linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Christoph Lameter <cl@linux-foundation.org>
To: Pekka Enberg <penberg@cs.helsinki.fi>
Cc: linux-mm@kvack.org, Tejun Heo <tj@kernel.org>,
	linux-kernel@vger.kernel.org, Nick Piggin <npiggin@suse.de>,
	David Rientjes <rientjes@google.com>
Subject: [S+Q3 02/23] percpu: allow limited allocation before slab is online
Date: Tue, 03 Aug 2010 21:45:16 -0500	[thread overview]
Message-ID: <20100804024524.971222174@linux.com> (raw)
In-Reply-To: 20100804024514.139976032@linux.com

[-- Attachment #1: percpu_early_2 --]
[-- Type: text/plain, Size: 6913 bytes --]

From: Tejun Heo <tj@kernel.org>

This patch updates percpu allocator such that it can serve limited
amount of allocation before slab comes online.  This is primarily to
allow slab to depend on working percpu allocator.

Two parameters, PERCPU_DYNAMIC_EARLY_SIZE and SLOTS, determine how
much memory space and allocation map slots are reserved.  If this
reserved area is exhausted, WARN_ON_ONCE() will trigger and allocation
will fail till slab comes online.

The following changes are made to implement early alloc.

* pcpu_mem_alloc() now checks slab_is_available()

* Chunks are allocated using pcpu_mem_alloc()

* Init paths make sure ai->dyn_size is at least as large as
  PERCPU_DYNAMIC_EARLY_SIZE.

* Initial alloc maps are allocated in __initdata and copied to
  kmalloc'd areas once slab is online.

Signed-off-by: Tejun Heo <tj@kernel.org>
Signed-off-by: Christoph Lameter <cl@linux-foundation.org>
---
 include/linux/percpu.h |   13 ++++++++++++
 init/main.c            |    1
 include/linux/percpu.h |   13 ++++++++++++
 init/main.c            |    1 
 mm/percpu.c            |   52 +++++++++++++++++++++++++++++++++++++------------
 3 files changed, 54 insertions(+), 12 deletions(-)

Index: linux-2.6/mm/percpu.c
===================================================================
--- linux-2.6.orig/mm/percpu.c	2010-07-07 08:47:18.000000000 -0500
+++ linux-2.6/mm/percpu.c	2010-07-07 08:47:19.000000000 -0500
@@ -282,6 +282,9 @@ static void __maybe_unused pcpu_next_pop
  */
 static void *pcpu_mem_alloc(size_t size)
 {
+	if (WARN_ON_ONCE(!slab_is_available()))
+		return NULL;
+
 	if (size <= PAGE_SIZE)
 		return kzalloc(size, GFP_KERNEL);
 	else {
@@ -392,13 +395,6 @@ static int pcpu_extend_area_map(struct p
 	old_size = chunk->map_alloc * sizeof(chunk->map[0]);
 	memcpy(new, chunk->map, old_size);
 
-	/*
-	 * map_alloc < PCPU_DFL_MAP_ALLOC indicates that the chunk is
-	 * one of the first chunks and still using static map.
-	 */
-	if (chunk->map_alloc >= PCPU_DFL_MAP_ALLOC)
-		old = chunk->map;
-
 	chunk->map_alloc = new_alloc;
 	chunk->map = new;
 	new = NULL;
@@ -604,7 +600,7 @@ static struct pcpu_chunk *pcpu_alloc_chu
 {
 	struct pcpu_chunk *chunk;
 
-	chunk = kzalloc(pcpu_chunk_struct_size, GFP_KERNEL);
+	chunk = pcpu_mem_alloc(pcpu_chunk_struct_size);
 	if (!chunk)
 		return NULL;
 
@@ -1109,7 +1105,9 @@ static struct pcpu_alloc_info * __init p
 	memset(group_map, 0, sizeof(group_map));
 	memset(group_cnt, 0, sizeof(group_cnt));
 
-	size_sum = PFN_ALIGN(static_size + reserved_size + dyn_size);
+	/* calculate size_sum and ensure dyn_size is enough for early alloc */
+	size_sum = PFN_ALIGN(static_size + reserved_size +
+			    max_t(size_t, dyn_size, PERCPU_DYNAMIC_EARLY_SIZE));
 	dyn_size = size_sum - static_size - reserved_size;
 
 	/*
@@ -1338,7 +1336,8 @@ int __init pcpu_setup_first_chunk(const 
 				  void *base_addr)
 {
 	static char cpus_buf[4096] __initdata;
-	static int smap[2], dmap[2];
+	static int smap[PERCPU_DYNAMIC_EARLY_SLOTS] __initdata;
+	static int dmap[PERCPU_DYNAMIC_EARLY_SLOTS] __initdata;
 	size_t dyn_size = ai->dyn_size;
 	size_t size_sum = ai->static_size + ai->reserved_size + dyn_size;
 	struct pcpu_chunk *schunk, *dchunk = NULL;
@@ -1361,14 +1360,13 @@ int __init pcpu_setup_first_chunk(const 
 } while (0)
 
 	/* sanity checks */
-	BUILD_BUG_ON(ARRAY_SIZE(smap) >= PCPU_DFL_MAP_ALLOC ||
-		     ARRAY_SIZE(dmap) >= PCPU_DFL_MAP_ALLOC);
 	PCPU_SETUP_BUG_ON(ai->nr_groups <= 0);
 	PCPU_SETUP_BUG_ON(!ai->static_size);
 	PCPU_SETUP_BUG_ON(!base_addr);
 	PCPU_SETUP_BUG_ON(ai->unit_size < size_sum);
 	PCPU_SETUP_BUG_ON(ai->unit_size & ~PAGE_MASK);
 	PCPU_SETUP_BUG_ON(ai->unit_size < PCPU_MIN_UNIT_SIZE);
+	PCPU_SETUP_BUG_ON(ai->dyn_size < PERCPU_DYNAMIC_EARLY_SIZE);
 	PCPU_SETUP_BUG_ON(pcpu_verify_alloc_info(ai) < 0);
 
 	/* process group information and build config tables accordingly */
@@ -1806,3 +1804,33 @@ void __init setup_per_cpu_areas(void)
 		__per_cpu_offset[cpu] = delta + pcpu_unit_offsets[cpu];
 }
 #endif /* CONFIG_HAVE_SETUP_PER_CPU_AREA */
+
+/*
+ * First and reserved chunks are initialized with temporary allocation
+ * map in initdata so that they can be used before slab is online.
+ * This function is called after slab is brought up and replaces those
+ * with properly allocated maps.
+ */
+void __init percpu_init_late(void)
+{
+	struct pcpu_chunk *target_chunks[] =
+		{ pcpu_first_chunk, pcpu_reserved_chunk, NULL };
+	struct pcpu_chunk *chunk;
+	unsigned long flags;
+	int i;
+
+	for (i = 0; (chunk = target_chunks[i]); i++) {
+		int *map;
+		const size_t size = PERCPU_DYNAMIC_EARLY_SLOTS * sizeof(map[0]);
+
+		BUILD_BUG_ON(size > PAGE_SIZE);
+
+		map = pcpu_mem_alloc(size);
+		BUG_ON(!map);
+
+		spin_lock_irqsave(&pcpu_lock, flags);
+		memcpy(map, chunk->map, size);
+		chunk->map = map;
+		spin_unlock_irqrestore(&pcpu_lock, flags);
+	}
+}
Index: linux-2.6/init/main.c
===================================================================
--- linux-2.6.orig/init/main.c	2010-07-07 08:45:22.000000000 -0500
+++ linux-2.6/init/main.c	2010-07-07 08:47:19.000000000 -0500
@@ -532,6 +532,7 @@ static void __init mm_init(void)
 	page_cgroup_init_flatmem();
 	mem_init();
 	kmem_cache_init();
+	percpu_init_late();
 	pgtable_cache_init();
 	vmalloc_init();
 }
Index: linux-2.6/include/linux/percpu.h
===================================================================
--- linux-2.6.orig/include/linux/percpu.h	2010-07-07 08:47:18.000000000 -0500
+++ linux-2.6/include/linux/percpu.h	2010-07-07 08:47:19.000000000 -0500
@@ -45,6 +45,16 @@
 #define PCPU_MIN_UNIT_SIZE		PFN_ALIGN(64 << 10)
 
 /*
+ * Percpu allocator can serve percpu allocations before slab is
+ * initialized which allows slab to depend on the percpu allocator.
+ * The following two parameters decide how much resource to
+ * preallocate for this.  Keep PERCPU_DYNAMIC_RESERVE equal to or
+ * larger than PERCPU_DYNAMIC_EARLY_SIZE.
+ */
+#define PERCPU_DYNAMIC_EARLY_SLOTS	128
+#define PERCPU_DYNAMIC_EARLY_SIZE	(12 << 10)
+
+/*
  * PERCPU_DYNAMIC_RESERVE indicates the amount of free area to piggy
  * back on the first chunk for dynamic percpu allocation if arch is
  * manually allocating and mapping it for faster access (as a part of
@@ -135,6 +145,7 @@ extern bool is_kernel_percpu_address(uns
 #ifndef CONFIG_HAVE_SETUP_PER_CPU_AREA
 extern void __init setup_per_cpu_areas(void);
 #endif
+extern void __init percpu_init_late(void);
 
 #else /* CONFIG_SMP */
 
@@ -148,6 +159,8 @@ static inline bool is_kernel_percpu_addr
 
 static inline void __init setup_per_cpu_areas(void) { }
 
+static inline void __init percpu_init_late(void) { }
+
 static inline void *pcpu_lpage_remapped(void *kaddr)
 {
 	return NULL;

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>

  parent reply	other threads:[~2010-08-04  2:45 UTC|newest]

Thread overview: 47+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2010-08-04  2:45 [S+Q3 00/23] SLUB: The Unified slab allocator (V3) Christoph Lameter
2010-08-04  2:45 ` [S+Q3 01/23] percpu: make @dyn_size always mean min dyn_size in first chunk init functions Christoph Lameter
2010-08-04  2:45 ` Christoph Lameter [this message]
2010-08-04  2:45 ` [S+Q3 03/23] slub: Use a constant for a unspecified node Christoph Lameter
2010-08-04  3:34   ` David Rientjes
2010-08-04 16:15     ` Christoph Lameter
2010-08-05  7:40       ` David Rientjes
2010-08-04  2:45 ` [S+Q3 04/23] SLUB: Constants need UL Christoph Lameter
2010-08-04  2:45 ` [S+Q3 05/23] Subjec Slub: Force no inlining of debug functions Christoph Lameter
2010-08-04  2:45 ` [S+Q3 06/23] slub: Check kasprintf results in kmem_cache_init() Christoph Lameter
2010-08-04  2:45 ` [S+Q3 07/23] slub: Use kmem_cache flags to detect if slab is in debugging mode Christoph Lameter
2010-08-04  2:45 ` [S+Q3 08/23] slub: remove dynamic dma slab allocation Christoph Lameter
2010-08-04  2:45 ` [S+Q3 09/23] slub: Remove static kmem_cache_cpu array for boot Christoph Lameter
2010-08-04  2:45 ` [S+Q3 10/23] slub: Allow removal of slab caches during boot V2 Christoph Lameter
2010-08-04  2:45 ` [S+Q3 11/23] slub: Dynamically size kmalloc cache allocations Christoph Lameter
2010-08-04  2:45 ` [S+Q3 12/23] slub: Extract hooks for memory checkers from hotpaths Christoph Lameter
2010-08-04  2:45 ` [S+Q3 13/23] slub: Move gfpflag masking out of the hotpath Christoph Lameter
2010-08-04  2:45 ` [S+Q3 14/23] slub: Add SLAB style per cpu queueing Christoph Lameter
2010-08-04  2:45 ` [S+Q3 15/23] slub: Allow resizing of per cpu queues Christoph Lameter
2010-08-04  2:45 ` [S+Q3 16/23] slub: Get rid of useless function count_free() Christoph Lameter
2010-08-04  2:45 ` [S+Q3 17/23] slub: Remove MAX_OBJS limitation Christoph Lameter
2010-08-04  2:45 ` [S+Q3 18/23] slub: Drop allocator announcement Christoph Lameter
2010-08-04  2:45 ` [S+Q3 19/23] slub: Object based NUMA policies Christoph Lameter
2010-08-04  2:45 ` [S+Q3 20/23] slub: Shared cache to exploit cross cpu caching abilities Christoph Lameter
2010-08-17  5:52   ` David Rientjes
2010-08-17 17:51     ` Christoph Lameter
2010-08-17 18:42       ` David Rientjes
2010-08-17 18:50         ` Christoph Lameter
2010-08-17 19:02           ` David Rientjes
2010-08-17 19:32             ` Christoph Lameter
2010-08-18 19:32               ` Christoph Lameter
2010-08-04  2:45 ` [S+Q3 21/23] slub: Support Alien Caches Christoph Lameter
2010-08-04  2:45 ` [S+Q3 22/23] slub: Cached object expiration Christoph Lameter
2010-08-04  2:45 ` [S+Q3 23/23] vmscan: Tie slub object expiration into page reclaim Christoph Lameter
2010-08-04  4:39 ` [S+Q3 00/23] SLUB: The Unified slab allocator (V3) David Rientjes
2010-08-04 16:17   ` Christoph Lameter
2010-08-05  8:38     ` David Rientjes
2010-08-05 17:33       ` Christoph Lameter
2010-08-17  4:56         ` David Rientjes
2010-08-17  7:55           ` Tejun Heo
2010-08-17 13:56             ` Christoph Lameter
2010-08-17 17:23           ` Christoph Lameter
2010-08-17 17:29             ` Christoph Lameter
2010-08-17 18:02             ` David Rientjes
2010-08-17 18:47               ` Christoph Lameter
2010-08-17 18:54                 ` David Rientjes
2010-08-17 19:34                   ` 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=20100804024524.971222174@linux.com \
    --to=cl@linux-foundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=npiggin@suse.de \
    --cc=penberg@cs.helsinki.fi \
    --cc=rientjes@google.com \
    --cc=tj@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).