From: Yang Shi <yang@os.amperecomputing.com>
To: cl@gentwo.org, dennis@kernel.org, tj@kernel.org,
urezki@gmail.com, catalin.marinas@arm.com, will@kernel.org,
ryan.roberts@arm.com, david@kernel.org,
akpm@linux-foundation.org, hca@linux.ibm.com, gor@linux.ibm.com,
agordeev@linux.ibm.com
Cc: yang@os.amperecomputing.com, linux-mm@kvack.org,
linux-arm-kernel@lists.infradead.org,
linux-kernel@vger.kernel.org
Subject: [PATCH 06/11] mm: percpu: set up first chunk and reserve chunk
Date: Wed, 29 Apr 2026 10:04:34 -0700 [thread overview]
Message-ID: <20260429170758.3018959-7-yang@os.amperecomputing.com> (raw)
In-Reply-To: <20260429170758.3018959-1-yang@os.amperecomputing.com>
Set up the first chunk and reserve chunk with local percpu map.
Signed-off-by: Yang Shi <yang@os.amperecomputing.com>
---
include/linux/percpu.h | 2 +-
mm/percpu-internal.h | 2 ++
mm/percpu.c | 24 +++++++++++++++---------
3 files changed, 18 insertions(+), 10 deletions(-)
diff --git a/include/linux/percpu.h b/include/linux/percpu.h
index 85bf8dd9f087..dba050f5b548 100644
--- a/include/linux/percpu.h
+++ b/include/linux/percpu.h
@@ -113,7 +113,7 @@ extern struct pcpu_alloc_info * __init pcpu_alloc_alloc_info(int nr_groups,
extern void __init pcpu_free_alloc_info(struct pcpu_alloc_info *ai);
extern void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
- void *base_addr);
+ void *base_addr, void *local_base);
extern int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
size_t atom_size,
diff --git a/mm/percpu-internal.h b/mm/percpu-internal.h
index b33d1f5aba1b..64b48b99ac06 100644
--- a/mm/percpu-internal.h
+++ b/mm/percpu-internal.h
@@ -64,6 +64,8 @@ struct pcpu_chunk {
* chunk_md.
*/
void *base_addr ____cacheline_aligned_in_smp;
+ /* percpu local base address of the chunk */
+ void *local_base;
unsigned long *alloc_map; /* allocation map */
struct pcpu_block_md *md_blocks; /* metadata blocks */
diff --git a/mm/percpu.c b/mm/percpu.c
index 59682b77089c..5148c5ccf9e3 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -1349,15 +1349,16 @@ static void pcpu_init_md_blocks(struct pcpu_chunk *chunk)
* Chunk serving the region at @tmp_addr of @map_size.
*/
static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr,
- int map_size)
+ unsigned long local_tmp, int map_size)
{
struct pcpu_chunk *chunk;
- unsigned long aligned_addr;
+ unsigned long aligned_addr, aligned_local;
int start_offset, offset_bits, region_size, region_bits;
size_t alloc_size;
/* region calculations */
aligned_addr = tmp_addr & PAGE_MASK;
+ aligned_local = local_tmp & PAGE_MASK;
start_offset = tmp_addr - aligned_addr;
region_size = ALIGN(start_offset + map_size, PAGE_SIZE);
@@ -1370,6 +1371,7 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr,
INIT_LIST_HEAD(&chunk->list);
chunk->base_addr = (void *)aligned_addr;
+ chunk->local_base = (void *)aligned_local;
chunk->start_offset = start_offset;
chunk->end_offset = region_size - chunk->start_offset - map_size;
@@ -2562,7 +2564,7 @@ static void pcpu_dump_alloc_info(const char *lvl,
* and available for dynamic allocation like any other chunk.
*/
void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
- void *base_addr)
+ void *base_addr, void *local_base)
{
size_t size_sum = ai->static_size + ai->reserved_size + ai->dyn_size;
size_t static_size, dyn_size;
@@ -2572,7 +2574,7 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
unsigned int cpu;
int *unit_map;
int group, unit, i;
- unsigned long tmp_addr;
+ unsigned long tmp_addr, local_tmp;
size_t alloc_size;
#define PCPU_SETUP_BUG_ON(cond) do { \
@@ -2713,11 +2715,13 @@ void __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai,
* chunk.
*/
tmp_addr = (unsigned long)base_addr + static_size;
+ local_tmp = (unsigned long)local_base + static_size;
if (ai->reserved_size)
- pcpu_reserved_chunk = pcpu_alloc_first_chunk(tmp_addr,
+ pcpu_reserved_chunk = pcpu_alloc_first_chunk(tmp_addr, local_tmp,
ai->reserved_size);
tmp_addr = (unsigned long)base_addr + static_size + ai->reserved_size;
- pcpu_first_chunk = pcpu_alloc_first_chunk(tmp_addr, dyn_size);
+ local_tmp = (unsigned long)local_base + static_size + ai->reserved_size;
+ pcpu_first_chunk = pcpu_alloc_first_chunk(tmp_addr, local_tmp, dyn_size);
pcpu_nr_empty_pop_pages = pcpu_first_chunk->nr_empty_pop_pages;
pcpu_chunk_relocate(pcpu_first_chunk, -1);
@@ -3108,7 +3112,7 @@ int __init pcpu_embed_first_chunk(size_t reserved_size, size_t dyn_size,
PFN_DOWN(size_sum), ai->static_size, ai->reserved_size,
ai->dyn_size, ai->unit_size);
- pcpu_setup_first_chunk(ai, base);
+ pcpu_setup_first_chunk(ai, base, NULL);
goto out_free;
out_free_areas:
@@ -3256,6 +3260,8 @@ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t
vm.flags = VM_ALLOC;
vm.size = num_possible_cpus() * ai->unit_size;
vm_area_register_early(&vm, PAGE_SIZE);
+
+ pcpu_vm.addr = NULL;
#endif
for (unit = 0; unit < num_possible_cpus(); unit++) {
@@ -3290,7 +3296,7 @@ int __init pcpu_page_first_chunk(size_t reserved_size, pcpu_fc_cpu_to_node_fn_t
unit_pages, psize_str, ai->static_size,
ai->reserved_size, ai->dyn_size);
- pcpu_setup_first_chunk(ai, vm.addr);
+ pcpu_setup_first_chunk(ai, vm.addr, pcpu_vm.addr);
goto out_free_ar;
enomem:
@@ -3372,7 +3378,7 @@ void __init setup_per_cpu_areas(void)
ai->groups[0].nr_units = 1;
ai->groups[0].cpu_map[0] = 0;
- pcpu_setup_first_chunk(ai, fc);
+ pcpu_setup_first_chunk(ai, fc, NULL);
pcpu_free_alloc_info(ai);
}
--
2.47.0
next prev parent reply other threads:[~2026-04-29 17:09 UTC|newest]
Thread overview: 13+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-04-29 17:04 [RFC v1 PATCH 0/11] Optimize this_cpu_*() ops for non-x86 (ARM64 for this series) Yang Shi
2026-04-29 17:04 ` [PATCH 01/11] arm64: mm: enable percpu kernel page table Yang Shi
2026-04-29 17:04 ` [PATCH 02/11] arm64: mm: define percpu virtual space area Yang Shi
2026-04-29 17:04 ` [PATCH 03/11] arm64: smp: define setup_per_cpu_areas() Yang Shi
2026-04-29 17:04 ` [PATCH 04/11] mm: percpu: prepare to use dedicated percpu area Yang Shi
2026-04-29 17:04 ` [PATCH 05/11] arm64: mm: map local percpu first chunk Yang Shi
2026-04-29 17:04 ` Yang Shi [this message]
2026-04-29 17:04 ` [PATCH 07/11] arm64: mm: introduce __per_cpu_local_off Yang Shi
2026-04-29 17:04 ` [PATCH 08/11] vmalloc: pass in pgd pointer for vmap{__vunmap}_range_noflush() Yang Shi
2026-04-29 17:04 ` [PATCH 09/11] mm: percpu: allocate and free local percpu vm area Yang Shi
2026-04-29 17:04 ` [PATCH 10/11] arm64: kconfig: select HAVE_LOCAL_PER_CPU_MAP Yang Shi
2026-04-29 17:04 ` [PATCH 11/11] arm64: percpu: use local percpu for this_cpu_*() APIs Yang Shi
2026-04-30 19:02 ` [RFC v1 PATCH 0/11] Optimize this_cpu_*() ops for non-x86 (ARM64 for this series) Yang Shi
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=20260429170758.3018959-7-yang@os.amperecomputing.com \
--to=yang@os.amperecomputing.com \
--cc=agordeev@linux.ibm.com \
--cc=akpm@linux-foundation.org \
--cc=catalin.marinas@arm.com \
--cc=cl@gentwo.org \
--cc=david@kernel.org \
--cc=dennis@kernel.org \
--cc=gor@linux.ibm.com \
--cc=hca@linux.ibm.com \
--cc=linux-arm-kernel@lists.infradead.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux-mm@kvack.org \
--cc=ryan.roberts@arm.com \
--cc=tj@kernel.org \
--cc=urezki@gmail.com \
--cc=will@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