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: <1506430406-26121-3-git-send-email-prarit@redhat.com>
Date:   Tue, 26 Sep 2017 08:53:25 -0400
From:   Prarit Bhargava <prarit@...hat.com>
To:     linux-kernel@...r.kernel.org
Cc:     Andi Kleen <ak@...ux.intel.com>,
        Thomas Gleixner <tglx@...utronix.de>,
        Ingo Molnar <mingo@...hat.com>,
        "H. Peter Anvin" <hpa@...or.com>, x86@...nel.org,
        Peter Zijlstra <peterz@...radead.org>,
        Dave Hansen <dave.hansen@...el.com>,
        Piotr Luc <piotr.luc@...el.com>,
        Kan Liang <kan.liang@...el.com>, Borislav Petkov <bp@...e.de>,
        Stephane Eranian <eranian@...gle.com>,
        Prarit Bhargava <prarit@...hat.com>,
        Arvind Yadav <arvind.yadav.cs@...il.com>,
        Andy Lutomirski <luto@...nel.org>,
        Christian Borntraeger <borntraeger@...ibm.com>,
        "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>,
        Tom Lendacky <thomas.lendacky@....com>,
        He Chen <he.chen@...ux.intel.com>,
        Mathias Krause <minipli@...glemail.com>,
        Tim Chen <tim.c.chen@...ux.intel.com>,
        Vitaly Kuznetsov <vkuznets@...hat.com>
Subject: [PATCH 2/3 v2 RESEND] x86/topology: Avoid wasting 128k for package id array

From: Andi Kleen <ak@...ux.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 for
MAX_LOCAL_APIC and that is always 32k on 64bit systems,
and it needs 4 bytes for each entry.

This is fairly wasteful, especially for the common case
of having only one socket, where we need 128K just to store
a single 4 byte value.

The max logical APIC value is not known at this point,
so it's hard to size it correctly.

The previous patch converted the only performance critical
user to cache the value, and all others are fairly
slow path, so we can just convert the O(1) array
lookup to a linear search in cpu_data()

This can also avoid the need for an extra bitmap structure
to know if the logical package ID is already allocated.
We can also save this information in cpu_data and look it
up during the search.

This patch removes the explicit arrays and replaces
the lookups with explicit searches.

Overall the new code is somewhat simpler, and needs a lot
less run time memory.

The naming of the variables in cpu_data is still not
great (_proc sometimes means package and sometimes means
logical processor), but I followed the existing (messy)
conventions when possible. At some point would be probably good
to clean this up too.

Tested on a 2S system, but it would be good
to test on more obscure systems which may have problems
with package IDs. I'm copying Prarit who had problematic systems
before.

[v2]: Decrease logical_packages when the last thread in a socket is
removed.

Signed-off-by: Andi Kleen <ak@...ux.intel.com>
Cc: Thomas Gleixner <tglx@...utronix.de>
Cc: Ingo Molnar <mingo@...hat.com>
Cc: "H. Peter Anvin" <hpa@...or.com>
Cc: x86@...nel.org
Cc: Peter Zijlstra <peterz@...radead.org>
Cc: Andi Kleen <ak@...ux.intel.com>
Cc: Dave Hansen <dave.hansen@...el.com>
Cc: Piotr Luc <piotr.luc@...el.com>
Cc: Kan Liang <kan.liang@...el.com>
Cc: Borislav Petkov <bp@...e.de>
Cc: Stephane Eranian <eranian@...gle.com>
Cc: Prarit Bhargava <prarit@...hat.com>
Cc: Arvind Yadav <arvind.yadav.cs@...il.com>
Cc: Andy Lutomirski <luto@...nel.org>
Cc: Christian Borntraeger <borntraeger@...ibm.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@...ux.intel.com>
Cc: Tom Lendacky <thomas.lendacky@....com>
Cc: He Chen <he.chen@...ux.intel.com>
Cc: Mathias Krause <minipli@...glemail.com>
Cc: Tim Chen <tim.c.chen@...ux.intel.com>
Cc: Vitaly Kuznetsov <vkuznets@...hat.com>
---
 arch/x86/include/asm/processor.h |  6 +++-
 arch/x86/kernel/smpboot.c        | 62 +++++++++++++++++-----------------------
 2 files changed, 32 insertions(+), 36 deletions(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 3fa26a61eabc..d369d2a82d8f 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -124,13 +124,17 @@ 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: */
 	u16			cpu_index;
 	u32			microcode;
+	/* Flags */
+	unsigned		logical_proc_set : 1;
 } __randomize_layout;
 
 struct cpuid_regs {
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 0854ff169274..e40edcddd0ff 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -100,9 +100,6 @@
 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;
 unsigned int __max_logical_packages __read_mostly;
 EXPORT_SYMBOL(__max_logical_packages);
 static unsigned int logical_packages __read_mostly;
@@ -284,17 +281,11 @@ static void notrace start_secondary(void *unused)
  */
 int topology_update_package_map(unsigned int pkg, unsigned int cpu)
 {
-	unsigned int new;
+	int new;
 
-	/* Called from early boot ? */
-	if (!physical_package_map)
-		return 0;
-
-	if (pkg >= max_physical_pkg_id)
-		return -EINVAL;
-
-	/* Set the logical package id */
-	if (test_and_set_bit(pkg, physical_package_map))
+	/* Already available somewhere? */
+	new = topology_phys_to_logical_pkg(pkg);
+	if (new >= 0)
 		goto found;
 
 	if (logical_packages >= __max_logical_packages) {
@@ -304,14 +295,14 @@ int topology_update_package_map(unsigned int pkg, unsigned int cpu)
 	}
 
 	new = logical_packages++;
-	if (new != pkg) {
+	if (new != pkg)
 		pr_info("CPU %u Converting physical %u to logical package %u\n",
 			cpu, pkg, new);
-	}
-	physical_to_logical_pkg[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;
+	cpu_data(cpu).logical_proc_set = 1;
 	return 0;
 }
 
@@ -322,16 +313,21 @@ int topology_update_package_map(unsigned int pkg, unsigned int cpu)
  */
 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];
+	int cpu;
+
+	for_each_possible_cpu(cpu) {
+		if (cpu_data(cpu).phys_pkg_id == phys_pkg &&
+		    cpu_data(cpu).logical_proc_set) {
+			return cpu_data(cpu).logical_proc_id;
+		}
+	}
+	return -1;
 }
 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
@@ -362,21 +358,10 @@ 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);
 }
 
@@ -1507,7 +1492,7 @@ static void recompute_smt_state(void)
 
 static void remove_siblinginfo(int cpu)
 {
-	int sibling;
+	int phys_pkg_id, sibling;
 	struct cpuinfo_x86 *c = &cpu_data(cpu);
 
 	for_each_cpu(sibling, topology_core_cpumask(cpu)) {
@@ -1528,6 +1513,13 @@ static void remove_siblinginfo(int cpu)
 	cpumask_clear(topology_core_cpumask(cpu));
 	c->phys_proc_id = 0;
 	c->cpu_core_id = 0;
+
+	/* last core in socket going down? */
+	phys_pkg_id = c->phys_pkg_id;
+	c->phys_pkg_id = U16_MAX;
+	if (topology_phys_to_logical_pkg(phys_pkg_id) < 0)
+		logical_packages--;
+
 	cpumask_clear_cpu(cpu, cpu_sibling_setup_mask);
 	recompute_smt_state();
 }
-- 
1.8.5.5

Powered by blists - more mailing lists

Powered by Openwall GNU/*/Linux Powered by OpenVZ