Skip to content

R
raspberrypi-kernel

openeuler / raspberrypi-kernel

通知 13
Star 1
Fork 0
R
raspberrypi-kernel
切换分支/标签
  1. 04 1月, 2012 7 次提交
  3. 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
  5. 22 12月, 2011 1 次提交
  7. 21 12月, 2011 3 次提交
  9. 16 12月, 2011 1 次提交
    • E
      percpu: fix per_cpu_ptr_to_phys() handling of non-page-aligned addresses · 9f57bd4d
      由 Eugene Surovegin 提交于 
      per_cpu_ptr_to_phys() incorrectly rounds up its result for non-kmalloc
case to the page boundary, which is bogus for any non-page-aligned
address.

This affects the only in-tree user of this function - sysfs handler
for per-cpu 'crash_notes' physical address.  The trouble is that the
crash_notes per-cpu variable is not page-aligned:

crash_notes = 0xc08e8ed4
PER-CPU OFFSET VALUES:
 CPU 0: 3711f000
 CPU 1: 37129000
 CPU 2: 37133000
 CPU 3: 3713d000

So, the per-cpu addresses are:
 crash_notes on CPU 0: f7a07ed4 => phys 36b57ed4
 crash_notes on CPU 1: f7a11ed4 => phys 36b4ded4
 crash_notes on CPU 2: f7a1bed4 => phys 36b43ed4
 crash_notes on CPU 3: f7a25ed4 => phys 36b39ed4

However, /sys/devices/system/cpu/cpu*/crash_notes says:
 /sys/devices/system/cpu/cpu0/crash_notes: 36b57000
 /sys/devices/system/cpu/cpu1/crash_notes: 36b4d000
 /sys/devices/system/cpu/cpu2/crash_notes: 36b43000
 /sys/devices/system/cpu/cpu3/crash_notes: 36b39000

As you can see, all values are rounded down to a page
boundary. Consequently, this is where kexec sets up the NOTE segments,
and thus where the secondary kernel is looking for them. However, when
the first kernel crashes, it saves the notes to the unaligned
addresses, where they are not found.

Fix it by adding offset_in_page() to the translated page address.

-tj: Combined Eugene's and Petr's commit messages.
Signed-off-by: NEugene Surovegin <ebs@ebshome.net>
Signed-off-by: NTejun Heo <tj@kernel.org>
Reported-by: NPetr Tesarik <ptesarik@suse.cz>
Cc: stable@kernel.org
      9f57bd4d
  11. 09 12月, 2011 7 次提交
  13. 08 12月, 2011 3 次提交
    • W
      writeback: set max_pause to lowest value on zero bdi_dirty · 82e230a0
      由 Wu Fengguang 提交于 
      Some trace shows lots of bdi_dirty=0 lines where it's actually some
small value if w/o the accounting errors in the per-cpu bdi stats.

In this case the max pause time should really be set to the smallest
(non-zero) value to avoid IO queue underrun and improve throughput.
Signed-off-by: NWu Fengguang <fengguang.wu@intel.com>
      82e230a0
    • W
      writeback: permit through good bdi even when global dirty exceeded · c5c6343c
      由 Wu Fengguang 提交于 
      On a system with 1 local mount and 1 NFS mount, if the NFS server
becomes not responding when dd to the NFS mount, the NFS dirty pages may
exceed the global dirty limit and _every_ task involving writing will be
blocked. The whole system appears unresponsive.

The workaround is to permit through the bdi's that only has a small
number of dirty pages. The number chosen (bdi_stat_error pages) is not
enough to enable the local disk to run in optimal throughput, however is
enough to make the system responsive on a broken NFS mount. The user can
then kill the dirtiers on the NFS mount and increase the global dirty
limit to bring up the local disk's throughput.

It risks allowing dirty pages to grow much larger than the global dirty
limit when there are 1000+ mounts, however that's very unlikely to happen,
especially in low memory profiles.
Signed-off-by: NWu Fengguang <fengguang.wu@intel.com>
      c5c6343c
    • W
      writeback: comment on the bdi dirty threshold · aed21ad2
      由 Wu Fengguang 提交于 
      We do "floating proportions" to let active devices to grow its target
share of dirty pages and stalled/inactive devices to decrease its target
share over time.

It works well except in the case of "an inactive disk suddenly goes
busy", where the initial target share may be too small. To mitigate
this, bdi_position_ratio() has the below line to raise a small
bdi_thresh when it's safe to do so, so that the disk be feed with enough
dirty pages for efficient IO and in turn fast rampup of bdi_thresh:

        bdi_thresh = max(bdi_thresh, (limit - dirty) / 8);

balance_dirty_pages() normally does negative feedback control which
adjusts ratelimit to balance the bdi dirty pages around the target.
In some extreme cases when that is not enough, it will have to block
the tasks completely until the bdi dirty pages drop below bdi_thresh.
Acked-by: NJan Kara <jack@suse.cz>
Acked-by: NPeter Zijlstra <a.p.zijlstra@chello.nl>
Signed-off-by: NWu Fengguang <fengguang.wu@intel.com>
      aed21ad2
  15. 05 12月, 2011 1 次提交
  17. 02 12月, 2011 1 次提交
  19. 24 11月, 2011 3 次提交
  21. 23 11月, 2011 2 次提交
    • T
      percpu: fix chunk range calculation · a855b84c
      由 Tejun Heo 提交于 
      Percpu allocator recorded the cpus which map to the first and last
units in pcpu_first/last_unit_cpu respectively and used them to
determine the address range of a chunk - e.g. it assumed that the
first unit has the lowest address in a chunk while the last unit has
the highest address.

This simply isn't true.  Groups in a chunk can have arbitrary positive
or negative offsets from the previous one and there is no guarantee
that the first unit occupies the lowest offset while the last one the
highest.

Fix it by actually comparing unit offsets to determine cpus occupying
the lowest and highest offsets.  Also, rename pcu_first/last_unit_cpu
to pcpu_low/high_unit_cpu to avoid confusion.

The chunk address range is used to flush cache on vmalloc area
map/unmap and decide whether a given address is in the first chunk by
per_cpu_ptr_to_phys() and the bug was discovered by invalid
per_cpu_ptr_to_phys() translation for crash_note.

Kudos to Dave Young for tracking down the problem.
Signed-off-by: NTejun Heo <tj@kernel.org>
Reported-by: NWANG Cong <xiyou.wangcong@gmail.com>
Reported-by: NDave Young <dyoung@redhat.com>
Tested-by: NDave Young <dyoung@redhat.com>
LKML-Reference: <4EC21F67.10905@redhat.com>
Cc: stable @kernel.org
      a855b84c
    • B
      percpu: rename pcpu_mem_alloc to pcpu_mem_zalloc · 90459ce0
      由 Bob Liu 提交于 
      Currently pcpu_mem_alloc() is implemented always return zeroed memory.
So rename it to make user like pcpu_get_pages_and_bitmap() know don't
reinit it.
Signed-off-by: NBob Liu <lliubbo@gmail.com>
Reviewed-by: NPekka Enberg <penberg@kernel.org>
Reviewed-by: NMichal Hocko <mhocko@suse.cz>
Signed-off-by: NTejun Heo <tj@kernel.org>
      90459ce0
  23. 17 11月, 2011 3 次提交
    • W
      writeback: remove vm_dirties and task->dirties · 468e6a20
      由 Wu Fengguang 提交于 
      They are not used any more.
Signed-off-by: NWu Fengguang <fengguang.wu@intel.com>
      468e6a20
    • W
      writeback: hard throttle 1000+ dd on a slow USB stick · 1df64719
      由 Wu Fengguang 提交于 
      The sleep based balance_dirty_pages() can pause at most MAX_PAUSE=200ms
on every 1 4KB-page, which means it cannot throttle a task under
4KB/200ms=20KB/s. So when there are more than 512 dd writing to a
10MB/s USB stick, its bdi dirty pages could grow out of control.

Even if we can increase MAX_PAUSE, the minimal (task_ratelimit = 1)
means a limit of 4KB/s.
                                                       
They can eventually be safeguarded by the global limit check 
(nr_dirty < dirty_thresh). However if someone is also writing to an 
HDD at the same time, it'll get poor HDD write performance.
                                                       
We at least want to maintain good write performance for other devices
when one device is attacked by some "massive parallel" workload, or
suffers from slow write bandwidth, or somehow get stalled due to some 
error condition (eg. NFS server not responding).

For a stalled device, we need to completely block its dirtiers, too,
before its bdi dirty pages grow all the way up to the global limit and
leave no space for the other functional devices.

So change the loop exit condition to

	/*
	 * Always enforce global dirty limit; also enforce bdi dirty limit
	 * if the normal max_pause sleeps cannot keep things under control.
	 */
	if (nr_dirty < dirty_thresh &&
	    (bdi_dirty < bdi_thresh || bdi->dirty_ratelimit > 1))
		break;

which can be further simplified to

	if (task_ratelimit)
		break;
Signed-off-by: NWu Fengguang <fengguang.wu@intel.com>
      1df64719
    • D
      xen: map foreign pages for shared rings by updating the PTEs directly · cd12909c
      由 David Vrabel 提交于 
      When mapping a foreign page with xenbus_map_ring_valloc() with the
GNTTABOP_map_grant_ref hypercall, set the GNTMAP_contains_pte flag and
pass a pointer to the PTE (in init_mm).

After the page is mapped, the usual fault mechanism can be used to
update additional MMs.  This allows the vmalloc_sync_all() to be
removed from alloc_vm_area().
Signed-off-by: NDavid Vrabel <david.vrabel@citrix.com>
Acked-by: NAndrew Morton <akpm@linux-foundation.org>
[v1: Squashed fix by Michal for no-mmu case]
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: NMichal Simek <monstr@monstr.eu>
      cd12909c
  25. 16 11月, 2011 5 次提交
  27. 11 11月, 2011 1 次提交
    • R
      backing-dev: ensure wakeup_timer is deleted · 7a401a97
      由 Rabin Vincent 提交于 
      bdi_prune_sb() in bdi_unregister() attempts to removes the bdi links
from all super_blocks and then del_timer_sync() the writeback timer.

However, this can race with __mark_inode_dirty(), leading to
bdi_wakeup_thread_delayed() rearming the writeback timer on the bdi
we're unregistering, after we've called del_timer_sync().

This can end up with the bdi being freed with an active timer inside it,
as in the case of the following dump after the removal of an SD card.

Fix this by redoing the del_timer_sync() in bdi_destory().

 ------------[ cut here ]------------
 WARNING: at /home/rabin/kernel/arm/lib/debugobjects.c:262 debug_print_object+0x9c/0xc8()
 ODEBUG: free active (active state 0) object type: timer_list hint: wakeup_timer_fn+0x0/0x180
 Modules linked in:
 Backtrace:
 [<c00109dc>] (dump_backtrace+0x0/0x110) from [<c0236e4c>] (dump_stack+0x18/0x1c)
  r6:c02bc638 r5:00000106 r4:c79f5d18 r3:00000000
 [<c0236e34>] (dump_stack+0x0/0x1c) from [<c0025e6c>] (warn_slowpath_common+0x54/0x6c)
 [<c0025e18>] (warn_slowpath_common+0x0/0x6c) from [<c0025f28>] (warn_slowpath_fmt+0x38/0x40)
  r8:20000013 r7:c780c6f0 r6:c031613c r5:c780c6f0 r4:c02b1b29
 r3:00000009
 [<c0025ef0>] (warn_slowpath_fmt+0x0/0x40) from [<c015eb4c>] (debug_print_object+0x9c/0xc8)
  r3:c02b1b29 r2:c02bc662
 [<c015eab0>] (debug_print_object+0x0/0xc8) from [<c015f574>] (debug_check_no_obj_freed+0xac/0x1dc)
  r6:c7964000 r5:00000001 r4:c7964000
 [<c015f4c8>] (debug_check_no_obj_freed+0x0/0x1dc) from [<c00a9e38>] (kmem_cache_free+0x88/0x1f8)
 [<c00a9db0>] (kmem_cache_free+0x0/0x1f8) from [<c014286c>] (blk_release_queue+0x70/0x78)
 [<c01427fc>] (blk_release_queue+0x0/0x78) from [<c015290c>] (kobject_release+0x70/0x84)
  r5:c79641f0 r4:c796420c
 [<c015289c>] (kobject_release+0x0/0x84) from [<c0153ce4>] (kref_put+0x68/0x80)
  r7:00000083 r6:c74083d0 r5:c015289c r4:c796420c
 [<c0153c7c>] (kref_put+0x0/0x80) from [<c01527d0>] (kobject_put+0x48/0x5c)
  r5:c79643b4 r4:c79641f0
 [<c0152788>] (kobject_put+0x0/0x5c) from [<c013ddd8>] (blk_cleanup_queue+0x68/0x74)
  r4:c7964000
 [<c013dd70>] (blk_cleanup_queue+0x0/0x74) from [<c01a6370>] (mmc_blk_put+0x78/0xe8)
  r5:00000000 r4:c794c400
 [<c01a62f8>] (mmc_blk_put+0x0/0xe8) from [<c01a64b4>] (mmc_blk_release+0x24/0x38)
  r5:c794c400 r4:c0322824
 [<c01a6490>] (mmc_blk_release+0x0/0x38) from [<c00de11c>] (__blkdev_put+0xe8/0x170)
  r5:c78d5e00 r4:c74083c0
 [<c00de034>] (__blkdev_put+0x0/0x170) from [<c00de2c0>] (blkdev_put+0x11c/0x12c)
  r8:c79f5f70 r7:00000001 r6:c74083d0 r5:00000083 r4:c74083c0
 r3:00000000
 [<c00de1a4>] (blkdev_put+0x0/0x12c) from [<c00b0724>] (kill_block_super+0x60/0x6c)
  r7:c7942300 r6:c79f4000 r5:00000083 r4:c74083c0
 [<c00b06c4>] (kill_block_super+0x0/0x6c) from [<c00b0a94>] (deactivate_locked_super+0x44/0x70)
  r6:c79f4000 r5:c031af64 r4:c794dc00 r3:c00b06c4
 [<c00b0a50>] (deactivate_locked_super+0x0/0x70) from [<c00b1358>] (deactivate_super+0x6c/0x70)
  r5:c794dc00 r4:c794dc00
 [<c00b12ec>] (deactivate_super+0x0/0x70) from [<c00c88b0>] (mntput_no_expire+0x188/0x194)
  r5:c794dc00 r4:c7942300
 [<c00c8728>] (mntput_no_expire+0x0/0x194) from [<c00c95e0>] (sys_umount+0x2e4/0x310)
  r6:c7942300 r5:00000000 r4:00000000 r3:00000000
 [<c00c92fc>] (sys_umount+0x0/0x310) from [<c000d940>] (ret_fast_syscall+0x0/0x30)
 ---[ end trace e5c83c92ada51c76 ]---

Cc: stable@kernel.org
Signed-off-by: NRabin Vincent <rabin.vincent@stericsson.com>
Signed-off-by: NLinus Walleij <linus.walleij@linaro.org>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
      7a401a97