These BUG_ON tests are to ensure that all the tags are clear when
inserting a new entry. If we insert a multiorder entry, we'll end up
looking at the tags for a different node, and so the BUG_ON can end up
triggering spuriously.
Also, we now have three tags, not two, so check all three are clear, and
check all the root tags with a single call to BUG_ON since the bits are
stored contiguously.
Include a test-case to ensure this problem does not reoccur.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Kirill Shutemov <kirill.shutemov@linux.intel.com>
Cc: Jan Kara <jack@suse.com>
Cc: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Use the new multi-order support functions to rewrite __radix_tree_lookup()
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Kirill Shutemov <kirill.shutemov@linux.intel.com>
Cc: Jan Kara <jack@suse.com>
Cc: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Setting the indirect bit on the user data entry used to be unambiguous
because the tree walking code knew not to expect internal nodes in the
last level of the tree. Multiorder entries can appear at any level of
the tree, and a leaf with the indirect bit set is indistinguishable from
a pointer to a node.
Introduce a special entry (RADIX_TREE_RETRY) which is neither a valid
user entry, nor a valid pointer to a node. The radix_tree_deref_retry()
function continues to work the same way, but tree walking code can
distinguish it from a pointer to a node.
Also fix the condition for setting slot->parent to NULL; it does not
matter what height the tree is, it only matters whether slot is an
indirect pointer. Move this code above the comment which is referring
to the assignment to root->rnode.
Also fix the condition for preventing the tree from shrinking to a
single entry if it's a multiorder entry.
Add a test-case to the test suite that checks that the tree goes back
down to its original height after an item is inserted & deleted from a
higher index in the tree.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Kirill Shutemov <kirill.shutemov@linux.intel.com>
Cc: Jan Kara <jack@suse.com>
Cc: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The current code will insert entries at each level, as if we're going to
add a new entry at the bottom level, so we then get an -EEXIST when we
try to insert the entry into the tree. The best way to fix this is to
not check 'order' when inserting into an empty tree.
We still need to 'extend' the tree to the height necessary for the maximum
index corresponding to this entry, so pass that value to
radix_tree_extend() rather than the index we're asked to create, or we
won't create a tree that's deep enough.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Kirill Shutemov <kirill.shutemov@linux.intel.com>
Cc: Jan Kara <jack@suse.com>
Cc: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
All the tree walking functions start with some variant of this code;
centralise it in one place so we're not chasing subtly different bugs
everywhere.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Kirill Shutemov <kirill.shutemov@linux.intel.com>
Cc: Jan Kara <jack@suse.com>
Cc: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Now that sibling pointers are handled explicitly, there is no purpose
served by restricting the order to be >= RADIX_TREE_MAP_SHIFT.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Kirill Shutemov <kirill.shutemov@linux.intel.com>
Cc: Jan Kara <jack@suse.com>
Cc: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
If we deleted an entry through an index which looked up a sibling
pointer, we'd end up zeroing out the wrong slots in the node. Use
get_slot_offset() to find the right slot.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Kirill Shutemov <kirill.shutemov@linux.intel.com>
Cc: Jan Kara <jack@suse.com>
Cc: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The subtraction was the wrong way round, leading to undefined behaviour
(shift by an amount larger than the size of the type).
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Kirill Shutemov <kirill.shutemov@linux.intel.com>
Cc: Jan Kara <jack@suse.com>
Cc: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The code I previously added to enable multiorder radix tree entries was
untested and therefore buggy. This commit adds the support functions
that Ross and I decided were necessary over a four-week period of
iterating various designs.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Kirill Shutemov <kirill.shutemov@linux.intel.com>
Cc: Jan Kara <jack@suse.com>
Cc: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
I've been receiving increasingly concerned notes from 0day about how
much my recent changes have been bloating the radix tree. Make it
happier by only including multiorder support if
CONFIG_TRANSPARENT_HUGEPAGES is set.
This is an independent Kconfig option, so other radix tree users can
also set it if they have a need.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Reviewed-by: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Konstantin Khlebnikov <koct9i@gmail.com>
Cc: Kirill Shutemov <kirill.shutemov@linux.intel.com>
Cc: Jan Kara <jack@suse.com>
Cc: Neil Brown <neilb@suse.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This is debug code which is #if 0 out.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Wilcox <willy@linux.intel.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
With huge pages, it is convenient to have the radix tree be able to
return an entry that covers multiple indices. Previous attempts to deal
with the problem have involved inserting N duplicate entries, which is a
waste of memory and leads to problems trying to handle aliased tags, or
probing the tree multiple times to find alternative entries which might
cover the requested index.
This approach inserts one canonical entry into the tree for a given
range of indices, and may also insert other entries in order to ensure
that lookups find the canonical entry.
This solution only tolerates inserting powers of two that are greater
than the fanout of the tree. If we wish to expand the radix tree's
abilities to support large-ish pages that is less than the fanout at the
penultimate level of the tree, then we would need to add one more step
in lookup to ensure that any sibling nodes in the final level of the
tree are dereferenced and we return the canonical entry that they
reference.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Wilcox <willy@linux.intel.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
When we introduce entries that can cover multiple indices, we will need
to stop in __radix_tree_create based on the shift, not the height.
Split out for ease of bisect.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Wilcox <willy@linux.intel.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Set the 'indirect_ptr' bit on all the pointers to internal nodes, not
just on the root node. This enables the following patches to support
multi-order entries in the radix tree. This patch is split out for ease
of bisection.
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Matthew Wilcox <willy@linux.intel.com>
Cc: "Kirill A. Shutemov" <kirill.shutemov@linux.intel.com>
Cc: Ross Zwisler <ross.zwisler@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Allocation of radix_tree_node objects can be easily triggered from
userspace, so we should account them to memory cgroup. Besides, we need
them accounted for making shadow node shrinker per memcg (see
mm/workingset.c).
A tricky thing about accounting radix_tree_node objects is that they are
mostly allocated through radix_tree_preload(), so we can't just set
SLAB_ACCOUNT for radix_tree_node_cachep - that would likely result in a
lot of unrelated cgroups using objects from each other's caches.
One way to overcome this would be making radix tree preloads per memcg,
but that would probably look cumbersome and overcomplicated.
Instead, we make radix_tree_node_alloc() first try to allocate from the
cache with __GFP_ACCOUNT, no matter if the caller has preloaded or not,
and only if it fails fall back on using per cpu preloads. This should
make most allocations accounted.
Signed-off-by: Vladimir Davydov <vdavydov@virtuozzo.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
If the indirect_ptr bit is set on a slot, that indicates we need to redo
the lookup. Introduce a new function radix_tree_iter_retry() which
forces the loop to retry the lookup by setting 'slot' to NULL and
turning the iterator back to point at the problematic entry.
This is a pretty rare problem to hit at the moment; the lookup has to
race with a grow of the radix tree from a height of 0. The consequences
of hitting this race are that gang lookup could return a pointer to a
radix_tree_node instead of a pointer to whatever the user had inserted
in the tree.
Fixes: cebbd29e1c ("radix-tree: rewrite gang lookup using iterator")
Signed-off-by: Matthew Wilcox <willy@linux.intel.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Ohad Ben-Cohen <ohad@wizery.com>
Cc: Konstantin Khlebnikov <khlebnikov@openvz.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
__GFP_WAIT has been used to identify atomic context in callers that hold
spinlocks or are in interrupts. They are expected to be high priority and
have access one of two watermarks lower than "min" which can be referred
to as the "atomic reserve". __GFP_HIGH users get access to the first
lower watermark and can be called the "high priority reserve".
Over time, callers had a requirement to not block when fallback options
were available. Some have abused __GFP_WAIT leading to a situation where
an optimisitic allocation with a fallback option can access atomic
reserves.
This patch uses __GFP_ATOMIC to identify callers that are truely atomic,
cannot sleep and have no alternative. High priority users continue to use
__GFP_HIGH. __GFP_DIRECT_RECLAIM identifies callers that can sleep and
are willing to enter direct reclaim. __GFP_KSWAPD_RECLAIM to identify
callers that want to wake kswapd for background reclaim. __GFP_WAIT is
redefined as a caller that is willing to enter direct reclaim and wake
kswapd for background reclaim.
This patch then converts a number of sites
o __GFP_ATOMIC is used by callers that are high priority and have memory
pools for those requests. GFP_ATOMIC uses this flag.
o Callers that have a limited mempool to guarantee forward progress clear
__GFP_DIRECT_RECLAIM but keep __GFP_KSWAPD_RECLAIM. bio allocations fall
into this category where kswapd will still be woken but atomic reserves
are not used as there is a one-entry mempool to guarantee progress.
o Callers that are checking if they are non-blocking should use the
helper gfpflags_allow_blocking() where possible. This is because
checking for __GFP_WAIT as was done historically now can trigger false
positives. Some exceptions like dm-crypt.c exist where the code intent
is clearer if __GFP_DIRECT_RECLAIM is used instead of the helper due to
flag manipulations.
o Callers that built their own GFP flags instead of starting with GFP_KERNEL
and friends now also need to specify __GFP_KSWAPD_RECLAIM.
The first key hazard to watch out for is callers that removed __GFP_WAIT
and was depending on access to atomic reserves for inconspicuous reasons.
In some cases it may be appropriate for them to use __GFP_HIGH.
The second key hazard is callers that assembled their own combination of
GFP flags instead of starting with something like GFP_KERNEL. They may
now wish to specify __GFP_KSWAPD_RECLAIM. It's almost certainly harmless
if it's missed in most cases as other activity will wake kswapd.
Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Vitaly Wool <vitalywool@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Currently we use per-cpu array to hold pointers to preallocated nodes.
Let's replace it with linked list. On x86_64 it saves 256 bytes in
per-cpu ELF section which may translate into freeing up 2MB of memory for
NR_CPUS==8192.
[akpm@linux-foundation.org: fix comment, coding style]
Signed-off-by: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
preempt_mask.h defines all the preempt_count semantics and related
symbols: preempt, softirq, hardirq, nmi, preempt active, need resched,
etc...
preempt.h defines the accessors and mutators of preempt_count.
But there is a messy dependency game around those two header files:
* preempt_mask.h includes preempt.h in order to access preempt_count()
* preempt_mask.h defines all preempt_count semantic and symbols
except PREEMPT_NEED_RESCHED that is needed by asm/preempt.h
Thus we need to define it from preempt.h, right before including
asm/preempt.h, instead of defining it to preempt_mask.h with the
other preempt_count symbols. Therefore the preempt_count semantics
happen to be spread out.
* We plan to introduce preempt_active_[enter,exit]() to consolidate
preempt_schedule*() code. But we'll need to access both preempt_count
mutators (preempt_count_add()) and preempt_count symbols
(PREEMPT_ACTIVE, PREEMPT_OFFSET). The usual place to define preempt
operations is in preempt.h but then we'll need symbols in
preempt_mask.h which already includes preempt.h. So we end up with
a ressource circle dependency.
Lets merge preempt_mask.h into preempt.h to solve these dependency issues.
This way we gather semantic symbols and operation definition of
preempt_count in a single file.
This is a dumb copy-paste merge. Further merge re-arrangments are
performed in a subsequent patch to ease review.
Signed-off-by: Frederic Weisbecker <fweisbec@gmail.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1431441711-29753-2-git-send-email-fweisbec@gmail.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>
The comment helpfully explains why hardirq.h is included, but since
commit 2d4b84739f ("hardirq: Split preempt count mask definitions")
in_interrupt() has been provided by preempt_mask.h. Use that instead,
saving around 40 lines in the generated dependency file.
Signed-off-by: Rasmus Villemoes <linux@rasmusvillemoes.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Since radix_tree_preload() stack trace is not always useful for
debugging an actual radix tree memory leak, this patch updates the
kmemleak allocation stack trace in the radix_tree_node_alloc() function.
Signed-off-by: Catalin Marinas <catalin.marinas@arm.com>
Acked-by: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
index has been removed from __radix_tree_delete_node in 449dd6984d
("mm: keep page cache radix tree nodes in check")
Signed-off-by: Fabian Frederick <fabf@skynet.be>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Replace places where __get_cpu_var() is used for an address calculation
with this_cpu_ptr().
Signed-off-by: Christoph Lameter <cl@linux.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Previously, page cache radix tree nodes were freed after reclaim emptied
out their page pointers. But now reclaim stores shadow entries in their
place, which are only reclaimed when the inodes themselves are
reclaimed. This is problematic for bigger files that are still in use
after they have a significant amount of their cache reclaimed, without
any of those pages actually refaulting. The shadow entries will just
sit there and waste memory. In the worst case, the shadow entries will
accumulate until the machine runs out of memory.
To get this under control, the VM will track radix tree nodes
exclusively containing shadow entries on a per-NUMA node list. Per-NUMA
rather than global because we expect the radix tree nodes themselves to
be allocated node-locally and we want to reduce cross-node references of
otherwise independent cache workloads. A simple shrinker will then
reclaim these nodes on memory pressure.
A few things need to be stored in the radix tree node to implement the
shadow node LRU and allow tree deletions coming from the list:
1. There is no index available that would describe the reverse path
from the node up to the tree root, which is needed to perform a
deletion. To solve this, encode in each node its offset inside the
parent. This can be stored in the unused upper bits of the same
member that stores the node's height at no extra space cost.
2. The number of shadow entries needs to be counted in addition to the
regular entries, to quickly detect when the node is ready to go to
the shadow node LRU list. The current entry count is an unsigned
int but the maximum number of entries is 64, so a shadow counter
can easily be stored in the unused upper bits.
3. Tree modification needs tree lock and tree root, which are located
in the address space, so store an address_space backpointer in the
node. The parent pointer of the node is in a union with the 2-word
rcu_head, so the backpointer comes at no extra cost as well.
4. The node needs to be linked to an LRU list, which requires a list
head inside the node. This does increase the size of the node, but
it does not change the number of objects that fit into a slab page.
[akpm@linux-foundation.org: export the right function]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Make struct radix_tree_node part of the public interface and provide API
functions to create, look up, and delete whole nodes. Refactor the
existing insert, look up, delete functions on top of these new node
primitives.
This will allow the VM to track and garbage collect page cache radix
tree nodes.
[sasha.levin@oracle.com: return correct error code on insertion failure]
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The radix tree hole searching code is only used for page cache, for
example the readahead code trying to get a a picture of the area
surrounding a fault.
It sufficed to rely on the radix tree definition of holes, which is
"empty tree slot". But this is about to change, though, as shadow page
descriptors will be stored in the page cache after the actual pages get
evicted from memory.
Move the functions over to mm/filemap.c and make them native page cache
operations, where they can later be adapted to handle the new definition
of "page cache hole".
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Provide a function that does not just delete an entry at a given index,
but also allows passing in an expected item. Delete only if that item
is still located at the specified index.
This is handy when lockless tree traversals want to delete entries as
well because they don't have to do an second, locked lookup to verify
the slot has not changed under them before deleting the entry.
Signed-off-by: Johannes Weiner <hannes@cmpxchg.org>
Reviewed-by: Minchan Kim <minchan@kernel.org>
Reviewed-by: Rik van Riel <riel@redhat.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Christoph Hellwig <hch@infradead.org>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Greg Thelen <gthelen@google.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Cc: Luigi Semenzato <semenzato@google.com>
Cc: Metin Doslu <metin@citusdata.com>
Cc: Michel Lespinasse <walken@google.com>
Cc: Ozgun Erdogan <ozgun@citusdata.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Roman Gushchin <klamm@yandex-team.ru>
Cc: Ryan Mallon <rmallon@gmail.com>
Cc: Tejun Heo <tj@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Running fsx on tmpfs with concurrent memhog-swapoff-swapon, lots of
BUG: sleeping function called from invalid context at kernel/fork.c:606
in_atomic(): 0, irqs_disabled(): 0, pid: 1394, name: swapoff
1 lock held by swapoff/1394:
#0: (rcu_read_lock){.+.+.+}, at: [<ffffffff812520a1>] radix_tree_locate_item+0x1f/0x2b6
followed by
================================================
[ BUG: lock held when returning to user space! ]
3.14.0-rc1 #3 Not tainted
------------------------------------------------
swapoff/1394 is leaving the kernel with locks still held!
1 lock held by swapoff/1394:
#0: (rcu_read_lock){.+.+.+}, at: [<ffffffff812520a1>] radix_tree_locate_item+0x1f/0x2b6
after which the system recovered nicely.
Whoops, I long ago forgot the rcu_read_unlock() on one unlikely branch.
Fixes e504f3fdd6 ("tmpfs radix_tree: locate_item to speed up swapoff")
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
With users of radix_tree_preload() run from interrupt (block/blk-ioc.c is
one such possible user), the following race can happen:
radix_tree_preload()
...
radix_tree_insert()
radix_tree_node_alloc()
if (rtp->nr) {
ret = rtp->nodes[rtp->nr - 1];
<interrupt>
...
radix_tree_preload()
...
radix_tree_insert()
radix_tree_node_alloc()
if (rtp->nr) {
ret = rtp->nodes[rtp->nr - 1];
And we give out one radix tree node twice. That clearly results in radix
tree corruption with different results (usually OOPS) depending on which
two users of radix tree race.
We fix the problem by making radix_tree_node_alloc() always allocate fresh
radix tree nodes when in interrupt. Using preloading when in interrupt
doesn't make sense since all the allocations have to be atomic anyway and
we cannot steal nodes from process-context users because some users rely
on radix_tree_insert() succeeding after radix_tree_preload().
in_interrupt() check is somewhat ugly but we cannot simply key off passed
gfp_mask as that is acquired from root_gfp_mask() and thus the same for
all preload users.
Another part of the fix is to avoid node preallocation in
radix_tree_preload() when passed gfp_mask doesn't allow waiting. Again,
preallocation in such case doesn't make sense and when preallocation would
happen in interrupt we could possibly leak some allocated nodes. However,
some users of radix_tree_preload() require following radix_tree_insert()
to succeed. To avoid unexpected effects for these users,
radix_tree_preload() only warns if passed gfp mask doesn't allow waiting
and we provide a new function radix_tree_maybe_preload() for those users
which get different gfp mask from different call sites and which are
prepared to handle radix_tree_insert() failure.
Signed-off-by: Jan Kara <jack@suse.cz>
Cc: Jens Axboe <jaxboe@fusionio.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
This patch fixes bug in macro radix_tree_for_each_contig().
If radix_tree_next_slot() sees NULL in next slot it returns NULL, but following
radix_tree_next_chunk() switches iterating into next chunk. As result iterating
becomes non-contiguous and breaks vfs "splice" and all its users.
Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org>
Reported-and-bisected-by: Hans de Bruin <jmdebruin@xmsnet.nl>
Reported-and-bisected-by: Ondrej Zary <linux@rainbow-software.org>
Reported-bisected-and-tested-by: Toralf Förster <toralf.foerster@gmx.de>
Link: https://lkml.org/lkml/2012/6/5/64
Cc: stable <stable@vger.kernel.org> # 3.4.x
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We are not preallocating a sufficient number of nodes.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Rewrite radix_tree_gang_lookup_* functions using the new radix-tree
iterator.
Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org>
Tested-by: Hugh Dickins <hughd@google.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
A series of radix tree cleanups, and usage of them in the core pagecache
code.
Micro-benchmark:
lookup 14 slots (typical page-vector size)
in radix-tree there earch <step> slot filled and tagged
before/after - nsec per full scan through tree
* Intel Sandy Bridge i7-2620M 4Mb L3
New code always faster
* AMD Athlon 6000+ 2x1Mb L2, without L3
New code generally faster,
Minor degradation (marked with "*") for huge sparse trees
* i386 on Sandy Bridge
New code faster for common cases: tagged and dense trees.
Some degradations for non-tagged lookup on sparse trees.
Ideally, there might help __ffs() analog for searching first non-zero
long element in array, gcc sometimes cannot optimize this loop corretly.
Numbers:
CPU: Intel Sandy Bridge i7-2620M 4Mb L3
radix-tree with 1024 slots:
tagged lookup
step 1 before 7156 after 3613
step 2 before 5399 after 2696
step 3 before 4779 after 1928
step 4 before 4456 after 1429
step 5 before 4292 after 1213
step 6 before 4183 after 1052
step 7 before 4157 after 951
step 8 before 4016 after 812
step 9 before 3952 after 851
step 10 before 3937 after 732
step 11 before 4023 after 709
step 12 before 3872 after 657
step 13 before 3892 after 633
step 14 before 3720 after 591
step 15 before 3879 after 578
step 16 before 3561 after 513
normal lookup
step 1 before 4266 after 3301
step 2 before 2695 after 2129
step 3 before 2083 after 1712
step 4 before 1801 after 1534
step 5 before 1628 after 1313
step 6 before 1551 after 1263
step 7 before 1475 after 1185
step 8 before 1432 after 1167
step 9 before 1373 after 1092
step 10 before 1339 after 1134
step 11 before 1292 after 1056
step 12 before 1319 after 1030
step 13 before 1276 after 1004
step 14 before 1256 after 987
step 15 before 1228 after 992
step 16 before 1247 after 999
radix-tree with 1024*1024*128 slots:
tagged lookup
step 1 before 1086102841 after 674196409
step 2 before 816839155 after 498138306
step 7 before 599728907 after 240676762
step 15 before 555729253 after 185219677
step 63 before 606637748 after 128585664
step 64 before 608384432 after 102945089
step 65 before 596987114 after 123996019
step 128 before 304459225 after 56783056
step 256 before 158846855 after 31232481
step 512 before 86085652 after 18950595
step 12345 before 6517189 after 1674057
normal lookup
step 1 before 626064869 after 544418266
step 2 before 418809975 after 336321473
step 7 before 242303598 after 207755560
step 15 before 208380563 after 176496355
step 63 before 186854206 after 167283638
step 64 before 176188060 after 170143976
step 65 before 185139608 after 167487116
step 128 before 88181865 after 86913490
step 256 before 45733628 after 45143534
step 512 before 24506038 after 23859036
step 12345 before 2177425 after 2018662
* AMD Athlon 6000+ 2x1Mb L2, without L3
radix-tree with 1024 slots:
tag-lookup
step 1 before 8164 after 5379
step 2 before 5818 after 5581
step 3 before 4959 after 4213
step 4 before 4371 after 3386
step 5 before 4204 after 2997
step 6 before 4950 after 2744
step 7 before 4598 after 2480
step 8 before 4251 after 2288
step 9 before 4262 after 2243
step 10 before 4175 after 2131
step 11 before 3999 after 2024
step 12 before 3979 after 1994
step 13 before 3842 after 1929
step 14 before 3750 after 1810
step 15 before 3735 after 1810
step 16 before 3532 after 1660
normal-lookup
step 1 before 7875 after 5847
step 2 before 4808 after 4071
step 3 before 4073 after 3462
step 4 before 3677 after 3074
step 5 before 4308 after 2978
step 6 before 3911 after 3807
step 7 before 3635 after 3522
step 8 before 3313 after 3202
step 9 before 3280 after 3257
step 10 before 3166 after 3083
step 11 before 3066 after 3026
step 12 before 2985 after 2982
step 13 before 2925 after 2924
step 14 before 2834 after 2808
step 15 before 2805 after 2803
step 16 before 2647 after 2622
radix-tree with 1024*1024*128 slots:
tag-lookup
step 1 before 1288059720 after 951736580
step 2 before 961292300 after 884212140
step 7 before 768905140 after 547267580
step 15 before 771319480 after 456550640
step 63 before 504847640 after 242704304
step 64 before 392484800 after 177920786
step 65 before 491162160 after 246895264
step 128 before 208084064 after 97348392
step 256 before 112401035 after 51408126
step 512 before 75825834 after 29145070
step 12345 before 5603166 after 2847330
normal-lookup
step 1 before 1025677120 after 861375100
step 2 before 647220080 after 572258540
step 7 before 505518960 after 484041813
step 15 before 430483053 after 444815320 *
step 63 before 388113453 after 404250546 *
step 64 before 374154666 after 396027440 *
step 65 before 381423973 after 396704853 *
step 128 before 190078700 after 202619384 *
step 256 before 100886756 after 102829108 *
step 512 before 64074505 after 56158720
step 12345 before 4237289 after 4422299 *
* i686 on Sandy bridge
radix-tree with 1024 slots:
tagged lookup
step 1 before 7990 after 4019
step 2 before 5698 after 2897
step 3 before 5013 after 2475
step 4 before 4630 after 1721
step 5 before 4346 after 1759
step 6 before 4299 after 1556
step 7 before 4098 after 1513
step 8 before 4115 after 1222
step 9 before 3983 after 1390
step 10 before 4077 after 1207
step 11 before 3921 after 1231
step 12 before 3894 after 1116
step 13 before 3840 after 1147
step 14 before 3799 after 1090
step 15 before 3797 after 1059
step 16 before 3783 after 745
normal lookup
step 1 before 5103 after 3499
step 2 before 3299 after 2550
step 3 before 2489 after 2370
step 4 before 2034 after 2302 *
step 5 before 1846 after 2268 *
step 6 before 1752 after 2249 *
step 7 before 1679 after 2164 *
step 8 before 1627 after 2153 *
step 9 before 1542 after 2095 *
step 10 before 1479 after 2109 *
step 11 before 1469 after 2009 *
step 12 before 1445 after 2039 *
step 13 before 1411 after 2013 *
step 14 before 1374 after 2046 *
step 15 before 1340 after 1975 *
step 16 before 1331 after 2000 *
radix-tree with 1024*1024*128 slots:
tagged lookup
step 1 before 1225865377 after 667153553
step 2 before 842427423 after 471533007
step 7 before 609296153 after 276260116
step 15 before 544232060 after 226859105
step 63 before 519209199 after 141343043
step 64 before 588980279 after 141951339
step 65 before 521099710 after 138282060
step 128 before 298476778 after 83390628
step 256 before 149358342 after 43602609
step 512 before 76994713 after 22911077
step 12345 before 5328666 after 1472111
normal lookup
step 1 before 819284564 after 533635310
step 2 before 512421605 after 364956155
step 7 before 271443305 after 305721345 *
step 15 before 223591630 after 273960216 *
step 63 before 190320247 after 217770207 *
step 64 before 178538168 after 267411372 *
step 65 before 186400423 after 215347937 *
step 128 before 88106045 after 140540612 *
step 256 before 44812420 after 70660377 *
step 512 before 24435438 after 36328275 *
step 12345 before 2123924 after 2148062 *
bloat-o-meter delta for this patchset + patchset with related shmem cleanups
bloat-o-meter: x86_64
add/remove: 4/3 grow/shrink: 5/6 up/down: 928/-939 (-11)
function old new delta
radix_tree_next_chunk - 499 +499
shmem_unuse 428 554 +126
shmem_radix_tree_replace 131 227 +96
find_get_pages_tag 354 419 +65
find_get_pages_contig 345 407 +62
find_get_pages 362 396 +34
__kstrtab_radix_tree_next_chunk - 22 +22
__ksymtab_radix_tree_next_chunk - 16 +16
__kcrctab_radix_tree_next_chunk - 8 +8
radix_tree_gang_lookup_slot 204 203 -1
static.shmem_xattr_set 384 381 -3
radix_tree_gang_lookup_tag_slot 208 191 -17
radix_tree_gang_lookup 231 187 -44
radix_tree_gang_lookup_tag 247 199 -48
shmem_unlock_mapping 278 190 -88
__lookup 217 - -217
__lookup_tag 242 - -242
radix_tree_locate_item 279 - -279
bloat-o-meter: i386
add/remove: 3/3 grow/shrink: 8/9 up/down: 1075/-1275 (-200)
function old new delta
radix_tree_next_chunk - 757 +757
shmem_unuse 352 449 +97
find_get_pages_contig 269 322 +53
shmem_radix_tree_replace 113 154 +41
find_get_pages_tag 277 318 +41
dcache_dir_lseek 426 458 +32
__kstrtab_radix_tree_next_chunk - 22 +22
vc_do_resize 968 977 +9
snd_pcm_lib_read1 725 733 +8
__ksymtab_radix_tree_next_chunk - 8 +8
netlbl_cipsov4_list 1120 1127 +7
find_get_pages 293 291 -2
new_slab 467 459 -8
bitfill_unaligned_rev 425 417 -8
radix_tree_gang_lookup_tag_slot 177 146 -31
blk_dump_cmd 267 229 -38
radix_tree_gang_lookup_slot 212 134 -78
shmem_unlock_mapping 221 128 -93
radix_tree_gang_lookup_tag 275 162 -113
radix_tree_gang_lookup 255 126 -129
__lookup 227 - -227
__lookup_tag 271 - -271
radix_tree_locate_item 277 - -277
This patch:
Implement a clean, simple and effective radix-tree iteration routine.
Iterating divided into two phases:
* lookup next chunk in radix-tree leaf node
* iterating through slots in this chunk
Main iterator function radix_tree_next_chunk() returns pointer to first
slot, and stores in the struct radix_tree_iter index of next-to-last slot.
For tagged-iterating it also constuct bitmask of tags for retunted chunk.
All additional logic implemented as static-inline functions and macroses.
Also adds radix_tree_find_next_bit() static-inline variant of
find_next_bit() optimized for small constant size arrays, because
find_next_bit() too heavy for searching in an array with one/two long
elements.
[akpm@linux-foundation.org: rework comments a bit]
Signed-off-by: Konstantin Khlebnikov <khlebnikov@openvz.org>
Tested-by: Hugh Dickins <hughd@google.com>
Cc: Christoph Hellwig <hch@lst.de>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
For files only using THIS_MODULE and/or EXPORT_SYMBOL, map
them onto including export.h -- or if the file isn't even
using those, then just delete the include. Fix up any implicit
include dependencies that were being masked by module.h along
the way.
Signed-off-by: Paul Gortmaker <paul.gortmaker@windriver.com>
Down, down in the deepest depths of GFP_NOIO page reclaim, we have
shrink_page_list() calling __remove_mapping() calling __delete_from_
swap_cache() or __delete_from_page_cache().
You would not expect those to need much stack, but in fact they call
radix_tree_delete(): which declares a 192-byte radix_tree_path array on
its stack (to record the node,offsets it visits when descending, in case
it needs to ascend to update them). And if any tag is still set [1],
that calls radix_tree_tag_clear(), which declares a further such
192-byte radix_tree_path array on the stack. (At least we have
interrupts disabled here, so won't then be pushing registers too.)
That was probably a good choice when most users were 32-bit (array of
half the size), and adding fields to radix_tree_node would have bloated
it unnecessarily. But nowadays many are 64-bit, and each
radix_tree_node contains a struct rcu_head, which is only used when
freeing; whereas the radix_tree_path info is only used for updating the
tree (deleting, clearing tags or setting tags if tagged) when a lock
must be held, of no interest when accessing the tree locklessly.
So add a parent pointer to the radix_tree_node, in union with the
rcu_head, and remove all uses of the radix_tree_path. There would be
space in that union to save the offset when descending as before (we can
argue that a lock must already be held to exclude other users), but
recalculating it when ascending is both easy (a constant shift and a
constant mask) and uncommon, so it seems better just to do that.
Two little optimizations: no need to decrement height when descending,
adjusting shift is enough; and once radix_tree_tag_if_tagged() has set
tag on a node and its ancestors, it need not ascend from that node
again.
perf on the radix tree test harness reports radix_tree_insert() as 2%
slower (now having to set parent), but radix_tree_delete() 24% faster.
Surely that's an exaggeration from rtth's artificially low map shift 3,
but forcing it back to 6 still rates radix_tree_delete() 8% faster.
[1] Can a pagecache tag (dirty, writeback or towrite) actually still be
set at the time of radix_tree_delete()? Perhaps not if the filesystem is
well-behaved. But although I've not tracked any stack overflow down to
this cause, I have observed a curious case in which a dirty tag is set
and left set on tmpfs: page migration's migrate_page_copy() happens to
use __set_page_dirty_nobuffers() to set PageDirty on the newpage, and
that sets PAGECACHE_TAG_DIRTY as a side-effect - harmless to a
filesystem which doesn't use tags, except for this stack depth issue.
Signed-off-by: Hugh Dickins <hughd@google.com>
Cc: Jan Kara <jack@suse.cz>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Mel Gorman <mgorman@suse.de>
Cc: Nai Xia <nai.xia@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
radix_tree_tag_get()'s BUG (when it sees a tag after saw_unset_tag) was
unsafe and removed in 2.6.34, but the pointless saw_unset_tag left behind.
Remove it now, and return 0 as soon as we see unset tag - we already rely
upon the root tag to be correct, returning 0 immediately if it's not set.
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We have already acknowledged that swapoff of a tmpfs file is slower than
it was before conversion to the generic radix_tree: a little slower
there will be acceptable, if the hotter paths are faster.
But it was a shock to find swapoff of a 500MB file 20 times slower on my
laptop, taking 10 minutes; and at that rate it significantly slows down
my testing.
Now, most of that turned out to be overhead from PROVE_LOCKING and
PROVE_RCU: without those it was only 4 times slower than before; and
more realistic tests on other machines don't fare as badly.
I've tried a number of things to improve it, including tagging the swap
entries, then doing lookup by tag: I'd expected that to halve the time,
but in practice it's erratic, and often counter-productive.
The only change I've so far found to make a consistent improvement, is
to short-circuit the way we go back and forth, gang lookup packing
entries into the array supplied, then shmem scanning that array for the
target entry. Scanning in place doubles the speed, so it's now only
twice as slow as before (or three times slower when the PROVEs are on).
So, add radix_tree_locate_item() as an expedient, once-off,
single-caller hack to do the lookup directly in place. #ifdef it on
CONFIG_SHMEM and CONFIG_SWAP, as much to document its limited
applicability as save space in other configurations. And, sadly,
#include sched.h for cond_resched().
Signed-off-by: Hugh Dickins <hughd@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
A patchset to extend tmpfs to MAX_LFS_FILESIZE by abandoning its
peculiar swap vector, instead keeping a file's swap entries in the same
radix tree as its struct page pointers: thus saving memory, and
simplifying its code and locking.
This patch:
The radix_tree is used by several subsystems for different purposes. A
major use is to store the struct page pointers of a file's pagecache for
memory management. But what if mm wanted to store something other than
page pointers there too?
The low bit of a radix_tree entry is already used to denote an indirect
pointer, for internal use, and the unlikely radix_tree_deref_retry()
case.
Define the next bit as denoting an exceptional entry, and supply inline
functions radix_tree_exception() to return non-0 in either unlikely
case, and radix_tree_exceptional_entry() to return non-0 in the second
case.
If a subsystem already uses radix_tree with that bit set, no problem: it
does not affect internal workings at all, but is defined for the
convenience of those storing well-aligned pointers in the radix_tree.
The radix_tree_gang_lookups have an implicit assumption that the caller
can deduce the offset of each entry returned e.g. by the page->index of
a struct page. But that may not be feasible for some kinds of item to
be stored there.
radix_tree_gang_lookup_slot() allow for an optional indices argument,
output array in which to return those offsets. The same could be added
to other radix_tree_gang_lookups, but for now keep it to the only one
for which we need it.
Signed-off-by: Hugh Dickins <hughd@google.com>
Acked-by: Rik van Riel <riel@redhat.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Executed command: fsstress -d /mnt -n 600 -p 850
crash> bt
PID: 7947 TASK: ffff880160546a70 CPU: 0 COMMAND: "fsstress"
#0 [ffff8800dfc07d00] machine_kexec at ffffffff81030db9
#1 [ffff8800dfc07d70] crash_kexec at ffffffff810a7952
#2 [ffff8800dfc07e40] oops_end at ffffffff814aa7c8
#3 [ffff8800dfc07e70] die_nmi at ffffffff814aa969
#4 [ffff8800dfc07ea0] do_nmi_callback at ffffffff8102b07b
#5 [ffff8800dfc07f10] do_nmi at ffffffff814aa514
#6 [ffff8800dfc07f50] nmi at ffffffff814a9d60
[exception RIP: __lookup_tag+100]
RIP: ffffffff812274b4 RSP: ffff88016056b998 RFLAGS: 00000287
RAX: 0000000000000000 RBX: 0000000000000002 RCX: 0000000000000006
RDX: 000000000000001d RSI: ffff88016056bb18 RDI: ffff8800c85366e0
RBP: ffff88016056b9c8 R8: ffff88016056b9e8 R9: 0000000000000000
R10: 000000000000000e R11: ffff8800c8536908 R12: 0000000000000010
R13: 0000000000000040 R14: ffffffffffffffc0 R15: ffff8800c85366e0
ORIG_RAX: ffffffffffffffff CS: 0010 SS: 0018
<NMI exception stack>
#7 [ffff88016056b998] __lookup_tag at ffffffff812274b4
#8 [ffff88016056b9d0] radix_tree_gang_lookup_tag_slot at ffffffff81227605
#9 [ffff88016056ba20] find_get_pages_tag at ffffffff810fc110
#10 [ffff88016056ba80] pagevec_lookup_tag at ffffffff81105e85
#11 [ffff88016056baa0] write_cache_pages at ffffffff81104c47
#12 [ffff88016056bbd0] generic_writepages at ffffffff81105014
#13 [ffff88016056bbe0] do_writepages at ffffffff81105055
#14 [ffff88016056bbf0] __filemap_fdatawrite_range at ffffffff810fb2cb
#15 [ffff88016056bc40] filemap_write_and_wait_range at ffffffff810fb32a
#16 [ffff88016056bc70] generic_file_direct_write at ffffffff810fb3dc
#17 [ffff88016056bce0] __generic_file_aio_write at ffffffff810fcee5
#18 [ffff88016056bda0] generic_file_aio_write at ffffffff810fd085
#19 [ffff88016056bdf0] do_sync_write at ffffffff8114f9ea
#20 [ffff88016056bf00] vfs_write at ffffffff8114fcf8
#21 [ffff88016056bf30] sys_write at ffffffff81150691
#22 [ffff88016056bf80] system_call_fastpath at ffffffff8100c0b2
I think this root cause is the following:
radix_tree_range_tag_if_tagged() always tags the root tag with settag
if the root tag is set with iftag even if there are no iftag tags
in the specified range (Of course, there are some iftag tags
outside the specified range).
===============================================================================
[[[Detailed description]]]
(1) Why cannot radix_tree_gang_lookup_tag_slot() return forever?
__lookup_tag():
- Return with 0.
- Return with the index which is not bigger than the old one as the
input parameter.
Therefore the following "while" repeats forever because the above
conditions cause "ret" not to be updated and the cur_index cannot be
changed into the bigger one.
(So, radix_tree_gang_lookup_tag_slot() cannot return forever.)
radix_tree_gang_lookup_tag_slot():
1178 while (ret < max_items) {
1179 unsigned int slots_found;
1180 unsigned long next_index; /* Index of next search */
1181
1182 if (cur_index > max_index)
1183 break;
1184 slots_found = __lookup_tag(node, results + ret,
1185 cur_index, max_items - ret, &next_index,
tag);
1186 ret += slots_found;
// cannot update ret because slots_found == 0.
// so, this while loops forever.
1187 if (next_index == 0)
1188 break;
1189 cur_index = next_index;
1190 }
(2) Why does __lookup_tag() return with 0 and doesn't update the index?
Assuming the following:
- the one of the slot in radix_tree_node is NULL.
- the one of the tag which corresponds to the slot sets with
PAGECACHE_TAG_TOWRITE or other.
- In a certain height(!=0), the corresponding index is 0.
a) __lookup_tag() notices that the tag is set.
1005 static unsigned int
1006 __lookup_tag(struct radix_tree_node *slot, void ***results, unsigned long index,
1007 unsigned int max_items, unsigned long *next_index, unsigned int tag)
1008 {
1009 unsigned int nr_found = 0;
1010 unsigned int shift, height;
1011
1012 height = slot->height;
1013 if (height == 0)
1014 goto out;
1015 shift = (height-1) * RADIX_TREE_MAP_SHIFT;
1016
1017 while (height > 0) {
1018 unsigned long i = (index >> shift) & RADIX_TREE_MAP_MASK ;
1019
1020 for (;;) {
1021 if (tag_get(slot, tag, i))
1022 break;
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
* the index is not updated yet.
b) __lookup_tag() notices that the slot is NULL.
1023 index &= ~((1UL << shift) - 1);
1024 index += 1UL << shift;
1025 if (index == 0)
1026 goto out; /* 32-bit wraparound */
1027 i++;
1028 if (i == RADIX_TREE_MAP_SIZE)
1029 goto out;
1030 }
1031 height--;
1032 if (height == 0) { /* Bottom level: grab some items */
...
1055 }
1056 shift -= RADIX_TREE_MAP_SHIFT;
1057 slot = rcu_dereference_raw(slot->slots[i]);
1058 if (slot == NULL)
1059 break;
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
c) __lookup_tag() doesn't update the index and return with 0.
1060 }
1061 out:
1062 *next_index = index;
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
1063 return nr_found;
1064 }
(3) Why is the slot NULL even if the tag is set?
Because radix_tree_range_tag_if_tagged() always sets the root tag with
PAGECACHE_TAG_TOWRITE if the root tag is set with PAGECACHE_TAG_DIRTY,
even if there is no tag which can be set with PAGECACHE_TAG_TOWRITE
in the specified range (from *first_indexp to last_index). Of course,
some PAGECACHE_TAG_DIRTY nodes must exist outside the specified range.
(radix_tree_range_tag_if_tagged() is called only from tag_pages_for_writeback())
640 unsigned long radix_tree_range_tag_if_tagged(struct radix_tree_root
*root,
641 unsigned long *first_indexp, unsigned long last_index,
642 unsigned long nr_to_tag,
643 unsigned int iftag, unsigned int settag)
644 {
645 unsigned int height = root->height;
646 struct radix_tree_path path[height];
647 struct radix_tree_path *pathp = path;
648 struct radix_tree_node *slot;
649 unsigned int shift;
650 unsigned long tagged = 0;
651 unsigned long index = *first_indexp;
652
653 last_index = min(last_index, radix_tree_maxindex(height));
654 if (index > last_index)
655 return 0;
656 if (!nr_to_tag)
657 return 0;
658 if (!root_tag_get(root, iftag)) {
659 *first_indexp = last_index + 1;
660 return 0;
661 }
662 if (height == 0) {
663 *first_indexp = last_index + 1;
664 root_tag_set(root, settag);
665 return 1;
666 }
...
733 root_tag_set(root, settag);
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
734 *first_indexp = index;
735
736 return tagged;
737 }
As the result, there is no radix_tree_node which is set with
PAGECACHE_TAG_TOWRITE but the root tag(radix_tree_root) is set with
PAGECACHE_TAG_TOWRITE.
[figure: inside radix_tree]
(Please see the figure with typewriter font)
===========================================
[roottag = DIRTY]
| tag=0:NOTHING
tag[0 0 0 1] 1:DIRTY
[x x x +] 2:WRITEBACK
| 3:DIRTY,WRITEBACK
p 4:TOWRITE
<---> 5:DIRTY,TOWRITE ...
specified range (index: 0 to 2)
* There is no DIRTY tag within the specified range.
(But there is a DIRTY tag outside that range.)
| | | | | | | | |
after calling tag_pages_for_writeback()
| | | | | | | | |
v v v v v v v v v
[roottag = DIRTY,TOWRITE]
| p is "page".
tag[0 0 0 1] x is NULL.
[x x x +] +- is a pointer to "page".
|
p
* But TOWRITE tag is set on the root tag.
============================================
After that, radix_tree_extend() via radix_tree_insert() is called
when the page is added.
This function sets the new radix_tree_node with PAGECACHE_TAG_TOWRITE
to succeed the status of the root tag.
246 static int radix_tree_extend(struct radix_tree_root *root, unsigned long
index)
247 {
248 struct radix_tree_node *node;
249 unsigned int height;
250 int tag;
251
252 /* Figure out what the height should be. */
253 height = root->height + 1;
254 while (index > radix_tree_maxindex(height))
255 height++;
256
257 if (root->rnode == NULL) {
258 root->height = height;
259 goto out;
260 }
261
262 do {
263 unsigned int newheight;
264 if (!(node = radix_tree_node_alloc(root)))
265 return -ENOMEM;
266
267 /* Increase the height. */
268 node->slots[0] = radix_tree_indirect_to_ptr(root->rnode);
269
270 /* Propagate the aggregated tag info into the new root */
271 for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) {
272 if (root_tag_get(root, tag))
273 tag_set(node, tag, 0);
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
274 }
===========================================
[roottag = DIRTY,TOWRITE]
| :
tag[0 0 0 1] [0 0 0 0]
[x x x +] [+ x x x]
| |
p p (new page)
| | | | | | | | |
after calling radix_tree_insert
| | | | | | | | |
v v v v v v v v v
[roottag = DIRTY,TOWRITE]
|
tag [5 0 0 0] * DIRTY and TOWRITE tags are
[+ + x x] succeeded to the new node.
| |
tag [0 0 0 1] [0 0 0 0]
[x x x +] [+ x x x]
| |
p p
============================================
After that, the index 3 page is released by remove_from_page_cache().
Then we can make the situation that the tag is set with PAGECACHE_TAG_TOWRITE
and that the slot which corresponds to the tag is NULL.
===========================================
[roottag = DIRTY,TOWRITE]
|
tag [5 0 0 0]
[+ + x x]
| |
tag [0 0 0 1] [0 0 0 0]
[x x x +] [+ x x x]
| |
p p
(remove)
| | | | | | | | |
after calling remove_page_cache
| | | | | | | | |
v v v v v v v v v
[roottag = DIRTY,TOWRITE]
|
tag [4 0 0 0] * Only DIRTY tag is cleared
[x + x x] because no TOWRITE tag is existed
| in the bottom node.
[0 0 0 0]
[+ x x x]
|
p
============================================
To solve this problem
Change to that radix_tree_tag_if_tagged() doesn't tag the root tag
if it doesn't set any tags within the specified range.
Like this.
============================================
640 unsigned long radix_tree_range_tag_if_tagged(struct radix_tree_root
*root,
641 unsigned long *first_indexp, unsigned long last_index,
642 unsigned long nr_to_tag,
643 unsigned int iftag, unsigned int settag)
644 {
650 unsigned long tagged = 0;
...
733 if (tagged)
^^^^^^^^^^^^^^^^^^^^^^^^
734 root_tag_set(root, settag);
735 *first_indexp = index;
736
737 return tagged;
738 }
============================================
Signed-off-by: Toshiyuki Okajima <toshi.okajima@jp.fujitsu.com>
Acked-by: Jan Kara <jack@suse.cz>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Salman Qazi describes the following radix-tree bug:
In the following case, we get can get a deadlock:
0. The radix tree contains two items, one has the index 0.
1. The reader (in this case find_get_pages) takes the rcu_read_lock.
2. The reader acquires slot(s) for item(s) including the index 0 item.
3. The non-zero index item is deleted, and as a consequence the other item is
moved to the root of the tree. The place where it used to be is queued for
deletion after the readers finish.
3b. The zero item is deleted, removing it from the direct slot, it remains in
the rcu-delayed indirect node.
4. The reader looks at the index 0 slot, and finds that the page has 0 ref
count
5. The reader looks at it again, hoping that the item will either be freed or
the ref count will increase. This never happens, as the slot it is looking
at will never be updated. Also, this slot can never be reclaimed because
the reader is holding rcu_read_lock and is in an infinite loop.
The fix is to re-use the same "indirect" pointer case that requires a slot
lookup retry into a general "retry the lookup" bit.
Signed-off-by: Nick Piggin <npiggin@kernel.dk>
Reported-by: Salman Qazi <sqazi@google.com>
Cc: <stable@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
* 'radix-tree' of git://git.kernel.org/pub/scm/linux/kernel/git/dgc/xfsdev:
radix-tree: radix_tree_range_tag_if_tagged() can set incorrect tags
radix-tree: clear all tags in radix_tree_node_rcu_free
Commit ebf8aa44be ("radix-tree:
omplement function radix_tree_range_tag_if_tagged") does not safely
set tags on on intermediate tree nodes. The code walks down the tree
setting tags before it has fully resolved the path to the leaf under
the assumption there will be a leaf slot with the tag set in the
range it is searching.
Unfortunately, this is not a valid assumption - we can abort after
setting a tag on an intermediate node if we overrun the number of
tags we are allowed to set in a batch, or stop scanning because we
we have passed the last scan index before we reach a leaf slot with
the tag we are searching for set.
As a result, we can leave the function with tags set on intemediate
nodes which can be tripped over later by tag-based lookups. The
result of these stale tags is that lookup may end prematurely or
livelock because the lookup cannot make progress.
The fix for the problem involves reocrding the traversal path we
take to the leaf nodes, and only propagating the tags back up the
tree once the tag is set in the leaf node slot. We are already
recording the path for efficient traversal, so there is no
additional overhead to do the intermediately node tag setting in
this manner.
This fixes a radix tree lookup livelock triggered by the new
writeback sync livelock avoidance code introduced in commit
f446daaea9 ("mm: implement writeback
livelock avoidance using page tagging").
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Acked-by: Jan Kara <jack@suse.cz>
Commit f446daaea9 ("mm: implement
writeback livelock avoidance using page tagging") introduced a new
radix tree tag, increasing the number of tags in each node from 2 to
3. It did not, however, fix up the code in
radix_tree_node_rcu_free() that cleans up after radix_tree_shrink()
and hence could leave stray tags set in the new tag array.
The result is that the livelock avoidance code added in the the
above commit would hit stale tags when doing tag based lookups,
resulting in livelocks when trying to traverse the tree.
Fix this problem in radix_tree_node_rcu_free() so it doesn't happen
again in the future by using a loop to walk all the tags up to
RADIX_TREE_MAX_TAGS to clear the stray tags radix_tree_shrink()
leaves behind.
Signed-off-by: Dave Chinner <dchinner@redhat.com>
Acked-by: Nick Piggin <npiggin@kernel.dk>
Acked-by: Jan Kara <jack@suse.cz>
When radix_tree_maxindex() is ~0UL, it can happen that scanning overflows
index and tree traversal code goes astray reading memory until it hits
unreadable memory. Check for overflow and exit in that case.
Signed-off-by: Jan Kara <jack@suse.cz>
Cc: Christoph Hellwig <hch@lst.de>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Implement function for setting one tag if another tag is set for each item
in given range.
Signed-off-by: Jan Kara <jack@suse.cz>
Cc: Dave Chinner <david@fromorbit.com>
Cc: Nick Piggin <nickpiggin@yahoo.com.au>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
radix_tree_prev_hole() used LONG_MAX to detect underflow; however,
ULONG_MAX is clearly what was intended, both here and by its only user
(count_history_pages at mm/readahead.c).
Reviewed-by: Wu Fengguang <fengguang.wu@intel.com>
Signed-off-by: Cesar Eduardo Barros <cesarb@cesarb.net>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
radix_tree_tag_get() is not safe to use concurrently with radix_tree_tag_set()
or radix_tree_tag_clear(). The problem is that the double tag_get() in
radix_tree_tag_get():
if (!tag_get(node, tag, offset))
saw_unset_tag = 1;
if (height == 1) {
int ret = tag_get(node, tag, offset);
may see the value change due to the action of set/clear. RCU is no protection
against this as no pointers are being changed, no nodes are being replaced
according to a COW protocol - set/clear alter the node directly.
The documentation in linux/radix-tree.h, however, says that
radix_tree_tag_get() is an exception to the rule that "any function modifying
the tree or tags (...) must exclude other modifications, and exclude any
functions reading the tree".
The problem is that the next statement in radix_tree_tag_get() checks that the
tag doesn't vary over time:
BUG_ON(ret && saw_unset_tag);
This has been seen happening in FS-Cache:
https://www.redhat.com/archives/linux-cachefs/2010-April/msg00013.html
To this end, remove the BUG_ON() from radix_tree_tag_get() and note in various
comments that the value of the tag may change whilst the RCU read lock is held,
and thus that the return value of radix_tree_tag_get() may not be relied upon
unless radix_tree_tag_set/clear() and radix_tree_delete() are excluded from
running concurrently with it.
Reported-by: Romain DEGEZ <romain.degez@smartjog.com>
Signed-off-by: David Howells <dhowells@redhat.com>
Acked-by: Nick Piggin <npiggin@suse.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Matthew Wilcox