From e180377f1ae48b3cbc559c9875d9b038f7f000c6 Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Wed, 12 Dec 2012 13:50:59 -0800
Subject: thp: change split_huge_page_pmd() interface
Pass vma instead of mm and add address parameter.
In most cases we already have vma on the stack. We provides
split_huge_page_pmd_mm() for few cases when we have mm, but not vma.
This change is preparation to huge zero pmd splitting implementation.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Andi Kleen <ak@linux.intel.com>
Cc: "H. Peter Anvin" <hpa@linux.intel.com>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
arch/x86/kernel/vm86_32.c | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
(limited to 'arch')
diff --git a/arch/x86/kernel/vm86_32.c b/arch/x86/kernel/vm86_32.c
index 5c9687b1bde6..1dfe69cc78a8 100644
--- a/arch/x86/kernel/vm86_32.c
+++ b/arch/x86/kernel/vm86_32.c
@@ -182,7 +182,7 @@ static void mark_screen_rdonly(struct mm_struct *mm)
if (pud_none_or_clear_bad(pud))
goto out;
pmd = pmd_offset(pud, 0xA0000);
- split_huge_page_pmd(mm, pmd);
+ split_huge_page_pmd_mm(mm, 0xA0000, pmd);
if (pmd_none_or_clear_bad(pmd))
goto out;
pte = pte_offset_map_lock(mm, pmd, 0xA0000, &ptl);
--
cgit v1.2.3-70-g09d2
From 4b0ef1fe8a626f0ba7f649764f979d0dc9eab86b Mon Sep 17 00:00:00 2001
From: Lai Jiangshan <laijs@cn.fujitsu.com>
Date: Wed, 12 Dec 2012 13:51:46 -0800
Subject: page_alloc: use N_MEMORY instead N_HIGH_MEMORY change the node_states
initialization
N_HIGH_MEMORY stands for the nodes that has normal or high memory.
N_MEMORY stands for the nodes that has any memory.
The code here need to handle with the nodes which have memory, we should
use N_MEMORY instead.
Since we introduced N_MEMORY, we update the initialization of node_states.
Signed-off-by: Lai Jiangshan <laijs@cn.fujitsu.com>
Signed-off-by: Lin Feng <linfeng@cn.fujitsu.com>
Signed-off-by: Wen Congyang <wency@cn.fujitsu.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Hillf Danton <dhillf@gmail.com>
Cc: David Rientjes <rientjes@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
arch/x86/mm/init_64.c | 4 +++-
mm/page_alloc.c | 40 ++++++++++++++++++++++------------------
2 files changed, 25 insertions(+), 19 deletions(-)
(limited to 'arch')
diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
index 3baff255adac..2ead3c8a4c84 100644
--- a/arch/x86/mm/init_64.c
+++ b/arch/x86/mm/init_64.c
@@ -630,7 +630,9 @@ void __init paging_init(void)
* numa support is not compiled in, and later node_set_state
* will not set it back.
*/
- node_clear_state(0, N_NORMAL_MEMORY);
+ node_clear_state(0, N_MEMORY);
+ if (N_MEMORY != N_NORMAL_MEMORY)
+ node_clear_state(0, N_NORMAL_MEMORY);
zone_sizes_init();
}
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 4171cd4f8257..35727168896b 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -1695,7 +1695,7 @@ bool zone_watermark_ok_safe(struct zone *z, int order, unsigned long mark,
*
* If the zonelist cache is present in the passed in zonelist, then
* returns a pointer to the allowed node mask (either the current
- * tasks mems_allowed, or node_states[N_HIGH_MEMORY].)
+ * tasks mems_allowed, or node_states[N_MEMORY].)
*
* If the zonelist cache is not available for this zonelist, does
* nothing and returns NULL.
@@ -1724,7 +1724,7 @@ static nodemask_t *zlc_setup(struct zonelist *zonelist, int alloc_flags)
allowednodes = !in_interrupt() && (alloc_flags & ALLOC_CPUSET) ?
&cpuset_current_mems_allowed :
- &node_states[N_HIGH_MEMORY];
+ &node_states[N_MEMORY];
return allowednodes;
}
@@ -3238,7 +3238,7 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask)
return node;
}
- for_each_node_state(n, N_HIGH_MEMORY) {
+ for_each_node_state(n, N_MEMORY) {
/* Don't want a node to appear more than once */
if (node_isset(n, *used_node_mask))
@@ -3380,7 +3380,7 @@ static int default_zonelist_order(void)
* local memory, NODE_ORDER may be suitable.
*/
average_size = total_size /
- (nodes_weight(node_states[N_HIGH_MEMORY]) + 1);
+ (nodes_weight(node_states[N_MEMORY]) + 1);
for_each_online_node(nid) {
low_kmem_size = 0;
total_size = 0;
@@ -4731,7 +4731,7 @@ unsigned long __init find_min_pfn_with_active_regions(void)
/*
* early_calculate_totalpages()
* Sum pages in active regions for movable zone.
- * Populate N_HIGH_MEMORY for calculating usable_nodes.
+ * Populate N_MEMORY for calculating usable_nodes.
*/
static unsigned long __init early_calculate_totalpages(void)
{
@@ -4744,7 +4744,7 @@ static unsigned long __init early_calculate_totalpages(void)
totalpages += pages;
if (pages)
- node_set_state(nid, N_HIGH_MEMORY);
+ node_set_state(nid, N_MEMORY);
}
return totalpages;
}
@@ -4761,9 +4761,9 @@ static void __init find_zone_movable_pfns_for_nodes(void)
unsigned long usable_startpfn;
unsigned long kernelcore_node, kernelcore_remaining;
/* save the state before borrow the nodemask */
- nodemask_t saved_node_state = node_states[N_HIGH_MEMORY];
+ nodemask_t saved_node_state = node_states[N_MEMORY];
unsigned long totalpages = early_calculate_totalpages();
- int usable_nodes = nodes_weight(node_states[N_HIGH_MEMORY]);
+ int usable_nodes = nodes_weight(node_states[N_MEMORY]);
/*
* If movablecore was specified, calculate what size of
@@ -4798,7 +4798,7 @@ static void __init find_zone_movable_pfns_for_nodes(void)
restart:
/* Spread kernelcore memory as evenly as possible throughout nodes */
kernelcore_node = required_kernelcore / usable_nodes;
- for_each_node_state(nid, N_HIGH_MEMORY) {
+ for_each_node_state(nid, N_MEMORY) {
unsigned long start_pfn, end_pfn;
/*
@@ -4890,23 +4890,27 @@ restart:
out:
/* restore the node_state */
- node_states[N_HIGH_MEMORY] = saved_node_state;
+ node_states[N_MEMORY] = saved_node_state;
}
-/* Any regular memory on that node ? */
-static void __init check_for_regular_memory(pg_data_t *pgdat)
+/* Any regular or high memory on that node ? */
+static void check_for_memory(pg_data_t *pgdat, int nid)
{
-#ifdef CONFIG_HIGHMEM
enum zone_type zone_type;
- for (zone_type = 0; zone_type <= ZONE_NORMAL; zone_type++) {
+ if (N_MEMORY == N_NORMAL_MEMORY)
+ return;
+
+ for (zone_type = 0; zone_type <= ZONE_MOVABLE - 1; zone_type++) {
struct zone *zone = &pgdat->node_zones[zone_type];
if (zone->present_pages) {
- node_set_state(zone_to_nid(zone), N_NORMAL_MEMORY);
+ node_set_state(nid, N_HIGH_MEMORY);
+ if (N_NORMAL_MEMORY != N_HIGH_MEMORY &&
+ zone_type <= ZONE_NORMAL)
+ node_set_state(nid, N_NORMAL_MEMORY);
break;
}
}
-#endif
}
/**
@@ -4989,8 +4993,8 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn)
/* Any memory on that node */
if (pgdat->node_present_pages)
- node_set_state(nid, N_HIGH_MEMORY);
- check_for_regular_memory(pgdat);
+ node_set_state(nid, N_MEMORY);
+ check_for_memory(pgdat, nid);
}
}
--
cgit v1.2.3-70-g09d2
From c2d23f919bafcbc2259f5257d9a7d729802f0e3a Mon Sep 17 00:00:00 2001
From: David Rientjes <rientjes@google.com>
Date: Wed, 12 Dec 2012 13:52:10 -0800
Subject: mm, oom: remove statically defined arch functions of same name
out_of_memory() is a globally defined function to call the oom killer.
x86, sh, and powerpc all use a function of the same name within file scope
in their respective fault.c unnecessarily. Inline the functions into the
pagefault handlers to clean the code up.
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Mundt <lethal@linux-sh.org>
Reviewed-by: Michal Hocko <mhocko@suse.cz>
Reviewed-by: KAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
arch/powerpc/mm/fault.c | 27 ++++++++++++---------------
arch/sh/mm/fault.c | 19 +++++++------------
arch/x86/mm/fault.c | 23 ++++++++---------------
3 files changed, 27 insertions(+), 42 deletions(-)
(limited to 'arch')
diff --git a/arch/powerpc/mm/fault.c b/arch/powerpc/mm/fault.c
index 0a6b28336eb0..3a8489a354e9 100644
--- a/arch/powerpc/mm/fault.c
+++ b/arch/powerpc/mm/fault.c
@@ -113,19 +113,6 @@ static int store_updates_sp(struct pt_regs *regs)
#define MM_FAULT_CONTINUE -1
#define MM_FAULT_ERR(sig) (sig)
-static int out_of_memory(struct pt_regs *regs)
-{
- /*
- * We ran out of memory, or some other thing happened to us that made
- * us unable to handle the page fault gracefully.
- */
- up_read(¤t->mm->mmap_sem);
- if (!user_mode(regs))
- return MM_FAULT_ERR(SIGKILL);
- pagefault_out_of_memory();
- return MM_FAULT_RETURN;
-}
-
static int do_sigbus(struct pt_regs *regs, unsigned long address)
{
siginfo_t info;
@@ -169,8 +156,18 @@ static int mm_fault_error(struct pt_regs *regs, unsigned long addr, int fault)
return MM_FAULT_CONTINUE;
/* Out of memory */
- if (fault & VM_FAULT_OOM)
- return out_of_memory(regs);
+ if (fault & VM_FAULT_OOM) {
+ up_read(¤t->mm->mmap_sem);
+
+ /*
+ * We ran out of memory, or some other thing happened to us that
+ * made us unable to handle the page fault gracefully.
+ */
+ if (!user_mode(regs))
+ return MM_FAULT_ERR(SIGKILL);
+ pagefault_out_of_memory();
+ return MM_FAULT_RETURN;
+ }
/* Bus error. x86 handles HWPOISON here, we'll add this if/when
* we support the feature in HW
diff --git a/arch/sh/mm/fault.c b/arch/sh/mm/fault.c
index cbbdcad8fcb3..1f49c28affa9 100644
--- a/arch/sh/mm/fault.c
+++ b/arch/sh/mm/fault.c
@@ -301,17 +301,6 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
__bad_area(regs, error_code, address, SEGV_ACCERR);
}
-static void out_of_memory(void)
-{
- /*
- * We ran out of memory, call the OOM killer, and return the userspace
- * (which will retry the fault, or kill us if we got oom-killed):
- */
- up_read(¤t->mm->mmap_sem);
-
- pagefault_out_of_memory();
-}
-
static void
do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address)
{
@@ -353,8 +342,14 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
no_context(regs, error_code, address);
return 1;
}
+ up_read(¤t->mm->mmap_sem);
- out_of_memory();
+ /*
+ * We ran out of memory, call the OOM killer, and return the
+ * userspace (which will retry the fault, or kill us if we got
+ * oom-killed):
+ */
+ pagefault_out_of_memory();
} else {
if (fault & VM_FAULT_SIGBUS)
do_sigbus(regs, error_code, address);
diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c
index 7a529cbab7ad..027088f2f7dd 100644
--- a/arch/x86/mm/fault.c
+++ b/arch/x86/mm/fault.c
@@ -803,20 +803,6 @@ bad_area_access_error(struct pt_regs *regs, unsigned long error_code,
__bad_area(regs, error_code, address, SEGV_ACCERR);
}
-/* TODO: fixup for "mm-invoke-oom-killer-from-page-fault.patch" */
-static void
-out_of_memory(struct pt_regs *regs, unsigned long error_code,
- unsigned long address)
-{
- /*
- * We ran out of memory, call the OOM killer, and return the userspace
- * (which will retry the fault, or kill us if we got oom-killed):
- */
- up_read(¤t->mm->mmap_sem);
-
- pagefault_out_of_memory();
-}
-
static void
do_sigbus(struct pt_regs *regs, unsigned long error_code, unsigned long address,
unsigned int fault)
@@ -879,7 +865,14 @@ mm_fault_error(struct pt_regs *regs, unsigned long error_code,
return 1;
}
- out_of_memory(regs, error_code, address);
+ up_read(¤t->mm->mmap_sem);
+
+ /*
+ * We ran out of memory, call the OOM killer, and return the
+ * userspace (which will retry the fault, or kill us if we got
+ * oom-killed):
+ */
+ pagefault_out_of_memory();
} else {
if (fault & (VM_FAULT_SIGBUS|VM_FAULT_HWPOISON|
VM_FAULT_HWPOISON_LARGE))
--
cgit v1.2.3-70-g09d2
From 816422ad76474fed8052b6f7b905a054d082e59a Mon Sep 17 00:00:00 2001
From: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Date: Wed, 12 Dec 2012 13:52:36 -0800
Subject: asm-generic, mm: pgtable: consolidate zero page helpers
We have two different implementation of is_zero_pfn() and my_zero_pfn()
helpers: for architectures with and without zero page coloring.
Let's consolidate them in <asm-generic/pgtable.h>.
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
---
arch/mips/include/asm/pgtable.h | 11 +----------
arch/s390/include/asm/pgtable.h | 11 +----------
include/asm-generic/pgtable.h | 26 ++++++++++++++++++++++++++
include/linux/mm.h | 8 --------
mm/memory.c | 7 -------
5 files changed, 28 insertions(+), 35 deletions(-)
(limited to 'arch')
diff --git a/arch/mips/include/asm/pgtable.h b/arch/mips/include/asm/pgtable.h
index c02158be836c..14490e9443af 100644
--- a/arch/mips/include/asm/pgtable.h
+++ b/arch/mips/include/asm/pgtable.h
@@ -76,16 +76,7 @@ extern unsigned long zero_page_mask;
#define ZERO_PAGE(vaddr) \
(virt_to_page((void *)(empty_zero_page + (((unsigned long)(vaddr)) & zero_page_mask))))
-
-#define is_zero_pfn is_zero_pfn
-static inline int is_zero_pfn(unsigned long pfn)
-{
- extern unsigned long zero_pfn;
- unsigned long offset_from_zero_pfn = pfn - zero_pfn;
- return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT);
-}
-
-#define my_zero_pfn(addr) page_to_pfn(ZERO_PAGE(addr))
+#define __HAVE_COLOR_ZERO_PAGE
extern void paging_init(void);
diff --git a/arch/s390/include/asm/pgtable.h b/arch/s390/include/asm/pgtable.h
index 2d3b7cb26005..c814e6f5b57d 100644
--- a/arch/s390/include/asm/pgtable.h
+++ b/arch/s390/include/asm/pgtable.h
@@ -55,16 +55,7 @@ extern unsigned long zero_page_mask;
#define ZERO_PAGE(vaddr) \
(virt_to_page((void *)(empty_zero_page + \
(((unsigned long)(vaddr)) &zero_page_mask))))
-
-#define is_zero_pfn is_zero_pfn
-static inline int is_zero_pfn(unsigned long pfn)
-{
- extern unsigned long zero_pfn;
- unsigned long offset_from_zero_pfn = pfn - zero_pfn;
- return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT);
-}
-
-#define my_zero_pfn(addr) page_to_pfn(ZERO_PAGE(addr))
+#define __HAVE_COLOR_ZERO_PAGE
#endif /* !__ASSEMBLY__ */
diff --git a/include/asm-generic/pgtable.h b/include/asm-generic/pgtable.h
index b36ce40bd1c6..284e80831d2c 100644
--- a/include/asm-generic/pgtable.h
+++ b/include/asm-generic/pgtable.h
@@ -449,6 +449,32 @@ extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
unsigned long size);
#endif
+#ifdef __HAVE_COLOR_ZERO_PAGE
+static inline int is_zero_pfn(unsigned long pfn)
+{
+ extern unsigned long zero_pfn;
+ unsigned long offset_from_zero_pfn = pfn - zero_pfn;
+ return offset_from_zero_pfn <= (zero_page_mask >> PAGE_SHIFT);
+}
+
+static inline unsigned long my_zero_pfn(unsigned long addr)
+{
+ return page_to_pfn(ZERO_PAGE(addr));
+}
+#else
+static inline int is_zero_pfn(unsigned long pfn)
+{
+ extern unsigned long zero_pfn;
+ return pfn == zero_pfn;
+}
+
+static inline unsigned long my_zero_pfn(unsigned long addr)
+{
+ extern unsigned long zero_pfn;
+ return zero_pfn;
+}
+#endif
+
#ifdef CONFIG_MMU
#ifndef CONFIG_TRANSPARENT_HUGEPAGE
diff --git a/include/linux/mm.h b/include/linux/mm.h
index 4b80bad4a367..4af4f0b1be4c 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -516,14 +516,6 @@ static inline pte_t maybe_mkwrite(pte_t pte, struct vm_area_struct *vma)
}
#endif
-#ifndef my_zero_pfn
-static inline unsigned long my_zero_pfn(unsigned long addr)
-{
- extern unsigned long zero_pfn;
- return zero_pfn;
-}
-#endif
-
/*
* Multiple processes may "see" the same page. E.g. for untouched
* mappings of /dev/null, all processes see the same page full of
diff --git a/mm/memory.c b/mm/memory.c
index f9a4b0cb8623..3f680e7c7645 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -717,13 +717,6 @@ static inline bool is_cow_mapping(vm_flags_t flags)
return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE;
}
-#ifndef is_zero_pfn
-static inline int is_zero_pfn(unsigned long pfn)
-{
- return pfn == zero_pfn;
-}
-#endif
-
/*
* vm_normal_page -- This function gets the "struct page" associated with a pte.
*
--
cgit v1.2.3-70-g09d2