From 32d8ad4e621d6620e925cf540ef1d35aa6fa5a7b Mon Sep 17 00:00:00 2001 From: Brian King Date: Wed, 7 Jul 2010 12:31:02 +0000 Subject: powerpc/pseries: Partition hibernation support Enables support for HMC initiated partition hibernation. This is a firmware assisted hibernation, since the firmware handles writing the memory out to disk, along with other partition information, so we just mimic suspend to ram. Signed-off-by: Brian King Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/Makefile | 4 + arch/powerpc/platforms/pseries/hotplug-cpu.c | 3 + arch/powerpc/platforms/pseries/suspend.c | 214 +++++++++++++++++++++++++++ 3 files changed, 221 insertions(+) create mode 100644 arch/powerpc/platforms/pseries/suspend.c (limited to 'arch/powerpc/platforms/pseries') diff --git a/arch/powerpc/platforms/pseries/Makefile b/arch/powerpc/platforms/pseries/Makefile index 3dbef309bc8d..046ace9c4381 100644 --- a/arch/powerpc/platforms/pseries/Makefile +++ b/arch/powerpc/platforms/pseries/Makefile @@ -26,3 +26,7 @@ obj-$(CONFIG_HCALL_STATS) += hvCall_inst.o obj-$(CONFIG_PHYP_DUMP) += phyp_dump.o obj-$(CONFIG_CMM) += cmm.o obj-$(CONFIG_DTL) += dtl.o + +ifeq ($(CONFIG_PPC_PSERIES),y) +obj-$(CONFIG_SUSPEND) += suspend.o +endif diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index 8f85f399ab9f..bbe507635364 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -116,6 +116,9 @@ static void pseries_mach_cpu_die(void) if (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) { set_cpu_current_state(cpu, CPU_STATE_INACTIVE); + if (ppc_md.suspend_disable_cpu) + ppc_md.suspend_disable_cpu(); + cede_latency_hint = 2; get_lppaca()->idle = 1; diff --git a/arch/powerpc/platforms/pseries/suspend.c b/arch/powerpc/platforms/pseries/suspend.c new file mode 100644 index 000000000000..ed72098bb4e3 --- /dev/null +++ b/arch/powerpc/platforms/pseries/suspend.c @@ -0,0 +1,214 @@ +/* + * Copyright (C) 2010 Brian King IBM Corporation + * + * 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. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA + */ + +#include +#include +#include +#include +#include +#include +#include + +static u64 stream_id; +static struct sys_device suspend_sysdev; +static DECLARE_COMPLETION(suspend_work); +static struct rtas_suspend_me_data suspend_data; +static atomic_t suspending; + +/** + * pseries_suspend_begin - First phase of hibernation + * + * Check to ensure we are in a valid state to hibernate + * + * Return value: + * 0 on success / other on failure + **/ +static int pseries_suspend_begin(suspend_state_t state) +{ + long vasi_state, rc; + unsigned long retbuf[PLPAR_HCALL_BUFSIZE]; + + /* Make sure the state is valid */ + rc = plpar_hcall(H_VASI_STATE, retbuf, stream_id); + + vasi_state = retbuf[0]; + + if (rc) { + pr_err("pseries_suspend_begin: vasi_state returned %ld\n",rc); + return rc; + } else if (vasi_state == H_VASI_ENABLED) { + return -EAGAIN; + } else if (vasi_state != H_VASI_SUSPENDING) { + pr_err("pseries_suspend_begin: vasi_state returned state %ld\n", + vasi_state); + return -EIO; + } + + return 0; +} + +/** + * pseries_suspend_cpu - Suspend a single CPU + * + * Makes the H_JOIN call to suspend the CPU + * + **/ +static int pseries_suspend_cpu(void) +{ + if (atomic_read(&suspending)) + return rtas_suspend_cpu(&suspend_data); + return 0; +} + +/** + * pseries_suspend_enter - Final phase of hibernation + * + * Return value: + * 0 on success / other on failure + **/ +static int pseries_suspend_enter(suspend_state_t state) +{ + int rc = rtas_suspend_last_cpu(&suspend_data); + + atomic_set(&suspending, 0); + atomic_set(&suspend_data.done, 1); + return rc; +} + +/** + * pseries_prepare_late - Prepare to suspend all other CPUs + * + * Return value: + * 0 on success / other on failure + **/ +static int pseries_prepare_late(void) +{ + atomic_set(&suspending, 1); + atomic_set(&suspend_data.working, 0); + atomic_set(&suspend_data.done, 0); + atomic_set(&suspend_data.error, 0); + suspend_data.complete = &suspend_work; + INIT_COMPLETION(suspend_work); + return 0; +} + +/** + * store_hibernate - Initiate partition hibernation + * @classdev: sysdev class struct + * @attr: class device attribute struct + * @buf: buffer + * @count: buffer size + * + * Write the stream ID received from the HMC to this file + * to trigger hibernating the partition + * + * Return value: + * number of bytes printed to buffer / other on failure + **/ +static ssize_t store_hibernate(struct sysdev_class *classdev, + struct sysdev_class_attribute *attr, + const char *buf, size_t count) +{ + int rc; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + stream_id = simple_strtoul(buf, NULL, 16); + + do { + rc = pseries_suspend_begin(PM_SUSPEND_MEM); + if (rc == -EAGAIN) + ssleep(1); + } while (rc == -EAGAIN); + + if (!rc) + rc = pm_suspend(PM_SUSPEND_MEM); + + stream_id = 0; + + if (!rc) + rc = count; + return rc; +} + +static SYSDEV_CLASS_ATTR(hibernate, S_IWUSR, NULL, store_hibernate); + +static struct sysdev_class suspend_sysdev_class = { + .name = "power", +}; + +static struct platform_suspend_ops pseries_suspend_ops = { + .valid = suspend_valid_only_mem, + .begin = pseries_suspend_begin, + .prepare_late = pseries_prepare_late, + .enter = pseries_suspend_enter, +}; + +/** + * pseries_suspend_sysfs_register - Register with sysfs + * + * Return value: + * 0 on success / other on failure + **/ +static int pseries_suspend_sysfs_register(struct sys_device *sysdev) +{ + int rc; + + if ((rc = sysdev_class_register(&suspend_sysdev_class))) + return rc; + + sysdev->id = 0; + sysdev->cls = &suspend_sysdev_class; + + if ((rc = sysdev_class_create_file(&suspend_sysdev_class, &attr_hibernate))) + goto class_unregister; + + return 0; + +class_unregister: + sysdev_class_unregister(&suspend_sysdev_class); + return rc; +} + +/** + * pseries_suspend_init - initcall for pSeries suspend + * + * Return value: + * 0 on success / other on failure + **/ +static int __init pseries_suspend_init(void) +{ + int rc; + + if (!machine_is(pseries) || !firmware_has_feature(FW_FEATURE_LPAR)) + return 0; + + suspend_data.token = rtas_token("ibm,suspend-me"); + if (suspend_data.token == RTAS_UNKNOWN_SERVICE) + return 0; + + if ((rc = pseries_suspend_sysfs_register(&suspend_sysdev))) + return rc; + + ppc_md.suspend_disable_cpu = pseries_suspend_cpu; + suspend_set_ops(&pseries_suspend_ops); + return 0; +} + +__initcall(pseries_suspend_init); -- cgit v1.2.3 From 6901c6cca1271d1724fc15e9937e0820e2d2fbd5 Mon Sep 17 00:00:00 2001 From: Kulikov Vasiliy Date: Sat, 3 Jul 2010 06:03:48 +0000 Subject: powerpc/pseries/eeh: Use for_each_pci_dev() Use for_each_pci_dev() to simplify the code. Signed-off-by: Kulikov Vasiliy Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/eeh_cache.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) (limited to 'arch/powerpc/platforms/pseries') diff --git a/arch/powerpc/platforms/pseries/eeh_cache.c b/arch/powerpc/platforms/pseries/eeh_cache.c index 30b987b73c20..8ed0d2d0e1b5 100644 --- a/arch/powerpc/platforms/pseries/eeh_cache.c +++ b/arch/powerpc/platforms/pseries/eeh_cache.c @@ -288,8 +288,7 @@ void __init pci_addr_cache_build(void) spin_lock_init(&pci_io_addr_cache_root.piar_lock); - while ((dev = pci_get_device(PCI_ANY_ID, PCI_ANY_ID, dev)) != NULL) { - + for_each_pci_dev(dev) { pci_addr_cache_insert_device(dev); dn = pci_device_to_OF_node(dev); -- cgit v1.2.3 From b08e281b5ae681abcbc1815c13d4a3eb3df4ff1b Mon Sep 17 00:00:00 2001 From: Mark Nelson Date: Wed, 26 May 2010 21:40:39 +0000 Subject: powerpc/pseries: Rename RAS_VECTOR_OFFSET to RTAS_VECTOR_EXTERNAL_INTERRUPT and move to rtas.h The RAS code has a #define, RAS_VECTOR_OFFSET, that's used in the check-exception RTAS call for the vector offset of the exception. We'll be using this same vector offset for the upcoming IO Event interrupts code (0x500) so let's move it to include/asm/rtas.h and call it RTAS_VECTOR_EXTERNAL_INTERRUPT. Signed-off-by: Mark Nelson Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/include/asm/rtas.h | 3 +++ arch/powerpc/platforms/pseries/ras.c | 5 ++--- 2 files changed, 5 insertions(+), 3 deletions(-) (limited to 'arch/powerpc/platforms/pseries') diff --git a/arch/powerpc/include/asm/rtas.h b/arch/powerpc/include/asm/rtas.h index 8941c54b30ea..3d35f8ae377e 100644 --- a/arch/powerpc/include/asm/rtas.h +++ b/arch/powerpc/include/asm/rtas.h @@ -145,6 +145,9 @@ struct rtas_suspend_me_data { #define RTAS_TYPE_PMGM_CONFIG_CHANGE 0x70 #define RTAS_TYPE_PMGM_SERVICE_PROC 0x71 +/* RTAS check-exception vector offset */ +#define RTAS_VECTOR_EXTERNAL_INTERRUPT 0x500 + struct rtas_error_log { unsigned long version:8; /* Architectural version */ unsigned long severity:3; /* Severity level of error */ diff --git a/arch/powerpc/platforms/pseries/ras.c b/arch/powerpc/platforms/pseries/ras.c index 41a3e9a039ed..a4fc6da87c2e 100644 --- a/arch/powerpc/platforms/pseries/ras.c +++ b/arch/powerpc/platforms/pseries/ras.c @@ -61,7 +61,6 @@ static int ras_check_exception_token; #define EPOW_SENSOR_TOKEN 9 #define EPOW_SENSOR_INDEX 0 -#define RAS_VECTOR_OFFSET 0x500 static irqreturn_t ras_epow_interrupt(int irq, void *dev_id); static irqreturn_t ras_error_interrupt(int irq, void *dev_id); @@ -121,7 +120,7 @@ static irqreturn_t ras_epow_interrupt(int irq, void *dev_id) spin_lock(&ras_log_buf_lock); status = rtas_call(ras_check_exception_token, 6, 1, NULL, - RAS_VECTOR_OFFSET, + RTAS_VECTOR_EXTERNAL_INTERRUPT, irq_map[irq].hwirq, RTAS_EPOW_WARNING | RTAS_POWERMGM_EVENTS, critical, __pa(&ras_log_buf), @@ -156,7 +155,7 @@ static irqreturn_t ras_error_interrupt(int irq, void *dev_id) spin_lock(&ras_log_buf_lock); status = rtas_call(ras_check_exception_token, 6, 1, NULL, - RAS_VECTOR_OFFSET, + RTAS_VECTOR_EXTERNAL_INTERRUPT, irq_map[irq].hwirq, RTAS_INTERNAL_ERROR, 1 /*Time Critical */, __pa(&ras_log_buf), -- cgit v1.2.3 From 68581e9350506dcf0160c3a29dcd21e5a848cda7 Mon Sep 17 00:00:00 2001 From: Mark Nelson Date: Wed, 26 May 2010 20:56:04 +0000 Subject: powerpc/pseries: Add WARN_ON() to request_event_sources_irqs() on irq allocation/request failure At the moment if request_event_sources_irqs() can't allocate or request the interrupt, it just does a KERN_ERR printk. This may be fine for the existing RAS code where if we miss an EPOW event it just means that the event won't be logged and if we miss one of the RAS errors then we could miss an event that we perhaps should take action on. But, for the upcoming IO events code that will use event-sources if we can't allocate or request the interrupt it means we'd potentially miss an interrupt from the device. So, let's add a WARN_ON() in this error case so that we're a bit more vocal when something's amiss. While we're at it, also use pr_err() to neaten the code up a bit. Signed-off-by: Mark Nelson Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/event_sources.c | 23 +++++++++++++++-------- 1 file changed, 15 insertions(+), 8 deletions(-) (limited to 'arch/powerpc/platforms/pseries') diff --git a/arch/powerpc/platforms/pseries/event_sources.c b/arch/powerpc/platforms/pseries/event_sources.c index e889c9d9586a..2605c310166a 100644 --- a/arch/powerpc/platforms/pseries/event_sources.c +++ b/arch/powerpc/platforms/pseries/event_sources.c @@ -41,9 +41,12 @@ void request_event_sources_irqs(struct device_node *np, if (count > 15) break; virqs[count] = irq_create_mapping(NULL, *(opicprop++)); - if (virqs[count] == NO_IRQ) - printk(KERN_ERR "Unable to allocate interrupt " - "number for %s\n", np->full_name); + if (virqs[count] == NO_IRQ) { + pr_err("event-sources: Unable to allocate " + "interrupt number for %s\n", + np->full_name); + WARN_ON(1); + } else count++; @@ -59,9 +62,12 @@ void request_event_sources_irqs(struct device_node *np, virqs[count] = irq_create_of_mapping(oirq.controller, oirq.specifier, oirq.size); - if (virqs[count] == NO_IRQ) - printk(KERN_ERR "Unable to allocate interrupt " - "number for %s\n", np->full_name); + if (virqs[count] == NO_IRQ) { + pr_err("event-sources: Unable to allocate " + "interrupt number for %s\n", + np->full_name); + WARN_ON(1); + } else count++; } @@ -70,8 +76,9 @@ void request_event_sources_irqs(struct device_node *np, /* Now request them */ for (i = 0; i < count; i++) { if (request_irq(virqs[i], handler, 0, name, NULL)) { - printk(KERN_ERR "Unable to request interrupt %d for " - "%s\n", virqs[i], np->full_name); + pr_err("event-sources: Unable to request interrupt " + "%d for %s\n", virqs[i], np->full_name); + WARN_ON(1); return; } } -- cgit v1.2.3 From 74052173177b7f969d9cc0c8f136093e1d447a01 Mon Sep 17 00:00:00 2001 From: Julia Lawall Date: Fri, 14 May 2010 09:30:13 +0000 Subject: powerpc/pseries: Use kstrdup Use kstrdup when the goal of an allocation is copy a string into the allocated region. The semantic patch that makes this change is as follows: (http://coccinelle.lip6.fr/) // @@ expression from,to; expression flag,E1,E2; statement S; @@ - to = kmalloc(strlen(from) + 1,flag); + to = kstrdup(from, flag); ... when != \(from = E1 \| to = E1 \) if (to==NULL || ...) S ... when != \(from = E2 \| to = E2 \) - strcpy(to, from); // Signed-off-by: Julia Lawall Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/reconfig.c | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'arch/powerpc/platforms/pseries') diff --git a/arch/powerpc/platforms/pseries/reconfig.c b/arch/powerpc/platforms/pseries/reconfig.c index 1a58637bcea5..57ddbb43b33a 100644 --- a/arch/powerpc/platforms/pseries/reconfig.c +++ b/arch/powerpc/platforms/pseries/reconfig.c @@ -118,12 +118,10 @@ static int pSeries_reconfig_add_node(const char *path, struct property *proplist if (!np) goto out_err; - np->full_name = kmalloc(strlen(path) + 1, GFP_KERNEL); + np->full_name = kstrdup(path, GFP_KERNEL); if (!np->full_name) goto out_err; - strcpy(np->full_name, path); - np->properties = proplist; of_node_set_flag(np, OF_DYNAMIC); kref_init(&np->kref); -- cgit v1.2.3 From e9ae9dabfc1df26d5eff0102c4d359f534e11087 Mon Sep 17 00:00:00 2001 From: Brian King Date: Wed, 14 Jul 2010 08:48:13 +0000 Subject: powerpc: Remove redundant xics badness warning While testing cpu offlining, we are regularly seeing the WARN_ON go off in xics_ipi_dispatch. It can occur when an IPI gets sent to the CPU while it is going offline. There is already a similar WARN_ON in the handlers for PPC_MSG_CALL_FUNCTION and PPC_MSG_CALL_FUNC_SINGLE, so the warning is not needed in that path. The debugger handler handles this case by simply ignoring IPIs for offline CPUs, so no warning is needed there. And the reschedule IPI, which is what is occurring in our test environment, can be safely ignored, so we can simply remove the WARN_ON from xics_ipi_dispatch. Signed-off-by: Brian King Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/xics.c | 2 -- 1 file changed, 2 deletions(-) (limited to 'arch/powerpc/platforms/pseries') diff --git a/arch/powerpc/platforms/pseries/xics.c b/arch/powerpc/platforms/pseries/xics.c index f19d19468393..5b22b07c8f67 100644 --- a/arch/powerpc/platforms/pseries/xics.c +++ b/arch/powerpc/platforms/pseries/xics.c @@ -549,8 +549,6 @@ static irqreturn_t xics_ipi_dispatch(int cpu) { unsigned long *tgt = &per_cpu(xics_ipi_message, cpu); - WARN_ON(cpu_is_offline(cpu)); - mb(); /* order mmio clearing qirr */ while (*tgt) { if (test_and_clear_bit(PPC_MSG_CALL_FUNCTION, tgt)) { -- cgit v1.2.3 From 940ce422a367c8e65404a5ef1ff5969527a06410 Mon Sep 17 00:00:00 2001 From: Benjamin Herrenschmidt Date: Sat, 31 Jul 2010 15:04:15 +1000 Subject: powerpc/pseries: Increase cpu die timeout In testing SMT disable, we have been regularly seeing the following message: Querying DEAD? cpu %i (%i) shows %i This indicates the current delay in pseries_cpu_die where we wait for the specified CPU to die, is insufficient. Usually, this does not cause a problem, but we've seen this result in BUG_ON's going off in the timer code when we try to migrate the timers off the dead cpu while a timer is still running. Increasing this delay, as is done in this patch, seems to resolve this issue. Signed-off-by: Brian King Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/hotplug-cpu.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'arch/powerpc/platforms/pseries') diff --git a/arch/powerpc/platforms/pseries/hotplug-cpu.c b/arch/powerpc/platforms/pseries/hotplug-cpu.c index bbe507635364..fd50ccd4bac1 100644 --- a/arch/powerpc/platforms/pseries/hotplug-cpu.c +++ b/arch/powerpc/platforms/pseries/hotplug-cpu.c @@ -193,12 +193,12 @@ static void pseries_cpu_die(unsigned int cpu) if (get_preferred_offline_state(cpu) == CPU_STATE_INACTIVE) { cpu_status = 1; - for (tries = 0; tries < 1000; tries++) { + for (tries = 0; tries < 5000; tries++) { if (get_cpu_current_state(cpu) == CPU_STATE_INACTIVE) { cpu_status = 0; break; } - cpu_relax(); + msleep(1); } } else if (get_preferred_offline_state(cpu) == CPU_STATE_OFFLINE) { -- cgit v1.2.3 From ceddee23be9fda04b928aa309fd95931bc4efb96 Mon Sep 17 00:00:00 2001 From: Robert Jennings Date: Thu, 22 Jul 2010 16:43:44 +0000 Subject: powerpc: ONLINE to OFFLINE CPU state transition during removal If a CPU remove is attempted using the 'release' interface on hardware which supports extended cede, the CPU will be put in the INACTIVE state rather than the OFFLINE state due to the default preferred_offline_state in that situation. In the INACTIVE state it will fail to be removed. This patch changes the preferred offline state to OFFLINE when an CPU is in the ONLINE state. After cpu_down() is called in dlpar_offline_cpu() the CPU will be OFFLINE and CPU removal can continue. Signed-off-by: Robert Jennings Signed-off-by: Benjamin Herrenschmidt --- arch/powerpc/platforms/pseries/dlpar.c | 1 + 1 file changed, 1 insertion(+) (limited to 'arch/powerpc/platforms/pseries') diff --git a/arch/powerpc/platforms/pseries/dlpar.c b/arch/powerpc/platforms/pseries/dlpar.c index d71e58584086..227c1c3d585e 100644 --- a/arch/powerpc/platforms/pseries/dlpar.c +++ b/arch/powerpc/platforms/pseries/dlpar.c @@ -463,6 +463,7 @@ static int dlpar_offline_cpu(struct device_node *dn) break; if (get_cpu_current_state(cpu) == CPU_STATE_ONLINE) { + set_preferred_offline_state(cpu, CPU_STATE_OFFLINE); cpu_maps_update_done(); rc = cpu_down(cpu); if (rc) -- cgit v1.2.3