Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 2620:137:e000::1:20 as permitted sender) client-ip=2620:137:e000::1:20;
Received-SPF: Pass (protection.outlook.com: domain of nvidia.com designates
 216.228.117.160 as permitted sender) receiver=protection.outlook.com;
 client-ip=216.228.117.160; helo=mail.nvidia.com; pr=C
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>
Subject: [PATCH v3 3/3] genirq: Use the maple tree for IRQ descriptors management
Date:   Mon, 10 Apr 2023 10:57:21 -0500
Message-ID: <20230410155721.3720991-4-sdonthineni@nvidia.com>
In-Reply-To: <20230410155721.3720991-1-sdonthineni@nvidia.com>
References: <20230410155721.3720991-1-sdonthineni@nvidia.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Content-Type: text/plain
X-MS-Exchange-CrossTenant-OriginalArrivalTime: 10 Apr 2023 15:57:30.7293
 (UTC)
X-MS-Exchange-CrossTenant-Network-Message-Id: 722891f6-bc38-4e20-4e46-08db39dc4a82
X-MS-Exchange-CrossTenant-Id: 43083d15-7273-40c1-b7db-39efd9ccc17a
X-MS-Exchange-CrossTenant-OriginalAttributedTenantConnectingIp: TenantId=43083d15-7273-40c1-b7db-39efd9ccc17a;Ip=[216.228.117.160];Helo=[mail.nvidia.com]
X-MS-Exchange-CrossTenant-AuthSource: DM6NAM11FT056.eop-nam11.prod.protection.outlook.com
X-MS-Exchange-CrossTenant-AuthAs: Anonymous
X-MS-Exchange-CrossTenant-FromEntityHeader: HybridOnPrem
X-MS-Exchange-Transport-CrossTenantHeadersStamped: DS7PR12MB6141
X-Spam-Status: No, score=0.8 required=5.0 tests=DKIMWL_WL_HIGH,DKIM_SIGNED,
        DKIM_VALID,DKIM_VALID_AU,DKIM_VALID_EF,FORGED_SPF_HELO,
        RCVD_IN_DNSWL_NONE,RCVD_IN_MSPIKE_H2,SPF_HELO_PASS,SPF_NONE
        autolearn=no autolearn_force=no version=3.4.6
X-Spam-Checker-Version: SpamAssassin 3.4.6 (2021-04-09) on
        lindbergh.monkeyblade.net
Precedence: bulk
List-ID: <linux-kernel.vger.kernel.org>
X-Mailing-List: linux-kernel@vger.kernel.org

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 interrupt
descriptors 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 f3f2090dd2de..7bdb7507efb0 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 9a71fc6f2c5f..d6d8120ffd56 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)
 {
@@ -517,7 +525,6 @@ 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:
@@ -557,7 +564,6 @@ 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();
@@ -612,6 +618,7 @@ 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,
@@ -624,8 +631,8 @@ 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;
 }
 
@@ -637,7 +644,7 @@ 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);
 }
 
@@ -781,7 +788,6 @@ 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