[PATCH v7 1/2] x86/sgx: Rename fallback labels in sgx_init()

[PATCH v7 1/2] x86/sgx: Rename fallback labels in sgx_init()

[Jarkko Sakkinen]

It's hard to add new content to this function because it is time
consuming to match fallback and its cause. Rename labels in a way
that the name of error label refers to the site where failure
happened. This way it is easier to keep on track what is going
on.

Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
---
v5:
* A new patch.
---
 arch/x86/kernel/cpu/sgx/main.c | 12 ++++++------
 1 file changed, 6 insertions(+), 6 deletions(-)

diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index 63d3de02bbcc..a6e313f1a82d 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -803,12 +803,12 @@ static int __init sgx_init(void)
 
 	if (!sgx_page_reclaimer_init()) {
 		ret = -ENOMEM;
-		goto err_page_cache;
+		goto err_reclaimer;
 	}
 
 	ret = misc_register(&sgx_dev_provision);
 	if (ret)
-		goto err_kthread;
+		goto err_provision;
 
 	/*
 	 * Always try to initialize the native *and* KVM drivers.
@@ -821,17 +821,17 @@ static int __init sgx_init(void)
 	ret = sgx_drv_init();
 
 	if (sgx_vepc_init() && ret)
-		goto err_provision;
+		goto err_driver;
 
 	return 0;
 
-err_provision:
+err_driver:
 	misc_deregister(&sgx_dev_provision);
 
-err_kthread:
+err_provision:
 	kthread_stop(ksgxd_tsk);
 
-err_page_cache:
+err_reclaimer:
 	for (i = 0; i < sgx_nr_epc_sections; i++) {
 		vfree(sgx_epc_sections[i].pages);
 		memunmap(sgx_epc_sections[i].virt_addr);
-- 
2.25.1

[PATCH v7 2/2] x86/sgx: Add an attribute for the amount of SGX memory in a NUMA node

[Jarkko Sakkinen]

The amount of SGX memory on the system is determined by the BIOS and it
varies wildly between systems.  It can be from dozens of MB's on desktops
or VM's, up to many GB's on servers.  Just like for regular memory, it is
sometimes useful to know the amount of usable SGX memory in the system.

Add an attribute for the amount of SGX memory in bytes to each NUMA
node. The path is /sys/devices/system/node/node[0-9]*/sgx/size.
Calculate these values by summing up EPC section sizes for each node
during the driver initalization.

Signed-off-by: Jarkko Sakkinen <jarkko@kernel.org>
---
v7:
* Shorten memory_size to size. The prefix makes the name only longer
  but does not clarify things more than "size" would.
* Use device_attribute instead of kobj_attribute.
* Use named attribute group instead of creating raw kobject just for
  the "sgx" subdirectory.

v6:
* Initialize node->size to zero in sgx_setup_epc_section(), when the
  node is first accessed.

v5
* A new patch based on the discussion on
  https://lore.kernel.org/linux-sgx/3a7cab4115b4f902f3509ad8652e616b91703e1d.camel@kernel.org/T/#t
---
 Documentation/ABI/stable/sysfs-devices-node |  7 ++
 arch/x86/kernel/cpu/sgx/main.c              | 82 +++++++++++++++++++++
 arch/x86/kernel/cpu/sgx/sgx.h               |  2 +
 3 files changed, 91 insertions(+)

diff --git a/Documentation/ABI/stable/sysfs-devices-node b/Documentation/ABI/stable/sysfs-devices-node
index 484fc04bcc25..12dc2149e8e0 100644
--- a/Documentation/ABI/stable/sysfs-devices-node
+++ b/Documentation/ABI/stable/sysfs-devices-node
@@ -176,3 +176,10 @@ Contact:	Keith Busch <keith.busch@intel.com>
 Description:
 		The cache write policy: 0 for write-back, 1 for write-through,
 		other or unknown.
+
+What:		/sys/devices/system/node/nodeX/sgx/size
+Date:		October 2021
+Contact:	Jarkko Sakkinen <jarkko@kernel.org>
+Description:
+		Total available physical SGX memory, also known as Enclave Page
+		Cache (EPC), in bytes.
diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
index a6e313f1a82d..4a4eb94ee5d2 100644
--- a/arch/x86/kernel/cpu/sgx/main.c
+++ b/arch/x86/kernel/cpu/sgx/main.c
@@ -714,9 +714,11 @@ static bool __init sgx_page_cache_init(void)
 			spin_lock_init(&sgx_numa_nodes[nid].lock);
 			INIT_LIST_HEAD(&sgx_numa_nodes[nid].free_page_list);
 			node_set(nid, sgx_numa_mask);
+			sgx_numa_nodes[nid].size = 0;
 		}
 
 		sgx_epc_sections[i].node =  &sgx_numa_nodes[nid];
+		sgx_numa_nodes[nid].size += size;
 
 		sgx_nr_epc_sections++;
 	}
@@ -790,6 +792,78 @@ int sgx_set_attribute(unsigned long *allowed_attributes,
 }
 EXPORT_SYMBOL_GPL(sgx_set_attribute);
 
+#ifdef CONFIG_NUMA
+static ssize_t size_show(struct device *dev, struct device_attribute *attr, char *buf)
+{
+	unsigned long size = 0;
+	int nid;
+
+	for (nid = 0; nid < num_possible_nodes(); nid++) {
+		if (dev == sgx_numa_nodes[nid].dev) {
+			size = sgx_numa_nodes[nid].size;
+			break;
+		}
+	}
+
+	return sysfs_emit(buf, "%lu\n", size);
+}
+DEVICE_ATTR_RO(size);
+
+static struct attribute *sgx_node_attrs[] = {
+	&dev_attr_size.attr,
+	NULL,
+};
+
+static const struct attribute_group sgx_node_attr_group = {
+	.name = "sgx",
+	.attrs = sgx_node_attrs,
+};
+
+static void sgx_numa_exit(void)
+{
+	struct device *dev;
+	int nid;
+
+	for (nid = 0; nid < num_possible_nodes(); nid++) {
+		dev = &node_devices[nid]->dev;
+		if (dev)
+			sysfs_remove_group(&dev->kobj, &sgx_node_attr_group);
+	}
+}
+
+static bool sgx_numa_init(void)
+{
+	struct sgx_numa_node *node;
+	int nid;
+	int ret;
+
+	for (nid = 0; nid < num_possible_nodes(); nid++) {
+		if (!sgx_numa_nodes[nid].size)
+			continue;
+
+		node = &sgx_numa_nodes[nid];
+		node->dev = &node_devices[nid]->dev;
+
+		ret = sysfs_create_group(&node->dev->kobj, &sgx_node_attr_group);
+		if (ret) {
+			sgx_numa_exit();
+			return false;
+		}
+	}
+
+	return true;
+}
+#else
+static inline void sgx_numa_exit(void)
+{
+}
+
+static inline bool sgx_numa_init(void)
+{
+	return true;
+}
+#endif /* CONFIG_NUMA */
+
 static int __init sgx_init(void)
 {
 	int ret;
@@ -806,6 +880,11 @@ static int __init sgx_init(void)
 		goto err_reclaimer;
 	}
 
+	if (!sgx_numa_init()) {
+		ret = -ENOMEM;
+		goto err_numa_nodes;
+	}
+
 	ret = misc_register(&sgx_dev_provision);
 	if (ret)
 		goto err_provision;
@@ -829,6 +908,9 @@ static int __init sgx_init(void)
 	misc_deregister(&sgx_dev_provision);
 
 err_provision:
+	sgx_numa_exit();
+
+err_numa_nodes:
 	kthread_stop(ksgxd_tsk);
 
 err_reclaimer:
diff --git a/arch/x86/kernel/cpu/sgx/sgx.h b/arch/x86/kernel/cpu/sgx/sgx.h
index 4628acec0009..1de8c627a286 100644
--- a/arch/x86/kernel/cpu/sgx/sgx.h
+++ b/arch/x86/kernel/cpu/sgx/sgx.h
@@ -39,6 +39,8 @@ struct sgx_epc_page {
  */
 struct sgx_numa_node {
 	struct list_head free_page_list;
+	struct device *dev;
+	unsigned long size;
 	spinlock_t lock;
 };
 
-- 
2.25.1

Re: [PATCH v7 2/2] x86/sgx: Add an attribute for the amount of SGX memory in a NUMA node

[Jarkko Sakkinen]

On Fri, 2021-10-08 at 23:33 +0300, Jarkko Sakkinen wrote:
> +static void sgx_numa_exit(void)
> +{
> +       struct device *dev;
> +       int nid;
> +
> +       for (nid = 0; nid < num_possible_nodes(); nid++) {
> +               dev = &node_devices[nid]->dev;
> +               if (dev)
> +                       sysfs_remove_group(&dev->kobj, &sgx_node_attr_group);
> +       }
> +}
> +
> +static bool sgx_numa_init(void)
> +{
> +       struct sgx_numa_node *node;
> +       int nid;
> +       int ret;
> +
> +       for (nid = 0; nid < num_possible_nodes(); nid++) {
> +               if (!sgx_numa_nodes[nid].size)
> +                       continue;
> +
> +               node = &sgx_numa_nodes[nid];
> +               node->dev = &node_devices[nid]->dev;
> +
> +               ret = sysfs_create_group(&node->dev->kobj, &sgx_node_attr_group);
> +               if (ret) {
> +                       sgx_numa_exit();
> +                       return false;
> +               }
> +       }

Here's a mistake: node->dev should be only set after sysfe_create_group().
Otherwise, sysfs_remove_group() will issue a warning in sgx_numa_exit(), when
sgx_create_group() is unsuccessful, because the group does not exist.

I'll fix this, and send a new version.

/Jarkko