From: Dan Williams <dan.j.williams@xxxxxxxxx>
Subject: x86/numa: cleanup configuration dependent command-line options
Patch series "device-dax: Support sub-dividing soft-reserved ranges", v5.
The device-dax facility allows an address range to be directly mapped
through a chardev, or optionally hotplugged to the core kernel page
allocator as System-RAM. It is the mechanism for converting persistent
memory (pmem) to be used as another volatile memory pool i.e. the current
Memory Tiering hot topic on linux-mm.
In the case of pmem the nvdimm-namespace-label mechanism can sub-divide
it, but that labeling mechanism is not available / applicable to
soft-reserved ("EFI specific purpose") memory [3]. This series provides a
sysfs-mechanism for the daxctl utility to enable provisioning of
volatile-soft-reserved memory ranges.
The motivations for this facility are:
1/ Allow performance differentiated memory ranges to be split between
kernel-managed and directly-accessed use cases.
2/ Allow physical memory to be provisioned along performance relevant
address boundaries. For example, divide a memory-side cache [4] along
cache-color boundaries.
3/ Parcel out soft-reserved memory to VMs using device-dax as a security
/ permissions boundary [5]. Specifically I have seen people (ab)using
memmap=nn!ss (mark System-RAM as Persistent Memory) just to get the
device-dax interface on custom address ranges. A follow-on for the VM
use case is to teach device-dax to dynamically allocate 'struct page' at
runtime to reduce the duplication of 'struct page' space in both the
guest and the host kernel for the same physical pages.
[2]: http://lore.kernel.org/r/20200713160837.13774-11-joao.m.martins@xxxxxxxxxx
[3]: http://lore.kernel.org/r/157309097008.1579826.12818463304589384434.stgit@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
[4]: http://lore.kernel.org/r/154899811738.3165233.12325692939590944259.stgit@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
[5]: http://lore.kernel.org/r/20200110190313.17144-1-joao.m.martins@xxxxxxxxxx
This patch (of 23):
In preparation for adding a new numa= option clean up the existing ones to
avoid ifdefs in numa_setup(), and provide feedback when the option is
numa=fake= option is invalid due to kernel config. The same does not need
to be done for numa=noacpi, since the capability is already hard disabled
at compile-time.
Link: https://lkml.kernel.org/r/160106109960.30709.7379926726669669398.stgit@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Link: https://lkml.kernel.org/r/159643094279.4062302.17779410714418721328.stgit@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Link: https://lkml.kernel.org/r/159643094925.4062302.14979872973043772305.stgit@xxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxxx
Signed-off-by: Dan Williams <dan.j.williams@xxxxxxxxx>
Suggested-by: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
Cc: Andy Lutomirski <luto@xxxxxxxxxx>
Cc: Ard Biesheuvel <ardb@xxxxxxxxxx>
Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
Cc: Ben Skeggs <bskeggs@xxxxxxxxxx>
Cc: Borislav Petkov <bp@xxxxxxxxx>
Cc: Brice Goglin <Brice.Goglin@xxxxxxxx>
Cc: Catalin Marinas <catalin.marinas@xxxxxxx>
Cc: Daniel Vetter <daniel@xxxxxxxx>
Cc: Dave Hansen <dave.hansen@xxxxxxxxxxxxxxx>
Cc: Dave Jiang <dave.jiang@xxxxxxxxx>
Cc: David Airlie <airlied@xxxxxxxx>
Cc: David Hildenbrand <david@xxxxxxxxxx>
Cc: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Cc: "H. Peter Anvin" <hpa@xxxxxxxxx>
Cc: Ingo Molnar <mingo@xxxxxxxxxx>
Cc: Ira Weiny <ira.weiny@xxxxxxxxx>
Cc: Jason Gunthorpe <jgg@xxxxxxxxxxxx>
Cc: Jeff Moyer <jmoyer@xxxxxxxxxx>
Cc: Jia He <justin.he@xxxxxxx>
Cc: Joao Martins <joao.m.martins@xxxxxxxxxx>
Cc: Jonathan Cameron <Jonathan.Cameron@xxxxxxxxxx>
Cc: Michael Ellerman <mpe@xxxxxxxxxxxxxx>
Cc: Mike Rapoport <rppt@xxxxxxxxxxxxx>
Cc: Paul Mackerras <paulus@xxxxxxxxxx>
Cc: Pavel Tatashin <pasha.tatashin@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Cc: Rafael J. Wysocki <rafael.j.wysocki@xxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Tom Lendacky <thomas.lendacky@xxxxxxx>
Cc: Vishal Verma <vishal.l.verma@xxxxxxxxx>
Cc: Wei Yang <richard.weiyang@xxxxxxxxxxxxxxxxx>
Cc: Will Deacon <will@xxxxxxxxxx>
Cc: Ard Biesheuvel <ard.biesheuvel@xxxxxxxxxx>
Cc: Bjorn Helgaas <bhelgaas@xxxxxxxxxx>
Cc: Boris Ostrovsky <boris.ostrovsky@xxxxxxxxxx>
Cc: Hulk Robot <hulkci@xxxxxxxxxx>
Cc: Jason Yan <yanaijie@xxxxxxxxxx>
Cc: "Jérôme Glisse" <jglisse@xxxxxxxxxx>
Cc: Juergen Gross <jgross@xxxxxxxx>
Cc: kernel test robot <lkp@xxxxxxxxx>
Cc: Randy Dunlap <rdunlap@xxxxxxxxxxxxx>
Cc: Stefano Stabellini <sstabellini@xxxxxxxxxx>
Cc: Vivek Goyal <vgoyal@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
---
arch/x86/include/asm/numa.h | 8 +++++++-
arch/x86/mm/numa.c | 8 ++------
arch/x86/mm/numa_emulation.c | 3 ++-
arch/x86/xen/enlighten_pv.c | 2 +-
drivers/acpi/numa/srat.c | 9 +++++++--
include/acpi/acpi_numa.h | 6 +++++-
6 files changed, 24 insertions(+), 12 deletions(-)
--- a/arch/x86/include/asm/numa.h~x86-numa-cleanup-configuration-dependent-command-line-options
+++ a/arch/x86/include/asm/numa.h
@@ -3,6 +3,7 @@
#define _ASM_X86_NUMA_H
#include <linux/nodemask.h>
+#include <linux/errno.h>
#include <asm/topology.h>
#include <asm/apicdef.h>
@@ -77,7 +78,12 @@ void debug_cpumask_set_cpu(int cpu, int
#ifdef CONFIG_NUMA_EMU
#define FAKE_NODE_MIN_SIZE ((u64)32 << 20)
#define FAKE_NODE_MIN_HASH_MASK (~(FAKE_NODE_MIN_SIZE - 1UL))
-void numa_emu_cmdline(char *);
+int numa_emu_cmdline(char *str);
+#else /* CONFIG_NUMA_EMU */
+static inline int numa_emu_cmdline(char *str)
+{
+ return -EINVAL;
+}
#endif /* CONFIG_NUMA_EMU */
#endif /* _ASM_X86_NUMA_H */
--- a/arch/x86/mm/numa.c~x86-numa-cleanup-configuration-dependent-command-line-options
+++ a/arch/x86/mm/numa.c
@@ -37,14 +37,10 @@ static __init int numa_setup(char *opt)
return -EINVAL;
if (!strncmp(opt, "off", 3))
numa_off = 1;
-#ifdef CONFIG_NUMA_EMU
if (!strncmp(opt, "fake=", 5))
- numa_emu_cmdline(opt + 5);
-#endif
-#ifdef CONFIG_ACPI_NUMA
+ return numa_emu_cmdline(opt + 5);
if (!strncmp(opt, "noacpi", 6))
- acpi_numa = -1;
-#endif
+ disable_srat();
return 0;
}
early_param("numa", numa_setup);
--- a/arch/x86/mm/numa_emulation.c~x86-numa-cleanup-configuration-dependent-command-line-options
+++ a/arch/x86/mm/numa_emulation.c
@@ -13,9 +13,10 @@
static int emu_nid_to_phys[MAX_NUMNODES];
static char *emu_cmdline __initdata;
-void __init numa_emu_cmdline(char *str)
+int __init numa_emu_cmdline(char *str)
{
emu_cmdline = str;
+ return 0;
}
static int __init emu_find_memblk_by_nid(int nid, const struct numa_meminfo *mi)
--- a/arch/x86/xen/enlighten_pv.c~x86-numa-cleanup-configuration-dependent-command-line-options
+++ a/arch/x86/xen/enlighten_pv.c
@@ -1300,7 +1300,7 @@ asmlinkage __visible void __init xen_sta
* any NUMA information the kernel tries to get from ACPI will
* be meaningless. Prevent it from trying.
*/
- acpi_numa = -1;
+ disable_srat();
#endif
WARN_ON(xen_cpuhp_setup(xen_cpu_up_prepare_pv, xen_cpu_dead_pv));
--- a/drivers/acpi/numa/srat.c~x86-numa-cleanup-configuration-dependent-command-line-options
+++ a/drivers/acpi/numa/srat.c
@@ -27,7 +27,12 @@ static int node_to_pxm_map[MAX_NUMNODES]
= { [0 ... MAX_NUMNODES - 1] = PXM_INVAL };
unsigned char acpi_srat_revision __initdata;
-int acpi_numa __initdata;
+static int acpi_numa __initdata;
+
+void __init disable_srat(void)
+{
+ acpi_numa = -1;
+}
int pxm_to_node(int pxm)
{
@@ -163,7 +168,7 @@ static int __init slit_valid(struct acpi
void __init bad_srat(void)
{
pr_err("SRAT: SRAT not used.\n");
- acpi_numa = -1;
+ disable_srat();
}
int __init srat_disabled(void)
--- a/include/acpi/acpi_numa.h~x86-numa-cleanup-configuration-dependent-command-line-options
+++ a/include/acpi/acpi_numa.h
@@ -17,10 +17,14 @@ extern int pxm_to_node(int);
extern int node_to_pxm(int);
extern int acpi_map_pxm_to_node(int);
extern unsigned char acpi_srat_revision;
-extern int acpi_numa __initdata;
+extern void disable_srat(void);
extern void bad_srat(void);
extern int srat_disabled(void);
+#else /* CONFIG_ACPI_NUMA */
+static inline void disable_srat(void)
+{
+}
#endif /* CONFIG_ACPI_NUMA */
#endif /* __ACP_NUMA_H */
_
