From: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
To: andriy.shevchenko@intel.com
Cc: platform-driver-x86@vger.kernel.org,
linux-kernel@vger.kernel.org, prarit@redhat.com,
Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Subject: [PATCH 09/10] tools/power/x86/intel-speed-select: Use core count for base-freq mask
Date: Mon, 4 Nov 2019 03:02:45 -0800 [thread overview]
Message-ID: <20191104110246.70465-10-srinivas.pandruvada@linux.intel.com> (raw)
In-Reply-To: <20191104110246.70465-1-srinivas.pandruvada@linux.intel.com>
Some firmware implementation gives error when a command is sent get mask
for core count 32-61. So use core count to decide.
But there is no function to get core count. So introduce one function to
get core count.
Signed-off-by: Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
---
.../x86/intel-speed-select/isst-config.c | 23 ++++++++++++++++++-
.../power/x86/intel-speed-select/isst-core.c | 7 ++++--
tools/power/x86/intel-speed-select/isst.h | 1 +
3 files changed, 28 insertions(+), 3 deletions(-)
diff --git a/tools/power/x86/intel-speed-select/isst-config.c b/tools/power/x86/intel-speed-select/isst-config.c
index 2dffb67d3194..e0bad43697dc 100644
--- a/tools/power/x86/intel-speed-select/isst-config.c
+++ b/tools/power/x86/intel-speed-select/isst-config.c
@@ -338,6 +338,7 @@ void free_cpu_set(cpu_set_t *cpu_set)
}
static int cpu_cnt[MAX_PACKAGE_COUNT][MAX_DIE_PER_PACKAGE];
+static long long core_mask[MAX_PACKAGE_COUNT][MAX_DIE_PER_PACKAGE];
static void set_cpu_present_cpu_mask(void)
{
size_t size;
@@ -362,13 +363,33 @@ static void set_cpu_present_cpu_mask(void)
pkg_id = get_physical_package_id(i);
if (pkg_id < MAX_PACKAGE_COUNT &&
- die_id < MAX_DIE_PER_PACKAGE)
+ die_id < MAX_DIE_PER_PACKAGE) {
+ int core_id = get_physical_core_id(i);
+
cpu_cnt[pkg_id][die_id]++;
+ core_mask[pkg_id][die_id] |= (1ULL << core_id);
+ }
}
closedir(dir);
}
}
+int get_core_count(int pkg_id, int die_id)
+{
+ int cnt = 0;
+
+ if (pkg_id < MAX_PACKAGE_COUNT && die_id < MAX_DIE_PER_PACKAGE) {
+ int i;
+
+ for (i = 0; i < sizeof(long long) * 8; ++i) {
+ if (core_mask[pkg_id][die_id] & (1ULL << i))
+ cnt++;
+ }
+ }
+
+ return cnt;
+}
+
int get_cpu_count(int pkg_id, int die_id)
{
if (pkg_id < MAX_PACKAGE_COUNT && die_id < MAX_DIE_PER_PACKAGE)
diff --git a/tools/power/x86/intel-speed-select/isst-core.c b/tools/power/x86/intel-speed-select/isst-core.c
index 8b3e1c7abb42..52698553de92 100644
--- a/tools/power/x86/intel-speed-select/isst-core.c
+++ b/tools/power/x86/intel-speed-select/isst-core.c
@@ -335,12 +335,15 @@ int isst_set_tdp_level(int cpu, int tdp_level)
int isst_get_pbf_info(int cpu, int level, struct isst_pbf_info *pbf_info)
{
+ int i, ret, core_cnt, max;
unsigned int req, resp;
- int i, ret;
pbf_info->core_cpumask_size = alloc_cpu_set(&pbf_info->core_cpumask);
- for (i = 0; i < 2; ++i) {
+ core_cnt = get_core_count(get_physical_package_id(cpu), get_physical_die_id(cpu));
+ max = core_cnt > 32 ? 2 : 1;
+
+ for (i = 0; i < max; ++i) {
unsigned long long mask;
int count;
diff --git a/tools/power/x86/intel-speed-select/isst.h b/tools/power/x86/intel-speed-select/isst.h
index 84f56a468f82..cdf0f8a6dbbf 100644
--- a/tools/power/x86/intel-speed-select/isst.h
+++ b/tools/power/x86/intel-speed-select/isst.h
@@ -163,6 +163,7 @@ struct isst_pkg_ctdp {
extern int get_topo_max_cpus(void);
extern int get_cpu_count(int pkg_id, int die_id);
+extern int get_core_count(int pkg_id, int die_id);
/* Common interfaces */
extern void debug_printf(const char *format, ...);
--
2.17.2
next prev parent reply other threads:[~2019-11-04 11:03 UTC|newest]
Thread overview: 11+ messages / expand[flat|nested] mbox.gz Atom feed top
2019-11-04 11:02 [PATCH 00/10] tools/power/x86/intel-speed-select: New version Srinivas Pandruvada
2019-11-04 11:02 ` [PATCH 01/10] tools/power/x86/intel-speed-select: Extend command set for perf-profile Srinivas Pandruvada
2019-11-04 11:02 ` [PATCH 02/10] tools/power/x86/intel-speed-select: Change display of "avx" to "avx2" Srinivas Pandruvada
2019-11-04 11:02 ` [PATCH 03/10] tools/power/x86/intel-speed-select: Correct CLX-N frequency units Srinivas Pandruvada
2019-11-04 11:02 ` [PATCH 04/10] tools/power/x86/intel-speed-select: Auto mode for CLX Srinivas Pandruvada
2019-11-04 11:02 ` [PATCH 05/10] tools/power/x86/intel-speed-select: Use mailbox for CLOS_PM_QOS_CONFIG Srinivas Pandruvada
2019-11-04 11:02 ` [PATCH 06/10] tools/power/x86/intel-speed-select: Make CLOS frequency in MHz Srinivas Pandruvada
2019-11-04 11:02 ` [PATCH 07/10] tools/power/x86/intel-speed-select: Use Frequency weight for CLOS Srinivas Pandruvada
2019-11-04 11:02 ` [PATCH 08/10] tools/power/x86/intel-speed-select: Support platform with limited Intel(R) Speed Select Srinivas Pandruvada
2019-11-04 11:02 ` Srinivas Pandruvada [this message]
2019-11-04 11:02 ` [PATCH 10/10] tools/power/x86/intel-speed-select: Increment version Srinivas Pandruvada
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=20191104110246.70465-10-srinivas.pandruvada@linux.intel.com \
--to=srinivas.pandruvada@linux.intel.com \
--cc=andriy.shevchenko@intel.com \
--cc=linux-kernel@vger.kernel.org \
--cc=platform-driver-x86@vger.kernel.org \
--cc=prarit@redhat.com \
/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).