| Message ID | 2003756.4bDvk8cJ93@vostro.rjw.lan (mailing list archive) |
|---|---|
| State | Superseded, archived |
| Headers | show |
(2013/12/23 23:00), Rafael J. Wysocki wrote: > From: Rafael J. Wysocki <rafael.j.wysocki@intel.com> > > Add a new ACPI hotplug profile flag, demand_offline, such that if > set for the given ACPI device object's scan handler, it will cause > acpi_scan_hot_remove() to check if that device object's physical > companions are offline upfront and fail the hot removal if that > is not the case. > > That flag will be useful to overcome a problem with containers on > some system where they can only be hot-removed after some cleanup > operations carried out by user space, which needs to be notified > of the container hot-removal before the kernel attempts to offline > devices in the container. In those cases the current implementation > of acpi_scan_hot_remove() is not sufficient, because it first tries > to offline the devices in the container and only if that is > suffcessful it tries to offline the container itself. As a result, > the container hot-removal notification is not delivered to user space > at the right time. > > Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> > --- > drivers/acpi/scan.c | 41 +++++++++++++++++++++++++++++++++++++---- > include/acpi/acpi_bus.h | 3 ++- > 2 files changed, 39 insertions(+), 5 deletions(-) > > Index: linux-pm/drivers/acpi/scan.c > =================================================================== > --- linux-pm.orig/drivers/acpi/scan.c > +++ linux-pm/drivers/acpi/scan.c > @@ -126,6 +126,24 @@ acpi_device_modalias_show(struct device > } > static DEVICE_ATTR(modalias, 0444, acpi_device_modalias_show, NULL); > > +static bool acpi_scan_is_offline(struct acpi_device *adev) > +{ > + struct acpi_device_physical_node *pn; > + bool offline = true; > + > + mutex_lock(&adev->physical_node_lock); > + > + list_for_each_entry(pn, &adev->physical_node_list, node) > + if (!pn->dev->offline) { Please check pn->dev->bus and pn->dev->bus->offline too as follow: if (pn->dev->bus && pn->dev->bus->offline && !pn->dev->offline) { My container has CPU and Memory and PCI root bridge. PCI root bridge does not has offline function (pn->dev->bus->offline). So I cannot offline the device and pn->dev->offline of the device is always 0. Therefore, following operation always returns -EBUSY even if I offline CPUs and all memory sections on a container device. echo 0 > /sys/bus/container/devices/ACPI0004:01/online Thanks, Yasuaki Ishimatsu > + kobject_uevent(&pn->dev->kobj, KOBJ_CHANGE); > + offline = false; > + break; > + } > + > + mutex_unlock(&adev->physical_node_lock); > + return offline; > +} > + > static acpi_status acpi_bus_offline(acpi_handle handle, u32 lvl, void *data, > void **ret_p) > { > @@ -196,12 +214,11 @@ static acpi_status acpi_bus_online(acpi_ > return AE_OK; > } > > -static int acpi_scan_hot_remove(struct acpi_device *device) > +static int acpi_scan_try_to_offline(struct acpi_device *device) > { > acpi_handle handle = device->handle; > - struct device *errdev; > + struct device *errdev = NULL; > acpi_status status; > - unsigned long long sta; > > /* > * Carry out two passes here and ignore errors in the first pass, > @@ -212,7 +229,6 @@ static int acpi_scan_hot_remove(struct a > * > * If the first pass is successful, the second one isn't needed, though. > */ > - errdev = NULL; > status = acpi_walk_namespace(ACPI_TYPE_ANY, handle, ACPI_UINT32_MAX, > NULL, acpi_bus_offline, (void *)false, > (void **)&errdev); > @@ -241,6 +257,23 @@ static int acpi_scan_hot_remove(struct a > return -EBUSY; > } > } > + return 0; > +} > + > +static int acpi_scan_hot_remove(struct acpi_device *device) > +{ > + acpi_handle handle = device->handle; > + unsigned long long sta; > + acpi_status status; > + > + if (device->handler->hotplug.demand_offline && !acpi_force_hot_remove) { > + if (!acpi_scan_is_offline(device)) > + return -EBUSY; > + } else { > + int error = acpi_scan_try_to_offline(device); > + if (error) > + return error; > + } > > ACPI_DEBUG_PRINT((ACPI_DB_INFO, > "Hot-removing device %s...\n", dev_name(&device->dev))); > Index: linux-pm/include/acpi/acpi_bus.h > =================================================================== > --- linux-pm.orig/include/acpi/acpi_bus.h > +++ linux-pm/include/acpi/acpi_bus.h > @@ -91,8 +91,9 @@ struct acpi_device; > > struct acpi_hotplug_profile { > struct kobject kobj; > - bool enabled:1; > int (*scan_dependent)(struct acpi_device *adev); > + bool enabled:1; > + bool demand_offline:1; > }; > > static inline struct acpi_hotplug_profile *to_acpi_hotplug_profile( > -- To unsubscribe from this list: send the line "unsubscribe linux-acpi" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
(2013/12/26 12:10), Yasuaki Ishimatsu wrote: > (2013/12/23 23:00), Rafael J. Wysocki wrote: >> From: Rafael J. Wysocki <rafael.j.wysocki@intel.com> >> >> Add a new ACPI hotplug profile flag, demand_offline, such that if >> set for the given ACPI device object's scan handler, it will cause >> acpi_scan_hot_remove() to check if that device object's physical >> companions are offline upfront and fail the hot removal if that >> is not the case. >> >> That flag will be useful to overcome a problem with containers on >> some system where they can only be hot-removed after some cleanup >> operations carried out by user space, which needs to be notified >> of the container hot-removal before the kernel attempts to offline >> devices in the container. In those cases the current implementation >> of acpi_scan_hot_remove() is not sufficient, because it first tries >> to offline the devices in the container and only if that is >> suffcessful it tries to offline the container itself. As a result, >> the container hot-removal notification is not delivered to user space >> at the right time. >> >> Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> >> --- >> drivers/acpi/scan.c | 41 +++++++++++++++++++++++++++++++++++++---- >> include/acpi/acpi_bus.h | 3 ++- >> 2 files changed, 39 insertions(+), 5 deletions(-) >> >> Index: linux-pm/drivers/acpi/scan.c >> =================================================================== >> --- linux-pm.orig/drivers/acpi/scan.c >> +++ linux-pm/drivers/acpi/scan.c >> @@ -126,6 +126,24 @@ acpi_device_modalias_show(struct device >> } >> static DEVICE_ATTR(modalias, 0444, acpi_device_modalias_show, NULL); >> >> +static bool acpi_scan_is_offline(struct acpi_device *adev) >> +{ >> + struct acpi_device_physical_node *pn; >> + bool offline = true; >> + >> + mutex_lock(&adev->physical_node_lock); >> + >> + list_for_each_entry(pn, &adev->physical_node_list, node) > >> + if (!pn->dev->offline) { > > Please check pn->dev->bus and pn->dev->bus->offline too as follow: > > if (pn->dev->bus && pn->dev->bus->offline && > !pn->dev->offline) { > Adding above check, I could remove container device by using eject sysfs. But following messages were shown: [ 1017.543000] ------------[ cut here ]------------ [ 1017.543000] WARNING: CPU: 0 PID: 6 at drivers/base/core.c:251 device_release+0x92/0xa0() [ 1017.543000] Device 'ACPI0004:01' does not have a release() function, it is broken and must be fixed. [ 1017.653000] Modules linked in: xt_CHECKSUM nf_conntrack_netbios_ns nf_conntrack_broadcast ipt_MASQUERADE ip6t_REJECT ipmi_devintf ipt_REJECT cfg80211 xt_conntrack rfkill ebtable_nat ebtable_broute bridge stp llc ebtable_filter ebtables ip6table_nat nf_conntrack_ipv6 nf_defrag_ipv6 nf_nat_ipv6 ip6table_mangle ip6table_security ip6table_raw ip6table_filter ip6_tables iptable_nat nf_conntrack_ipv4 nf_defrag_ipv4 nf_nat_ipv4 nf_nat nf_conntrack iptable_mangle iptable_security iptable_raw iptable_filter sg ip_tables vfat fat x86_pkg_temp_thermal coretemp iTCO_wdt iTCO_vendor_support kvm_intel kvm crct10dif_pclmul crc32_pclmul crc32c_intel ghash_clmulni_intel aesni_intel lrw gf128mul glue_helper ablk_helper cryptd dm_mirror dm_region_hash dm_log dm_mod microcode lpc_ich igb sb_edac e1000e pcspkr i2c_i801 [ 1017.653000] edac_core mfd_core dca ptp pps_core shpchp ipmi_si ipmi_msghandler tpm_infineon nfsd auth_rpcgss nfs_acl lockd sunrpc xfs libcrc32c sd_mod mgag200 syscopyarea sysfillrect sysimgblt lpfc i2c_algo_bit drm_kms_helper ttm drm crc_t10dif crct10dif_common scsi_transport_fc megaraid_sas i2c_core scsi_tgt [ 1017.653000] CPU: 0 PID: 6 Comm: kworker/u512:0 Tainted: G W 3.13.0-rc5+ #5 [ 1017.653000] Hardware name: [ 1017.653000] Workqueue: kacpi_hotplug acpi_hotplug_work_fn [ 1017.653000] 0000000000000009 ffff880873a6dc68 ffffffff815d85ca ffff880873a6dcb0 [ 1017.653000] ffff880873a6dca0 ffffffff8106594d ffff8a07d221c010 ffff8a07d221c000 [ 1017.653000] ffff8808715472c0 ffff880871e91018 0000000000000103 ffff880873a6dd00 [ 1017.653000] Call Trace: [ 1017.653000] [<ffffffff815d85ca>] dump_stack+0x45/0x56 [ 1017.653000] [<ffffffff8106594d>] warn_slowpath_common+0x7d/0xa0 [ 1017.653000] [<ffffffff810659bc>] warn_slowpath_fmt+0x4c/0x50 [ 1017.653000] [<ffffffff813ad892>] device_release+0x92/0xa0 [ 1017.653000] [<ffffffff812b7197>] kobject_cleanup+0x77/0x1b0 [ 1017.653000] [<ffffffff812b7045>] kobject_put+0x35/0x70 [ 1017.653000] [<ffffffff813ae38c>] device_unregister+0x2c/0x60 [ 1017.653000] [<ffffffff8134c87c>] container_device_detach+0x28/0x2a [ 1017.653000] [<ffffffff81323096>] acpi_bus_trim+0x56/0x89 [ 1017.653000] [<ffffffff813246ae>] acpi_device_hotplug+0x168/0x383 [ 1017.653000] [<ffffffff8131efba>] acpi_hotplug_work_fn+0x1c/0x27 [ 1017.653000] [<ffffffff81080f1b>] process_one_work+0x17b/0x460 [ 1017.653000] [<ffffffff81081ccb>] worker_thread+0x11b/0x400 [ 1017.653000] [<ffffffff81081bb0>] ? rescuer_thread+0x3e0/0x3e0 [ 1017.653000] [<ffffffff81088a12>] kthread+0xd2/0xf0 [ 1017.653000] [<ffffffff81088940>] ? kthread_create_on_node+0x180/0x180 [ 1017.653000] [<ffffffff815e82fc>] ret_from_fork+0x7c/0xb0 [ 1017.653000] [<ffffffff81088940>] ? kthread_create_on_node+0x180/0x180 [ 1017.653000] ---[ end trace 41394323eb4b690a ]--- Thanks, Yasuaki Ishimatsu > My container has CPU and Memory and PCI root bridge. PCI root bridge > does not has offline function (pn->dev->bus->offline). So I cannot offline > the device and pn->dev->offline of the device is always 0. Therefore, > following operation always returns -EBUSY even if I offline CPUs and > all memory sections on a container device. > > echo 0 > /sys/bus/container/devices/ACPI0004:01/online > > Thanks, > Yasuaki Ishimatsu > >> + kobject_uevent(&pn->dev->kobj, KOBJ_CHANGE); >> + offline = false; >> + break; >> + } >> + >> + mutex_unlock(&adev->physical_node_lock); >> + return offline; >> +} >> + >> static acpi_status acpi_bus_offline(acpi_handle handle, u32 lvl, void *data, >> void **ret_p) >> { >> @@ -196,12 +214,11 @@ static acpi_status acpi_bus_online(acpi_ >> return AE_OK; >> } >> >> -static int acpi_scan_hot_remove(struct acpi_device *device) >> +static int acpi_scan_try_to_offline(struct acpi_device *device) >> { >> acpi_handle handle = device->handle; >> - struct device *errdev; >> + struct device *errdev = NULL; >> acpi_status status; >> - unsigned long long sta; >> >> /* >> * Carry out two passes here and ignore errors in the first pass, >> @@ -212,7 +229,6 @@ static int acpi_scan_hot_remove(struct a >> * >> * If the first pass is successful, the second one isn't needed, though. >> */ >> - errdev = NULL; >> status = acpi_walk_namespace(ACPI_TYPE_ANY, handle, ACPI_UINT32_MAX, >> NULL, acpi_bus_offline, (void *)false, >> (void **)&errdev); >> @@ -241,6 +257,23 @@ static int acpi_scan_hot_remove(struct a >> return -EBUSY; >> } >> } >> + return 0; >> +} >> + >> +static int acpi_scan_hot_remove(struct acpi_device *device) >> +{ >> + acpi_handle handle = device->handle; >> + unsigned long long sta; >> + acpi_status status; >> + >> + if (device->handler->hotplug.demand_offline && !acpi_force_hot_remove) { >> + if (!acpi_scan_is_offline(device)) >> + return -EBUSY; >> + } else { >> + int error = acpi_scan_try_to_offline(device); >> + if (error) >> + return error; >> + } >> >> ACPI_DEBUG_PRINT((ACPI_DB_INFO, >> "Hot-removing device %s...\n", dev_name(&device->dev))); >> Index: linux-pm/include/acpi/acpi_bus.h >> =================================================================== >> --- linux-pm.orig/include/acpi/acpi_bus.h >> +++ linux-pm/include/acpi/acpi_bus.h >> @@ -91,8 +91,9 @@ struct acpi_device; >> >> struct acpi_hotplug_profile { >> struct kobject kobj; >> - bool enabled:1; >> int (*scan_dependent)(struct acpi_device *adev); >> + bool enabled:1; >> + bool demand_offline:1; >> }; >> >> static inline struct acpi_hotplug_profile *to_acpi_hotplug_profile( >> > -- To unsubscribe from this list: send the line "unsubscribe linux-acpi" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
On Thursday, December 26, 2013 12:10:04 PM Yasuaki Ishimatsu wrote: > (2013/12/23 23:00), Rafael J. Wysocki wrote: > > From: Rafael J. Wysocki <rafael.j.wysocki@intel.com> > > > > Add a new ACPI hotplug profile flag, demand_offline, such that if > > set for the given ACPI device object's scan handler, it will cause > > acpi_scan_hot_remove() to check if that device object's physical > > companions are offline upfront and fail the hot removal if that > > is not the case. > > > > That flag will be useful to overcome a problem with containers on > > some system where they can only be hot-removed after some cleanup > > operations carried out by user space, which needs to be notified > > of the container hot-removal before the kernel attempts to offline > > devices in the container. In those cases the current implementation > > of acpi_scan_hot_remove() is not sufficient, because it first tries > > to offline the devices in the container and only if that is > > suffcessful it tries to offline the container itself. As a result, > > the container hot-removal notification is not delivered to user space > > at the right time. > > > > Signed-off-by: Rafael J. Wysocki <rafael.j.wysocki@intel.com> > > --- > > drivers/acpi/scan.c | 41 +++++++++++++++++++++++++++++++++++++---- > > include/acpi/acpi_bus.h | 3 ++- > > 2 files changed, 39 insertions(+), 5 deletions(-) > > > > Index: linux-pm/drivers/acpi/scan.c > > =================================================================== > > --- linux-pm.orig/drivers/acpi/scan.c > > +++ linux-pm/drivers/acpi/scan.c > > @@ -126,6 +126,24 @@ acpi_device_modalias_show(struct device > > } > > static DEVICE_ATTR(modalias, 0444, acpi_device_modalias_show, NULL); > > > > +static bool acpi_scan_is_offline(struct acpi_device *adev) > > +{ > > + struct acpi_device_physical_node *pn; > > + bool offline = true; > > + > > + mutex_lock(&adev->physical_node_lock); > > + > > + list_for_each_entry(pn, &adev->physical_node_list, node) > > > + if (!pn->dev->offline) { > > Please check pn->dev->bus and pn->dev->bus->offline too as follow: > > if (pn->dev->bus && pn->dev->bus->offline && > !pn->dev->offline) { > > My container has CPU and Memory and PCI root bridge. PCI root bridge > does not has offline function (pn->dev->bus->offline). So I cannot offline > the device and pn->dev->offline of the device is always 0. Therefore, > following operation always returns -EBUSY even if I offline CPUs and > all memory sections on a container device. > > echo 0 > /sys/bus/container/devices/ACPI0004:01/online I see. We simply can do if (device_supports_offline(pn->dev) && !pn->dev->offline) { there I think. Thanks, Rafael -- To unsubscribe from this list: send the line "unsubscribe linux-acpi" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html
Index: linux-pm/drivers/acpi/scan.c =================================================================== --- linux-pm.orig/drivers/acpi/scan.c +++ linux-pm/drivers/acpi/scan.c @@ -126,6 +126,24 @@ acpi_device_modalias_show(struct device } static DEVICE_ATTR(modalias, 0444, acpi_device_modalias_show, NULL); +static bool acpi_scan_is_offline(struct acpi_device *adev) +{ + struct acpi_device_physical_node *pn; + bool offline = true; + + mutex_lock(&adev->physical_node_lock); + + list_for_each_entry(pn, &adev->physical_node_list, node) + if (!pn->dev->offline) { + kobject_uevent(&pn->dev->kobj, KOBJ_CHANGE); + offline = false; + break; + } + + mutex_unlock(&adev->physical_node_lock); + return offline; +} + static acpi_status acpi_bus_offline(acpi_handle handle, u32 lvl, void *data, void **ret_p) { @@ -196,12 +214,11 @@ static acpi_status acpi_bus_online(acpi_ return AE_OK; } -static int acpi_scan_hot_remove(struct acpi_device *device) +static int acpi_scan_try_to_offline(struct acpi_device *device) { acpi_handle handle = device->handle; - struct device *errdev; + struct device *errdev = NULL; acpi_status status; - unsigned long long sta; /* * Carry out two passes here and ignore errors in the first pass, @@ -212,7 +229,6 @@ static int acpi_scan_hot_remove(struct a * * If the first pass is successful, the second one isn't needed, though. */ - errdev = NULL; status = acpi_walk_namespace(ACPI_TYPE_ANY, handle, ACPI_UINT32_MAX, NULL, acpi_bus_offline, (void *)false, (void **)&errdev); @@ -241,6 +257,23 @@ static int acpi_scan_hot_remove(struct a return -EBUSY; } } + return 0; +} + +static int acpi_scan_hot_remove(struct acpi_device *device) +{ + acpi_handle handle = device->handle; + unsigned long long sta; + acpi_status status; + + if (device->handler->hotplug.demand_offline && !acpi_force_hot_remove) { + if (!acpi_scan_is_offline(device)) + return -EBUSY; + } else { + int error = acpi_scan_try_to_offline(device); + if (error) + return error; + } ACPI_DEBUG_PRINT((ACPI_DB_INFO, "Hot-removing device %s...\n", dev_name(&device->dev))); Index: linux-pm/include/acpi/acpi_bus.h =================================================================== --- linux-pm.orig/include/acpi/acpi_bus.h +++ linux-pm/include/acpi/acpi_bus.h @@ -91,8 +91,9 @@ struct acpi_device; struct acpi_hotplug_profile { struct kobject kobj; - bool enabled:1; int (*scan_dependent)(struct acpi_device *adev); + bool enabled:1; + bool demand_offline:1; }; static inline struct acpi_hotplug_profile *to_acpi_hotplug_profile(