* [PATCH 0/11] NUMA CPU Reconfiguration using PRRN
@ 2013-03-09 3:56 Nathan Fontenot
2013-03-09 3:59 ` [PATCH 1/11] Expose pseries devicetree_update() Nathan Fontenot
` (10 more replies)
0 siblings, 11 replies; 24+ messages in thread
From: Nathan Fontenot @ 2013-03-09 3:56 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.
PRRN Events are RTAS events sent up through the event-scan mechanism on
Power. When these events are received the system needs can get the updated
device tree affinity information for the affected CPUs/memory via the
rtas update-nodes and update-properties calls. This information is then
used to update the NUMA affinity of the CPUs/Memory in the kernel.
This patch set adds the ability to recognize PRRN events, update the device
tree and kernel information for CPUs (memory will be handled in a later
patch), and add an interface to enable/disable toplogy updates from /proc.
Additionally, these updates solve an exisitng problem with the VPHN (Virtual
Processor Home Node) capability and allow us to re-enable this feature.
Nathan Fontenot
---
arch/powerpc/include/asm/prom.h | 42 +++--
arch/powerpc/include/asm/rtas.h | 2
arch/powerpc/kernel/prom_init.c | 89 +---------
arch/powerpc/kernel/rtasd.c | 35 ++++
arch/powerpc/mm/numa.c | 183 ++++++++++++++--------
powerpc/arch/powerpc/include/asm/prom.h | 73 ++++++++
powerpc/arch/powerpc/include/asm/rtas.h | 1
powerpc/arch/powerpc/include/asm/topology.h | 5
powerpc/arch/powerpc/kernel/prom.c | 19 ++
powerpc/arch/powerpc/kernel/prom_init.c | 2
powerpc/arch/powerpc/kernel/rtasd.c | 6
powerpc/arch/powerpc/mm/numa.c | 62 +++++++
powerpc/arch/powerpc/platforms/pseries/mobility.c | 21 +-
13 files changed, 372 insertions(+), 168 deletions(-)
^ permalink raw reply [flat|nested] 24+ messages in thread
* [PATCH 1/11] Expose pseries devicetree_update()
2013-03-09 3:56 [PATCH 0/11] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
@ 2013-03-09 3:59 ` Nathan Fontenot
2013-03-14 8:49 ` Paul Mackerras
2013-03-09 4:00 ` [PATCH2/11] Add PRRN Event Handler Nathan Fontenot
` (9 subsequent siblings)
10 siblings, 1 reply; 24+ messages in thread
From: Nathan Fontenot @ 2013-03-09 3:59 UTC (permalink / raw)
To: linuxppc-dev
From: Jesse Larrew <jlarrew@linux.vnet.ibm.com>
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_devtree_update() routine used in partition migration.
This patch simply exposes pseries_devicetree_update() so it can be
called by rtasd. pseries_devicetree_update() and supporting functions
are also modified to take a 32-bit 'scope' parameter. This parameter is
required by the ibm,update-nodes/ibm,update-properties RTAS calls, and
the appropriate value is contained within the RTAS event for PRRN
notifications. In pseries_devicetree_update() it was previously
hard-coded to 1, the scope value for partition migration.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/rtas.h | 1 +
arch/powerpc/platforms/pseries/mobility.c | 21 ++++++++++++---------
2 files changed, 13 insertions(+), 9 deletions(-)
Index: powerpc/arch/powerpc/include/asm/rtas.h
===================================================================
--- powerpc.orig/arch/powerpc/include/asm/rtas.h 2013-03-08 19:23:06.000000000 -0600
+++ powerpc/arch/powerpc/include/asm/rtas.h 2013-03-08 19:56:13.000000000 -0600
@@ -276,6 +276,7 @@
const char *uname, int depth, void *data);
extern void pSeries_log_error(char *buf, unsigned int err_type, int fatal);
+extern int pseries_devicetree_update(s32 scope);
#ifdef CONFIG_PPC_RTAS_DAEMON
extern void rtas_cancel_event_scan(void);
Index: powerpc/arch/powerpc/platforms/pseries/mobility.c
===================================================================
--- powerpc.orig/arch/powerpc/platforms/pseries/mobility.c 2013-03-08 19:23:07.000000000 -0600
+++ powerpc/arch/powerpc/platforms/pseries/mobility.c 2013-03-08 19:56:13.000000000 -0600
@@ -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);
^ permalink raw reply [flat|nested] 24+ messages in thread
* [PATCH2/11] Add PRRN Event Handler
2013-03-09 3:56 [PATCH 0/11] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
2013-03-09 3:59 ` [PATCH 1/11] Expose pseries devicetree_update() Nathan Fontenot
@ 2013-03-09 4:00 ` Nathan Fontenot
2013-03-14 8:51 ` Paul Mackerras
2013-03-09 4:01 ` [PATCH 3/11] Move architecture vector definitions to prom.h Nathan Fontenot
` (8 subsequent siblings)
10 siblings, 1 reply; 24+ messages in thread
From: Nathan Fontenot @ 2013-03-09 4:00 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 repurposed (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 in rtasd for PRRN 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 rtasd to continue processing events.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/rtas.h | 2 ++
arch/powerpc/kernel/rtasd.c | 35 ++++++++++++++++++++++++++++++++++-
2 files changed, 36 insertions(+), 1 deletion(-)
Index: powerpc/arch/powerpc/include/asm/rtas.h
===================================================================
--- powerpc.orig/arch/powerpc/include/asm/rtas.h 2013-03-08 19:56:13.000000000 -0600
+++ powerpc/arch/powerpc/include/asm/rtas.h 2013-03-08 19:56:48.000000000 -0600
@@ -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 2013-03-08 19:23:06.000000000 -0600
+++ powerpc/arch/powerpc/kernel/rtasd.c 2013-03-08 19:56:48.000000000 -0600
@@ -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];
@@ -265,7 +267,38 @@
spin_unlock_irqrestore(&rtasd_log_lock, s);
return;
}
+}
+
+static s32 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(-update_scope);
+}
+static DECLARE_WORK(prrn_work, prrn_work_fn);
+
+void prrn_schedule_update(u32 scope)
+{
+ flush_work(&prrn_work);
+ update_scope = scope;
+ schedule_work(&prrn_work);
+}
+
+static void pseries_handle_event(const struct rtas_error_log *log)
+{
+ pSeries_log_error((char *)log, ERR_TYPE_RTAS_LOG, 0);
+
+ 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;
}
static int rtas_log_open(struct inode * inode, struct file * file)
@@ -389,7 +422,7 @@
}
if (error == 0)
- pSeries_log_error(logdata, ERR_TYPE_RTAS_LOG, 0);
+ pseries_handle_event((struct rtas_error_log *)logdata);
} while(error == 0);
}
^ permalink raw reply [flat|nested] 24+ messages in thread
* [PATCH 3/11] Move architecture vector definitions to prom.h
2013-03-09 3:56 [PATCH 0/11] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
2013-03-09 3:59 ` [PATCH 1/11] Expose pseries devicetree_update() Nathan Fontenot
2013-03-09 4:00 ` [PATCH2/11] Add PRRN Event Handler Nathan Fontenot
@ 2013-03-09 4:01 ` Nathan Fontenot
2013-03-14 8:52 ` Paul Mackerras
2013-03-09 4:02 ` [PATCH 4/11] Add platform_has_feature() Nathan Fontenot
` (7 subsequent siblings)
10 siblings, 1 reply; 24+ messages in thread
From: Nathan Fontenot @ 2013-03-09 4:01 UTC (permalink / raw)
To: linuxppc-dev
As part of handling of handling PRRN events we will need to check the
vector 5 portion of the architecture bits reported in the device tree
to ensure that PRRN event handling is enabled. In order to do this a
new platform_has_feature call is introduced (in a subsequent patch) to
make this check. To avoid having to re-define bits in the architecture
vector the bits are moved to prom.h.
This patch is the first step in implementing the platform_has_feature
call by simply moving the bit definitions from prom_init.c to asm/prom.h.
There are no functional.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/prom.h | 73 ++++++++++++++++++++++++++++++++++++++
arch/powerpc/kernel/prom_init.c | 75 +++-------------------------------------
2 files changed, 79 insertions(+), 69 deletions(-)
Index: powerpc/arch/powerpc/include/asm/prom.h
===================================================================
--- powerpc.orig/arch/powerpc/include/asm/prom.h 2013-03-08 19:23:06.000000000 -0600
+++ powerpc/arch/powerpc/include/asm/prom.h 2013-03-08 19:57:05.000000000 -0600
@@ -74,6 +74,79 @@
#define DRCONF_MEM_AI_INVALID 0x00000040
#define DRCONF_MEM_RESERVED 0x00000080
+#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. */
+
+/* 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[];
+#endif
+
/* 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 2013-03-08 19:23:06.000000000 -0600
+++ powerpc/arch/powerpc/kernel/prom_init.c 2013-03-08 19:57:05.000000000 -0600
@@ -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] 24+ messages in thread
* [PATCH 4/11] Add platform_has_feature()
2013-03-09 3:56 [PATCH 0/11] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
` (2 preceding siblings ...)
2013-03-09 4:01 ` [PATCH 3/11] Move architecture vector definitions to prom.h Nathan Fontenot
@ 2013-03-09 4:02 ` Nathan Fontenot
2013-03-14 8:56 ` Paul Mackerras
` (2 more replies)
2013-03-09 4:03 ` [PATCH 5/11] Update numa.c to use platform_has_feature() Nathan Fontenot
` (6 subsequent siblings)
10 siblings, 3 replies; 24+ messages in thread
From: Nathan Fontenot @ 2013-03-09 4:02 UTC (permalink / raw)
To: linuxppc-dev
The firmware_has_feature() function makes it easy to check for supported
features of the hardware. There is not corresponding function to check for
features supported by the client architecture.
This patch adds a platform_has_feature() function to check features selected
by firmware and reported via the device tree 'ibm,architecture-vec5'
property. As part of this the #defines used for the architecture vector are
moved to prom.h and re-defined such that the vector 5 options have the vector
index and the feature bits encoded into them. This allows for callers of
platform_has_feature() to pass in a single pre-defined value.
Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
---
arch/powerpc/include/asm/prom.h | 41 +++++++++++++++++++++++-----------------
arch/powerpc/kernel/prom.c | 19 ++++++++++++++++++
arch/powerpc/kernel/prom_init.c | 14 +++++++------
3 files changed, 51 insertions(+), 23 deletions(-)
Index: powerpc/arch/powerpc/include/asm/prom.h
===================================================================
--- powerpc.orig/arch/powerpc/include/asm/prom.h 2013-03-08 19:57:05.000000000 -0600
+++ powerpc/arch/powerpc/include/asm/prom.h 2013-03-08 19:57:14.000000000 -0600
@@ -111,31 +111,37 @@
/* 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 for the platform_has_feature() call 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 */
+#define OV5_DRCONF_MEMORY 0x0220
+#define OV5_LARGE_PAGES 0x0210 /* large pages supported */
+#define OV5_DONATE_DEDICATE_CPU 0x0202 /* 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 */
+#define OV5_MSI 0x0201 /* PCIe/MSI support */
#else
-#define OV5_MSI 0x00
+#define OV5_MSI 0x0200
#endif /* CONFIG_PCI_MSI */
#ifdef CONFIG_PPC_SMLPAR
-#define OV5_CMO 0x80 /* Cooperative Memory Overcommitment */
-#define OV5_XCMO 0x40 /* Page Coalescing */
+#define OV5_CMO 0x0480 /* Cooperative Memory Overcommitment */
+#define OV5_XCMO 0x0440 /* Page Coalescing */
#else
-#define OV5_CMO 0x00
-#define OV5_XCMO 0x00
+#define OV5_CMO 0x0400
+#define OV5_XCMO 0x0400
#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_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 */
@@ -145,6 +151,7 @@
* followed by # option vectors - 1, followed by the option vectors.
*/
extern unsigned char ibm_architecture_vec[];
+bool platform_has_feature(unsigned int);
#endif
/* These includes are put at the bottom because they may contain things
Index: powerpc/arch/powerpc/kernel/prom_init.c
===================================================================
--- powerpc.orig/arch/powerpc/kernel/prom_init.c 2013-03-08 19:57:05.000000000 -0600
+++ powerpc/arch/powerpc/kernel/prom_init.c 2013-03-08 19:57:14.000000000 -0600
@@ -684,11 +684,12 @@
/* 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) |
+ OV5_FEAT(OV5_MSI),
0,
- OV5_CMO | OV5_XCMO,
- OV5_TYPE1_AFFINITY,
+ OV5_FEAT(OV5_CMO) | OV5_FEAT(OV5_XCMO),
+ OV5_FEAT(OV5_TYPE1_AFFINITY),
0,
0,
0,
@@ -702,8 +703,9 @@
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/kernel/prom.c
===================================================================
--- powerpc.orig/arch/powerpc/kernel/prom.c 2013-03-08 19:23:06.000000000 -0600
+++ powerpc/arch/powerpc/kernel/prom.c 2013-03-08 19:57:14.000000000 -0600
@@ -871,6 +871,25 @@
}
EXPORT_SYMBOL(of_get_cpu_node);
+#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
+bool platform_has_feature(unsigned int feature)
+{
+ struct device_node *chosen;
+ const char *vec5;
+ bool has_option;
+
+ chosen = of_find_node_by_path("/chosen");
+ if (!chosen)
+ return false;
+
+ vec5 = of_get_property(chosen, "ibm,architecture-vec-5", NULL);
+ has_option = vec5 && (vec5[OV5_INDX(feature)] & OV5_FEAT(feature));
+ of_node_put(chosen);
+
+ return has_option;
+}
+#endif
+
#if defined(CONFIG_DEBUG_FS) && defined(DEBUG)
static struct debugfs_blob_wrapper flat_dt_blob;
^ permalink raw reply [flat|nested] 24+ messages in thread
* [PATCH 5/11] Update numa.c to use platform_has_feature()
2013-03-09 3:56 [PATCH 0/11] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
` (3 preceding siblings ...)
2013-03-09 4:02 ` [PATCH 4/11] Add platform_has_feature() Nathan Fontenot
@ 2013-03-09 4:03 ` Nathan Fontenot
2013-03-09 4:04 ` [PATCH 6/11] Update CPU maps Nathan Fontenot
` (5 subsequent siblings)
10 siblings, 0 replies; 24+ messages in thread
From: Nathan Fontenot @ 2013-03-09 4:03 UTC (permalink / raw)
To: linuxppc-dev
Update the numa code to use the new platform_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 2013-03-08 19:23:06.000000000 -0600
+++ powerpc/arch/powerpc/mm/numa.c 2013-03-08 19:57:27.000000000 -0600
@@ -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) ||
+ platform_has_feature(OV5_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] 24+ messages in thread
* [PATCH 6/11] Update CPU maps
2013-03-09 3:56 [PATCH 0/11] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
` (4 preceding siblings ...)
2013-03-09 4:03 ` [PATCH 5/11] Update numa.c to use platform_has_feature() Nathan Fontenot
@ 2013-03-09 4:04 ` Nathan Fontenot
2013-03-09 4:05 ` [PATCH 7/11] Use stop machine to update cpu maps Nathan Fontenot
` (4 subsequent siblings)
10 siblings, 0 replies; 24+ messages in thread
From: Nathan Fontenot @ 2013-03-09 4:04 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/prom.h | 1
arch/powerpc/mm/numa.c | 99 ++++++++++++++++++++++++++++++----------
2 files changed, 76 insertions(+), 24 deletions(-)
Index: powerpc/arch/powerpc/include/asm/prom.h
===================================================================
--- powerpc.orig/arch/powerpc/include/asm/prom.h 2013-03-08 19:57:14.000000000 -0600
+++ powerpc/arch/powerpc/include/asm/prom.h 2013-03-08 19:57:38.000000000 -0600
@@ -138,6 +138,7 @@
#define OV5_XCMO 0x0400
#endif
#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 2013-03-08 19:57:27.000000000 -0600
+++ powerpc/arch/powerpc/mm/numa.c 2013-03-08 19:57:38.000000000 -0600
@@ -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 (platform_has_feature(OV5_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 */
^ permalink raw reply [flat|nested] 24+ messages in thread
* [PATCH 7/11] Use stop machine to update cpu maps
2013-03-09 3:56 [PATCH 0/11] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
` (5 preceding siblings ...)
2013-03-09 4:04 ` [PATCH 6/11] Update CPU maps Nathan Fontenot
@ 2013-03-09 4:05 ` Nathan Fontenot
2013-03-09 4:07 ` [PATCH 8/11] Update numa cpu vdso info Nathan Fontenot
` (3 subsequent siblings)
10 siblings, 0 replies; 24+ messages in thread
From: Nathan Fontenot @ 2013-03-09 4:05 UTC (permalink / raw)
To: linuxppc-dev
From: Jesse Larrew <jlarrew@linux.vnet.ibm.com>
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.
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 | 51 +++++++++++++++++++++++++++++++++----------------
1 file changed, 35 insertions(+), 16 deletions(-)
Index: powerpc/arch/powerpc/mm/numa.c
===================================================================
--- powerpc.orig/arch/powerpc/mm/numa.c 2013-03-08 19:57:38.000000000 -0600
+++ powerpc/arch/powerpc/mm/numa.c 2013-03-08 19:57:47.000000000 -0600
@@ -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 +1255,12 @@
/* Virtual Processor Home Node (VPHN) support */
#ifdef CONFIG_PPC_SPLPAR
+struct topology_update_data {
+ 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;
@@ -1405,34 +1412,46 @@
}
/*
+ * 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 = data;
+
+ if (!update)
+ return -EINVAL;
+
+ 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;
+ int cpu, changed = 0;
+ struct topology_update_data update;
unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
struct device *dev;
for_each_cpu(cpu, &cpu_associativity_changes_mask) {
+ update.cpu = cpu;
vphn_get_associativity(cpu, associativity);
- nid = associativity_to_nid(associativity);
-
- if (nid < 0 || !node_online(nid))
- nid = first_online_node;
+ update.new_nid = associativity_to_nid(associativity);
- 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 (update.new_nid < 0 || !node_online(update.new_nid))
+ update.new_nid = first_online_node;
+ update.old_nid = numa_cpu_lookup_table[cpu];
+ stop_machine(update_cpu_topology, &update, cpu_online_mask);
dev = get_cpu_device(cpu);
if (dev)
kobject_uevent(&dev->kobj, KOBJ_CHANGE);
^ permalink raw reply [flat|nested] 24+ messages in thread
* [PATCH 8/11] Update numa cpu vdso info
2013-03-09 3:56 [PATCH 0/11] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
` (6 preceding siblings ...)
2013-03-09 4:05 ` [PATCH 7/11] Use stop machine to update cpu maps Nathan Fontenot
@ 2013-03-09 4:07 ` Nathan Fontenot
2013-03-14 9:02 ` Paul Mackerras
2013-03-09 4:08 ` [PATCH 9/11] Re-enable Virtual Private Home Node capabilities Nathan Fontenot
` (2 subsequent siblings)
10 siblings, 1 reply; 24+ messages in thread
From: Nathan Fontenot @ 2013-03-09 4:07 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:
http://patchwork.ozlabs.org/patch/169070/
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 2013-03-08 19:57:47.000000000 -0600
+++ powerpc/arch/powerpc/mm/numa.c 2013-03-08 19:57:59.000000000 -0600
@@ -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;
@@ -1426,6 +1427,7 @@
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);
return 0;
@@ -1440,8 +1442,11 @@
int cpu, changed = 0;
struct topology_update_data update;
unsigned int associativity[VPHN_ASSOC_BUFSIZE] = {0};
+ cpumask_t updated_cpu;
struct device *dev;
+ cpumask_clear(&updated_cpu);
+
for_each_cpu(cpu, &cpu_associativity_changes_mask) {
update.cpu = cpu;
vphn_get_associativity(cpu, associativity);
@@ -1451,7 +1456,8 @@
update.new_nid = first_online_node;
update.old_nid = numa_cpu_lookup_table[cpu];
- stop_machine(update_cpu_topology, &update, cpu_online_mask);
+ cpumask_set_cpu(cpu, &updated_cpu);
+ stop_machine(update_cpu_topology, &update, &updated_cpu);
dev = get_cpu_device(cpu);
if (dev)
kobject_uevent(&dev->kobj, KOBJ_CHANGE);
^ permalink raw reply [flat|nested] 24+ messages in thread
* [PATCH 9/11] Re-enable Virtual Private Home Node capabilities
2013-03-09 3:56 [PATCH 0/11] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
` (7 preceding siblings ...)
2013-03-09 4:07 ` [PATCH 8/11] Update numa cpu vdso info Nathan Fontenot
@ 2013-03-09 4:08 ` Nathan Fontenot
2013-03-09 4:08 ` [PATCH 10/11] Enable PRRN Nathan Fontenot
2013-03-09 4:10 ` [PATCH 11/11] Add /proc interface to control topology updates Nathan Fontenot
10 siblings, 0 replies; 24+ messages in thread
From: Nathan Fontenot @ 2013-03-09 4:08 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 2013-03-08 19:57:59.000000000 -0600
+++ powerpc/arch/powerpc/mm/numa.c 2013-03-08 19:58:09.000000000 -0600
@@ -1545,9 +1545,8 @@
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] 24+ messages in thread
* [PATCH 10/11] Enable PRRN
2013-03-09 3:56 [PATCH 0/11] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
` (8 preceding siblings ...)
2013-03-09 4:08 ` [PATCH 9/11] Re-enable Virtual Private Home Node capabilities Nathan Fontenot
@ 2013-03-09 4:08 ` Nathan Fontenot
2013-03-09 4:10 ` [PATCH 11/11] Add /proc interface to control topology updates Nathan Fontenot
10 siblings, 0 replies; 24+ messages in thread
From: Nathan Fontenot @ 2013-03-09 4:08 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 and will cause the firmware to begin
sending 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 2013-03-08 19:57:14.000000000 -0600
+++ powerpc/arch/powerpc/kernel/prom_init.c 2013-03-08 19:58:18.000000000 -0600
@@ -689,7 +689,7 @@
OV5_FEAT(OV5_MSI),
0,
OV5_FEAT(OV5_CMO) | OV5_FEAT(OV5_XCMO),
- OV5_FEAT(OV5_TYPE1_AFFINITY),
+ OV5_FEAT(OV5_TYPE1_AFFINITY) | OV5_FEAT(OV5_PRRN),
0,
0,
0,
^ permalink raw reply [flat|nested] 24+ messages in thread
* [PATCH 11/11] Add /proc interface to control topology updates
2013-03-09 3:56 [PATCH 0/11] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
` (9 preceding siblings ...)
2013-03-09 4:08 ` [PATCH 10/11] Enable PRRN Nathan Fontenot
@ 2013-03-09 4:10 ` Nathan Fontenot
10 siblings, 0 replies; 24+ messages in thread
From: Nathan Fontenot @ 2013-03-09 4:10 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 | 6 ++-
arch/powerpc/mm/numa.c | 62 +++++++++++++++++++++++++++++++++++-
3 files changed, 70 insertions(+), 3 deletions(-)
Index: powerpc/arch/powerpc/mm/numa.c
===================================================================
--- powerpc.orig/arch/powerpc/mm/numa.c 2013-03-08 19:58:09.000000000 -0600
+++ powerpc/arch/powerpc/mm/numa.c 2013-03-08 19:58:37.000000000 -0600
@@ -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>
@@ -1558,7 +1561,6 @@
return rc;
}
-__initcall(start_topology_update);
/*
* Disable polling for VPHN associativity changes.
@@ -1577,4 +1579,62 @@
return rc;
}
+
+inline 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 2013-03-08 19:23:06.000000000 -0600
+++ powerpc/arch/powerpc/include/asm/topology.h 2013-03-08 19:58:37.000000000 -0600
@@ -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 inline 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 2013-03-08 19:56:48.000000000 -0600
+++ powerpc/arch/powerpc/kernel/rtasd.c 2013-03-08 19:58:37.000000000 -0600
@@ -292,11 +292,13 @@
{
pSeries_log_error((char *)log, ERR_TYPE_RTAS_LOG, 0);
- 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] 24+ messages in thread
* Re: [PATCH 1/11] Expose pseries devicetree_update()
2013-03-09 3:59 ` [PATCH 1/11] Expose pseries devicetree_update() Nathan Fontenot
@ 2013-03-14 8:49 ` Paul Mackerras
0 siblings, 0 replies; 24+ messages in thread
From: Paul Mackerras @ 2013-03-14 8:49 UTC (permalink / raw)
To: Nathan Fontenot; +Cc: linuxppc-dev
On Fri, Mar 08, 2013 at 09:59:26PM -0600, Nathan Fontenot wrote:
> From: Jesse Larrew <jlarrew@linux.vnet.ibm.com>
>
> 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_devtree_update() routine used in partition migration.
>
> This patch simply exposes pseries_devicetree_update() so it can be
> called by rtasd. pseries_devicetree_update() and supporting functions
> are also modified to take a 32-bit 'scope' parameter. This parameter is
> required by the ibm,update-nodes/ibm,update-properties RTAS calls, and
> the appropriate value is contained within the RTAS event for PRRN
> notifications. In pseries_devicetree_update() it was previously
> hard-coded to 1, the scope value for partition migration.
>
> Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Patch looks fine, so:
Acked-by: Paul Mackerras <paulus@samba.org>
However, you could usefully put some of the description from your 0/11
email into this patch description, since the 0/11 email doesn't get
preserved in git.
Paul.
^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [PATCH2/11] Add PRRN Event Handler
2013-03-09 4:00 ` [PATCH2/11] Add PRRN Event Handler Nathan Fontenot
@ 2013-03-14 8:51 ` Paul Mackerras
2013-03-19 18:01 ` Nathan Fontenot
0 siblings, 1 reply; 24+ messages in thread
From: Paul Mackerras @ 2013-03-14 8:51 UTC (permalink / raw)
To: Nathan Fontenot; +Cc: linuxppc-dev
On Fri, Mar 08, 2013 at 10:00:09PM -0600, Nathan Fontenot wrote:
> 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 repurposed (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 in rtasd for PRRN 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 rtasd to continue processing events.
>
> Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
[snip]
> +static s32 update_scope;
Do we have a guarantee that there can only be one of these events
outstanding at a time? If so it would be nice to document that in a
comment next to this declaration, so we know in future that this is
why this is safe.
Paul.
^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [PATCH 3/11] Move architecture vector definitions to prom.h
2013-03-09 4:01 ` [PATCH 3/11] Move architecture vector definitions to prom.h Nathan Fontenot
@ 2013-03-14 8:52 ` Paul Mackerras
0 siblings, 0 replies; 24+ messages in thread
From: Paul Mackerras @ 2013-03-14 8:52 UTC (permalink / raw)
To: Nathan Fontenot; +Cc: linuxppc-dev
On Fri, Mar 08, 2013 at 10:01:25PM -0600, Nathan Fontenot wrote:
> As part of handling of handling PRRN events we will need to check the
> vector 5 portion of the architecture bits reported in the device tree
> to ensure that PRRN event handling is enabled. In order to do this a
> new platform_has_feature call is introduced (in a subsequent patch) to
> make this check. To avoid having to re-define bits in the architecture
> vector the bits are moved to prom.h.
>
> This patch is the first step in implementing the platform_has_feature
> call by simply moving the bit definitions from prom_init.c to asm/prom.h.
> There are no functional.
>
> Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
Acked-by: Paul Mackerras <paulus@samba.org>
^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [PATCH 4/11] Add platform_has_feature()
2013-03-09 4:02 ` [PATCH 4/11] Add platform_has_feature() Nathan Fontenot
@ 2013-03-14 8:56 ` Paul Mackerras
2013-03-19 18:03 ` Nathan Fontenot
2013-03-14 8:59 ` Paul Mackerras
2013-03-14 13:42 ` Michael Ellerman
2 siblings, 1 reply; 24+ messages in thread
From: Paul Mackerras @ 2013-03-14 8:56 UTC (permalink / raw)
To: Nathan Fontenot; +Cc: linuxppc-dev
On Fri, Mar 08, 2013 at 10:02:31PM -0600, Nathan Fontenot wrote:
> The firmware_has_feature() function makes it easy to check for supported
> features of the hardware. There is not corresponding function to check for
> features supported by the client architecture.
Actually, firmware_has_feature checks for supported features of the
hypervisor, or in a sense the platform, rather than hardware.
> This patch adds a platform_has_feature() function to check features selected
> by firmware and reported via the device tree 'ibm,architecture-vec5'
> property. As part of this the #defines used for the architecture vector are
> moved to prom.h and re-defined such that the vector 5 options have the vector
> index and the feature bits encoded into them. This allows for callers of
> platform_has_feature() to pass in a single pre-defined value.
One other comment below...
> /* PCIe/MSI support. Without MSI full PCIe is not supported */
> #ifdef CONFIG_PCI_MSI
> -#define OV5_MSI 0x01 /* PCIe/MSI support */
> +#define OV5_MSI 0x0201 /* PCIe/MSI support */
> #else
> -#define OV5_MSI 0x00
> +#define OV5_MSI 0x0200
> #endif /* CONFIG_PCI_MSI */
The #ifdef was done this way in order to control what ended up in the
option vector we pass to the platform firmware. For checking what the
platform supports, wouldn't we want OV5_MSI to be 0x0201 always?
Similarly for OV5_CMO, OV5_XCMO, etc.?
Paul.
^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [PATCH 4/11] Add platform_has_feature()
2013-03-09 4:02 ` [PATCH 4/11] Add platform_has_feature() Nathan Fontenot
2013-03-14 8:56 ` Paul Mackerras
@ 2013-03-14 8:59 ` Paul Mackerras
2013-03-19 18:05 ` Nathan Fontenot
2013-03-14 13:42 ` Michael Ellerman
2 siblings, 1 reply; 24+ messages in thread
From: Paul Mackerras @ 2013-03-14 8:59 UTC (permalink / raw)
To: Nathan Fontenot; +Cc: linuxppc-dev
On Fri, Mar 08, 2013 at 10:02:31PM -0600, Nathan Fontenot wrote:
> This patch adds a platform_has_feature() function to check features selected
> by firmware and reported via the device tree 'ibm,architecture-vec5'
> property. As part of this the #defines used for the architecture vector are
> moved to prom.h and re-defined such that the vector 5 options have the vector
> index and the feature bits encoded into them. This allows for callers of
> platform_has_feature() to pass in a single pre-defined value.
One other comment...
> +#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
> +bool platform_has_feature(unsigned int feature)
> +{
> + struct device_node *chosen;
> + const char *vec5;
> + bool has_option;
> +
> + chosen = of_find_node_by_path("/chosen");
> + if (!chosen)
> + return false;
> +
> + vec5 = of_get_property(chosen, "ibm,architecture-vec-5", NULL);
> + has_option = vec5 && (vec5[OV5_INDX(feature)] & OV5_FEAT(feature));
You access vec5[index] without checking that the vector is at least
index+1 bytes long, according to either the length byte at the
beginning of the vector, or the total length of the property.
Checking both would be a good idea.
Paul.
^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [PATCH 8/11] Update numa cpu vdso info
2013-03-09 4:07 ` [PATCH 8/11] Update numa cpu vdso info Nathan Fontenot
@ 2013-03-14 9:02 ` Paul Mackerras
0 siblings, 0 replies; 24+ messages in thread
From: Paul Mackerras @ 2013-03-14 9:02 UTC (permalink / raw)
To: Nathan Fontenot; +Cc: linuxppc-dev
On Fri, Mar 08, 2013 at 10:07:05PM -0600, Nathan Fontenot wrote:
> 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:
>
> http://patchwork.ozlabs.org/patch/169070/
Since that patch is now upstream, it would be better to refer to it by
its git SHA1 ID and title, like this:
Commit 18ad51dd34 ("powerpc: Add VDSO version of getcpu") adds
vdso_getcpu_init(), which stores the NUMA node for a cpu in SPRG3.
Paul.
^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [PATCH 4/11] Add platform_has_feature()
2013-03-09 4:02 ` [PATCH 4/11] Add platform_has_feature() Nathan Fontenot
2013-03-14 8:56 ` Paul Mackerras
2013-03-14 8:59 ` Paul Mackerras
@ 2013-03-14 13:42 ` Michael Ellerman
2013-03-19 18:15 ` Nathan Fontenot
2 siblings, 1 reply; 24+ messages in thread
From: Michael Ellerman @ 2013-03-14 13:42 UTC (permalink / raw)
To: Nathan Fontenot; +Cc: linuxppc-dev
On Fri, Mar 08, 2013 at 10:02:31PM -0600, Nathan Fontenot wrote:
> The firmware_has_feature() function makes it easy to check for supported
> features of the hardware. There is not corresponding function to check for
> features supported by the client architecture.
Actually it doesn't tell you about features of the hardware, it tells
you about features of the firmware, or the platform ..
So I think you should really just be adding a new firmware feature flag,
and adding whatever glue code is required to set it based on what you
find in the device tree.
Also notice where you end up using it:
- if (firmware_has_feature(FW_FEATURE_OPAL))
+ if (firmware_has_feature(FW_FEATURE_OPAL) ||
+ platform_has_feature(OV5_TYPE1_AFFINITY)) {
+ dbg("Using form 1 affinity\n");
form1_affinity = 1;
Could be:
+ if (firmware_has_feature(FW_FEATURE_FORM1_AFFINITY) ||
cheers
^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [PATCH2/11] Add PRRN Event Handler
2013-03-14 8:51 ` Paul Mackerras
@ 2013-03-19 18:01 ` Nathan Fontenot
0 siblings, 0 replies; 24+ messages in thread
From: Nathan Fontenot @ 2013-03-19 18:01 UTC (permalink / raw)
To: Paul Mackerras; +Cc: linuxppc-dev
On 03/14/2013 03:51 AM, Paul Mackerras wrote:
> On Fri, Mar 08, 2013 at 10:00:09PM -0600, Nathan Fontenot wrote:
>> 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 repurposed (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 in rtasd for PRRN 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 rtasd to continue processing events.
>>
>> Signed-off-by: Nathan Fontenot <nfont@linux.vnet.ibm.com>
>
> [snip]
>
>> +static s32 update_scope;
>
> Do we have a guarantee that there can only be one of these events
> outstanding at a time? If so it would be nice to document that in a
> comment next to this declaration, so we know in future that this is
> why this is safe.
>
We only allow for one event to be outstanding. When a PRRN Event is
received we flush any work currently queued up and add the new event
event to the workqueue (see prrn_schedule_work() from the patch).
As I understand flush_work(), this would wait for any work in flight
to complete, then remove all work before returning. I'll add a comment
and update the patch description.
-Nathan
^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [PATCH 4/11] Add platform_has_feature()
2013-03-14 8:56 ` Paul Mackerras
@ 2013-03-19 18:03 ` Nathan Fontenot
0 siblings, 0 replies; 24+ messages in thread
From: Nathan Fontenot @ 2013-03-19 18:03 UTC (permalink / raw)
To: Paul Mackerras; +Cc: linuxppc-dev
On 03/14/2013 03:56 AM, Paul Mackerras wrote:
> On Fri, Mar 08, 2013 at 10:02:31PM -0600, Nathan Fontenot wrote:
>> The firmware_has_feature() function makes it easy to check for supported
>> features of the hardware. There is not corresponding function to check for
>> features supported by the client architecture.
>
> Actually, firmware_has_feature checks for supported features of the
> hypervisor, or in a sense the platform, rather than hardware.
Ahh, thanks for clarifying that for me. I'll update the description.
>
>> This patch adds a platform_has_feature() function to check features selected
>> by firmware and reported via the device tree 'ibm,architecture-vec5'
>> property. As part of this the #defines used for the architecture vector are
>> moved to prom.h and re-defined such that the vector 5 options have the vector
>> index and the feature bits encoded into them. This allows for callers of
>> platform_has_feature() to pass in a single pre-defined value.
>
> One other comment below...
>
>> /* PCIe/MSI support. Without MSI full PCIe is not supported */
>> #ifdef CONFIG_PCI_MSI
>> -#define OV5_MSI 0x01 /* PCIe/MSI support */
>> +#define OV5_MSI 0x0201 /* PCIe/MSI support */
>> #else
>> -#define OV5_MSI 0x00
>> +#define OV5_MSI 0x0200
>> #endif /* CONFIG_PCI_MSI */
>
> The #ifdef was done this way in order to control what ended up in the
> option vector we pass to the platform firmware. For checking what the
> platform supports, wouldn't we want OV5_MSI to be 0x0201 always?
> Similarly for OV5_CMO, OV5_XCMO, etc.?
Yes, you're correct. I will update this.
--
-Nathan
^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [PATCH 4/11] Add platform_has_feature()
2013-03-14 8:59 ` Paul Mackerras
@ 2013-03-19 18:05 ` Nathan Fontenot
0 siblings, 0 replies; 24+ messages in thread
From: Nathan Fontenot @ 2013-03-19 18:05 UTC (permalink / raw)
To: Paul Mackerras; +Cc: linuxppc-dev
On 03/14/2013 03:59 AM, Paul Mackerras wrote:
> On Fri, Mar 08, 2013 at 10:02:31PM -0600, Nathan Fontenot wrote:
>> This patch adds a platform_has_feature() function to check features selected
>> by firmware and reported via the device tree 'ibm,architecture-vec5'
>> property. As part of this the #defines used for the architecture vector are
>> moved to prom.h and re-defined such that the vector 5 options have the vector
>> index and the feature bits encoded into them. This allows for callers of
>> platform_has_feature() to pass in a single pre-defined value.
>
> One other comment...
>
>> +#if defined(CONFIG_PPC_PSERIES) || defined(CONFIG_PPC_POWERNV)
>> +bool platform_has_feature(unsigned int feature)
>> +{
>> + struct device_node *chosen;
>> + const char *vec5;
>> + bool has_option;
>> +
>> + chosen = of_find_node_by_path("/chosen");
>> + if (!chosen)
>> + return false;
>> +
>> + vec5 = of_get_property(chosen, "ibm,architecture-vec-5", NULL);
>> + has_option = vec5 && (vec5[OV5_INDX(feature)] & OV5_FEAT(feature));
>
> You access vec5[index] without checking that the vector is at least
> index+1 bytes long, according to either the length byte at the
> beginning of the vector, or the total length of the property.
> Checking both would be a good idea.
>
Yep. Thanks for letting me know.
--
-Nathan
^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [PATCH 4/11] Add platform_has_feature()
2013-03-14 13:42 ` Michael Ellerman
@ 2013-03-19 18:15 ` Nathan Fontenot
2013-03-22 3:56 ` Michael Ellerman
0 siblings, 1 reply; 24+ messages in thread
From: Nathan Fontenot @ 2013-03-19 18:15 UTC (permalink / raw)
To: Michael Ellerman; +Cc: linuxppc-dev
On 03/14/2013 08:42 AM, Michael Ellerman wrote:
> On Fri, Mar 08, 2013 at 10:02:31PM -0600, Nathan Fontenot wrote:
>> The firmware_has_feature() function makes it easy to check for supported
>> features of the hardware. There is not corresponding function to check for
>> features supported by the client architecture.
>
> Actually it doesn't tell you about features of the hardware, it tells
> you about features of the firmware, or the platform ..
>
> So I think you should really just be adding a new firmware feature flag,
> and adding whatever glue code is required to set it based on what you
> find in the device tree.
>
> Also notice where you end up using it:
>
> - if (firmware_has_feature(FW_FEATURE_OPAL))
> + if (firmware_has_feature(FW_FEATURE_OPAL) ||
> + platform_has_feature(OV5_TYPE1_AFFINITY)) {
> + dbg("Using form 1 affinity\n");
> form1_affinity = 1;
>
> Could be:
>
> + if (firmware_has_feature(FW_FEATURE_FORM1_AFFINITY) ||
>
To make sure I understand what you're suggesting...
You think there should be a single firmware_has_feature() for all current
uses and also for checking items such as FORM1_AFFINITY and PRRN
features as reported by the device tree for vector 5 portions of the
client architecture bits. I think this could be done by checking the
device tree ibm,architecture-vec-5 node for a specified feature and
setting a bit the appropriate bit in powerpc_firmware_features.
I like this more than separate firmware_has_feature() and platform_has_feature()
routines to check.
--
-Nathan
^ permalink raw reply [flat|nested] 24+ messages in thread
* Re: [PATCH 4/11] Add platform_has_feature()
2013-03-19 18:15 ` Nathan Fontenot
@ 2013-03-22 3:56 ` Michael Ellerman
0 siblings, 0 replies; 24+ messages in thread
From: Michael Ellerman @ 2013-03-22 3:56 UTC (permalink / raw)
To: Nathan Fontenot; +Cc: linuxppc-dev
On Tue, Mar 19, 2013 at 01:15:02PM -0500, Nathan Fontenot wrote:
> On 03/14/2013 08:42 AM, Michael Ellerman wrote:
> > On Fri, Mar 08, 2013 at 10:02:31PM -0600, Nathan Fontenot wrote:
> >> The firmware_has_feature() function makes it easy to check for supported
> >> features of the hardware. There is not corresponding function to check for
> >> features supported by the client architecture.
> >
> > Actually it doesn't tell you about features of the hardware, it tells
> > you about features of the firmware, or the platform ..
> >
> > So I think you should really just be adding a new firmware feature flag,
> > and adding whatever glue code is required to set it based on what you
> > find in the device tree.
> >
> > Also notice where you end up using it:
> >
> > - if (firmware_has_feature(FW_FEATURE_OPAL))
> > + if (firmware_has_feature(FW_FEATURE_OPAL) ||
> > + platform_has_feature(OV5_TYPE1_AFFINITY)) {
> > + dbg("Using form 1 affinity\n");
> > form1_affinity = 1;
> >
> > Could be:
> >
> > + if (firmware_has_feature(FW_FEATURE_FORM1_AFFINITY) ||
> >
>
> To make sure I understand what you're suggesting...
>
> You think there should be a single firmware_has_feature() for all current
> uses and also for checking items such as FORM1_AFFINITY and PRRN
> features as reported by the device tree for vector 5 portions of the
> client architecture bits. I think this could be done by checking the
> device tree ibm,architecture-vec-5 node for a specified feature and
> setting a bit the appropriate bit in powerpc_firmware_features.
Yes that's right.
So you'd add a new FW_FEATURE_FORM1_AFFINITY, and set it depending on what
you find in "ibm,architecture-vec-5" on IBM pseries machines.
As a cleanup you'd also set it unconditionally on OPAL and then the
check above could be simply for FW_FEATURE_FORM1_AFFINITY.
cheers
^ permalink raw reply [flat|nested] 24+ messages in thread
end of thread, other threads:[~2013-03-22 3:56 UTC | newest]
Thread overview: 24+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2013-03-09 3:56 [PATCH 0/11] NUMA CPU Reconfiguration using PRRN Nathan Fontenot
2013-03-09 3:59 ` [PATCH 1/11] Expose pseries devicetree_update() Nathan Fontenot
2013-03-14 8:49 ` Paul Mackerras
2013-03-09 4:00 ` [PATCH2/11] Add PRRN Event Handler Nathan Fontenot
2013-03-14 8:51 ` Paul Mackerras
2013-03-19 18:01 ` Nathan Fontenot
2013-03-09 4:01 ` [PATCH 3/11] Move architecture vector definitions to prom.h Nathan Fontenot
2013-03-14 8:52 ` Paul Mackerras
2013-03-09 4:02 ` [PATCH 4/11] Add platform_has_feature() Nathan Fontenot
2013-03-14 8:56 ` Paul Mackerras
2013-03-19 18:03 ` Nathan Fontenot
2013-03-14 8:59 ` Paul Mackerras
2013-03-19 18:05 ` Nathan Fontenot
2013-03-14 13:42 ` Michael Ellerman
2013-03-19 18:15 ` Nathan Fontenot
2013-03-22 3:56 ` Michael Ellerman
2013-03-09 4:03 ` [PATCH 5/11] Update numa.c to use platform_has_feature() Nathan Fontenot
2013-03-09 4:04 ` [PATCH 6/11] Update CPU maps Nathan Fontenot
2013-03-09 4:05 ` [PATCH 7/11] Use stop machine to update cpu maps Nathan Fontenot
2013-03-09 4:07 ` [PATCH 8/11] Update numa cpu vdso info Nathan Fontenot
2013-03-14 9:02 ` Paul Mackerras
2013-03-09 4:08 ` [PATCH 9/11] Re-enable Virtual Private Home Node capabilities Nathan Fontenot
2013-03-09 4:08 ` [PATCH 10/11] Enable PRRN Nathan Fontenot
2013-03-09 4:10 ` [PATCH 11/11] Add /proc interface to control topology updates Nathan Fontenot
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).