Skip to content

K
Kernel

openeuler / Kernel
1 年多 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 17 2月, 2021 1 次提交
  3. 28 1月, 2021 1 次提交
  5. 14 1月, 2021 1 次提交
  7. 23 12月, 2020 1 次提交
  9. 02 12月, 2020 1 次提交
    • G
      kernel: Implement selective syscall userspace redirection · 1446e1df
      由 Gabriel Krisman Bertazi 提交于 
      Introduce a mechanism to quickly disable/enable syscall handling for a
specific process and redirect to userspace via SIGSYS.  This is useful
for processes with parts that require syscall redirection and parts that
don't, but who need to perform this boundary crossing really fast,
without paying the cost of a system call to reconfigure syscall handling
on each boundary transition.  This is particularly important for Windows
games running over Wine.

The proposed interface looks like this:

  prctl(PR_SET_SYSCALL_USER_DISPATCH, <op>, <off>, <length>, [selector])

The range [<offset>,<offset>+<length>) is a part of the process memory
map that is allowed to by-pass the redirection code and dispatch
syscalls directly, such that in fast paths a process doesn't need to
disable the trap nor the kernel has to check the selector.  This is
essential to return from SIGSYS to a blocked area without triggering
another SIGSYS from rt_sigreturn.

selector is an optional pointer to a char-sized userspace memory region
that has a key switch for the mechanism. This key switch is set to
either PR_SYS_DISPATCH_ON, PR_SYS_DISPATCH_OFF to enable and disable the
redirection without calling the kernel.

The feature is meant to be set per-thread and it is disabled on
fork/clone/execv.

Internally, this doesn't add overhead to the syscall hot path, and it
requires very little per-architecture support.  I avoided using seccomp,
even though it duplicates some functionality, due to previous feedback
that maybe it shouldn't mix with seccomp since it is not a security
mechanism.  And obviously, this should never be considered a security
mechanism, since any part of the program can by-pass it by using the
syscall dispatcher.

For the sysinfo benchmark, which measures the overhead added to
executing a native syscall that doesn't require interception, the
overhead using only the direct dispatcher region to issue syscalls is
pretty much irrelevant.  The overhead of using the selector goes around
40ns for a native (unredirected) syscall in my system, and it is (as
expected) dominated by the supervisor-mode user-address access.  In
fact, with SMAP off, the overhead is consistently less than 5ns on my
test box.
Signed-off-by: NGabriel Krisman Bertazi <krisman@collabora.com>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Reviewed-by: NAndy Lutomirski <luto@kernel.org>
Acked-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: NKees Cook <keescook@chromium.org>
Link: https://lore.kernel.org/r/20201127193238.821364-4-krisman@collabora.com
      1446e1df
  11. 24 11月, 2020 2 次提交
  13. 17 11月, 2020 2 次提交
    • J
      sched/deadline: Fix priority inheritance with multiple scheduling classes · 2279f540
      由 Juri Lelli 提交于 
      Glenn reported that "an application [he developed produces] a BUG in
deadline.c when a SCHED_DEADLINE task contends with CFS tasks on nested
PTHREAD_PRIO_INHERIT mutexes.  I believe the bug is triggered when a CFS
task that was boosted by a SCHED_DEADLINE task boosts another CFS task
(nested priority inheritance).

 ------------[ cut here ]------------
 kernel BUG at kernel/sched/deadline.c:1462!
 invalid opcode: 0000 [#1] PREEMPT SMP
 CPU: 12 PID: 19171 Comm: dl_boost_bug Tainted: ...
 Hardware name: ...
 RIP: 0010:enqueue_task_dl+0x335/0x910
 Code: ...
 RSP: 0018:ffffc9000c2bbc68 EFLAGS: 00010002
 RAX: 0000000000000009 RBX: ffff888c0af94c00 RCX: ffffffff81e12500
 RDX: 000000000000002e RSI: ffff888c0af94c00 RDI: ffff888c10b22600
 RBP: ffffc9000c2bbd08 R08: 0000000000000009 R09: 0000000000000078
 R10: ffffffff81e12440 R11: ffffffff81e1236c R12: ffff888bc8932600
 R13: ffff888c0af94eb8 R14: ffff888c10b22600 R15: ffff888bc8932600
 FS:  00007fa58ac55700(0000) GS:ffff888c10b00000(0000) knlGS:0000000000000000
 CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 CR2: 00007fa58b523230 CR3: 0000000bf44ab003 CR4: 00000000007606e0
 DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
 DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
 PKRU: 55555554
 Call Trace:
  ? intel_pstate_update_util_hwp+0x13/0x170
  rt_mutex_setprio+0x1cc/0x4b0
  task_blocks_on_rt_mutex+0x225/0x260
  rt_spin_lock_slowlock_locked+0xab/0x2d0
  rt_spin_lock_slowlock+0x50/0x80
  hrtimer_grab_expiry_lock+0x20/0x30
  hrtimer_cancel+0x13/0x30
  do_nanosleep+0xa0/0x150
  hrtimer_nanosleep+0xe1/0x230
  ? __hrtimer_init_sleeper+0x60/0x60
  __x64_sys_nanosleep+0x8d/0xa0
  do_syscall_64+0x4a/0x100
  entry_SYSCALL_64_after_hwframe+0x49/0xbe
 RIP: 0033:0x7fa58b52330d
 ...
 ---[ end trace 0000000000000002 ]—

He also provided a simple reproducer creating the situation below:

 So the execution order of locking steps are the following
 (N1 and N2 are non-deadline tasks. D1 is a deadline task. M1 and M2
 are mutexes that are enabled * with priority inheritance.)

 Time moves forward as this timeline goes down:

 N1              N2               D1
 |               |                |
 |               |                |
 Lock(M1)        |                |
 |               |                |
 |             Lock(M2)           |
 |               |                |
 |               |              Lock(M2)
 |               |                |
 |             Lock(M1)           |
 |             (!!bug triggered!) |

Daniel reported a similar situation as well, by just letting ksoftirqd
run with DEADLINE (and eventually block on a mutex).

Problem is that boosted entities (Priority Inheritance) use static
DEADLINE parameters of the top priority waiter. However, there might be
cases where top waiter could be a non-DEADLINE entity that is currently
boosted by a DEADLINE entity from a different lock chain (i.e., nested
priority chains involving entities of non-DEADLINE classes). In this
case, top waiter static DEADLINE parameters could be null (initialized
to 0 at fork()) and replenish_dl_entity() would hit a BUG().

Fix this by keeping track of the original donor and using its parameters
when a task is boosted.
Reported-by: NGlenn Elliott <glenn@aurora.tech>
Reported-by: NDaniel Bristot de Oliveira <bristot@redhat.com>
Signed-off-by: NJuri Lelli <juri.lelli@redhat.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Tested-by: NDaniel Bristot de Oliveira <bristot@redhat.com>
Link: https://lkml.kernel.org/r/20201117061432.517340-1-juri.lelli@redhat.com
      2279f540
    • P
      sched: Fix data-race in wakeup · f97bb527
      由 Peter Zijlstra 提交于 
      Mel reported that on some ARM64 platforms loadavg goes bananas and
Will tracked it down to the following race:

  CPU0					CPU1

  schedule()
    prev->sched_contributes_to_load = X;
    deactivate_task(prev);

					try_to_wake_up()
					  if (p->on_rq &&) // false
					  if (smp_load_acquire(&p->on_cpu) && // true
					      ttwu_queue_wakelist())
					        p->sched_remote_wakeup = Y;

    smp_store_release(prev->on_cpu, 0);

where both p->sched_contributes_to_load and p->sched_remote_wakeup are
in the same word, and thus the stores X and Y race (and can clobber
one another's data).

Whereas prior to commit c6e7bd7a ("sched/core: Optimize ttwu()
spinning on p->on_cpu") the p->on_cpu handoff serialized access to
p->sched_remote_wakeup (just as it still does with
p->sched_contributes_to_load) that commit broke that by calling
ttwu_queue_wakelist() with p->on_cpu != 0.

However, due to

  p->XXX = X			ttwu()
  schedule()			  if (p->on_rq && ...) // false
    smp_mb__after_spinlock()	  if (smp_load_acquire(&p->on_cpu) &&
    deactivate_task()		      ttwu_queue_wakelist())
      p->on_rq = 0;		        p->sched_remote_wakeup = Y;

We can be sure any 'current' store is complete and 'current' is
guaranteed asleep. Therefore we can move p->sched_remote_wakeup into
the current flags word.

Note: while the observed failure was loadavg accounting gone wrong due
to ttwu() cobbering p->sched_contributes_to_load, the reverse problem
is also possible where schedule() clobbers p->sched_remote_wakeup,
this could result in enqueue_entity() wrecking ->vruntime and causing
scheduling artifacts.

Fixes: c6e7bd7a ("sched/core: Optimize ttwu() spinning on p->on_cpu")
Reported-by: NMel Gorman <mgorman@techsingularity.net>
Debugged-by: NWill Deacon <will@kernel.org>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20201117083016.GK3121392@hirez.programming.kicks-ass.net
      f97bb527
  15. 11 11月, 2020 3 次提交
  17. 17 10月, 2020 1 次提交
  19. 14 10月, 2020 1 次提交
  21. 13 10月, 2020 1 次提交
  23. 07 10月, 2020 1 次提交
    • T
      x86/mce: Recover from poison found while copying from user space · c0ab7ffc
      由 Tony Luck 提交于 
      Existing kernel code can only recover from a machine check on code that
is tagged in the exception table with a fault handling recovery path.

Add two new fields in the task structure to pass information from
machine check handler to the "task_work" that is queued to run before
the task returns to user mode:

+ mce_vaddr: will be initialized to the user virtual address of the fault
  in the case where the fault occurred in the kernel copying data from
  a user address.  This is so that kill_me_maybe() can provide that
  information to the user SIGBUS handler.

+ mce_kflags: copy of the struct mce.kflags needed by kill_me_maybe()
  to determine if mce_vaddr is applicable to this error.

Add code to recover from a machine check while copying data from user
space to the kernel. Action for this case is the same as if the user
touched the poison directly; unmap the page and send a SIGBUS to the task.

Use a new helper function to share common code between the "fault
in user mode" case and the "fault while copying from user" case.

New code paths will be activated by the next patch which sets
MCE_IN_KERNEL_COPYIN.
Suggested-by: NBorislav Petkov <bp@alien8.de>
Signed-off-by: NTony Luck <tony.luck@intel.com>
Signed-off-by: NBorislav Petkov <bp@suse.de>
Link: https://lkml.kernel.org/r/20201006210910.21062-6-tony.luck@intel.com
      c0ab7ffc
  25. 03 10月, 2020 1 次提交
  27. 01 10月, 2020 1 次提交
    • J
      io_uring: don't rely on weak ->files references · 0f212204
      由 Jens Axboe 提交于 
      Grab actual references to the files_struct. To avoid circular references
issues due to this, we add a per-task note that keeps track of what
io_uring contexts a task has used. When the tasks execs or exits its
assigned files, we cancel requests based on this tracking.

With that, we can grab proper references to the files table, and no
longer need to rely on stashing away ring_fd and ring_file to check
if the ring_fd may have been closed.

Cc: stable@vger.kernel.org # v5.5+
Reviewed-by: NPavel Begunkov <asml.silence@gmail.com>
Signed-off-by: NJens Axboe <axboe@kernel.dk>
      0f212204
  29. 26 8月, 2020 2 次提交
  31. 06 8月, 2020 2 次提交
    • T
      posix-cpu-timers: Provide mechanisms to defer timer handling to task_work · 1fb497dd
      由 Thomas Gleixner 提交于 
      Running posix CPU timers in hard interrupt context has a few downsides:

 - For PREEMPT_RT it cannot work as the expiry code needs to take
   sighand lock, which is a 'sleeping spinlock' in RT. The original RT
   approach of offloading the posix CPU timer handling into a high
   priority thread was clumsy and provided no real benefit in general.

 - For fine grained accounting it's just wrong to run this in context of
   the timer interrupt because that way a process specific CPU time is
   accounted to the timer interrupt.

 - Long running timer interrupts caused by a large amount of expiring
   timers which can be created and armed by unpriviledged user space.

There is no hard requirement to expire them in interrupt context.

If the signal is targeted at the task itself then it won't be delivered
before the task returns to user space anyway. If the signal is targeted at
a supervisor process then it might be slightly delayed, but posix CPU
timers are inaccurate anyway due to the fact that they are tied to the
tick.

Provide infrastructure to schedule task work which allows splitting the
posix CPU timer code into a quick check in interrupt context and a thread
context expiry and signal delivery function. This has to be enabled by
architectures as it requires that the architecture specific KVM
implementation handles pending task work before exiting to guest mode.
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Signed-off-by: NIngo Molnar <mingo@kernel.org>
Reviewed-by: NOleg Nesterov <oleg@redhat.com>
Acked-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lore.kernel.org/r/20200730102337.783470146@linutronix.de
      1fb497dd
    • P
      locking/seqlock, headers: Untangle the spaghetti monster · 0cd39f46
      由 Peter Zijlstra 提交于 
      By using lockdep_assert_*() from seqlock.h, the spaghetti monster
attacked.

Attack back by reducing seqlock.h dependencies from two key high level headers:

 - <linux/seqlock.h>:               -Remove <linux/ww_mutex.h>
 - <linux/time.h>:                  -Remove <linux/seqlock.h>
 - <linux/sched.h>:                 +Add    <linux/seqlock.h>

The price was to add it to sched.h ...

Core header fallout, we add direct header dependencies instead of gaining them
parasitically from higher level headers:

 - <linux/dynamic_queue_limits.h>:  +Add <asm/bug.h>
 - <linux/hrtimer.h>:               +Add <linux/seqlock.h>
 - <linux/ktime.h>:                 +Add <asm/bug.h>
 - <linux/lockdep.h>:               +Add <linux/smp.h>
 - <linux/sched.h>:                 +Add <linux/seqlock.h>
 - <linux/videodev2.h>:             +Add <linux/kernel.h>

Arch headers fallout:

 - PARISC: <asm/timex.h>:           +Add <asm/special_insns.h>
 - SH:     <asm/io.h>:              +Add <asm/page.h>
 - SPARC:  <asm/timer_64.h>:        +Add <uapi/asm/asi.h>
 - SPARC:  <asm/vvar.h>:            +Add <asm/processor.h>, <asm/barrier.h>
                                    -Remove <linux/seqlock.h>
 - X86:    <asm/fixmap.h>:          +Add <asm/pgtable_types.h>
                                    -Remove <asm/acpi.h>

There's also a bunch of parasitic header dependency fallout in .c files, not listed
separately.

[ mingo: Extended the changelog, split up & fixed the original patch. ]
Co-developed-by: NIngo Molnar <mingo@kernel.org>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: NIngo Molnar <mingo@kernel.org>
Link: https://lore.kernel.org/r/20200804133438.GK2674@hirez.programming.kicks-ass.net
      0cd39f46
  33. 31 7月, 2020 2 次提交
  35. 29 7月, 2020 2 次提交
    • A
      sched: tasks: Use sequence counter with associated spinlock · b7505861
      由 Ahmed S. Darwish 提交于 
      A sequence counter write side critical section must be protected by some
form of locking to serialize writers. A plain seqcount_t does not
contain the information of which lock must be held when entering a write
side critical section.

Use the new seqcount_spinlock_t data type, which allows to associate a
spinlock with the sequence counter. This enables lockdep to verify that
the spinlock used for writer serialization is held when the write side
critical section is entered.

If lockdep is disabled this lock association is compiled out and has
neither storage size nor runtime overhead.
Signed-off-by: NAhmed S. Darwish <a.darwish@linutronix.de>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200720155530.1173732-14-a.darwish@linutronix.de
      b7505861
    • Q
      sched/uclamp: Add a new sysctl to control RT default boost value · 13685c4a
      由 Qais Yousef 提交于 
      RT tasks by default run at the highest capacity/performance level. When
uclamp is selected this default behavior is retained by enforcing the
requested uclamp.min (p->uclamp_req[UCLAMP_MIN]) of the RT tasks to be
uclamp_none(UCLAMP_MAX), which is SCHED_CAPACITY_SCALE; the maximum
value.

This is also referred to as 'the default boost value of RT tasks'.

See commit 1a00d999 ("sched/uclamp: Set default clamps for RT tasks").

On battery powered devices, it is desired to control this default
(currently hardcoded) behavior at runtime to reduce energy consumed by
RT tasks.

For example, a mobile device manufacturer where big.LITTLE architecture
is dominant, the performance of the little cores varies across SoCs, and
on high end ones the big cores could be too power hungry.

Given the diversity of SoCs, the new knob allows manufactures to tune
the best performance/power for RT tasks for the particular hardware they
run on.

They could opt to further tune the value when the user selects
a different power saving mode or when the device is actively charging.

The runtime aspect of it further helps in creating a single kernel image
that can be run on multiple devices that require different tuning.

Keep in mind that a lot of RT tasks in the system are created by the
kernel. On Android for instance I can see over 50 RT tasks, only
a handful of which created by the Android framework.

To control the default behavior globally by system admins and device
integrator, introduce the new sysctl_sched_uclamp_util_min_rt_default
to change the default boost value of the RT tasks.

I anticipate this to be mostly in the form of modifying the init script
of a particular device.

To avoid polluting the fast path with unnecessary code, the approach
taken is to synchronously do the update by traversing all the existing
tasks in the system. This could race with a concurrent fork(), which is
dealt with by introducing sched_post_fork() function which will ensure
the racy fork will get the right update applied.

Tested on Juno-r2 in combination with the RT capacity awareness [1].
By default an RT task will go to the highest capacity CPU and run at the
maximum frequency, which is particularly energy inefficient on high end
mobile devices because the biggest core[s] are 'huge' and power hungry.

With this patch the RT task can be controlled to run anywhere by
default, and doesn't cause the frequency to be maximum all the time.
Yet any task that really needs to be boosted can easily escape this
default behavior by modifying its requested uclamp.min value
(p->uclamp_req[UCLAMP_MIN]) via sched_setattr() syscall.

[1] 804d402f: ("sched/rt: Make RT capacity-aware")
Signed-off-by: NQais Yousef <qais.yousef@arm.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Link: https://lkml.kernel.org/r/20200716110347.19553-2-qais.yousef@arm.com
      13685c4a
  37. 28 7月, 2020 1 次提交
  39. 22 7月, 2020 1 次提交
  41. 10 7月, 2020 1 次提交
  43. 08 7月, 2020 3 次提交
  45. 04 7月, 2020 1 次提交
  47. 28 6月, 2020 2 次提交
  49. 15 6月, 2020 2 次提交
    • P
      sched: Remove sched_set_*() return value · 8b700983
      由 Peter Zijlstra 提交于 
      Ingo suggested that since the new sched_set_*() functions are
implemented using the 'nocheck' variants, they really shouldn't ever
fail, so remove the return value.

Cc: axboe@kernel.dk
Cc: daniel.lezcano@linaro.org
Cc: sudeep.holla@arm.com
Cc: airlied@redhat.com
Cc: broonie@kernel.org
Cc: paulmck@kernel.org
Suggested-by: NIngo Molnar <mingo@kernel.org>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: NIngo Molnar <mingo@kernel.org>
      8b700983
    • P
      sched: Provide sched_set_fifo() · 7318d4cc
      由 Peter Zijlstra 提交于 
      SCHED_FIFO (or any static priority scheduler) is a broken scheduler
model; it is fundamentally incapable of resource management, the one
thing an OS is actually supposed to do.

It is impossible to compose static priority workloads. One cannot take
two well designed and functional static priority workloads and mash
them together and still expect them to work.

Therefore it doesn't make sense to expose the priority field; the
kernel is fundamentally incapable of setting a sensible value, it
needs systems knowledge that it doesn't have.

Take away sched_setschedule() / sched_setattr() from modules and
replace them with:

  - sched_set_fifo(p); create a FIFO task (at prio 50)
  - sched_set_fifo_low(p); create a task higher than NORMAL,
	which ends up being a FIFO task at prio 1.
  - sched_set_normal(p, nice); (re)set the task to normal

This stops the proliferation of randomly chosen, and irrelevant, FIFO
priorities that dont't really mean anything anyway.

The system administrator/integrator, whoever has insight into the
actual system design and requirements (userspace) can set-up
appropriate priorities if and when needed.

Cc: airlied@redhat.com
Cc: alexander.deucher@amd.com
Cc: awalls@md.metrocast.net
Cc: axboe@kernel.dk
Cc: broonie@kernel.org
Cc: daniel.lezcano@linaro.org
Cc: gregkh@linuxfoundation.org
Cc: hannes@cmpxchg.org
Cc: herbert@gondor.apana.org.au
Cc: hverkuil@xs4all.nl
Cc: john.stultz@linaro.org
Cc: nico@fluxnic.net
Cc: paulmck@kernel.org
Cc: rafael.j.wysocki@intel.com
Cc: rmk+kernel@arm.linux.org.uk
Cc: sudeep.holla@arm.com
Cc: tglx@linutronix.de
Cc: ulf.hansson@linaro.org
Cc: wim@linux-watchdog.org
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Reviewed-by: NIngo Molnar <mingo@kernel.org>
Tested-by: NPaul E. McKenney <paulmck@kernel.org>
      7318d4cc
  51. 11 6月, 2020 1 次提交
    • T
      x86/{mce,mm}: Unmap the entire page if the whole page is affected and poisoned · 17fae129
      由 Tony Luck 提交于 
      An interesting thing happened when a guest Linux instance took a machine
check. The VMM unmapped the bad page from guest physical space and
passed the machine check to the guest.

Linux took all the normal actions to offline the page from the process
that was using it. But then guest Linux crashed because it said there
was a second machine check inside the kernel with this stack trace:

do_memory_failure
    set_mce_nospec
         set_memory_uc
              _set_memory_uc
                   change_page_attr_set_clr
                        cpa_flush
                             clflush_cache_range_opt

This was odd, because a CLFLUSH instruction shouldn't raise a machine
check (it isn't consuming the data). Further investigation showed that
the VMM had passed in another machine check because is appeared that the
guest was accessing the bad page.

Fix is to check the scope of the poison by checking the MCi_MISC register.
If the entire page is affected, then unmap the page. If only part of the
page is affected, then mark the page as uncacheable.

This assumes that VMMs will do the logical thing and pass in the "whole
page scope" via the MCi_MISC register (since they unmapped the entire
page).

  [ bp: Adjust to x86/entry changes. ]

Fixes: 284ce401 ("x86/memory_failure: Introduce {set, clear}_mce_nospec()")
Reported-by: NJue Wang <juew@google.com>
Signed-off-by: NTony Luck <tony.luck@intel.com>
Signed-off-by: NBorislav Petkov <bp@suse.de>
Signed-off-by: NThomas Gleixner <tglx@linutronix.de>
Tested-by: NJue Wang <juew@google.com>
Cc: <stable@vger.kernel.org>
Link: https://lkml.kernel.org/r/20200520163546.GA7977@agluck-desk2.amr.corp.intel.com
      17fae129
  53. 05 6月, 2020 1 次提交
  55. 03 6月, 2020 1 次提交
    • N
      mm/writeback: replace PF_LESS_THROTTLE with PF_LOCAL_THROTTLE · a37b0715
      由 NeilBrown 提交于 
      PF_LESS_THROTTLE exists for loop-back nfsd (and a similar need in the
loop block driver and callers of prctl(PR_SET_IO_FLUSHER)), where a
daemon needs to write to one bdi (the final bdi) in order to free up
writes queued to another bdi (the client bdi).

The daemon sets PF_LESS_THROTTLE and gets a larger allowance of dirty
pages, so that it can still dirty pages after other processses have been
throttled.  The purpose of this is to avoid deadlock that happen when
the PF_LESS_THROTTLE process must write for any dirty pages to be freed,
but it is being thottled and cannot write.

This approach was designed when all threads were blocked equally,
independently on which device they were writing to, or how fast it was.
Since that time the writeback algorithm has changed substantially with
different threads getting different allowances based on non-trivial
heuristics.  This means the simple "add 25%" heuristic is no longer
reliable.

The important issue is not that the daemon needs a *larger* dirty page
allowance, but that it needs a *private* dirty page allowance, so that
dirty pages for the "client" bdi that it is helping to clear (the bdi
for an NFS filesystem or loop block device etc) do not affect the
throttling of the daemon writing to the "final" bdi.

This patch changes the heuristic so that the task is not throttled when
the bdi it is writing to has a dirty page count below below (or equal
to) the free-run threshold for that bdi.  This ensures it will always be
able to have some pages in flight, and so will not deadlock.

In a steady-state, it is expected that PF_LOCAL_THROTTLE tasks might
still be throttled by global threshold, but that is acceptable as it is
only the deadlock state that is interesting for this flag.

This approach of "only throttle when target bdi is busy" is consistent
with the other use of PF_LESS_THROTTLE in current_may_throttle(), were
it causes attention to be focussed only on the target bdi.

So this patch
 - renames PF_LESS_THROTTLE to PF_LOCAL_THROTTLE,
 - removes the 25% bonus that that flag gives, and
 - If PF_LOCAL_THROTTLE is set, don't delay at all unless the
   global and the local free-run thresholds are exceeded.

Note that previously realtime threads were treated the same as
PF_LESS_THROTTLE threads.  This patch does *not* change the behvaiour
for real-time threads, so it is now different from the behaviour of nfsd
and loop tasks.  I don't know what is wanted for realtime.

[akpm@linux-foundation.org: coding style fixes]
Signed-off-by: NNeilBrown <neilb@suse.de>
Signed-off-by: NAndrew Morton <akpm@linux-foundation.org>
Reviewed-by: NJan Kara <jack@suse.cz>
Acked-by: Chuck Lever <chuck.lever@oracle.com>	[nfsd]
Cc: Christoph Hellwig <hch@lst.de>
Cc: Michal Hocko <mhocko@suse.com>
Cc: Trond Myklebust <trond.myklebust@hammerspace.com>
Link: http://lkml.kernel.org/r/87ftbf7gs3.fsf@notabene.neil.brown.nameSigned-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      a37b0715