All of lore.kernel.org
 help / color / mirror / Atom feed
From: David Woodhouse <dwmw2@infradead.org>
To: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>, Borislav Petkov <bp@alien8.de>,
	Dave Hansen <dave.hansen@linux.intel.com>,
	x86@kernel.org, "H . Peter Anvin" <hpa@zytor.com>,
	Paolo Bonzini <pbonzini@redhat.com>,
	"Paul E . McKenney" <paulmck@kernel.org>,
	linux-kernel@vger.kernel.org, kvm@vger.kernel.org,
	rcu@vger.kernel.org, mimoja@mimoja.de, hewenliang4@huawei.com,
	hushiyuan@huawei.com, luolongjun@huawei.com,
	hejingxian@huawei.com
Subject: [PATCH v3 1/9] x86/apic/x2apic: Fix parallel handling of cluster_mask
Date: Wed, 15 Dec 2021 14:56:25 +0000	[thread overview]
Message-ID: <20211215145633.5238-2-dwmw2@infradead.org> (raw)
In-Reply-To: <20211215145633.5238-1-dwmw2@infradead.org>

From: David Woodhouse <dwmw@amazon.co.uk>

For each CPU being brought up, the alloc_clustermask() function
allocates a new struct cluster_mask just in case it's needed. Then the
target CPU actually runs, and in init_x2apic_ldr() it either uses a
cluster_mask from a previous CPU in the same cluster, or consumes the
"spare" one and sets the global pointer to NULL.

That isn't going to parallelise stunningly well.

Ditch the global variable, let alloc_clustermask() install the struct
*directly* in the per_cpu data for the CPU being brought up. As an
optimisation, actually make it do so for *all* present CPUs in the same
cluster, which means only one iteration over for_each_present_cpu()
instead of doing so repeatedly, once for each CPU.

Now, in fact, there's no point in the 'node' or 'clusterid' members of
the struct cluster_mask, so just kill it and use struct cpumask instead.

This was a harmless "bug" while CPU bringup wasn't actually happening in
parallel. It's about to become less harmless...

Fixes: 023a611748fd5 ("x86/apic/x2apic: Simplify cluster management")
Signed-off-by: David Woodhouse <dwmw@amazon.co.uk>
---
 arch/x86/kernel/apic/x2apic_cluster.c | 108 +++++++++++++++-----------
 1 file changed, 62 insertions(+), 46 deletions(-)

diff --git a/arch/x86/kernel/apic/x2apic_cluster.c b/arch/x86/kernel/apic/x2apic_cluster.c
index e696e22d0531..e116dfaf5922 100644
--- a/arch/x86/kernel/apic/x2apic_cluster.c
+++ b/arch/x86/kernel/apic/x2apic_cluster.c
@@ -9,11 +9,7 @@
 
 #include "local.h"
 
-struct cluster_mask {
-	unsigned int	clusterid;
-	int		node;
-	struct cpumask	mask;
-};
+#define apic_cluster(apicid) ((apicid) >> 4)
 
 /*
  * __x2apic_send_IPI_mask() possibly needs to read
@@ -23,8 +19,7 @@ struct cluster_mask {
 static u32 *x86_cpu_to_logical_apicid __read_mostly;
 
 static DEFINE_PER_CPU(cpumask_var_t, ipi_mask);
-static DEFINE_PER_CPU_READ_MOSTLY(struct cluster_mask *, cluster_masks);
-static struct cluster_mask *cluster_hotplug_mask;
+static DEFINE_PER_CPU_READ_MOSTLY(struct cpumask *, cluster_masks);
 
 static int x2apic_acpi_madt_oem_check(char *oem_id, char *oem_table_id)
 {
@@ -60,10 +55,10 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
 
 	/* Collapse cpus in a cluster so a single IPI per cluster is sent */
 	for_each_cpu(cpu, tmpmsk) {
-		struct cluster_mask *cmsk = per_cpu(cluster_masks, cpu);
+		struct cpumask *cmsk = per_cpu(cluster_masks, cpu);
 
 		dest = 0;
-		for_each_cpu_and(clustercpu, tmpmsk, &cmsk->mask)
+		for_each_cpu_and(clustercpu, tmpmsk, cmsk)
 			dest |= x86_cpu_to_logical_apicid[clustercpu];
 
 		if (!dest)
@@ -71,7 +66,7 @@ __x2apic_send_IPI_mask(const struct cpumask *mask, int vector, int apic_dest)
 
 		__x2apic_send_IPI_dest(dest, vector, APIC_DEST_LOGICAL);
 		/* Remove cluster CPUs from tmpmask */
-		cpumask_andnot(tmpmsk, tmpmsk, &cmsk->mask);
+		cpumask_andnot(tmpmsk, tmpmsk, cmsk);
 	}
 
 	local_irq_restore(flags);
@@ -105,55 +100,76 @@ static u32 x2apic_calc_apicid(unsigned int cpu)
 
 static void init_x2apic_ldr(void)
 {
-	struct cluster_mask *cmsk = this_cpu_read(cluster_masks);
-	u32 cluster, apicid = apic_read(APIC_LDR);
-	unsigned int cpu;
+	struct cpumask *cmsk = this_cpu_read(cluster_masks);
 
-	x86_cpu_to_logical_apicid[smp_processor_id()] = apicid;
+	BUG_ON(!cmsk);
 
-	if (cmsk)
-		goto update;
-
-	cluster = apicid >> 16;
-	for_each_online_cpu(cpu) {
-		cmsk = per_cpu(cluster_masks, cpu);
-		/* Matching cluster found. Link and update it. */
-		if (cmsk && cmsk->clusterid == cluster)
-			goto update;
+	cpumask_set_cpu(smp_processor_id(), cmsk);
+}
+
+/*
+ * As an optimisation during boot, set the cluster_mask for *all*
+ * present CPUs at once, to prevent *each* of them having to iterate
+ * over the others to find the existing cluster_mask.
+ */
+static void prefill_clustermask(struct cpumask *cmsk, u32 cluster)
+{
+	int cpu;
+
+	for_each_present_cpu(cpu) {
+		u32 apicid = apic->cpu_present_to_apicid(cpu);
+		if (apicid != BAD_APICID && apic_cluster(apicid) == cluster) {
+			struct cpumask **cpu_cmsk = &per_cpu(cluster_masks, cpu);
+
+			BUG_ON(*cpu_cmsk && *cpu_cmsk != cmsk);
+			*cpu_cmsk = cmsk;
+		}
 	}
-	cmsk = cluster_hotplug_mask;
-	cmsk->clusterid = cluster;
-	cluster_hotplug_mask = NULL;
-update:
-	this_cpu_write(cluster_masks, cmsk);
-	cpumask_set_cpu(smp_processor_id(), &cmsk->mask);
 }
 
-static int alloc_clustermask(unsigned int cpu, int node)
+static int alloc_clustermask(unsigned int cpu, u32 cluster, int node)
 {
+	struct cpumask *cmsk = NULL;
+	unsigned int cpu_i;
+	u32 apicid;
+
 	if (per_cpu(cluster_masks, cpu))
 		return 0;
-	/*
-	 * If a hotplug spare mask exists, check whether it's on the right
-	 * node. If not, free it and allocate a new one.
-	 */
-	if (cluster_hotplug_mask) {
-		if (cluster_hotplug_mask->node == node)
-			return 0;
-		kfree(cluster_hotplug_mask);
+
+	/* For the hotplug case, don't always allocate a new one */
+	if (system_state >= SYSTEM_RUNNING) {
+		for_each_present_cpu(cpu_i) {
+			apicid = apic->cpu_present_to_apicid(cpu_i);
+			if (apicid != BAD_APICID && apic_cluster(apicid) == cluster) {
+				cmsk = per_cpu(cluster_masks, cpu_i);
+				if (cmsk)
+					break;
+			}
+		}
+	}
+	if (!cmsk) {
+		cmsk = kzalloc_node(sizeof(*cmsk), GFP_KERNEL, node);
+		if (!cmsk)
+			return -ENOMEM;
 	}
 
-	cluster_hotplug_mask = kzalloc_node(sizeof(*cluster_hotplug_mask),
-					    GFP_KERNEL, node);
-	if (!cluster_hotplug_mask)
-		return -ENOMEM;
-	cluster_hotplug_mask->node = node;
+	per_cpu(cluster_masks, cpu) = cmsk;
+
+	if (system_state < SYSTEM_RUNNING)
+		prefill_clustermask(cmsk, cluster);
+
 	return 0;
 }
 
 static int x2apic_prepare_cpu(unsigned int cpu)
 {
-	if (alloc_clustermask(cpu, cpu_to_node(cpu)) < 0)
+	u32 phys_apicid = apic->cpu_present_to_apicid(cpu);
+	u32 cluster = apic_cluster(phys_apicid);
+	u32 logical_apicid = (cluster << 16) | (1 << (phys_apicid & 0xf));
+
+	x86_cpu_to_logical_apicid[cpu] = logical_apicid;
+
+	if (alloc_clustermask(cpu, cluster, cpu_to_node(cpu)) < 0)
 		return -ENOMEM;
 	if (!zalloc_cpumask_var(&per_cpu(ipi_mask, cpu), GFP_KERNEL))
 		return -ENOMEM;
@@ -162,10 +178,10 @@ static int x2apic_prepare_cpu(unsigned int cpu)
 
 static int x2apic_dead_cpu(unsigned int dead_cpu)
 {
-	struct cluster_mask *cmsk = per_cpu(cluster_masks, dead_cpu);
+	struct cpumask *cmsk = per_cpu(cluster_masks, dead_cpu);
 
 	if (cmsk)
-		cpumask_clear_cpu(dead_cpu, &cmsk->mask);
+		cpumask_clear_cpu(dead_cpu, cmsk);
 	free_cpumask_var(per_cpu(ipi_mask, dead_cpu));
 	return 0;
 }
-- 
2.31.1


  reply	other threads:[~2021-12-15 14:57 UTC|newest]

Thread overview: 57+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-12-15 14:56 [PATCH v3 0/9] Parallel CPU bringup for x86_64 David Woodhouse
2021-12-15 14:56 ` David Woodhouse [this message]
2021-12-15 14:56 ` [PATCH v3 2/9] cpu/hotplug: Move idle_thread_get() to <linux/smpboot.h> David Woodhouse
2021-12-15 14:56 ` [PATCH v3 3/9] cpu/hotplug: Add dynamic parallel bringup states before CPUHP_BRINGUP_CPU David Woodhouse
2021-12-15 14:56 ` [PATCH v3 4/9] x86/smpboot: Reference count on smpboot_setup_warm_reset_vector() David Woodhouse
2021-12-15 14:56 ` [PATCH v3 5/9] x86/smpboot: Split up native_cpu_up into separate phases and document them David Woodhouse
2021-12-15 14:56 ` [PATCH v3 6/9] x86/smpboot: Support parallel startup of secondary CPUs David Woodhouse
2021-12-16 14:24   ` Tom Lendacky
2021-12-16 18:24     ` David Woodhouse
2021-12-16 19:00       ` Tom Lendacky
2021-12-16 19:20         ` David Woodhouse
2022-01-29 12:04           ` David Woodhouse
2022-01-31 13:59             ` Borislav Petkov
2022-02-01 10:25               ` David Woodhouse
2022-02-01 10:56                 ` Borislav Petkov
2022-02-01 12:39                   ` David Woodhouse
2022-02-01 12:56                     ` Borislav Petkov
2022-02-01 13:02                       ` David Woodhouse
2021-12-15 14:56 ` [PATCH v3 7/9] x86/smpboot: Send INIT/SIPI/SIPI to secondary CPUs in parallel David Woodhouse
2021-12-15 14:56 ` [PATCH v3 8/9] x86/mtrr: Avoid repeated save of MTRRs on boot-time CPU bringup David Woodhouse
2021-12-15 14:56 ` [PATCH v3 9/9] x86/smpboot: Serialize topology updates for secondary bringup David Woodhouse
2021-12-16 16:27 ` [PATCH v3 0/9] Parallel CPU bringup for x86_64 Tom Lendacky
2021-12-16 19:24   ` David Woodhouse
2021-12-16 22:52     ` Tom Lendacky
2021-12-17  0:13       ` David Woodhouse
2021-12-17 10:09         ` Igor Mammedov
2021-12-17 15:40           ` David Woodhouse
2021-12-20 17:10           ` David Woodhouse
2021-12-20 18:54             ` Tom Lendacky
2021-12-20 21:29               ` David Woodhouse
2021-12-20 21:47                 ` Tom Lendacky
2021-12-21 22:25                   ` Tom Lendacky
2021-12-21 22:33                     ` David Woodhouse
2021-12-17 17:48         ` Tom Lendacky
2021-12-17 19:11           ` David Woodhouse
2021-12-17 19:26             ` David Woodhouse
2021-12-17 20:15               ` Tom Lendacky
2021-12-17 19:46             ` Tom Lendacky
2021-12-17 20:13               ` David Woodhouse
2021-12-17 20:55                 ` Tom Lendacky
2021-12-17 22:48                   ` David Woodhouse
2022-01-28  9:54                   ` David Woodhouse
2022-01-28 21:40                     ` Sean Christopherson
2022-01-28 21:48                       ` David Woodhouse
2022-01-29  9:22                       ` David Woodhouse
2021-12-16 19:52   ` David Woodhouse
2021-12-16 19:55     ` Tom Lendacky
2021-12-16 19:59       ` David Woodhouse
2021-12-27 16:57 ` Paul Menzel
2021-12-28 11:34   ` Paul Menzel
2021-12-28 14:18     ` David Woodhouse
2021-12-29 13:18       ` Paul Menzel
2021-12-29 13:54         ` David Woodhouse
2022-02-14 13:45           ` Paul Menzel
2022-04-21 10:00             ` Mimoja
2022-04-22 21:19               ` Tom Lendacky
2022-06-01  8:30                 ` David Woodhouse

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=20211215145633.5238-2-dwmw2@infradead.org \
    --to=dwmw2@infradead.org \
    --cc=bp@alien8.de \
    --cc=dave.hansen@linux.intel.com \
    --cc=hejingxian@huawei.com \
    --cc=hewenliang4@huawei.com \
    --cc=hpa@zytor.com \
    --cc=hushiyuan@huawei.com \
    --cc=kvm@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luolongjun@huawei.com \
    --cc=mimoja@mimoja.de \
    --cc=mingo@redhat.com \
    --cc=paulmck@kernel.org \
    --cc=pbonzini@redhat.com \
    --cc=rcu@vger.kernel.org \
    --cc=tglx@linutronix.de \
    --cc=x86@kernel.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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.