[GIT PULL] x86/mm changes for v3.3

From: Ingo Molnar
Date: Thu Jan 05 2012 - 10:17:41 EST

Linus,

Please pull the latest x86-mm-for-linus git tree from:

git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git x86-mm-for-linus


out-of-topic modifications in x86-mm-for-linus:
-----------------------------------------------
include/linux/mm.h # 54c29c6: mm, x86: Remove debug_pagealloc_e
mm/debug-pagealloc.c # 54c29c6: mm, x86: Remove debug_pagealloc_e

Thanks,

Ingo

------------------>
H Hartley Sweeten (1):
arch/x86/kernel/e820.c: quiet sparse noise about plain integer as NULL pointer

Ludwig Nussel (1):
x86: Fix mmap random address range

Mike Ditto (1):
arch/x86/kernel/e820.c: Eliminate bubble sort from sanitize_e820_map()

Pekka Enberg (7):
x86, mm: Use MAX_DMA_PFN for ZONE_DMA on 32-bit
x86, mm: Move zone init from paging_init() on 64-bit
x86, mm: Use max_pfn instead of highend_pfn
x86, mm: Wrap ZONE_DMA32 with CONFIG_ZONE_DMA32
x86, mm: Use max_low_pfn for ZONE_NORMAL on 64-bit
x86, mm: Prepare zone_sizes_init() for unification
x86, mm: Unify zone_sizes_init()

Petr Holasek (1):
x86/numa: Add constraints check for nid parameters

Stanislaw Gruszka (2):
x86/mm: Initialize high mem before free_all_bootmem()
mm, x86: Remove debug_pagealloc_enabled


arch/x86/include/asm/init.h | 2 +
arch/x86/kernel/e820.c | 59 +++++++++++++++++-------------------------
arch/x86/mm/init.c | 23 ++++++++++++++++
arch/x86/mm/init_32.c | 29 ++++++++-------------
arch/x86/mm/init_64.c | 11 +-------
arch/x86/mm/mmap.c | 4 +-
arch/x86/mm/numa.c | 10 ++++---
arch/x86/mm/pageattr.c | 6 ----
include/linux/mm.h | 10 -------
init/main.c | 5 ---
mm/debug-pagealloc.c | 3 --
11 files changed, 69 insertions(+), 93 deletions(-)

diff --git a/arch/x86/include/asm/init.h b/arch/x86/include/asm/init.h
index 8dbe353..adcc0ae 100644
--- a/arch/x86/include/asm/init.h
+++ b/arch/x86/include/asm/init.h
@@ -5,6 +5,8 @@
extern void __init early_ioremap_page_table_range_init(void);
#endif

+extern void __init zone_sizes_init(void);
+
extern unsigned long __init
kernel_physical_mapping_init(unsigned long start,
unsigned long end,
diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c
index 303a0e4..d6bd853 100644
--- a/arch/x86/kernel/e820.c
+++ b/arch/x86/kernel/e820.c
@@ -19,6 +19,7 @@
#include <linux/acpi.h>
#include <linux/firmware-map.h>
#include <linux/memblock.h>
+#include <linux/sort.h>

#include <asm/e820.h>
#include <asm/proto.h>
@@ -227,22 +228,38 @@ void __init e820_print_map(char *who)
* ____________________33__
* ______________________4_
*/
+struct change_member {
+ struct e820entry *pbios; /* pointer to original bios entry */
+ unsigned long long addr; /* address for this change point */
+};
+
+static int __init cpcompare(const void *a, const void *b)
+{
+ struct change_member * const *app = a, * const *bpp = b;
+ const struct change_member *ap = *app, *bp = *bpp;
+
+ /*
+ * Inputs are pointers to two elements of change_point[]. If their
+ * addresses are unequal, their difference dominates. If the addresses
+ * are equal, then consider one that represents the end of its region
+ * to be greater than one that does not.
+ */
+ if (ap->addr != bp->addr)
+ return ap->addr > bp->addr ? 1 : -1;
+
+ return (ap->addr != ap->pbios->addr) - (bp->addr != bp->pbios->addr);
+}

int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map,
u32 *pnr_map)
{
- struct change_member {
- struct e820entry *pbios; /* pointer to original bios entry */
- unsigned long long addr; /* address for this change point */
- };
static struct change_member change_point_list[2*E820_X_MAX] __initdata;
static struct change_member *change_point[2*E820_X_MAX] __initdata;
static struct e820entry *overlap_list[E820_X_MAX] __initdata;
static struct e820entry new_bios[E820_X_MAX] __initdata;
- struct change_member *change_tmp;
unsigned long current_type, last_type;
unsigned long long last_addr;
- int chgidx, still_changing;
+ int chgidx;
int overlap_entries;
int new_bios_entry;
int old_nr, new_nr, chg_nr;
@@ -279,35 +296,7 @@ int __init sanitize_e820_map(struct e820entry *biosmap, int max_nr_map,
chg_nr = chgidx;

/* sort change-point list by memory addresses (low -> high) */
- still_changing = 1;
- while (still_changing) {
- still_changing = 0;
- for (i = 1; i < chg_nr; i++) {
- unsigned long long curaddr, lastaddr;
- unsigned long long curpbaddr, lastpbaddr;
-
- curaddr = change_point[i]->addr;
- lastaddr = change_point[i - 1]->addr;
- curpbaddr = change_point[i]->pbios->addr;
- lastpbaddr = change_point[i - 1]->pbios->addr;
-
- /*
- * swap entries, when:
- *
- * curaddr > lastaddr or
- * curaddr == lastaddr and curaddr == curpbaddr and
- * lastaddr != lastpbaddr
- */
- if (curaddr < lastaddr ||
- (curaddr == lastaddr && curaddr == curpbaddr &&
- lastaddr != lastpbaddr)) {
- change_tmp = change_point[i];
- change_point[i] = change_point[i-1];
- change_point[i-1] = change_tmp;
- still_changing = 1;
- }
- }
- }
+ sort(change_point, chg_nr, sizeof *change_point, cpcompare, NULL);

/* create a new bios memory map, removing overlaps */
overlap_entries = 0; /* number of entries in the overlap table */
diff --git a/arch/x86/mm/init.c b/arch/x86/mm/init.c
index 87488b9..2426b60 100644
--- a/arch/x86/mm/init.c
+++ b/arch/x86/mm/init.c
@@ -3,6 +3,7 @@
#include <linux/ioport.h>
#include <linux/swap.h>
#include <linux/memblock.h>
+#include <linux/bootmem.h> /* for max_low_pfn */

#include <asm/cacheflush.h>
#include <asm/e820.h>
@@ -15,6 +16,7 @@
#include <asm/tlbflush.h>
#include <asm/tlb.h>
#include <asm/proto.h>
+#include <asm/dma.h> /* for MAX_DMA_PFN */

unsigned long __initdata pgt_buf_start;
unsigned long __meminitdata pgt_buf_end;
@@ -392,3 +394,24 @@ void free_initrd_mem(unsigned long start, unsigned long end)
free_init_pages("initrd memory", start, PAGE_ALIGN(end));
}
#endif
+
+void __init zone_sizes_init(void)
+{
+ unsigned long max_zone_pfns[MAX_NR_ZONES];
+
+ memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
+
+#ifdef CONFIG_ZONE_DMA
+ max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
+#endif
+#ifdef CONFIG_ZONE_DMA32
+ max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
+#endif
+ max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
+#ifdef CONFIG_HIGHMEM
+ max_zone_pfns[ZONE_HIGHMEM] = max_pfn;
+#endif
+
+ free_area_init_nodes(max_zone_pfns);
+}
+
diff --git a/arch/x86/mm/init_32.c b/arch/x86/mm/init_32.c
index 29f7c6d..a2fecb1 100644
--- a/arch/x86/mm/init_32.c
+++ b/arch/x86/mm/init_32.c
@@ -674,22 +674,6 @@ void __init initmem_init(void)
}
#endif /* !CONFIG_NEED_MULTIPLE_NODES */

-static void __init zone_sizes_init(void)
-{
- unsigned long max_zone_pfns[MAX_NR_ZONES];
- memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
-#ifdef CONFIG_ZONE_DMA
- max_zone_pfns[ZONE_DMA] =
- virt_to_phys((char *)MAX_DMA_ADDRESS) >> PAGE_SHIFT;
-#endif
- max_zone_pfns[ZONE_NORMAL] = max_low_pfn;
-#ifdef CONFIG_HIGHMEM
- max_zone_pfns[ZONE_HIGHMEM] = highend_pfn;
-#endif
-
- free_area_init_nodes(max_zone_pfns);
-}
-
void __init setup_bootmem_allocator(void)
{
printk(KERN_INFO " mapped low ram: 0 - %08lx\n",
@@ -760,6 +744,17 @@ void __init mem_init(void)
#ifdef CONFIG_FLATMEM
BUG_ON(!mem_map);
#endif
+ /*
+ * With CONFIG_DEBUG_PAGEALLOC initialization of highmem pages has to
+ * be done before free_all_bootmem(). Memblock use free low memory for
+ * temporary data (see find_range_array()) and for this purpose can use
+ * pages that was already passed to the buddy allocator, hence marked as
+ * not accessible in the page tables when compiled with
+ * CONFIG_DEBUG_PAGEALLOC. Otherwise order of initialization is not
+ * important here.
+ */
+ set_highmem_pages_init();
+
/* this will put all low memory onto the freelists */
totalram_pages += free_all_bootmem();

@@ -771,8 +766,6 @@ void __init mem_init(void)
if (page_is_ram(tmp) && PageReserved(pfn_to_page(tmp)))
reservedpages++;

- set_highmem_pages_init();
-
codesize = (unsigned long) &_etext - (unsigned long) &_text;
datasize = (unsigned long) &_edata - (unsigned long) &_etext;
initsize = (unsigned long) &__init_end - (unsigned long) &__init_begin;
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index bbaaa00..6fcce7d 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -614,15 +614,6 @@ void __init initmem_init(void)

void __init paging_init(void)
{
- unsigned long max_zone_pfns[MAX_NR_ZONES];
-
- memset(max_zone_pfns, 0, sizeof(max_zone_pfns));
-#ifdef CONFIG_ZONE_DMA
- max_zone_pfns[ZONE_DMA] = MAX_DMA_PFN;
-#endif
- max_zone_pfns[ZONE_DMA32] = MAX_DMA32_PFN;
- max_zone_pfns[ZONE_NORMAL] = max_pfn;
-
sparse_memory_present_with_active_regions(MAX_NUMNODES);
sparse_init();

@@ -634,7 +625,7 @@ void __init paging_init(void)
*/
node_clear_state(0, N_NORMAL_MEMORY);

- free_area_init_nodes(max_zone_pfns);
+ zone_sizes_init();
}

/*
diff --git a/arch/x86/mm/mmap.c b/arch/x86/mm/mmap.c
index 4b5ba85..845df68 100644
--- a/arch/x86/mm/mmap.c
+++ b/arch/x86/mm/mmap.c
@@ -75,9 +75,9 @@ static unsigned long mmap_rnd(void)
*/
if (current->flags & PF_RANDOMIZE) {
if (mmap_is_ia32())
- rnd = (long)get_random_int() % (1<<8);
+ rnd = get_random_int() % (1<<8);
else
- rnd = (long)(get_random_int() % (1<<28));
+ rnd = get_random_int() % (1<<28);
}
return rnd << PAGE_SHIFT;
}
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
index fbeaaf4..cdc0054 100644
--- a/arch/x86/mm/numa.c
+++ b/arch/x86/mm/numa.c
@@ -430,8 +430,9 @@ static int __init numa_alloc_distance(void)
* calls are ignored until the distance table is reset with
* numa_reset_distance().
*
- * If @from or @to is higher than the highest known node at the time of
- * table creation or @distance doesn't make sense, the call is ignored.
+ * If @from or @to is higher than the highest known node or lower than zero
+ * at the time of table creation or @distance doesn't make sense, the call
+ * is ignored.
* This is to allow simplification of specific NUMA config implementations.
*/
void __init numa_set_distance(int from, int to, int distance)
@@ -439,8 +440,9 @@ void __init numa_set_distance(int from, int to, int distance)
if (!numa_distance && numa_alloc_distance() < 0)
return;

- if (from >= numa_distance_cnt || to >= numa_distance_cnt) {
- printk_once(KERN_DEBUG "NUMA: Debug: distance out of bound, from=%d to=%d distance=%d\n",
+ if (from >= numa_distance_cnt || to >= numa_distance_cnt ||
+ from < 0 || to < 0) {
+ pr_warn_once("NUMA: Warning: node ids are out of bound, from=%d to=%d distance=%d\n",
from, to, distance);
return;
}
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index f9e5267..5031eef 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -1334,12 +1334,6 @@ void kernel_map_pages(struct page *page, int numpages, int enable)
}

/*
- * If page allocator is not up yet then do not call c_p_a():
- */
- if (!debug_pagealloc_enabled)
- return;
-
- /*
* The return value is ignored as the calls cannot fail.
* Large pages for identity mappings are not used at boot time
* and hence no memory allocations during large page split.
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 3dc3a8c..0a22db1 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1537,23 +1537,13 @@ static inline void vm_stat_account(struct mm_struct *mm,
#endif /* CONFIG_PROC_FS */

#ifdef CONFIG_DEBUG_PAGEALLOC
-extern int debug_pagealloc_enabled;
-
extern void kernel_map_pages(struct page *page, int numpages, int enable);
-
-static inline void enable_debug_pagealloc(void)
-{
- debug_pagealloc_enabled = 1;
-}
#ifdef CONFIG_HIBERNATION
extern bool kernel_page_present(struct page *page);
#endif /* CONFIG_HIBERNATION */
#else
static inline void
kernel_map_pages(struct page *page, int numpages, int enable) {}
-static inline void enable_debug_pagealloc(void)
-{
-}
#ifdef CONFIG_HIBERNATION
static inline bool kernel_page_present(struct page *page) { return true; }
#endif /* CONFIG_HIBERNATION */
diff --git a/init/main.c b/init/main.c
index 217ed23..99c4ba3 100644
--- a/init/main.c
+++ b/init/main.c
@@ -282,10 +282,6 @@ static int __init unknown_bootoption(char *param, char *val)
return 0;
}

-#ifdef CONFIG_DEBUG_PAGEALLOC
-int __read_mostly debug_pagealloc_enabled = 0;
-#endif
-
static int __init init_setup(char *str)
{
unsigned int i;
@@ -597,7 +593,6 @@ asmlinkage void __init start_kernel(void)
}
#endif
page_cgroup_init();
- enable_debug_pagealloc();
debug_objects_mem_init();
kmemleak_init();
setup_per_cpu_pageset();
diff --git a/mm/debug-pagealloc.c b/mm/debug-pagealloc.c
index 7cea557..789ff70 100644
--- a/mm/debug-pagealloc.c
+++ b/mm/debug-pagealloc.c
@@ -95,9 +95,6 @@ static void unpoison_pages(struct page *page, int n)

void kernel_map_pages(struct page *page, int numpages, int enable)
{
- if (!debug_pagealloc_enabled)
- return;
-
if (enable)
unpoison_pages(page, numpages);
else
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/