Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
IronPort-SDR: eJpOe+XAc+AI/++edxux7v4kWgCXgSh+4Blj0vTdd5bcCuouKWZydV0YqKWEFMPDxkXp3qgiw5
 2wBH1QQ1iaDnOW6uRs5D+snhrmyUt67QdaCfBZv8EZSbQdtvAOSGHvGP+eKa+h2EhFmhNgfYTb
 zJRQX/OtwHQH+gdfRwRhDIAolfbWEQeadZ93qQva1PGONTBqk0vK6LmAY4tVs1n3oNBK69xraZ
 qnzWW12LZvTaupt97rfNAmudTotfhkSiQVlqvygC56Cgd1pZjXwXrMkWva/EWq02zYz/2/9Nec
 Thk=
IronPort-SDR: RcsrxLy+TnnmwgcYnKbwd2AXFz5vh+P1hXVAlTc9+YwkYMmEaHDy06Ah26PIgkZ/TtZFUx1APa
 ReWLkPtiGuREtGUpTdu5IvA+MoLhSGDcPh0BEReIZZpCJxy3JDOBY9bXniVtMCHtgK61uqDiBw
 vabF8y4d/3AhOw7D9YKBygD9ikRDNftzOKuwQWRlc6VgWk3/+hJRh5fQ7IE7HtGldZ4HL5F4RG
 Dz5rUPHOWliKZhKXoeolJLAR2UIuEafnSaiU4ywj6XG363AxSFaArTwLMM1CnoB9kGJ76GZoWj
 xj8ztwfgYgYVPhqXR/r8DdYL
IronPort-SDR: DPKcQX/zxw2ZOLdwjTS7GYEy7EASSCZZAQM+RLZswNbsNxIUM1N2R5WsxNblGc95ErRxRCB5+S
 Kg8w/M4bFDhhhvWI6K7eNcrTX55MABWoxQD17ol9MJ1+rZv3TllpcfZkFJ8AP3StZU9nvulDpB
 t6bNnX+G59YsKkHpbeIyWPJpljqkJV2uYXhf6RC+A0x/B6EzD3WqTBS9uH97J6yoDr5Ts2PuIA
 wxHmFjmMHKIcfvDXVGn2XZfm1BuEx5kTv2W6JILPtPQZj0Kw4koC1H4bdxhCpNBkR4+ZsAQy/A
 uUM=
WDCIronportException: Internal
From:   Atish Patra <atish.patra@wdc.com>
To:     linux-kernel@vger.kernel.org
Cc:     Atish Patra <atish.patra@wdc.com>,
        Albert Ou <aou@eecs.berkeley.edu>,
        Allison Randal <allison@lohutok.net>,
        Anup Patel <anup@brainfault.org>, Borislav Petkov <bp@suse.de>,
        Daniel Lezcano <daniel.lezcano@linaro.org>,
        "Eric W. Biederman" <ebiederm@xmission.com>,
        Geert Uytterhoeven <geert@linux-m68k.org>,
        Heiko Carstens <heiko.carstens@de.ibm.com>,
        Jason Cooper <jason@lakedaemon.net>,
        Kees Cook <keescook@chromium.org>,
        linux-riscv@lists.infradead.org, Mao Han <han_mao@c-sky.com>,
        Marc Zyngier <maz@kernel.org>,
        Marek Szyprowski <m.szyprowski@samsung.com>,
        Michael Ellerman <mpe@ellerman.id.au>,
        Mike Rapoport <rppt@linux.ibm.com>,
        Palmer Dabbelt <palmer@dabbelt.com>,
        Paul Walmsley <paul.walmsley@sifive.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Vincent Chen <vincent.chen@sifive.com>
Subject: [PATCH v8 11/11] RISC-V: Support cpu hotplug
Date:   Tue, 11 Feb 2020 17:48:22 -0800
Message-Id: <20200212014822.28684-12-atish.patra@wdc.com>
In-Reply-To: <20200212014822.28684-1-atish.patra@wdc.com>
References: <20200212014822.28684-1-atish.patra@wdc.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

This patch enable support for cpu hotplug in RISC-V. It uses SBI HSM
extension to online/offline any hart. As a result, the harts are
returned to firmware once they are offline. If the harts are brought
online afterwards, they re-enter Linux kernel as if a secondary hart
booted for the first time. All booting requirements are honored during
this process.

Tested both on QEMU and HighFive Unleashed board with. Test result follows.

---------------------------------------------------
Offline cpu 2
---------------------------------------------------
$ echo 0 > /sys/devices/system/cpu/cpu2/online
[   32.828684] CPU2: off
$ cat /proc/cpuinfo
processor       : 0
hart            : 0
isa             : rv64imafdcsu
mmu             : sv48

processor       : 1
hart            : 1
isa             : rv64imafdcsu
mmu             : sv48

processor       : 3
hart            : 3
isa             : rv64imafdcsu
mmu             : sv48

processor       : 4
hart            : 4
isa             : rv64imafdcsu
mmu             : sv48

processor       : 5
hart            : 5
isa             : rv64imafdcsu
mmu             : sv48

processor       : 6
hart            : 6
isa             : rv64imafdcsu
mmu             : sv48

processor       : 7
hart            : 7
isa             : rv64imafdcsu
mmu             : sv48

---------------------------------------------------
online cpu 2
---------------------------------------------------
$ echo 1 > /sys/devices/system/cpu/cpu2/online
$ cat /proc/cpuinfo
processor       : 0
hart            : 0
isa             : rv64imafdcsu
mmu             : sv48

processor       : 1
hart            : 1
isa             : rv64imafdcsu
mmu             : sv48

processor       : 2
hart            : 2
isa             : rv64imafdcsu
mmu             : sv48

processor       : 3
hart            : 3
isa             : rv64imafdcsu
mmu             : sv48

processor       : 4
hart            : 4
isa             : rv64imafdcsu
mmu             : sv48

processor       : 5
hart            : 5
isa             : rv64imafdcsu
mmu             : sv48

processor       : 6
hart            : 6
isa             : rv64imafdcsu
mmu             : sv48

processor       : 7
hart            : 7
isa             : rv64imafdcsu
mmu             : sv48

Signed-off-by: Atish Patra <atish.patra@wdc.com>
---
 arch/riscv/Kconfig               | 12 ++++-
 arch/riscv/include/asm/cpu_ops.h | 12 +++++
 arch/riscv/include/asm/smp.h     | 17 +++++++
 arch/riscv/kernel/Makefile       |  1 +
 arch/riscv/kernel/cpu-hotplug.c  | 87 ++++++++++++++++++++++++++++++++
 arch/riscv/kernel/cpu_ops_sbi.c  | 34 +++++++++++++
 arch/riscv/kernel/setup.c        | 19 ++++++-
 7 files changed, 180 insertions(+), 2 deletions(-)
 create mode 100644 arch/riscv/kernel/cpu-hotplug.c

diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
index 2afe1382dc36..ffd9f4dbd4fc 100644
--- a/arch/riscv/Kconfig
+++ b/arch/riscv/Kconfig
@@ -22,7 +22,6 @@ config RISCV
 	select CLONE_BACKWARDS
 	select COMMON_CLK
 	select GENERIC_CLOCKEVENTS
-	select GENERIC_CPU_DEVICES
 	select GENERIC_IRQ_SHOW
 	select GENERIC_PCI_IOMAP
 	select GENERIC_SCHED_CLOCK
@@ -247,6 +246,17 @@ config NR_CPUS
 	depends on SMP
 	default "8"
 
+config HOTPLUG_CPU
+	bool "Support for hot-pluggable CPUs"
+	depends on SMP
+	select GENERIC_IRQ_MIGRATION
+	help
+
+	  Say Y here to experiment with turning CPUs off and on.  CPUs
+	  can be controlled through /sys/devices/system/cpu.
+
+	  Say N if you want to disable CPU hotplug.
+
 choice
 	prompt "CPU Tuning"
 	default TUNE_GENERIC
diff --git a/arch/riscv/include/asm/cpu_ops.h b/arch/riscv/include/asm/cpu_ops.h
index 7db276284009..df92d20e3a50 100644
--- a/arch/riscv/include/asm/cpu_ops.h
+++ b/arch/riscv/include/asm/cpu_ops.h
@@ -18,12 +18,24 @@
  *			is a mechanism for doing so, tests whether it is
  *			possible to boot the given HART.
  * @cpu_start:		Boots a cpu into the kernel.
+ * @cpu_disable:	Prepares a cpu to die. May fail for some
+ *			mechanism-specific reason, which will cause the hot
+ *			unplug to be aborted. Called from the cpu to be killed.
+ * @cpu_stop:		Makes a cpu leave the kernel. Must not fail. Called from
+ *			the cpu being stopped.
+ * @cpu_is_stopped:	Ensures a cpu has left the kernel. Called from another
+ *			cpu.
  */
 struct cpu_operations {
 	const char	*name;
 	int		(*cpu_prepare)(unsigned int cpu);
 	int		(*cpu_start)(unsigned int cpu,
 				     struct task_struct *tidle);
+#ifdef CONFIG_HOTPLUG_CPU
+	int		(*cpu_disable)(unsigned int cpu);
+	void		(*cpu_stop)(void);
+	int		(*cpu_is_stopped)(unsigned int cpu);
+#endif
 };
 
 extern const struct cpu_operations *cpu_ops[NR_CPUS];
diff --git a/arch/riscv/include/asm/smp.h b/arch/riscv/include/asm/smp.h
index 023f74fb8b3b..f4c7cfda6b7f 100644
--- a/arch/riscv/include/asm/smp.h
+++ b/arch/riscv/include/asm/smp.h
@@ -43,6 +43,13 @@ void riscv_cpuid_to_hartid_mask(const struct cpumask *in, struct cpumask *out);
  */
 #define raw_smp_processor_id() (current_thread_info()->cpu)
 
+#if defined CONFIG_HOTPLUG_CPU
+int __cpu_disable(void);
+void __cpu_die(unsigned int cpu);
+void cpu_stop(void);
+#else
+#endif /* CONFIG_HOTPLUG_CPU */
+
 #else
 
 static inline void show_ipi_stats(struct seq_file *p, int prec)
@@ -69,4 +76,14 @@ static inline void riscv_cpuid_to_hartid_mask(const struct cpumask *in,
 }
 
 #endif /* CONFIG_SMP */
+
+#if defined(CONFIG_HOTPLUG_CPU) && (CONFIG_SMP)
+bool cpu_has_hotplug(unsigned int cpu);
+#else
+static inline bool cpu_has_hotplug(unsigned int cpu)
+{
+	return false;
+}
+#endif
+
 #endif /* _ASM_RISCV_SMP_H */
diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
index a0be34b96846..9601ac907f70 100644
--- a/arch/riscv/kernel/Makefile
+++ b/arch/riscv/kernel/Makefile
@@ -47,5 +47,6 @@ obj-$(CONFIG_RISCV_SBI)		+= sbi.o
 ifeq ($(CONFIG_RISCV_SBI), y)
 obj-$(CONFIG_SMP) += cpu_ops_sbi.o
 endif
+obj-$(CONFIG_HOTPLUG_CPU)	+= cpu-hotplug.o
 
 clean:
diff --git a/arch/riscv/kernel/cpu-hotplug.c b/arch/riscv/kernel/cpu-hotplug.c
new file mode 100644
index 000000000000..2a37cfb6eb46
--- /dev/null
+++ b/arch/riscv/kernel/cpu-hotplug.c
@@ -0,0 +1,87 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018 Western Digital Corporation or its affiliates.
+ */
+
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/sched.h>
+#include <linux/err.h>
+#include <linux/irq.h>
+#include <linux/cpu.h>
+#include <linux/sched/hotplug.h>
+#include <asm/irq.h>
+#include <asm/cpu_ops.h>
+#include <asm/sbi.h>
+
+void cpu_stop(void);
+void arch_cpu_idle_dead(void)
+{
+	cpu_stop();
+}
+
+bool cpu_has_hotplug(unsigned int cpu)
+{
+	if (cpu_ops[cpu]->cpu_stop)
+		return true;
+
+	return false;
+}
+
+/*
+ * __cpu_disable runs on the processor to be shutdown.
+ */
+int __cpu_disable(void)
+{
+	int ret = 0;
+	unsigned int cpu = smp_processor_id();
+
+	if (!cpu_ops[cpu] || !cpu_ops[cpu]->cpu_stop)
+		return -EOPNOTSUPP;
+
+	if (cpu_ops[cpu]->cpu_disable)
+		ret = cpu_ops[cpu]->cpu_disable(cpu);
+
+	if (ret)
+		return ret;
+
+	remove_cpu_topology(cpu);
+	set_cpu_online(cpu, false);
+	irq_migrate_all_off_this_cpu();
+
+	return ret;
+}
+
+/*
+ * Called on the thread which is asking for a CPU to be shutdown.
+ */
+void __cpu_die(unsigned int cpu)
+{
+	int ret = 0;
+
+	if (!cpu_wait_death(cpu, 5)) {
+		pr_err("CPU %u: didn't die\n", cpu);
+		return;
+	}
+	pr_notice("CPU%u: off\n", cpu);
+
+	/* Verify from the firmware if the cpu is really stopped*/
+	if (cpu_ops[cpu]->cpu_is_stopped)
+		ret = cpu_ops[cpu]->cpu_is_stopped(cpu);
+	if (ret)
+		pr_warn("CPU%d may not have stopped: %d\n", cpu, ret);
+}
+
+/*
+ * Called from the idle thread for the CPU which has been shutdown.
+ */
+void cpu_stop(void)
+{
+	idle_task_exit();
+
+	(void)cpu_report_death();
+
+	cpu_ops[smp_processor_id()]->cpu_stop();
+	/* It should never reach here */
+	BUG();
+}
diff --git a/arch/riscv/kernel/cpu_ops_sbi.c b/arch/riscv/kernel/cpu_ops_sbi.c
index 31487a80c3b8..3f77db8a256a 100644
--- a/arch/riscv/kernel/cpu_ops_sbi.c
+++ b/arch/riscv/kernel/cpu_ops_sbi.c
@@ -72,8 +72,42 @@ static int sbi_cpu_prepare(unsigned int cpuid)
 	return 0;
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
+static int sbi_cpu_disable(unsigned int cpuid)
+{
+	if (!cpu_ops_sbi.cpu_stop)
+		return -EOPNOTSUPP;
+	return 0;
+}
+
+static void sbi_cpu_stop(void)
+{
+	int ret;
+
+	ret = sbi_hsm_hart_stop();
+	pr_crit("Unable to stop the cpu %u (%d)\n", smp_processor_id(), ret);
+}
+
+static int sbi_cpu_is_stopped(unsigned int cpuid)
+{
+	int rc;
+	int hartid = cpuid_to_hartid_map(cpuid);
+
+	rc = sbi_hsm_hart_get_status(hartid);
+
+	if (rc == SBI_HSM_HART_STATUS_NOT_AVAILABLE)
+		return 0;
+	return rc;
+}
+#endif
+
 const struct cpu_operations cpu_ops_sbi = {
 	.name		= "sbi",
 	.cpu_prepare	= sbi_cpu_prepare,
 	.cpu_start	= sbi_cpu_start,
+#ifdef CONFIG_HOTPLUG_CPU
+	.cpu_disable	= sbi_cpu_disable,
+	.cpu_stop	= sbi_cpu_stop,
+	.cpu_is_stopped	= sbi_cpu_is_stopped,
+#endif
 };
diff --git a/arch/riscv/kernel/setup.c b/arch/riscv/kernel/setup.c
index 64d17cbae66b..21543a732a3d 100644
--- a/arch/riscv/kernel/setup.c
+++ b/arch/riscv/kernel/setup.c
@@ -16,12 +16,13 @@
 #include <linux/of_platform.h>
 #include <linux/sched/task.h>
 #include <linux/swiotlb.h>
+#include <linux/smp.h>
 
 #include <asm/clint.h>
+#include <asm/cpu_ops.h>
 #include <asm/setup.h>
 #include <asm/sections.h>
 #include <asm/pgtable.h>
-#include <asm/smp.h>
 #include <asm/sbi.h>
 #include <asm/tlbflush.h>
 #include <asm/thread_info.h>
@@ -42,6 +43,7 @@ struct screen_info screen_info = {
 /* The lucky hart to first increment this variable will boot the other cores */
 atomic_t hart_lottery;
 unsigned long boot_cpu_hartid;
+static DEFINE_PER_CPU(struct cpu, cpu_devices);
 
 void __init parse_dtb(void)
 {
@@ -89,3 +91,18 @@ void __init setup_arch(char **cmdline_p)
 
 	riscv_fill_hwcap();
 }
+
+static int __init topology_init(void)
+{
+	int i;
+
+	for_each_possible_cpu(i) {
+		struct cpu *cpu = &per_cpu(cpu_devices, i);
+
+		cpu->hotpluggable = cpu_has_hotplug(i);
+		register_cpu(cpu, i);
+	}
+
+	return 0;
+}
+subsys_initcall(topology_init);
-- 
2.24.0