powerpc/pseries: Create new device hotplug entry point

The current hotplug (or dlpar) of devices (the process is generally the
same for memory, cpu, and pci) on PowerVM systems is initiated
from the HMC, which communicates the request to the partitions through
the RSCT framework. The RSCT framework then invokes the drmgr command.
The drmgr command performs the hotplug operation by doing some pieces,
such as most of the rtas calls and device tree parsing, in userspace
and make requests to the kernel to online/offline the device, update the
device tree and add/remove the device.

For PowerKVM the approach for device hotplug is to follow what is currently
being done for pci hotplug. A hotplug request is initiated from the host.
QEMU then generates an EPOW interrupt to the guest which causes the guest
to make the rtas,check-exception call. In QEMU, the rtas,check-exception call
returns a rtas hotplug event to the guest.

Please note that the current pci hotplug path for PowerKVM involves the
kernel receiving the rtas hotplug event, passing it to rtas_errd in
userspace, and having rtas_errd invoke drmgr. The drmgr command then
handles the request as described above for PowerVM systems.

There is no need for this circuitous route, we should just handle the entire
hotplug of devices in the kernel. What I am planning is to enable this
by moving the code to handle hotplug from drmgr into the kernel to
provide a single path for handling device hotplug for both PowerVM and
PowerKVM systems. This patch provides the common iframework and entry point.
For PowerKVM a future update to the kernel rtas code will recognize rtas
hotplug events returned from rtas,check-exception calls and use the common
entry point to handle hotplug of the device.

For PowerVM systems, This patch creates /sys/kernel/dlpar that can be
used by the drmgr command to initiate hotplug requests. In order to do
this a string of the format "<resource> <action> <id_type> <id>" is
written to this file. The string consists of a resource (cpu, memory, pci,
phb), an action (add or remove), an id_type (count, drc index, drc name),
and the corresponding id. The kernel will parse the string and create a
rtas hotplug section that can be passed to the common entry point for
handling hotplug requests.

It should be noted that there is no chance of updating how we receive
hotplug (dlpar) requests from the HMC on PowerVM systems.

Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

1 files changed, 116 insertions, 2 deletions

diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c
index c22bb1b4beb8..b4b11096ea8b 100644
--- a/arch/powerpc/platforms/pseries/dlpar.c
+++ b/arch/powerpc/platforms/pseries/dlpar.c
@@ -10,6 +10,8 @@
  * 2 as published by the Free Software Foundation.
  */
 
+#define pr_fmt(fmt)	"dlpar: " fmt
+
 #include <linux/kernel.h>
 #include <linux/notifier.h>
 #include <linux/spinlock.h>
@@ -535,13 +537,125 @@ static ssize_t dlpar_cpu_release(const char *buf, size_t count)
 	return count;
 }
 
+#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */
+
+static int handle_dlpar_errorlog(struct pseries_hp_errorlog *hp_elog)
+{
+	int rc;
+
+	/* pseries error logs are in BE format, convert to cpu type */
+	switch (hp_elog->id_type) {
+	case PSERIES_HP_ELOG_ID_DRC_COUNT:
+		hp_elog->_drc_u.drc_count =
+					be32_to_cpu(hp_elog->_drc_u.drc_count);
+		break;
+	case PSERIES_HP_ELOG_ID_DRC_INDEX:
+		hp_elog->_drc_u.drc_index =
+					be32_to_cpu(hp_elog->_drc_u.drc_index);
+	}
+
+	switch (hp_elog->resource) {
+	case PSERIES_HP_ELOG_RESOURCE_MEM:
+		rc = dlpar_memory(hp_elog);
+		break;
+	default:
+		pr_warn_ratelimited("Invalid resource (%d) specified\n",
+				    hp_elog->resource);
+		rc = -EINVAL;
+	}
+
+	return rc;
+}
+
+static ssize_t dlpar_store(struct class *class, struct class_attribute *attr,
+			   const char *buf, size_t count)
+{
+	struct pseries_hp_errorlog *hp_elog;
+	const char *arg;
+	int rc;
+
+	hp_elog = kzalloc(sizeof(*hp_elog), GFP_KERNEL);
+	if (!hp_elog) {
+		rc = -ENOMEM;
+		goto dlpar_store_out;
+	}
+
+	/* Parse out the request from the user, this will be in the form
+	 * <resource> <action> <id_type> <id>
+	 */
+	arg = buf;
+	if (!strncmp(arg, "memory", 6)) {
+		hp_elog->resource = PSERIES_HP_ELOG_RESOURCE_MEM;
+		arg += strlen("memory ");
+	} else {
+		pr_err("Invalid resource specified: \"%s\"\n", buf);
+		rc = -EINVAL;
+		goto dlpar_store_out;
+	}
+
+	if (!strncmp(arg, "add", 3)) {
+		hp_elog->action = PSERIES_HP_ELOG_ACTION_ADD;
+		arg += strlen("add ");
+	} else if (!strncmp(arg, "remove", 6)) {
+		hp_elog->action = PSERIES_HP_ELOG_ACTION_REMOVE;
+		arg += strlen("remove ");
+	} else {
+		pr_err("Invalid action specified: \"%s\"\n", buf);
+		rc = -EINVAL;
+		goto dlpar_store_out;
+	}
+
+	if (!strncmp(arg, "index", 5)) {
+		u32 index;
+
+		hp_elog->id_type = PSERIES_HP_ELOG_ID_DRC_INDEX;
+		arg += strlen("index ");
+		if (kstrtou32(arg, 0, &index)) {
+			rc = -EINVAL;
+			pr_err("Invalid drc_index specified: \"%s\"\n", buf);
+			goto dlpar_store_out;
+		}
+
+		hp_elog->_drc_u.drc_index = cpu_to_be32(index);
+	} else if (!strncmp(arg, "count", 5)) {
+		u32 count;
+
+		hp_elog->id_type = PSERIES_HP_ELOG_ID_DRC_COUNT;
+		arg += strlen("count ");
+		if (kstrtou32(arg, 0, &count)) {
+			rc = -EINVAL;
+			pr_err("Invalid count specified: \"%s\"\n", buf);
+			goto dlpar_store_out;
+		}
+
+		hp_elog->_drc_u.drc_count = cpu_to_be32(count);
+	} else {
+		pr_err("Invalid id_type specified: \"%s\"\n", buf);
+		rc = -EINVAL;
+		goto dlpar_store_out;
+	}
+
+	rc = handle_dlpar_errorlog(hp_elog);
+
+dlpar_store_out:
+	kfree(hp_elog);
+	return rc ? rc : count;
+}
+
+static CLASS_ATTR(dlpar, S_IWUSR, NULL, dlpar_store);
+
 static int __init pseries_dlpar_init(void)
 {
+	int rc;
+
+#ifdef CONFIG_ARCH_CPU_PROBE_RELEASE
 	ppc_md.cpu_probe = dlpar_cpu_probe;
 	ppc_md.cpu_release = dlpar_cpu_release;
+#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */
 
-	return 0;
+	rc = sysfs_create_file(kernel_kobj, &class_attr_dlpar.attr);
+
+	return rc;
 }
 machine_device_initcall(pseries, pseries_dlpar_init);
 
-#endif /* CONFIG_ARCH_CPU_PROBE_RELEASE */