linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Zhen Lei <thunder.leizhen@huawei.com>
To: Russell King <rmk+kernel@arm.linux.org.uk>,
	Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
	Will Deacon <will.deacon@arm.com>,
	"Haojian Zhuang" <haojian.zhuang@gmail.com>,
	Arnd Bergmann <arnd@arndb.de>, Rob Herring <robh+dt@kernel.org>,
	Wei Xu <xuwei5@hisilicon.com>,
	devicetree <devicetree@vger.kernel.org>,
	linux-arm-kernel <linux-arm-kernel@lists.infradead.org>,
	linux-kernel <linux-kernel@vger.kernel.org>
Cc: Zhen Lei <thunder.leizhen@huawei.com>
Subject: [PATCH v7 4/4] ARM: Add support for Hisilicon Kunpeng L3 cache controller
Date: Tue, 2 Feb 2021 15:16:48 +0800	[thread overview]
Message-ID: <20210202071648.1776-5-thunder.leizhen@huawei.com> (raw)
In-Reply-To: <20210202071648.1776-1-thunder.leizhen@huawei.com>

Add support for the Hisilicon Kunpeng L3 cache controller as used with
Kunpeng506 and Kunpeng509 SoCs.

These Hisilicon SoCs support LPAE, so the physical addresses is wider than
32-bits, but the actual bit width does not exceed 36 bits. When the cache
operation is performed based on the address range, the upper 30 bits of
the physical address are recorded in registers L3_MAINT_START and
L3_MAINT_END, and ignore the lower 6 bits cacheline offset.

Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
---
 arch/arm/mm/Kconfig            |  10 ++
 arch/arm/mm/Makefile           |   1 +
 arch/arm/mm/cache-kunpeng-l3.c | 178 +++++++++++++++++++++++++++++++++
 3 files changed, 189 insertions(+)
 create mode 100644 arch/arm/mm/cache-kunpeng-l3.c

diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 02692fbe2db5c59..d2082503de053d2 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -1070,6 +1070,16 @@ config CACHE_XSC3L2
 	help
 	  This option enables the L2 cache on XScale3.
 
+config CACHE_KUNPENG_L3
+	bool "Enable the Hisilicon Kunpeng L3 cache controller"
+	depends on ARCH_KUNPENG50X && OF
+	default y
+	select OUTER_CACHE
+	help
+	  This option enables the Kunpeng L3 cache controller on Hisilicon
+	  Kunpeng506 and Kunpeng509 SoCs. It supports a maximum of 36-bit
+	  physical addresses.
+
 config ARM_L1_CACHE_SHIFT_6
 	bool
 	default y if CPU_V7
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 3510503bc5e688b..ececc5489e353eb 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -112,6 +112,7 @@ obj-$(CONFIG_CACHE_L2X0_PMU)	+= cache-l2x0-pmu.o
 obj-$(CONFIG_CACHE_XSC3L2)	+= cache-xsc3l2.o
 obj-$(CONFIG_CACHE_TAUROS2)	+= cache-tauros2.o
 obj-$(CONFIG_CACHE_UNIPHIER)	+= cache-uniphier.o
+obj-$(CONFIG_CACHE_KUNPENG_L3)	+= cache-kunpeng-l3.o
 
 KASAN_SANITIZE_kasan_init.o	:= n
 obj-$(CONFIG_KASAN)		+= kasan_init.o
diff --git a/arch/arm/mm/cache-kunpeng-l3.c b/arch/arm/mm/cache-kunpeng-l3.c
new file mode 100644
index 000000000000000..64f892de9d68058
--- /dev/null
+++ b/arch/arm/mm/cache-kunpeng-l3.c
@@ -0,0 +1,178 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (C) 2021 Hisilicon Limited.
+ */
+
+#include <linux/init.h>
+#include <linux/spinlock.h>
+#include <linux/io.h>
+#include <linux/of_address.h>
+
+#include <asm/cacheflush.h>
+
+#define L3_CACHE_LINE_SHITF		6
+
+#define L3_CTRL				0x0
+#define L3_CTRL_ENABLE			(1U << 0)
+#define L3_CTRL_DISABLE			(0U << 0)
+
+#define L3_AUCTRL			0x4
+#define L3_AUCTRL_EVENT_EN		BIT(23)
+#define L3_AUCTRL_ECC_EN		BIT(8)
+
+#define L3_MAINT_CTRL			0x20
+#define L3_MAINT_RANGE_MASK		GENMASK(3, 3)
+#define L3_MAINT_RANGE_ALL		(0U << 3)
+#define L3_MAINT_RANGE_ADDR		(1U << 3)
+#define L3_MAINT_TYPE_MASK		GENMASK(2, 1)
+#define L3_MAINT_TYPE_CLEAN		(1U << 1)
+#define L3_MAINT_TYPE_INV		(2U << 1)
+#define L3_MAINT_TYPE_FLUSH		(3U << 1)
+#define L3_MAINT_STATUS_MASK		GENMASK(0, 0)
+#define L3_MAINT_STATUS_START		(1U << 0)
+#define L3_MAINT_STATUS_END		(0U << 0)
+
+#define L3_MAINT_START			0x24
+#define L3_MAINT_END			0x28
+
+static DEFINE_RAW_SPINLOCK(l3cache_lock);
+static void __iomem *l3_ctrl_base;
+
+/*
+ * All read and write operations on L3 cache registers are protected by the
+ * spinlock, except for l3cache_init(). Each time the L3 cache operation is
+ * performed, all related information is filled into its registers. Therefore,
+ * there is no memory order problem when only _relaxed() functions are used.
+ * This can help us achieve some performance improvement:
+ * 1) The readl_relaxed() is about 20ns faster than readl().
+ * 2) The writel_relaxed() is about 123ns faster than writel().
+ */
+static void l3cache_maint_common(u32 range, u32 op_type)
+{
+	u32 reg;
+
+	reg = readl_relaxed(l3_ctrl_base + L3_MAINT_CTRL);
+	reg &= ~(L3_MAINT_RANGE_MASK | L3_MAINT_TYPE_MASK);
+	reg |= range | op_type;
+	reg |= L3_MAINT_STATUS_START;
+	writel_relaxed(reg, l3_ctrl_base + L3_MAINT_CTRL);
+
+	/* Wait until the hardware maintenance operation is complete. */
+	do {
+		cpu_relax();
+		reg = readl_relaxed(l3_ctrl_base + L3_MAINT_CTRL);
+	} while ((reg & L3_MAINT_STATUS_MASK) != L3_MAINT_STATUS_END);
+}
+
+static void l3cache_maint_range(phys_addr_t start, phys_addr_t end, u32 op_type)
+{
+	start = start >> L3_CACHE_LINE_SHITF;
+	end = ((end - 1) >> L3_CACHE_LINE_SHITF) + 1;
+
+	writel_relaxed(start, l3_ctrl_base + L3_MAINT_START);
+	writel_relaxed(end, l3_ctrl_base + L3_MAINT_END);
+
+	l3cache_maint_common(L3_MAINT_RANGE_ADDR, op_type);
+}
+
+static inline void l3cache_flush_all_nolock(void)
+{
+	l3cache_maint_common(L3_MAINT_RANGE_ALL, L3_MAINT_TYPE_FLUSH);
+}
+
+static void l3cache_flush_all(void)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&l3cache_lock, flags);
+	l3cache_flush_all_nolock();
+	raw_spin_unlock_irqrestore(&l3cache_lock, flags);
+}
+
+static void l3cache_inv_range(phys_addr_t start, phys_addr_t end)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&l3cache_lock, flags);
+	l3cache_maint_range(start, end, L3_MAINT_TYPE_INV);
+	raw_spin_unlock_irqrestore(&l3cache_lock, flags);
+}
+
+static void l3cache_clean_range(phys_addr_t start, phys_addr_t end)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&l3cache_lock, flags);
+	l3cache_maint_range(start, end, L3_MAINT_TYPE_CLEAN);
+	raw_spin_unlock_irqrestore(&l3cache_lock, flags);
+}
+
+static void l3cache_flush_range(phys_addr_t start, phys_addr_t end)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&l3cache_lock, flags);
+	l3cache_maint_range(start, end, L3_MAINT_TYPE_FLUSH);
+	raw_spin_unlock_irqrestore(&l3cache_lock, flags);
+}
+
+static void l3cache_disable(void)
+{
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&l3cache_lock, flags);
+	l3cache_flush_all_nolock();
+	writel_relaxed(L3_CTRL_DISABLE, l3_ctrl_base + L3_CTRL);
+	raw_spin_unlock_irqrestore(&l3cache_lock, flags);
+}
+
+static const struct of_device_id l3cache_ids[] __initconst = {
+	{.compatible = "hisilicon,kunpeng-l3cache", .data = NULL},
+	{}
+};
+
+static int __init l3cache_init(void)
+{
+	u32 reg;
+	struct device_node *node;
+
+	node = of_find_matching_node(NULL, l3cache_ids);
+	if (!node)
+		return -ENODEV;
+
+	l3_ctrl_base = of_iomap(node, 0);
+	if (!l3_ctrl_base) {
+		pr_err("failed to map Kunpeng L3 cache controller registers\n");
+		return -ENOMEM;
+	}
+
+	reg = readl_relaxed(l3_ctrl_base + L3_CTRL);
+	if (!(reg & L3_CTRL_ENABLE)) {
+		/*
+		 * Ensure that no L3 cache hardware maintenance operations are
+		 * being performed before enabling the L3 cache. Wait for it to
+		 * finish.
+		 */
+		do {
+			cpu_relax();
+			reg = readl_relaxed(l3_ctrl_base + L3_MAINT_CTRL);
+		} while ((reg & L3_MAINT_STATUS_MASK) != L3_MAINT_STATUS_END);
+
+		reg = readl_relaxed(l3_ctrl_base + L3_AUCTRL);
+		reg |= L3_AUCTRL_EVENT_EN | L3_AUCTRL_ECC_EN;
+		writel_relaxed(reg, l3_ctrl_base + L3_AUCTRL);
+
+		writel_relaxed(L3_CTRL_ENABLE, l3_ctrl_base + L3_CTRL);
+	}
+
+	outer_cache.inv_range = l3cache_inv_range;
+	outer_cache.clean_range = l3cache_clean_range;
+	outer_cache.flush_range = l3cache_flush_range;
+	outer_cache.flush_all = l3cache_flush_all;
+	outer_cache.disable = l3cache_disable;
+
+	pr_info("Hisilicon Kunpeng L3 cache controller enabled\n");
+
+	return 0;
+}
+arch_initcall(l3cache_init);
-- 
2.26.0.106.g9fadedd



  parent reply	other threads:[~2021-02-02  7:22 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-02-02  7:16 [PATCH v7 0/4] ARM: Add support for Hisilicon Kunpeng L3 cache controller Zhen Lei
2021-02-02  7:16 ` [PATCH v7 1/4] ARM: LPAE: Use phys_addr_t instead of unsigned long in outercache hooks Zhen Lei
2021-02-02  7:16 ` [PATCH v7 2/4] ARM: hisi: add support for Kunpeng50x SoC Zhen Lei
2021-02-02  7:16 ` [PATCH v7 3/4] dt-bindings: arm: hisilicon: Add binding for Kunpeng L3 cache controller Zhen Lei
2021-02-05 21:12   ` Rob Herring
2021-02-02  7:16 ` Zhen Lei [this message]
2021-02-02  8:44   ` [PATCH v7 4/4] ARM: Add support for Hisilicon " Arnd Bergmann
2021-02-02 12:18     ` Leizhen (ThunderTown)
2021-02-02 15:54       ` Arnd Bergmann

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=20210202071648.1776-5-thunder.leizhen@huawei.com \
    --to=thunder.leizhen@huawei.com \
    --cc=arnd@arndb.de \
    --cc=devicetree@vger.kernel.org \
    --cc=gregkh@linuxfoundation.org \
    --cc=haojian.zhuang@gmail.com \
    --cc=linux-arm-kernel@lists.infradead.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=rmk+kernel@arm.linux.org.uk \
    --cc=robh+dt@kernel.org \
    --cc=will.deacon@arm.com \
    --cc=xuwei5@hisilicon.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;
as well as URLs for NNTP newsgroup(s).