From: Yi Sun <yi.y.sun@linux.intel.com>
To: xen-devel@lists.xenproject.org
Cc: kevin.tian@intel.com, wei.liu2@citrix.com,
andrew.cooper3@citrix.com, dario.faggioli@citrix.com,
he.chen@linux.intel.com, ian.jackson@eu.citrix.com,
Yi Sun <yi.y.sun@linux.intel.com>,
mengxu@cis.upenn.edu, jbeulich@suse.com,
chao.p.peng@linux.intel.com, roger.pau@citrix.com
Subject: [PATCH v9 17/25] x86: refactor psr: CDP: implement set value callback functions.
Date: Thu, 16 Mar 2017 19:08:07 +0800 [thread overview]
Message-ID: <1489662495-5375-18-git-send-email-yi.y.sun@linux.intel.com> (raw)
In-Reply-To: <1489662495-5375-1-git-send-email-yi.y.sun@linux.intel.com>
This patch implements L3 CDP set value related callback functions.
With this patch, 'psr-cat-cbm-set' command can work for L3 CDP.
Signed-off-by: Yi Sun <yi.y.sun@linux.intel.com>
---
v9:
- add comment to explain why CDP uses 2 COSs.
(suggested by Wei Liu)
- use 'cat_default_val'.
(suggested by Wei Liu)
- remove 'l3_cdp_get_cos_num' because we can directly get cos_num from
feat_node now.
(suggested by Jan Beulich)
- remove cos checking because it has been moved to common function.
(suggested by Jan Beulich)
- l3_cdp_set_new_val parameter 'm' is changed to 'new_val'.
(suggested by Jan Beulich)
- directly use get_cdp_data(feat, 0) and get_cdp_code(feat, 0) to get
default value.
(suggested by Jan Beulich)
- modify 'l3_cdp_write_msr' flow to write value into register according
to input type.
- changes about 'uint64_t' to 'uint32_t'.
(suggested by Jan Beulich)
v8:
- modify 'l3_cdp_write_msr' type to 'void'.
v5:
- remove type check in callback function.
(suggested by Jan Beulich)
- modify return value of callback functions because we do not need them
to return number of entries the feature uses. In caller, we call
'get_cos_num' to get the number of entries the feature uses.
(suggested by Jan Beulich)
- remove 'l3_cdp_get_cos_max_from_type'.
- rename 'l3_cdp_exceeds_cos_max' to 'l3_cdp_fits_cos_max'.
(suggested by Jan Beulich)
v4:
- create this patch to make codes easier to understand.
(suggested by Jan Beulich)
---
xen/arch/x86/psr.c | 91 ++++++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 91 insertions(+)
diff --git a/xen/arch/x86/psr.c b/xen/arch/x86/psr.c
index 0ce8a6b..7ede8a1 100644
--- a/xen/arch/x86/psr.c
+++ b/xen/arch/x86/psr.c
@@ -530,10 +530,101 @@ static void l3_cdp_get_val(const struct feat_node *feat, unsigned int cos,
*val = get_cdp_code(feat, cos);
}
+static void l3_cdp_get_old_val(uint32_t val[],
+ const struct feat_node *feat,
+ unsigned int old_cos)
+{
+ /* Data */
+ val[0] = get_cdp_data(feat, old_cos);
+ /* Code */
+ val[1] = get_cdp_code(feat, old_cos);
+}
+
+static int l3_cdp_set_new_val(uint32_t val[],
+ const struct feat_node *feat,
+ enum cbm_type type,
+ uint32_t new_val)
+{
+ if ( !psr_check_cbm(feat->info.cat_info.cbm_len, new_val) )
+ return -EINVAL;
+
+ if ( type == PSR_CBM_TYPE_L3_DATA )
+ val[0] = new_val;
+ else
+ val[1] = new_val;
+
+ return 0;
+}
+
+static int l3_cdp_compare_val(const uint32_t val[],
+ const struct feat_node *feat,
+ unsigned int cos)
+{
+ /*
+ * Different features' cos_max are different. If cos id of the feature
+ * being set exceeds other feature's cos_max, the val of other feature
+ * must be default value. HW supports such case.
+ */
+ if ( cos > feat->info.cat_info.cos_max )
+ {
+ if ( val[0] != get_cdp_data(feat, 0) ||
+ val[1] != get_cdp_code(feat, 0) )
+ return -EINVAL;
+
+ /* Find */
+ return 1;
+ }
+
+ if ( val[0] == get_cdp_data(feat, cos) &&
+ val[1] == get_cdp_code(feat, cos) )
+ /* Find */
+ return 1;
+
+ /* Not find */
+ return 0;
+}
+
+static bool l3_cdp_fits_cos_max(const uint32_t val[],
+ const struct feat_node *feat,
+ unsigned int cos)
+{
+ if ( cos > feat->info.cat_info.cos_max &&
+ (val[0] != get_cdp_data(feat, 0) || val[1] != get_cdp_code(feat, 0)) )
+ /*
+ * Exceed cos_max and value to set is not default,
+ * return error.
+ */
+ return false;
+
+ return true;
+}
+
+static void l3_cdp_write_msr(unsigned int cos, uint32_t val,
+ enum cbm_type type, struct feat_node *feat)
+{
+ /* Data */
+ if ( type == PSR_CBM_TYPE_L3_DATA && get_cdp_data(feat, cos) != val )
+ {
+ get_cdp_data(feat, cos) = val;
+ wrmsrl(MSR_IA32_PSR_L3_MASK_DATA(cos), (uint64_t)val);
+ }
+ /* Code */
+ if ( type == PSR_CBM_TYPE_L3_CODE && get_cdp_code(feat, cos) != val )
+ {
+ get_cdp_code(feat, cos) = val;
+ wrmsrl(MSR_IA32_PSR_L3_MASK_CODE(cos), (uint64_t)val);
+ }
+}
+
struct feat_ops l3_cdp_ops = {
.get_cos_max = cat_get_cos_max,
.get_feat_info = l3_cdp_get_feat_info,
.get_val = l3_cdp_get_val,
+ .get_old_val = l3_cdp_get_old_val,
+ .set_new_val = l3_cdp_set_new_val,
+ .compare_val = l3_cdp_compare_val,
+ .fits_cos_max = l3_cdp_fits_cos_max,
+ .write_msr = l3_cdp_write_msr,
};
static void __init parse_psr_bool(char *s, char *value, char *feature,
--
1.9.1
_______________________________________________
Xen-devel mailing list
Xen-devel@lists.xen.org
https://lists.xen.org/xen-devel
next prev parent reply other threads:[~2017-03-16 11:14 UTC|newest]
Thread overview: 105+ messages / expand[flat|nested] mbox.gz Atom feed top
2017-03-16 11:07 [PATCH v9 00/25] Enable L2 Cache Allocation Technology & Refactor psr.c Yi Sun
2017-03-16 11:07 ` [PATCH v9 01/25] docs: create Cache Allocation Technology (CAT) and Code and Data Prioritization (CDP) feature document Yi Sun
2017-03-16 11:07 ` [PATCH v9 02/25] x86: refactor psr: remove L3 CAT/CDP codes Yi Sun
2017-03-16 11:07 ` [PATCH v9 03/25] x86: refactor psr: implement main data structures Yi Sun
2017-03-24 16:19 ` Jan Beulich
2017-03-27 2:38 ` Yi Sun
2017-03-27 6:20 ` Jan Beulich
2017-03-27 7:12 ` Yi Sun
2017-03-27 7:37 ` Jan Beulich
2017-03-16 11:07 ` [PATCH v9 04/25] x86: move cpuid_count_leaf from cpuid.c to processor.h Yi Sun
2017-03-24 16:22 ` Jan Beulich
2017-03-16 11:07 ` [PATCH v9 05/25] x86: refactor psr: L3 CAT: implement CPU init and free flow Yi Sun
2017-03-24 16:52 ` Jan Beulich
2017-03-27 4:41 ` Yi Sun
2017-03-27 6:34 ` Jan Beulich
2017-03-27 8:16 ` Yi Sun
2017-03-27 8:43 ` Jan Beulich
2017-03-16 11:07 ` [PATCH v9 06/25] x86: refactor psr: L3 CAT: implement Domain init/free and schedule flows Yi Sun
2017-03-16 11:07 ` [PATCH v9 07/25] x86: refactor psr: L3 CAT: implement get hw info flow Yi Sun
2017-03-27 9:07 ` Jan Beulich
2017-03-27 12:24 ` Yi Sun
2017-03-27 12:51 ` Jan Beulich
2017-03-27 13:19 ` Yi Sun
2017-03-27 13:32 ` Jan Beulich
2017-03-16 11:07 ` [PATCH v9 08/25] x86: refactor psr: L3 CAT: implement get value flow Yi Sun
2017-03-27 9:23 ` Jan Beulich
2017-03-27 12:59 ` Yi Sun
2017-03-27 13:34 ` Jan Beulich
2017-03-28 2:13 ` Yi Sun
2017-03-28 8:10 ` Jan Beulich
2017-03-16 11:07 ` [PATCH v9 09/25] x86: refactor psr: L3 CAT: set value: implement framework Yi Sun
2017-03-27 9:59 ` Jan Beulich
2017-03-28 1:21 ` Yi Sun
2017-03-28 8:21 ` Jan Beulich
2017-03-16 11:08 ` [PATCH v9 10/25] x86: refactor psr: L3 CAT: set value: assemble features value array Yi Sun
2017-03-27 10:17 ` Jan Beulich
2017-03-28 3:12 ` Yi Sun
2017-03-28 8:05 ` Yi Sun
2017-03-28 8:36 ` Jan Beulich
2017-03-28 9:11 ` Yi Sun
2017-03-28 9:20 ` Jan Beulich
2017-03-28 10:18 ` Yi Sun
2017-03-28 10:39 ` Jan Beulich
2017-03-28 8:34 ` Jan Beulich
2017-03-28 10:12 ` Yi Sun
2017-03-28 10:36 ` Jan Beulich
2017-03-16 11:08 ` [PATCH v9 11/25] x86: refactor psr: L3 CAT: set value: implement cos finding flow Yi Sun
2017-03-27 10:28 ` Jan Beulich
2017-03-28 3:26 ` Yi Sun
2017-03-28 8:41 ` Jan Beulich
2017-03-16 11:08 ` [PATCH v9 12/25] x86: refactor psr: L3 CAT: set value: implement cos id picking flow Yi Sun
2017-03-27 10:37 ` Jan Beulich
2017-03-28 4:58 ` Yi Sun
2017-03-28 8:45 ` Jan Beulich
2017-03-28 10:31 ` Yi Sun
2017-03-28 10:40 ` Jan Beulich
2017-03-28 11:59 ` Yi Sun
2017-03-28 12:20 ` Jan Beulich
2017-03-29 1:20 ` Yi Sun
2017-03-29 1:36 ` Yi Sun
2017-03-29 9:57 ` Jan Beulich
2017-03-30 1:37 ` Yi Sun
2017-03-30 1:39 ` Yi Sun
2017-03-30 11:55 ` Jan Beulich
2017-03-30 12:10 ` Yi Sun
2017-03-31 8:47 ` Jan Beulich
2017-03-31 9:12 ` Yi Sun
2017-03-31 9:18 ` Yi Sun
2017-03-31 10:19 ` Jan Beulich
2017-03-31 12:40 ` Yi Sun
2017-03-31 12:51 ` Jan Beulich
2017-03-31 13:22 ` Yi Sun
2017-03-31 14:35 ` Jan Beulich
2017-03-31 14:46 ` Yi Sun
2017-03-16 11:08 ` [PATCH v9 13/25] x86: refactor psr: L3 CAT: set value: implement write msr flow Yi Sun
2017-03-27 10:46 ` Jan Beulich
2017-03-28 5:06 ` Yi Sun
2017-03-28 8:48 ` Jan Beulich
2017-03-28 10:20 ` Yi Sun
2017-03-16 11:08 ` [PATCH v9 14/25] x86: refactor psr: CDP: implement CPU init and free flow Yi Sun
2017-03-27 13:58 ` Jan Beulich
2017-03-16 11:08 ` [PATCH v9 15/25] x86: refactor psr: CDP: implement get hw info flow Yi Sun
2017-03-27 14:08 ` Jan Beulich
2017-03-28 5:13 ` Yi Sun
2017-03-16 11:08 ` [PATCH v9 16/25] x86: refactor psr: CDP: implement get value flow Yi Sun
2017-03-16 11:08 ` Yi Sun [this message]
2017-03-27 14:17 ` [PATCH v9 17/25] x86: refactor psr: CDP: implement set value callback functions Jan Beulich
2017-03-28 5:14 ` Yi Sun
2017-03-16 11:08 ` [PATCH v9 18/25] x86: L2 CAT: implement CPU init and free flow Yi Sun
2017-03-16 11:08 ` [PATCH v9 19/25] x86: L2 CAT: implement get hw info flow Yi Sun
2017-03-27 14:38 ` Jan Beulich
2017-03-28 5:16 ` Yi Sun
2017-03-16 11:08 ` [PATCH v9 20/25] x86: L2 CAT: implement get value flow Yi Sun
2017-03-27 14:39 ` Jan Beulich
2017-03-16 11:08 ` [PATCH v9 21/25] x86: L2 CAT: implement set " Yi Sun
2017-03-27 14:40 ` Jan Beulich
2017-03-16 11:08 ` [PATCH v9 22/25] tools: L2 CAT: support get HW info for L2 CAT Yi Sun
2017-03-16 11:08 ` [PATCH v9 23/25] tools: L2 CAT: support show cbm " Yi Sun
2017-03-16 11:08 ` [PATCH v9 24/25] tools: L2 CAT: support set " Yi Sun
2017-03-28 14:04 ` Wei Liu
2017-03-29 1:21 ` Yi Sun
2017-03-16 11:08 ` [PATCH v9 25/25] docs: add L2 CAT description in docs Yi Sun
2017-03-16 11:20 ` [PATCH v9 00/25] Enable L2 Cache Allocation Technology & Refactor psr.c Jan Beulich
2017-03-17 1:29 ` Yi Sun
2017-03-17 7:25 ` Jan Beulich
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=1489662495-5375-18-git-send-email-yi.y.sun@linux.intel.com \
--to=yi.y.sun@linux.intel.com \
--cc=andrew.cooper3@citrix.com \
--cc=chao.p.peng@linux.intel.com \
--cc=dario.faggioli@citrix.com \
--cc=he.chen@linux.intel.com \
--cc=ian.jackson@eu.citrix.com \
--cc=jbeulich@suse.com \
--cc=kevin.tian@intel.com \
--cc=mengxu@cis.upenn.edu \
--cc=roger.pau@citrix.com \
--cc=wei.liu2@citrix.com \
--cc=xen-devel@lists.xenproject.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).