From: Peter Zijlstra <peterz@infradead.org>
To: x86@kernel.org, tglx@kernel.org
Cc: linux-kernel@vger.kernel.org, peterz@infradead.org,
tim.c.chen@linux.intel.com, yu.c.chen@intel.com,
kyle.meyer@hpe.com, vinicius.gomes@intel.com, brgerst@gmail.com,
hpa@zytor.com, kprateek.nayak@amd.com,
patryk.wlazlyn@linux.intel.com, rafael.j.wysocki@intel.com,
russ.anderson@hpe.com, zhao1.liu@intel.com, tony.luck@intel.com,
Zhang Rui <rui.zhang@intel.com>
Subject: [PATCH v2 1/5] x86/numa: Store extra copy of numa_nodes_parsed
Date: Tue, 03 Mar 2026 11:55:40 +0100 [thread overview]
Message-ID: <20260303110059.889884023@infradead.org> (raw)
In-Reply-To: <20260303105539.428037056@infradead.org>
The topology setup code needs to know the total number of physical
nodes enumerated in SRAT; however NUMA_EMU can cause the existing
numa_nodes_parsed bitmap to be fictitious. Therefore, keep a copy of
the bitmap specifically to retain the physical node count.
Suggested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: K Prateek Nayak <kprateek.nayak@amd.com>
Tested-by: Zhang Rui <rui.zhang@intel.com>
Tested-by: Chen Yu <yu.c.chen@intel.com>
Tested-by: Kyle Meyer <kyle.meyer@hpe.com>
---
arch/x86/include/asm/numa.h | 6 ++++++
arch/x86/kernel/cpu/topology.c | 1 +
arch/x86/mm/numa.c | 8 ++++++++
arch/x86/mm/srat.c | 2 ++
4 files changed, 17 insertions(+)
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -22,6 +22,7 @@ extern int numa_off;
*/
extern s16 __apicid_to_node[MAX_LOCAL_APIC];
extern nodemask_t numa_nodes_parsed __initdata;
+extern nodemask_t numa_phys_nodes_parsed __initdata;
static inline void set_apicid_to_node(int apicid, s16 node)
{
@@ -48,6 +49,7 @@ extern void __init init_cpu_to_node(void
extern void numa_add_cpu(unsigned int cpu);
extern void numa_remove_cpu(unsigned int cpu);
extern void init_gi_nodes(void);
+extern int num_phys_nodes(void);
#else /* CONFIG_NUMA */
static inline void numa_set_node(int cpu, int node) { }
static inline void numa_clear_node(int cpu) { }
@@ -55,6 +57,10 @@ static inline void init_cpu_to_node(void
static inline void numa_add_cpu(unsigned int cpu) { }
static inline void numa_remove_cpu(unsigned int cpu) { }
static inline void init_gi_nodes(void) { }
+static inline int num_phys_nodes(void)
+{
+ return 1;
+}
#endif /* CONFIG_NUMA */
#ifdef CONFIG_DEBUG_PER_CPU_MAPS
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -48,6 +48,8 @@ s16 __apicid_to_node[MAX_LOCAL_APIC] = {
[0 ... MAX_LOCAL_APIC-1] = NUMA_NO_NODE
};
+nodemask_t numa_phys_nodes_parsed __initdata;
+
int numa_cpu_node(int cpu)
{
u32 apicid = early_per_cpu(x86_cpu_to_apicid, cpu);
@@ -57,6 +59,11 @@ int numa_cpu_node(int cpu)
return NUMA_NO_NODE;
}
+int __init num_phys_nodes(void)
+{
+ return bitmap_weight(numa_phys_nodes_parsed.bits, MAX_NUMNODES);
+}
+
cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
EXPORT_SYMBOL(node_to_cpumask_map);
@@ -210,6 +217,7 @@ static int __init dummy_numa_init(void)
0LLU, PFN_PHYS(max_pfn) - 1);
node_set(0, numa_nodes_parsed);
+ node_set(0, numa_phys_nodes_parsed);
numa_add_memblk(0, 0, PFN_PHYS(max_pfn));
return 0;
--- a/arch/x86/mm/srat.c
+++ b/arch/x86/mm/srat.c
@@ -57,6 +57,7 @@ acpi_numa_x2apic_affinity_init(struct ac
}
set_apicid_to_node(apic_id, node);
node_set(node, numa_nodes_parsed);
+ node_set(node, numa_phys_nodes_parsed);
pr_debug("SRAT: PXM %u -> APIC 0x%04x -> Node %u\n", pxm, apic_id, node);
}
@@ -97,6 +98,7 @@ acpi_numa_processor_affinity_init(struct
set_apicid_to_node(apic_id, node);
node_set(node, numa_nodes_parsed);
+ node_set(node, numa_phys_nodes_parsed);
pr_debug("SRAT: PXM %u -> APIC 0x%02x -> Node %u\n", pxm, apic_id, node);
}
next prev parent reply other threads:[~2026-03-03 11:05 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-03-03 10:55 [PATCH v2 0/5] x86/topo: SNC Divination Peter Zijlstra
2026-03-03 10:55 ` Peter Zijlstra [this message]
2026-03-04 15:46 ` [tip: x86/urgent] x86/numa: Store extra copy of numa_nodes_parsed tip-bot2 for Peter Zijlstra
2026-03-03 10:55 ` [PATCH v2 2/5] x86/topo: Add topology_num_nodes_per_package() Peter Zijlstra
2026-03-04 15:46 ` [tip: x86/urgent] " tip-bot2 for Peter Zijlstra
2026-03-03 10:55 ` [PATCH v2 3/5] x86/topo: Replace x86_has_numa_in_package Peter Zijlstra
2026-03-04 15:46 ` [tip: x86/urgent] " tip-bot2 for Peter Zijlstra
2026-03-03 10:55 ` [PATCH v2 4/5] x86/topo: Fix SNC topology mess Peter Zijlstra
2026-03-03 11:59 ` Ingo Molnar
2026-03-03 14:45 ` Peter Zijlstra
2026-03-04 15:46 ` [tip: x86/urgent] " tip-bot2 for Peter Zijlstra
2026-03-03 10:55 ` [PATCH v2 5/5] x86/resctrl: Fix SNC detection Peter Zijlstra
2026-03-04 15:46 ` [tip: x86/urgent] " tip-bot2 for Tony Luck
2026-04-28 20:41 ` Babu Moger
2026-04-28 20:52 ` Luck, Tony
2026-04-28 23:09 ` Moger, Babu
2026-03-03 12:01 ` [PATCH v2 0/5] x86/topo: SNC Divination Ingo Molnar
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=20260303110059.889884023@infradead.org \
--to=peterz@infradead.org \
--cc=brgerst@gmail.com \
--cc=hpa@zytor.com \
--cc=kprateek.nayak@amd.com \
--cc=kyle.meyer@hpe.com \
--cc=linux-kernel@vger.kernel.org \
--cc=patryk.wlazlyn@linux.intel.com \
--cc=rafael.j.wysocki@intel.com \
--cc=rui.zhang@intel.com \
--cc=russ.anderson@hpe.com \
--cc=tglx@kernel.org \
--cc=tim.c.chen@linux.intel.com \
--cc=tony.luck@intel.com \
--cc=vinicius.gomes@intel.com \
--cc=x86@kernel.org \
--cc=yu.c.chen@intel.com \
--cc=zhao1.liu@intel.com \
/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
all inboxes | Powered by JetHome®