public inbox for linux-kernel@vger.kernel.org
 help / color / mirror / Atom feed
From: Thomas Gleixner <tglx@linutronix.de>
To: LKML <linux-kernel@vger.kernel.org>
Cc: x86@kernel.org, Tom Lendacky <thomas.lendacky@amd.com>,
	Andrew Cooper <andrew.cooper3@citrix.com>,
	Arjan van de Ven <arjan@linux.intel.com>,
	Huang Rui <ray.huang@amd.com>, Juergen Gross <jgross@suse.com>,
	Dimitri Sivanich <dimitri.sivanich@hpe.com>,
	Michael Kelley <mikelley@microsoft.com>,
	Wei Liu <wei.liu@kernel.org>, Pu Wen <puwen@hygon.cn>,
	Qiuxu Zhuo <qiuxu.zhuo@intel.com>,
	Sohil Mehta <sohil.mehta@intel.com>
Subject: [patch V4 25/41] x86/cpu: Add legacy topology parser
Date: Mon, 14 Aug 2023 10:54:13 +0200 (CEST)	[thread overview]
Message-ID: <20230814085113.530288551@linutronix.de> (raw)
In-Reply-To: 20230814085006.593997112@linutronix.de

The legacy topology detection via CPUID leaf 4, which provides the number
of cores in the package and CPUID leaf 1 which provides the number of
logical CPUs in case that FEATURE_HT is enabled and the CMP_LEGACY feature
is not set, is shared for Intel, Centaur amd Zhaoxin CPUs.

Lift the code from common.c without the early detection hack and provide it
as common fallback mechanism.

Will be utilized in later changes.

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Juergen Gross <jgross@suse.com>
Tested-by: Sohil Mehta <sohil.mehta@intel.com>
Tested-by: Michael Kelley <mikelley@microsoft.com>

---
V4: Cure the off by one in fake_topology()

V3: Provide legacy data in leaf 0xb/0x1f format as expected by the rest of
    the code - Borislav
---
 arch/x86/kernel/cpu/common.c          |    3 ++
 arch/x86/kernel/cpu/topology.h        |    3 ++
 arch/x86/kernel/cpu/topology_common.c |   46 +++++++++++++++++++++++++++++++++-
 3 files changed, 51 insertions(+), 1 deletion(-)

--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -883,6 +883,9 @@ void detect_ht(struct cpuinfo_x86 *c)
 #ifdef CONFIG_SMP
 	int index_msb, core_bits;
 
+	if (topo_is_converted(c))
+		return;
+
 	if (detect_ht_early(c) < 0)
 		return;
 
--- a/arch/x86/kernel/cpu/topology.h
+++ b/arch/x86/kernel/cpu/topology.h
@@ -6,6 +6,9 @@ struct topo_scan {
 	struct cpuinfo_x86	*c;
 	unsigned int		dom_shifts[TOPO_MAX_DOMAIN];
 	unsigned int		dom_ncpus[TOPO_MAX_DOMAIN];
+
+	// Legacy CPUID[1]:EBX[23:16] number of logical processors
+	unsigned int		ebx1_nproc_shift;
 };
 
 bool topo_is_converted(struct cpuinfo_x86 *c);
--- a/arch/x86/kernel/cpu/topology_common.c
+++ b/arch/x86/kernel/cpu/topology_common.c
@@ -24,6 +24,48 @@ void topology_set_dom(struct topo_scan *
 	}
 }
 
+static unsigned int parse_num_cores(struct cpuinfo_x86 *c)
+{
+	struct {
+		u32	cache_type	:  5,
+			unused		: 21,
+			ncores		:  6;
+	} eax;
+
+	if (c->cpuid_level < 4)
+		return 1;
+
+	cpuid_subleaf_reg(4, 0, CPUID_EAX, &eax);
+	if (!eax.cache_type)
+		return 1;
+
+	return eax.ncores + 1;
+}
+
+static void __maybe_unused parse_legacy(struct topo_scan *tscan)
+{
+	unsigned int cores, core_shift, smt_shift = 0;
+	struct cpuinfo_x86 *c = tscan->c;
+
+	cores = parse_num_cores(c);
+	core_shift = get_count_order(cores);
+
+	if (cpu_has(c, X86_FEATURE_HT)) {
+		if (!WARN_ON_ONCE(tscan->ebx1_nproc_shift < core_shift))
+			smt_shift = tscan->ebx1_nproc_shift - core_shift;
+		/*
+		 * The parser expects leaf 0xb/0x1f format, which means
+		 * the number of logical processors at core level is
+		 * counting threads.
+		 */
+		core_shift += smt_shift;
+		cores <<= smt_shift;
+	}
+
+	topology_set_dom(tscan, TOPO_SMT_DOMAIN, smt_shift, 1U << smt_shift);
+	topology_set_dom(tscan, TOPO_CORE_DOMAIN, core_shift, cores);
+}
+
 bool topo_is_converted(struct cpuinfo_x86 *c)
 {
 	/* Temporary until everything is converted over. */
@@ -47,7 +89,7 @@ static bool fake_topology(struct topo_sc
 	 * which has useless CPUID information.
 	 */
 	topology_set_dom(tscan, TOPO_SMT_DOMAIN, 0, 1);
-	topology_set_dom(tscan, TOPO_CORE_DOMAIN, 1, 1);
+	topology_set_dom(tscan, TOPO_CORE_DOMAIN, 0, 1);
 
 	return tscan->c->cpuid_level < 1 || xen_pv_domain();
 }
@@ -88,6 +130,8 @@ static void parse_topology(struct topo_s
 	/* The above is sufficient for UP */
 	if (!IS_ENABLED(CONFIG_SMP))
 		return;
+
+	tscan->ebx1_nproc_shift = get_count_order(ebx.nproc);
 }
 
 static void topo_set_ids(struct topo_scan *tscan)




  parent reply	other threads:[~2023-08-14  8:56 UTC|newest]

Thread overview: 85+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2023-08-14  8:53 [patch V4 00/41] x86/cpu: Rework the topology evaluation Thomas Gleixner
2023-08-14  8:53 ` [patch V4 01/41] x86/cpu/hygon: Fix the CPU topology evaluation for real Thomas Gleixner
2023-08-14  8:53 ` [patch V4 02/41] cpu/SMT: Make SMT control more robust against enumeration failures Thomas Gleixner
2023-08-15 21:15   ` Dave Hansen
2023-10-10 12:18     ` Thomas Gleixner
2023-10-13  9:38   ` [tip: x86/core] " tip-bot2 for Thomas Gleixner
2023-08-14  8:53 ` [patch V4 03/41] x86/apic: Fake primary thread mask for XEN/PV Thomas Gleixner
2023-10-13  9:38   ` [tip: x86/core] " tip-bot2 for Thomas Gleixner
2023-08-14  8:53 ` [patch V4 04/41] x86/cpu: Encapsulate topology information in cpuinfo_x86 Thomas Gleixner
2023-10-13  9:38   ` [tip: x86/core] " tip-bot2 for Thomas Gleixner
2023-08-14  8:53 ` [patch V4 05/41] x86/cpu: Move phys_proc_id into topology info Thomas Gleixner
2023-10-13  9:38   ` [tip: x86/core] " tip-bot2 for Thomas Gleixner
2023-08-14  8:53 ` [patch V4 06/41] x86/cpu: Move cpu_die_id " Thomas Gleixner
2023-10-13  9:38   ` [tip: x86/core] " tip-bot2 for Thomas Gleixner
2023-08-14  8:53 ` [patch V4 07/41] scsi: lpfc: Use topology_core_id() Thomas Gleixner
2023-10-13  9:38   ` [tip: x86/core] " tip-bot2 for Thomas Gleixner
2023-08-14  8:53 ` [patch V4 08/41] hwmon: (fam15h_power) " Thomas Gleixner
2023-10-13  9:38   ` [tip: x86/core] " tip-bot2 for Thomas Gleixner
2023-08-14  8:53 ` [patch V4 09/41] x86/cpu: Move cpu_core_id into topology info Thomas Gleixner
2023-10-13  9:38   ` [tip: x86/core] " tip-bot2 for Thomas Gleixner
2023-08-14  8:53 ` [patch V4 10/41] x86/cpu: Move cu_id " Thomas Gleixner
2023-10-13  9:38   ` [tip: x86/core] " tip-bot2 for Thomas Gleixner
2023-08-14  8:53 ` [patch V4 11/41] x86/cpu: Remove pointless evaluation of x86_coreid_bits Thomas Gleixner
2023-10-13  9:38   ` [tip: x86/core] " tip-bot2 for Thomas Gleixner
2023-08-14  8:53 ` [patch V4 12/41] x86/cpu: Move logical package and die IDs into topology info Thomas Gleixner
2023-10-13  9:38   ` [tip: x86/core] " tip-bot2 for Thomas Gleixner
2023-08-14  8:53 ` [patch V4 13/41] x86/cpu: Move cpu_l[l2]c_id " Thomas Gleixner
2023-10-13  9:38   ` [tip: x86/core] " tip-bot2 for Thomas Gleixner
2023-08-14  8:53 ` [patch V4 14/41] x86/apic: Use BAD_APICID consistently Thomas Gleixner
2023-10-13  9:38   ` [tip: x86/core] " tip-bot2 for Thomas Gleixner
2023-08-14  8:53 ` [patch V4 15/41] x86/apic: Use u32 for APIC IDs in global data Thomas Gleixner
2023-10-13  9:38   ` [tip: x86/core] " tip-bot2 for Thomas Gleixner
2023-08-14  8:53 ` [patch V4 16/41] x86/apic: Use u32 for check_apicid_used() Thomas Gleixner
2023-10-13  9:38   ` [tip: x86/core] " tip-bot2 for Thomas Gleixner
2023-08-14  8:54 ` [patch V4 17/41] x86/apic: Use u32 for cpu_present_to_apicid() Thomas Gleixner
2023-10-13  9:38   ` [tip: x86/core] " tip-bot2 for Thomas Gleixner
2023-08-14  8:54 ` [patch V4 18/41] x86/apic: Use u32 for phys_pkg_id() Thomas Gleixner
2023-10-13  9:38   ` [tip: x86/core] " tip-bot2 for Thomas Gleixner
2023-08-14  8:54 ` [patch V4 19/41] x86/apic: Use u32 for [gs]et_apic_id() Thomas Gleixner
2023-10-13  9:38   ` [tip: x86/core] " tip-bot2 for Thomas Gleixner
2023-08-14  8:54 ` [patch V4 20/41] x86/apic: Use u32 for wakeup_secondary_cpu[_64]() Thomas Gleixner
2023-10-13  9:38   ` [tip: x86/core] " tip-bot2 for Thomas Gleixner
2023-10-13 10:32   ` [tip: x86/core] x86/apic, x86/hyperv: Use u32 in hv_snp_boot_ap() too tip-bot2 for Ingo Molnar
2023-08-14  8:54 ` [patch V4 21/41] x86/cpu/topology: Cure the abuse of cpuinfo for persisting logical ids Thomas Gleixner
2023-10-13  9:38   ` [tip: x86/core] " tip-bot2 for Thomas Gleixner
2023-08-14  8:54 ` [patch V4 22/41] x86/cpu: Provide debug interface Thomas Gleixner
2023-10-13  9:38   ` [tip: x86/core] " tip-bot2 for Thomas Gleixner
2023-08-14  8:54 ` [patch V4 23/41] x86/cpu: Provide cpuid_read() et al Thomas Gleixner
2023-08-14  8:54 ` [patch V4 24/41] x86/cpu: Provide cpu_init/parse_topology() Thomas Gleixner
2023-08-28  6:07   ` K Prateek Nayak
2023-08-28 10:05     ` Thomas Gleixner
2023-08-28 14:03       ` Arjan van de Ven
2023-08-28 14:28       ` K Prateek Nayak
2023-08-28 14:34         ` Arjan van de Ven
2023-08-29  3:16           ` K Prateek Nayak
2023-09-15 11:54             ` Peter Zijlstra
2023-09-15 14:04               ` Arjan van de Ven
2023-09-19  3:54                 ` K Prateek Nayak
2023-09-19  8:13                   ` Thomas Gleixner
2023-09-20  3:23                     ` K Prateek Nayak
2023-09-19 13:44                   ` Arjan van de Ven
2023-09-20  3:21                     ` K Prateek Nayak
2023-09-14  9:20         ` K Prateek Nayak
2023-09-15 11:46           ` Thomas Gleixner
2023-08-14  8:54 ` Thomas Gleixner [this message]
2023-08-14  8:54 ` [patch V4 26/41] x86/cpu: Use common topology code for Centaur and Zhaoxin Thomas Gleixner
2023-08-14  8:54 ` [patch V4 27/41] x86/cpu: Move __max_die_per_package to common.c Thomas Gleixner
2023-08-14  8:54 ` [patch V4 28/41] x86/cpu: Provide a sane leaf 0xb/0x1f parser Thomas Gleixner
2023-08-16 12:09   ` Zhang, Rui
2023-08-17  9:11     ` Thomas Gleixner
2023-08-14  8:54 ` [patch V4 29/41] x86/cpu: Use common topology code for Intel Thomas Gleixner
2023-08-14  8:54 ` [patch V4 30/41] x86/cpu/amd: Provide a separate accessor for Node ID Thomas Gleixner
2023-08-14  8:54 ` [patch V4 31/41] x86/cpu: Provide an AMD/HYGON specific topology parser Thomas Gleixner
2023-08-14  8:54 ` [patch V4 32/41] x86/smpboot: Teach it about topo.amd_node_id Thomas Gleixner
2023-08-14  8:54 ` [patch V4 33/41] x86/cpu: Use common topology code for AMD Thomas Gleixner
2023-08-14  8:54 ` [patch V4 34/41] x86/cpu: Use common topology code for HYGON Thomas Gleixner
2023-08-14  8:54 ` [patch V4 35/41] x86/mm/numa: Use core domain size on AMD Thomas Gleixner
2023-08-14  8:54 ` [patch V4 36/41] x86/cpu: Make topology_amd_node_id() use the actual node info Thomas Gleixner
2023-08-14  8:54 ` [patch V4 37/41] x86/cpu: Remove topology.c Thomas Gleixner
2023-08-14  8:54 ` [patch V4 38/41] x86/cpu: Remove x86_coreid_bits Thomas Gleixner
2023-08-14  8:54 ` [patch V4 39/41] x86/apic: Remove unused phys_pkg_id() callback Thomas Gleixner
2023-08-14  8:54 ` [patch V4 40/41] x86/xen/smp_pv: Remove cpudata fiddling Thomas Gleixner
2023-08-14  8:54 ` [patch V4 41/41] x86/apic/uv: Remove the private leaf 0xb parser Thomas Gleixner
2023-08-14 14:36 ` [patch V4 00/41] x86/cpu: Rework the topology evaluation Peter Zijlstra
2023-08-16 11:36 ` Zhang, Rui

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=20230814085113.530288551@linutronix.de \
    --to=tglx@linutronix.de \
    --cc=andrew.cooper3@citrix.com \
    --cc=arjan@linux.intel.com \
    --cc=dimitri.sivanich@hpe.com \
    --cc=jgross@suse.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mikelley@microsoft.com \
    --cc=puwen@hygon.cn \
    --cc=qiuxu.zhuo@intel.com \
    --cc=ray.huang@amd.com \
    --cc=sohil.mehta@intel.com \
    --cc=thomas.lendacky@amd.com \
    --cc=wei.liu@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