linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Len Brown <lenb@kernel.org>
To: x86@kernel.org
Cc: linux-kernel@vger.kernel.org, Len Brown <len.brown@intel.com>,
	linux-doc@vger.kernel.org
Subject: [PATCH 04/14] x86 topology: Add CPUID.1F multi-die/package support
Date: Tue, 26 Feb 2019 01:20:02 -0500	[thread overview]
Message-ID: <204e9bf2afff8e6cb7a8a39d86038075f1bb4ab8.1551160674.git.len.brown@intel.com> (raw)
In-Reply-To: <e2810a5317d3a109a98204e883fd1461f77b9339.1551160674.git.len.brown@intel.com>

From: Len Brown <len.brown@intel.com>

Some new systems have multiple software-visible die within each package.

Update Linux parsing of the Intel CPUID "Extended Topology Leaf"
to handle either CPUID.B, or the new CPUID.1F.

Add cpuinfo_x86.die_id and cpuinfo_x86.max_dies to store the result.

die_id will be non-zero only for multi-die/package systems.

Signed-off-by: Len Brown <len.brown@intel.com>
Cc: linux-doc@vger.kernel.org
---
 Documentation/x86/topology.txt   |  4 ++
 arch/x86/include/asm/processor.h |  4 +-
 arch/x86/kernel/cpu/topology.c   | 85 +++++++++++++++++++++++++-------
 arch/x86/kernel/smpboot.c        |  2 +
 4 files changed, 75 insertions(+), 20 deletions(-)

diff --git a/Documentation/x86/topology.txt b/Documentation/x86/topology.txt
index 06b3cdbc4048..8107b6cfc9ea 100644
--- a/Documentation/x86/topology.txt
+++ b/Documentation/x86/topology.txt
@@ -46,6 +46,10 @@ The topology of a system is described in the units of:
 
     The number of cores in a package. This information is retrieved via CPUID.
 
+  - cpuinfo_x86.x86_max_dies:
+
+    The number of dies in a package. This information is retrieved via CPUID.
+
   - cpuinfo_x86.phys_proc_id:
 
     The physical ID of the package. This information is retrieved via CPUID
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 33051436c864..f2856fe03715 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -105,7 +105,8 @@ struct cpuinfo_x86 {
 	int			x86_power;
 	unsigned long		loops_per_jiffy;
 	/* cpuid returned max cores value: */
-	u16			 x86_max_cores;
+	u16			x86_max_cores;
+	u16			x86_max_dies;
 	u16			apicid;
 	u16			initial_apicid;
 	u16			x86_clflush_size;
@@ -117,6 +118,7 @@ struct cpuinfo_x86 {
 	u16			logical_proc_id;
 	/* Core id: */
 	u16			cpu_core_id;
+	u16			cpu_die_id;
 	/* Index into per_cpu list: */
 	u16			cpu_index;
 	u32			microcode;
diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c
index 8f6c784141d1..4d17e699657d 100644
--- a/arch/x86/kernel/cpu/topology.c
+++ b/arch/x86/kernel/cpu/topology.c
@@ -15,33 +15,63 @@
 /* leaf 0xb SMT level */
 #define SMT_LEVEL	0
 
-/* leaf 0xb sub-leaf types */
+/* extended topology sub-leaf types */
 #define INVALID_TYPE	0
 #define SMT_TYPE	1
 #define CORE_TYPE	2
+#define DIE_TYPE	5
 
 #define LEAFB_SUBTYPE(ecx)		(((ecx) >> 8) & 0xff)
 #define BITS_SHIFT_NEXT_LEVEL(eax)	((eax) & 0x1f)
 #define LEVEL_MAX_SIBLINGS(ebx)		((ebx) & 0xffff)
 
-int detect_extended_topology_early(struct cpuinfo_x86 *c)
-{
 #ifdef CONFIG_SMP
+/*
+ * Check if given CPUID extended toplogy "leaf" is implemented
+ */
+static int check_extended_topology_leaf(int leaf)
+{
 	unsigned int eax, ebx, ecx, edx;
 
-	if (c->cpuid_level < 0xb)
+	cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+
+	if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE))
 		return -1;
 
-	cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+	return 0;
+}
+/*
+ * Return best CPUID Extended Toplogy Leaf supported
+ */
+static int detect_extended_topology_leaf(struct cpuinfo_x86 *c)
+{
+	if (c->cpuid_level >= 0x1f) {
+		if (check_extended_topology_leaf(0x1f) == 0)
+			return 0x1f;
+	}
 
-	/*
-	 * check if the cpuid leaf 0xb is actually implemented.
-	 */
-	if (ebx == 0 || (LEAFB_SUBTYPE(ecx) != SMT_TYPE))
+	if (c->cpuid_level >= 0xb) {
+		if (check_extended_topology_leaf(0xb) == 0)
+			return 0xb;
+	}
+
+	return -1;
+}
+#endif
+
+int detect_extended_topology_early(struct cpuinfo_x86 *c)
+{
+#ifdef CONFIG_SMP
+	unsigned int eax, ebx, ecx, edx;
+	int leaf;
+
+	leaf = detect_extended_topology_leaf(c);
+	if (leaf < 0)
 		return -1;
 
 	set_cpu_cap(c, X86_FEATURE_XTOPOLOGY);
 
+	cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
 	/*
 	 * initial apic id, which also represents 32-bit extended x2apic id.
 	 */
@@ -52,7 +82,7 @@ int detect_extended_topology_early(struct cpuinfo_x86 *c)
 }
 
 /*
- * Check for extended topology enumeration cpuid leaf 0xb and if it
+ * Check for extended topology enumeration cpuid leaf, and if it
  * exists, use it for populating initial_apicid and cpu topology
  * detection.
  */
@@ -60,22 +90,28 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 {
 #ifdef CONFIG_SMP
 	unsigned int eax, ebx, ecx, edx, sub_index;
-	unsigned int ht_mask_width, core_plus_mask_width;
+	unsigned int ht_mask_width, core_plus_mask_width, die_plus_mask_width;
 	unsigned int core_select_mask, core_level_siblings;
+	unsigned int die_select_mask, die_level_siblings;
+	int leaf;
 
-	if (detect_extended_topology_early(c) < 0)
+	leaf = detect_extended_topology_leaf(c);
+	if (leaf < 0)
 		return -1;
 
 	/*
 	 * Populate HT related information from sub-leaf level 0.
 	 */
-	cpuid_count(0xb, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+	cpuid_count(leaf, SMT_LEVEL, &eax, &ebx, &ecx, &edx);
+	c->initial_apicid = edx;
 	core_level_siblings = smp_num_siblings = LEVEL_MAX_SIBLINGS(ebx);
 	core_plus_mask_width = ht_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
+	die_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
+	die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
 
 	sub_index = 1;
 	do {
-		cpuid_count(0xb, sub_index, &eax, &ebx, &ecx, &edx);
+		cpuid_count(leaf, sub_index, &eax, &ebx, &ecx, &edx);
 
 		/*
 		 * Check for the Core type in the implemented sub leaves.
@@ -83,23 +119,34 @@ int detect_extended_topology(struct cpuinfo_x86 *c)
 		if (LEAFB_SUBTYPE(ecx) == CORE_TYPE) {
 			core_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
 			core_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
-			break;
+			die_level_siblings = core_level_siblings;
+			die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
+		}
+		if (LEAFB_SUBTYPE(ecx) == DIE_TYPE) {
+			die_level_siblings = LEVEL_MAX_SIBLINGS(ebx);
+			die_plus_mask_width = BITS_SHIFT_NEXT_LEVEL(eax);
 		}
 
 		sub_index++;
 	} while (LEAFB_SUBTYPE(ecx) != INVALID_TYPE);
 
 	core_select_mask = (~(-1 << core_plus_mask_width)) >> ht_mask_width;
-
-	c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid, ht_mask_width)
-						 & core_select_mask;
-	c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid, core_plus_mask_width);
+	die_select_mask = (~(-1 << die_plus_mask_width)) >>
+				core_plus_mask_width;
+
+	c->cpu_core_id = apic->phys_pkg_id(c->initial_apicid,
+				ht_mask_width) & core_select_mask;
+	c->cpu_die_id = apic->phys_pkg_id(c->initial_apicid,
+				core_plus_mask_width) & die_select_mask;
+	c->phys_proc_id = apic->phys_pkg_id(c->initial_apicid,
+				die_plus_mask_width);
 	/*
 	 * Reinit the apicid, now that we have extended initial_apicid.
 	 */
 	c->apicid = apic->phys_pkg_id(c->initial_apicid, 0);
 
 	c->x86_max_cores = (core_level_siblings / smp_num_siblings);
+	c->x86_max_dies = (die_level_siblings / core_level_siblings);
 #endif
 	return 0;
 }
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index 19a963890bbe..c70e547b18c2 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -393,6 +393,7 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 		int cpu1 = c->cpu_index, cpu2 = o->cpu_index;
 
 		if (c->phys_proc_id == o->phys_proc_id &&
+		    c->cpu_die_id == o->cpu_die_id &&
 		    per_cpu(cpu_llc_id, cpu1) == per_cpu(cpu_llc_id, cpu2)) {
 			if (c->cpu_core_id == o->cpu_core_id)
 				return topology_sane(c, o, "smt");
@@ -404,6 +405,7 @@ static bool match_smt(struct cpuinfo_x86 *c, struct cpuinfo_x86 *o)
 		}
 
 	} else if (c->phys_proc_id == o->phys_proc_id &&
+		   c->cpu_die_id == o->cpu_die_id &&
 		   c->cpu_core_id == o->cpu_core_id) {
 		return topology_sane(c, o, "smt");
 	}
-- 
2.18.0-rc0


  parent reply	other threads:[~2019-02-26  6:20 UTC|newest]

Thread overview: 40+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-02-26  6:19 [PATCH 0/14] v2 multi-die/package topology support Len Brown
2019-02-26  6:19 ` [PATCH 01/14] x86 topology: Fix doc typo Len Brown
2019-02-26  6:20   ` [PATCH 02/14] topolgy: Simplify cputopology.txt formatting and wording Len Brown
2019-02-26  6:20   ` [PATCH 03/14] x86 smpboot: Rename match_die() to match_pkg() Len Brown
2019-02-26  6:20   ` Len Brown [this message]
2019-02-26 19:46     ` [PATCH 04/14] x86 topology: Add CPUID.1F multi-die/package support Dave Hansen
2019-02-28 15:43       ` Len Brown
2019-04-05 18:16         ` Thomas Gleixner
2019-02-26  6:20   ` [PATCH 05/14] cpu topology: Export die_id Len Brown
2019-03-07 14:45     ` Morten Rasmussen
2019-03-26 18:18       ` Len Brown
2019-02-26  6:20   ` [PATCH 06/14] x86 topology: Define topology_logical_die_id() Len Brown
2019-02-26  6:20   ` [PATCH 07/14] powercap/intel_rapl: Simplify rapl_find_package() Len Brown
2019-02-26 19:06     ` Peter Zijlstra
2019-03-26 18:27       ` Len Brown
2019-02-26  6:20   ` [PATCH 08/14] powercap/intel_rapl: Support multi-die/package Len Brown
2019-04-05 18:27     ` Thomas Gleixner
2019-04-08  1:35       ` Zhang Rui
2019-02-26  6:20   ` [PATCH 09/14] thermal/x86_pkg_temp_thermal: " Len Brown
2019-04-05 18:29     ` Thomas Gleixner
2019-04-05 18:39       ` Brown, Len
2019-04-05 18:50         ` Thomas Gleixner
2019-02-26  6:20   ` [PATCH 10/14] powercap/intel_rapl: update rapl domain name and debug messages Len Brown
2019-02-26  6:20   ` [PATCH 11/14] hwmon/coretemp: Support multi-die/package Len Brown
2019-02-26  6:20   ` [PATCH 12/14] topology: Create package_threads sysfs attribute Len Brown
2019-02-26  6:20   ` [PATCH 13/14] topology: Create core_threads " Len Brown
2019-02-26  6:20   ` [PATCH 14/14] topology: Create die_threads " Len Brown
2019-02-26 18:51 ` [PATCH 0/14] v2 multi-die/package topology support Peter Zijlstra
2019-04-12 19:32   ` Len Brown
2019-02-26 18:53 ` Peter Zijlstra
2019-03-07 14:59   ` Morten Rasmussen
2019-04-05 18:33     ` Thomas Gleixner
2019-04-12 19:52       ` Len Brown
2019-04-12 20:40         ` Brice Goglin
2019-02-26 19:05 ` Peter Zijlstra
2019-04-30  6:50   ` Len Brown
2019-04-30  9:33     ` Borislav Petkov
2019-04-30 18:46       ` Len Brown
2019-04-05 18:33 ` Thomas Gleixner
2019-04-30 20:55 [PATCH 01/14] x86 topology: Fix doc typo Len Brown
2019-04-30 20:55 ` [PATCH 04/14] x86 topology: Add CPUID.1F multi-die/package support Len Brown

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=204e9bf2afff8e6cb7a8a39d86038075f1bb4ab8.1551160674.git.len.brown@intel.com \
    --to=lenb@kernel.org \
    --cc=len.brown@intel.com \
    --cc=linux-doc@vger.kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --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).