linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Alexander Gordeev <agordeev@redhat.com>
To: linux-kernel@vger.kernel.org
Cc: Ingo Molnar <mingo@redhat.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Bjorn Helgaas <bhelgaas@google.com>,
	Suresh Siddha <suresh.b.siddha@intel.com>,
	Yinghai Lu <yinghai@kernel.org>, Jeff Garzik <jgarzik@pobox.com>,
	Matthew Wilcox <willy@linux.intel.com>,
	x86@kernel.org, linux-pci@vger.kernel.org,
	linux-ide@vger.kernel.org
Subject: [PATCH v2 -tip 1/5] x86, MSI: Support multiple MSIs in presense of IRQ remapping
Date: Mon, 3 Sep 2012 11:17:40 +0200	[thread overview]
Message-ID: <034a9cbb168501954408f1004a28c827f3a4158b.1346653435.git.agordeev@redhat.com> (raw)
In-Reply-To: <cover.1346653435.git.agordeev@redhat.com>

The MSI specification has several constraints in comparison with MSI-X,
most notable of them is the inability to configure MSIs independently.
As a result, it is impossible to dispatch interrupts from different
queues to different CPUs. This is largely devalues the support of
multiple MSIs in SMP systems.

Also, a necessity to allocate a contiguous block of vector numbers for
devices capable of multiple MSIs might cause a considerable pressure on
x86 interrupt vector allocator and could lead to fragmentation of the
interrupt vectors space.

This patch overcomes both drawbacks in presense of IRQ remapping and
lets devices take advantage of multiple queues and per-IRQ affinity
assignments.

Signed-off-by: Alexander Gordeev <agordeev@redhat.com>
---
 arch/x86/kernel/apic/io_apic.c |  166 +++++++++++++++++++++++++++++++++++++--
 include/linux/irq.h            |    6 ++
 kernel/irq/chip.c              |   30 +++++--
 kernel/irq/irqdesc.c           |   31 ++++++++
 4 files changed, 216 insertions(+), 17 deletions(-)

diff --git a/arch/x86/kernel/apic/io_apic.c b/arch/x86/kernel/apic/io_apic.c
index c265593..5fd2577 100644
--- a/arch/x86/kernel/apic/io_apic.c
+++ b/arch/x86/kernel/apic/io_apic.c
@@ -305,6 +305,11 @@ static int alloc_irq_from(unsigned int from, int node)
 	return irq_alloc_desc_from(from, node);
 }
 
+static int alloc_irqs_from(unsigned int from, unsigned int count, int node)
+{
+	return irq_alloc_descs_from(from, count, node);
+}
+
 static void free_irq_at(unsigned int at, struct irq_cfg *cfg)
 {
 	free_irq_cfg(at, cfg);
@@ -3039,6 +3044,55 @@ int create_irq(void)
 	return irq;
 }
 
+unsigned int create_irqs(unsigned int from, unsigned int count, int node)
+{
+	struct irq_cfg **cfg;
+	unsigned long flags;
+	int irq, i;
+
+	if (from < nr_irqs_gsi)
+		from = nr_irqs_gsi;
+
+	cfg = kzalloc_node(count * sizeof(cfg[0]), GFP_KERNEL, node);
+	if (!cfg)
+		return 0;
+
+	irq = alloc_irqs_from(from, count, node);
+	if (irq < 0)
+		goto out_cfgs;
+
+	for (i = 0; i < count; i++) {
+		cfg[i] = alloc_irq_cfg(irq + i, node);
+		if (!cfg[i])
+			goto out_irqs;
+	}
+
+	raw_spin_lock_irqsave(&vector_lock, flags);
+	for (i = 0; i < count; i++)
+		if (__assign_irq_vector(irq + i, cfg[i], apic->target_cpus()))
+			goto out_vecs;
+	raw_spin_unlock_irqrestore(&vector_lock, flags);
+
+	for (i = 0; i < count; i++) {
+		irq_set_chip_data(irq + i, cfg[i]);
+		irq_clear_status_flags(irq + i, IRQ_NOREQUEST);
+	}
+
+	kfree(cfg);
+	return irq;
+
+out_vecs:
+	for (; i; i--)
+		__clear_irq_vector(irq + i - 1, cfg[i - 1]);
+	raw_spin_unlock_irqrestore(&vector_lock, flags);
+out_irqs:
+	for (i = 0; i < count; i++)
+		free_irq_at(irq + i, cfg[i]);
+out_cfgs:
+	kfree(cfg);
+	return 0;
+}
+
 void destroy_irq(unsigned int irq)
 {
 	struct irq_cfg *cfg = irq_get_chip_data(irq);
@@ -3054,6 +3108,27 @@ void destroy_irq(unsigned int irq)
 	free_irq_at(irq, cfg);
 }
 
+static inline void destroy_irqs(unsigned int irq, unsigned int count)
+{
+	unsigned int i;
+	for (i = 0; i < count; i++)
+		destroy_irq(irq + i);
+}
+
+static inline int
+can_create_pow_of_two_irqs(unsigned int from, unsigned int count)
+{
+	if ((count > 1) && (count % 2))
+		return -EINVAL;
+
+	for (; count; count = count / 2) {
+		if (!irq_can_alloc_irqs(from, count))
+			return count;
+	}
+
+	return -ENOSPC;
+}
+
 /*
  * MSI message composition
  */
@@ -3145,18 +3220,25 @@ static struct irq_chip msi_chip = {
 	.irq_retrigger		= ioapic_retrigger_irq,
 };
 
-static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
+static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc,
+			 unsigned int irq_base, unsigned int irq_offset)
 {
 	struct irq_chip *chip = &msi_chip;
 	struct msi_msg msg;
+	unsigned int irq = irq_base + irq_offset;
 	int ret;
 
 	ret = msi_compose_msg(dev, irq, &msg, -1);
 	if (ret < 0)
 		return ret;
 
-	irq_set_msi_desc(irq, msidesc);
-	write_msi_msg(irq, &msg);
+	irq_set_msi_desc_off(irq_base, irq_offset, msidesc);
+
+	/* MSI-X message is written per-IRQ, the offset is always 0.
+	 * MSI message denotes a contiguous group of IRQs, written for 0th IRQ.
+	 */
+	if (!irq_offset)
+		write_msi_msg(irq, &msg);
 
 	if (irq_remapped(irq_get_chip_data(irq))) {
 		irq_set_status_flags(irq, IRQ_MOVE_PCNTXT);
@@ -3170,16 +3252,12 @@ static int setup_msi_irq(struct pci_dev *dev, struct msi_desc *msidesc, int irq)
 	return 0;
 }
 
-int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+int setup_msix_irqs(struct pci_dev *dev, int nvec)
 {
 	int node, ret, sub_handle, index = 0;
 	unsigned int irq, irq_want;
 	struct msi_desc *msidesc;
 
-	/* x86 doesn't support multiple MSI yet */
-	if (type == PCI_CAP_ID_MSI && nvec > 1)
-		return 1;
-
 	node = dev_to_node(&dev->dev);
 	irq_want = nr_irqs_gsi;
 	sub_handle = 0;
@@ -3208,7 +3286,7 @@ int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
 				goto error;
 		}
 no_ir:
-		ret = setup_msi_irq(dev, msidesc, irq);
+		ret = setup_msi_irq(dev, msidesc, irq, 0);
 		if (ret < 0)
 			goto error;
 		sub_handle++;
@@ -3220,6 +3298,76 @@ error:
 	return ret;
 }
 
+int setup_msi_irqs(struct pci_dev *dev, int nvec)
+{
+	int node, ret, sub_handle, index = 0;
+	unsigned int irq;
+	struct msi_desc *msidesc;
+
+	if (nvec > 1 && !irq_remapping_enabled)
+		return 1;
+
+	nvec = __roundup_pow_of_two(nvec);
+	ret = can_create_pow_of_two_irqs(nr_irqs_gsi, nvec);
+	if (ret != nvec)
+		return ret;
+
+	WARN_ON(!list_is_singular(&dev->msi_list));
+	msidesc = list_entry(dev->msi_list.next, struct msi_desc, list);
+	WARN_ON(msidesc->irq);
+	WARN_ON(msidesc->msi_attrib.multiple);
+
+	node = dev_to_node(&dev->dev);
+	irq = create_irqs(nr_irqs_gsi, nvec, node);
+	if (irq == 0)
+		return -ENOSPC;
+
+	if (!irq_remapping_enabled) {
+		ret = setup_msi_irq(dev, msidesc, irq, 0);
+		if (ret < 0)
+			goto error;
+		return 0;
+	}
+
+	msidesc->msi_attrib.multiple = ilog2(nvec);
+	for (sub_handle = 0; sub_handle < nvec; sub_handle++) {
+		if (!sub_handle) {
+			index = msi_alloc_remapped_irq(dev, irq, nvec);
+			if (index < 0) {
+				ret = index;
+				goto error;
+			}
+		} else {
+			ret = msi_setup_remapped_irq(dev, irq + sub_handle,
+						     index, sub_handle);
+			if (ret < 0)
+				goto error;
+		}
+		ret = setup_msi_irq(dev, msidesc, irq, sub_handle);
+		if (ret < 0)
+			goto error;
+	}
+	return 0;
+
+error:
+	destroy_irqs(irq, nvec);
+
+	/* Restore altered MSI descriptor fields and prevent just destroyed
+	 * IRQs from tearing down again in default_teardown_msi_irqs()
+	 */
+	msidesc->irq = 0;
+	msidesc->msi_attrib.multiple = 0;
+
+	return ret;
+}
+
+int native_setup_msi_irqs(struct pci_dev *dev, int nvec, int type)
+{
+	if (type == PCI_CAP_ID_MSI)
+		return setup_msi_irqs(dev, nvec);
+	return setup_msix_irqs(dev, nvec);
+}
+
 void native_teardown_msi_irq(unsigned int irq)
 {
 	destroy_irq(irq);
diff --git a/include/linux/irq.h b/include/linux/irq.h
index 216b0ba..c3ba39f 100644
--- a/include/linux/irq.h
+++ b/include/linux/irq.h
@@ -522,6 +522,8 @@ extern int irq_set_handler_data(unsigned int irq, void *data);
 extern int irq_set_chip_data(unsigned int irq, void *data);
 extern int irq_set_irq_type(unsigned int irq, unsigned int type);
 extern int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry);
+extern int irq_set_msi_desc_off(unsigned int irq_base, unsigned int irq_offset,
+				struct msi_desc *entry);
 extern struct irq_data *irq_get_irq_data(unsigned int irq);
 
 static inline struct irq_chip *irq_get_chip(unsigned int irq)
@@ -584,8 +586,12 @@ int __irq_alloc_descs(int irq, unsigned int from, unsigned int cnt, int node,
 #define irq_alloc_desc_from(from, node)		\
 	irq_alloc_descs(-1, from, 1, node)
 
+#define irq_alloc_descs_from(from, cnt, node)	\
+	irq_alloc_descs(-1, from, cnt, node)
+
 void irq_free_descs(unsigned int irq, unsigned int cnt);
 int irq_reserve_irqs(unsigned int from, unsigned int cnt);
+int irq_can_alloc_irqs(unsigned int from, unsigned int cnt);
 
 static inline void irq_free_desc(unsigned int irq)
 {
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 57d86d0..2230389 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -90,27 +90,41 @@ int irq_set_handler_data(unsigned int irq, void *data)
 EXPORT_SYMBOL(irq_set_handler_data);
 
 /**
- *	irq_set_msi_desc - set MSI descriptor data for an irq
- *	@irq:	Interrupt number
- *	@entry:	Pointer to MSI descriptor data
+ *	irq_set_msi_desc_off - set MSI descriptor data for an irq at offset
+ *	@irq_base:	Interrupt number base
+ *	@irq_offset:	Interrupt number offset
+ *	@entry:		Pointer to MSI descriptor data
  *
- *	Set the MSI descriptor entry for an irq
+ *	Set the MSI descriptor entry for an irq at offset
  */
-int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry)
+int irq_set_msi_desc_off(unsigned int irq_base, unsigned int irq_offset,
+			 struct msi_desc *entry)
 {
 	unsigned long flags;
-	struct irq_desc *desc = irq_get_desc_lock(irq, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
+	struct irq_desc *desc = irq_get_desc_lock(irq_base + irq_offset, &flags, IRQ_GET_DESC_CHECK_GLOBAL);
 
 	if (!desc)
 		return -EINVAL;
 	desc->irq_data.msi_desc = entry;
-	if (entry)
-		entry->irq = irq;
+	if (entry && !irq_offset)
+		entry->irq = irq_base;
 	irq_put_desc_unlock(desc, flags);
 	return 0;
 }
 
 /**
+ *	irq_set_msi_desc - set MSI descriptor data for an irq
+ *	@irq:	Interrupt number
+ *	@entry:	Pointer to MSI descriptor data
+ *
+ *	Set the MSI descriptor entry for an irq
+ */
+int irq_set_msi_desc(unsigned int irq, struct msi_desc *entry)
+{
+	return irq_set_msi_desc_off(irq, 0, entry);
+}
+
+/**
  *	irq_set_chip_data - set irq chip data for an irq
  *	@irq:	Interrupt number
  *	@data:	Pointer to chip specific data
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index 192a302..8287b78 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -210,6 +210,13 @@ static int irq_expand_nr_irqs(unsigned int nr)
 	return 0;
 }
 
+static int irq_can_expand_nr_irqs(unsigned int nr)
+{
+	if (nr > IRQ_BITMAP_BITS)
+		return -ENOMEM;
+	return 0;
+}
+
 int __init early_irq_init(void)
 {
 	int i, initcnt, node = first_online_node;
@@ -414,6 +421,30 @@ int irq_reserve_irqs(unsigned int from, unsigned int cnt)
 }
 
 /**
+ * irq_can_alloc_irqs - checks if a range of irqs could be allocated
+ * @from:	check from irq number
+ * @cnt:	number of irqs to check
+ *
+ * Returns 0 on success or an appropriate error code
+ */
+int irq_can_alloc_irqs(unsigned int from, unsigned int cnt)
+{
+	unsigned int start;
+	int ret = 0;
+
+	if (!cnt)
+		return -EINVAL;
+
+	mutex_lock(&sparse_irq_lock);
+	start = bitmap_find_next_zero_area(allocated_irqs, IRQ_BITMAP_BITS,
+					   from, cnt, 0);
+	mutex_unlock(&sparse_irq_lock);
+	if (start + cnt > nr_irqs)
+		ret = irq_can_expand_nr_irqs(start + cnt);
+	return ret;
+}
+
+/**
  * irq_get_next_irq - get next allocated irq number
  * @offset:	where to start the search
  *
-- 
1.7.7.6


-- 
Regards,
Alexander Gordeev
agordeev@redhat.com

  reply	other threads:[~2012-09-03  9:18 UTC|newest]

Thread overview: 12+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-09-03  9:16 [PATCH v2 -tip 0/5] x86, MSI, AHCI: Support multiple MSIs Alexander Gordeev
2012-09-03  9:17 ` Alexander Gordeev [this message]
2012-09-03 18:53   ` [PATCH v2 -tip 1/5] x86, MSI: Support multiple MSIs in presense of IRQ remapping Yinghai Lu
2012-09-04  9:32     ` Alexander Gordeev
2012-09-03  9:18 ` [PATCH v2 -tip 2/5] x86, MSI: Allocate as many multiple IRQs as requested Alexander Gordeev
2012-09-03  9:19 ` [PATCH v2 -tip 3/5] x86, MSI: Minor readability fixes Alexander Gordeev
2012-09-03  9:19 ` [PATCH v2 -tip 4/5] PCI, MSI: Enable multiple MSIs with pci_enable_msi_block_auto() Alexander Gordeev
2012-09-07 20:53   ` Bjorn Helgaas
2012-09-03  9:20 ` [PATCH v2 -tip 5/5] AHCI: Support multiple MSIs Alexander Gordeev
2012-09-27  4:59   ` Jeff Garzik
2012-09-26 12:38 ` [PATCH v2 -tip 0/5] x86, MSI, " Alexander Gordeev
2012-09-27  4:03   ` Ingo Molnar

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=034a9cbb168501954408f1004a28c827f3a4158b.1346653435.git.agordeev@redhat.com \
    --to=agordeev@redhat.com \
    --cc=bhelgaas@google.com \
    --cc=jgarzik@pobox.com \
    --cc=linux-ide@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-pci@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=suresh.b.siddha@intel.com \
    --cc=tglx@linutronix.de \
    --cc=willy@linux.intel.com \
    --cc=x86@kernel.org \
    --cc=yinghai@kernel.org \
    --subject='Re: [PATCH v2 -tip 1/5] x86, MSI: Support multiple MSIs in presense of IRQ remapping' \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).