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;
Message-ID: <20220908195111.661824729@redhat.com>
User-Agent: quilt/0.66
Date:   Thu, 08 Sep 2022 16:29:00 -0300
From:   Marcelo Tosatti <mtosatti@redhat.com>
To:     linux-kernel@vger.kernel.org
Cc:     Frederic Weisbecker <frederic@kernel.org>,
        Juri Lelli <juri.lelli@redhat.com>,
        Daniel Bristot de Oliveira <bristot@kernel.org>,
        Prasad Pandit <ppandit@redhat.com>,
        Valentin Schneider <vschneid@redhat.com>,
        Yair Podemsky <ypodemsk@redhat.com>,
        Thomas Gleixner <tglx@linutronix.de>,
        Marcelo Tosatti <mtosatti@redhat.com>
Subject: [RFC PATCH 1/7] cpu isolation: basic block interference infrastructure
References: <20220908192859.546633738@redhat.com>
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Precedence: bulk

There are a number of codepaths in the kernel that interrupt
code execution in remote CPUs. A subset of such codepaths are
triggered from userspace and can therefore return errors.

Introduce a cpumask named "block interference", writable from userspace.

This cpumask (and associated helpers) can be used by code that executes
code on remote CPUs to optionally return an error.

Signed-off-by: Marcelo Tosatti <mtosatti@redhat.com>

Index: linux-2.6/include/linux/sched/isolation.h
===================================================================
--- linux-2.6.orig/include/linux/sched/isolation.h
+++ linux-2.6/include/linux/sched/isolation.h
@@ -58,4 +58,33 @@ static inline bool housekeeping_cpu(int
 	return true;
 }
 
+#ifdef CONFIG_CPU_ISOLATION
+extern cpumask_var_t block_interf_cpumask;
+extern bool block_interf_cpumask_active;
+
+void block_interf_read_lock(void);
+void block_interf_read_unlock(void);
+
+void block_interf_write_lock(void);
+void block_interf_write_unlock(void);
+
+void block_interf_assert_held(void);
+
+#else
+static inline void block_interf_read_lock(void)		{ }
+static inline void block_interf_read_unlock(void)	{ }
+static inline void block_interf_write_lock(void)	{ }
+static inline void block_interf_write_unlock(void)	{ }
+static inline void block_interf_assert_held(void)	{ }
+#endif
+
+static inline bool block_interf_cpu(int cpu)
+{
+#ifdef CONFIG_CPU_ISOLATION
+	if (block_interf_cpumask_active)
+		return cpumask_test_cpu(cpu, block_interf_cpumask);
+#endif
+	return false;
+}
+
 #endif /* _LINUX_SCHED_ISOLATION_H */
Index: linux-2.6/kernel/sched/isolation.c
===================================================================
--- linux-2.6.orig/kernel/sched/isolation.c
+++ linux-2.6/kernel/sched/isolation.c
@@ -239,3 +239,116 @@ static int __init housekeeping_isolcpus_
 	return housekeeping_setup(str, flags);
 }
 __setup("isolcpus=", housekeeping_isolcpus_setup);
+
+DEFINE_STATIC_PERCPU_RWSEM(block_interf_lock);
+
+cpumask_var_t block_interf_cpumask;
+EXPORT_SYMBOL_GPL(block_interf_cpumask);
+
+bool block_interf_cpumask_active;
+EXPORT_SYMBOL_GPL(block_interf_cpumask_active);
+
+void block_interf_read_lock(void)
+{
+	percpu_down_read(&block_interf_lock);
+}
+EXPORT_SYMBOL_GPL(block_interf_read_lock);
+
+void block_interf_read_unlock(void)
+{
+	percpu_up_read(&block_interf_lock);
+}
+EXPORT_SYMBOL_GPL(block_interf_read_unlock);
+
+void block_interf_write_lock(void)
+{
+	percpu_down_write(&block_interf_lock);
+}
+EXPORT_SYMBOL_GPL(block_interf_write_lock);
+
+void block_interf_write_unlock(void)
+{
+	percpu_up_write(&block_interf_lock);
+}
+EXPORT_SYMBOL_GPL(block_interf_write_unlock);
+
+void block_interf_assert_held(void)
+{
+	percpu_rwsem_assert_held(&block_interf_lock);
+}
+EXPORT_SYMBOL_GPL(block_interf_assert_held);
+
+static ssize_t
+block_interf_cpumask_read(struct file *filp, char __user *ubuf,
+		     size_t count, loff_t *ppos)
+{
+	char *mask_str;
+	int len;
+
+	len = snprintf(NULL, 0, "%*pb\n",
+		       cpumask_pr_args(block_interf_cpumask)) + 1;
+	mask_str = kmalloc(len, GFP_KERNEL);
+	if (!mask_str)
+		return -ENOMEM;
+
+	len = snprintf(mask_str, len, "%*pb\n",
+		       cpumask_pr_args(block_interf_cpumask));
+	if (len >= count) {
+		count = -EINVAL;
+		goto out_err;
+	}
+	count = simple_read_from_buffer(ubuf, count, ppos, mask_str, len);
+
+out_err:
+	kfree(mask_str);
+
+	return count;
+}
+
+static ssize_t
+block_interf_cpumask_write(struct file *filp, const char __user *ubuf,
+			   size_t count, loff_t *ppos)
+{
+	cpumask_var_t block_interf_cpumask_new;
+	int err;
+
+	if (!zalloc_cpumask_var(&block_interf_cpumask_new, GFP_KERNEL))
+		return -ENOMEM;
+
+	err = cpumask_parse_user(ubuf, count, block_interf_cpumask_new);
+	if (err)
+		goto err_free;
+
+	block_interf_write_lock();
+	cpumask_copy(block_interf_cpumask, block_interf_cpumask_new);
+	block_interf_write_unlock();
+	free_cpumask_var(block_interf_cpumask_new);
+
+	return count;
+
+err_free:
+	free_cpumask_var(block_interf_cpumask_new);
+
+	return err;
+}
+
+static const struct file_operations block_interf_cpumask_fops = {
+	.read		= block_interf_cpumask_read,
+	.write		= block_interf_cpumask_write,
+};
+
+
+static int __init block_interf_cpumask_init(void)
+{
+	if (!zalloc_cpumask_var(&block_interf_cpumask, GFP_KERNEL))
+		return -ENOMEM;
+
+	debugfs_create_file_unsafe("block_interf_cpumask", 0644, NULL, NULL,
+				   &block_interf_cpumask_fops);
+
+	block_interf_cpumask_active = true;
+	return 0;
+}
+
+late_initcall(block_interf_cpumask_init);
+