* [PATCH 1/3] powerpc: Add VPHN firmware feature
2010-10-29 0:27 [PATCH 0/3][RFC][REPOST] Add Support for Virtual Processor Home Node (VPHN) Jesse Larrew
@ 2010-10-29 0:28 ` Jesse Larrew
2010-10-29 0:30 ` [PATCH 3/3] powerpc: Disable VPHN polling during a suspend operation Jesse Larrew
2010-10-29 0:33 ` [PATCH 2/3] powerpc: Poll VPA for topology changes and update NUMA maps Jesse Larrew
2 siblings, 0 replies; 6+ messages in thread
From: Jesse Larrew @ 2010-10-29 0:28 UTC (permalink / raw)
To: linuxppc-dev; +Cc: markn, pmac, tbreeds, lkessler, Jesse Larrew, mjwolf
From: Jesse Larrew <jlarrew@linux.vnet.ibm.com>
This simple patch adds the firmware feature for VPHN to the firmware
features bitmask.
Signed-off-by: Jesse Larrew <jlarrew@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/firmware.h | 3 ++-
arch/powerpc/include/asm/hvcall.h | 3 ++-
arch/powerpc/platforms/pseries/firmware.c | 1 +
3 files changed, 5 insertions(+), 2 deletions(-)
diff --git a/arch/powerpc/include/asm/firmware.h b/arch/powerpc/include/asm/firmware.h
index 20778a4..4ef662e 100644
--- a/arch/powerpc/include/asm/firmware.h
+++ b/arch/powerpc/include/asm/firmware.h
@@ -46,6 +46,7 @@
#define FW_FEATURE_PS3_LV1 ASM_CONST(0x0000000000800000)
#define FW_FEATURE_BEAT ASM_CONST(0x0000000001000000)
#define FW_FEATURE_CMO ASM_CONST(0x0000000002000000)
+#define FW_FEATURE_VPHN ASM_CONST(0x0000000004000000)
#ifndef __ASSEMBLY__
@@ -59,7 +60,7 @@ enum {
FW_FEATURE_VIO | FW_FEATURE_RDMA | FW_FEATURE_LLAN |
FW_FEATURE_BULK_REMOVE | FW_FEATURE_XDABR |
FW_FEATURE_MULTITCE | FW_FEATURE_SPLPAR | FW_FEATURE_LPAR |
- FW_FEATURE_CMO,
+ FW_FEATURE_CMO | FW_FEATURE_VPHN,
FW_FEATURE_PSERIES_ALWAYS = 0,
FW_FEATURE_ISERIES_POSSIBLE = FW_FEATURE_ISERIES | FW_FEATURE_LPAR,
FW_FEATURE_ISERIES_ALWAYS = FW_FEATURE_ISERIES | FW_FEATURE_LPAR,
diff --git a/arch/powerpc/include/asm/hvcall.h b/arch/powerpc/include/asm/hvcall.h
index de03ca5..6de1e5f 100644
--- a/arch/powerpc/include/asm/hvcall.h
+++ b/arch/powerpc/include/asm/hvcall.h
@@ -232,7 +232,8 @@
#define H_GET_EM_PARMS 0x2B8
#define H_SET_MPP 0x2D0
#define H_GET_MPP 0x2D4
-#define MAX_HCALL_OPCODE H_GET_MPP
+#define H_HOME_NODE_ASSOCIATIVITY 0x2EC
+#define MAX_HCALL_OPCODE H_HOME_NODE_ASSOCIATIVITY
#ifndef __ASSEMBLY__
diff --git a/arch/powerpc/platforms/pseries/firmware.c b/arch/powerpc/platforms/pseries/firmware.c
index 0a14d8c..0b0eff0 100644
--- a/arch/powerpc/platforms/pseries/firmware.c
+++ b/arch/powerpc/platforms/pseries/firmware.c
@@ -55,6 +55,7 @@ firmware_features_table[FIRMWARE_MAX_FEATURES] = {
{FW_FEATURE_XDABR, "hcall-xdabr"},
{FW_FEATURE_MULTITCE, "hcall-multi-tce"},
{FW_FEATURE_SPLPAR, "hcall-splpar"},
+ {FW_FEATURE_VPHN, "hcall-vphn"},
};
/* Build up the firmware features bitmask using the contents of
--
1.7.2.3
^ permalink raw reply related [flat|nested] 6+ messages in thread* [PATCH 3/3] powerpc: Disable VPHN polling during a suspend operation
2010-10-29 0:27 [PATCH 0/3][RFC][REPOST] Add Support for Virtual Processor Home Node (VPHN) Jesse Larrew
2010-10-29 0:28 ` [PATCH 1/3] powerpc: Add VPHN firmware feature Jesse Larrew
@ 2010-10-29 0:30 ` Jesse Larrew
2010-11-03 12:12 ` Michael Ellerman
2010-10-29 0:33 ` [PATCH 2/3] powerpc: Poll VPA for topology changes and update NUMA maps Jesse Larrew
2 siblings, 1 reply; 6+ messages in thread
From: Jesse Larrew @ 2010-10-29 0:30 UTC (permalink / raw)
To: linuxppc-dev; +Cc: markn, pmac, tbreeds, lkessler, Jesse Larrew, mjwolf
From: Jesse Larrew <jlarrew@linux.vnet.ibm.com>
Tie the polling mechanism into the ibm,suspend-me rtas call to
stop/restart polling before/after a suspend, hibernate, migrate,
or checkpoint restart operation. This ensures that the system has a
chance to disable the polling if the partition is migrated to a system
that does not support VPHN (and vice versa).
Signed-off-by: Jesse Larrew <jlarrew@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/topology.h | 6 +++++-
arch/powerpc/kernel/rtas.c | 15 +++++++++++++++
2 files changed, 20 insertions(+), 1 deletions(-)
diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
index afe4aaa..1747d27 100644
--- a/arch/powerpc/include/asm/topology.h
+++ b/arch/powerpc/include/asm/topology.h
@@ -49,7 +49,7 @@ static inline int pcibus_to_node(struct pci_bus *bus)
{
return -1;
}
-#endif
+#endif /* CONFIG_PCI */
#define cpumask_of_pcibus(bus) (pcibus_to_node(bus) == -1 ? \
cpu_all_mask : \
@@ -93,6 +93,8 @@ extern void __init dump_numa_cpu_topology(void);
extern int sysfs_add_device_to_node(struct sys_device *dev, int nid);
extern void sysfs_remove_device_from_node(struct sys_device *dev, int nid);
+extern int __init init_topology_update(void);
+extern int stop_topology_update(void);
#else
static inline void dump_numa_cpu_topology(void) {}
@@ -107,6 +109,8 @@ static inline void sysfs_remove_device_from_node(struct sys_device *dev,
{
}
+static int __init init_topology_update(void) {}
+static int stop_topology_update(void) {}
#endif /* CONFIG_NUMA */
#include <asm-generic/topology.h>
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 8fe8bc6..317ff2f 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -41,6 +41,7 @@
#include <asm/atomic.h>
#include <asm/time.h>
#include <asm/mmu.h>
+#include <asm/topology.h>
struct rtas_t rtas = {
.lock = __ARCH_SPIN_LOCK_UNLOCKED
@@ -706,6 +707,18 @@ void rtas_os_term(char *str)
static int ibm_suspend_me_token = RTAS_UNKNOWN_SERVICE;
#ifdef CONFIG_PPC_PSERIES
+static void pre_suspend_work(void)
+{
+ stop_topology_update();
+ return;
+}
+
+static void post_suspend_work(void)
+{
+ init_topology_update();
+ return;
+}
+
static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_when_done)
{
u16 slb_size = mmu_slb_size;
@@ -713,6 +726,7 @@ static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_w
int cpu;
slb_set_size(SLB_MIN_SIZE);
+ pre_suspend_work();
printk(KERN_DEBUG "calling ibm,suspend-me on cpu %i\n", smp_processor_id());
while (rc == H_MULTI_THREADS_ACTIVE && !atomic_read(&data->done) &&
@@ -728,6 +742,7 @@ static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_w
rc = atomic_read(&data->error);
atomic_set(&data->error, rc);
+ post_suspend_work();
if (wake_when_done) {
atomic_set(&data->done, 1);
--
1.7.2.3
^ permalink raw reply related [flat|nested] 6+ messages in thread* Re: [PATCH 3/3] powerpc: Disable VPHN polling during a suspend operation
2010-10-29 0:30 ` [PATCH 3/3] powerpc: Disable VPHN polling during a suspend operation Jesse Larrew
@ 2010-11-03 12:12 ` Michael Ellerman
2010-11-05 20:33 ` Jesse Larrew
0 siblings, 1 reply; 6+ messages in thread
From: Michael Ellerman @ 2010-11-03 12:12 UTC (permalink / raw)
To: Jesse Larrew; +Cc: markn, pmac, tbreeds, lkessler, mjwolf, linuxppc-dev
[-- Attachment #1: Type: text/plain, Size: 3361 bytes --]
On Thu, 2010-10-28 at 20:30 -0400, Jesse Larrew wrote:
> From: Jesse Larrew <jlarrew@linux.vnet.ibm.com>
Hi Jesse, a few comments ...
> diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
> index afe4aaa..1747d27 100644
> --- a/arch/powerpc/include/asm/topology.h
> +++ b/arch/powerpc/include/asm/topology.h
> @@ -49,7 +49,7 @@ static inline int pcibus_to_node(struct pci_bus *bus)
> {
> return -1;
> }
> -#endif
> +#endif /* CONFIG_PCI */
Random change, though not a biggy I suppose.
> #define cpumask_of_pcibus(bus) (pcibus_to_node(bus) == -1 ? \
> cpu_all_mask : \
> @@ -93,6 +93,8 @@ extern void __init dump_numa_cpu_topology(void);
> extern int sysfs_add_device_to_node(struct sys_device *dev, int nid);
> extern void sysfs_remove_device_from_node(struct sys_device *dev, int nid);
>
> +extern int __init init_topology_update(void);
> +extern int stop_topology_update(void);
init_topology_update() is called repeatedly from post_suspend_work() so
it seems like it should be called start_topology_update(). And it can't
be __init because the suspend code is called after boot. You should get
a section mismatch warning if they are enabled.
> #else
>
> static inline void dump_numa_cpu_topology(void) {}
> @@ -107,6 +109,8 @@ static inline void sysfs_remove_device_from_node(struct sys_device *dev,
> {
> }
>
> +static int __init init_topology_update(void) {}
> +static int stop_topology_update(void) {}
That doesn't look like it compiles to me, you want static inline, and
they both return int.
> #endif /* CONFIG_NUMA */
>
> #include <asm-generic/topology.h>
> diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
> index 8fe8bc6..317ff2f 100644
> --- a/arch/powerpc/kernel/rtas.c
> +++ b/arch/powerpc/kernel/rtas.c
> @@ -41,6 +41,7 @@
> #include <asm/atomic.h>
> #include <asm/time.h>
> #include <asm/mmu.h>
> +#include <asm/topology.h>
>
> struct rtas_t rtas = {
> .lock = __ARCH_SPIN_LOCK_UNLOCKED
> @@ -706,6 +707,18 @@ void rtas_os_term(char *str)
>
> static int ibm_suspend_me_token = RTAS_UNKNOWN_SERVICE;
> #ifdef CONFIG_PPC_PSERIES
> +static void pre_suspend_work(void)
> +{
> + stop_topology_update();
> + return;
> +}
> +
> +static void post_suspend_work(void)
> +{
> + init_topology_update();
> + return;
> +}
I'm not sure if it's worth splitting these out into "generic"
callbacks ..
> static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_when_done)
> {
> u16 slb_size = mmu_slb_size;
> @@ -713,6 +726,7 @@ static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_w
> int cpu;
>
> slb_set_size(SLB_MIN_SIZE);
> + pre_suspend_work();
> printk(KERN_DEBUG "calling ibm,suspend-me on cpu %i\n", smp_processor_id());
>
> while (rc == H_MULTI_THREADS_ACTIVE && !atomic_read(&data->done) &&
And isn't there an error case here where you're not re-enabling the
polling? See eg. the slb_set_size() call.
> @@ -728,6 +742,7 @@ static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_w
> rc = atomic_read(&data->error);
>
> atomic_set(&data->error, rc);
> + post_suspend_work();
>
> if (wake_when_done) {
> atomic_set(&data->done, 1);
cheers
[-- Attachment #2: This is a digitally signed message part --]
[-- Type: application/pgp-signature, Size: 198 bytes --]
^ permalink raw reply [flat|nested] 6+ messages in thread* Re: [PATCH 3/3] powerpc: Disable VPHN polling during a suspend operation
2010-11-03 12:12 ` Michael Ellerman
@ 2010-11-05 20:33 ` Jesse Larrew
0 siblings, 0 replies; 6+ messages in thread
From: Jesse Larrew @ 2010-11-05 20:33 UTC (permalink / raw)
To: michael; +Cc: markn, pmac, tbreeds, lkessler, mjwolf, linuxppc-dev
On 11/03/2010 07:12 AM, Michael Ellerman wrote:
> On Thu, 2010-10-28 at 20:30 -0400, Jesse Larrew wrote:
>> From: Jesse Larrew <jlarrew@linux.vnet.ibm.com>
>
> Hi Jesse, a few comments ...
>
>> diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
>> index afe4aaa..1747d27 100644
>> --- a/arch/powerpc/include/asm/topology.h
>> +++ b/arch/powerpc/include/asm/topology.h
>> @@ -49,7 +49,7 @@ static inline int pcibus_to_node(struct pci_bus *bus)
>> {
>> return -1;
>> }
>> -#endif
>> +#endif /* CONFIG_PCI */
>
> Random change, though not a biggy I suppose.
>
That was a change that made the header easier to read, but that change should probably be submitted separately.
>> #define cpumask_of_pcibus(bus) (pcibus_to_node(bus) == -1 ? \
>> cpu_all_mask : \
>> @@ -93,6 +93,8 @@ extern void __init dump_numa_cpu_topology(void);
>> extern int sysfs_add_device_to_node(struct sys_device *dev, int nid);
>> extern void sysfs_remove_device_from_node(struct sys_device *dev, int nid);
>>
>> +extern int __init init_topology_update(void);
>> +extern int stop_topology_update(void);
>
> init_topology_update() is called repeatedly from post_suspend_work() so
> it seems like it should be called start_topology_update(). And it can't
> be __init because the suspend code is called after boot. You should get
> a section mismatch warning if they are enabled.
>
Agreed. My implementation was based on a similar feature for System Z in arch/s390/kernel/topology.c, and I had simply carried over some of their naming conventions. start_topology_update() is a better name.
>> #else
>>
>> static inline void dump_numa_cpu_topology(void) {}
>> @@ -107,6 +109,8 @@ static inline void sysfs_remove_device_from_node(struct sys_device *dev,
>> {
>> }
>>
>> +static int __init init_topology_update(void) {}
>> +static int stop_topology_update(void) {}
>
> That doesn't look like it compiles to me, you want static inline, and
> they both return int.
>
Good catch! I hadn't tried to compile this with CONFIG_NUMA turned off.
>> #endif /* CONFIG_NUMA */
>>
>> #include <asm-generic/topology.h>
>> diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
>> index 8fe8bc6..317ff2f 100644
>> --- a/arch/powerpc/kernel/rtas.c
>> +++ b/arch/powerpc/kernel/rtas.c
>> @@ -41,6 +41,7 @@
>> #include <asm/atomic.h>
>> #include <asm/time.h>
>> #include <asm/mmu.h>
>> +#include <asm/topology.h>
>>
>> struct rtas_t rtas = {
>> .lock = __ARCH_SPIN_LOCK_UNLOCKED
>> @@ -706,6 +707,18 @@ void rtas_os_term(char *str)
>>
>> static int ibm_suspend_me_token = RTAS_UNKNOWN_SERVICE;
>> #ifdef CONFIG_PPC_PSERIES
>> +static void pre_suspend_work(void)
>> +{
>> + stop_topology_update();
>> + return;
>> +}
>> +
>> +static void post_suspend_work(void)
>> +{
>> + init_topology_update();
>> + return;
>> +}
>
> I'm not sure if it's worth splitting these out into "generic"
> callbacks ..
>
I talked with Nathan Fontenot about this a couple weeks ago, and I think the plan going forward is to implement a notifier call chain that executes before/after a suspend operation to handle reinitializations like this. In the mean time, I'll just remove the pre_suspend_work() and post_suspend_work() functions in my next revision.
>> static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_when_done)
>> {
>> u16 slb_size = mmu_slb_size;
>> @@ -713,6 +726,7 @@ static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_w
>> int cpu;
>>
>> slb_set_size(SLB_MIN_SIZE);
>> + pre_suspend_work();
>> printk(KERN_DEBUG "calling ibm,suspend-me on cpu %i\n", smp_processor_id());
>>
>> while (rc == H_MULTI_THREADS_ACTIVE && !atomic_read(&data->done) &&
>
> And isn't there an error case here where you're not re-enabling the
> polling? See eg. the slb_set_size() call.
>
I'm not sure that I understand this point. I looked it over, and it looks to me that all possible code paths touch pre_suspend_work() and post_suspend_work() exactly once (even the paths that call slb_set_size()). Which path appears to be unhandled?
>> @@ -728,6 +742,7 @@ static int __rtas_suspend_last_cpu(struct rtas_suspend_me_data *data, int wake_w
>> rc = atomic_read(&data->error);
>>
>> atomic_set(&data->error, rc);
>> + post_suspend_work();
>>
>> if (wake_when_done) {
>> atomic_set(&data->done, 1);
>
> cheers
>
>
--
Jesse Larrew
Software Engineer, Linux on Power Kernel Team
IBM Linux Technology Center
Phone: (512) 973-2052 (T/L: 363-2052)
jlarrew@linux.vnet.ibm.com
^ permalink raw reply [flat|nested] 6+ messages in thread
* [PATCH 2/3] powerpc: Poll VPA for topology changes and update NUMA maps
2010-10-29 0:27 [PATCH 0/3][RFC][REPOST] Add Support for Virtual Processor Home Node (VPHN) Jesse Larrew
2010-10-29 0:28 ` [PATCH 1/3] powerpc: Add VPHN firmware feature Jesse Larrew
2010-10-29 0:30 ` [PATCH 3/3] powerpc: Disable VPHN polling during a suspend operation Jesse Larrew
@ 2010-10-29 0:33 ` Jesse Larrew
2 siblings, 0 replies; 6+ messages in thread
From: Jesse Larrew @ 2010-10-29 0:33 UTC (permalink / raw)
To: linuxppc-dev; +Cc: markn, pmac, tbreeds, lkessler, Jesse Larrew, mjwolf
From: Jesse Larrew <jlarrew@linux.vnet.ibm.com>
This patch sets a timer during boot that will periodically poll the
associativity change counters in the VPA. When a change in
associativity is detected, it retrieves the new associativity domain
information via the H_HOME_NODE_ASSOCIATIVITY hcall and updates the
NUMA node maps and sysfs entries accordingly. Note that since the
ibm,associativity device tree property does not exist on configurations
with both NUMA and SPLPAR enabled, no device tree updates are necessary.
Signed-off-by: Jesse Larrew <jlarrew@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/lppaca.h | 5 +-
arch/powerpc/mm/numa.c | 274 +++++++++++++++++++++++++++++++++++--
2 files changed, 268 insertions(+), 11 deletions(-)
diff --git a/arch/powerpc/include/asm/lppaca.h b/arch/powerpc/include/asm/lppaca.h
index 7f5e0fe..380d48b 100644
--- a/arch/powerpc/include/asm/lppaca.h
+++ b/arch/powerpc/include/asm/lppaca.h
@@ -62,7 +62,10 @@ struct lppaca {
volatile u32 dyn_pir; // Dynamic ProcIdReg value x20-x23
u32 dsei_data; // DSEI data x24-x27
u64 sprg3; // SPRG3 value x28-x2F
- u8 reserved3[80]; // Reserved x30-x7F
+ u8 reserved3[40]; // Reserved x30-x57
+ volatile u8 vphn_assoc_counts[8]; // Virtual processor home node
+ // associativity change counters x58-x5F
+ u8 reserved4[32]; // Reserved x60-x7F
//=============================================================================
// CACHE_LINE_2 0x0080 - 0x00FF Contains local read-write data
diff --git a/arch/powerpc/mm/numa.c b/arch/powerpc/mm/numa.c
index 74505b2..3150c32 100644
--- a/arch/powerpc/mm/numa.c
+++ b/arch/powerpc/mm/numa.c
@@ -20,10 +20,14 @@
#include <linux/memblock.h>
#include <linux/of.h>
#include <linux/pfn.h>
+#include <linux/cpuset.h>
+#include <linux/node.h>
#include <asm/sparsemem.h>
#include <asm/prom.h>
#include <asm/system.h>
#include <asm/smp.h>
+#include <asm/firmware.h>
+#include <asm/paca.h>
static int numa_enabled = 1;
@@ -246,32 +250,41 @@ static void initialize_distance_lookup_table(int nid,
/* Returns nid in the range [0..MAX_NUMNODES-1], or -1 if no useful numa
* info is found.
*/
-static int of_node_to_nid_single(struct device_node *device)
+static int associativity_to_nid(const unsigned int *associativity)
{
int nid = -1;
- const unsigned int *tmp;
if (min_common_depth == -1)
goto out;
- tmp = of_get_associativity(device);
- if (!tmp)
- goto out;
-
- if (tmp[0] >= min_common_depth)
- nid = tmp[min_common_depth];
+ if (associativity[0] >= min_common_depth)
+ nid = associativity[min_common_depth];
/* POWER4 LPAR uses 0xffff as invalid node */
if (nid == 0xffff || nid >= MAX_NUMNODES)
nid = -1;
- if (nid > 0 && tmp[0] >= distance_ref_points_depth)
- initialize_distance_lookup_table(nid, tmp);
+ if (nid > 0 && associativity[0] >= distance_ref_points_depth)
+ initialize_distance_lookup_table(nid, associativity);
out:
return nid;
}
+/* Returns the nid associated with the given device tree node,
+ * or -1 if not found.
+ */
+static int of_node_to_nid_single(struct device_node *device)
+{
+ int nid = -1;
+ const unsigned int *tmp;
+
+ tmp = of_get_associativity(device);
+ if (tmp)
+ nid = associativity_to_nid(tmp);
+ return nid;
+}
+
/* Walk the device tree upwards, looking for an associativity id */
int of_node_to_nid(struct device_node *device)
{
@@ -1248,3 +1261,244 @@ int hot_add_scn_to_nid(unsigned long scn_addr)
}
#endif /* CONFIG_MEMORY_HOTPLUG */
+
+/* Vrtual Processor Home Node (VPHN) support */
+#define VPHN_NR_CHANGE_CTRS (8)
+static u8 vphn_cpu_change_counts[NR_CPUS][VPHN_NR_CHANGE_CTRS];
+static cpumask_t cpu_associativity_changes_mask;
+static void topology_work_fn(struct work_struct *work);
+static DECLARE_WORK(topology_work, topology_work_fn);
+static void topology_timer_fn(unsigned long ignored);
+static struct timer_list topology_timer =
+ TIMER_INITIALIZER(topology_timer_fn, 0, 0);
+
+static void set_topology_timer(void);
+int stop_topology_update(void);
+
+/*
+ * Store the current values of the associativity change counters in the
+ * hypervisor.
+ */
+static void setup_cpu_associativity_change_counters(void)
+{
+ int cpu = 0;
+
+ for_each_possible_cpu(cpu) {
+ int i = 0;
+ u8 *counts = vphn_cpu_change_counts[cpu];
+ volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts;
+
+ for (i = 0; i < VPHN_NR_CHANGE_CTRS; i++) {
+ counts[i] = hypervisor_counts[i];
+ }
+ }
+
+ return;
+}
+
+/*
+ * The hypervisor maintains a set of 8 associativity change counters in
+ * the VPA of each cpu that correspond to the associativity levels in the
+ * ibm,associativity-reference-points property. When an associativity
+ * level changes, the corresponding counter is incremented.
+ *
+ * Set a bit in cpu_associativity_changes_mask for each cpu whose home
+ * node associativity levels have changed.
+ */
+static void update_cpu_associativity_changes_mask(void)
+{
+ int cpu = 0;
+ cpumask_t *changes = &cpu_associativity_changes_mask;
+
+ cpumask_clear(changes);
+
+ for_each_possible_cpu(cpu) {
+ int i;
+ u8 *counts = vphn_cpu_change_counts[cpu];
+ volatile u8 *hypervisor_counts = lppaca[cpu].vphn_assoc_counts;
+
+ for (i = 0; i < VPHN_NR_CHANGE_CTRS; i++) {
+ if (hypervisor_counts[i] > counts[i]) {
+ counts[i] = hypervisor_counts[i];
+
+ if (!(cpumask_test_cpu(cpu, changes)))
+ cpumask_set_cpu(cpu, changes);
+ }
+ }
+ }
+
+ return;
+}
+
+/* 6 64-bit registers unpacked into 12 32-bit associativity values */
+#define VPHN_ASSOC_BUFSIZE (6*sizeof(u64)/sizeof(u32))
+
+/*
+ * Convert the associativity domain numbers returned from the hypervisor
+ * to the sequence they would appear in the ibm,associativity property.
+ */
+static int vphn_unpack_associativity(const long *packed, unsigned int *unpacked)
+{
+ int i = 0;
+ int nr_assoc_doms = 0;
+ const u16 *field = (const u16*) packed;
+
+#define VPHN_FIELD_UNUSED (0xffff)
+#define VPHN_FIELD_MSB (0x8000)
+#define VPHN_FIELD_MASK (~VPHN_FIELD_MSB)
+
+ for (i = 0; i < VPHN_ASSOC_BUFSIZE; i++) {
+ if (*field == VPHN_FIELD_UNUSED) {
+ /* All significant fields processed, and remaining
+ * fields contain the reserved value of all 1's.
+ * Just store them.
+ */
+ unpacked[i] = *((u32*)field);
+ field += 2;
+ }
+ else if (*field & VPHN_FIELD_MSB) {
+ /* Data is in the lower 15 bits of this field */
+ unpacked[i] = *field & VPHN_FIELD_MASK;
+ field++;
+ nr_assoc_doms++;
+ }
+ else {
+ /* Data is in the lower 15 bits of this field
+ * concatenated with the next 16 bit field
+ */
+ unpacked[i] = *((u32*)field);
+ field += 2;
+ nr_assoc_doms++;
+ }
+ }
+
+ return nr_assoc_doms;
+}
+
+/*
+ * Retrieve the new associativity information for a virtual processor's
+ * home node.
+ */
+static long hcall_vphn(unsigned long cpu, unsigned int *associativity)
+{
+ long rc = 0;
+ long retbuf[PLPAR_HCALL9_BUFSIZE] = {0};
+ u64 flags = 1;
+ int hwcpu = get_hard_smp_processor_id(cpu);
+
+ rc = plpar_hcall9(H_HOME_NODE_ASSOCIATIVITY, retbuf, flags, hwcpu);
+ vphn_unpack_associativity(retbuf, associativity);
+
+ return rc;
+}
+
+static long
+vphn_get_associativity(unsigned long cpu, unsigned int *associativity)
+{
+ long rc = 0;
+
+ rc = hcall_vphn(cpu, associativity);
+
+ switch (rc) {
+ case H_FUNCTION:
+ printk(KERN_INFO
+ "VPHN is not supported. Disabling polling...\n");
+ stop_topology_update();
+ break;
+ case H_HARDWARE:
+ printk(KERN_ERR
+ "hcall_vphn() experienced a hardware fault "
+ "preventing VPHN. Disabling polling...\n");
+ stop_topology_update();
+ }
+
+ return rc;
+}
+
+/*
+ * Update the node maps and sysfs entries for each cpu whose home node
+ * has changed.
+ */
+int arch_update_cpu_topology(void)
+{
+ int cpu = 0, nid = 0, old_nid = 0;
+ unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
+ struct sys_device *sysdev = NULL;
+
+ for_each_cpu_mask(cpu, cpu_associativity_changes_mask) {
+ vphn_get_associativity(cpu, associativity);
+ nid = associativity_to_nid(associativity);
+
+ if (nid < 0 || !node_online(nid))
+ nid = first_online_node;
+
+ old_nid = numa_cpu_lookup_table[cpu];
+
+ /* Disable hotplug while we update the cpu
+ * masks and sysfs.
+ */
+ get_online_cpus();
+ unregister_cpu_under_node(cpu, old_nid);
+ unmap_cpu_from_node(cpu);
+ map_cpu_to_node(cpu, nid);
+ register_cpu_under_node(cpu, nid);
+ put_online_cpus();
+
+ sysdev = get_cpu_sysdev(cpu);
+ if (sysdev)
+ kobject_uevent(&sysdev->kobj, KOBJ_CHANGE);
+ }
+
+ return 1;
+}
+
+static void topology_work_fn(struct work_struct *work)
+{
+ rebuild_sched_domains();
+}
+
+void topology_schedule_update(void)
+{
+ schedule_work(&topology_work);
+}
+
+static void topology_timer_fn(unsigned long ignored)
+{
+ update_cpu_associativity_changes_mask();
+ if (!cpumask_empty(&cpu_associativity_changes_mask))
+ topology_schedule_update();
+ set_topology_timer();
+}
+
+static void set_topology_timer(void)
+{
+ topology_timer.data = 0;
+ topology_timer.expires = jiffies + 60 * HZ;
+ add_timer(&topology_timer);
+}
+
+/*
+ * Start polling for VPHN associativity changes.
+ */
+int __init init_topology_update(void)
+{
+ int rc = 0;
+
+ if (firmware_has_feature(FW_FEATURE_VPHN)) {
+ setup_cpu_associativity_change_counters();
+ init_timer_deferrable(&topology_timer);
+ set_topology_timer();
+ rc = 1;
+ }
+
+ return rc;
+}
+__initcall(init_topology_update);
+
+/*
+ * Disable polling for VPHN associativity changes.
+ */
+int stop_topology_update(void)
+{
+ return del_timer(&topology_timer);
+}
--
1.7.2.3
^ permalink raw reply related [flat|nested] 6+ messages in thread