* [PATCH v4 1/13] Expose pseries devicetree_update()
2013-04-24 15:34 [PATCH v4 0/13] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
@ 2013-04-24 15:47 ` Nathan Fontenot
2013-04-24 15:49 ` [PATCH v4 2/13] Correct buffer parsing in update_dt_node() Nathan Fontenot
` (11 subsequent siblings)
12 siblings, 0 replies; 16+ messages in thread
From: Nathan Fontenot @ 2013-04-24 15:47 UTC (permalink / raw)
To: linuxppc-dev
Newer firmware on Power systems can transparently reassign platform resources
(CPU and Memory) in use. For instance, if a processor or memory unit is
predicted to fail, the platform may transparently move the processing to an
equivalent unused processor or the memory state to an equivalent unused
memory unit. However, reassigning resources across NUMA boundaries may alter
the performance of the partition. When such reassignment is necessary, the
Platform Resource Reassignment Notification (PRRN) option provides a
mechanism to inform the Linux kernel of changes to the NUMA affinity of
its platform resources.
When rtasd receives a PRRN event, it needs to make a series of RTAS
calls (ibm,update-nodes and ibm,update-properties) to retrieve the
updated device tree information. These calls are already handled in the
pseries_devicetree_update() routine used in partition migration.
This patch exposes pseries_devicetree_update() to make it accessible
to other pseries routines, this patch also updates pseries_devicetree_update()
to take a 32-bit scope parameter. The scope value, which was previously hard
coded to 1 for partition migration, is used for the RTAS calls
ibm,update-nodes/properties to update the device tree.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/rtas.h | 4 ++++
arch/powerpc/platforms/pseries/mobility.c | 21 ++++++++++++---------
2 files changed, 16 insertions(+), 9 deletions(-)
Index: powerpc/arch/powerpc/platforms/pseries/mobility.c
===================================================================
--- powerpc.orig/arch/powerpc/platforms/pseries/mobility.c 2013-04-15 09:18:10.000000000 -0500
+++ powerpc/arch/powerpc/platforms/pseries/mobility.c 2013-04-23 13:22:05.000000000 -0500
@@ -37,14 +37,16 @@
#define UPDATE_DT_NODE 0x02000000
#define ADD_DT_NODE 0x03000000
-static int mobility_rtas_call(int token, char *buf)
+#define MIGRATION_SCOPE (1)
+
+static int mobility_rtas_call(int token, char *buf, s32 scope)
{
int rc;
spin_lock(&rtas_data_buf_lock);
memcpy(rtas_data_buf, buf, RTAS_DATA_BUF_SIZE);
- rc = rtas_call(token, 2, 1, NULL, rtas_data_buf, 1);
+ rc = rtas_call(token, 2, 1, NULL, rtas_data_buf, scope);
memcpy(buf, rtas_data_buf, RTAS_DATA_BUF_SIZE);
spin_unlock(&rtas_data_buf_lock);
@@ -123,7 +125,7 @@
return 0;
}
-static int update_dt_node(u32 phandle)
+static int update_dt_node(u32 phandle, s32 scope)
{
struct update_props_workarea *upwa;
struct device_node *dn;
@@ -151,7 +153,8 @@
upwa->phandle = phandle;
do {
- rc = mobility_rtas_call(update_properties_token, rtas_buf);
+ rc = mobility_rtas_call(update_properties_token, rtas_buf,
+ scope);
if (rc < 0)
break;
@@ -219,7 +222,7 @@
return rc;
}
-static int pseries_devicetree_update(void)
+int pseries_devicetree_update(s32 scope)
{
char *rtas_buf;
u32 *data;
@@ -235,7 +238,7 @@
return -ENOMEM;
do {
- rc = mobility_rtas_call(update_nodes_token, rtas_buf);
+ rc = mobility_rtas_call(update_nodes_token, rtas_buf, scope);
if (rc && rc != 1)
break;
@@ -256,7 +259,7 @@
delete_dt_node(phandle);
break;
case UPDATE_DT_NODE:
- update_dt_node(phandle);
+ update_dt_node(phandle, scope);
break;
case ADD_DT_NODE:
drc_index = *data++;
@@ -276,7 +279,7 @@
int rc;
int activate_fw_token;
- rc = pseries_devicetree_update();
+ rc = pseries_devicetree_update(MIGRATION_SCOPE);
if (rc) {
printk(KERN_ERR "Initial post-mobility device tree update "
"failed: %d\n", rc);
@@ -292,7 +295,7 @@
rc = rtas_call(activate_fw_token, 0, 1, NULL);
if (!rc) {
- rc = pseries_devicetree_update();
+ rc = pseries_devicetree_update(MIGRATION_SCOPE);
if (rc)
printk(KERN_ERR "Secondary post-mobility device tree "
"update failed: %d\n", rc);
Index: powerpc/arch/powerpc/include/asm/rtas.h
===================================================================
--- powerpc.orig/arch/powerpc/include/asm/rtas.h 2013-04-15 09:18:10.000000000 -0500
+++ powerpc/arch/powerpc/include/asm/rtas.h 2013-04-23 13:22:37.000000000 -0500
@@ -277,6 +277,10 @@
extern void pSeries_log_error(char *buf, unsigned int err_type, int fatal);
+#ifdef CONFIG_PPC_PSERIES
+extern int pseries_devicetree_update(s32 scope);
+#endif
+
#ifdef CONFIG_PPC_RTAS_DAEMON
extern void rtas_cancel_event_scan(void);
#else
^ permalink raw reply [flat|nested] 16+ messages in thread* [PATCH v4 2/13] Correct buffer parsing in update_dt_node()
2013-04-24 15:34 [PATCH v4 0/13] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
2013-04-24 15:47 ` [PATCH v4 1/13] Expose pseries devicetree_update() Nathan Fontenot
@ 2013-04-24 15:49 ` Nathan Fontenot
2013-04-26 3:01 ` Stephen Rothwell
2013-04-24 15:51 ` [PATCH v4 3/13] Add PRRN RTAS event handler Nathan Fontenot
` (10 subsequent siblings)
12 siblings, 1 reply; 16+ messages in thread
From: Nathan Fontenot @ 2013-04-24 15:49 UTC (permalink / raw)
To: linuxppc-dev
Correct parsing of the buffer returned from ibm,update-properties. The first
element is a length and the path to the property which is slightly different
from the list of properties in the buffer so we need to specifically
handle this.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
---
arch/powerpc/platforms/pseries/mobility.c | 20 ++++++++++++++++----
1 file changed, 16 insertions(+), 4 deletions(-)
Index: powerpc/arch/powerpc/platforms/pseries/mobility.c
===================================================================
--- powerpc.orig/arch/powerpc/platforms/pseries/mobility.c 2013-04-23 13:22:05.000000000 -0500
+++ powerpc/arch/powerpc/platforms/pseries/mobility.c 2013-04-23 13:39:36.000000000 -0500
@@ -134,6 +134,7 @@
char *prop_data;
char *rtas_buf;
int update_properties_token;
+ u32 vd;
update_properties_token = rtas_token("ibm,update-properties");
if (update_properties_token == RTAS_UNKNOWN_SERVICE)
@@ -160,13 +161,24 @@
prop_data = rtas_buf + sizeof(*upwa);
- for (i = 0; i < upwa->nprops; i++) {
+ /* The first element of the buffer is the path of the node
+ * being updated in the form of a 8 byte string length
+ * followed by the string. Skip past this to get to the
+ * properties being updated.
+ */
+ vd = *prop_data++;
+ prop_data += vd;
+
+ /* The path we skipped over is counted as one of the elements
+ * returned so start counting at one.
+ */
+ for (i = 1; i < upwa->nprops; i++) {
char *prop_name;
- u32 vd;
- prop_name = prop_data + 1;
+ prop_name = prop_data;
prop_data += strlen(prop_name) + 1;
- vd = *prop_data++;
+ vd = *(u32 *)prop_data;
+ prop_data += sizeof(vd);
switch (vd) {
case 0x00000000:
^ permalink raw reply [flat|nested] 16+ messages in thread* Re: [PATCH v4 2/13] Correct buffer parsing in update_dt_node()
2013-04-24 15:49 ` [PATCH v4 2/13] Correct buffer parsing in update_dt_node() Nathan Fontenot
@ 2013-04-26 3:01 ` Stephen Rothwell
0 siblings, 0 replies; 16+ messages in thread
From: Stephen Rothwell @ 2013-04-26 3:01 UTC (permalink / raw)
To: Nathan Fontenot; +Cc: linuxppc-dev
[-- Attachment #1: Type: text/plain, Size: 893 bytes --]
Hi Nathan,
On Wed, 24 Apr 2013 10:49:36 -0500 Nathan Fontenot <nfont@linux.vnet.ibm.com> wrote:
>
> @@ -134,6 +134,7 @@
> char *prop_data;
> char *rtas_buf;
> int update_properties_token;
> + u32 vd;
>
> update_properties_token = rtas_token("ibm,update-properties");
> if (update_properties_token == RTAS_UNKNOWN_SERVICE)
> @@ -160,13 +161,24 @@
>
> prop_data = rtas_buf + sizeof(*upwa);
>
> - for (i = 0; i < upwa->nprops; i++) {
> + /* The first element of the buffer is the path of the node
> + * being updated in the form of a 8 byte string length
^^^^
"bit" ?
> + * followed by the string. Skip past this to get to the
> + * properties being updated.
> + */
> + vd = *prop_data++;
> + prop_data += vd;
--
Cheers,
Stephen Rothwell sfr@canb.auug.org.au
[-- Attachment #2: Type: application/pgp-signature, Size: 836 bytes --]
^ permalink raw reply [flat|nested] 16+ messages in thread
* [PATCH v4 3/13] Add PRRN RTAS event handler
2013-04-24 15:34 [PATCH v4 0/13] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
2013-04-24 15:47 ` [PATCH v4 1/13] Expose pseries devicetree_update() Nathan Fontenot
2013-04-24 15:49 ` [PATCH v4 2/13] Correct buffer parsing in update_dt_node() Nathan Fontenot
@ 2013-04-24 15:51 ` Nathan Fontenot
2013-04-24 15:53 ` [PATCH v4 4/13] Move architecture vector definitions to prom.h Nathan Fontenot
` (9 subsequent siblings)
12 siblings, 0 replies; 16+ messages in thread
From: Nathan Fontenot @ 2013-04-24 15:51 UTC (permalink / raw)
To: linuxppc-dev
From: Jesse Larrew <jlarrew@linux.vnet.ibm.com>
A PRRN event is signaled via the RTAS event-scan mechanism, which
returns a Hot Plug Event message "fixed part" indicating "Platform
Resource Reassignment". In response to the Hot Plug Event message,
we must call ibm,update-nodes to determine which resources were
reassigned and then ibm,update-properties to obtain the new affinity
information about those resources.
The PRRN event-scan RTAS message contains only the "fixed part" with
the "Type" field set to the value 160 and no Extended Event Log. The
four-byte Extended Event Log Length field is re-purposed (since no
Extended Event Log message is included) to pass the "scope" parameter
that causes the ibm,update-nodes to return the nodes affected by the
specific resource reassignment.
This patch adds a handler for RTAS events. The function
pseries_devicetree_update() (from mobility.c) is used to make the
ibm,update-nodes/ibm,update-properties RTAS calls. Updating the NUMA maps
(handled by a subsequent patch) will require significant processing,
so pseries_devicetree_update() is called from an asynchronous workqueue
to allow event processing to continue.
PRRN RTAS events on pseries systems are rare events that have to be
initiated from the HMC console for the system by an IBM tech. This allows
us to assume that these events are widely spaced. Additionally, all work
on the queue is flushed before handling any new work to ensure we only have
one event in flight being handled at a time.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/rtas.h | 2 +
arch/powerpc/kernel/rtasd.c | 46 +++++++++++++++++++++++++++++++++++++++-
2 files changed, 47 insertions(+), 1 deletion(-)
Index: powerpc/arch/powerpc/include/asm/rtas.h
===================================================================
--- powerpc.orig/arch/powerpc/include/asm/rtas.h 2013-04-23 13:22:37.000000000 -0500
+++ powerpc/arch/powerpc/include/asm/rtas.h 2013-04-23 13:40:36.000000000 -0500
@@ -143,6 +143,8 @@
#define RTAS_TYPE_PMGM_TIME_ALARM 0x6f
#define RTAS_TYPE_PMGM_CONFIG_CHANGE 0x70
#define RTAS_TYPE_PMGM_SERVICE_PROC 0x71
+/* Platform Resource Reassignment Notification */
+#define RTAS_TYPE_PRRN 0xA0
/* RTAS check-exception vector offset */
#define RTAS_VECTOR_EXTERNAL_INTERRUPT 0x500
Index: powerpc/arch/powerpc/kernel/rtasd.c
===================================================================
--- powerpc.orig/arch/powerpc/kernel/rtasd.c 2013-04-23 12:54:23.000000000 -0500
+++ powerpc/arch/powerpc/kernel/rtasd.c 2013-04-23 13:52:08.000000000 -0500
@@ -87,6 +87,8 @@
return "Resource Deallocation Event";
case RTAS_TYPE_DUMP:
return "Dump Notification Event";
+ case RTAS_TYPE_PRRN:
+ return "Platform Resource Reassignment Event";
}
return rtas_type[0];
@@ -265,9 +267,49 @@
spin_unlock_irqrestore(&rtasd_log_lock, s);
return;
}
+}
+
+#ifdef CONFIG_PPC_PSERIES
+static s32 prrn_update_scope;
+
+static void prrn_work_fn(struct work_struct *work)
+{
+ /*
+ * For PRRN, we must pass the negative of the scope value in
+ * the RTAS event.
+ */
+ pseries_devicetree_update(-prrn_update_scope);
+}
+
+static DECLARE_WORK(prrn_work, prrn_work_fn);
+
+void prrn_schedule_update(u32 scope)
+{
+ flush_work(&prrn_work);
+ prrn_update_scope = scope;
+ schedule_work(&prrn_work);
+}
+
+static void handle_rtas_event(const struct rtas_error_log *log)
+{
+ if (log->type == RTAS_TYPE_PRRN)
+ /* For PRRN Events the extended log length is used to denote
+ * the scope for calling rtas update-nodes.
+ */
+ prrn_schedule_update(log->extended_log_length);
+
+ return;
+}
+
+#else
+static void handle_rtas_event(const struct rtas_error_log *log)
+{
+ return;
}
+#endif
+
static int rtas_log_open(struct inode * inode, struct file * file)
{
return 0;
@@ -388,8 +430,10 @@
break;
}
- if (error == 0)
+ if (error == 0) {
pSeries_log_error(logdata, ERR_TYPE_RTAS_LOG, 0);
+ handle_rtas_event((struct rtas_error_log *)logdata);
+ }
} while(error == 0);
}
^ permalink raw reply [flat|nested] 16+ messages in thread* [PATCH v4 4/13] Move architecture vector definitions to prom.h
2013-04-24 15:34 [PATCH v4 0/13] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
` (2 preceding siblings ...)
2013-04-24 15:51 ` [PATCH v4 3/13] Add PRRN RTAS event handler Nathan Fontenot
@ 2013-04-24 15:53 ` Nathan Fontenot
2013-04-24 15:55 ` [PATCH v4 5/13] Use ARRAY_SIZE to iterate over firmware_features_table array Nathan Fontenot
` (8 subsequent siblings)
12 siblings, 0 replies; 16+ messages in thread
From: Nathan Fontenot @ 2013-04-24 15:53 UTC (permalink / raw)
To: linuxppc-dev
As part of handling of PRRN events we need to check vector 5 of the
architecture vector bits reported in the device tree to ensure PRRN event
handling is enabled. To do this firmware_has_feature() is updated (in a
subsequent patch) to make this check vector 5 bits. To avoid having to
re-define bits in the architecture vector the bit definitions are moved
to prom.h.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/prom.h | 71 +++++++++++++++++++++++++++++++++++++
arch/powerpc/kernel/prom_init.c | 75 +++-------------------------------------
2 files changed, 77 insertions(+), 69 deletions(-)
Index: powerpc/arch/powerpc/include/asm/prom.h
===================================================================
--- powerpc.orig/arch/powerpc/include/asm/prom.h 2013-04-23 12:54:23.000000000 -0500
+++ powerpc/arch/powerpc/include/asm/prom.h 2013-04-23 13:56:15.000000000 -0500
@@ -74,6 +74,77 @@
#define DRCONF_MEM_AI_INVALID 0x00000040
#define DRCONF_MEM_RESERVED 0x00000080
+/*
+ * There are two methods for telling firmware what our capabilities are.
+ * Newer machines have an "ibm,client-architecture-support" method on the
+ * root node. For older machines, we have to call the "process-elf-header"
+ * method in the /packages/elf-loader node, passing it a fake 32-bit
+ * ELF header containing a couple of PT_NOTE sections that contain
+ * structures that contain various information.
+ */
+
+/* New method - extensible architecture description vector. */
+
+/* Option vector bits - generic bits in byte 1 */
+#define OV_IGNORE 0x80 /* ignore this vector */
+#define OV_CESSATION_POLICY 0x40 /* halt if unsupported option present*/
+
+/* Option vector 1: processor architectures supported */
+#define OV1_PPC_2_00 0x80 /* set if we support PowerPC 2.00 */
+#define OV1_PPC_2_01 0x40 /* set if we support PowerPC 2.01 */
+#define OV1_PPC_2_02 0x20 /* set if we support PowerPC 2.02 */
+#define OV1_PPC_2_03 0x10 /* set if we support PowerPC 2.03 */
+#define OV1_PPC_2_04 0x08 /* set if we support PowerPC 2.04 */
+#define OV1_PPC_2_05 0x04 /* set if we support PowerPC 2.05 */
+#define OV1_PPC_2_06 0x02 /* set if we support PowerPC 2.06 */
+#define OV1_PPC_2_07 0x01 /* set if we support PowerPC 2.07 */
+
+/* Option vector 2: Open Firmware options supported */
+#define OV2_REAL_MODE 0x20 /* set if we want OF in real mode */
+
+/* Option vector 3: processor options supported */
+#define OV3_FP 0x80 /* floating point */
+#define OV3_VMX 0x40 /* VMX/Altivec */
+#define OV3_DFP 0x20 /* decimal FP */
+
+/* Option vector 4: IBM PAPR implementation */
+#define OV4_MIN_ENT_CAP 0x01 /* minimum VP entitled capacity */
+
+/* Option vector 5: PAPR/OF options supported */
+#define OV5_LPAR 0x80 /* logical partitioning supported */
+#define OV5_SPLPAR 0x40 /* shared-processor LPAR supported */
+/* ibm,dynamic-reconfiguration-memory property supported */
+#define OV5_DRCONF_MEMORY 0x20
+#define OV5_LARGE_PAGES 0x10 /* large pages supported */
+#define OV5_DONATE_DEDICATE_CPU 0x02 /* donate dedicated CPU support */
+/* PCIe/MSI support. Without MSI full PCIe is not supported */
+#ifdef CONFIG_PCI_MSI
+#define OV5_MSI 0x01 /* PCIe/MSI support */
+#else
+#define OV5_MSI 0x00
+#endif /* CONFIG_PCI_MSI */
+#ifdef CONFIG_PPC_SMLPAR
+#define OV5_CMO 0x80 /* Cooperative Memory Overcommitment */
+#define OV5_XCMO 0x40 /* Page Coalescing */
+#else
+#define OV5_CMO 0x00
+#define OV5_XCMO 0x00
+#endif
+#define OV5_TYPE1_AFFINITY 0x80 /* Type 1 NUMA affinity */
+#define OV5_PFO_HW_RNG 0x80 /* PFO Random Number Generator */
+#define OV5_PFO_HW_842 0x40 /* PFO Compression Accelerator */
+#define OV5_PFO_HW_ENCR 0x20 /* PFO Encryption Accelerator */
+#define OV5_SUB_PROCESSORS 0x01 /* 1,2,or 4 Sub-Processors supported */
+
+/* Option Vector 6: IBM PAPR hints */
+#define OV6_LINUX 0x02 /* Linux is our OS */
+
+/*
+ * The architecture vector has an array of PVR mask/value pairs,
+ * followed by # option vectors - 1, followed by the option vectors.
+ */
+extern unsigned char ibm_architecture_vec[];
+
/* These includes are put at the bottom because they may contain things
* that are overridden by this file. Ideally they shouldn't be included
* by this file, but there are a bunch of .c files that currently depend
Index: powerpc/arch/powerpc/kernel/prom_init.c
===================================================================
--- powerpc.orig/arch/powerpc/kernel/prom_init.c 2013-04-23 12:54:23.000000000 -0500
+++ powerpc/arch/powerpc/kernel/prom_init.c 2013-04-23 13:55:21.000000000 -0500
@@ -627,16 +627,11 @@
#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
/*
- * There are two methods for telling firmware what our capabilities are.
- * Newer machines have an "ibm,client-architecture-support" method on the
- * root node. For older machines, we have to call the "process-elf-header"
- * method in the /packages/elf-loader node, passing it a fake 32-bit
- * ELF header containing a couple of PT_NOTE sections that contain
- * structures that contain various information.
- */
-
-/*
- * New method - extensible architecture description vector.
+ * The architecture vector has an array of PVR mask/value pairs,
+ * followed by # option vectors - 1, followed by the option vectors.
+ *
+ * See prom.h for the definition of the bits specified in the
+ * architecture vector.
*
* Because the description vector contains a mix of byte and word
* values, we declare it as an unsigned char array, and use this
@@ -645,65 +640,7 @@
#define W(x) ((x) >> 24) & 0xff, ((x) >> 16) & 0xff, \
((x) >> 8) & 0xff, (x) & 0xff
-/* Option vector bits - generic bits in byte 1 */
-#define OV_IGNORE 0x80 /* ignore this vector */
-#define OV_CESSATION_POLICY 0x40 /* halt if unsupported option present*/
-
-/* Option vector 1: processor architectures supported */
-#define OV1_PPC_2_00 0x80 /* set if we support PowerPC 2.00 */
-#define OV1_PPC_2_01 0x40 /* set if we support PowerPC 2.01 */
-#define OV1_PPC_2_02 0x20 /* set if we support PowerPC 2.02 */
-#define OV1_PPC_2_03 0x10 /* set if we support PowerPC 2.03 */
-#define OV1_PPC_2_04 0x08 /* set if we support PowerPC 2.04 */
-#define OV1_PPC_2_05 0x04 /* set if we support PowerPC 2.05 */
-#define OV1_PPC_2_06 0x02 /* set if we support PowerPC 2.06 */
-#define OV1_PPC_2_07 0x01 /* set if we support PowerPC 2.07 */
-
-/* Option vector 2: Open Firmware options supported */
-#define OV2_REAL_MODE 0x20 /* set if we want OF in real mode */
-
-/* Option vector 3: processor options supported */
-#define OV3_FP 0x80 /* floating point */
-#define OV3_VMX 0x40 /* VMX/Altivec */
-#define OV3_DFP 0x20 /* decimal FP */
-
-/* Option vector 4: IBM PAPR implementation */
-#define OV4_MIN_ENT_CAP 0x01 /* minimum VP entitled capacity */
-
-/* Option vector 5: PAPR/OF options supported */
-#define OV5_LPAR 0x80 /* logical partitioning supported */
-#define OV5_SPLPAR 0x40 /* shared-processor LPAR supported */
-/* ibm,dynamic-reconfiguration-memory property supported */
-#define OV5_DRCONF_MEMORY 0x20
-#define OV5_LARGE_PAGES 0x10 /* large pages supported */
-#define OV5_DONATE_DEDICATE_CPU 0x02 /* donate dedicated CPU support */
-/* PCIe/MSI support. Without MSI full PCIe is not supported */
-#ifdef CONFIG_PCI_MSI
-#define OV5_MSI 0x01 /* PCIe/MSI support */
-#else
-#define OV5_MSI 0x00
-#endif /* CONFIG_PCI_MSI */
-#ifdef CONFIG_PPC_SMLPAR
-#define OV5_CMO 0x80 /* Cooperative Memory Overcommitment */
-#define OV5_XCMO 0x40 /* Page Coalescing */
-#else
-#define OV5_CMO 0x00
-#define OV5_XCMO 0x00
-#endif
-#define OV5_TYPE1_AFFINITY 0x80 /* Type 1 NUMA affinity */
-#define OV5_PFO_HW_RNG 0x80 /* PFO Random Number Generator */
-#define OV5_PFO_HW_842 0x40 /* PFO Compression Accelerator */
-#define OV5_PFO_HW_ENCR 0x20 /* PFO Encryption Accelerator */
-#define OV5_SUB_PROCESSORS 0x01 /* 1,2,or 4 Sub-Processors supported */
-
-/* Option Vector 6: IBM PAPR hints */
-#define OV6_LINUX 0x02 /* Linux is our OS */
-
-/*
- * The architecture vector has an array of PVR mask/value pairs,
- * followed by # option vectors - 1, followed by the option vectors.
- */
-static unsigned char ibm_architecture_vec[] = {
+unsigned char ibm_architecture_vec[] = {
W(0xfffe0000), W(0x003a0000), /* POWER5/POWER5+ */
W(0xffff0000), W(0x003e0000), /* POWER6 */
W(0xffff0000), W(0x003f0000), /* POWER7 */
^ permalink raw reply [flat|nested] 16+ messages in thread* [PATCH v4 5/13] Use ARRAY_SIZE to iterate over firmware_features_table array
2013-04-24 15:34 [PATCH v4 0/13] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
` (3 preceding siblings ...)
2013-04-24 15:53 ` [PATCH v4 4/13] Move architecture vector definitions to prom.h Nathan Fontenot
@ 2013-04-24 15:55 ` Nathan Fontenot
2013-04-26 3:08 ` Stephen Rothwell
2013-04-24 15:57 ` [PATCH v4 6/13] Update firmware_has_feature() to check architecture vector 5 bits Nathan Fontenot
` (7 subsequent siblings)
12 siblings, 1 reply; 16+ messages in thread
From: Nathan Fontenot @ 2013-04-24 15:55 UTC (permalink / raw)
To: linuxppc-dev
When iterating over the entries in firmware_features_table we only need
to go over the actual number of entries in the array instead of declaring
it to be bigger and checking to make sure there is a valid entry in every
slot.
This patch removes the FIRMWARE_MAX_FEATURES #define and replaces the
array looping with the use of ARRAY_SIZE().
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/firmware.h | 1 -
arch/powerpc/platforms/pseries/firmware.c | 8 +++-----
2 files changed, 3 insertions(+), 6 deletions(-)
Index: powerpc/arch/powerpc/include/asm/firmware.h
===================================================================
--- powerpc.orig/arch/powerpc/include/asm/firmware.h 2013-04-23 14:17:16.000000000 -0500
+++ powerpc/arch/powerpc/include/asm/firmware.h 2013-04-23 14:19:54.000000000 -0500
@@ -18,7 +18,6 @@
#include <asm/feature-fixups.h>
/* firmware feature bitmask values */
-#define FIRMWARE_MAX_FEATURES 63
#define FW_FEATURE_PFT ASM_CONST(0x0000000000000001)
#define FW_FEATURE_TCE ASM_CONST(0x0000000000000002)
Index: powerpc/arch/powerpc/platforms/pseries/firmware.c
===================================================================
--- powerpc.orig/arch/powerpc/platforms/pseries/firmware.c 2013-04-23 14:17:16.000000000 -0500
+++ powerpc/arch/powerpc/platforms/pseries/firmware.c 2013-04-23 14:46:10.000000000 -0500
@@ -39,7 +39,7 @@
* string must match.
*/
static __initdata firmware_feature_t
-firmware_features_table[FIRMWARE_MAX_FEATURES] = {
+firmware_features_table[] = {
{FW_FEATURE_PFT, "hcall-pft"},
{FW_FEATURE_TCE, "hcall-tce"},
{FW_FEATURE_SPRG0, "hcall-sprg0"},
@@ -77,12 +77,10 @@
pr_debug(" -> fw_feature_init()\n");
for (s = hypertas; s < hypertas + len; s += strlen(s) + 1) {
- for (i = 0; i < FIRMWARE_MAX_FEATURES; i++) {
+ for (i = 0; i < ARRAY_SIZE(firmware_features_table); i++) {
const char *name = firmware_features_table[i].name;
size_t size;
- /* check value against table of strings */
- if (!name)
- continue;
+
/*
* If there is a '*' at the end of name, only check
* upto there
^ permalink raw reply [flat|nested] 16+ messages in thread* [PATCH v4 6/13] Update firmware_has_feature() to check architecture vector 5 bits
2013-04-24 15:34 [PATCH v4 0/13] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
` (4 preceding siblings ...)
2013-04-24 15:55 ` [PATCH v4 5/13] Use ARRAY_SIZE to iterate over firmware_features_table array Nathan Fontenot
@ 2013-04-24 15:57 ` Nathan Fontenot
2013-04-24 15:58 ` [PATCH v4 7/13] Update numa.c to use updated firmware_has_feature() Nathan Fontenot
` (6 subsequent siblings)
12 siblings, 0 replies; 16+ messages in thread
From: Nathan Fontenot @ 2013-04-24 15:57 UTC (permalink / raw)
To: linuxppc-dev
The firmware_has_feature() function makes it easy to check for supported
features of the hypervisor. This patch extends the capability of
firmware_has_feature() to include checking for specified bits
in vector 5 of the architecture vector as reported in the device tree.
As part of this the #defines used for the architecture vector are re-defined
such that each option has the index into vector 5 and the feature bit encoded
into it. This makes checking for architecture bits when initiating data
for firmware_has_feature much easier.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/firmware.h | 4 +-
arch/powerpc/include/asm/prom.h | 45 ++++++++++++---------------
arch/powerpc/kernel/prom_init.c | 23 ++++++++++----
arch/powerpc/platforms/pseries/firmware.c | 49 +++++++++++++++++++++++-------
arch/powerpc/platforms/pseries/pseries.h | 5 ++-
arch/powerpc/platforms/pseries/setup.c | 40 ++++++++++++++++--------
6 files changed, 111 insertions(+), 55 deletions(-)
Index: powerpc/arch/powerpc/include/asm/prom.h
===================================================================
--- powerpc.orig/arch/powerpc/include/asm/prom.h 2013-04-23 14:17:16.000000000 -0500
+++ powerpc/arch/powerpc/include/asm/prom.h 2013-04-23 14:46:23.000000000 -0500
@@ -110,31 +110,28 @@
/* Option vector 4: IBM PAPR implementation */
#define OV4_MIN_ENT_CAP 0x01 /* minimum VP entitled capacity */
-/* Option vector 5: PAPR/OF options supported */
-#define OV5_LPAR 0x80 /* logical partitioning supported */
-#define OV5_SPLPAR 0x40 /* shared-processor LPAR supported */
+/* Option vector 5: PAPR/OF options supported
+ * These bits are also used in firmware_has_feature() to validate
+ * the capabilities reported for vector 5 in the device tree so we
+ * encode the vector index in the define and use the OV5_FEAT()
+ * and OV5_INDX() macros to extract the desired information.
+ */
+#define OV5_FEAT(x) ((x) & 0xff)
+#define OV5_INDX(x) ((x) >> 8)
+#define OV5_LPAR 0x0280 /* logical partitioning supported */
+#define OV5_SPLPAR 0x0240 /* shared-processor LPAR supported */
/* ibm,dynamic-reconfiguration-memory property supported */
-#define OV5_DRCONF_MEMORY 0x20
-#define OV5_LARGE_PAGES 0x10 /* large pages supported */
-#define OV5_DONATE_DEDICATE_CPU 0x02 /* donate dedicated CPU support */
-/* PCIe/MSI support. Without MSI full PCIe is not supported */
-#ifdef CONFIG_PCI_MSI
-#define OV5_MSI 0x01 /* PCIe/MSI support */
-#else
-#define OV5_MSI 0x00
-#endif /* CONFIG_PCI_MSI */
-#ifdef CONFIG_PPC_SMLPAR
-#define OV5_CMO 0x80 /* Cooperative Memory Overcommitment */
-#define OV5_XCMO 0x40 /* Page Coalescing */
-#else
-#define OV5_CMO 0x00
-#define OV5_XCMO 0x00
-#endif
-#define OV5_TYPE1_AFFINITY 0x80 /* Type 1 NUMA affinity */
-#define OV5_PFO_HW_RNG 0x80 /* PFO Random Number Generator */
-#define OV5_PFO_HW_842 0x40 /* PFO Compression Accelerator */
-#define OV5_PFO_HW_ENCR 0x20 /* PFO Encryption Accelerator */
-#define OV5_SUB_PROCESSORS 0x01 /* 1,2,or 4 Sub-Processors supported */
+#define OV5_DRCONF_MEMORY 0x0220
+#define OV5_LARGE_PAGES 0x0210 /* large pages supported */
+#define OV5_DONATE_DEDICATE_CPU 0x0202 /* donate dedicated CPU support */
+#define OV5_MSI 0x0201 /* PCIe/MSI support */
+#define OV5_CMO 0x0480 /* Cooperative Memory Overcommitment */
+#define OV5_XCMO 0x0440 /* Page Coalescing */
+#define OV5_TYPE1_AFFINITY 0x0580 /* Type 1 NUMA affinity */
+#define OV5_PFO_HW_RNG 0x0E80 /* PFO Random Number Generator */
+#define OV5_PFO_HW_842 0x0E40 /* PFO Compression Accelerator */
+#define OV5_PFO_HW_ENCR 0x0E20 /* PFO Encryption Accelerator */
+#define OV5_SUB_PROCESSORS 0x0F01 /* 1,2,or 4 Sub-Processors supported */
/* Option Vector 6: IBM PAPR hints */
#define OV6_LINUX 0x02 /* Linux is our OS */
Index: powerpc/arch/powerpc/kernel/prom_init.c
===================================================================
--- powerpc.orig/arch/powerpc/kernel/prom_init.c 2013-04-23 14:17:16.000000000 -0500
+++ powerpc/arch/powerpc/kernel/prom_init.c 2013-04-23 14:46:23.000000000 -0500
@@ -684,11 +684,21 @@
/* option vector 5: PAPR/OF options */
19 - 2, /* length */
0, /* don't ignore, don't halt */
- OV5_LPAR | OV5_SPLPAR | OV5_LARGE_PAGES | OV5_DRCONF_MEMORY |
- OV5_DONATE_DEDICATE_CPU | OV5_MSI,
+ OV5_FEAT(OV5_LPAR) | OV5_FEAT(OV5_SPLPAR) | OV5_FEAT(OV5_LARGE_PAGES) |
+ OV5_FEAT(OV5_DRCONF_MEMORY) | OV5_FEAT(OV5_DONATE_DEDICATE_CPU) |
+#ifdef CONFIG_PCI_MSI
+ /* PCIe/MSI support. Without MSI full PCIe is not supported */
+ OV5_FEAT(OV5_MSI),
+#else
+ 0,
+#endif
+ 0,
+#ifdef CONFIG_PPC_SMLPAR
+ OV5_FEAT(OV5_CMO) | OV5_FEAT(OV5_XCMO),
+#else
0,
- OV5_CMO | OV5_XCMO,
- OV5_TYPE1_AFFINITY,
+#endif
+ OV5_FEAT(OV5_TYPE1_AFFINITY),
0,
0,
0,
@@ -702,8 +712,9 @@
0,
0,
0,
- OV5_PFO_HW_RNG | OV5_PFO_HW_ENCR | OV5_PFO_HW_842,
- OV5_SUB_PROCESSORS,
+ OV5_FEAT(OV5_PFO_HW_RNG) | OV5_FEAT(OV5_PFO_HW_ENCR) |
+ OV5_FEAT(OV5_PFO_HW_842),
+ OV5_FEAT(OV5_SUB_PROCESSORS),
/* option vector 6: IBM PAPR hints */
4 - 2, /* length */
0,
Index: powerpc/arch/powerpc/platforms/pseries/setup.c
===================================================================
--- powerpc.orig/arch/powerpc/platforms/pseries/setup.c 2013-04-23 14:17:16.000000000 -0500
+++ powerpc/arch/powerpc/platforms/pseries/setup.c 2013-04-23 14:46:23.000000000 -0500
@@ -628,25 +628,39 @@
* Called very early, MMU is off, device-tree isn't unflattened
*/
-static int __init pSeries_probe_hypertas(unsigned long node,
- const char *uname, int depth,
- void *data)
+static int __init pseries_probe_fw_features(unsigned long node,
+ const char *uname, int depth,
+ void *data)
{
- const char *hypertas;
+ const char *prop;
unsigned long len;
+ static int hypertas_found;
+ static int vec5_found;
- if (depth != 1 ||
- (strcmp(uname, "rtas") != 0 && strcmp(uname, "rtas@0") != 0))
+ if (depth != 1)
return 0;
- hypertas = of_get_flat_dt_prop(node, "ibm,hypertas-functions", &len);
- if (!hypertas)
- return 1;
+ if (!strcmp(uname, "rtas") || !strcmp(uname, "rtas@0")) {
+ prop = of_get_flat_dt_prop(node, "ibm,hypertas-functions",
+ &len);
+ if (prop) {
+ powerpc_firmware_features |= FW_FEATURE_LPAR;
+ fw_hypertas_feature_init(prop, len);
+ }
+
+ hypertas_found = 1;
+ }
+
+ if (!strcmp(uname, "chosen")) {
+ prop = of_get_flat_dt_prop(node, "ibm,architecture-vec-5",
+ &len);
+ if (prop)
+ fw_vec5_feature_init(prop, len);
- powerpc_firmware_features |= FW_FEATURE_LPAR;
- fw_feature_init(hypertas, len);
+ vec5_found = 1;
+ }
- return 1;
+ return hypertas_found && vec5_found;
}
static int __init pSeries_probe(void)
@@ -669,7 +683,7 @@
pr_debug("pSeries detected, looking for LPAR capability...\n");
/* Now try to figure out if we are running on LPAR */
- of_scan_flat_dt(pSeries_probe_hypertas, NULL);
+ of_scan_flat_dt(pseries_probe_fw_features, NULL);
if (firmware_has_feature(FW_FEATURE_LPAR))
hpte_init_lpar();
Index: powerpc/arch/powerpc/platforms/pseries/firmware.c
===================================================================
--- powerpc.orig/arch/powerpc/platforms/pseries/firmware.c 2013-04-23 14:46:10.000000000 -0500
+++ powerpc/arch/powerpc/platforms/pseries/firmware.c 2013-04-23 14:56:46.000000000 -0500
@@ -28,18 +28,18 @@
#include "pseries.h"
-typedef struct {
+struct hypertas_fw_feature {
unsigned long val;
char * name;
-} firmware_feature_t;
+};
/*
* The names in this table match names in rtas/ibm,hypertas-functions. If the
* entry ends in a '*', only upto the '*' is matched. Otherwise the entire
* string must match.
*/
-static __initdata firmware_feature_t
-firmware_features_table[] = {
+static __initdata struct hypertas_fw_feature
+hypertas_fw_features_table[] = {
{FW_FEATURE_PFT, "hcall-pft"},
{FW_FEATURE_TCE, "hcall-tce"},
{FW_FEATURE_SPRG0, "hcall-sprg0"},
@@ -69,16 +69,16 @@
* device-tree/ibm,hypertas-functions. Ultimately this functionality may
* be moved into prom.c prom_init().
*/
-void __init fw_feature_init(const char *hypertas, unsigned long len)
+void __init fw_hypertas_feature_init(const char *hypertas, unsigned long len)
{
const char *s;
int i;
- pr_debug(" -> fw_feature_init()\n");
+ pr_debug(" -> fw_hypertas_feature_init()\n");
for (s = hypertas; s < hypertas + len; s += strlen(s) + 1) {
- for (i = 0; i < ARRAY_SIZE(firmware_features_table); i++) {
- const char *name = firmware_features_table[i].name;
+ for (i = 0; i < ARRAY_SIZE(hypertas_fw_features_table); i++) {
+ const char *name = hypertas_fw_features_table[i].name;
size_t size;
/*
@@ -94,10 +94,39 @@
/* we have a match */
powerpc_firmware_features |=
- firmware_features_table[i].val;
+ hypertas_fw_features_table[i].val;
break;
}
}
- pr_debug(" <- fw_feature_init()\n");
+ pr_debug(" <- fw_hypertas_feature_init()\n");
+}
+
+struct vec5_fw_feature {
+ unsigned long val;
+ unsigned int feature;
+};
+
+static __initdata struct vec5_fw_feature
+vec5_fw_features_table[] = {
+ {FW_FEATURE_TYPE1_AFFINITY, OV5_TYPE1_AFFINITY},
+};
+
+void __init fw_vec5_feature_init(const char *vec5, unsigned long len)
+{
+ unsigned int index, feat;
+ int i;
+
+ pr_debug(" -> fw_vec5_feature_init()\n");
+
+ for (i = 0; i < ARRAY_SIZE(vec5_fw_features_table); i++) {
+ index = OV5_INDX(vec5_fw_features_table[i].feature);
+ feat = OV5_FEAT(vec5_fw_features_table[i].feature);
+
+ if (vec5[index] & feat)
+ powerpc_firmware_features |=
+ vec5_fw_features_table[i].val;
+ }
+
+ pr_debug(" <- fw_vec5_feature_init()\n");
}
Index: powerpc/arch/powerpc/include/asm/firmware.h
===================================================================
--- powerpc.orig/arch/powerpc/include/asm/firmware.h 2013-04-23 14:19:54.000000000 -0500
+++ powerpc/arch/powerpc/include/asm/firmware.h 2013-04-23 14:46:23.000000000 -0500
@@ -50,6 +50,7 @@
#define FW_FEATURE_OPALv2 ASM_CONST(0x0000000020000000)
#define FW_FEATURE_SET_MODE ASM_CONST(0x0000000040000000)
#define FW_FEATURE_BEST_ENERGY ASM_CONST(0x0000000080000000)
+#define FW_FEATURE_TYPE1_AFFINITY ASM_CONST(0x0000000100000000)
#ifndef __ASSEMBLY__
@@ -64,7 +65,8 @@
FW_FEATURE_BULK_REMOVE | FW_FEATURE_XDABR |
FW_FEATURE_MULTITCE | FW_FEATURE_SPLPAR | FW_FEATURE_LPAR |
FW_FEATURE_CMO | FW_FEATURE_VPHN | FW_FEATURE_XCMO |
- FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY,
+ FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY |
+ FW_FEATURE_TYPE1_AFFINITY,
FW_FEATURE_PSERIES_ALWAYS = 0,
FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_OPALv2,
FW_FEATURE_POWERNV_ALWAYS = 0,
Index: powerpc/arch/powerpc/platforms/pseries/pseries.h
===================================================================
--- powerpc.orig/arch/powerpc/platforms/pseries/pseries.h 2013-04-23 14:17:16.000000000 -0500
+++ powerpc/arch/powerpc/platforms/pseries/pseries.h 2013-04-23 14:46:23.000000000 -0500
@@ -19,7 +19,10 @@
#include <linux/of.h>
-extern void __init fw_feature_init(const char *hypertas, unsigned long len);
+extern void __init fw_hypertas_feature_init(const char *hypertas,
+ unsigned long len);
+extern void __init fw_vec5_feature_init(const char *hypertas,
+ unsigned long len);
struct pt_regs;
^ permalink raw reply [flat|nested] 16+ messages in thread* [PATCH v4 7/13] Update numa.c to use updated firmware_has_feature()
2013-04-24 15:34 [PATCH v4 0/13] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
` (5 preceding siblings ...)
2013-04-24 15:57 ` [PATCH v4 6/13] Update firmware_has_feature() to check architecture vector 5 bits Nathan Fontenot
@ 2013-04-24 15:58 ` Nathan Fontenot
2013-04-24 16:00 ` [PATCH v4 8/13] Update CPU maps when device tree is updated Nathan Fontenot
` (5 subsequent siblings)
12 siblings, 0 replies; 16+ messages in thread
From: Nathan Fontenot @ 2013-04-24 15:58 UTC (permalink / raw)
To: linuxppc-dev
Update the numa code to use the updated firmware_has_feature() when checking
for type 1 affinity.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
---
arch/powerpc/mm/numa.c | 22 +++-------------------
1 file changed, 3 insertions(+), 19 deletions(-)
Index: powerpc/arch/powerpc/mm/numa.c
===================================================================
--- powerpc.orig/arch/powerpc/mm/numa.c 2013-04-23 12:54:23.000000000 -0500
+++ powerpc/arch/powerpc/mm/numa.c 2013-04-23 15:19:15.000000000 -0500
@@ -291,9 +291,7 @@
static int __init find_min_common_depth(void)
{
int depth;
- struct device_node *chosen;
struct device_node *root;
- const char *vec5;
if (firmware_has_feature(FW_FEATURE_OPAL))
root = of_find_node_by_path("/ibm,opal");
@@ -325,24 +323,10 @@
distance_ref_points_depth /= sizeof(int);
-#define VEC5_AFFINITY_BYTE 5
-#define VEC5_AFFINITY 0x80
-
- if (firmware_has_feature(FW_FEATURE_OPAL))
+ if (firmware_has_feature(FW_FEATURE_OPAL) ||
+ firmware_has_feature(FW_FEATURE_TYPE1_AFFINITY)) {
+ dbg("Using form 1 affinity\n");
form1_affinity = 1;
- else {
- chosen = of_find_node_by_path("/chosen");
- if (chosen) {
- vec5 = of_get_property(chosen,
- "ibm,architecture-vec-5", NULL);
- if (vec5 && (vec5[VEC5_AFFINITY_BYTE] &
- VEC5_AFFINITY)) {
- dbg("Using form 1 affinity\n");
- form1_affinity = 1;
- }
-
- of_node_put(chosen);
- }
}
if (form1_affinity) {
^ permalink raw reply [flat|nested] 16+ messages in thread* [PATCH v4 8/13] Update CPU maps when device tree is updated
2013-04-24 15:34 [PATCH v4 0/13] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
` (6 preceding siblings ...)
2013-04-24 15:58 ` [PATCH v4 7/13] Update numa.c to use updated firmware_has_feature() Nathan Fontenot
@ 2013-04-24 16:00 ` Nathan Fontenot
2013-04-24 16:02 ` [PATCH v4 9/13] Use stop machine to update cpu maps Nathan Fontenot
` (4 subsequent siblings)
12 siblings, 0 replies; 16+ messages in thread
From: Nathan Fontenot @ 2013-04-24 16:00 UTC (permalink / raw)
To: linuxppc-dev
From: Jesse Larrew <jlarrew@linux.vnet.ibm.com>
Platform events such as partition migration or the new PRRN firmware
feature can cause the NUMA characteristics of a CPU to change, and these
changes will be reflected in the device tree nodes for the affected
CPUs.
This patch registers a handler for Open Firmware device tree updates
and reconfigures the CPU and node maps whenever the associativity
changes. Currently, this is accomplished by marking the affected CPUs in
the cpu_associativity_changes_mask and allowing
arch_update_cpu_topology() to retrieve the new associativity information
using hcall_vphn().
Protecting the NUMA cpu maps from concurrent access during an update
operation will be addressed in a subsequent patch in this series.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/firmware.h | 3
arch/powerpc/include/asm/prom.h | 1
arch/powerpc/mm/numa.c | 99 ++++++++++++++++++++++--------
arch/powerpc/platforms/pseries/firmware.c | 1
4 files changed, 79 insertions(+), 25 deletions(-)
Index: powerpc/arch/powerpc/include/asm/prom.h
===================================================================
--- powerpc.orig/arch/powerpc/include/asm/prom.h 2013-04-23 14:46:23.000000000 -0500
+++ powerpc/arch/powerpc/include/asm/prom.h 2013-04-23 15:20:18.000000000 -0500
@@ -128,6 +128,7 @@
#define OV5_CMO 0x0480 /* Cooperative Memory Overcommitment */
#define OV5_XCMO 0x0440 /* Page Coalescing */
#define OV5_TYPE1_AFFINITY 0x0580 /* Type 1 NUMA affinity */
+#define OV5_PRRN 0x0540 /* Platform Resource Reassignment */
#define OV5_PFO_HW_RNG 0x0E80 /* PFO Random Number Generator */
#define OV5_PFO_HW_842 0x0E40 /* PFO Compression Accelerator */
#define OV5_PFO_HW_ENCR 0x0E20 /* PFO Encryption Accelerator */
Index: powerpc/arch/powerpc/mm/numa.c
===================================================================
--- powerpc.orig/arch/powerpc/mm/numa.c 2013-04-23 15:19:15.000000000 -0500
+++ powerpc/arch/powerpc/mm/numa.c 2013-04-23 15:20:18.000000000 -0500
@@ -1257,7 +1257,8 @@
static u8 vphn_cpu_change_counts[NR_CPUS][MAX_DISTANCE_REF_POINTS];
static cpumask_t cpu_associativity_changes_mask;
static int vphn_enabled;
-static void set_topology_timer(void);
+static int prrn_enabled;
+static void reset_topology_timer(void);
/*
* Store the current values of the associativity change counters in the
@@ -1293,11 +1294,9 @@
*/
static int update_cpu_associativity_changes_mask(void)
{
- int cpu, nr_cpus = 0;
+ int cpu;
cpumask_t *changes = &cpu_associativity_changes_mask;
- cpumask_clear(changes);
-
for_each_possible_cpu(cpu) {
int i, changed = 0;
u8 *counts = vphn_cpu_change_counts[cpu];
@@ -1311,11 +1310,10 @@
}
if (changed) {
cpumask_set_cpu(cpu, changes);
- nr_cpus++;
}
}
- return nr_cpus;
+ return cpumask_weight(changes);
}
/*
@@ -1416,7 +1414,7 @@
unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
struct device *dev;
- for_each_cpu(cpu,&cpu_associativity_changes_mask) {
+ for_each_cpu(cpu, &cpu_associativity_changes_mask) {
vphn_get_associativity(cpu, associativity);
nid = associativity_to_nid(associativity);
@@ -1438,6 +1436,7 @@
dev = get_cpu_device(cpu);
if (dev)
kobject_uevent(&dev->kobj, KOBJ_CHANGE);
+ cpumask_clear_cpu(cpu, &cpu_associativity_changes_mask);
changed = 1;
}
@@ -1457,37 +1456,80 @@
static void topology_timer_fn(unsigned long ignored)
{
- if (!vphn_enabled)
- return;
- if (update_cpu_associativity_changes_mask() > 0)
+ if (prrn_enabled && cpumask_weight(&cpu_associativity_changes_mask))
topology_schedule_update();
- set_topology_timer();
+ else if (vphn_enabled) {
+ if (update_cpu_associativity_changes_mask() > 0)
+ topology_schedule_update();
+ reset_topology_timer();
+ }
}
static struct timer_list topology_timer =
TIMER_INITIALIZER(topology_timer_fn, 0, 0);
-static void set_topology_timer(void)
+static void reset_topology_timer(void)
{
topology_timer.data = 0;
topology_timer.expires = jiffies + 60 * HZ;
- add_timer(&topology_timer);
+ mod_timer(&topology_timer, topology_timer.expires);
+}
+
+static void stage_topology_update(int core_id)
+{
+ cpumask_or(&cpu_associativity_changes_mask,
+ &cpu_associativity_changes_mask, cpu_sibling_mask(core_id));
+ reset_topology_timer();
}
+static int dt_update_callback(struct notifier_block *nb,
+ unsigned long action, void *data)
+{
+ struct of_prop_reconfig *update;
+ int rc = NOTIFY_DONE;
+
+ switch (action) {
+ case OF_RECONFIG_ADD_PROPERTY:
+ case OF_RECONFIG_UPDATE_PROPERTY:
+ update = (struct of_prop_reconfig *)data;
+ if (!of_prop_cmp(update->dn->type, "cpu")) {
+ u32 core_id;
+ of_property_read_u32(update->dn, "reg", &core_id);
+ stage_topology_update(core_id);
+ rc = NOTIFY_OK;
+ }
+ break;
+ }
+
+ return rc;
+}
+
+static struct notifier_block dt_update_nb = {
+ .notifier_call = dt_update_callback,
+};
+
/*
- * Start polling for VPHN associativity changes.
+ * Start polling for associativity changes.
*/
int start_topology_update(void)
{
int rc = 0;
- /* Disabled until races with load balancing are fixed */
- if (0 && firmware_has_feature(FW_FEATURE_VPHN) &&
- get_lppaca()->shared_proc) {
- vphn_enabled = 1;
- setup_cpu_associativity_change_counters();
- init_timer_deferrable(&topology_timer);
- set_topology_timer();
- rc = 1;
+ if (firmware_has_feature(FW_FEATURE_PRRN)) {
+ if (!prrn_enabled) {
+ prrn_enabled = 1;
+ vphn_enabled = 0;
+ rc = of_reconfig_notifier_register(&dt_update_nb);
+ }
+ } else if (0 && firmware_has_feature(FW_FEATURE_VPHN) &&
+ get_lppaca()->shared_proc) {
+ /* Disabled until races with load balancing are fixed */
+ if (!vphn_enabled) {
+ prrn_enabled = 0;
+ vphn_enabled = 1;
+ setup_cpu_associativity_change_counters();
+ init_timer_deferrable(&topology_timer);
+ reset_topology_timer();
+ }
}
return rc;
@@ -1499,7 +1541,16 @@
*/
int stop_topology_update(void)
{
- vphn_enabled = 0;
- return del_timer_sync(&topology_timer);
+ int rc = 0;
+
+ if (prrn_enabled) {
+ prrn_enabled = 0;
+ rc = of_reconfig_notifier_unregister(&dt_update_nb);
+ } else if (vphn_enabled) {
+ vphn_enabled = 0;
+ rc = del_timer_sync(&topology_timer);
+ }
+
+ return rc;
}
#endif /* CONFIG_PPC_SPLPAR */
Index: powerpc/arch/powerpc/include/asm/firmware.h
===================================================================
--- powerpc.orig/arch/powerpc/include/asm/firmware.h 2013-04-23 14:46:23.000000000 -0500
+++ powerpc/arch/powerpc/include/asm/firmware.h 2013-04-23 15:20:18.000000000 -0500
@@ -51,6 +51,7 @@
#define FW_FEATURE_SET_MODE ASM_CONST(0x0000000040000000)
#define FW_FEATURE_BEST_ENERGY ASM_CONST(0x0000000080000000)
#define FW_FEATURE_TYPE1_AFFINITY ASM_CONST(0x0000000100000000)
+#define FW_FEATURE_PRRN ASM_CONST(0x0000000200000000)
#ifndef __ASSEMBLY__
@@ -66,7 +67,7 @@
FW_FEATURE_MULTITCE | FW_FEATURE_SPLPAR | FW_FEATURE_LPAR |
FW_FEATURE_CMO | FW_FEATURE_VPHN | FW_FEATURE_XCMO |
FW_FEATURE_SET_MODE | FW_FEATURE_BEST_ENERGY |
- FW_FEATURE_TYPE1_AFFINITY,
+ FW_FEATURE_TYPE1_AFFINITY | FW_FEATURE_PRRN,
FW_FEATURE_PSERIES_ALWAYS = 0,
FW_FEATURE_POWERNV_POSSIBLE = FW_FEATURE_OPAL | FW_FEATURE_OPALv2,
FW_FEATURE_POWERNV_ALWAYS = 0,
Index: powerpc/arch/powerpc/platforms/pseries/firmware.c
===================================================================
--- powerpc.orig/arch/powerpc/platforms/pseries/firmware.c 2013-04-23 14:56:46.000000000 -0500
+++ powerpc/arch/powerpc/platforms/pseries/firmware.c 2013-04-23 15:20:18.000000000 -0500
@@ -110,6 +110,7 @@
static __initdata struct vec5_fw_feature
vec5_fw_features_table[] = {
{FW_FEATURE_TYPE1_AFFINITY, OV5_TYPE1_AFFINITY},
+ {FW_FEATURE_PRRN, OV5_PRRN},
};
void __init fw_vec5_feature_init(const char *vec5, unsigned long len)
^ permalink raw reply [flat|nested] 16+ messages in thread* [PATCH v4 9/13] Use stop machine to update cpu maps
2013-04-24 15:34 [PATCH v4 0/13] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
` (7 preceding siblings ...)
2013-04-24 16:00 ` [PATCH v4 8/13] Update CPU maps when device tree is updated Nathan Fontenot
@ 2013-04-24 16:02 ` Nathan Fontenot
2013-04-24 16:03 ` [PATCH v4 10/13] Update NUMA VDSO information when updating CPU maps Nathan Fontenot
` (3 subsequent siblings)
12 siblings, 0 replies; 16+ messages in thread
From: Nathan Fontenot @ 2013-04-24 16:02 UTC (permalink / raw)
To: linuxppc-dev
The new PRRN firmware feature allows CPU and memory resources to be
transparently reassigned across NUMA boundaries. When this happens, the
kernel must update the node maps to reflect the new affinity information.
Although the NUMA maps can be protected by locking primitives during the
update itself, this is insufficient to prevent concurrent accesses to these
structures. Since cpumask_of_node() hands out a pointer to these
structures, they can still be modified outside of the lock. Furthermore,
tracking down each usage of these pointers and adding locks would be quite
invasive and difficult to maintain.
The approach used is to make a list of affected cpus and call stop_machine
to have the update routine run on each of the affected cpus allowing them
to update themselves. Each cpu finds itself in the list of cpus and makes
the appropriate updates. We need to have each cpu do this for themselves to
handle calls to vdso_getcpu_init() added in a subsequent patch.
Situations like these are best handled using stop_machine(). Since the NUMA
affinity updates are exceptionally rare events, this approach has the
benefit of not adding any overhead while accessing the NUMA maps during
normal operation.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
---
arch/powerpc/mm/numa.c | 82 ++++++++++++++++++++++++++++++++++++++-----------
1 file changed, 64 insertions(+), 18 deletions(-)
Index: powerpc/arch/powerpc/mm/numa.c
===================================================================
--- powerpc.orig/arch/powerpc/mm/numa.c 2013-04-23 15:20:18.000000000 -0500
+++ powerpc/arch/powerpc/mm/numa.c 2013-04-23 15:26:54.000000000 -0500
@@ -22,6 +22,7 @@
#include <linux/pfn.h>
#include <linux/cpuset.h>
#include <linux/node.h>
+#include <linux/stop_machine.h>
#include <asm/sparsemem.h>
#include <asm/prom.h>
#include <asm/smp.h>
@@ -1254,6 +1255,13 @@
/* Virtual Processor Home Node (VPHN) support */
#ifdef CONFIG_PPC_SPLPAR
+struct topology_update_data {
+ struct topology_update_data *next;
+ unsigned int cpu;
+ int old_nid;
+ int new_nid;
+};
+
static u8 vphn_cpu_change_counts[NR_CPUS][MAX_DISTANCE_REF_POINTS];
static cpumask_t cpu_associativity_changes_mask;
static int vphn_enabled;
@@ -1405,41 +1413,79 @@
}
/*
+ * Update the CPU maps and sysfs entries for a single CPU when its NUMA
+ * characteristics change. This function doesn't perform any locking and is
+ * only safe to call from stop_machine().
+ */
+static int update_cpu_topology(void *data)
+{
+ struct topology_update_data *update;
+ unsigned long cpu;
+
+ if (!data)
+ return -EINVAL;
+
+ cpu = get_cpu();
+
+ for (update = data; update; update = update->next) {
+ if (cpu != update->cpu)
+ continue;
+
+ unregister_cpu_under_node(update->cpu, update->old_nid);
+ unmap_cpu_from_node(update->cpu);
+ map_cpu_to_node(update->cpu, update->new_nid);
+ register_cpu_under_node(update->cpu, update->new_nid);
+ }
+
+ return 0;
+}
+
+/*
* Update the node maps and sysfs entries for each cpu whose home node
* has changed. Returns 1 when the topology has changed, and 0 otherwise.
*/
int arch_update_cpu_topology(void)
{
- int cpu, nid, old_nid, changed = 0;
+ unsigned int cpu, changed = 0;
+ struct topology_update_data *updates, *ud;
unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
struct device *dev;
+ int weight, i = 0;
+
+ weight = cpumask_weight(&cpu_associativity_changes_mask);
+ if (!weight)
+ return 0;
+
+ updates = kzalloc(weight * (sizeof(*updates)), GFP_KERNEL);
+ if (!updates)
+ return 0;
for_each_cpu(cpu, &cpu_associativity_changes_mask) {
+ ud = &updates[i++];
+ ud->cpu = cpu;
vphn_get_associativity(cpu, associativity);
- nid = associativity_to_nid(associativity);
+ ud->new_nid = associativity_to_nid(associativity);
- if (nid < 0 || !node_online(nid))
- nid = first_online_node;
+ if (ud->new_nid < 0 || !node_online(ud->new_nid))
+ ud->new_nid = first_online_node;
- old_nid = numa_cpu_lookup_table[cpu];
+ ud->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();
+ if (i < weight)
+ ud->next = &updates[i];
+ }
+
+ stop_machine(update_cpu_topology, &updates[0], cpu_online_mask);
- dev = get_cpu_device(cpu);
+ for (ud = &updates[0]; ud; ud = ud->next) {
+ dev = get_cpu_device(ud->cpu);
if (dev)
kobject_uevent(&dev->kobj, KOBJ_CHANGE);
- cpumask_clear_cpu(cpu, &cpu_associativity_changes_mask);
+ cpumask_clear_cpu(ud->cpu, &cpu_associativity_changes_mask);
changed = 1;
}
+ kfree(updates);
return changed;
}
@@ -1488,10 +1534,10 @@
int rc = NOTIFY_DONE;
switch (action) {
- case OF_RECONFIG_ADD_PROPERTY:
case OF_RECONFIG_UPDATE_PROPERTY:
update = (struct of_prop_reconfig *)data;
- if (!of_prop_cmp(update->dn->type, "cpu")) {
+ if (!of_prop_cmp(update->dn->type, "cpu") &&
+ !of_prop_cmp(update->prop->name, "ibm,associativity")) {
u32 core_id;
of_property_read_u32(update->dn, "reg", &core_id);
stage_topology_update(core_id);
^ permalink raw reply [flat|nested] 16+ messages in thread* [PATCH v4 10/13] Update NUMA VDSO information when updating CPU maps
2013-04-24 15:34 [PATCH v4 0/13] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
` (8 preceding siblings ...)
2013-04-24 16:02 ` [PATCH v4 9/13] Use stop machine to update cpu maps Nathan Fontenot
@ 2013-04-24 16:03 ` Nathan Fontenot
2013-04-24 16:05 ` [PATCH v4 11/13] RE-enable Virtual Processor Home Node updating Nathan Fontenot
` (2 subsequent siblings)
12 siblings, 0 replies; 16+ messages in thread
From: Nathan Fontenot @ 2013-04-24 16:03 UTC (permalink / raw)
To: linuxppc-dev
From: Jesse Larrew <jlarrew@linux.vnet.ibm.com>
The following patch adds vdso_getcpu_init(), which stores the NUMA node for
a cpu in SPRG3:
Commit 18ad51dd34 ("powerpc: Add VDSO version of getcpu") adds
vdso_getcpu_init(), which stores the NUMA node for a cpu in SPRG3.
This patch ensures that this information is also updated when the NUMA
affinity of a cpu changes.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
---
arch/powerpc/mm/numa.c | 8 +++++++-
1 file changed, 7 insertions(+), 1 deletion(-)
Index: powerpc/arch/powerpc/mm/numa.c
===================================================================
--- powerpc.orig/arch/powerpc/mm/numa.c 2013-04-23 15:26:54.000000000 -0500
+++ powerpc/arch/powerpc/mm/numa.c 2013-04-23 15:28:21.000000000 -0500
@@ -30,6 +30,7 @@
#include <asm/paca.h>
#include <asm/hvcall.h>
#include <asm/setup.h>
+#include <asm/vdso.h>
static int numa_enabled = 1;
@@ -1434,6 +1435,7 @@
unregister_cpu_under_node(update->cpu, update->old_nid);
unmap_cpu_from_node(update->cpu);
map_cpu_to_node(update->cpu, update->new_nid);
+ vdso_getcpu_init();
register_cpu_under_node(update->cpu, update->new_nid);
}
@@ -1449,6 +1451,7 @@
unsigned int cpu, changed = 0;
struct topology_update_data *updates, *ud;
unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
+ cpumask_t updated_cpus;
struct device *dev;
int weight, i = 0;
@@ -1460,6 +1463,8 @@
if (!updates)
return 0;
+ cpumask_clear(&updated_cpus);
+
for_each_cpu(cpu, &cpu_associativity_changes_mask) {
ud = &updates[i++];
ud->cpu = cpu;
@@ -1470,12 +1475,13 @@
ud->new_nid = first_online_node;
ud->old_nid = numa_cpu_lookup_table[cpu];
+ cpumask_set_cpu(cpu, &updated_cpus);
if (i < weight)
ud->next = &updates[i];
}
- stop_machine(update_cpu_topology, &updates[0], cpu_online_mask);
+ stop_machine(update_cpu_topology, &updates[0], &updated_cpus);
for (ud = &updates[0]; ud; ud = ud->next) {
dev = get_cpu_device(ud->cpu);
^ permalink raw reply [flat|nested] 16+ messages in thread* [PATCH v4 11/13] RE-enable Virtual Processor Home Node updating
2013-04-24 15:34 [PATCH v4 0/13] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
` (9 preceding siblings ...)
2013-04-24 16:03 ` [PATCH v4 10/13] Update NUMA VDSO information when updating CPU maps Nathan Fontenot
@ 2013-04-24 16:05 ` Nathan Fontenot
2013-04-24 16:06 ` [PATCH v4 12/13] Enable PRRN handling Nathan Fontenot
2013-04-24 16:07 ` [PATCH v4 13/13] Add /proc interface to control topology updates Nathan Fontenot
12 siblings, 0 replies; 16+ messages in thread
From: Nathan Fontenot @ 2013-04-24 16:05 UTC (permalink / raw)
To: linuxppc-dev
From: Jesse Larrew <jlarrew@linux.vnet.ibm.com>
The new PRRN firmware feature provides a more convenient and event-driven
interface than VPHN for notifying Linux of changes to the NUMA affinity of
platform resources. However, for practical reasons, it may not be feasible
for some customers to update to the latest firmware. For these customers,
the VPHN feature supported on previous firmware versions may still be the
best option.
The VPHN feature was previously disabled due to races with the load
balancing code when accessing the NUMA cpu maps, but the new stop_machine()
approach protects the NUMA cpu maps from these concurrent accesses. It
should be safe to re-enable this feature now.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
---
arch/powerpc/mm/numa.c | 3 +--
1 file changed, 1 insertion(+), 2 deletions(-)
Index: powerpc/arch/powerpc/mm/numa.c
===================================================================
--- powerpc.orig/arch/powerpc/mm/numa.c 2013-04-23 15:28:21.000000000 -0500
+++ powerpc/arch/powerpc/mm/numa.c 2013-04-23 15:29:39.000000000 -0500
@@ -1572,9 +1572,8 @@
vphn_enabled = 0;
rc = of_reconfig_notifier_register(&dt_update_nb);
}
- } else if (0 && firmware_has_feature(FW_FEATURE_VPHN) &&
+ } else if (firmware_has_feature(FW_FEATURE_VPHN) &&
get_lppaca()->shared_proc) {
- /* Disabled until races with load balancing are fixed */
if (!vphn_enabled) {
prrn_enabled = 0;
vphn_enabled = 1;
^ permalink raw reply [flat|nested] 16+ messages in thread* [PATCH v4 12/13] Enable PRRN handling
2013-04-24 15:34 [PATCH v4 0/13] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
` (10 preceding siblings ...)
2013-04-24 16:05 ` [PATCH v4 11/13] RE-enable Virtual Processor Home Node updating Nathan Fontenot
@ 2013-04-24 16:06 ` Nathan Fontenot
2013-04-24 16:07 ` [PATCH v4 13/13] Add /proc interface to control topology updates Nathan Fontenot
12 siblings, 0 replies; 16+ messages in thread
From: Nathan Fontenot @ 2013-04-24 16:06 UTC (permalink / raw)
To: linuxppc-dev
The Linux kernel and platform firmware negotiate their mutual support
of the PRRN option via the ibm,client-architecture-support interface.
This patch simply sets the appropriate fields in the client architecture
vector to indicate Linux support for PRRN and will allow the firmware to
report PRRN events via the RTAS event-scan mechanism.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
---
arch/powerpc/kernel/prom_init.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
Index: powerpc/arch/powerpc/kernel/prom_init.c
===================================================================
--- powerpc.orig/arch/powerpc/kernel/prom_init.c 2013-04-23 14:46:23.000000000 -0500
+++ powerpc/arch/powerpc/kernel/prom_init.c 2013-04-23 15:30:36.000000000 -0500
@@ -698,7 +698,7 @@
#else
0,
#endif
- OV5_FEAT(OV5_TYPE1_AFFINITY),
+ OV5_FEAT(OV5_TYPE1_AFFINITY) | OV5_FEAT(OV5_PRRN),
0,
0,
0,
^ permalink raw reply [flat|nested] 16+ messages in thread* [PATCH v4 13/13] Add /proc interface to control topology updates
2013-04-24 15:34 [PATCH v4 0/13] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
` (11 preceding siblings ...)
2013-04-24 16:06 ` [PATCH v4 12/13] Enable PRRN handling Nathan Fontenot
@ 2013-04-24 16:07 ` Nathan Fontenot
12 siblings, 0 replies; 16+ messages in thread
From: Nathan Fontenot @ 2013-04-24 16:07 UTC (permalink / raw)
To: linuxppc-dev
There are instances in which we do not want topology updates to occur.
In order to allow this a /proc interface (/proc/powerpc/topology_updates)
is introduced so that topology updates can be enabled and disabled.
This patch also adds a prrn_is_enabled() call so that PRRN events are
handled in the kernel only if topology updating is enabled.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/topology.h | 5 ++
arch/powerpc/kernel/rtasd.c | 7 ++--
arch/powerpc/mm/numa.c | 62 +++++++++++++++++++++++++++++++++++-
3 files changed, 71 insertions(+), 3 deletions(-)
Index: powerpc/arch/powerpc/mm/numa.c
===================================================================
--- powerpc.orig/arch/powerpc/mm/numa.c 2013-04-23 15:29:39.000000000 -0500
+++ powerpc/arch/powerpc/mm/numa.c 2013-04-23 19:30:33.000000000 -0500
@@ -23,6 +23,9 @@
#include <linux/cpuset.h>
#include <linux/node.h>
#include <linux/stop_machine.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <linux/uaccess.h>
#include <asm/sparsemem.h>
#include <asm/prom.h>
#include <asm/smp.h>
@@ -1585,7 +1588,6 @@
return rc;
}
-__initcall(start_topology_update);
/*
* Disable polling for VPHN associativity changes.
@@ -1604,4 +1606,62 @@
return rc;
}
+
+int prrn_is_enabled(void)
+{
+ return prrn_enabled;
+}
+
+static int topology_read(struct seq_file *file, void *v)
+{
+ if (vphn_enabled || prrn_enabled)
+ seq_puts(file, "on\n");
+ else
+ seq_puts(file, "off\n");
+
+ return 0;
+}
+
+static int topology_open(struct inode *inode, struct file *file)
+{
+ return single_open(file, topology_read, NULL);
+}
+
+static ssize_t topology_write(struct file *file, const char __user *buf,
+ size_t count, loff_t *off)
+{
+ char kbuf[4]; /* "on" or "off" plus null. */
+ int read_len;
+
+ read_len = count < 3 ? count : 3;
+ if (copy_from_user(kbuf, buf, read_len))
+ return -EINVAL;
+
+ kbuf[read_len] = '\0';
+
+ if (!strncmp(kbuf, "on", 2))
+ start_topology_update();
+ else if (!strncmp(kbuf, "off", 3))
+ stop_topology_update();
+ else
+ return -EINVAL;
+
+ return count;
+}
+
+static const struct file_operations topology_ops = {
+ .read = seq_read,
+ .write = topology_write,
+ .open = topology_open,
+ .release = single_release
+};
+
+static int topology_update_init(void)
+{
+ start_topology_update();
+ proc_create("powerpc/topology_updates", 644, NULL, &topology_ops);
+
+ return 0;
+}
+device_initcall(topology_update_init);
#endif /* CONFIG_PPC_SPLPAR */
Index: powerpc/arch/powerpc/include/asm/topology.h
===================================================================
--- powerpc.orig/arch/powerpc/include/asm/topology.h 2013-04-23 12:54:22.000000000 -0500
+++ powerpc/arch/powerpc/include/asm/topology.h 2013-04-23 19:31:57.000000000 -0500
@@ -71,6 +71,7 @@
#if defined(CONFIG_NUMA) && defined(CONFIG_PPC_SPLPAR)
extern int start_topology_update(void);
extern int stop_topology_update(void);
+extern int prrn_is_enabled(void);
#else
static inline int start_topology_update(void)
{
@@ -80,6 +81,10 @@
{
return 0;
}
+static inline int prrn_is_enabled(void)
+{
+ return 0;
+}
#endif /* CONFIG_NUMA && CONFIG_PPC_SPLPAR */
#include <asm-generic/topology.h>
Index: powerpc/arch/powerpc/kernel/rtasd.c
===================================================================
--- powerpc.orig/arch/powerpc/kernel/rtasd.c 2013-04-23 13:52:08.000000000 -0500
+++ powerpc/arch/powerpc/kernel/rtasd.c 2013-04-23 17:47:09.000000000 -0500
@@ -29,6 +29,7 @@
#include <asm/nvram.h>
#include <linux/atomic.h>
#include <asm/machdep.h>
+#include <asm/topology.h>
static DEFINE_SPINLOCK(rtasd_log_lock);
@@ -292,11 +293,13 @@
static void handle_rtas_event(const struct rtas_error_log *log)
{
- if (log->type == RTAS_TYPE_PRRN)
+ if (log->type == RTAS_TYPE_PRRN) {
/* For PRRN Events the extended log length is used to denote
* the scope for calling rtas update-nodes.
*/
- prrn_schedule_update(log->extended_log_length);
+ if (prrn_is_enabled())
+ prrn_schedule_update(log->extended_log_length);
+ }
return;
}
^ permalink raw reply [flat|nested] 16+ messages in thread