From: Robert Jennings <rcj@linux.vnet.ibm.com>
To: paulus@samba.org
Cc: Brian King <brking@linux.vnet.ibm.com>,
linuxppc-dev@ozlabs.org,
David Darrington <ddarring@linux.vnet.ibm.com>
Subject: [PATCH 09/16 v3] powerpc: Add CMO paging statistics
Date: Fri, 4 Jul 2008 07:54:31 -0500 [thread overview]
Message-ID: <20080704125430.GL1310@linux.vnet.ibm.com> (raw)
In-Reply-To: <20080704124449.GA1310@linux.vnet.ibm.com>
=46rom: Brian King <brking@linux.vnet.ibm.com>
With the addition of Cooperative Memory Overcommitment (CMO) support
for IBM Power Systems, two fields have been added to the VPA to report
paging statistics. Add support in lparcfg to report them to userspace.
Signed-off-by: Brian King <brking@linux.vnet.ibm.com>
Signed-off-by: Robert Jennings <rcj@linux.vnet.ibm.com>
---
arch/powerpc/kernel/lparcfg.c | 20 ++++++++++++++++++++
include/asm-powerpc/lppaca.h | 5 ++++-
2 files changed, 24 insertions(+), 1 deletion(-)
Index: b/arch/powerpc/kernel/lparcfg.c
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D
--- a/arch/powerpc/kernel/lparcfg.c
+++ b/arch/powerpc/kernel/lparcfg.c
@@ -410,6 +410,25 @@ static int lparcfg_count_active_processo
return count;
}
=20
+static void pseries_cmo_data(struct seq_file *m)
+{
+ int cpu;
+ unsigned long cmo_faults =3D 0;
+ unsigned long cmo_fault_time =3D 0;
+
+ if (!firmware_has_feature(FW_FEATURE_CMO))
+ return;
+
+ for_each_possible_cpu(cpu) {
+ cmo_faults +=3D lppaca[cpu].cmo_faults;
+ cmo_fault_time +=3D lppaca[cpu].cmo_fault_time;
+ }
+
+ seq_printf(m, "cmo_faults=3D%lu\n", cmo_faults);
+ seq_printf(m, "cmo_fault_time_usec=3D%lu\n",
+ cmo_fault_time / tb_ticks_per_usec);
+}
+
static int pseries_lparcfg_data(struct seq_file *m, void *v)
{
int partition_potential_processors;
@@ -435,6 +454,7 @@ static int pseries_lparcfg_data(struct s
parse_system_parameter_string(m);
parse_ppp_data(m);
parse_mpp_data(m);
+ pseries_cmo_data(m);
=20
seq_printf(m, "purr=3D%ld\n", get_purr());
} else { /* non SPLPAR case */
Index: b/include/asm-powerpc/lppaca.h
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D
--- a/include/asm-powerpc/lppaca.h
+++ b/include/asm-powerpc/lppaca.h
@@ -125,7 +125,10 @@ struct lppaca {
// NOTE: This value will ALWAYS be zero for dedicated processors and
// will NEVER be zero for shared processors (ie, initialized to a 1).
volatile u32 yield_count; // PLIC increments each dispatchx00-x03
- u8 reserved6[124]; // Reserved x04-x7F
+ u32 reserved6;
+ volatile u64 cmo_faults; // CMO page fault count x08-x0F
+ volatile u64 cmo_fault_time; // CMO page fault time x10-x17
+ u8 reserved7[104]; // Reserved x18-x7F
=20
//=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=3D=
=3D=3D=3D
// CACHE_LINE_4-5 0x0180 - 0x027F Contains PMC interrupt data
next prev parent reply other threads:[~2008-07-04 12:54 UTC|newest]
Thread overview: 38+ messages / expand[flat|nested] mbox.gz Atom feed top
2008-07-04 12:44 [PATCH 00/16 v3] powerpc: pSeries Cooperative Memory Overcommitment support Robert Jennings
2008-07-04 12:51 ` [PATCH 01/16 v3] powerpc: Remove extraneous error reporting for hcall failures in lparcfg Robert Jennings
2008-07-22 3:34 ` Paul Mackerras
2008-07-04 12:51 ` [PATCH 02/16 v3] powerpc: Split processor entitlement retrieval and gathering to helper routines Robert Jennings
2008-07-22 18:53 ` Nathan Fontenot
2008-07-04 12:51 ` [PATCH 03/16 v3] powerpc: Add memory entitlement capabilities to /proc/ppc64/lparcfg Robert Jennings
2008-07-22 18:55 ` Nathan Fontenot
2008-07-04 12:52 ` [PATCH 04/16 v3] powerpc: Split retrieval of processor entitlement data into a helper routine Robert Jennings
2008-07-22 5:54 ` Paul Mackerras
2008-07-22 18:49 ` Nathan Fontenot
2008-07-22 18:56 ` Nathan Fontenot
2008-07-04 12:52 ` [PATCH 05/16 v3] powerpc: Enable CMO feature during platform setup Robert Jennings
2008-07-04 12:52 ` Robert Jennings
2008-07-04 12:52 ` [PATCH 06/16 v3] powerpc: Utilities to set firmware page state Robert Jennings
2008-07-04 12:53 ` Robert Jennings
2008-07-04 12:53 ` [PATCH 07/16 v3] powerpc: Add collaborative memory manager Robert Jennings
2008-07-22 4:53 ` Paul Mackerras
2008-07-04 12:54 ` [PATCH 08/16 v3] powerpc: Do not probe PCI buses or eBus devices if CMO is enabled Robert Jennings
2008-07-14 21:35 ` Brian King
2008-07-04 12:54 ` Robert Jennings [this message]
2008-07-04 12:54 ` [PATCH 10/16 v3] powerpc: iommu enablement for CMO Robert Jennings
2008-07-05 17:51 ` Olof Johansson
2008-07-08 20:48 ` [PATCH 10/16 v3] [v2] " Robert Jennings
2008-07-22 5:04 ` Paul Mackerras
2008-07-22 13:30 ` Robert Jennings
2008-07-22 4:57 ` [PATCH 10/16 v3] " Paul Mackerras
2008-07-22 13:28 ` Robert Jennings
2008-07-04 12:55 ` [PATCH 11/16 v3] powerpc: vio bus support " Robert Jennings
2008-07-04 12:55 ` [PATCH 12/16 v3] powerpc: Verify CMO memory entitlement updates with virtual I/O Robert Jennings
2008-07-04 12:55 ` [PATCH 13/16 v3] ibmveth: Automatically enable larger rx buffer pools for larger mtu Robert Jennings
2008-07-04 12:56 ` [PATCH 14/16 v3] ibmveth: enable driver for CMO Robert Jennings
2008-07-08 20:38 ` [PATCH 14/16 v3] [v2] " Robert Jennings
2008-07-04 12:56 ` [PATCH 15/16 v3] ibmvscsi: driver enablement " Robert Jennings
2008-07-07 14:34 ` Brian King
2008-07-08 17:41 ` Robert Jennings
2008-07-08 20:35 ` [PATCH 15/16 v3] [v2] " Robert Jennings
2008-07-10 13:43 ` Brian King
2008-07-04 12:57 ` [PATCH 16/16 v3] powerpc: Update arch vector to indicate support " Robert Jennings
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20080704125430.GL1310@linux.vnet.ibm.com \
--to=rcj@linux.vnet.ibm.com \
--cc=brking@linux.vnet.ibm.com \
--cc=ddarring@linux.vnet.ibm.com \
--cc=linuxppc-dev@ozlabs.org \
--cc=paulus@samba.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
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).