Received-SPF: pass (google.com: domain of linux-kernel-owner@vger.kernel.org designates 23.128.96.33 as permitted sender) client-ip=23.128.96.33;
From:   Srikar Dronamraju <srikar@linux.vnet.ibm.com>
To:     Michael Ellerman <mpe@ellerman.id.au>,
        Nicholas Piggin <npiggin@gmail.com>,
        Christophe Leroy <christophe.leroy@csgroup.eu>
Cc:     linuxppc-dev <linuxppc-dev@lists.ozlabs.org>,
        Srikar Dronamraju <srikar@linux.vnet.ibm.com>,
        Josh Poimboeuf <jpoimboe@kernel.org>,
        linux-kernel@vger.kernel.org, Mark Rutland <mark.rutland@arm.com>,
        "Paul E. McKenney" <paulmck@kernel.org>,
        Peter Zijlstra <peterz@infradead.org>,
        Rohan McLure <rmclure@linux.ibm.com>,
        Valentin Schneider <vschneid@redhat.com>,
        Vincent Guittot <vincent.guittot@linaro.org>,
        Aneesh <aneesh.kumar@kernel.org>,
        "ndesaulniers@google.com" <ndesaulniers@google.com>
Subject: [PATCH v5 5/5] powerpc/smp: Dynamically build Powerpc topology
Date:   Thu, 14 Dec 2023 23:37:15 +0530
Message-ID: <20231214180720.310852-6-srikar@linux.vnet.ibm.com>
In-Reply-To: <20231214180720.310852-1-srikar@linux.vnet.ibm.com>
References: <20231214180720.310852-1-srikar@linux.vnet.ibm.com>
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit
Precedence: bulk

Currently there are four Powerpc specific sched topologies.  These are
all statically defined.  However not all these topologies are used by
all Powerpc systems.

To avoid unnecessary degenerations by the scheduler, masks and flags
are compared. However if the sched topologies are build dynamically then
the code is simpler and there are greater chances of avoiding
degenerations.

Note:
Even X86 builds its sched topologies dynamically and proposed changes
are very similar to the way X86 is building its topologies.

Signed-off-by: Srikar Dronamraju <srikar@linux.vnet.ibm.com>
---
Changelog:
v3 -> v4:
- Conflict resolution due to rebase
	(DIE changed to PKG)

 arch/powerpc/kernel/smp.c | 78 ++++++++++++++-------------------------
 1 file changed, 28 insertions(+), 50 deletions(-)

diff --git a/arch/powerpc/kernel/smp.c b/arch/powerpc/kernel/smp.c
index 9d8bb9a084bd..693334c20d07 100644
--- a/arch/powerpc/kernel/smp.c
+++ b/arch/powerpc/kernel/smp.c
@@ -93,15 +93,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_l2_cache_map);
 EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 EXPORT_SYMBOL_GPL(has_big_cores);
 
-enum {
-#ifdef CONFIG_SCHED_SMT
-	smt_idx,
-#endif
-	cache_idx,
-	mc_idx,
-	die_idx,
-};
-
 #define MAX_THREAD_LIST_SIZE	8
 #define THREAD_GROUP_SHARE_L1   1
 #define THREAD_GROUP_SHARE_L2_L3 2
@@ -1067,16 +1058,6 @@ static const struct cpumask *cpu_mc_mask(int cpu)
 	return cpu_coregroup_mask(cpu);
 }
 
-static struct sched_domain_topology_level powerpc_topology[] = {
-#ifdef CONFIG_SCHED_SMT
-	{ cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT) },
-#endif
-	{ shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE) },
-	{ cpu_mc_mask, powerpc_shared_proc_flags, SD_INIT_NAME(MC) },
-	{ cpu_cpu_mask, powerpc_shared_proc_flags, SD_INIT_NAME(PKG) },
-	{ NULL, },
-};
-
 static int __init init_big_cores(void)
 {
 	int cpu;
@@ -1704,9 +1685,11 @@ void start_secondary(void *unused)
 	BUG();
 }
 
-static void __init fixup_topology(void)
+static struct sched_domain_topology_level powerpc_topology[6];
+
+static void __init build_sched_topology(void)
 {
-	int i;
+	int i = 0;
 
 	if (is_shared_processor() && has_big_cores)
 		static_branch_enable(&splpar_asym_pack);
@@ -1714,36 +1697,33 @@ static void __init fixup_topology(void)
 #ifdef CONFIG_SCHED_SMT
 	if (has_big_cores) {
 		pr_info("Big cores detected but using small core scheduling\n");
-		powerpc_topology[smt_idx].mask = smallcore_smt_mask;
+		powerpc_topology[i++] = (struct sched_domain_topology_level){
+			smallcore_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT)
+		};
+	} else {
+		powerpc_topology[i++] = (struct sched_domain_topology_level){
+			cpu_smt_mask, powerpc_smt_flags, SD_INIT_NAME(SMT)
+		};
 	}
 #endif
+	if (shared_caches) {
+		powerpc_topology[i++] = (struct sched_domain_topology_level){
+			shared_cache_mask, powerpc_shared_cache_flags, SD_INIT_NAME(CACHE)
+		};
+	}
+	if (has_coregroup_support()) {
+		powerpc_topology[i++] = (struct sched_domain_topology_level){
+			cpu_mc_mask, powerpc_shared_proc_flags, SD_INIT_NAME(MC)
+		};
+	}
+	powerpc_topology[i++] = (struct sched_domain_topology_level){
+		cpu_cpu_mask, powerpc_shared_proc_flags, SD_INIT_NAME(PKG)
+	};
 
-	if (!has_coregroup_support())
-		powerpc_topology[mc_idx].mask = powerpc_topology[cache_idx].mask;
-
-	/*
-	 * Try to consolidate topology levels here instead of
-	 * allowing scheduler to degenerate.
-	 * - Dont consolidate if masks are different.
-	 * - Dont consolidate if sd_flags exists and are different.
-	 */
-	for (i = 1; i <= die_idx; i++) {
-		if (powerpc_topology[i].mask != powerpc_topology[i - 1].mask)
-			continue;
-
-		if (powerpc_topology[i].sd_flags && powerpc_topology[i - 1].sd_flags &&
-				powerpc_topology[i].sd_flags != powerpc_topology[i - 1].sd_flags)
-			continue;
-
-		if (!powerpc_topology[i - 1].sd_flags)
-			powerpc_topology[i - 1].sd_flags = powerpc_topology[i].sd_flags;
+	/* There must be one trailing NULL entry left.  */
+	BUG_ON(i >= ARRAY_SIZE(powerpc_topology) - 1);
 
-		powerpc_topology[i].mask = powerpc_topology[i + 1].mask;
-		powerpc_topology[i].sd_flags = powerpc_topology[i + 1].sd_flags;
-#ifdef CONFIG_SCHED_DEBUG
-		powerpc_topology[i].name = powerpc_topology[i + 1].name;
-#endif
-	}
+	set_sched_topology(powerpc_topology);
 }
 
 void __init smp_cpus_done(unsigned int max_cpus)
@@ -1758,9 +1738,7 @@ void __init smp_cpus_done(unsigned int max_cpus)
 		smp_ops->bringup_done();
 
 	dump_numa_cpu_topology();
-
-	fixup_topology();
-	set_sched_topology(powerpc_topology);
+	build_sched_topology();
 }
 
 /*
-- 
2.35.3