From: Tejun Heo <tj@kernel.org>
To: mingo@elte.hu, rusty@rustcorp.com.au, tglx@linutronix.de,
x86@kernel.org, linux-kernel@vger.kernel.org, hpa@zytor.com,
jeremy@goop.org, cpw@sgi.com, nickpiggin@yahoo.com.au,
ink@jurassic.park.msu.ru
Cc: Tejun Heo <tj@kernel.org>
Subject: [PATCH 06/10] percpu: remove unit_size power-of-2 restriction
Date: Tue, 24 Feb 2009 12:11:37 +0900 [thread overview]
Message-ID: <1235445101-7882-7-git-send-email-tj@kernel.org> (raw)
In-Reply-To: <1235445101-7882-1-git-send-email-tj@kernel.org>
Impact: allow unit_size to be arbitrary multiple of PAGE_SIZE
In dynamic percpu allocator, there is no reason the unit size should
be power of two. Remove the restriction.
As non-power-of-two unit size means that empty chunks fall into the
same slot index as lightly occupied chunks which is bad for reclaming.
Reserve an extra slot for empty chunks.
Signed-off-by: Tejun Heo <tj@kernel.org>
---
mm/percpu.c | 33 +++++++++++++++++++--------------
1 files changed, 19 insertions(+), 14 deletions(-)
diff --git a/mm/percpu.c b/mm/percpu.c
index 41e7a5f..d9e6e5d 100644
--- a/mm/percpu.c
+++ b/mm/percpu.c
@@ -67,7 +67,7 @@
#include <asm/cacheflush.h>
#include <asm/tlbflush.h>
-#define PCPU_MIN_UNIT_PAGES_SHIFT 4 /* also max alloc size */
+#define PCPU_MIN_UNIT_PAGES 16 /* max alloc size in pages */
#define PCPU_SLOT_BASE_SHIFT 5 /* 1-31 shares the same slot */
#define PCPU_DFL_MAP_ALLOC 16 /* start a map with 16 ents */
@@ -83,9 +83,7 @@ struct pcpu_chunk {
struct page *page[]; /* #cpus * UNIT_PAGES */
};
-static int pcpu_unit_pages_shift;
static int pcpu_unit_pages;
-static int pcpu_unit_shift;
static int pcpu_unit_size;
static int pcpu_chunk_size;
static int pcpu_nr_slots;
@@ -117,12 +115,19 @@ static DEFINE_MUTEX(pcpu_mutex);
static struct list_head *pcpu_slot; /* chunk list slots */
static struct rb_root pcpu_addr_root = RB_ROOT; /* chunks by address */
-static int pcpu_size_to_slot(int size)
+static int __pcpu_size_to_slot(int size)
{
int highbit = fls(size); /* size is in bytes */
return max(highbit - PCPU_SLOT_BASE_SHIFT + 2, 1);
}
+static int pcpu_size_to_slot(int size)
+{
+ if (size == pcpu_unit_size)
+ return pcpu_nr_slots - 1;
+ return __pcpu_size_to_slot(size);
+}
+
static int pcpu_chunk_slot(const struct pcpu_chunk *chunk)
{
if (chunk->free_size < sizeof(int) || chunk->contig_hint < sizeof(int))
@@ -133,7 +138,7 @@ static int pcpu_chunk_slot(const struct pcpu_chunk *chunk)
static int pcpu_page_idx(unsigned int cpu, int page_idx)
{
- return (cpu << pcpu_unit_pages_shift) + page_idx;
+ return cpu * pcpu_unit_pages + page_idx;
}
static struct page **pcpu_chunk_pagep(struct pcpu_chunk *chunk,
@@ -659,7 +664,7 @@ static int pcpu_populate_chunk(struct pcpu_chunk *chunk, int off, int size)
goto err;
for_each_possible_cpu(cpu)
- memset(chunk->vm->addr + (cpu << pcpu_unit_shift) + off, 0,
+ memset(chunk->vm->addr + cpu * pcpu_unit_size + off, 0,
size);
return 0;
@@ -722,7 +727,7 @@ void *__alloc_percpu(size_t size, size_t align)
struct pcpu_chunk *chunk;
int slot, off;
- if (unlikely(!size || size > PAGE_SIZE << PCPU_MIN_UNIT_PAGES_SHIFT ||
+ if (unlikely(!size || size > PCPU_MIN_UNIT_PAGES * PAGE_SIZE ||
align > PAGE_SIZE)) {
WARN(true, "illegal size (%zu) or align (%zu) for "
"percpu allocation\n", size, align);
@@ -840,19 +845,19 @@ size_t __init pcpu_setup_static(pcpu_populate_pte_fn_t populate_pte_fn,
unsigned int cpu;
int err, i;
- pcpu_unit_pages_shift = max_t(int, PCPU_MIN_UNIT_PAGES_SHIFT,
- order_base_2(cpu_size) - PAGE_SHIFT);
+ pcpu_unit_pages = max_t(int, PCPU_MIN_UNIT_PAGES, PFN_UP(cpu_size));
pcpu_static_size = cpu_size;
- pcpu_unit_pages = 1 << pcpu_unit_pages_shift;
- pcpu_unit_shift = PAGE_SHIFT + pcpu_unit_pages_shift;
- pcpu_unit_size = 1 << pcpu_unit_shift;
+ pcpu_unit_size = pcpu_unit_pages << PAGE_SHIFT;
pcpu_chunk_size = num_possible_cpus() * pcpu_unit_size;
- pcpu_nr_slots = pcpu_size_to_slot(pcpu_unit_size) + 1;
pcpu_chunk_struct_size = sizeof(struct pcpu_chunk)
+ num_possible_cpus() * pcpu_unit_pages * sizeof(struct page *);
- /* allocate chunk slots */
+ /*
+ * Allocate chunk slots. The additional last slot is for
+ * empty chunks.
+ */
+ pcpu_nr_slots = __pcpu_size_to_slot(pcpu_unit_size) + 2;
pcpu_slot = alloc_bootmem(pcpu_nr_slots * sizeof(pcpu_slot[0]));
for (i = 0; i < pcpu_nr_slots; i++)
INIT_LIST_HEAD(&pcpu_slot[i]);
--
1.6.0.2
next prev parent reply other threads:[~2009-02-24 3:14 UTC|newest]
Thread overview: 45+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-02-24 3:11 [PATCHSET x86/core/percpu] improve the first percpu chunk allocation Tejun Heo
2009-02-24 3:11 ` [PATCH 01/10] percpu: fix pcpu_chunk_struct_size Tejun Heo
2009-02-24 3:11 ` [PATCH 02/10] bootmem: clean up arch-specific bootmem wrapping Tejun Heo
2009-02-24 11:30 ` Johannes Weiner
2009-02-24 11:39 ` Tejun Heo
2009-02-24 3:11 ` [PATCH 03/10] bootmem: reorder interface functions and add a missing one Tejun Heo
2009-02-24 3:11 ` [PATCH 04/10] vmalloc: add @align to vm_area_register_early() Tejun Heo
2009-02-24 3:11 ` [PATCH 05/10] x86: update populate_extra_pte() and add populate_extra_pmd() Tejun Heo
2009-02-24 3:11 ` Tejun Heo [this message]
2009-02-24 3:11 ` [PATCH 07/10] percpu: give more latitude to arch specific first chunk initialization Tejun Heo
2009-02-24 3:11 ` [PATCH 08/10] x86: separate out setup_pcpu_4k() from setup_per_cpu_areas() Tejun Heo
2009-02-24 3:11 ` [PATCH 09/10] x86: add embedding percpu first chunk allocator Tejun Heo
2009-02-24 3:11 ` [PATCH 10/10] x86: add remapping " Tejun Heo
2009-02-24 9:57 ` [PATCHSET x86/core/percpu] improve the first percpu chunk allocation Ingo Molnar
2009-02-24 11:48 ` Tejun Heo
2009-02-24 12:40 ` Ingo Molnar
2009-02-24 13:27 ` Tejun Heo
2009-02-24 14:12 ` Ingo Molnar
2009-02-24 14:37 ` Tejun Heo
2009-02-24 15:15 ` Ingo Molnar
2009-02-24 23:33 ` Tejun Heo
2009-03-04 0:03 ` Rusty Russell
2009-03-04 0:15 ` H. Peter Anvin
2009-03-04 0:50 ` Ingo Molnar
2009-02-24 12:51 ` Ingo Molnar
2009-02-24 14:47 ` Tejun Heo
2009-02-24 15:19 ` Ingo Molnar
2009-02-24 15:30 ` Nick Piggin
2009-02-24 13:02 ` Ingo Molnar
2009-02-24 14:40 ` Tejun Heo
2009-02-24 20:17 ` Ingo Molnar
2009-02-24 20:51 ` Ingo Molnar
2009-02-24 21:02 ` Yinghai Lu
2009-02-24 21:12 ` [PATCH] x86: check range in reserve_early() -v2 Yinghai Lu
2009-02-24 21:16 ` [PATCHSET x86/core/percpu] improve the first percpu chunk allocation Ingo Molnar
2009-02-25 2:09 ` [PATCH x86/core/percpu 1/2] x86, percpu: fix minor bugs in setup_percpu.c Tejun Heo
2009-02-25 2:10 ` [PATCH x86/core/percpu 2/2] x86: convert cacheflush macros inline functions Tejun Heo
2009-02-25 2:23 ` [PATCHSET x86/core/percpu] improve the first percpu chunk allocation Tejun Heo
2009-02-25 2:56 ` Tejun Heo
2009-02-25 12:59 ` Ingo Molnar
2009-02-25 13:43 ` WARNING: at include/linux/percpu.h:159 __create_workqueue_key+0x1f6/0x220() Ingo Molnar
2009-02-26 2:03 ` [PATCH core/percpu] percpu: fix too low alignment restriction on UP Tejun Heo
2009-02-26 3:26 ` Ingo Molnar
2009-02-25 6:40 ` [PATCHSET x86/core/percpu] improve the first percpu chunk allocation Rusty Russell
2009-02-25 12:54 ` 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=1235445101-7882-7-git-send-email-tj@kernel.org \
--to=tj@kernel.org \
--cc=cpw@sgi.com \
--cc=hpa@zytor.com \
--cc=ink@jurassic.park.msu.ru \
--cc=jeremy@goop.org \
--cc=linux-kernel@vger.kernel.org \
--cc=mingo@elte.hu \
--cc=nickpiggin@yahoo.com.au \
--cc=rusty@rustcorp.com.au \
--cc=tglx@linutronix.de \
--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