lists.openwall.net   lists  /  announce  owl-users  owl-dev  john-users  john-dev  passwdqc-users  yescrypt  popa3d-users  /  oss-security  kernel-hardening  musl  sabotage  tlsify  passwords  /  crypt-dev  xvendor  /  Bugtraq  Full-Disclosure  linux-kernel  linux-netdev  linux-ext4  linux-hardening  linux-cve-announce  PHC 
Open Source and information security mailing list archives
 
Hash Suite: Windows password security audit tool. GUI, reports in PDF.
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20220217182110.7176-16-james.morse@arm.com>
Date:   Thu, 17 Feb 2022 18:21:04 +0000
From:   James Morse <james.morse@....com>
To:     x86@...nel.org, linux-kernel@...r.kernel.org
Cc:     Fenghua Yu <fenghua.yu@...el.com>,
        Reinette Chatre <reinette.chatre@...el.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...hat.com>, Borislav Petkov <bp@...en8.de>,
        H Peter Anvin <hpa@...or.com>,
        Babu Moger <Babu.Moger@....com>,
        James Morse <james.morse@....com>,
        shameerali.kolothum.thodi@...wei.com,
        Jamie Iles <jamie@...iainc.com>,
        D Scott Phillips OS <scott@...amperecomputing.com>,
        lcherian@...vell.com, bobo.shaobowang@...wei.com,
        tan.shaopeng@...itsu.com
Subject: [PATCH v3 15/21] x86/resctrl: Abstract __rmid_read()

__rmid_read() selects the specified eventid and returns the counter
value from the MSR. The error handling is architecture specific, and
handled by the callers, rdtgroup_mondata_show() and __mon_event_count().

Error handling should be handled by architecture specific code, as
a different architecture may have different requirements. MPAM's
counters can report that they are 'not ready', requiring a second
read after a short delay. This should be hidden from resctrl.

Make __rmid_read() the architecture specific function for reading
a counter. Rename it resctrl_arch_rmid_read() and move the error
handling into it.

Signed-off-by: James Morse <james.morse@....com>
---
Changes since v2:
 * Capitalisation
 * Stray newline restored
 * Removed rr->val set to the error value, and replaced it with clearing the
   the error to hide Unavailable from monitor group reads. (and added a block
   comment).

Changes since v1:
 * Return EINVAL from the impossible case in __mon_event_count() instead
   of an x86 hardware specific value.
---
 arch/x86/kernel/cpu/resctrl/ctrlmondata.c |  4 +-
 arch/x86/kernel/cpu/resctrl/internal.h    |  1 +
 arch/x86/kernel/cpu/resctrl/monitor.c     | 53 +++++++++++++++--------
 include/linux/resctrl.h                   |  1 +
 4 files changed, 39 insertions(+), 20 deletions(-)

diff --git a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
index ece3a1e0e6f2..d3f7eb2ac14b 100644
--- a/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
+++ b/arch/x86/kernel/cpu/resctrl/ctrlmondata.c
@@ -579,9 +579,9 @@ int rdtgroup_mondata_show(struct seq_file *m, void *arg)
 
 	mon_event_read(&rr, r, d, rdtgrp, evtid, false);
 
-	if (rr.val & RMID_VAL_ERROR)
+	if (rr.err == -EIO)
 		seq_puts(m, "Error\n");
-	else if (rr.val & RMID_VAL_UNAVAIL)
+	else if (rr.err == -EINVAL)
 		seq_puts(m, "Unavailable\n");
 	else
 		seq_printf(m, "%llu\n", rr.val * hw_res->mon_scale);
diff --git a/arch/x86/kernel/cpu/resctrl/internal.h b/arch/x86/kernel/cpu/resctrl/internal.h
index 726065bc02e4..e55d1774ce9c 100644
--- a/arch/x86/kernel/cpu/resctrl/internal.h
+++ b/arch/x86/kernel/cpu/resctrl/internal.h
@@ -94,6 +94,7 @@ struct rmid_read {
 	struct rdt_domain	*d;
 	enum resctrl_event_id	evtid;
 	bool			first;
+	int			err;
 	u64			val;
 };
 
diff --git a/arch/x86/kernel/cpu/resctrl/monitor.c b/arch/x86/kernel/cpu/resctrl/monitor.c
index 431acc3d3eb8..b6ad290fda8d 100644
--- a/arch/x86/kernel/cpu/resctrl/monitor.c
+++ b/arch/x86/kernel/cpu/resctrl/monitor.c
@@ -167,9 +167,9 @@ void resctrl_arch_reset_rmid(struct rdt_resource *r, struct rdt_domain *d,
 		memset(am, 0, sizeof(*am));
 }
 
-static u64 __rmid_read(u32 rmid, enum resctrl_event_id eventid)
+int resctrl_arch_rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *val)
 {
-	u64 val;
+	u64 msr_val;
 
 	/*
 	 * As per the SDM, when IA32_QM_EVTSEL.EvtID (bits 7:0) is configured
@@ -180,14 +180,24 @@ static u64 __rmid_read(u32 rmid, enum resctrl_event_id eventid)
 	 * are error bits.
 	 */
 	wrmsr(MSR_IA32_QM_EVTSEL, eventid, rmid);
-	rdmsrl(MSR_IA32_QM_CTR, val);
+	rdmsrl(MSR_IA32_QM_CTR, msr_val);
 
-	return val;
+	if (msr_val & RMID_VAL_ERROR)
+		return -EIO;
+	if (msr_val & RMID_VAL_UNAVAIL)
+		return -EINVAL;
+
+	*val = msr_val;
+
+	return 0;
 }
 
 static bool rmid_dirty(struct rmid_entry *entry)
 {
-	u64 val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID);
+	u64 val = 0;
+
+	if (resctrl_arch_rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID, &val))
+		return true;
 
 	return val >= resctrl_cqm_threshold;
 }
@@ -259,8 +269,8 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 {
 	struct rdt_resource *r;
 	struct rdt_domain *d;
-	int cpu;
-	u64 val;
+	int cpu, err;
+	u64 val = 0;
 
 	r = &rdt_resources_all[RDT_RESOURCE_L3].r_resctrl;
 
@@ -268,8 +278,10 @@ static void add_rmid_to_limbo(struct rmid_entry *entry)
 	cpu = get_cpu();
 	list_for_each_entry(d, &r->domains, list) {
 		if (cpumask_test_cpu(cpu, &d->cpu_mask)) {
-			val = __rmid_read(entry->rmid, QOS_L3_OCCUP_EVENT_ID);
-			if (val <= resctrl_cqm_threshold)
+			err = resctrl_arch_rmid_read(entry->rmid,
+						     QOS_L3_OCCUP_EVENT_ID,
+						     &val);
+			if (err || val <= resctrl_cqm_threshold)
 				continue;
 		}
 
@@ -319,15 +331,15 @@ static u64 __mon_event_count(u32 rmid, struct rmid_read *rr)
 {
 	struct rdt_hw_resource *hw_res = resctrl_to_arch_res(rr->r);
 	struct mbm_state *m;
-	u64 chunks, tval;
+	u64 chunks, tval = 0;
 
 	if (rr->first)
 		resctrl_arch_reset_rmid(rr->r, rr->d, rmid, rr->evtid);
 
-	tval = __rmid_read(rmid, rr->evtid);
-	if (tval & (RMID_VAL_ERROR | RMID_VAL_UNAVAIL)) {
-		return tval;
-	}
+	rr->err = resctrl_arch_rmid_read(rmid, rr->evtid, &tval);
+	if (rr->err)
+		return rr->err;
+
 	switch (rr->evtid) {
 	case QOS_L3_OCCUP_EVENT_ID:
 		rr->val += tval;
@@ -343,7 +355,7 @@ static u64 __mon_event_count(u32 rmid, struct rmid_read *rr)
 		 * Code would never reach here because an invalid
 		 * event id would fail the __rmid_read.
 		 */
-		return RMID_VAL_ERROR;
+		return -EINVAL;
 	}
 
 	if (rr->first) {
@@ -419,9 +431,14 @@ void mon_event_count(void *info)
 		}
 	}
 
-	/* Report error if none of rmid_reads are successful */
-	if (ret_val)
-		rr->val = ret_val;
+	/*
+	 * __mon_event_count() calls for newly created monitor groups may
+	 * report -EINVAL/Unavailable if the monitor hasn't seen any traffic.
+	 * If the first call for the control group succeed, discard any error
+	 * set by reads of monitor groups.
+	 */
+	if (ret_val == 0)
+		rr->err = 0;
 }
 
 /*
diff --git a/include/linux/resctrl.h b/include/linux/resctrl.h
index 0b48239f5920..70112dbfa128 100644
--- a/include/linux/resctrl.h
+++ b/include/linux/resctrl.h
@@ -219,6 +219,7 @@ u32 resctrl_arch_get_config(struct rdt_resource *r, struct rdt_domain *d,
 			    u32 closid, enum resctrl_conf_type type);
 int resctrl_online_domain(struct rdt_resource *r, struct rdt_domain *d);
 void resctrl_offline_domain(struct rdt_resource *r, struct rdt_domain *d);
+int resctrl_arch_rmid_read(u32 rmid, enum resctrl_event_id eventid, u64 *res);
 
 /**
  * resctrl_arch_reset_rmid() - Reset any private state associated with rmid
-- 
2.30.2

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ