struct irq_affinity {
 	int	pre_vectors;
 	int	post_vectors;
 	int	nr_sets;
 	int	*sets;
+	void	(*recalc_sets)(struct irq_affinity *, unsigned int);
+	void	*priv;
 };
 
 /**
Signature · 1 line
2.14.4
#4 lore raw

PATCH 3/4 pci/irq: Handle vector reduce and retry

Quoted 6 lines · Bjorn Helgaas

Hi Keith,

Thanks a lot for jumping on this.

I know I'm a broken record. Please run "git log --oneline drivers/pci/msi.c" and make your subject match.

Sure thing, my mistake.

Quoted 4 lines · Keith Busch

Can you also add some explanation to Documentation/PCI/MSI-HOWTO.txt about the concept of "sets" and how to use nr_sets/sets/recalc_sets/priv?

Yes, will do. Do you prefer documentation in a separate patch or the same one?

Quoted 4 lines
Quoted 4 lines
include/linux/interrupt.h +0 -0
index c672f34235e7..326c9bd05f62 100644
Quoted 8 lines

include/linux/interrupt.h struct irq_affinity_notify { · line 252

Quoted 5 lines
include/linux/interrupt.h +1 -0
@@ -249,12 +249,16 @@ struct irq_affinity_notify {
  *			the MSI(-X) vector space
  * @nr_sets:		Length of passed in *sets array
  * @sets:		Number of affinitized sets
+ * @recalc_sets:	Recalculate sets original requested allocation failed

This sentence is missing something and doesn't parse quite right. "if"? Is "original" superfluous?

Yikes, that was a very poor merge of two different thought streams. I'll fix that up.

#5 lore raw

PATCH 4/4 nvme-pci: Use PCI to handle IRQ reduce and retry

In reply to Keith Busch

Restore the previous error handling for vector allocation to the PCI core.

Signed-off-by Keith Busch <keith.busch at intel.com>
---
 drivers/nvme/host/pci.c | 77 ++++++++++++++-----------------------------------
 1 file changed, 21 insertions(+), 56 deletions(-)
drivers/nvme/host/pci.c +21 -56
index 1481bb6d9c42..f3ef09a8e8f9 100644
@@ -2059,37 +2059,43 @@ static int nvme_setup_host_mem(struct nvme_dev *dev)
 	return ret;
 }
 
-static void nvme_calc_io_queues(struct nvme_dev *dev, unsigned int irq_queues)
+static void nvme_calc_io_queues(struct irq_affinity *affd, unsigned int nvecs)
 {
+	struct nvme_dev *dev = affd->priv;
 	unsigned int this_w_queues = write_queues;
 
 	/*
 	 * Setup read/write queue split
 	 */
-	if (irq_queues == 1) {
+	if (nvecs == 1) {
 		dev->io_queues[HCTX_TYPE_DEFAULT] = 1;
 		dev->io_queues[HCTX_TYPE_READ] = 0;
-		return;
+		goto set_sets;
 	}
 
 	/*
 	 * If 'write_queues' is set, ensure it leaves room for at least
 	 * one read queue
 	 */
-	if (this_w_queues >= irq_queues)
-		this_w_queues = irq_queues - 1;
+	if (this_w_queues >= nvecs - 1)
+		this_w_queues = nvecs - 1;
 
 	/*
 	 * If 'write_queues' is set to zero, reads and writes will share
 	 * a queue set.
 	 */
 	if (!this_w_queues) {
-		dev->io_queues[HCTX_TYPE_DEFAULT] = irq_queues;
+		dev->io_queues[HCTX_TYPE_DEFAULT] = nvecs - 1;
 		dev->io_queues[HCTX_TYPE_READ] = 0;
 	} else {
 		dev->io_queues[HCTX_TYPE_DEFAULT] = this_w_queues;
-		dev->io_queues[HCTX_TYPE_READ] = irq_queues - this_w_queues;
+		dev->io_queues[HCTX_TYPE_READ] = nvecs - this_w_queues - 1;
 	}
+set_sets:
+	affd->sets[0] = dev->io_queues[HCTX_TYPE_DEFAULT];
+	affd->sets[1] = dev->io_queues[HCTX_TYPE_READ];
+	if (!affd->sets[1])
+		affd->nr_sets = 1;
 }
 
 static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
@@ -2100,9 +2106,10 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
 		.pre_vectors = 1,
 		.nr_sets = ARRAY_SIZE(irq_sets),
 		.sets = irq_sets,
+		.recalc_sets = nvme_calc_io_queues,
+		.priv = dev,
 	};
-	int result = 0;
-	unsigned int irq_queues, this_p_queues;
+	unsigned int nvecs, this_p_queues;
 
 	/*
 	 * Poll queues don't need interrupts, but we need at least one IO
@@ -2111,56 +2118,14 @@ static int nvme_setup_irqs(struct nvme_dev *dev, unsigned int nr_io_queues)
 	this_p_queues = poll_queues;
 	if (this_p_queues >= nr_io_queues) {
 		this_p_queues = nr_io_queues - 1;
-		irq_queues = 1;
+		nvecs = 2;
 	} else {
-		irq_queues = nr_io_queues - this_p_queues;
+		nvecs = nr_io_queues - this_p_queues + 1;
 	}
 	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.
-		 */
-		if (result >= 0 && 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);
-
-	return result;
+	nvme_calc_io_queues(&affd, nvecs);
+	return pci_alloc_irq_vectors_affinity(pdev, affd.pre_vectors, nvecs,
+			PCI_IRQ_ALL_TYPES | PCI_IRQ_AFFINITY, &affd);
 }
 
 static int nvme_setup_io_queues(struct nvme_dev *dev)
Signature · 1 line
2.14.4
#6 lore raw

PATCH 1/4 nvme-pci: Set tagset nr_maps just once

In reply to Keith Busch
Quoted 4 lines · Keith Busch

The driver overwrites the intermediate nr_map assignments to HCTX_MAX_TYPES, so remove those unnecessary temporary settings.

Signed-off-by Keith Busch <keith.busch at intel.com>

Actually the more complex calculation is the right one here. I've just merged a patch from Jianchao to remove the other line.

#7 lore raw

PATCH 1/4 nvme-pci: Set tagset nr_maps just once

Quoted 8 lines · Christoph Hellwig
Quoted 4 lines · Keith Busch

The driver overwrites the intermediate nr_map assignments to HCTX_MAX_TYPES, so remove those unnecessary temporary settings.

Signed-off-by Keith Busch <keith.busch at intel.com>

Actually the more complex calculation is the right one here. I've just merged a patch from Jianchao to remove the other line.

Yep, I just saw that. Jianchao's is the right way to go here.