diff mbox series

[v3,19/26] mm: introduce numa_emulation

Message ID 20240801060826.559858-20-rppt@kernel.org
State New
Headers show
Series mm: introduce numa_memblks | expand

Commit Message

Mike Rapoport Aug. 1, 2024, 6:08 a.m. UTC
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>

Move numa_emulation codfrom arch/x86 to mm/numa_emulation.c

This code will be later reused by arch_numa.

No functional changes.

Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
Tested-by: Zi Yan <ziy@nvidia.com> # for x86_64 and arm64
---
 arch/x86/Kconfig                     |  8 --------
 arch/x86/include/asm/numa.h          | 12 ------------
 arch/x86/mm/Makefile                 |  1 -
 arch/x86/mm/numa_internal.h          | 11 -----------
 include/linux/numa_memblks.h         | 17 +++++++++++++++++
 mm/Kconfig                           |  8 ++++++++
 mm/Makefile                          |  1 +
 {arch/x86/mm => mm}/numa_emulation.c |  4 +---
 8 files changed, 27 insertions(+), 35 deletions(-)
 rename {arch/x86/mm => mm}/numa_emulation.c (99%)

Comments

Jonathan Cameron Aug. 2, 2024, 11:19 a.m. UTC | #1
On Thu,  1 Aug 2024 09:08:19 +0300
Mike Rapoport <rppt@kernel.org> wrote:

> From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
> 
> Move numa_emulation codfrom arch/x86 to mm/numa_emulation.c
> 
> This code will be later reused by arch_numa.
> 
> No functional changes.
> 
> Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
> Tested-by: Zi Yan <ziy@nvidia.com> # for x86_64 and arm64
I ran some basic tests on ARM with this. Seems to do the job.
Reviewed-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>
Tested-by: Jonathan Cameron <Jonathan.Cameron@huawei.com>

Works on both ACPI and dsdt boots.
Dan Williams Aug. 5, 2024, 8:09 p.m. UTC | #2
Mike Rapoport wrote:
> From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
> 
> Move numa_emulation codfrom arch/x86 to mm/numa_emulation.c

s/codfrom/code from/

I am surprised that numa-emulation stayed x86 only for so long. I think
it is useful facility for debugging NUMA scaling and heterogenous memory
topologies. So, glad to see it upleveled.
David Hildenbrand Aug. 6, 2024, 1:18 p.m. UTC | #3
On 05.08.24 22:09, Dan Williams wrote:
> Mike Rapoport wrote:
>> From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
>>
>> Move numa_emulation codfrom arch/x86 to mm/numa_emulation.c
> 
> s/codfrom/code from/
> 
> I am surprised that numa-emulation stayed x86 only for so long. I think
> it is useful facility for debugging NUMA scaling and heterogenous memory
> topologies. So, glad to see it upleveled.

I recall that s390x had NUMA emulation at some point (primarily to have 
multiple kthreads be responsible for different physical memory ranges), 
but it got removed a while ago.
David Hildenbrand Aug. 6, 2024, 1:20 p.m. UTC | #4
On 01.08.24 08:08, Mike Rapoport wrote:
> From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
> 
> Move numa_emulation codfrom arch/x86 to mm/numa_emulation.c
> 
> This code will be later reused by arch_numa.
> 

I'm confused why documentation lists for "numa=fake="

[KNL, ARM64, RISCV, X86, EARLY]
David Hildenbrand Aug. 6, 2024, 1:24 p.m. UTC | #5
On 06.08.24 15:20, David Hildenbrand wrote:
> On 01.08.24 08:08, Mike Rapoport wrote:
>> From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
>>
>> Move numa_emulation codfrom arch/x86 to mm/numa_emulation.c
>>
>> This code will be later reused by arch_numa.
>>
> 
> I'm confused why documentation lists for "numa=fake="
> 
> [KNL, ARM64, RISCV, X86, EARLY]

Ahh, I looked at mm-unstable which contain your patches (in particular 
the one that documents this :)) )
diff mbox series

Patch

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 74afb59c6603..acd9745bf2ae 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1600,14 +1600,6 @@  config X86_64_ACPI_NUMA
 	help
 	  Enable ACPI SRAT based node topology detection.
 
-config NUMA_EMU
-	bool "NUMA emulation"
-	depends on NUMA
-	help
-	  Enable NUMA emulation. A flat machine will be split
-	  into virtual nodes when booted with "numa=fake=N", where N is the
-	  number of nodes. This is only useful for debugging.
-
 config NODES_SHIFT
 	int "Maximum NUMA Nodes (as a power of 2)" if !MAXSMP
 	range 1 10
diff --git a/arch/x86/include/asm/numa.h b/arch/x86/include/asm/numa.h
index 203100500f24..5469d7a7c40f 100644
--- a/arch/x86/include/asm/numa.h
+++ b/arch/x86/include/asm/numa.h
@@ -65,16 +65,4 @@  static inline void init_gi_nodes(void)			{ }
 void debug_cpumask_set_cpu(unsigned int cpu, int node, bool enable);
 #endif
 
-#ifdef CONFIG_NUMA_EMU
-int numa_emu_cmdline(char *str);
-void __init numa_emu_update_cpu_to_node(int *emu_nid_to_phys,
-					unsigned int nr_emu_nids);
-u64 __init numa_emu_dma_end(void);
-#else /* CONFIG_NUMA_EMU */
-static inline int numa_emu_cmdline(char *str)
-{
-	return -EINVAL;
-}
-#endif /* CONFIG_NUMA_EMU */
-
 #endif	/* _ASM_X86_NUMA_H */
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 8d3a00e5c528..690fbf48e853 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -57,7 +57,6 @@  obj-$(CONFIG_MMIOTRACE_TEST)	+= testmmiotrace.o
 obj-$(CONFIG_NUMA)		+= numa.o numa_$(BITS).o
 obj-$(CONFIG_AMD_NUMA)		+= amdtopology.o
 obj-$(CONFIG_ACPI_NUMA)		+= srat.o
-obj-$(CONFIG_NUMA_EMU)		+= numa_emulation.o
 
 obj-$(CONFIG_X86_INTEL_MEMORY_PROTECTION_KEYS)	+= pkeys.o
 obj-$(CONFIG_RANDOMIZE_MEMORY)			+= kaslr.o
diff --git a/arch/x86/mm/numa_internal.h b/arch/x86/mm/numa_internal.h
index 249e3aaeadce..11e1ff370c10 100644
--- a/arch/x86/mm/numa_internal.h
+++ b/arch/x86/mm/numa_internal.h
@@ -7,15 +7,4 @@ 
 
 void __init x86_numa_init(void);
 
-struct numa_meminfo;
-
-#ifdef CONFIG_NUMA_EMU
-void __init numa_emulation(struct numa_meminfo *numa_meminfo,
-			   int numa_dist_cnt);
-#else
-static inline void numa_emulation(struct numa_meminfo *numa_meminfo,
-				  int numa_dist_cnt)
-{ }
-#endif
-
 #endif	/* __X86_MM_NUMA_INTERNAL_H */
diff --git a/include/linux/numa_memblks.h b/include/linux/numa_memblks.h
index 968a590535ac..f81f98678074 100644
--- a/include/linux/numa_memblks.h
+++ b/include/linux/numa_memblks.h
@@ -34,6 +34,23 @@  int __init numa_register_meminfo(struct numa_meminfo *mi);
 void __init numa_nodemask_from_meminfo(nodemask_t *nodemask,
 				       const struct numa_meminfo *mi);
 
+#ifdef CONFIG_NUMA_EMU
+int numa_emu_cmdline(char *str);
+void __init numa_emu_update_cpu_to_node(int *emu_nid_to_phys,
+					unsigned int nr_emu_nids);
+u64 __init numa_emu_dma_end(void);
+void __init numa_emulation(struct numa_meminfo *numa_meminfo,
+			   int numa_dist_cnt);
+#else
+static inline void numa_emulation(struct numa_meminfo *numa_meminfo,
+				  int numa_dist_cnt)
+{ }
+static inline int numa_emu_cmdline(char *str)
+{
+	return -EINVAL;
+}
+#endif /* CONFIG_NUMA_EMU */
+
 #endif /* CONFIG_NUMA_MEMBLKS */
 
 #endif	/* __NUMA_MEMBLKS_H */
diff --git a/mm/Kconfig b/mm/Kconfig
index dc5912d29ed5..3b466df1d9e2 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -1266,6 +1266,14 @@  config EXECMEM
 config NUMA_MEMBLKS
 	bool
 
+config NUMA_EMU
+	bool "NUMA emulation"
+	depends on NUMA_MEMBLKS
+	help
+	  Enable NUMA emulation. A flat machine will be split
+	  into virtual nodes when booted with "numa=fake=N", where N is the
+	  number of nodes. This is only useful for debugging.
+
 source "mm/damon/Kconfig"
 
 endmenu
diff --git a/mm/Makefile b/mm/Makefile
index e3fac7efd880..75a189cc67ef 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -143,3 +143,4 @@  obj-$(CONFIG_SHRINKER_DEBUG) += shrinker_debug.o
 obj-$(CONFIG_EXECMEM) += execmem.o
 obj-$(CONFIG_NUMA) += numa.o
 obj-$(CONFIG_NUMA_MEMBLKS) += numa_memblks.o
+obj-$(CONFIG_NUMA_EMU) += numa_emulation.o
diff --git a/arch/x86/mm/numa_emulation.c b/mm/numa_emulation.c
similarity index 99%
rename from arch/x86/mm/numa_emulation.c
rename to mm/numa_emulation.c
index 33610026b7a3..031fb9961bf7 100644
--- a/arch/x86/mm/numa_emulation.c
+++ b/mm/numa_emulation.c
@@ -7,9 +7,7 @@ 
 #include <linux/topology.h>
 #include <linux/memblock.h>
 #include <linux/numa_memblks.h>
-#include <asm/dma.h>
-
-#include "numa_internal.h"
+#include <asm/numa.h>
 
 #define FAKE_NODE_MIN_SIZE	((u64)32 << 20)
 #define FAKE_NODE_MIN_HASH_MASK	(~(FAKE_NODE_MIN_SIZE - 1UL))