Skip to content

K
Kernel

openeuler / Kernel
1 年多 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 11 1月, 2012 23 次提交
  3. 10 1月, 2012 1 次提交
  5. 08 1月, 2012 1 次提交
    • G
      net: fix sock_clone reference mismatch with tcp memcontrol · f3f511e1
      由 Glauber Costa 提交于 
      Sockets can also be created through sock_clone. Because it copies
all data in the sock structure, it also copies the memcg-related pointer,
and all should be fine. However, since we now use reference counts in
socket creation, we are left with some sockets that have no reference
counts. It matters when we destroy them, since it leads to a mismatch.
Signed-off-by: NGlauber Costa <glommer@parallels.com>
CC: David S. Miller <davem@davemloft.net>
CC: Greg Thelen <gthelen@google.com>
CC: Hiroyouki Kamezawa <kamezawa.hiroyu@jp.fujitsu.com>
CC: Laurent Chavey <chavey@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      f3f511e1
  7. 07 1月, 2012 1 次提交
  9. 04 1月, 2012 9 次提交
  11. 30 12月, 2011 2 次提交
    • H
      mm: hugetlb: fix non-atomic enqueue of huge page · b0365c8d
      由 Hillf Danton 提交于 
      If a huge page is enqueued under the protection of hugetlb_lock, then the
operation is atomic and safe.
Signed-off-by: NHillf Danton <dhillf@gmail.com>
Reviewed-by: NMichal Hocko <mhocko@suse.cz>
Acked-by: NKAMEZAWA Hiroyuki <kamezawa.hiroyu@jp.fujitsu.com>
Cc: <stable@vger.kernel.org>		[2.6.37+]
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      b0365c8d
    • K
      mm/mempolicy.c: refix mbind_range() vma issue · e26a5114
      由 KOSAKI Motohiro 提交于 
      commit 8aacc9f5 ("mm/mempolicy.c: fix pgoff in mbind vma merge") is the
slightly incorrect fix.

Why? Think following case.

1. map 4 pages of a file at offset 0

   [0123]

2. map 2 pages just after the first mapping of the same file but with
   page offset 2

   [0123][23]

3. mbind() 2 pages from the first mapping at offset 2.
   mbind_range() should treat new vma is,

   [0123][23]
     |23|
     mbind vma

   but it does

   [0123][23]
     |01|
     mbind vma

   Oops. then, it makes wrong vma merge and splitting ([01][0123] or similar).

This patch fixes it.

[testcase]
  test result - before the patch

	case4: 126: test failed. expect '2,4', actual '2,2,2'
       	case5: passed
	case6: passed
	case7: passed
	case8: passed
	case_n: 246: test failed. expect '4,2', actual '1,4'

	------------[ cut here ]------------
	kernel BUG at mm/filemap.c:135!
	invalid opcode: 0000 [#4] SMP DEBUG_PAGEALLOC

	(snip long bug on messages)

  test result - after the patch

	case4: passed
       	case5: passed
	case6: passed
	case7: passed
	case8: passed
	case_n: passed

  source:  mbind_vma_test.c
============================================================
 #include <numaif.h>
 #include <numa.h>
 #include <sys/mman.h>
 #include <stdio.h>
 #include <unistd.h>
 #include <stdlib.h>
 #include <string.h>

static unsigned long pagesize;
void* mmap_addr;
struct bitmask *nmask;
char buf[1024];
FILE *file;
char retbuf[10240] = "";
int mapped_fd;

char *rubysrc = "ruby -e '\
  pid = %d; \
  vstart = 0x%llx; \
  vend = 0x%llx; \
  s = `pmap -q #{pid}`; \
  rary = []; \
  s.each_line {|line|; \
    ary=line.split(\" \"); \
    addr = ary[0].to_i(16); \
    if(vstart <= addr && addr < vend) then \
      rary.push(ary[1].to_i()/4); \
    end; \
  }; \
  print rary.join(\",\"); \
'";

void init(void)
{
	void* addr;
	char buf[128];

	nmask = numa_allocate_nodemask();
	numa_bitmask_setbit(nmask, 0);

	pagesize = getpagesize();

	sprintf(buf, "%s", "mbind_vma_XXXXXX");
	mapped_fd = mkstemp(buf);
	if (mapped_fd == -1)
		perror("mkstemp "), exit(1);
	unlink(buf);

	if (lseek(mapped_fd, pagesize*8, SEEK_SET) < 0)
		perror("lseek "), exit(1);
	if (write(mapped_fd, "\0", 1) < 0)
		perror("write "), exit(1);

	addr = mmap(NULL, pagesize*8, PROT_NONE,
		    MAP_SHARED, mapped_fd, 0);
	if (addr == MAP_FAILED)
		perror("mmap "), exit(1);

	if (mprotect(addr+pagesize, pagesize*6, PROT_READ|PROT_WRITE) < 0)
		perror("mprotect "), exit(1);

	mmap_addr = addr + pagesize;

	/* make page populate */
	memset(mmap_addr, 0, pagesize*6);
}

void fin(void)
{
	void* addr = mmap_addr - pagesize;
	munmap(addr, pagesize*8);

	memset(buf, 0, sizeof(buf));
	memset(retbuf, 0, sizeof(retbuf));
}

void mem_bind(int index, int len)
{
	int err;

	err = mbind(mmap_addr+pagesize*index, pagesize*len,
		    MPOL_BIND, nmask->maskp, nmask->size, 0);
	if (err)
		perror("mbind "), exit(err);
}

void mem_interleave(int index, int len)
{
	int err;

	err = mbind(mmap_addr+pagesize*index, pagesize*len,
		    MPOL_INTERLEAVE, nmask->maskp, nmask->size, 0);
	if (err)
		perror("mbind "), exit(err);
}

void mem_unbind(int index, int len)
{
	int err;

	err = mbind(mmap_addr+pagesize*index, pagesize*len,
		    MPOL_DEFAULT, NULL, 0, 0);
	if (err)
		perror("mbind "), exit(err);
}

void Assert(char *expected, char *value, char *name, int line)
{
	if (strcmp(expected, value) == 0) {
		fprintf(stderr, "%s: passed\n", name);
		return;
	}
	else {
		fprintf(stderr, "%s: %d: test failed. expect '%s', actual '%s'\n",
			name, line,
			expected, value);
//		exit(1);
	}
}

/*
      AAAA
    PPPPPPNNNNNN
    might become
    PPNNNNNNNNNN
    case 4 below
*/
void case4(void)
{
	init();
	sprintf(buf, rubysrc, getpid(), mmap_addr, mmap_addr+pagesize*6);

	mem_bind(0, 4);
	mem_unbind(2, 2);

	file = popen(buf, "r");
	fread(retbuf, sizeof(retbuf), 1, file);
	Assert("2,4", retbuf, "case4", __LINE__);

	fin();
}

/*
       AAAA
 PPPPPPNNNNNN
 might become
 PPPPPPPPPPNN
 case 5 below
*/
void case5(void)
{
	init();
	sprintf(buf, rubysrc, getpid(), mmap_addr, mmap_addr+pagesize*6);

	mem_bind(0, 2);
	mem_bind(2, 2);

	file = popen(buf, "r");
	fread(retbuf, sizeof(retbuf), 1, file);
	Assert("4,2", retbuf, "case5", __LINE__);

	fin();
}

/*
	    AAAA
	PPPPNNNNXXXX
	might become
	PPPPPPPPPPPP 6
*/
void case6(void)
{
	init();
	sprintf(buf, rubysrc, getpid(), mmap_addr, mmap_addr+pagesize*6);

	mem_bind(0, 2);
	mem_bind(4, 2);
	mem_bind(2, 2);

	file = popen(buf, "r");
	fread(retbuf, sizeof(retbuf), 1, file);
	Assert("6", retbuf, "case6", __LINE__);

	fin();
}

/*
    AAAA
PPPPNNNNXXXX
might become
PPPPPPPPXXXX 7
*/
void case7(void)
{
	init();
	sprintf(buf, rubysrc, getpid(), mmap_addr, mmap_addr+pagesize*6);

	mem_bind(0, 2);
	mem_interleave(4, 2);
	mem_bind(2, 2);

	file = popen(buf, "r");
	fread(retbuf, sizeof(retbuf), 1, file);
	Assert("4,2", retbuf, "case7", __LINE__);

	fin();
}

/*
    AAAA
PPPPNNNNXXXX
might become
PPPPNNNNNNNN 8
*/
void case8(void)
{
	init();
	sprintf(buf, rubysrc, getpid(), mmap_addr, mmap_addr+pagesize*6);

	mem_bind(0, 2);
	mem_interleave(4, 2);
	mem_interleave(2, 2);

	file = popen(buf, "r");
	fread(retbuf, sizeof(retbuf), 1, file);
	Assert("2,4", retbuf, "case8", __LINE__);

	fin();
}

void case_n(void)
{
	init();
	sprintf(buf, rubysrc, getpid(), mmap_addr, mmap_addr+pagesize*6);

	/* make redundunt mappings [0][1234][34][7] */
	mmap(mmap_addr + pagesize*4, pagesize*2, PROT_READ|PROT_WRITE,
	     MAP_FIXED|MAP_SHARED, mapped_fd, pagesize*3);

	/* Expect to do nothing. */
	mem_unbind(2, 2);

	file = popen(buf, "r");
	fread(retbuf, sizeof(retbuf), 1, file);
	Assert("4,2", retbuf, "case_n", __LINE__);

	fin();
}

int main(int argc, char** argv)
{
	case4();
	case5();
	case6();
	case7();
	case8();
	case_n();

	return 0;
}
=============================================================
Signed-off-by: NKOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: NJohannes Weiner <hannes@cmpxchg.org>
Cc: Minchan Kim <minchan.kim@gmail.com>
Cc: Caspar Zhang <caspar@casparzhang.com>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Cc: Mel Gorman <mel@csn.ul.ie>
Cc: Lee Schermerhorn <lee.schermerhorn@hp.com>
Cc: <stable@vger.kernel.org>		[3.1.x]
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      e26a5114
  13. 23 12月, 2011 2 次提交
    • G
      Partial revert "Basic kernel memory functionality for the Memory Controller" · 65c64ce8
      由 Glauber Costa 提交于 
      This reverts commit e5671dfa.

After a follow up discussion with Michal, it was agreed it would
be better to leave the kmem controller with just the tcp files,
deferring the behavior of the other general memory.kmem.* files
for a later time, when more caches are controlled. This is because
generic kmem files are not used by tcp accounting and it is
not clear how other slab caches would fit into the scheme.

We are reverting the original commit so we can track the reference.
Part of the patch is kept, because it was used by the later tcp
code. Conflicts are shown in the bottom. init/Kconfig is removed from
the revert entirely.
Signed-off-by: NGlauber Costa <glommer@parallels.com>
Acked-by: NMichal Hocko <mhocko@suse.cz>
CC: Kirill A. Shutemov <kirill@shutemov.name>
CC: Paul Menage <paul@paulmenage.org>
CC: Greg Thelen <gthelen@google.com>
CC: Johannes Weiner <jweiner@redhat.com>
CC: David S. Miller <davem@davemloft.net>

Conflicts:

	Documentation/cgroups/memory.txt
	mm/memcontrol.c
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      65c64ce8
    • C
      percpu: Remove irqsafe_cpu_xxx variants · 933393f5
      由 Christoph Lameter 提交于 
      We simply say that regular this_cpu use must be safe regardless of
preemption and interrupt state.  That has no material change for x86
and s390 implementations of this_cpu operations.  However, arches that
do not provide their own implementation for this_cpu operations will
now get code generated that disables interrupts instead of preemption.

-tj: This is part of on-going percpu API cleanup.  For detailed
     discussion of the subject, please refer to the following thread.

     http://thread.gmane.org/gmane.linux.kernel/1222078Signed-off-by: NChristoph Lameter <cl@linux.com>
Signed-off-by: NTejun Heo <tj@kernel.org>
LKML-Reference: <alpine.DEB.2.00.1112221154380.11787@router.home>
      933393f5
  15. 22 12月, 2011 1 次提交