From: Babu Moger <babu.moger@amd.com>
To: ehabkost@redhat.com, marcel.apfelbaum@gmail.com,
pbonzini@redhat.com, rth@twiddle.net, mst@redhat.com,
imammedo@redhat.com
Cc: qemu-devel@nongnu.org
Subject: [PATCH v4 00/16] APIC ID fixes for AMD EPYC CPU model
Date: Thu, 13 Feb 2020 12:16:23 -0600 [thread overview]
Message-ID: <158161767653.48948.10578064482878399556.stgit@naples-babu.amd.com> (raw)
This series fixes APIC ID encoding problem reported on AMD EPYC cpu model.
https://bugzilla.redhat.com/show_bug.cgi?id=1728166
Currently, the APIC ID is decoded based on the sequence
sockets->dies->cores->threads. This works for most standard AMD and other
vendors' configurations, but this decoding sequence does not follow that of
AMD's APIC ID enumeration strictly. In some cases this can cause CPU topology
inconsistency. When booting a guest VM, the kernel tries to validate the
topology, and finds it inconsistent with the enumeration of EPYC cpu models.
To fix the problem we need to build the topology as per the Processor
Programming Reference (PPR) for AMD Family 17h Model 01h, Revision B1
Processors. It is available at https://www.amd.com/system/files/TechDocs/55570-B1_PUB.zip
Here is the text from the PPR.
Operating systems are expected to use Core::X86::Cpuid::SizeId[ApicIdSize], the
number of least significant bits in the Initial APIC ID that indicate core ID
within a processor, in constructing per-core CPUID masks.
Core::X86::Cpuid::SizeId[ApicIdSize] determines the maximum number of cores
(MNC) that the processor could theoretically support, not the actual number of
cores that are actually implemented or enabled on the processor, as indicated
by Core::X86::Cpuid::SizeId[NC].
Each Core::X86::Apic::ApicId[ApicId] register is preset as follows:
• ApicId[6] = Socket ID.
• ApicId[5:4] = Node ID.
• ApicId[3] = Logical CCX L3 complex ID
• ApicId[2:0]= (SMT) ? {LogicalCoreID[1:0],ThreadId} : {1'b0,LogicalCoreID[1:0]}
v4:
Generated the patches on top of git://github.com/ehabkost/qemu.git (x86-next).
Changes from v3.
1. Moved the arch_id calculation inside the function x86_cpus_init. With this change,
we dont need to change common numa code(suggested by Igor).
2. Introduced the model specific handlers inside X86CPUDefinitions.
These handlers are loaded into X86MachineState during the init(suggested by Eduardo).
Removed the string comparison for EPYC model.
3. Removed llc_id from x86CPU. Added node_id inside X86CPUTopoIDs to take care of
EPYC apicid decoding.
4. Removed init_apicid_fn hanlder from MachineClass. Kept all the code changes
inside the x86.
5. Added new handler function apicid_pkg_offset for pkg_offset calculation.
6. And some other minor changes.
v3:
https://lore.kernel.org/qemu-devel/157541968844.46157.17994918142533791313.stgit@naples-babu.amd.com/
1. Consolidated the topology information in structure X86CPUTopoInfo.
2. Changed the ccx_id to llc_id as commented by upstream.
3. Generalized the apic id decoding. It is mostly similar to current apic id
except that it adds new field llc_id when numa configured. Removes all the
hardcoded values.
4. Removed the earlier parse_numa split. And moved the numa node initialization
inside the numa_complete_configuration. This is bit cleaner as commented by
Eduardo.
5. Added new function init_apicid_fn inside machine_class structure. This
will be used to update the apic id handler specific to cpu model.
6. Updated the cpuid unit tests.
7. TODO : Need to figure out how to dynamically update the handlers using cpu models.
I might some guidance on that.
v2:
https://lore.kernel.org/qemu-devel/156779689013.21957.1631551572950676212.stgit@localhost.localdomain/
1. Introduced the new property epyc to enable new epyc mode.
2. Separated the epyc mode and non epyc mode function.
3. Introduced function pointers in PCMachineState to handle the
differences.
4. Mildly tested different combinations to make things are working as expected.
5. TODO : Setting the epyc feature bit needs to be worked out. This feature is
supported only on AMD EPYC models. I may need some guidance on that.
v1:
https://lore.kernel.org/qemu-devel/20190731232032.51786-1-babu.moger@amd.com/
---
Babu Moger (16):
hw/i386: Rename X86CPUTopoInfo structure to X86CPUTopoIDs
hw/i386: Introduce X86CPUTopoInfo to contain topology info
hw/i386: Consolidate topology functions
hw/i386: Introduce init_topo_info to initialize X86CPUTopoInfo
machine: Add SMP Sockets in CpuTopology
hw/i386: Update structures for nodes_per_pkg
hw/i386: Rename apicid_from_topo_ids to x86_apicid_from_topo_ids
hw/386: Add EPYC mode topology decoding functions
target/i386: Cleanup and use the EPYC mode topology functions
hw/i386: Introduce apicid functions inside X86MachineState
target/i386: Load apicid model specific handlers from X86CPUDefinition
hw/i386: Use the apicid handlers from X86MachineState
target/i386: Add EPYC model specific handlers
hw/i386: Move arch_id decode inside x86_cpus_init
i386: Fix pkg_id offset for EPYC cpu models
tests: Update the Unit tests
hw/core/machine.c | 1
hw/i386/pc.c | 51 +++++-----
hw/i386/x86.c | 73 ++++++++++----
include/hw/boards.h | 2
include/hw/i386/topology.h | 219 +++++++++++++++++++++++++++++-------------
include/hw/i386/x86.h | 28 +++++
target/i386/cpu.c | 228 +++++++++++++++++---------------------------
target/i386/cpu.h | 3 +
tests/test-x86-cpuid.c | 115 +++++++++++++---------
vl.c | 1
10 files changed, 421 insertions(+), 300 deletions(-)
--
Signature
next reply other threads:[~2020-02-13 18:21 UTC|newest]
Thread overview: 44+ messages / expand[flat|nested] mbox.gz Atom feed top
2020-02-13 18:16 Babu Moger [this message]
2020-02-13 18:16 ` [PATCH v4 01/16] hw/i386: Rename X86CPUTopoInfo structure to X86CPUTopoIDs Babu Moger
2020-02-13 18:16 ` [PATCH v4 02/16] hw/i386: Introduce X86CPUTopoInfo to contain topology info Babu Moger
2020-02-13 18:16 ` [PATCH v4 03/16] hw/i386: Consolidate topology functions Babu Moger
2020-02-13 18:16 ` [PATCH v4 04/16] hw/i386: Introduce init_topo_info to initialize X86CPUTopoInfo Babu Moger
2020-02-21 17:05 ` Igor Mammedov
2020-02-21 17:51 ` Babu Moger
2020-02-24 8:18 ` Igor Mammedov
2020-02-24 16:54 ` Babu Moger
2020-02-13 18:16 ` [PATCH v4 05/16] machine: Add SMP Sockets in CpuTopology Babu Moger
2020-02-24 8:37 ` Igor Mammedov
2020-02-13 18:17 ` [PATCH v4 06/16] hw/i386: Update structures for nodes_per_pkg Babu Moger
2020-02-24 8:34 ` Igor Mammedov
2020-02-24 17:12 ` Babu Moger
2020-02-25 7:42 ` Igor Mammedov
2020-02-13 18:17 ` [PATCH v4 07/16] hw/i386: Rename apicid_from_topo_ids to x86_apicid_from_topo_ids Babu Moger
2020-02-20 12:43 ` Igor Mammedov
2020-02-13 18:17 ` [PATCH v4 08/16] hw/386: Add EPYC mode topology decoding functions Babu Moger
2020-02-24 8:50 ` Igor Mammedov
2020-02-24 17:24 ` Babu Moger
2020-02-13 18:17 ` [PATCH v4 09/16] target/i386: Cleanup and use the EPYC mode topology functions Babu Moger
2020-02-24 8:52 ` Igor Mammedov
2020-02-24 17:29 ` Babu Moger
2020-02-25 7:49 ` Igor Mammedov
2020-02-25 15:10 ` Babu Moger
2020-03-02 17:09 ` Babu Moger
2020-03-03 8:47 ` Igor Mammedov
2020-02-13 18:17 ` [PATCH v4 10/16] hw/i386: Introduce apicid functions inside X86MachineState Babu Moger
2020-02-24 17:01 ` Igor Mammedov
2020-02-24 17:30 ` Babu Moger
2020-02-13 18:17 ` [PATCH v4 11/16] target/i386: Load apicid model specific handlers from X86CPUDefinition Babu Moger
2020-02-13 18:17 ` [PATCH v4 12/16] hw/i386: Use the apicid handlers from X86MachineState Babu Moger
2020-02-24 17:19 ` Igor Mammedov
2020-02-24 17:58 ` Babu Moger
2020-02-24 22:31 ` Eduardo Habkost
2020-02-24 23:13 ` Babu Moger
2020-02-25 15:32 ` Eduardo Habkost
2020-02-25 15:41 ` Babu Moger
2020-02-25 8:16 ` Igor Mammedov
2020-02-25 15:26 ` Eduardo Habkost
2020-02-13 18:17 ` [PATCH v4 13/16] target/i386: Add EPYC model specific handlers Babu Moger
2020-02-13 18:17 ` [PATCH v4 14/16] hw/i386: Move arch_id decode inside x86_cpus_init Babu Moger
2020-02-13 18:18 ` [PATCH v4 15/16] i386: Fix pkg_id offset for EPYC cpu models Babu Moger
2020-02-13 18:18 ` [PATCH v4 16/16] tests: Update the Unit tests Babu Moger
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=158161767653.48948.10578064482878399556.stgit@naples-babu.amd.com \
--to=babu.moger@amd.com \
--cc=ehabkost@redhat.com \
--cc=imammedo@redhat.com \
--cc=marcel.apfelbaum@gmail.com \
--cc=mst@redhat.com \
--cc=pbonzini@redhat.com \
--cc=qemu-devel@nongnu.org \
--cc=rth@twiddle.net \
/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).