linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
* [PATCH 1/2] x86: UV BAU Increase maximum CPUs per socket/hub
@ 2014-11-02 18:16 James Custer
  2014-11-02 18:16 ` [PATCH 2/2] x86: UV BAU Avoid NULL pointer reference in ptc_seq_show James Custer
  2014-11-03 12:51 ` [tip:x86/uv] x86: UV BAU: Increase maximum CPUs per socket/hub tip-bot for James Custer
  0 siblings, 2 replies; 4+ messages in thread
From: James Custer @ 2014-11-02 18:16 UTC (permalink / raw)
  To: x86
  Cc: James Custer, linux-kernel, Thomas Gleixner, Ingo Molnar,
	H . Peter Anvin, Russ Anderson

We have encountered hardware with 18 cores/socket that gives 36 CPUs/socket
with hyperthreading enabled. This exceeds the current MAX_CPUS_PER_SOCKET
causing a failure in get_cpu_topology. Increase MAX_CPUS_PER_SOCKET to 64
and MAX_CPUS_PER_UVHUB to 128.

Signed-off-by: James Custer <jcuster@sgi.com>
---
 arch/x86/include/asm/uv/uv_bau.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 2d60a78..fc808b8 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -33,8 +33,8 @@
  * Each of the descriptors is 64 bytes in size (8*64 = 512 bytes in a set).
  */
 
-#define MAX_CPUS_PER_UVHUB		64
-#define MAX_CPUS_PER_SOCKET		32
+#define MAX_CPUS_PER_UVHUB		128
+#define MAX_CPUS_PER_SOCKET		64
 #define ADP_SZ				64 /* hardware-provided max. */
 #define UV_CPUS_PER_AS			32 /* hardware-provided max. */
 #define ITEMS_PER_DESC			8
-- 
1.7.12.4


^ permalink raw reply related	[flat|nested] 4+ messages in thread

* [PATCH 2/2] x86: UV BAU Avoid NULL pointer reference in ptc_seq_show
  2014-11-02 18:16 [PATCH 1/2] x86: UV BAU Increase maximum CPUs per socket/hub James Custer
@ 2014-11-02 18:16 ` James Custer
  2014-11-03 12:51   ` [tip:x86/uv] x86: UV BAU: " tip-bot for James Custer
  2014-11-03 12:51 ` [tip:x86/uv] x86: UV BAU: Increase maximum CPUs per socket/hub tip-bot for James Custer
  1 sibling, 1 reply; 4+ messages in thread
From: James Custer @ 2014-11-02 18:16 UTC (permalink / raw)
  To: x86
  Cc: James Custer, linux-kernel, Thomas Gleixner, Ingo Molnar,
	H . Peter Anvin, Russ Anderson

In init_per_cpu(), when get_cpu_topology() fails, init_per_cpu_tunables()
is not called afterwards. This means that bau_control->statp is NULL.
If a user then reads /proc/sgi_uv/ptc_statistics ptc_seq_show() references
a NULL pointer. Therefore, since uv_bau_init calls set_bau_off when
init_per_cpu() fails, we add code that detects when the bau is off in
ptc_seq_show() to avoid referencing a NULL pointer.

Signed-off-by: James Custer <jcuster@sgi.com>
---
 arch/x86/platform/uv/tlb_uv.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 3968d67..570b1b1 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1384,6 +1384,10 @@ static int ptc_seq_show(struct seq_file *file, void *data)
 	}
 	if (cpu < num_possible_cpus() && cpu_online(cpu)) {
 		bcp = &per_cpu(bau_control, cpu);
+		if (bcp->nobau) {
+			seq_printf(file, "cpu %d bau disabled\n", cpu);
+			return 0;
+		}
 		stat = bcp->statp;
 		/* source side statistics */
 		seq_printf(file,
-- 
1.7.12.4


^ permalink raw reply related	[flat|nested] 4+ messages in thread

* [tip:x86/uv] x86: UV BAU: Avoid NULL pointer reference in ptc_seq_show
  2014-11-02 18:16 ` [PATCH 2/2] x86: UV BAU Avoid NULL pointer reference in ptc_seq_show James Custer
@ 2014-11-03 12:51   ` tip-bot for James Custer
  0 siblings, 0 replies; 4+ messages in thread
From: tip-bot for James Custer @ 2014-11-03 12:51 UTC (permalink / raw)
  To: linux-tip-commits; +Cc: hpa, jcuster, tglx, rja, mingo, linux-kernel

Commit-ID:  fa2a79ce6aef5de35a4d50487da35deb6b634944
Gitweb:     http://git.kernel.org/tip/fa2a79ce6aef5de35a4d50487da35deb6b634944
Author:     James Custer <jcuster@sgi.com>
AuthorDate: Sun, 2 Nov 2014 12:16:39 -0600
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Mon, 3 Nov 2014 13:49:24 +0100

x86: UV BAU: Avoid NULL pointer reference in ptc_seq_show

In init_per_cpu(), when get_cpu_topology() fails, init_per_cpu_tunables()
is not called afterwards. This means that bau_control->statp is NULL.
If a user then reads /proc/sgi_uv/ptc_statistics ptc_seq_show() references
a NULL pointer. Therefore, since uv_bau_init calls set_bau_off when
init_per_cpu() fails, we add code that detects when the bau is off in
ptc_seq_show() to avoid referencing a NULL pointer.

Signed-off-by: James Custer <jcuster@sgi.com>
Cc: Russ Anderson <rja@sgi.com>
Link: http://lkml.kernel.org/r/1414952199-185319-2-git-send-email-jcuster@sgi.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/platform/uv/tlb_uv.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/arch/x86/platform/uv/tlb_uv.c b/arch/x86/platform/uv/tlb_uv.c
index 3968d67..570b1b1 100644
--- a/arch/x86/platform/uv/tlb_uv.c
+++ b/arch/x86/platform/uv/tlb_uv.c
@@ -1384,6 +1384,10 @@ static int ptc_seq_show(struct seq_file *file, void *data)
 	}
 	if (cpu < num_possible_cpus() && cpu_online(cpu)) {
 		bcp = &per_cpu(bau_control, cpu);
+		if (bcp->nobau) {
+			seq_printf(file, "cpu %d bau disabled\n", cpu);
+			return 0;
+		}
 		stat = bcp->statp;
 		/* source side statistics */
 		seq_printf(file,

^ permalink raw reply related	[flat|nested] 4+ messages in thread

* [tip:x86/uv] x86: UV BAU: Increase maximum CPUs per socket/hub
  2014-11-02 18:16 [PATCH 1/2] x86: UV BAU Increase maximum CPUs per socket/hub James Custer
  2014-11-02 18:16 ` [PATCH 2/2] x86: UV BAU Avoid NULL pointer reference in ptc_seq_show James Custer
@ 2014-11-03 12:51 ` tip-bot for James Custer
  1 sibling, 0 replies; 4+ messages in thread
From: tip-bot for James Custer @ 2014-11-03 12:51 UTC (permalink / raw)
  To: linux-tip-commits; +Cc: hpa, tglx, mingo, jcuster, linux-kernel, rja

Commit-ID:  3ab0c49fd6b1e80438d0a649584d292880112262
Gitweb:     http://git.kernel.org/tip/3ab0c49fd6b1e80438d0a649584d292880112262
Author:     James Custer <jcuster@sgi.com>
AuthorDate: Sun, 2 Nov 2014 12:16:38 -0600
Committer:  Thomas Gleixner <tglx@linutronix.de>
CommitDate: Mon, 3 Nov 2014 13:49:24 +0100

x86: UV BAU: Increase maximum CPUs per socket/hub

We have encountered hardware with 18 cores/socket that gives 36 CPUs/socket
with hyperthreading enabled. This exceeds the current MAX_CPUS_PER_SOCKET
causing a failure in get_cpu_topology. Increase MAX_CPUS_PER_SOCKET to 64
and MAX_CPUS_PER_UVHUB to 128.

Signed-off-by: James Custer <jcuster@sgi.com>
Cc: Russ Anderson <rja@sgi.com>
Link: http://lkml.kernel.org/r/1414952199-185319-1-git-send-email-jcuster@sgi.com
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
---
 arch/x86/include/asm/uv/uv_bau.h | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/arch/x86/include/asm/uv/uv_bau.h b/arch/x86/include/asm/uv/uv_bau.h
index 2d60a78..fc808b8 100644
--- a/arch/x86/include/asm/uv/uv_bau.h
+++ b/arch/x86/include/asm/uv/uv_bau.h
@@ -33,8 +33,8 @@
  * Each of the descriptors is 64 bytes in size (8*64 = 512 bytes in a set).
  */
 
-#define MAX_CPUS_PER_UVHUB		64
-#define MAX_CPUS_PER_SOCKET		32
+#define MAX_CPUS_PER_UVHUB		128
+#define MAX_CPUS_PER_SOCKET		64
 #define ADP_SZ				64 /* hardware-provided max. */
 #define UV_CPUS_PER_AS			32 /* hardware-provided max. */
 #define ITEMS_PER_DESC			8

^ permalink raw reply related	[flat|nested] 4+ messages in thread

end of thread, other threads:[~2014-11-03 12:52 UTC | newest]

Thread overview: 4+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2014-11-02 18:16 [PATCH 1/2] x86: UV BAU Increase maximum CPUs per socket/hub James Custer
2014-11-02 18:16 ` [PATCH 2/2] x86: UV BAU Avoid NULL pointer reference in ptc_seq_show James Custer
2014-11-03 12:51   ` [tip:x86/uv] x86: UV BAU: " tip-bot for James Custer
2014-11-03 12:51 ` [tip:x86/uv] x86: UV BAU: Increase maximum CPUs per socket/hub tip-bot for James Custer

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).