linux/drivers/xen/xen-acpi-memhotplug.c

486 lines
12 KiB
C
Raw Normal View History

/*
* Copyright (C) 2012 Intel Corporation
* Author: Liu Jinsong <jinsong.liu@intel.com>
* Author: Jiang Yunhong <yunhong.jiang@intel.com>
*
* This program is free software; you can redistribute it and/or modify
* it under the terms of the GNU General Public License as published by
* the Free Software Foundation; either version 2 of the License, or (at
* your option) any later version.
*
* This program is distributed in the hope that it will be useful, but
* WITHOUT ANY WARRANTY; without even the implied warranty of
* MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE, GOOD TITLE or
* NON INFRINGEMENT. See the GNU General Public License for more
* details.
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#include <linux/kernel.h>
#include <linux/module.h>
#include <linux/init.h>
#include <linux/types.h>
#include <linux/acpi.h>
#include <xen/acpi.h>
#include <xen/interface/platform.h>
#include <asm/xen/hypercall.h>
#define PREFIX "ACPI:xen_memory_hotplug:"
struct acpi_memory_info {
struct list_head list;
u64 start_addr; /* Memory Range start physical addr */
u64 length; /* Memory Range length */
unsigned short caching; /* memory cache attribute */
unsigned short write_protect; /* memory read/write attribute */
/* copied from buffer getting from _CRS */
unsigned int enabled:1;
};
struct acpi_memory_device {
struct acpi_device *device;
struct list_head res_list;
};
static bool acpi_hotmem_initialized __read_mostly;
static int xen_hotadd_memory(int pxm, struct acpi_memory_info *info)
{
int rc;
struct xen_platform_op op;
op.cmd = XENPF_mem_hotadd;
op.u.mem_add.spfn = info->start_addr >> PAGE_SHIFT;
op.u.mem_add.epfn = (info->start_addr + info->length) >> PAGE_SHIFT;
op.u.mem_add.pxm = pxm;
rc = HYPERVISOR_dom0_op(&op);
if (rc)
pr_err(PREFIX "Xen Hotplug Memory Add failed on "
"0x%lx -> 0x%lx, _PXM: %d, error: %d\n",
(unsigned long)info->start_addr,
(unsigned long)(info->start_addr + info->length),
pxm, rc);
return rc;
}
static int xen_acpi_memory_enable_device(struct acpi_memory_device *mem_device)
{
int pxm, result;
int num_enabled = 0;
struct acpi_memory_info *info;
if (!mem_device)
return -EINVAL;
pxm = xen_acpi_get_pxm(mem_device->device->handle);
if (pxm < 0)
return pxm;
list_for_each_entry(info, &mem_device->res_list, list) {
if (info->enabled) { /* just sanity check...*/
num_enabled++;
continue;
}
if (!info->length)
continue;
result = xen_hotadd_memory(pxm, info);
if (result)
continue;
info->enabled = 1;
num_enabled++;
}
if (!num_enabled)
return -ENODEV;
return 0;
}
static acpi_status
acpi_memory_get_resource(struct acpi_resource *resource, void *context)
{
struct acpi_memory_device *mem_device = context;
struct acpi_resource_address64 address64;
struct acpi_memory_info *info, *new;
acpi_status status;
status = acpi_resource_to_address64(resource, &address64);
if (ACPI_FAILURE(status) ||
(address64.resource_type != ACPI_MEMORY_RANGE))
return AE_OK;
list_for_each_entry(info, &mem_device->res_list, list) {
if ((info->caching == address64.info.mem.caching) &&
(info->write_protect == address64.info.mem.write_protect) &&
(info->start_addr + info->length == address64.address.minimum)) {
info->length += address64.address.address_length;
return AE_OK;
}
}
new = kzalloc(sizeof(struct acpi_memory_info), GFP_KERNEL);
if (!new)
return AE_ERROR;
INIT_LIST_HEAD(&new->list);
new->caching = address64.info.mem.caching;
new->write_protect = address64.info.mem.write_protect;
new->start_addr = address64.address.minimum;
new->length = address64.address.address_length;
list_add_tail(&new->list, &mem_device->res_list);
return AE_OK;
}
static int
acpi_memory_get_device_resources(struct acpi_memory_device *mem_device)
{
acpi_status status;
struct acpi_memory_info *info, *n;
if (!list_empty(&mem_device->res_list))
return 0;
status = acpi_walk_resources(mem_device->device->handle,
METHOD_NAME__CRS, acpi_memory_get_resource, mem_device);
if (ACPI_FAILURE(status)) {
list_for_each_entry_safe(info, n, &mem_device->res_list, list)
kfree(info);
INIT_LIST_HEAD(&mem_device->res_list);
return -EINVAL;
}
return 0;
}
static int acpi_memory_get_device(acpi_handle handle,
struct acpi_memory_device **mem_device)
{
struct acpi_device *device = NULL;
int result = 0;
acpi_scan_lock_acquire();
acpi_bus_get_device(handle, &device);
ACPI / scan: Add acpi_device objects for all device nodes in the namespace Modify the ACPI namespace scanning code to register a struct acpi_device object for every namespace node representing a device, processor and so on, even if the device represented by that namespace node is reported to be not present and not functional by _STA. There are multiple reasons to do that. First of all, it avoids quite a lot of overhead when struct acpi_device objects are deleted every time acpi_bus_trim() is run and then added again by a subsequent acpi_bus_scan() for the same scope, although the namespace objects they correspond to stay in memory all the time (which always is the case on a vast majority of systems). Second, it will allow user space to see that there are namespace nodes representing devices that are not present at the moment and may be added to the system. It will also allow user space to evaluate _SUN for those nodes to check what physical slots the "missing" devices may be put into and it will make sense to add a sysfs attribute for _STA evaluation after this change (that will be useful for thermal management on some systems). Next, it will help to consolidate the ACPI hotplug handling among subsystems by making it possible to store hotplug-related information in struct acpi_device objects in a standard common way. Finally, it will help to avoid a race condition related to the deletion of ACPI namespace nodes. Namely, namespace nodes may be deleted as a result of a table unload triggered by _EJ0 or _DCK. If a hotplug notification for one of those nodes is triggered right before the deletion and it executes a hotplug callback via acpi_hotplug_execute(), the ACPI handle passed to that callback may be stale when the callback actually runs. One way to work around that is to always pass struct acpi_device pointers to hotplug callbacks after doing a get_device() on the objects in question which eliminates the use-after-free possibility (the ACPI handles in those objects are invalidated by acpi_scan_drop_device(), so they will trigger ACPICA errors on attempts to use them). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Tested-by: Mika Westerberg <mika.westerberg@linux.intel.com>
2013-11-23 04:54:37 +08:00
if (acpi_device_enumerated(device))
goto end;
/*
* Now add the notified device. This creates the acpi_device
* and invokes .add function
*/
Features: - Xen ACPI memory and CPU hotplug drivers - allowing Xen hypervisor to be aware of new CPU and new DIMMs - Cleanups Bug-fixes: - Fixes a long-standing bug in the PV spinlock wherein we did not kick VCPUs that were in a tight loop. - Fixes in the error paths for the event channel machinery. -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.13 (GNU/Linux) iQEcBAABAgAGBQJRJS1kAAoJEFjIrFwIi8fJj2YIAMO3/LVUZyojX/d8U9pqrCly lFfEF2UVjcxHJSj0ZFNXt1o3fnYP1SLRlT9u7ZLDjXf6Lmxmw6/C3Haw2wp3DfGq yUR0G/X9CPTBEgMYDdX7bjeTjyURvZcUaFwr+qodaaeL3uXx2pW6621Sc6jRKuia yAFVZMAKeaRrvUUIXjKHtlpRp9LKFdSztShMtYqmFvxEwrJPq2b37caKruoUCa6o X/YO0fvE9QtYD/pG0jsghFmLh/mcr+n9IFMCUXo1Yc9FdQBExtKzABDS5jdpuFND 4aMDE3dqUmHmpbaQhRE7SdblvpyrGdQXL6FSTjvwBgISfLo847CrnRKRgPp0YeA= =LQeU -----END PGP SIGNATURE----- Merge tag 'stable/for-linus-3.9-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen Pull Xen update from Konrad Rzeszutek Wilk: "This has two new ACPI drivers for Xen - a physical CPU offline/online and a memory hotplug. The way this works is that ACPI kicks the drivers and they make the appropiate hypercall to the hypervisor to tell it that there is a new CPU or memory. There also some changes to the Xen ARM ABIs and couple of fixes. One particularly nasty bug in the Xen PV spinlock code was fixed by Stefan Bader - and has been there since the 2.6.32! Features: - Xen ACPI memory and CPU hotplug drivers - allowing Xen hypervisor to be aware of new CPU and new DIMMs - Cleanups Bug-fixes: - Fixes a long-standing bug in the PV spinlock wherein we did not kick VCPUs that were in a tight loop. - Fixes in the error paths for the event channel machinery" Fix up a few semantic conflicts with the ACPI interface changes in drivers/xen/xen-acpi-{cpu,mem}hotplug.c. * tag 'stable/for-linus-3.9-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen: xen: event channel arrays are xen_ulong_t and not unsigned long xen: Send spinlock IPI to all waiters xen: introduce xen_remap, use it instead of ioremap xen: close evtchn port if binding to irq fails xen-evtchn: correct comment and error output xen/tmem: Add missing %s in the printk statement. xen/acpi: move xen_acpi_get_pxm under CONFIG_XEN_DOM0 xen/acpi: ACPI cpu hotplug xen/acpi: Move xen_acpi_get_pxm to Xen's acpi.h xen/stub: driver for CPU hotplug xen/acpi: ACPI memory hotplug xen/stub: driver for memory hotplug xen: implement updated XENMEM_add_to_physmap_range ABI xen/smp: Move the common CPU init code a bit to prep for PVH patch.
2013-02-25 08:06:13 +08:00
result = acpi_bus_scan(handle);
if (result) {
pr_warn(PREFIX "ACPI namespace scan failed\n");
result = -EINVAL;
goto out;
}
ACPI / scan: Add acpi_device objects for all device nodes in the namespace Modify the ACPI namespace scanning code to register a struct acpi_device object for every namespace node representing a device, processor and so on, even if the device represented by that namespace node is reported to be not present and not functional by _STA. There are multiple reasons to do that. First of all, it avoids quite a lot of overhead when struct acpi_device objects are deleted every time acpi_bus_trim() is run and then added again by a subsequent acpi_bus_scan() for the same scope, although the namespace objects they correspond to stay in memory all the time (which always is the case on a vast majority of systems). Second, it will allow user space to see that there are namespace nodes representing devices that are not present at the moment and may be added to the system. It will also allow user space to evaluate _SUN for those nodes to check what physical slots the "missing" devices may be put into and it will make sense to add a sysfs attribute for _STA evaluation after this change (that will be useful for thermal management on some systems). Next, it will help to consolidate the ACPI hotplug handling among subsystems by making it possible to store hotplug-related information in struct acpi_device objects in a standard common way. Finally, it will help to avoid a race condition related to the deletion of ACPI namespace nodes. Namely, namespace nodes may be deleted as a result of a table unload triggered by _EJ0 or _DCK. If a hotplug notification for one of those nodes is triggered right before the deletion and it executes a hotplug callback via acpi_hotplug_execute(), the ACPI handle passed to that callback may be stale when the callback actually runs. One way to work around that is to always pass struct acpi_device pointers to hotplug callbacks after doing a get_device() on the objects in question which eliminates the use-after-free possibility (the ACPI handles in those objects are invalidated by acpi_scan_drop_device(), so they will trigger ACPICA errors on attempts to use them). Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> Tested-by: Mika Westerberg <mika.westerberg@linux.intel.com>
2013-11-23 04:54:37 +08:00
device = NULL;
acpi_bus_get_device(handle, &device);
if (!acpi_device_enumerated(device)) {
pr_warn(PREFIX "Missing device object\n");
result = -EINVAL;
goto out;
}
end:
*mem_device = acpi_driver_data(device);
if (!(*mem_device)) {
pr_err(PREFIX "driver data not found\n");
result = -ENODEV;
goto out;
}
out:
acpi_scan_lock_release();
return result;
}
static int acpi_memory_check_device(struct acpi_memory_device *mem_device)
{
unsigned long long current_status;
/* Get device present/absent information from the _STA */
if (ACPI_FAILURE(acpi_evaluate_integer(mem_device->device->handle,
"_STA", NULL, &current_status)))
return -ENODEV;
/*
* Check for device status. Device should be
* present/enabled/functioning.
*/
if (!((current_status & ACPI_STA_DEVICE_PRESENT)
&& (current_status & ACPI_STA_DEVICE_ENABLED)
&& (current_status & ACPI_STA_DEVICE_FUNCTIONING)))
return -ENODEV;
return 0;
}
static int acpi_memory_disable_device(struct acpi_memory_device *mem_device)
{
pr_debug(PREFIX "Xen does not support memory hotremove\n");
return -ENOSYS;
}
static void acpi_memory_device_notify(acpi_handle handle, u32 event, void *data)
{
struct acpi_memory_device *mem_device;
struct acpi_device *device;
u32 ost_code = ACPI_OST_SC_NON_SPECIFIC_FAILURE; /* default */
switch (event) {
case ACPI_NOTIFY_BUS_CHECK:
ACPI_DEBUG_PRINT((ACPI_DB_INFO,
"\nReceived BUS CHECK notification for device\n"));
/* Fall Through */
case ACPI_NOTIFY_DEVICE_CHECK:
if (event == ACPI_NOTIFY_DEVICE_CHECK)
ACPI_DEBUG_PRINT((ACPI_DB_INFO,
"\nReceived DEVICE CHECK notification for device\n"));
if (acpi_memory_get_device(handle, &mem_device)) {
pr_err(PREFIX "Cannot find driver data\n");
break;
}
ost_code = ACPI_OST_SC_SUCCESS;
break;
case ACPI_NOTIFY_EJECT_REQUEST:
ACPI_DEBUG_PRINT((ACPI_DB_INFO,
"\nReceived EJECT REQUEST notification for device\n"));
acpi_scan_lock_acquire();
if (acpi_bus_get_device(handle, &device)) {
acpi_scan_lock_release();
pr_err(PREFIX "Device doesn't exist\n");
break;
}
mem_device = acpi_driver_data(device);
if (!mem_device) {
acpi_scan_lock_release();
pr_err(PREFIX "Driver Data is NULL\n");
break;
}
/*
* TBD: implement acpi_memory_disable_device and invoke
* acpi_bus_remove if Xen support hotremove in the future
*/
acpi_memory_disable_device(mem_device);
acpi_scan_lock_release();
break;
default:
ACPI_DEBUG_PRINT((ACPI_DB_INFO,
"Unsupported event [0x%x]\n", event));
/* non-hotplug event; possibly handled by other handler */
return;
}
(void) acpi_evaluate_ost(handle, event, ost_code, NULL);
return;
}
static int xen_acpi_memory_device_add(struct acpi_device *device)
{
int result;
struct acpi_memory_device *mem_device = NULL;
if (!device)
return -EINVAL;
mem_device = kzalloc(sizeof(struct acpi_memory_device), GFP_KERNEL);
if (!mem_device)
return -ENOMEM;
INIT_LIST_HEAD(&mem_device->res_list);
mem_device->device = device;
sprintf(acpi_device_name(device), "%s", ACPI_MEMORY_DEVICE_NAME);
sprintf(acpi_device_class(device), "%s", ACPI_MEMORY_DEVICE_CLASS);
device->driver_data = mem_device;
/* Get the range from the _CRS */
result = acpi_memory_get_device_resources(mem_device);
if (result) {
kfree(mem_device);
return result;
}
/*
* For booting existed memory devices, early boot code has recognized
* memory area by EFI/E820. If DSDT shows these memory devices on boot,
* hotplug is not necessary for them.
* For hot-added memory devices during runtime, it need hypercall to
* Xen hypervisor to add memory.
*/
if (!acpi_hotmem_initialized)
return 0;
if (!acpi_memory_check_device(mem_device))
result = xen_acpi_memory_enable_device(mem_device);
return result;
}
Features: - Xen ACPI memory and CPU hotplug drivers - allowing Xen hypervisor to be aware of new CPU and new DIMMs - Cleanups Bug-fixes: - Fixes a long-standing bug in the PV spinlock wherein we did not kick VCPUs that were in a tight loop. - Fixes in the error paths for the event channel machinery. -----BEGIN PGP SIGNATURE----- Version: GnuPG v1.4.13 (GNU/Linux) iQEcBAABAgAGBQJRJS1kAAoJEFjIrFwIi8fJj2YIAMO3/LVUZyojX/d8U9pqrCly lFfEF2UVjcxHJSj0ZFNXt1o3fnYP1SLRlT9u7ZLDjXf6Lmxmw6/C3Haw2wp3DfGq yUR0G/X9CPTBEgMYDdX7bjeTjyURvZcUaFwr+qodaaeL3uXx2pW6621Sc6jRKuia yAFVZMAKeaRrvUUIXjKHtlpRp9LKFdSztShMtYqmFvxEwrJPq2b37caKruoUCa6o X/YO0fvE9QtYD/pG0jsghFmLh/mcr+n9IFMCUXo1Yc9FdQBExtKzABDS5jdpuFND 4aMDE3dqUmHmpbaQhRE7SdblvpyrGdQXL6FSTjvwBgISfLo847CrnRKRgPp0YeA= =LQeU -----END PGP SIGNATURE----- Merge tag 'stable/for-linus-3.9-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen Pull Xen update from Konrad Rzeszutek Wilk: "This has two new ACPI drivers for Xen - a physical CPU offline/online and a memory hotplug. The way this works is that ACPI kicks the drivers and they make the appropiate hypercall to the hypervisor to tell it that there is a new CPU or memory. There also some changes to the Xen ARM ABIs and couple of fixes. One particularly nasty bug in the Xen PV spinlock code was fixed by Stefan Bader - and has been there since the 2.6.32! Features: - Xen ACPI memory and CPU hotplug drivers - allowing Xen hypervisor to be aware of new CPU and new DIMMs - Cleanups Bug-fixes: - Fixes a long-standing bug in the PV spinlock wherein we did not kick VCPUs that were in a tight loop. - Fixes in the error paths for the event channel machinery" Fix up a few semantic conflicts with the ACPI interface changes in drivers/xen/xen-acpi-{cpu,mem}hotplug.c. * tag 'stable/for-linus-3.9-rc0-tag' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/xen: xen: event channel arrays are xen_ulong_t and not unsigned long xen: Send spinlock IPI to all waiters xen: introduce xen_remap, use it instead of ioremap xen: close evtchn port if binding to irq fails xen-evtchn: correct comment and error output xen/tmem: Add missing %s in the printk statement. xen/acpi: move xen_acpi_get_pxm under CONFIG_XEN_DOM0 xen/acpi: ACPI cpu hotplug xen/acpi: Move xen_acpi_get_pxm to Xen's acpi.h xen/stub: driver for CPU hotplug xen/acpi: ACPI memory hotplug xen/stub: driver for memory hotplug xen: implement updated XENMEM_add_to_physmap_range ABI xen/smp: Move the common CPU init code a bit to prep for PVH patch.
2013-02-25 08:06:13 +08:00
static int xen_acpi_memory_device_remove(struct acpi_device *device)
{
struct acpi_memory_device *mem_device = NULL;
if (!device || !acpi_driver_data(device))
return -EINVAL;
mem_device = acpi_driver_data(device);
kfree(mem_device);
return 0;
}
/*
* Helper function to check for memory device
*/
static acpi_status is_memory_device(acpi_handle handle)
{
char *hardware_id;
acpi_status status;
struct acpi_device_info *info;
status = acpi_get_object_info(handle, &info);
if (ACPI_FAILURE(status))
return status;
if (!(info->valid & ACPI_VALID_HID)) {
kfree(info);
return AE_ERROR;
}
hardware_id = info->hardware_id.string;
if ((hardware_id == NULL) ||
(strcmp(hardware_id, ACPI_MEMORY_DEVICE_HID)))
status = AE_ERROR;
kfree(info);
return status;
}
static acpi_status
acpi_memory_register_notify_handler(acpi_handle handle,
u32 level, void *ctxt, void **retv)
{
acpi_status status;
status = is_memory_device(handle);
if (ACPI_FAILURE(status))
return AE_OK; /* continue */
status = acpi_install_notify_handler(handle, ACPI_SYSTEM_NOTIFY,
acpi_memory_device_notify, NULL);
/* continue */
return AE_OK;
}
static acpi_status
acpi_memory_deregister_notify_handler(acpi_handle handle,
u32 level, void *ctxt, void **retv)
{
acpi_status status;
status = is_memory_device(handle);
if (ACPI_FAILURE(status))
return AE_OK; /* continue */
status = acpi_remove_notify_handler(handle,
ACPI_SYSTEM_NOTIFY,
acpi_memory_device_notify);
return AE_OK; /* continue */
}
static const struct acpi_device_id memory_device_ids[] = {
{ACPI_MEMORY_DEVICE_HID, 0},
{"", 0},
};
MODULE_DEVICE_TABLE(acpi, memory_device_ids);
static struct acpi_driver xen_acpi_memory_device_driver = {
.name = "acpi_memhotplug",
.class = ACPI_MEMORY_DEVICE_CLASS,
.ids = memory_device_ids,
.ops = {
.add = xen_acpi_memory_device_add,
.remove = xen_acpi_memory_device_remove,
},
};
static int __init xen_acpi_memory_device_init(void)
{
int result;
acpi_status status;
if (!xen_initial_domain())
return -ENODEV;
/* unregister the stub which only used to reserve driver space */
xen_stub_memory_device_exit();
result = acpi_bus_register_driver(&xen_acpi_memory_device_driver);
if (result < 0) {
xen_stub_memory_device_init();
return -ENODEV;
}
status = acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT,
ACPI_UINT32_MAX,
acpi_memory_register_notify_handler,
NULL, NULL, NULL);
if (ACPI_FAILURE(status)) {
pr_warn(PREFIX "walk_namespace failed\n");
acpi_bus_unregister_driver(&xen_acpi_memory_device_driver);
xen_stub_memory_device_init();
return -ENODEV;
}
acpi_hotmem_initialized = true;
return 0;
}
static void __exit xen_acpi_memory_device_exit(void)
{
acpi_status status;
if (!xen_initial_domain())
return;
status = acpi_walk_namespace(ACPI_TYPE_DEVICE, ACPI_ROOT_OBJECT,
ACPI_UINT32_MAX,
acpi_memory_deregister_notify_handler,
NULL, NULL, NULL);
if (ACPI_FAILURE(status))
pr_warn(PREFIX "walk_namespace failed\n");
acpi_bus_unregister_driver(&xen_acpi_memory_device_driver);
/*
* stub reserve space again to prevent any chance of native
* driver loading.
*/
xen_stub_memory_device_init();
return;
}
module_init(xen_acpi_memory_device_init);
module_exit(xen_acpi_memory_device_exit);
ACPI_MODULE_NAME("xen-acpi-memhotplug");
MODULE_AUTHOR("Liu Jinsong <jinsong.liu@intel.com>");
MODULE_DESCRIPTION("Xen Hotplug Mem Driver");
MODULE_LICENSE("GPL");