From: Christoph Lameter <clameter@sgi.com>
To: akpm@linux-foundation.org
Cc: linux-arch@vger.kernel.org, linux-kernel@vger.kernel.org,
David Miller <davem@davemloft.net>,
Eric Dumazet <dada1@cosmosbay.com>,
Peter Zijlstra <peterz@infradead.org>
Subject: [patch 06/30] cpu alloc: x86 support
Date: Fri, 16 Nov 2007 15:09:26 -0800 [thread overview]
Message-ID: <20071116231103.528413375@sgi.com> (raw)
In-Reply-To: 20071116230920.278761667@sgi.com
[-- Attachment #1: cpu_alloc_x86_support --]
[-- Type: text/plain, Size: 6345 bytes --]
64 bit:
Set up a cpu area that allows the use of up 16MB for each processor.
Cpu memory use can grow a bit. F.e. if we assume that a pageset
occupies 64 bytes of memory and we have 3 zones in each of 1024 nodes
then we need 3 * 1k * 16k = 50 million pagesets or 3096 pagesets per
processor. This results in a total of 3.2 GB of page structs.
Each cpu needs around 200k of cpu storage for the page allocator alone.
So its a worth it to use a 2M huge mapping here.
For the UP and SMP case map the area using 4k ptes. Typical use of per cpu
data is around 16k for UP and SMP configurations. It goes up to 45k when the
per cpu area is managed by cpu_alloc (see special x86_64 patchset).
Allocating in 2M segments would be overkill.
For NUMA map the area using 2M PMDs. A large NUMA system may use
lots of cpu data for the page allocator data alone. We typically
have large amounts of memory around on those size. Using a 2M page size
reduces TLB pressure for that case.
Some numbers for envisioned maximum configurations of NUMA systems:
4k cpu configurations with 1k nodes:
4096 * 16MB = 64TB of virtual space.
Maximum theoretical configuration 16384 processors 1k nodes:
16384 * 16MB = 256TB of virtual space.
Both fit within the established limits established.
32 bit:
Setup a 256 kB area for the cpu areas below the FIXADDR area.
The use of the cpu alloc area is pretty minimal on i386. An 8p system
with no extras uses only ~8kb. So 256kb should be plenty. A configuration
that supports up to 8 processors takes up 2MB of the scarce
virtual address space
Signed-off-by: Christoph Lameter <clameter@sgi.com>
---
arch/x86/Kconfig | 15 +++++++++++++++
arch/x86/mm/init_32.c | 3 +++
arch/x86/mm/init_64.c | 38 ++++++++++++++++++++++++++++++++++++++
include/asm-x86/pgtable_32.h | 7 +++++--
include/asm-x86/pgtable_64.h | 1 +
5 files changed, 62 insertions(+), 2 deletions(-)
Index: linux-2.6/arch/x86/mm/init_64.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/init_64.c 2007-11-15 21:24:47.059904335 -0800
+++ linux-2.6/arch/x86/mm/init_64.c 2007-11-15 21:25:18.578584246 -0800
@@ -781,3 +781,41 @@ int __meminit vmemmap_populate(struct pa
return 0;
}
#endif
+
+#ifdef CONFIG_NUMA
+int __meminit cpu_area_populate(void *start, unsigned long size,
+ gfp_t flags, int node)
+{
+ unsigned long addr = (unsigned long)start;
+ unsigned long end = addr + size;
+ unsigned long next;
+ pgd_t *pgd;
+ pud_t *pud;
+ pmd_t *pmd;
+
+ for (; addr < end; addr = next) {
+ next = pmd_addr_end(addr, end);
+
+ pgd = cpu_area_pgd_populate(addr, flags, node);
+ if (!pgd)
+ return -ENOMEM;
+ pud = cpu_area_pud_populate(pgd, addr, flags, node);
+ if (!pud)
+ return -ENOMEM;
+
+ pmd = pmd_offset(pud, addr);
+ if (pmd_none(*pmd)) {
+ pte_t entry;
+ void *p = cpu_area_alloc_block(PMD_SIZE, flags, node);
+ if (!p)
+ return -ENOMEM;
+
+ entry = pfn_pte(__pa(p) >> PAGE_SHIFT, PAGE_KERNEL);
+ mk_pte_huge(entry);
+ set_pmd(pmd, __pmd(pte_val(entry)));
+ }
+ }
+
+ return 0;
+}
+#endif
Index: linux-2.6/include/asm-x86/pgtable_64.h
===================================================================
--- linux-2.6.orig/include/asm-x86/pgtable_64.h 2007-11-15 21:24:47.079904686 -0800
+++ linux-2.6/include/asm-x86/pgtable_64.h 2007-11-15 21:25:18.578584246 -0800
@@ -138,6 +138,7 @@ static inline pte_t ptep_get_and_clear_f
#define VMALLOC_START _AC(0xffffc20000000000, UL)
#define VMALLOC_END _AC(0xffffe1ffffffffff, UL)
#define VMEMMAP_START _AC(0xffffe20000000000, UL)
+#define CPU_AREA_BASE _AC(0xfffff20000000000, UL)
#define MODULES_VADDR _AC(0xffffffff88000000, UL)
#define MODULES_END _AC(0xfffffffffff00000, UL)
#define MODULES_LEN (MODULES_END - MODULES_VADDR)
Index: linux-2.6/arch/x86/Kconfig
===================================================================
--- linux-2.6.orig/arch/x86/Kconfig 2007-11-15 21:24:47.075904383 -0800
+++ linux-2.6/arch/x86/Kconfig 2007-11-15 21:25:18.578584246 -0800
@@ -163,6 +163,21 @@ config X86_TRAMPOLINE
config KTIME_SCALAR
def_bool X86_32
+
+config CPU_AREA_VIRTUAL
+ bool
+ default y
+
+config CPU_AREA_ORDER
+ int
+ default "16" if X86_64
+ default "6" if X86_32
+
+config CPU_AREA_ALLOC_ORDER
+ int
+ default "9" if NUMA && X86_64
+ default "0" if !NUMA || X86_32
+
source "init/Kconfig"
menu "Processor type and features"
Index: linux-2.6/arch/x86/mm/init_32.c
===================================================================
--- linux-2.6.orig/arch/x86/mm/init_32.c 2007-11-15 21:24:47.067904108 -0800
+++ linux-2.6/arch/x86/mm/init_32.c 2007-11-15 21:25:18.578584246 -0800
@@ -674,6 +674,7 @@ void __init mem_init(void)
#if 1 /* double-sanity-check paranoia */
printk("virtual kernel memory layout:\n"
" fixmap : 0x%08lx - 0x%08lx (%4ld kB)\n"
+ " cpu area: 0x%08lx - 0x%08lx (%4ld kb)\n"
#ifdef CONFIG_HIGHMEM
" pkmap : 0x%08lx - 0x%08lx (%4ld kB)\n"
#endif
@@ -684,6 +685,8 @@ void __init mem_init(void)
" .text : 0x%08lx - 0x%08lx (%4ld kB)\n",
FIXADDR_START, FIXADDR_TOP,
(FIXADDR_TOP - FIXADDR_START) >> 10,
+ CPU_AREA_BASE, FIXADDR_START,
+ (FIXADDR_START - CPU_AREA_BASE) >> 10,
#ifdef CONFIG_HIGHMEM
PKMAP_BASE, PKMAP_BASE+LAST_PKMAP*PAGE_SIZE,
Index: linux-2.6/include/asm-x86/pgtable_32.h
===================================================================
--- linux-2.6.orig/include/asm-x86/pgtable_32.h 2007-11-15 21:24:47.087904440 -0800
+++ linux-2.6/include/asm-x86/pgtable_32.h 2007-11-15 21:25:18.578584246 -0800
@@ -79,11 +79,14 @@ void paging_init(void);
#define VMALLOC_START (((unsigned long) high_memory + \
2*VMALLOC_OFFSET-1) & ~(VMALLOC_OFFSET-1))
#ifdef CONFIG_HIGHMEM
-# define VMALLOC_END (PKMAP_BASE-2*PAGE_SIZE)
+# define CPU_AREA_BASE (PKMAP_BASE - NR_CPUS * \
+ (1 << (CONFIG_CPU_AREA_ORDER + PAGE_SHIFT)))
#else
-# define VMALLOC_END (FIXADDR_START-2*PAGE_SIZE)
+# define CPU_AREA_BASE (FIXADDR_START - NR_CPUS * \
+ (1 << (CONFIG_CPU_AREA_ORDER + PAGE_SHIFT)))
#endif
+#define VMALLOC_END (CPU_AREA_BASE - 2 * PAGE_SIZE)
/*
* _PAGE_PSE set in the page directory entry just means that
* the page directory entry points directly to a 4MB-aligned block of
--
next prev parent reply other threads:[~2007-11-16 23:11 UTC|newest]
Thread overview: 34+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-11-16 23:09 [patch 00/30] cpu alloc v2: Optimize by removing arrays of pointers to per cpu objects Christoph Lameter
2007-11-16 23:09 ` [patch 01/30] cpu alloc: Simple version of the allocator (static allocations) Christoph Lameter
2007-11-16 23:09 ` [patch 02/30] cpu alloc: Use in SLUB Christoph Lameter
2007-11-16 23:09 ` [patch 03/30] cpu alloc: Remove SLUB fields Christoph Lameter
2007-11-16 23:09 ` [patch 04/30] cpu alloc: page allocator conversion Christoph Lameter
2007-11-16 23:09 ` [patch 05/30] cpu_alloc: Implement dynamically extendable cpu areas Christoph Lameter
2007-11-16 23:09 ` Christoph Lameter [this message]
2007-11-16 23:09 ` [patch 07/30] cpu alloc: IA64 support Christoph Lameter
2007-11-16 23:32 ` Luck, Tony
2007-11-17 0:05 ` Christoph Lameter
2007-11-16 23:09 ` [patch 08/30] cpu_alloc: Sparc64 support Christoph Lameter
2007-11-16 23:09 ` [patch 09/30] cpu alloc: percpu_counter conversion Christoph Lameter
2007-11-16 23:09 ` [patch 10/30] cpu alloc: crash_notes conversion Christoph Lameter
2007-11-16 23:09 ` [patch 11/30] cpu alloc: workqueue conversion Christoph Lameter
2007-11-16 23:09 ` [patch 12/30] cpu alloc: ACPI cstate handling conversion Christoph Lameter
2007-11-16 23:09 ` [patch 13/30] cpu alloc: genhd statistics conversion Christoph Lameter
2007-11-16 23:09 ` [patch 14/30] cpu alloc: blktrace conversion Christoph Lameter
2007-11-16 23:09 ` [patch 15/30] cpu alloc: SRCU Christoph Lameter
2007-11-16 23:09 ` [patch 16/30] cpu alloc: XFS counters Christoph Lameter
2007-11-19 12:58 ` Christoph Hellwig
2007-11-16 23:09 ` [patch 17/30] cpu alloc: NFS statistics Christoph Lameter
2007-11-16 23:09 ` [patch 18/30] cpu alloc: neigbour statistics Christoph Lameter
2007-11-16 23:09 ` [patch 19/30] cpu alloc: tcp statistics Christoph Lameter
2007-11-16 23:09 ` [patch 20/30] cpu alloc: convert scatches Christoph Lameter
2007-11-16 23:09 ` [patch 21/30] cpu alloc: dmaengine conversion Christoph Lameter
2007-11-16 23:09 ` [patch 22/30] cpu alloc: convert loopback statistics Christoph Lameter
2007-11-16 23:09 ` [patch 23/30] cpu alloc: veth conversion Christoph Lameter
2007-11-16 23:09 ` [patch 24/30] cpu alloc: Chelsio statistics conversion Christoph Lameter
2007-11-16 23:09 ` [patch 25/30] cpu alloc: convert mib handling to cpu alloc Christoph Lameter
2007-11-16 23:09 ` [patch 26/30] cpu_alloc: convert network sockets Christoph Lameter
2007-11-16 23:09 ` [patch 27/30] cpu alloc: Explicitly code allocpercpu calls in iucv Christoph Lameter
2007-11-16 23:09 ` [patch 28/30] cpu alloc: Use for infiniband Christoph Lameter
2007-11-16 23:09 ` [patch 29/30] cpu alloc: Use in the crypto subsystem Christoph Lameter
2007-11-16 23:09 ` [patch 30/30] cpu alloc: Remove the allocpercpu functionality Christoph Lameter
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=20071116231103.528413375@sgi.com \
--to=clameter@sgi.com \
--cc=akpm@linux-foundation.org \
--cc=dada1@cosmosbay.com \
--cc=davem@davemloft.net \
--cc=linux-arch@vger.kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=peterz@infradead.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).