From: Mike Rapoport <rppt@kernel.org>
To: linux-kernel@vger.kernel.org
Cc: Alexander Gordeev <agordeev@linux.ibm.com>,
Andreas Larsson <andreas@gaisler.com>,
Andrew Morton <akpm@linux-foundation.org>,
Arnd Bergmann <arnd@arndb.de>, Borislav Petkov <bp@alien8.de>,
Catalin Marinas <catalin.marinas@arm.com>,
Christophe Leroy <christophe.leroy@csgroup.eu>,
Dan Williams <dan.j.williams@intel.com>,
Dave Hansen <dave.hansen@linux.intel.com>,
David Hildenbrand <david@redhat.com>,
"David S. Miller" <davem@davemloft.net>,
Greg Kroah-Hartman <gregkh@linuxfoundation.org>,
Heiko Carstens <hca@linux.ibm.com>,
Huacai Chen <chenhuacai@kernel.org>,
Ingo Molnar <mingo@redhat.com>,
Jiaxun Yang <jiaxun.yang@flygoat.com>,
John Paul Adrian Glaubitz <glaubitz@physik.fu-berlin.de>,
Jonathan Cameron <jonathan.cameron@huawei.com>,
Michael Ellerman <mpe@ellerman.id.au>,
Mike Rapoport <rppt@kernel.org>,
Palmer Dabbelt <palmer@dabbelt.com>,
"Rafael J. Wysocki" <rafael@kernel.org>,
Rob Herring <robh@kernel.org>,
Thomas Bogendoerfer <tsbogend@alpha.franken.de>,
Thomas Gleixner <tglx@linutronix.de>,
Vasily Gorbik <gor@linux.ibm.com>, Will Deacon <will@kernel.org>,
linux-arm-kernel@lists.infradead.org, loongarch@lists.linux.dev,
linux-mips@vger.kernel.org, linuxppc-dev@lists.ozlabs.org,
linux-riscv@lists.infradead.org, linux-s390@vger.kernel.org,
linux-sh@vger.kernel.org, sparclinux@vger.kernel.org,
linux-acpi@vger.kernel.org, linux-cxl@vger.kernel.org,
nvdimm@lists.linux.dev, devicetree@vger.kernel.org,
linux-arch@vger.kernel.org, linux-mm@kvack.org, x86@kernel.org
Subject: [PATCH 16/17] arch_numa: switch over to numa_memblks
Date: Tue, 16 Jul 2024 14:13:45 +0300 [thread overview]
Message-ID: <20240716111346.3676969-17-rppt@kernel.org> (raw)
In-Reply-To: <20240716111346.3676969-1-rppt@kernel.org>
From: "Mike Rapoport (Microsoft)" <rppt@kernel.org>
Until now arch_numa was directly translating firmware NUMA information
to memblock.
Using numa_memblks as an intermediate step has a few advantages:
* alignment with more battle tested x86 implementation
* availability of NUMA emulation
* maintaining node information for not yet populated memory
Replace current functionality related to numa_add_memblk() and
__node_distance() with the implementation based on numa_memblks and add
functions required by numa_emulation.
Signed-off-by: Mike Rapoport (Microsoft) <rppt@kernel.org>
---
drivers/base/Kconfig | 1 +
drivers/base/arch_numa.c | 200 +++++++++++--------------------------
include/asm-generic/numa.h | 6 +-
3 files changed, 64 insertions(+), 143 deletions(-)
diff --git a/drivers/base/Kconfig b/drivers/base/Kconfig
index 2b8fd6bb7da0..064eb52ff7e2 100644
--- a/drivers/base/Kconfig
+++ b/drivers/base/Kconfig
@@ -226,6 +226,7 @@ config GENERIC_ARCH_TOPOLOGY
config GENERIC_ARCH_NUMA
bool
+ select NUMA_MEMBLKS
help
Enable support for generic NUMA implementation. Currently, RISC-V
and ARM64 use it.
diff --git a/drivers/base/arch_numa.c b/drivers/base/arch_numa.c
index 2ebf12eab99f..333cbbad7466 100644
--- a/drivers/base/arch_numa.c
+++ b/drivers/base/arch_numa.c
@@ -12,14 +12,12 @@
#include <linux/memblock.h>
#include <linux/module.h>
#include <linux/of.h>
+#include <linux/numa_memblks.h>
#include <asm/sections.h>
-nodemask_t numa_nodes_parsed __initdata;
static int cpu_to_node_map[NR_CPUS] = { [0 ... NR_CPUS-1] = NUMA_NO_NODE };
-static int numa_distance_cnt;
-static u8 *numa_distance;
bool numa_off;
static __init int numa_parse_early_param(char *opt)
@@ -28,6 +26,8 @@ static __init int numa_parse_early_param(char *opt)
return -EINVAL;
if (str_has_prefix(opt, "off"))
numa_off = true;
+ if (!strncmp(opt, "fake=", 5))
+ return numa_emu_cmdline(opt + 5);
return 0;
}
@@ -59,6 +59,7 @@ EXPORT_SYMBOL(cpumask_of_node);
#endif
+#ifndef CONFIG_NUMA_EMU
static void numa_update_cpu(unsigned int cpu, bool remove)
{
int nid = cpu_to_node(cpu);
@@ -81,6 +82,7 @@ void numa_remove_cpu(unsigned int cpu)
{
numa_update_cpu(cpu, true);
}
+#endif
void numa_clear_node(unsigned int cpu)
{
@@ -142,7 +144,7 @@ void __init early_map_cpu_to_node(unsigned int cpu, int nid)
unsigned long __per_cpu_offset[NR_CPUS] __read_mostly;
EXPORT_SYMBOL(__per_cpu_offset);
-int __init early_cpu_to_node(int cpu)
+int early_cpu_to_node(int cpu)
{
return cpu_to_node_map[cpu];
}
@@ -187,30 +189,6 @@ void __init setup_per_cpu_areas(void)
}
#endif
-/**
- * numa_add_memblk() - Set node id to memblk
- * @nid: NUMA node ID of the new memblk
- * @start: Start address of the new memblk
- * @end: End address of the new memblk
- *
- * RETURNS:
- * 0 on success, -errno on failure.
- */
-int __init numa_add_memblk(int nid, u64 start, u64 end)
-{
- int ret;
-
- ret = memblock_set_node(start, (end - start), &memblock.memory, nid);
- if (ret < 0) {
- pr_err("memblock [0x%llx - 0x%llx] failed to add on node %d\n",
- start, (end - 1), nid);
- return ret;
- }
-
- node_set(nid, numa_nodes_parsed);
- return ret;
-}
-
/*
* Initialize NODE_DATA for a node on the local memory
*/
@@ -226,116 +204,9 @@ static void __init setup_node_data(int nid, u64 start_pfn, u64 end_pfn)
NODE_DATA(nid)->node_spanned_pages = end_pfn - start_pfn;
}
-/*
- * numa_free_distance
- *
- * The current table is freed.
- */
-void __init numa_free_distance(void)
-{
- size_t size;
-
- if (!numa_distance)
- return;
-
- size = numa_distance_cnt * numa_distance_cnt *
- sizeof(numa_distance[0]);
-
- memblock_free(numa_distance, size);
- numa_distance_cnt = 0;
- numa_distance = NULL;
-}
-
-/*
- * Create a new NUMA distance table.
- */
-static int __init numa_alloc_distance(void)
-{
- size_t size;
- int i, j;
-
- size = nr_node_ids * nr_node_ids * sizeof(numa_distance[0]);
- numa_distance = memblock_alloc(size, PAGE_SIZE);
- if (WARN_ON(!numa_distance))
- return -ENOMEM;
-
- numa_distance_cnt = nr_node_ids;
-
- /* fill with the default distances */
- for (i = 0; i < numa_distance_cnt; i++)
- for (j = 0; j < numa_distance_cnt; j++)
- numa_distance[i * numa_distance_cnt + j] = i == j ?
- LOCAL_DISTANCE : REMOTE_DISTANCE;
-
- pr_debug("Initialized distance table, cnt=%d\n", numa_distance_cnt);
-
- return 0;
-}
-
-/**
- * numa_set_distance() - Set inter node NUMA distance from node to node.
- * @from: the 'from' node to set distance
- * @to: the 'to' node to set distance
- * @distance: NUMA distance
- *
- * Set the distance from node @from to @to to @distance.
- * If distance table doesn't exist, a warning is printed.
- *
- * If @from or @to is higher than the highest known node or lower than zero
- * or @distance doesn't make sense, the call is ignored.
- */
-void __init numa_set_distance(int from, int to, int distance)
-{
- if (!numa_distance) {
- pr_warn_once("Warning: distance table not allocated yet\n");
- return;
- }
-
- if (from >= numa_distance_cnt || to >= numa_distance_cnt ||
- from < 0 || to < 0) {
- pr_warn_once("Warning: node ids are out of bound, from=%d to=%d distance=%d\n",
- from, to, distance);
- return;
- }
-
- if ((u8)distance != distance ||
- (from == to && distance != LOCAL_DISTANCE)) {
- pr_warn_once("Warning: invalid distance parameter, from=%d to=%d distance=%d\n",
- from, to, distance);
- return;
- }
-
- numa_distance[from * numa_distance_cnt + to] = distance;
-}
-
-/*
- * Return NUMA distance @from to @to
- */
-int __node_distance(int from, int to)
-{
- if (from >= numa_distance_cnt || to >= numa_distance_cnt)
- return from == to ? LOCAL_DISTANCE : REMOTE_DISTANCE;
- return numa_distance[from * numa_distance_cnt + to];
-}
-EXPORT_SYMBOL(__node_distance);
-
static int __init numa_register_nodes(void)
{
int nid;
- struct memblock_region *mblk;
-
- /* Check that valid nid is set to memblks */
- for_each_mem_region(mblk) {
- int mblk_nid = memblock_get_region_node(mblk);
- phys_addr_t start = mblk->base;
- phys_addr_t end = mblk->base + mblk->size - 1;
-
- if (mblk_nid == NUMA_NO_NODE || mblk_nid >= MAX_NUMNODES) {
- pr_warn("Warning: invalid memblk node %d [mem %pap-%pap]\n",
- mblk_nid, &start, &end);
- return -EINVAL;
- }
- }
/* Finally register nodes. */
for_each_node_mask(nid, numa_nodes_parsed) {
@@ -360,11 +231,7 @@ static int __init numa_init(int (*init_func)(void))
nodes_clear(node_possible_map);
nodes_clear(node_online_map);
- ret = numa_alloc_distance();
- if (ret < 0)
- return ret;
-
- ret = init_func();
+ ret = numa_memblks_init(init_func, /* memblock_force_top_down */ false);
if (ret < 0)
goto out_free_distance;
@@ -382,7 +249,7 @@ static int __init numa_init(int (*init_func)(void))
return 0;
out_free_distance:
- numa_free_distance();
+ numa_reset_distance();
return ret;
}
@@ -454,3 +321,54 @@ void __init arch_numa_init(void)
numa_init(dummy_numa_init);
}
+
+#ifdef CONFIG_NUMA_EMU
+void __init numa_emu_update_cpu_to_node(int *emu_nid_to_phys,
+ unsigned int nr_emu_nids)
+{
+ int i, j;
+
+ /*
+ * Transform __apicid_to_node table to use emulated nids by
+ * reverse-mapping phys_nid. The maps should always exist but fall
+ * back to zero just in case.
+ */
+ for (i = 0; i < ARRAY_SIZE(cpu_to_node_map); i++) {
+ if (cpu_to_node_map[i] == NUMA_NO_NODE)
+ continue;
+ for (j = 0; j < nr_emu_nids; j++)
+ if (cpu_to_node_map[i] == emu_nid_to_phys[j])
+ break;
+ cpu_to_node_map[i] = j < nr_emu_nids ? j : 0;
+ }
+}
+
+u64 __init numa_emu_dma_end(void)
+{
+ return PFN_PHYS(memblock_start_of_DRAM() + SZ_4G);
+}
+
+void debug_cpumask_set_cpu(unsigned int cpu, int node, bool enable)
+{
+ struct cpumask *mask;
+
+ if (node == NUMA_NO_NODE)
+ return;
+
+ mask = node_to_cpumask_map[node];
+ if (!cpumask_available(mask)) {
+ pr_err("node_to_cpumask_map[%i] NULL\n", node);
+ dump_stack();
+ return;
+ }
+
+ if (enable)
+ cpumask_set_cpu(cpu, mask);
+ else
+ cpumask_clear_cpu(cpu, mask);
+
+ pr_debug("%s cpu %d node %d: mask now %*pbl\n",
+ enable ? "numa_add_cpu" : "numa_remove_cpu",
+ cpu, node, cpumask_pr_args(mask));
+}
+#endif /* CONFIG_NUMA_EMU */
diff --git a/include/asm-generic/numa.h b/include/asm-generic/numa.h
index c32e0cf23c90..c2b046d1fd82 100644
--- a/include/asm-generic/numa.h
+++ b/include/asm-generic/numa.h
@@ -32,8 +32,6 @@ static inline const struct cpumask *cpumask_of_node(int node)
void __init arch_numa_init(void);
int __init numa_add_memblk(int nodeid, u64 start, u64 end);
-void __init numa_set_distance(int from, int to, int distance);
-void __init numa_free_distance(void);
void __init early_map_cpu_to_node(unsigned int cpu, int nid);
int __init early_cpu_to_node(int cpu);
void numa_store_cpu_info(unsigned int cpu);
@@ -51,4 +49,8 @@ static inline int early_cpu_to_node(int cpu) { return 0; }
#endif /* CONFIG_NUMA */
+#ifdef CONFIG_NUMA_EMU
+void debug_cpumask_set_cpu(unsigned int cpu, int node, bool enable);
+#endif
+
#endif /* __ASM_GENERIC_NUMA_H */
--
2.43.0
next prev parent reply other threads:[~2024-07-16 11:16 UTC|newest]
Thread overview: 60+ messages / expand[flat|nested] mbox.gz Atom feed top
2024-07-16 11:13 [PATCH 00/17] mm: introduce numa_memblks Mike Rapoport
2024-07-16 11:13 ` [PATCH 01/17] mm: move kernel/numa.c to mm/ Mike Rapoport
2024-07-17 14:35 ` David Hildenbrand
2024-07-19 13:55 ` Jonathan Cameron
2024-07-16 11:13 ` [PATCH 02/17] MIPS: sgi-ip27: make NODE_DATA() the same as on all other architectures Mike Rapoport
2024-07-17 14:32 ` David Hildenbrand
2024-07-19 14:38 ` Jonathan Cameron
2024-07-22 7:34 ` Mike Rapoport
2024-07-16 11:13 ` [PATCH 03/17] MIPS: loongson64: rename __node_data to node_data Mike Rapoport
2024-07-16 13:07 ` Jiaxun Yang
2024-07-17 14:33 ` David Hildenbrand
2024-07-19 15:27 ` Jonathan Cameron
2024-07-16 11:13 ` [PATCH 04/17] arch, mm: move definition of node_data to generic code Mike Rapoport
2024-07-17 14:35 ` David Hildenbrand
2024-07-19 15:39 ` Jonathan Cameron
2024-07-23 0:15 ` Davidlohr Bueso
2024-07-16 11:13 ` [PATCH 05/17] arch, mm: pull out allocation of NODE_DATA " Mike Rapoport
2024-07-17 14:42 ` David Hildenbrand
2024-07-18 7:02 ` Mike Rapoport
2024-07-19 15:07 ` David Hildenbrand
2024-07-19 15:34 ` Mike Rapoport
2024-07-19 15:46 ` David Hildenbrand
2024-07-19 15:51 ` Jonathan Cameron
2024-07-19 16:07 ` David Hildenbrand
2024-07-20 10:24 ` Mike Rapoport
2024-07-19 16:11 ` Jonathan Cameron
2024-07-16 11:13 ` [PATCH 06/17] x86/numa: simplify numa_distance allocation Mike Rapoport
2024-07-19 16:28 ` Jonathan Cameron
2024-07-22 7:51 ` Mike Rapoport
2024-07-16 11:13 ` [PATCH 07/17] x86/numa: move FAKE_NODE_* defines to numa_emu Mike Rapoport
2024-07-19 16:30 ` Jonathan Cameron
2024-07-16 11:13 ` [PATCH 08/17] x86/numa_emu: simplify allocation of phys_dist Mike Rapoport
2024-07-19 16:38 ` Jonathan Cameron
2024-07-16 11:13 ` [PATCH 09/17] x86/numa_emu: split __apicid_to_node update to a helper function Mike Rapoport
2024-07-19 16:47 ` Jonathan Cameron
2024-07-16 11:13 ` [PATCH 10/17] x86/numa_emu: use a helper function to get MAX_DMA32_PFN Mike Rapoport
2024-07-19 16:50 ` Jonathan Cameron
2024-07-16 11:13 ` [PATCH 11/17] x86/numa: numa_{add,remove}_cpu: make cpu parameter unsigned Mike Rapoport
2024-07-19 16:57 ` Jonathan Cameron
2024-07-16 11:13 ` [PATCH 12/17] mm: introduce numa_memblks Mike Rapoport
2024-07-19 18:16 ` Jonathan Cameron
2024-07-22 8:03 ` Mike Rapoport
2024-07-16 11:13 ` [PATCH 13/17] mm: move numa_distance and related code from x86 to numa_memblks Mike Rapoport
2024-07-18 21:46 ` Samuel Holland
2024-07-19 5:55 ` Mike Rapoport
2024-07-19 17:48 ` Jonathan Cameron
2024-07-20 12:25 ` Mike Rapoport
2024-07-16 11:13 ` [PATCH 14/17] mm: introduce numa_emulation Mike Rapoport
2024-07-19 16:03 ` Zi Yan
2024-07-20 12:09 ` Mike Rapoport
2024-07-16 11:13 ` [PATCH 15/17] mm: make numa_memblks more self-contained Mike Rapoport
2024-07-19 18:07 ` Jonathan Cameron
2024-07-20 12:32 ` Mike Rapoport
2024-07-22 8:05 ` Mike Rapoport
2024-07-16 11:13 ` Mike Rapoport [this message]
2024-07-19 18:16 ` [PATCH 16/17] arch_numa: switch over to numa_memblks Jonathan Cameron
2024-07-16 11:13 ` [PATCH 17/17] mm: make range-to-target_node lookup facility a part of numa_memblks Mike Rapoport
2024-07-19 18:19 ` Jonathan Cameron
2024-07-19 13:33 ` [PATCH 00/17] mm: introduce numa_memblks Jonathan Cameron
2024-07-22 8:08 ` Mike Rapoport
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=20240716111346.3676969-17-rppt@kernel.org \
--to=rppt@kernel.org \
--cc=agordeev@linux.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=andreas@gaisler.com \
--cc=arnd@arndb.de \
--cc=bp@alien8.de \
--cc=catalin.marinas@arm.com \
--cc=chenhuacai@kernel.org \
--cc=christophe.leroy@csgroup.eu \
--cc=dan.j.williams@intel.com \
--cc=dave.hansen@linux.intel.com \
--cc=davem@davemloft.net \
--cc=david@redhat.com \
--cc=devicetree@vger.kernel.org \
--cc=glaubitz@physik.fu-berlin.de \
--cc=gor@linux.ibm.com \
--cc=gregkh@linuxfoundation.org \
--cc=hca@linux.ibm.com \
--cc=jiaxun.yang@flygoat.com \
--cc=jonathan.cameron@huawei.com \
--cc=linux-acpi@vger.kernel.org \
--cc=linux-arch@vger.kernel.org \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-cxl@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mips@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=linux-riscv@lists.infradead.org \
--cc=linux-s390@vger.kernel.org \
--cc=linux-sh@vger.kernel.org \
--cc=linuxppc-dev@lists.ozlabs.org \
--cc=loongarch@lists.linux.dev \
--cc=mingo@redhat.com \
--cc=mpe@ellerman.id.au \
--cc=nvdimm@lists.linux.dev \
--cc=palmer@dabbelt.com \
--cc=rafael@kernel.org \
--cc=robh@kernel.org \
--cc=sparclinux@vger.kernel.org \
--cc=tglx@linutronix.de \
--cc=tsbogend@alpha.franken.de \
--cc=will@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;
as well as URLs for NNTP newsgroup(s).