The logic controlling the singly-linked list of swap_info_struct entries
for all active, i.e.  swapon'ed, swap targets is rather complex, because:

 - it stores the entries in priority order
 - there is a pointer to the highest priority entry
 - there is a pointer to the highest priority not-full entry
 - there is a highest_priority_index variable set outside the swap_lock
 - swap entries of equal priority should be used equally

this complexity leads to bugs such as: https://lkml.org/lkml/2014/2/13/181
where different priority swap targets are incorrectly used equally.

That bug probably could be solved with the existing singly-linked lists,
but I think it would only add more complexity to the already difficult to
understand get_swap_page() swap_list iteration logic.

The first patch changes from a singly-linked list to a doubly-linked list
using list_heads; the highest_priority_index and related code are removed
and get_swap_page() starts each iteration at the highest priority
swap_info entry, even if it's full.  While this does introduce unnecessary
list iteration (i.e.  Schlemiel the painter's algorithm) in the case where
one or more of the highest priority entries are full, the iteration and
manipulation code is much simpler and behaves correctly re: the above bug;
and the fourth patch removes the unnecessary iteration.

The second patch adds some minor plist helper functions; nothing new
really, just functions to match existing regular list functions.  These
are used by the next two patches.

The third patch adds plist_requeue(), which is used by get_swap_page() in
the next patch - it performs the requeueing of same-priority entries
(which moves the entry to the end of its priority in the plist), so that
all equal-priority swap_info_structs get used equally.

The fourth patch converts the main list into a plist, and adds a new plist
that contains only swap_info entries that are both active and not full.
As Mel suggested using plists allows removing all the ordering code from
swap - plists handle ordering automatically.  The list naming is also
clarified now that there are two lists, with the original list changed
from swap_list_head to swap_active_head and the new list named
swap_avail_head.  A new spinlock is also added for the new list, so
swap_info entries can be added or removed from the new list immediately as
they become full or not full.

This patch (of 4):

Replace the singly-linked list tracking active, i.e.  swapon'ed,
swap_info_struct entries with a doubly-linked list using struct
list_heads.  Simplify the logic iterating and manipulating the list of
entries, especially get_swap_page(), by using standard list_head
functions, and removing the highest priority iteration logic.

The change fixes the bug:
https://lkml.org/lkml/2014/2/13/181
in which different priority swap entries after the highest priority entry
are incorrectly used equally in pairs.  The swap behavior is now as
advertised, i.e. different priority swap entries are used in order, and
equal priority swap targets are used concurrently.
Signed-off-by: NDan Streetman <ddstreet@ieee.org>
Acked-by: NMel Gorman <mgorman@suse.de>
Cc: Shaohua Li <shli@fusionio.com>
Cc: Hugh Dickins <hughd@google.com>
Cc: Dan Streetman <ddstreet@ieee.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Christian Ehrhardt <ehrhardt@linux.vnet.ibm.com>
Cc: Weijie Yang <weijieut@gmail.com>
Cc: Rik van Riel <riel@redhat.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Bob Liu <bob.liu@oracle.com>
Cc: Steven Rostedt <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul Gortmaker <paul.gortmaker@windriver.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

The bitmap accessed by bitops must have enough size to hold the required
numbers of bits rounded up to a multiple of BITS_PER_LONG.  And the
bitmap must not be zeroed by memset() if the number of bits cleared is
not a multiple of BITS_PER_LONG.

This fixes incorrect zeroing and allocation size for frontswap_map.  The
incorrect zeroing part doesn't cause any problem because frontswap_map
is freed just after zeroing.  But the wrongly calculated allocation size
may cause the problem.

For 32bit systems, the allocation size of frontswap_map is about twice
as large as required size.  For 64bit systems, the allocation size is
smaller than requeired if the number of bits is not a multiple of
BITS_PER_LONG.
Signed-off-by: NAkinobu Mita <akinobu.mita@gmail.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Frontswap initialization routine depends on swap_lock, which want to be
atomic about frontswap's first appearance.  IOW, frontswap is not present
and will fail all calls OR frontswap is fully functional but if new
swap_info_struct isn't registered by enable_swap_info, swap subsystem
doesn't start I/O so there is no race between init procedure and page I/O
working on frontswap.

So let's remove unnecessary swap_lock dependency.

Cc: Dan Magenheimer <dan.magenheimer@oracle.com>
Signed-off-by: NMinchan Kim <minchan@kernel.org>
[v1: Rebased on my branch, reworked to work with backends loading late]
[v2: Added a check for !map]
[v3: Made the invalidate path follow the init path]
[v4: Address comments by Wanpeng Li <liwanp@linux.vnet.ibm.com>]
Signed-off-by: NKonrad Rzeszutek Wilk <konrad@darnok.org>
Signed-off-by: NBob Liu <lliubbo@gmail.com>
Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Andor Daam <andor.daam@googlemail.com>
Cc: Florian Schmaus <fschmaus@gmail.com>
Cc: Stefan Hengelein <ilendir@googlemail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

After allowing tmem backends to build/run as modules, frontswap_enabled
always true if defined CONFIG_FRONTSWAP.  But frontswap_test() depends on
whether backend is registered, mv it into frontswap.c using fronstswap_ops
to make the decision.

frontswap_set/clear are not used outside frontswap, so don't export them.
Signed-off-by: NBob Liu <lliubbo@gmail.com>
Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Andor Daam <andor.daam@googlemail.com>
Cc: Dan Magenheimer <dan.magenheimer@oracle.com>
Cc: Florian Schmaus <fschmaus@gmail.com>
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Stefan Hengelein <ilendir@googlemail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

This simplifies the code in the frontswap - we can get rid of the
'backend_registered' test and instead check against frontswap_ops.

[v1: Rebase on top of 703ba7fe (ramster->zcache move]
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: NBob Liu <lliubbo@gmail.com>
Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Andor Daam <andor.daam@googlemail.com>
Cc: Dan Magenheimer <dan.magenheimer@oracle.com>
Cc: Florian Schmaus <fschmaus@gmail.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Stefan Hengelein <ilendir@googlemail.com>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

With the goal of allowing tmem backends (zcache, ramster, Xen tmem) to
be built/loaded as modules rather than built-in and enabled by a boot
parameter, this patch provides "lazy initialization", allowing backends
to register to frontswap even after swapon was run.  Before a backend
registers all calls to init are recorded and the creation of tmem_pools
delayed until a backend registers or until a frontswap store is
attempted.
Signed-off-by: NStefan Hengelein <ilendir@googlemail.com>
Signed-off-by: NFlorian Schmaus <fschmaus@gmail.com>
Signed-off-by: NAndor Daam <andor.daam@googlemail.com>
Signed-off-by: NDan Magenheimer <dan.magenheimer@oracle.com>
[v1: Fixes per Seth Jennings suggestions]
[v2: Removed FRONTSWAP_HAS_.. ]
[v3: Fix up per Bob Liu <lliubbo@gmail.com> recommendations]
[v4: Fix up per Andrew's comments]
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Signed-off-by: NBob Liu <lliubbo@gmail.com>
Cc: Wanpeng Li <liwanp@linux.vnet.ibm.com>
Cc: Dan Magenheimer <dan.magenheimer@oracle.com>
Cc: Minchan Kim <minchan@kernel.org>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>

Tmem, as originally specified, assumes that "get" operations
performed on persistent pools never flush the page of data out
of tmem on a successful get, waiting instead for a flush
operation.  This is intended to mimic the model of a swap
disk, where a disk read is non-destructive.  Unlike a
disk, however, freeing up the RAM can be valuable.  Over
the years that frontswap was in the review process, several
reviewers (and notably Hugh Dickins in 2010) pointed out that
this would result, at least temporarily, in two copies of the
data in RAM: one (compressed for zcache) copy in tmem,
and one copy in the swap cache.  We wondered if this could
be done differently, at least optionally.

This patch allows tmem backends to instruct the frontswap
code that this backend performs exclusive gets.  Zcache2
already contains hooks to support this feature.  Other
backends are completely unaffected unless/until they are
updated to support this feature.

While it is not clear that exclusive gets are a performance
win on all workloads at all times, this small patch allows for
experimentation by backends.

P.S. Let's not quibble about the naming of "get" vs "read" vs
"load" etc.  The naming is currently horribly inconsistent between
cleancache and frontswap and existing tmem backends, so will need
to be straightened out as a separate patch.  "Get" is used
by the tmem architecture spec, existing backends, and
all documentation and presentation material so I am
using it in this patch.
Signed-off-by: NDan Magenheimer <dan.magenheimer@oracle.com>
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>

pages_to_unuse is set to 0 to unuse all frontswap pages
But that doesn't happen since a wrong condition in frontswap_shrink
cancel it.

-v2: Add comment to explain return value of __frontswap_shrink,
as suggested by Dan Carpenter, thanks
Signed-off-by: NZhenzhong Duan <zhenzhong.duan@oracle.com>
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>

Fixes uninitialized variable warning on 'type' in frontswap_shrink().
type is set before use by __frontswap_unuse_pages() called by
__frontswap_shrink() called by frontswap_shrink() before use by
try_to_unuse().
Signed-off-by: NSeth Jennings <sjenning@linux.vnet.ibm.com>
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>

Signed-off-by: NWanpeng Li <liwp.linux@gmail.com>
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>

Signed-off-by: NSasha Levin <levinsasha928@gmail.com>
[v1: Rebased with tracing removed]
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>

Signed-off-by: NWanpeng Li <liwp.linux@gmail.com>
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>

Signed-off-by: NSasha Levin <levinsasha928@gmail.com>
[v1: Rebased with tracing removed]
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>

Signed-off-by: NSasha Levin <levinsasha928@gmail.com>
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>

The check whether frontswap is enabled or not is done in the API functions in
the frontswap header, before they are passed to the internal
double-underscored frontswap functions.

Remove the check from __frontswap_init for consistency.
Reviewed-by: NMinchan Kim <minchan@kernel.org>
Signed-off-by: NSasha Levin <levinsasha928@gmail.com>
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>

Currently it has a complex structure where different things are compared
at each branch. Simplify that and make both branches look similar.
Reviewed-by: NMinchan Kim <minchan@kernel.org>
Signed-off-by: NSasha Levin <levinsasha928@gmail.com>
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>

Split frontswap_shrink to simplify the locking in the original code.

Also, assert that the function that was split still runs under the
swap spinlock.
Signed-off-by: NSasha Levin <levinsasha928@gmail.com>
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>

An attempt at making frontswap_shrink shorter and more readable. This patch
splits out walking through the swap list to find an entry with enough
pages to unuse.

Also, assert that the internal __frontswap_unuse_pages is called under swap
lock, since that part of code was previously directly happen inside the lock.
Signed-off-by: NSasha Levin <levinsasha928@gmail.com>
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>

Code was duplicated in two functions, clean it up.

Also, assert that the deduplicated code runs under the swap spinlock.
Reviewed-by: NMinchan Kim <minchan@kernel.org>
Signed-off-by: NSasha Levin <levinsasha928@gmail.com>
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>

Reviewed-by: NMinchan Kim <minchan@kernel.org>
Signed-off-by: NSasha Levin <levinsasha928@gmail.com>
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>

Removes unneeded casts.
Reviewed-by: NMinchan Kim <minchan@kernel.org>
Signed-off-by: NSasha Levin <levinsasha928@gmail.com>
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>

Sounds so much more natural.
Suggested-by: NAndrea Arcangeli <aarcange@redhat.com>
Signed-off-by: NKonrad Rzeszutek Wilk <konrad.wilk@oracle.com>

This patch, 3of4, provides the core frontswap code that interfaces between
the hooks in the swap subsystem and a frontswap backend via frontswap_ops.

---
New file added: mm/frontswap.c

[v14: add support for writethrough, per suggestion by aarcange@redhat.com]
[v11: sjenning@linux.vnet.ibm.com: s/puts/failed_puts/]
[v10: sjenning@linux.vnet.ibm.com: fix debugfs calls on 32-bit]
[v9: akpm@linux-foundation.org: change "flush" to "invalidate", part 1]
[v9: akpm@linux-foundation.org: mark some statics __read_mostly]
[v9: akpm@linux-foundation.org: add clarifying comments]
[v9: akpm@linux-foundation.org: no need to loop repeating try_to_unuse]
[v9: error27@gmail.com: remove superfluous check for NULL]
[v8: rebase to 3.0-rc4]
[v8: kamezawa.hiroyu@jp.fujitsu.com: add comment to clarify find_next_to_unuse]
[v7: rebase to 3.0-rc3]
[v7: JBeulich@novell.com: use new static inlines, no-ops if not config'd]
[v6: rebase to 3.1-rc1]
[v6: lliubbo@gmail.com: use vzalloc]
[v6: lliubbo@gmail.com: fix null pointer deref if vzalloc fails]
[v6: konrad.wilk@oracl.com: various checks and code clarifications/comments]
[v4: rebase to 2.6.39]
Signed-off-by: NDan Magenheimer <dan.magenheimer@oracle.com>
Acked-by: NJan Beulich <JBeulich@novell.com>
Acked-by: NSeth Jennings <sjenning@linux.vnet.ibm.com>
Cc: Jeremy Fitzhardinge <jeremy@goop.org>
Cc: Hugh Dickins <hughd@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Nitin Gupta <ngupta@vflare.org>
Cc: Matthew Wilcox <matthew@wil.cx>
Cc: Chris Mason <chris.mason@oracle.com>
Cc: Rik Riel <riel@redhat.com>
Cc: Andrew Morton <akpm@linux-foundation.org>
[v12: Squashed s/flush/invalidate/ in]
[v15: A bit of cleanup and seperate DEBUGFS]
Signed-off-by: NKonrad Wilk <konrad.wilk@oracle.com>