Received-SPF: pass (google.com: domain of linux-kernel+bounces-78048-linux.lists.archive=gmail.com@vger.kernel.org designates 147.75.199.223 as permitted sender) client-ip=147.75.199.223;
Date: Fri, 23 Feb 2024 09:43:51 -0000
From:
 tip-bot2 for =?utf-8?q?Bj=C3=B6rn_T=C3=B6pel?= <tip-bot2@linutronix.de>
Sender: tip-bot2@linutronix.de
Reply-to: linux-kernel@vger.kernel.org
To: linux-tip-commits@vger.kernel.org
Subject: [tip: irq/msi] genirq/matrix: Dynamic bitmap allocation
Cc: bjorn@rivosinc.com, Anup Patel <apatel@ventanamicro.com>,
 Thomas Gleixner <tglx@linutronix.de>, x86@kernel.org,
 linux-kernel@vger.kernel.org
In-Reply-To: <20240222094006.1030709-11-apatel@ventanamicro.com>
References: <20240222094006.1030709-11-apatel@ventanamicro.com>
Precedence: bulk
MIME-Version: 1.0
Message-ID: <170868143119.398.7440083204320178509.tip-bot2@tip-bot2>
Robot-ID: <tip-bot2@linutronix.de>
Robot-Unsubscribe:
 Contact <mailto:tglx@linutronix.de> to get blacklisted from these emails
Precedence: bulk
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: quoted-printable

The following commit has been merged into the irq/msi branch of tip:

Commit-ID:     5b98d210ac1e4eb35abfbd940df50dec10ae81e1
Gitweb:        https://git.kernel.org/tip/5b98d210ac1e4eb35abfbd940df50dec10a=
e81e1
Author:        Bj=C3=B6rn T=C3=B6pel <bjorn@rivosinc.com>
AuthorDate:    Thu, 22 Feb 2024 15:09:58 +05:30
Committer:     Thomas Gleixner <tglx@linutronix.de>
CommitterDate: Fri, 23 Feb 2024 10:18:44 +01:00

genirq/matrix: Dynamic bitmap allocation

A future user of the matrix allocator, does not know the size of the matrix
bitmaps at compile time.

To avoid wasting memory on unnecessary large bitmaps, size the bitmap at
matrix allocation time.

Signed-off-by: Bj=C3=B6rn T=C3=B6pel <bjorn@rivosinc.com>
Signed-off-by: Anup Patel <apatel@ventanamicro.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Link: https://lore.kernel.org/r/20240222094006.1030709-11-apatel@ventanamicro=
com

---
 arch/x86/include/asm/hw_irq.h |  2 --
 kernel/irq/matrix.c           | 28 +++++++++++++++++-----------
 2 files changed, 17 insertions(+), 13 deletions(-)

diff --git a/arch/x86/include/asm/hw_irq.h b/arch/x86/include/asm/hw_irq.h
index b02c3cd..edebf10 100644
--- a/arch/x86/include/asm/hw_irq.h
+++ b/arch/x86/include/asm/hw_irq.h
@@ -16,8 +16,6 @@
=20
 #include <asm/irq_vectors.h>
=20
-#define IRQ_MATRIX_BITS		NR_VECTORS
-
 #ifndef __ASSEMBLY__
=20
 #include <linux/percpu.h>
diff --git a/kernel/irq/matrix.c b/kernel/irq/matrix.c
index 75d0ae4..8f222d1 100644
--- a/kernel/irq/matrix.c
+++ b/kernel/irq/matrix.c
@@ -8,8 +8,6 @@
 #include <linux/cpu.h>
 #include <linux/irq.h>
=20
-#define IRQ_MATRIX_SIZE	(BITS_TO_LONGS(IRQ_MATRIX_BITS))
-
 struct cpumap {
 	unsigned int		available;
 	unsigned int		allocated;
@@ -17,8 +15,8 @@ struct cpumap {
 	unsigned int		managed_allocated;
 	bool			initialized;
 	bool			online;
-	unsigned long		alloc_map[IRQ_MATRIX_SIZE];
-	unsigned long		managed_map[IRQ_MATRIX_SIZE];
+	unsigned long		*managed_map;
+	unsigned long		alloc_map[];
 };
=20
 struct irq_matrix {
@@ -32,8 +30,8 @@ struct irq_matrix {
 	unsigned int		total_allocated;
 	unsigned int		online_maps;
 	struct cpumap __percpu	*maps;
-	unsigned long		scratch_map[IRQ_MATRIX_SIZE];
-	unsigned long		system_map[IRQ_MATRIX_SIZE];
+	unsigned long		*system_map;
+	unsigned long		scratch_map[];
 };
=20
 #define CREATE_TRACE_POINTS
@@ -50,24 +48,32 @@ __init struct irq_matrix *irq_alloc_matrix(unsigned int m=
atrix_bits,
 					   unsigned int alloc_start,
 					   unsigned int alloc_end)
 {
+	unsigned int cpu, matrix_size =3D BITS_TO_LONGS(matrix_bits);
 	struct irq_matrix *m;
=20
-	if (matrix_bits > IRQ_MATRIX_BITS)
-		return NULL;
-
-	m =3D kzalloc(sizeof(*m), GFP_KERNEL);
+	m =3D kzalloc(struct_size(m, scratch_map, matrix_size * 2), GFP_KERNEL);
 	if (!m)
 		return NULL;
=20
+	m->system_map =3D &m->scratch_map[matrix_size];
+
 	m->matrix_bits =3D matrix_bits;
 	m->alloc_start =3D alloc_start;
 	m->alloc_end =3D alloc_end;
 	m->alloc_size =3D alloc_end - alloc_start;
-	m->maps =3D alloc_percpu(*m->maps);
+	m->maps =3D __alloc_percpu(struct_size(m->maps, alloc_map, matrix_size * 2),
+				 __alignof__(*m->maps));
 	if (!m->maps) {
 		kfree(m);
 		return NULL;
 	}
+
+	for_each_possible_cpu(cpu) {
+		struct cpumap *cm =3D per_cpu_ptr(m->maps, cpu);
+
+		cm->managed_map =3D &cm->alloc_map[matrix_size];
+	}
+
 	return m;
 }
=20