mirror of https://lore.kernel.org/lkml/
 help / color / mirror / Atom feed
From: Shanker Donthineni <sdonthineni@nvidia.com>
To: Thomas Gleixner <tglx@linutronix.de>, Marc Zyngier <maz@kernel.org>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>,
	Michael Walle <michael@walle.cc>,
	Shanker Donthineni <sdonthineni@nvidia.com>,
	<linux-kernel@vger.kernel.org>, Vikram Sethi <vsethi@nvidia.com>,
	"Liam R . Howlett" <Liam.Howlett@oracle.com>
Subject: [PATCH v2 3/3] genirq: Use the maple tree for IRQ descriptors management
Date: Sat, 8 Apr 2023 12:15:26 -0500	[thread overview]
Message-ID: <20230408171526.3059039-4-sdonthineni@nvidia.com> (raw)
In-Reply-To: <20230408171526.3059039-1-sdonthineni@nvidia.com>

The current implementation uses a static bitmap and a radix tree
to manage IRQ allocation and irq_desc pointer store respectively.
However, the size of the bitmap is constrained by the build time
macro MAX_SPARSE_IRQS, which may not be sufficient to support the
high-end servers, particularly those with GICv4.1 hardware, which
require a large interrupt space to cover LPIs and vSGIs

The maple tree is a highly efficient data structure for storing
non-overlapping ranges and can handle a large number of entries,
up to ULONG_MAX. It can be utilized for both storing IRQD and
identifying available free spaces.

The interrupt descriptors management can be simplified by switching
to a maple tree data structure, which offers greater flexibility
and scalability. To support modern servers, the maximum number of
IRQs has been increased to INT_MAX, which provides a more adequate
value than the previous limit of NR_IRQS+8192.

Signed-off-by: Shanker Donthineni <sdonthineni@nvidia.com>
---
 kernel/irq/internals.h |  2 +-
 kernel/irq/irqdesc.c   | 54 +++++++++++++++++++++++-------------------
 2 files changed, 31 insertions(+), 25 deletions(-)

diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 5d741b0e7d5e..e35de737802c 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -12,7 +12,7 @@
 #include <linux/sched/clock.h>
 
 #ifdef CONFIG_SPARSE_IRQ
-# define MAX_SPARSE_IRQS	(NR_IRQS + 8196)
+# define MAX_SPARSE_IRQS	INT_MAX
 #else
 # define MAX_SPARSE_IRQS	NR_IRQS
 #endif
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index e0c259769d3a..e2e95e937c11 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -12,8 +12,7 @@
 #include <linux/export.h>
 #include <linux/interrupt.h>
 #include <linux/kernel_stat.h>
-#include <linux/radix-tree.h>
-#include <linux/bitmap.h>
+#include <linux/maple_tree.h>
 #include <linux/irqdomain.h>
 #include <linux/sysfs.h>
 
@@ -131,17 +130,38 @@ int nr_irqs = NR_IRQS;
 EXPORT_SYMBOL_GPL(nr_irqs);
 
 static DEFINE_MUTEX(sparse_irq_lock);
-static DECLARE_BITMAP(allocated_irqs, MAX_SPARSE_IRQS);
+static struct maple_tree sparse_irqs = MTREE_INIT_EXT(sparse_irqs,
+					MT_FLAGS_ALLOC_RANGE |
+					MT_FLAGS_LOCK_EXTERN |
+					MT_FLAGS_USE_RCU,
+					sparse_irq_lock);
 
 static int irq_find_free_area(unsigned int from, unsigned int cnt)
 {
-	return bitmap_find_next_zero_area(allocated_irqs, MAX_SPARSE_IRQS,
-					  from, cnt, 0);
+	MA_STATE(mas, &sparse_irqs, 0, 0);
+
+	if (mas_empty_area(&mas, from, MAX_SPARSE_IRQS, cnt))
+		return -ENOSPC;
+	return mas.index;
 }
 
 static unsigned int irq_find_next_irq(unsigned int offset)
 {
-	return find_next_bit(allocated_irqs, nr_irqs, offset);
+	struct irq_desc *desc = mt_next(&sparse_irqs, offset, nr_irqs);
+
+	return desc ? irq_desc_get_irq(desc) : nr_irqs;
+}
+
+static void irq_insert_desc(unsigned int irq, struct irq_desc *desc)
+{
+	MA_STATE(mas, &sparse_irqs, irq, irq);
+	WARN_ON(mas_store_gfp(&mas, desc, GFP_KERNEL) != 0);
+}
+
+static void delete_irq_desc(unsigned int irq)
+{
+	MA_STATE(mas, &sparse_irqs, irq, irq);
+	mas_erase(&mas);
 }
 
 #ifdef CONFIG_SPARSE_IRQ
@@ -355,26 +375,14 @@ static void irq_sysfs_del(struct irq_desc *desc) {}
 
 #endif /* CONFIG_SYSFS */
 
-static RADIX_TREE(irq_desc_tree, GFP_KERNEL);
-
-static void irq_insert_desc(unsigned int irq, struct irq_desc *desc)
-{
-	radix_tree_insert(&irq_desc_tree, irq, desc);
-}
-
 struct irq_desc *irq_to_desc(unsigned int irq)
 {
-	return radix_tree_lookup(&irq_desc_tree, irq);
+	return mtree_load(&sparse_irqs, irq);
 }
 #ifdef CONFIG_KVM_BOOK3S_64_HV_MODULE
 EXPORT_SYMBOL_GPL(irq_to_desc);
 #endif
 
-static void delete_irq_desc(unsigned int irq)
-{
-	radix_tree_delete(&irq_desc_tree, irq);
-}
-
 #ifdef CONFIG_SMP
 static void free_masks(struct irq_desc *desc)
 {
@@ -519,7 +527,6 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node,
 		irq_sysfs_add(start + i, desc);
 		irq_add_debugfs_entry(start + i, desc);
 	}
-	bitmap_set(allocated_irqs, start, cnt);
 	return start;
 
 err:
@@ -559,7 +566,6 @@ int __init early_irq_init(void)
 
 	for (i = 0; i < initcnt; i++) {
 		desc = alloc_desc(i, node, 0, NULL, NULL);
-		set_bit(i, allocated_irqs);
 		irq_insert_desc(i, desc);
 	}
 	return arch_early_irq_init();
@@ -616,6 +622,7 @@ static void free_desc(unsigned int irq)
 	raw_spin_lock_irqsave(&desc->lock, flags);
 	desc_set_defaults(irq, desc, irq_desc_get_node(desc), NULL, NULL);
 	raw_spin_unlock_irqrestore(&desc->lock, flags);
+	delete_irq_desc(irq);
 }
 
 static inline int alloc_descs(unsigned int start, unsigned int cnt, int node,
@@ -628,8 +635,8 @@ static inline int alloc_descs(unsigned int start, unsigned int cnt, int node,
 		struct irq_desc *desc = irq_to_desc(start + i);
 
 		desc->owner = owner;
+		irq_insert_desc(start + i, desc);
 	}
-	bitmap_set(allocated_irqs, start, cnt);
 	return start;
 }
 
@@ -641,7 +648,7 @@ static int irq_expand_nr_irqs(unsigned int nr)
 void irq_mark_irq(unsigned int irq)
 {
 	mutex_lock(&sparse_irq_lock);
-	bitmap_set(allocated_irqs, irq, 1);
+	irq_insert_desc(irq, irq_desc + irq);
 	mutex_unlock(&sparse_irq_lock);
 }
 
@@ -785,7 +792,6 @@ void irq_free_descs(unsigned int from, unsigned int cnt)
 	for (i = 0; i < cnt; i++)
 		free_desc(from + i);
 
-	bitmap_clear(allocated_irqs, from, cnt);
 	mutex_unlock(&sparse_irq_lock);
 }
 EXPORT_SYMBOL_GPL(irq_free_descs);
-- 
2.25.1


      parent reply	other threads:[~2023-04-08 17:16 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-04-08 17:15 [PATCH v2 0/3] Increase the number of IRQ descriptors for SPARSEIRQ Shanker Donthineni
2023-04-08 17:15 ` [PATCH v2 1/3] genirq: Use hlist for managing resend handlers Shanker Donthineni
     [not found]   ` <863559mne0.wl-maz@kernel.org>
2023-04-09 12:00     ` Shanker Donthineni
2023-04-10 10:05       ` Marc Zyngier
2023-04-10 11:52         ` Shanker Donthineni
2023-04-08 17:15 ` [PATCH v2 2/3] genirq: Encapsulate sparse bitmap handling Shanker Donthineni
2023-04-08 17:15 ` Shanker Donthineni [this message]

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=20230408171526.3059039-4-sdonthineni@nvidia.com \
    --to=sdonthineni@nvidia.com \
    --cc=Liam.Howlett@oracle.com \
    --cc=bigeasy@linutronix.de \
    --cc=linux-kernel@vger.kernel.org \
    --cc=maz@kernel.org \
    --cc=michael@walle.cc \
    --cc=tglx@linutronix.de \
    --cc=vsethi@nvidia.com \
    /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
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox

all inboxes | Powered by JetHome®