linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Prarit Bhargava <prarit@redhat.com>
To: linux-kernel@vger.kernel.org
Cc: Andi Kleen <ak@linux.intel.com>,
	Prarit Bhargava <prarit@redhat.com>,
	Thomas Gleixner <tglx@linutronix.de>,
	Ingo Molnar <mingo@redhat.com>, "H. Peter Anvin" <hpa@zytor.com>,
	x86@kernel.org, Peter Zijlstra <peterz@infradead.org>,
	Dave Hansen <dave.hansen@intel.com>,
	Piotr Luc <piotr.luc@intel.com>, Kan Liang <kan.liang@intel.com>,
	Borislav Petkov <bp@suse.de>,
	Stephane Eranian <eranian@google.com>,
	Arvind Yadav <arvind.yadav.cs@gmail.com>,
	Andy Lutomirski <luto@kernel.org>,
	Christian Borntraeger <borntraeger@de.ibm.com>,
	"Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>,
	Tom Lendacky <thomas.lendacky@amd.com>,
	Mathias Krause <minipli@googlemail.com>,
	Tim Chen <tim.c.chen@linux.intel.com>,
	Vitaly Kuznetsov <vkuznets@redhat.com>
Subject: [PATCH 2/3 v4] x86/topology: Avoid wasting 128k for package id array
Date: Wed, 25 Oct 2017 08:09:39 -0400	[thread overview]
Message-ID: <20171025120940.15721-3-prarit@redhat.com> (raw)
In-Reply-To: <20171025120940.15721-1-prarit@redhat.com>

From: Andi Kleen <ak@linux.intel.com>

I was looking at large early boot allocations and noticed that since
(1f12e32f x86/topology: Create logical package id) every 64bit system
allocates a 128k array to convert logical package ids.

This happens because the array is sized to (MAX_LOCAL_APIC * u16) = 128k.
This is a lot of waste especially for most systems which have one or two
sockets.

Use a dynamically allocated array of size logical_packages to map
the logical and physical packages.

[v2]: Decrease logical_packages when the last thread in a socket is
removed.
[v3]: Add more logic to keep logical and physical package IDs
in synch.
[v4]: Keep logical mapping static by using hybrid approach of a small logical
to physical array and keeping logical cpu information in cpu_data.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Prarit Bhargava <prarit@redhat.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: x86@kernel.org
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Piotr Luc <piotr.luc@intel.com>
Cc: Kan Liang <kan.liang@intel.com>
Cc: Borislav Petkov <bp@suse.de>
Cc: Stephane Eranian <eranian@google.com>
Cc: Prarit Bhargava <prarit@redhat.com>
Cc: Arvind Yadav <arvind.yadav.cs@gmail.com>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Christian Borntraeger <borntraeger@de.ibm.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Tom Lendacky <thomas.lendacky@amd.com>
Cc: Mathias Krause <minipli@googlemail.com>
Cc: Tim Chen <tim.c.chen@linux.intel.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
---
 arch/x86/include/asm/processor.h |  4 +-
 arch/x86/kernel/smpboot.c        | 86 +++++++++++++++++++---------------------
 2 files changed, 43 insertions(+), 47 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index b390ff76e58f..f4ab1edf4e24 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -124,8 +124,10 @@ struct cpuinfo_x86 {
 	u16			booted_cores;
 	/* Physical processor id: */
 	u16			phys_proc_id;
-	/* Logical processor id: */
+	/* Logical processor (package) id: */
 	u16			logical_proc_id;
+	/* Physical package ID */
+	u16			phys_pkg_id;
 	/* Core id: */
 	u16			cpu_core_id;
 	/* Index into per_cpu list: */
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index ad59edd84de7..ca615bc94e82 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -99,12 +99,10 @@ DEFINE_PER_CPU_READ_MOSTLY(cpumask_var_t, cpu_llc_shared_map);
 DEFINE_PER_CPU_READ_MOSTLY(struct cpuinfo_x86, cpu_info);
 EXPORT_PER_CPU_SYMBOL(cpu_info);
 
-/* Logical package management. We might want to allocate that dynamically */
-static int *physical_to_logical_pkg __read_mostly;
-static unsigned long *physical_package_map __read_mostly;;
-static unsigned int max_physical_pkg_id __read_mostly;
+/* Logical package management.*/
 unsigned int __max_logical_packages __read_mostly;
 EXPORT_SYMBOL(__max_logical_packages);
+static u16 *logical_to_physical_pkg_map;
 static unsigned int logical_packages __read_mostly;
 
 /* Maximum number of SMT threads on any online core */
@@ -278,6 +276,23 @@ static void notrace start_secondary(void *unused)
 	cpu_startup_entry(CPUHP_AP_ONLINE_IDLE);
 }
 
+/**
+ * topology_phys_to_logical_pkg - Map a physical package id to a logical
+ *
+ * Returns logical package id or -1 if not found
+ */
+int topology_phys_to_logical_pkg(unsigned int phys_pkg)
+{
+	int log_pkg;
+
+	for (log_pkg = 0; log_pkg < logical_packages; log_pkg++)
+		if (logical_to_physical_pkg_map[log_pkg] == phys_pkg)
+			return log_pkg;
+
+	return -1;
+}
+EXPORT_SYMBOL(topology_phys_to_logical_pkg);
+
 /**
  * topology_update_package_map - Update the physical to logical package map
  * @pkg:	The physical package id as retrieved via CPUID
@@ -285,17 +300,11 @@ static void notrace start_secondary(void *unused)
  */
 int topology_update_package_map(unsigned int pkg, unsigned int cpu)
 {
-	unsigned int new;
-
-	/* Called from early boot ? */
-	if (!physical_package_map)
-		return 0;
-
-	if (pkg >= max_physical_pkg_id)
-		return -EINVAL;
+	int new;
+	u16 *ltp_pkg_map_new;
 
-	/* Set the logical package id */
-	if (test_and_set_bit(pkg, physical_package_map))
+	new = topology_phys_to_logical_pkg(pkg);
+	if (new >= 0)
 		goto found;
 
 	if (logical_packages >= __max_logical_packages) {
@@ -305,34 +314,30 @@ int topology_update_package_map(unsigned int pkg, unsigned int cpu)
 	}
 
 	new = logical_packages++;
-	if (new != pkg) {
-		pr_info("CPU %u Converting physical %u to logical package %u\n",
-			cpu, pkg, new);
+
+	/* Allocate and copy a new array */
+	ltp_pkg_map_new = kmalloc(logical_packages * sizeof(u16), GFP_KERNEL);
+	BUG_ON(!ltp_pkg_map_new);
+	if (logical_to_physical_pkg_map) {
+		memcpy(ltp_pkg_map_new, logical_to_physical_pkg_map,
+		       logical_packages * sizeof(u16));
+		kfree(logical_to_physical_pkg_map);
 	}
-	physical_to_logical_pkg[pkg] = new;
+	logical_to_physical_pkg_map = ltp_pkg_map_new;
+	logical_to_physical_pkg_map[new] = pkg;
 
+	if (pkg != new)
+		pr_info("CPU %u Converting physical %u to logical package %u\n",
+			cpu, pkg, new);
 found:
-	cpu_data(cpu).logical_proc_id = physical_to_logical_pkg[pkg];
+	cpu_data(cpu).phys_pkg_id = pkg;
+	cpu_data(cpu).logical_proc_id = new;
 	return 0;
 }
 
-/**
- * topology_phys_to_logical_pkg - Map a physical package id to a logical
- *
- * Returns logical package id or -1 if not found
- */
-int topology_phys_to_logical_pkg(unsigned int phys_pkg)
-{
-	if (phys_pkg >= max_physical_pkg_id)
-		return -1;
-	return physical_to_logical_pkg[phys_pkg];
-}
-EXPORT_SYMBOL(topology_phys_to_logical_pkg);
-
 static void __init smp_init_package_map(struct cpuinfo_x86 *c, unsigned int cpu)
 {
 	unsigned int ncpus;
-	size_t size;
 
 	/*
 	 * Today neither Intel nor AMD support heterogenous systems. That
@@ -363,21 +368,10 @@ static void __init smp_init_package_map(struct cpuinfo_x86 *c, unsigned int cpu)
 	}
 
 	__max_logical_packages = DIV_ROUND_UP(total_cpus, ncpus);
-	logical_packages = 0;
-
-	/*
-	 * Possibly larger than what we need as the number of apic ids per
-	 * package can be smaller than the actual used apic ids.
-	 */
-	max_physical_pkg_id = DIV_ROUND_UP(MAX_LOCAL_APIC, ncpus);
-	size = max_physical_pkg_id * sizeof(unsigned int);
-	physical_to_logical_pkg = kmalloc(size, GFP_KERNEL);
-	memset(physical_to_logical_pkg, 0xff, size);
-	size = BITS_TO_LONGS(max_physical_pkg_id) * sizeof(unsigned long);
-	physical_package_map = kzalloc(size, GFP_KERNEL);
-
 	pr_info("Max logical packages: %u\n", __max_logical_packages);
 
+	logical_packages = 0;
+
 	topology_update_package_map(c->phys_proc_id, cpu);
 }
 
-- 
2.15.0.rc0.39.g2f0e14e64

  parent reply	other threads:[~2017-10-25 12:09 UTC|newest]

Thread overview: 7+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2017-10-25 12:09 [PATCH 0/3 v4] Fix panic in logical packages calculation Prarit Bhargava
2017-10-25 12:09 ` [PATCH 1/3 v4] perf/x86/intel/uncore: Cache logical pkg id in uncore driver Prarit Bhargava
2017-11-01 16:30   ` Thomas Gleixner
2017-10-25 12:09 ` Prarit Bhargava [this message]
2017-11-01 16:56   ` [PATCH 2/3 v4] x86/topology: Avoid wasting 128k for package id array Thomas Gleixner
2017-11-03 14:53     ` Prarit Bhargava
2017-10-25 12:09 ` [PATCH 3/3 v4] x86/smpboot: Fix __max_logical_packages estimate Prarit Bhargava

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=20171025120940.15721-3-prarit@redhat.com \
    --to=prarit@redhat.com \
    --cc=ak@linux.intel.com \
    --cc=arvind.yadav.cs@gmail.com \
    --cc=borntraeger@de.ibm.com \
    --cc=bp@suse.de \
    --cc=dave.hansen@intel.com \
    --cc=eranian@google.com \
    --cc=hpa@zytor.com \
    --cc=kan.liang@intel.com \
    --cc=kirill.shutemov@linux.intel.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=luto@kernel.org \
    --cc=mingo@redhat.com \
    --cc=minipli@googlemail.com \
    --cc=peterz@infradead.org \
    --cc=piotr.luc@intel.com \
    --cc=tglx@linutronix.de \
    --cc=thomas.lendacky@amd.com \
    --cc=tim.c.chen@linux.intel.com \
    --cc=vkuznets@redhat.com \
    --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 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).