05 Oct, 2016
2 commits
-
in order to ensure the percpu group areas within a chunk aren't
distributed too sparsely, pcpu_embed_first_chunk() goes to error handling
path when a chunk spans over 3/4 VMALLOC area, however, during the error
handling, it forget to free the memory allocated for all percpu groups by
going to label @out_free other than @out_free_areas.it will cause memory leakage issue if the rare scene really happens, in
order to fix the issue, we check chunk spanned area immediately after
completing memory allocation for all percpu groups, we go to label
@out_free_areas to free the memory then return if the checking is failed.in order to verify the approach, we dump all memory allocated then
enforce the jump then dump all memory freed, the result is okay after
checking whether we free all memory we allocate in this function.BTW, The approach is chosen after thinking over the below scenes
- we don't go to label @out_free directly to fix this issue since we
maybe free several allocated memory blocks twice
- the aim of jumping after pcpu_setup_first_chunk() is bypassing free
usable memory other than handling error, moreover, the function does
not return error code in any case, it either panics due to BUG_ON()
or return 0.Signed-off-by: zijun_hu
Tested-by: zijun_hu
Signed-off-by: Tejun Heo -
pcpu_embed_first_chunk() calculates the range a percpu chunk spans into
@max_distance and uses it to ensure that a chunk is not too big compared
to the total vmalloc area. However, during calculation, it used incorrect
top address by adding a unit size to the highest group's base address.This can make the calculated max_distance slightly smaller than the actual
distance although given the scale of values involved the error is very
unlikely to have an actual impact.Fix this issue by adding the group's size instead of a unit size.
BTW, The type of variable max_distance is changed from size_t to unsigned
long too based on below consideration:
- type unsigned long usually have same width with IP core registers and
can be applied at here very well
- make @max_distance type consistent with the operand calculated against
it such as @ai->groups[i].base_offset and macro VMALLOC_TOTAL
- type unsigned long is more universal then size_t, size_t is type defined
to unsigned int or unsigned long among various ARCHs usuallySigned-off-by: zijun_hu
Signed-off-by: Tejun Heo
25 May, 2016
2 commits
-
For non-atomic allocations, pcpu_alloc() can try to extend the area
map synchronously after dropping pcpu_lock; however, the extension
wasn't synchronized against chunk destruction and the chunk might get
freed while extension is in progress.This patch fixes the bug by putting most of non-atomic allocations
under pcpu_alloc_mutex to synchronize against pcpu_balance_work which
is responsible for async chunk management including destruction.Signed-off-by: Tejun Heo
Reported-and-tested-by: Alexei Starovoitov
Reported-by: Vlastimil Babka
Reported-by: Sasha Levin
Cc: stable@vger.kernel.org # v3.18+
Fixes: 1a4d76076cda ("percpu: implement asynchronous chunk population") -
Atomic allocations can trigger async map extensions which is serviced
by chunk->map_extend_work. pcpu_balance_work which is responsible for
destroying idle chunks wasn't synchronizing properly against
chunk->map_extend_work and may end up freeing the chunk while the work
item is still in flight.This patch fixes the bug by rolling async map extension operations
into pcpu_balance_work.Signed-off-by: Tejun Heo
Reported-and-tested-by: Alexei Starovoitov
Reported-by: Vlastimil Babka
Reported-by: Sasha Levin
Cc: stable@vger.kernel.org # v3.18+
Fixes: 9c824b6a172c ("percpu: make sure chunk->map array has available space")
18 Mar, 2016
4 commits
-
Use the normal mechanism to make the logging output consistently
"percpu:" instead of a mix of "PERCPU:" and "percpu:"Signed-off-by: Joe Perches
Acked-by: Tejun Heo
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Most of the mm subsystem uses pr_ so make it consistent.
Miscellanea:
- Realign arguments
- Add missing newline to format
- kmemleak-test.c has a "kmemleak: " prefix added to the
"Kmemleak testing" logging message via pr_fmtSigned-off-by: Joe Perches
Acked-by: Tejun Heo [percpu]
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
Kernel style prefers a single string over split strings when the string is
'user-visible'.Miscellanea:
- Add a missing newline
- Realign argumentsSigned-off-by: Joe Perches
Acked-by: Tejun Heo [percpu]
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds -
There are a mixture of pr_warning and pr_warn uses in mm. Use pr_warn
consistently.Miscellanea:
- Coalesce formats
- Realign argumentsSigned-off-by: Joe Perches
Acked-by: Tejun Heo [percpu]
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
23 Jan, 2016
1 commit
-
There are many locations that do
if (memory_was_allocated_by_vmalloc)
vfree(ptr);
else
kfree(ptr);but kvfree() can handle both kmalloc()ed memory and vmalloc()ed memory
using is_vmalloc_addr(). Unless callers have special reasons, we can
replace this branch with kvfree(). Please check and reply if you found
problems.Signed-off-by: Tetsuo Handa
Acked-by: Michal Hocko
Acked-by: Jan Kara
Acked-by: Russell King
Reviewed-by: Andreas Dilger
Acked-by: "Rafael J. Wysocki"
Acked-by: David Rientjes
Cc: "Luck, Tony"
Cc: Oleg Drokin
Cc: Boris Petkov
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
06 Nov, 2015
1 commit
-
linux/mm.h provides offset_in_page() macro. Let's use already predefined
macro instead of (addr & ~PAGE_MASK).Signed-off-by: Alexander Kuleshov
Acked-by: Tejun Heo
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
21 Jul, 2015
1 commit
-
The original assignment is a little redundent.
Signed-off-by: Baoquan He
Acked-by: Christoph Lameter
Signed-off-by: Tejun Heo
25 Jun, 2015
1 commit
-
Beginning at commit d52d3997f843 ("ipv6: Create percpu rt6_info"), the
following INFO splat is logged:===============================
[ INFO: suspicious RCU usage. ]
4.1.0-rc7-next-20150612 #1 Not tainted
-------------------------------
kernel/sched/core.c:7318 Illegal context switch in RCU-bh read-side critical section!
other info that might help us debug this:
rcu_scheduler_active = 1, debug_locks = 0
3 locks held by systemd/1:
#0: (rtnl_mutex){+.+.+.}, at: [] rtnetlink_rcv+0x1f/0x40
#1: (rcu_read_lock_bh){......}, at: [] ipv6_add_addr+0x62/0x540
#2: (addrconf_hash_lock){+...+.}, at: [] ipv6_add_addr+0x184/0x540
stack backtrace:
CPU: 0 PID: 1 Comm: systemd Not tainted 4.1.0-rc7-next-20150612 #1
Hardware name: TOSHIBA TECRA A50-A/TECRA A50-A, BIOS Version 4.20 04/17/2014
Call Trace:
dump_stack+0x4c/0x6e
lockdep_rcu_suspicious+0xe7/0x120
___might_sleep+0x1d5/0x1f0
__might_sleep+0x4d/0x90
kmem_cache_alloc+0x47/0x250
create_object+0x39/0x2e0
kmemleak_alloc_percpu+0x61/0xe0
pcpu_alloc+0x370/0x630Additional backtrace lines are truncated. In addition, the above splat
is followed by several "BUG: sleeping function called from invalid
context at mm/slub.c:1268" outputs. As suggested by Martin KaFai Lau,
these are the clue to the fix. Routine kmemleak_alloc_percpu() always
uses GFP_KERNEL for its allocations, whereas it should follow the gfp
from its callers.Reviewed-by: Catalin Marinas
Reviewed-by: Kamalesh Babulal
Acked-by: Martin KaFai Lau
Signed-off-by: Larry Finger
Cc: Martin KaFai Lau
Cc: Catalin Marinas
Cc: Tejun Heo
Cc: Christoph Lameter
Cc: [3.18+]
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
25 Mar, 2015
1 commit
-
Change 'tranlated' to 'translated'
Change 'mutliples' to 'multiples'Signed-off-by: Yannick Guerrini
Signed-off-by: Tejun Heo
14 Feb, 2015
1 commit
-
printk and friends can now format bitmaps using '%*pb[l]'. cpumask
and nodemask also provide cpumask_pr_args() and nodemask_pr_args()
respectively which can be used to generate the two printf arguments
necessary to format the specified cpu/nodemask.Signed-off-by: Tejun Heo
Cc: Christoph Lameter
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
29 Oct, 2014
1 commit
-
The unit_map[] array has "nr_cpu_ids" number of elements. It's
allocated a few lines earlier in the function. So this test should be
>= instead of >.Signed-off-by: Dan Carpenter
Signed-off-by: Tejun Heo
09 Oct, 2014
1 commit
-
When @gfp is specified, the percpu allocator is interested in whether
it contains all of GFP_KERNEL or not. If it does, the normal
allocation path is taken; otherwise, the atomic allocation path.
Unfortunately, pcpu_alloc() was incorrectly testing for whether @gfp
contains any part of GFP_KERNEL.Fix it by testing "(gfp & GFP_KERNEL) != GFP_KERNEL" instead of
"!(gfp & GFP_KERNEL)" to decide whether the allocation should be
atomic or not.Signed-off-by: Tejun Heo
22 Sep, 2014
1 commit
-
This reverts commit 3189eddbcafc ("percpu: free percpu allocation info for
uniprocessor system").The commit causes a hang with a crisv32 image. This may be an architecture
problem, but at least for now the revert is necessary to be able to boot a
crisv32 image.Cc: Tejun Heo
Cc: Honggang Li
Signed-off-by: Guenter Roeck
Signed-off-by: Tejun Heo
Fixes: 3189eddbcafc ("percpu: free percpu allocation info for uniprocessor system")
Cc: stable@vger.kernel.org # Please don't apply 3189eddbcafc
09 Sep, 2014
1 commit
-
While updating locking, b38d08f3181c ("percpu: restructure locking")
broke pcpu_create_chunk() creation path in pcpu_alloc(). It returns
without releasing pcpu_alloc_mutex. Fix it.Signed-off-by: Tejun Heo
Reported-by: Julia Lawall
03 Sep, 2014
10 commits
-
The percpu allocator now supports atomic allocations by only
allocating from already populated areas but the mechanism to ensure
that there's adequate amount of populated areas was missing.This patch expands pcpu_balance_work so that in addition to freeing
excess free chunks it also populates chunks to maintain an adequate
level of populated areas. pcpu_alloc() schedules pcpu_balance_work if
the amount of free populated areas is too low or after an atomic
allocation failure.* PERPCU_DYNAMIC_RESERVE is increased by two pages to account for
PCPU_EMPTY_POP_PAGES_LOW.* pcpu_async_enabled is added to gate both async jobs -
chunk->map_extend_work and pcpu_balance_work - so that we don't end
up scheduling them while the needed subsystems aren't up yet.Signed-off-by: Tejun Heo
-
pcpu_reclaim_work will also be used to populate chunks asynchronously.
Rename it to pcpu_balance_work in preparation. pcpu_reclaim() is
renamed to pcpu_balance_workfn() and some of its local variables are
renamed too.This is pure rename.
Signed-off-by: Tejun Heo
-
pcpu_nr_empty_pop_pages counts the number of empty populated pages
across all chunks and chunk->nr_populated counts the number of
populated pages in a chunk. Both will be used to implement pre/async
population for atomic allocations.pcpu_chunk_[de]populated() are added to update chunk->populated,
chunk->nr_populated and pcpu_nr_empty_pop_pages together. All
successful chunk [de]populations should be followed by the
corresponding pcpu_chunk_[de]populated() calls.Signed-off-by: Tejun Heo
-
An allocation attempt may require extending chunk->map array which
requires GFP_KERNEL context which isn't available for atomic
allocations. This patch ensures that chunk->map array usually keeps
some amount of available space by directly allocating buffer space
during GFP_KERNEL allocations and scheduling async extension during
atomic ones. This should make atomic allocation failures from map
space exhaustion rare.Signed-off-by: Tejun Heo
-
Now that pcpu_alloc_area() can allocate only from populated areas,
it's easy to add atomic allocation support to [__]alloc_percpu().
Update pcpu_alloc() so that it accepts @gfp and skips all the blocking
operations and allocates only from the populated areas if @gfp doesn't
contain GFP_KERNEL. New interface functions [__]alloc_percpu_gfp()
are added.While this means that atomic allocations are possible, this isn't
complete yet as there's no mechanism to ensure that certain amount of
populated areas is kept available and atomic allocations may keep
failing under certain conditions.Signed-off-by: Tejun Heo
-
The next patch will conditionalize the population block in
pcpu_alloc() which will end up making a rather large indentation
change obfuscating the actual logic change. This patch puts the block
under "if (true)" so that the next patch can avoid indentation
changes. The defintions of the local variables which are used only in
the block are moved into the block.This patch is purely cosmetic.
Signed-off-by: Tejun Heo
-
Update pcpu_alloc_area() so that it can skip unpopulated areas if the
new parameter @pop_only is true. This is implemented by a new
function, pcpu_fit_in_area(), which determines the amount of head
padding considering the alignment and populated state.@pop_only is currently always false but this will be used to implement
atomic allocation.Signed-off-by: Tejun Heo
-
At first, the percpu allocator required a sleepable context for both
alloc and free paths and used pcpu_alloc_mutex to protect everything.
Later, pcpu_lock was introduced to protect the index data structure so
that the free path can be invoked from atomic contexts. The
conversion only updated what's necessary and left most of the
allocation path under pcpu_alloc_mutex.The percpu allocator is planned to add support for atomic allocation
and this patch restructures locking so that the coverage of
pcpu_alloc_mutex is further reduced.* pcpu_alloc() now grab pcpu_alloc_mutex only while creating a new
chunk and populating the allocated area. Everything else is now
protected soley by pcpu_lock.After this change, multiple instances of pcpu_extend_area_map() may
race but the function already implements sufficient synchronization
using pcpu_lock.This also allows multiple allocators to arrive at new chunk
creation. To avoid creating multiple empty chunks back-to-back, a
new chunk is created iff there is no other empty chunk after
grabbing pcpu_alloc_mutex.* pcpu_lock is now held while modifying chunk->populated bitmap.
After this, all data structures are protected by pcpu_lock.Signed-off-by: Tejun Heo
-
Previously, pcpu_[de]populate_chunk() were called with the range which
may contain multiple target regions in it and
pcpu_[de]populate_chunk() iterated over the regions. This has the
benefit of batching up cache flushes for all the regions; however,
we're planning to add more bookkeeping logic around [de]population to
support atomic allocations and this delegation of iterations gets in
the way.This patch moves the region iterations out of
pcpu_[de]populate_chunk() into its callers - pcpu_alloc() and
pcpu_reclaim() - so that we can later add logic to track more states
around them. This change may make cache and tlb flushes more frequent
but multi-region [de]populations are rare anyway and if this actually
becomes a problem, it's not difficult to factor out cache flushes as
separate callbacks which are directly invoked from percpu.c.Signed-off-by: Tejun Heo
-
percpu-vm and percpu-km implement separate versions of
pcpu_[de]populate_chunk() and some part which is or should be common
are currently in the specific implementations. Make the following
changes.* Allocate area clearing is moved from the pcpu_populate_chunk()
implementations to pcpu_alloc(). This makes percpu-km's version
noop.* Quick exit tests in pcpu_[de]populate_chunk() of percpu-vm are moved
to their respective callers so that they are applied to percpu-km
too. This doesn't make any meaningful difference as both functions
are noop for percpu-km; however, this is more consistent and will
help implementing atomic allocation support.Signed-off-by: Tejun Heo
16 Aug, 2014
1 commit
-
Currently, only SMP system free the percpu allocation info.
Uniprocessor system should free it too. For example, one x86 UML
virtual machine with 256MB memory, UML kernel wastes one page memory.Signed-off-by: Honggang Li
Signed-off-by: Tejun Heo
Cc: stable@vger.kernel.org
19 Jun, 2014
1 commit
-
Signed-off-by: Christoph Lameter
Signed-off-by: Tejun Heo
15 Apr, 2014
1 commit
-
pcpu_chunk_struct_size = sizeof(struct pcpu_chunk) +
BITS_TO_LONGS(pcpu_unit_pages) * sizeof(unsigned long)It hardly could be ever bigger than PAGE_SIZE even for large-scale machine,
but for consistency with its couterpart pcpu_mem_zalloc(),
use pcpu_mem_free() instead.Commit b4916cb17c26 ("percpu: make pcpu_free_chunk() use
pcpu_mem_free() instead of kfree()") addressed this problem, but
missed this one.tj: commit message updated
Signed-off-by: Jianyu Zhan
Signed-off-by: Tejun Heo
Fixes: 099a19d91ca4 ("percpu: allow limited allocation before slab is online)
Cc: stable@vger.kernel.org
29 Mar, 2014
1 commit
-
During pcpu_alloc_area(), we might merge the current head with the
previous block. Since we have calculated the max_contig using the
size of previous block before we skip it, and now we update the size
of previous block, so we should renew the max_contig.Signed-off-by: Jianyu Zhan
Signed-off-by: Tejun Heo
18 Mar, 2014
1 commit
-
723ad1d90b56 ("percpu: store offsets instead of lengths in ->map[]")
updated percpu area allocator to use the lowest bit, instead of sign,
to signify whether the area is occupied and forced min align to 2;
unfortunately, it forgot to force the allocation size to be even
causing malfunctions for the very rare odd-sized allocations.Always force the allocations to be even sized.
tj: Wrote patch description.
Original-patch-by: Al Viro
Signed-off-by: Tejun Heo
07 Mar, 2014
3 commits
-
If we know that first N areas are all in use, we can obviously skip
them when searching for a free one. And that kind of hint is very
easy to maintain.Signed-off-by: Al Viro
Signed-off-by: Tejun Heo -
Current code keeps +-length for each area in chunk->map[]. It has
several unpleasant consequences:
* even if we know that first 50 areas are all in use, allocation
still needs to go through all those areas just to sum their sizes, just
to get the offset of free one.
* freeing needs to find the array entry refering to the area
in question; again, the need to sum the sizes until we reach the offset
we are interested in. Note that offsets are monotonous, so simple
binary search would do here.New data representation: array of pairs.
Each pair is represented by one int - we use offset|1 for
and offset for (we make sure that all offsets are even).
In the end we put a sentry entry - . The first
entry is ; it would be possible to store together the flag
for Nth area and offset for N+1st, but that leads to much hairier code.In other words, where the old variant would have
4, -8, -4, 4, -12, 100
(4 bytes free, 8 in use, 4 in use, 4 free, 12 in use, 100 free) we store
, , , , , ,
i.e.
0, 5, 13, 16, 21, 32, 133This commit switches to new data representation and takes care of a couple
of low-hanging fruits in free_pcpu_area() - one is the switch to binary
search, another is not doing two memmove() when one would do. Speeding
the alloc side up (by keeping track of how many areas in the beginning are
known to be all in use) also becomes possible - that'll be done in the next
commit.Signed-off-by: Al Viro
Signed-off-by: Tejun Heo -
... and simplify the results a bit. Makes the next step easier
to deal with - we will be changing the data representation for
chunk->map[] and it's easier to do if the code in question is
not split between pcpu_alloc_area() and pcpu_split_block().Signed-off-by: Al Viro
Signed-off-by: Tejun Heo
22 Jan, 2014
2 commits
-
Merge first patch-bomb from Andrew Morton:
- a couple of misc things
- inotify/fsnotify work from Jan
- ocfs2 updates (partial)
- about half of MM
* emailed patches from Andrew Morton : (117 commits)
mm/migrate: remove unused function, fail_migrate_page()
mm/migrate: remove putback_lru_pages, fix comment on putback_movable_pages
mm/migrate: correct failure handling if !hugepage_migration_support()
mm/migrate: add comment about permanent failure path
mm, page_alloc: warn for non-blockable __GFP_NOFAIL allocation failure
mm: compaction: reset scanner positions immediately when they meet
mm: compaction: do not mark unmovable pageblocks as skipped in async compaction
mm: compaction: detect when scanners meet in isolate_freepages
mm: compaction: reset cached scanner pfn's before reading them
mm: compaction: encapsulate defer reset logic
mm: compaction: trace compaction begin and end
memcg, oom: lock mem_cgroup_print_oom_info
sched: add tracepoints related to NUMA task migration
mm: numa: do not automatically migrate KSM pages
mm: numa: trace tasks that fail migration due to rate limiting
mm: numa: limit scope of lock for NUMA migrate rate limiting
mm: numa: make NUMA-migrate related functions static
lib/show_mem.c: show num_poisoned_pages when oom
mm/hwpoison: add '#' to hwpoison_inject
mm/memblock: use WARN_ONCE when MAX_NUMNODES passed as input parameter
... -
Switch to memblock interfaces for early memory allocator instead of
bootmem allocator. No functional change in beahvior than what it is in
current code from bootmem users points of view.Archs already converted to NO_BOOTMEM now directly use memblock
interfaces instead of bootmem wrappers build on top of memblock. And
the archs which still uses bootmem, these new apis just fallback to
exiting bootmem APIs.Signed-off-by: Santosh Shilimkar
Cc: "Rafael J. Wysocki"
Cc: Arnd Bergmann
Cc: Christoph Lameter
Cc: Greg Kroah-Hartman
Cc: Grygorii Strashko
Cc: H. Peter Anvin
Cc: Johannes Weiner
Cc: KAMEZAWA Hiroyuki
Cc: Konrad Rzeszutek Wilk
Cc: Michal Hocko
Cc: Paul Walmsley
Cc: Pavel Machek
Cc: Russell King
Cc: Tejun Heo
Cc: Tony Lindgren
Cc: Yinghai Lu
Signed-off-by: Andrew Morton
Signed-off-by: Linus Torvalds
21 Jan, 2014
1 commit
-
vmalloc already gives a useful macro to calculate the total vmalloc
size. Use it.Signed-off-by: Laura Abbott
Signed-off-by: Tejun Heo
23 Sep, 2013
1 commit
-
If memory allocation of in pcpu_embed_first_chunk() fails, the
allocated memory is not released correctly. In the release loop also
the non-allocated elements are released which leads to the following
kernel BUG on systems with very little memory:[ 0.000000] kernel BUG at mm/bootmem.c:307!
[ 0.000000] illegal operation: 0001 [#1] PREEMPT SMP DEBUG_PAGEALLOC
[ 0.000000] Modules linked in:
[ 0.000000] CPU: 0 PID: 0 Comm: swapper Not tainted 3.10.0 #22
[ 0.000000] task: 0000000000a20ae0 ti: 0000000000a08000 task.ti: 0000000000a08000
[ 0.000000] Krnl PSW : 0400000180000000 0000000000abda7a (__free+0x116/0x154)
[ 0.000000] R:0 T:1 IO:0 EX:0 Key:0 M:0 W:0 P:0 AS:0 CC:0 PM:0 EA:3
...
[ 0.000000] [] mark_bootmem_node+0xde/0xf0
[ 0.000000] [] mark_bootmem+0xa8/0x118
[ 0.000000] [] pcpu_embed_first_chunk+0xe7a/0xf0c
[ 0.000000] [] setup_per_cpu_areas+0x4a/0x28cTo fix the problem now only allocated elements are released. This then
leads to the correct kernel panic:[ 0.000000] Kernel panic - not syncing: Failed to initialize percpu areas.
...
[ 0.000000] Call Trace:
[ 0.000000] ([] show_trace+0x132/0x150)
[ 0.000000] [] show_stack+0xc4/0xd4
[ 0.000000] [] dump_stack+0x74/0xd8
[ 0.000000] [] panic+0xea/0x264
[ 0.000000] [] setup_per_cpu_areas+0x5c/0x28ctj: Flipped if conditional so that it doesn't need "continue".
Signed-off-by: Michael Holzheu
Signed-off-by: Tejun Heo
