linux-stable.git/kernel, branch v4.4.291 Linux kernel stable tree tracing: Have all levels of checks prevent recursion 2021-10-27T07:32:40+00:00 Steven Rostedt (VMware) rostedt@goodmis.org 2021-10-18T19:44:12+00:00 77bd0fb6e20472c02707439b2ecc2080a5fe5046 commit ed65df63a39a3f6ed04f7258de8b6789e5021c18 upstream. While writing an email explaining the "bit = 0" logic for a discussion on making ftrace_test_recursion_trylock() disable preemption, I discovered a path that makes the "not do the logic if bit is zero" unsafe. The recursion logic is done in hot paths like the function tracer. Thus, any code executed causes noticeable overhead. Thus, tricks are done to try to limit the amount of code executed. This included the recursion testing logic. Having recursion testing is important, as there are many paths that can end up in an infinite recursion cycle when tracing every function in the kernel. Thus protection is needed to prevent that from happening. Because it is OK to recurse due to different running context levels (e.g. an interrupt preempts a trace, and then a trace occurs in the interrupt handler), a set of bits are used to know which context one is in (normal, softirq, irq and NMI). If a recursion occurs in the same level, it is prevented*. Then there are infrastructure levels of recursion as well. When more than one callback is attached to the same function to trace, it calls a loop function to iterate over all the callbacks. Both the callbacks and the loop function have recursion protection. The callbacks use the "ftrace_test_recursion_trylock()" which has a "function" set of context bits to test, and the loop function calls the internal trace_test_and_set_recursion() directly, with an "internal" set of bits. If an architecture does not implement all the features supported by ftrace then the callbacks are never called directly, and the loop function is called instead, which will implement the features of ftrace. Since both the loop function and the callbacks do recursion protection, it was seemed unnecessary to do it in both locations. Thus, a trick was made to have the internal set of recursion bits at a more significant bit location than the function bits. Then, if any of the higher bits were set, the logic of the function bits could be skipped, as any new recursion would first have to go through the loop function. This is true for architectures that do not support all the ftrace features, because all functions being traced must first go through the loop function before going to the callbacks. But this is not true for architectures that support all the ftrace features. That's because the loop function could be called due to two callbacks attached to the same function, but then a recursion function inside the callback could be called that does not share any other callback, and it will be called directly. i.e. traced_function_1: [ more than one callback tracing it ] call loop_func loop_func: trace_recursion set internal bit call callback callback: trace_recursion [ skipped because internal bit is set, return 0 ] call traced_function_2 traced_function_2: [ only traced by above callback ] call callback callback: trace_recursion [ skipped because internal bit is set, return 0 ] call traced_function_2 [ wash, rinse, repeat, BOOM! out of shampoo! ] Thus, the "bit == 0 skip" trick is not safe, unless the loop function is call for all functions. Since we want to encourage architectures to implement all ftrace features, having them slow down due to this extra logic may encourage the maintainers to update to the latest ftrace features. And because this logic is only safe for them, remove it completely. [*] There is on layer of recursion that is allowed, and that is to allow for the transition between interrupt context (normal -> softirq -> irq -> NMI), because a trace may occur before the context update is visible to the trace recursion logic. Link: https://lore.kernel.org/all/609b565a-ed6e-a1da-f025-166691b5d994@linux.alibaba.com/ Link: https://lkml.kernel.org/r/20211018154412.09fcad3c@gandalf.local.home Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Petr Mladek <pmladek@suse.com> Cc: Ingo Molnar <mingo@redhat.com> Cc: "James E.J. Bottomley" <James.Bottomley@hansenpartnership.com> Cc: Helge Deller <deller@gmx.de> Cc: Michael Ellerman <mpe@ellerman.id.au> Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org> Cc: Paul Mackerras <paulus@samba.org> Cc: Paul Walmsley <paul.walmsley@sifive.com> Cc: Palmer Dabbelt <palmer@dabbelt.com> Cc: Albert Ou <aou@eecs.berkeley.edu> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Borislav Petkov <bp@alien8.de> Cc: "H. Peter Anvin" <hpa@zytor.com> Cc: Josh Poimboeuf <jpoimboe@redhat.com> Cc: Jiri Kosina <jikos@kernel.org> Cc: Miroslav Benes <mbenes@suse.cz> Cc: Joe Lawrence <joe.lawrence@redhat.com> Cc: Colin Ian King <colin.king@canonical.com> Cc: Masami Hiramatsu <mhiramat@kernel.org> Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org> Cc: Nicholas Piggin <npiggin@gmail.com> Cc: Jisheng Zhang <jszhang@kernel.org> Cc: =?utf-8?b?546L6LSH?= <yun.wang@linux.alibaba.com> Cc: Guo Ren <guoren@kernel.org> Cc: stable@vger.kernel.org Fixes: edc15cafcbfa3 ("tracing: Avoid unnecessary multiple recursion checks") Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit ed65df63a39a3f6ed04f7258de8b6789e5021c18 upstream.

While writing an email explaining the "bit = 0" logic for a discussion on
making ftrace_test_recursion_trylock() disable preemption, I discovered a
path that makes the "not do the logic if bit is zero" unsafe.

The recursion logic is done in hot paths like the function tracer. Thus,
any code executed causes noticeable overhead. Thus, tricks are done to try
to limit the amount of code executed. This included the recursion testing
logic.

Having recursion testing is important, as there are many paths that can
end up in an infinite recursion cycle when tracing every function in the
kernel. Thus protection is needed to prevent that from happening.

Because it is OK to recurse due to different running context levels (e.g.
an interrupt preempts a trace, and then a trace occurs in the interrupt
handler), a set of bits are used to know which context one is in (normal,
softirq, irq and NMI). If a recursion occurs in the same level, it is
prevented*.

Then there are infrastructure levels of recursion as well. When more than
one callback is attached to the same function to trace, it calls a loop
function to iterate over all the callbacks. Both the callbacks and the
loop function have recursion protection. The callbacks use the
"ftrace_test_recursion_trylock()" which has a "function" set of context
bits to test, and the loop function calls the internal
trace_test_and_set_recursion() directly, with an "internal" set of bits.

If an architecture does not implement all the features supported by ftrace
then the callbacks are never called directly, and the loop function is
called instead, which will implement the features of ftrace.

Since both the loop function and the callbacks do recursion protection, it
was seemed unnecessary to do it in both locations. Thus, a trick was made
to have the internal set of recursion bits at a more significant bit
location than the function bits. Then, if any of the higher bits were set,
the logic of the function bits could be skipped, as any new recursion
would first have to go through the loop function.

This is true for architectures that do not support all the ftrace
features, because all functions being traced must first go through the
loop function before going to the callbacks. But this is not true for
architectures that support all the ftrace features. That's because the
loop function could be called due to two callbacks attached to the same
function, but then a recursion function inside the callback could be
called that does not share any other callback, and it will be called
directly.

i.e.

 traced_function_1: [ more than one callback tracing it ]
   call loop_func

 loop_func:
   trace_recursion set internal bit
   call callback

 callback:
   trace_recursion [ skipped because internal bit is set, return 0 ]
   call traced_function_2

 traced_function_2: [ only traced by above callback ]
   call callback

 callback:
   trace_recursion [ skipped because internal bit is set, return 0 ]
   call traced_function_2

 [ wash, rinse, repeat, BOOM! out of shampoo! ]

Thus, the "bit == 0 skip" trick is not safe, unless the loop function is
call for all functions.

Since we want to encourage architectures to implement all ftrace features,
having them slow down due to this extra logic may encourage the
maintainers to update to the latest ftrace features. And because this
logic is only safe for them, remove it completely.

 [*] There is on layer of recursion that is allowed, and that is to allow
     for the transition between interrupt context (normal -> softirq ->
     irq -> NMI), because a trace may occur before the context update is
     visible to the trace recursion logic.

Link: https://lore.kernel.org/all/609b565a-ed6e-a1da-f025-166691b5d994@linux.alibaba.com/
Link: https://lkml.kernel.org/r/20211018154412.09fcad3c@gandalf.local.home

Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Petr Mladek <pmladek@suse.com>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: "James E.J. Bottomley" <James.Bottomley@hansenpartnership.com>
Cc: Helge Deller <deller@gmx.de>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Benjamin Herrenschmidt <benh@kernel.crashing.org>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Paul Walmsley <paul.walmsley@sifive.com>
Cc: Palmer Dabbelt <palmer@dabbelt.com>
Cc: Albert Ou <aou@eecs.berkeley.edu>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Borislav Petkov <bp@alien8.de>
Cc: "H. Peter Anvin" <hpa@zytor.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Jiri Kosina <jikos@kernel.org>
Cc: Miroslav Benes <mbenes@suse.cz>
Cc: Joe Lawrence <joe.lawrence@redhat.com>
Cc: Colin Ian King <colin.king@canonical.com>
Cc: Masami Hiramatsu <mhiramat@kernel.org>
Cc: "Peter Zijlstra (Intel)" <peterz@infradead.org>
Cc: Nicholas Piggin <npiggin@gmail.com>
Cc: Jisheng Zhang <jszhang@kernel.org>
Cc: =?utf-8?b?546L6LSH?= <yun.wang@linux.alibaba.com>
Cc: Guo Ren <guoren@kernel.org>
Cc: stable@vger.kernel.org
Fixes: edc15cafcbfa3 ("tracing: Avoid unnecessary multiple recursion checks")
Signed-off-by: Steven Rostedt (VMware) <rostedt@goodmis.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
blktrace: Fix uaf in blk_trace access after removing by sysfs 2021-10-06T08:22:23+00:00 Zhihao Cheng chengzhihao1@huawei.com 2021-09-23T13:49:21+00:00 488da313edf3abea7f7733efe011c96b23740ab5 [ Upstream commit 5afedf670caf30a2b5a52da96eb7eac7dee6a9c9 ] There is an use-after-free problem triggered by following process: P1(sda) P2(sdb) echo 0 > /sys/block/sdb/trace/enable blk_trace_remove_queue synchronize_rcu blk_trace_free relay_close rcu_read_lock __blk_add_trace trace_note_tsk (Iterate running_trace_list) relay_close_buf relay_destroy_buf kfree(buf) trace_note(sdb's bt) relay_reserve buf->offset <- nullptr deference (use-after-free) !!! rcu_read_unlock [ 502.714379] BUG: kernel NULL pointer dereference, address: 0000000000000010 [ 502.715260] #PF: supervisor read access in kernel mode [ 502.715903] #PF: error_code(0x0000) - not-present page [ 502.716546] PGD 103984067 P4D 103984067 PUD 17592b067 PMD 0 [ 502.717252] Oops: 0000 [#1] SMP [ 502.720308] RIP: 0010:trace_note.isra.0+0x86/0x360 [ 502.732872] Call Trace: [ 502.733193] __blk_add_trace.cold+0x137/0x1a3 [ 502.733734] blk_add_trace_rq+0x7b/0xd0 [ 502.734207] blk_add_trace_rq_issue+0x54/0xa0 [ 502.734755] blk_mq_start_request+0xde/0x1b0 [ 502.735287] scsi_queue_rq+0x528/0x1140 ... [ 502.742704] sg_new_write.isra.0+0x16e/0x3e0 [ 502.747501] sg_ioctl+0x466/0x1100 Reproduce method: ioctl(/dev/sda, BLKTRACESETUP, blk_user_trace_setup[buf_size=127]) ioctl(/dev/sda, BLKTRACESTART) ioctl(/dev/sdb, BLKTRACESETUP, blk_user_trace_setup[buf_size=127]) ioctl(/dev/sdb, BLKTRACESTART) echo 0 > /sys/block/sdb/trace/enable & // Add delay(mdelay/msleep) before kernel enters blk_trace_free() ioctl$SG_IO(/dev/sda, SG_IO, ...) // Enters trace_note_tsk() after blk_trace_free() returned // Use mdelay in rcu region rather than msleep(which may schedule out) Remove blk_trace from running_list before calling blk_trace_free() by sysfs if blk_trace is at Blktrace_running state. Fixes: c71a896154119f ("blktrace: add ftrace plugin") Signed-off-by: Zhihao Cheng <chengzhihao1@huawei.com> Link: https://lore.kernel.org/r/20210923134921.109194-1-chengzhihao1@huawei.com Signed-off-by: Jens Axboe <axboe@kernel.dk> Signed-off-by: Sasha Levin <sashal@kernel.org> 
[ Upstream commit 5afedf670caf30a2b5a52da96eb7eac7dee6a9c9 ]

There is an use-after-free problem triggered by following process:

      P1(sda)				P2(sdb)
			echo 0 > /sys/block/sdb/trace/enable
			  blk_trace_remove_queue
			    synchronize_rcu
			    blk_trace_free
			      relay_close
rcu_read_lock
__blk_add_trace
  trace_note_tsk
  (Iterate running_trace_list)
			        relay_close_buf
				  relay_destroy_buf
				    kfree(buf)
    trace_note(sdb's bt)
      relay_reserve
        buf->offset <- nullptr deference (use-after-free) !!!
rcu_read_unlock

[  502.714379] BUG: kernel NULL pointer dereference, address:
0000000000000010
[  502.715260] #PF: supervisor read access in kernel mode
[  502.715903] #PF: error_code(0x0000) - not-present page
[  502.716546] PGD 103984067 P4D 103984067 PUD 17592b067 PMD 0
[  502.717252] Oops: 0000 [#1] SMP
[  502.720308] RIP: 0010:trace_note.isra.0+0x86/0x360
[  502.732872] Call Trace:
[  502.733193]  __blk_add_trace.cold+0x137/0x1a3
[  502.733734]  blk_add_trace_rq+0x7b/0xd0
[  502.734207]  blk_add_trace_rq_issue+0x54/0xa0
[  502.734755]  blk_mq_start_request+0xde/0x1b0
[  502.735287]  scsi_queue_rq+0x528/0x1140
...
[  502.742704]  sg_new_write.isra.0+0x16e/0x3e0
[  502.747501]  sg_ioctl+0x466/0x1100

Reproduce method:
  ioctl(/dev/sda, BLKTRACESETUP, blk_user_trace_setup[buf_size=127])
  ioctl(/dev/sda, BLKTRACESTART)
  ioctl(/dev/sdb, BLKTRACESETUP, blk_user_trace_setup[buf_size=127])
  ioctl(/dev/sdb, BLKTRACESTART)

  echo 0 > /sys/block/sdb/trace/enable &
  // Add delay(mdelay/msleep) before kernel enters blk_trace_free()

  ioctl$SG_IO(/dev/sda, SG_IO, ...)
  // Enters trace_note_tsk() after blk_trace_free() returned
  // Use mdelay in rcu region rather than msleep(which may schedule out)

Remove blk_trace from running_list before calling blk_trace_free() by
sysfs if blk_trace is at Blktrace_running state.

Fixes: c71a896154119f ("blktrace: add ftrace plugin")
Signed-off-by: Zhihao Cheng <chengzhihao1@huawei.com>
Link: https://lore.kernel.org/r/20210923134921.109194-1-chengzhihao1@huawei.com
Signed-off-by: Jens Axboe <axboe@kernel.dk>
Signed-off-by: Sasha Levin <sashal@kernel.org>
profiling: fix shift-out-of-bounds bugs 2021-09-26T11:33:46+00:00 Pavel Skripkin paskripkin@gmail.com 2021-09-08T02:58:21+00:00 270b31d3e3a1b66dc40810140da7fcc0734f02e6 commit 2d186afd04d669fe9c48b994c41a7405a3c9f16d upstream. Syzbot reported shift-out-of-bounds bug in profile_init(). The problem was in incorrect prof_shift. Since prof_shift value comes from userspace we need to clamp this value into [0, BITS_PER_LONG -1] boundaries. Second possible shiht-out-of-bounds was found by Tetsuo: sample_step local variable in read_profile() had "unsigned int" type, but prof_shift allows to make a BITS_PER_LONG shift. So, to prevent possible shiht-out-of-bounds sample_step type was changed to "unsigned long". Also, "unsigned short int" will be sufficient for storing [0, BITS_PER_LONG] value, that's why there is no need for "unsigned long" prof_shift. Link: https://lkml.kernel.org/r/20210813140022.5011-1-paskripkin@gmail.com Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2") Reported-and-tested-by: syzbot+e68c89a9510c159d9684@syzkaller.appspotmail.com Suggested-by: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp> Signed-off-by: Pavel Skripkin <paskripkin@gmail.com> Cc: Thomas Gleixner <tglx@linutronix.de> Cc: Steven Rostedt <rostedt@goodmis.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit 2d186afd04d669fe9c48b994c41a7405a3c9f16d upstream.

Syzbot reported shift-out-of-bounds bug in profile_init().
The problem was in incorrect prof_shift. Since prof_shift value comes from
userspace we need to clamp this value into [0, BITS_PER_LONG -1]
boundaries.

Second possible shiht-out-of-bounds was found by Tetsuo:
sample_step local variable in read_profile() had "unsigned int" type,
but prof_shift allows to make a BITS_PER_LONG shift. So, to prevent
possible shiht-out-of-bounds sample_step type was changed to
"unsigned long".

Also, "unsigned short int" will be sufficient for storing
[0, BITS_PER_LONG] value, that's why there is no need for
"unsigned long" prof_shift.

Link: https://lkml.kernel.org/r/20210813140022.5011-1-paskripkin@gmail.com
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Reported-and-tested-by: syzbot+e68c89a9510c159d9684@syzkaller.appspotmail.com
Suggested-by: Tetsuo Handa <penguin-kernel@i-love.sakura.ne.jp>
Signed-off-by: Pavel Skripkin <paskripkin@gmail.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
prctl: allow to setup brk for et_dyn executables 2021-09-26T11:33:46+00:00 Cyrill Gorcunov gorcunov@gmail.com 2021-09-08T03:00:41+00:00 806df2502fb36d0068a3c18af1c9d2102ac912df commit e1fbbd073137a9d63279f6bf363151a938347640 upstream. Keno Fischer reported that when a binray loaded via ld-linux-x the prctl(PR_SET_MM_MAP) doesn't allow to setup brk value because it lays before mm:end_data. For example a test program shows | # ~/t | | start_code 401000 | end_code 401a15 | start_stack 7ffce4577dd0 | start_data 403e10 | end_data 40408c | start_brk b5b000 | sbrk(0) b5b000 and when executed via ld-linux | # /lib64/ld-linux-x86-64.so.2 ~/t | | start_code 7fc25b0a4000 | end_code 7fc25b0c4524 | start_stack 7fffcc6b2400 | start_data 7fc25b0ce4c0 | end_data 7fc25b0cff98 | start_brk 55555710c000 | sbrk(0) 55555710c000 This of course prevent criu from restoring such programs. Looking into how kernel operates with brk/start_brk inside brk() syscall I don't see any problem if we allow to setup brk/start_brk without checking for end_data. Even if someone pass some weird address here on a purpose then the worst possible result will be an unexpected unmapping of existing vma (own vma, since prctl works with the callers memory) but test for RLIMIT_DATA is still valid and a user won't be able to gain more memory in case of expanding VMAs via new values shipped with prctl call. Link: https://lkml.kernel.org/r/20210121221207.GB2174@grain Fixes: bbdc6076d2e5 ("binfmt_elf: move brk out of mmap when doing direct loader exec") Signed-off-by: Cyrill Gorcunov <gorcunov@gmail.com> Reported-by: Keno Fischer <keno@juliacomputing.com> Acked-by: Andrey Vagin <avagin@gmail.com> Tested-by: Andrey Vagin <avagin@gmail.com> Cc: Dmitry Safonov <0x7f454c46@gmail.com> Cc: Kirill Tkhai <ktkhai@virtuozzo.com> Cc: Eric W. Biederman <ebiederm@xmission.com> Cc: Pavel Tikhomirov <ptikhomirov@virtuozzo.com> Cc: Alexander Mikhalitsyn <alexander.mikhalitsyn@virtuozzo.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
commit e1fbbd073137a9d63279f6bf363151a938347640 upstream.

Keno Fischer reported that when a binray loaded via ld-linux-x the
prctl(PR_SET_MM_MAP) doesn't allow to setup brk value because it lays
before mm:end_data.

For example a test program shows

 | # ~/t
 |
 | start_code      401000
 | end_code        401a15
 | start_stack     7ffce4577dd0
 | start_data	   403e10
 | end_data        40408c
 | start_brk	   b5b000
 | sbrk(0)         b5b000

and when executed via ld-linux

 | # /lib64/ld-linux-x86-64.so.2 ~/t
 |
 | start_code      7fc25b0a4000
 | end_code        7fc25b0c4524
 | start_stack     7fffcc6b2400
 | start_data	   7fc25b0ce4c0
 | end_data        7fc25b0cff98
 | start_brk	   55555710c000
 | sbrk(0)         55555710c000

This of course prevent criu from restoring such programs.  Looking into
how kernel operates with brk/start_brk inside brk() syscall I don't see
any problem if we allow to setup brk/start_brk without checking for
end_data.  Even if someone pass some weird address here on a purpose then
the worst possible result will be an unexpected unmapping of existing vma
(own vma, since prctl works with the callers memory) but test for
RLIMIT_DATA is still valid and a user won't be able to gain more memory in
case of expanding VMAs via new values shipped with prctl call.

Link: https://lkml.kernel.org/r/20210121221207.GB2174@grain
Fixes: bbdc6076d2e5 ("binfmt_elf: move brk out of mmap when doing direct loader exec")
Signed-off-by: Cyrill Gorcunov <gorcunov@gmail.com>
Reported-by: Keno Fischer <keno@juliacomputing.com>
Acked-by: Andrey Vagin <avagin@gmail.com>
Tested-by: Andrey Vagin <avagin@gmail.com>
Cc: Dmitry Safonov <0x7f454c46@gmail.com>
Cc: Kirill Tkhai <ktkhai@virtuozzo.com>
Cc: Eric W. Biederman <ebiederm@xmission.com>
Cc: Pavel Tikhomirov <ptikhomirov@virtuozzo.com>
Cc: Alexander Mikhalitsyn <alexander.mikhalitsyn@virtuozzo.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
futex,rt_mutex: Fix rt_mutex_cleanup_proxy_lock() 2021-08-10T15:39:42+00:00 Peter Zijlstra peterz@infradead.org 2021-08-02T13:46:23+00:00 66edc0dded9863962505c42c0f726db97204ed4e [ Upstream commit 04dc1b2fff4e96cb4142227fbdc63c8871ad4ed9 ] Markus reported that the glibc/nptl/tst-robustpi8 test was failing after commit: cfafcd117da0 ("futex: Rework futex_lock_pi() to use rt_mutex_*_proxy_lock()") The following trace shows the problem: ld-linux-x86-64-2161 [019] .... 410.760971: SyS_futex: 00007ffbeb76b028: 80000875 op=FUTEX_LOCK_PI ld-linux-x86-64-2161 [019] ...1 410.760972: lock_pi_update_atomic: 00007ffbeb76b028: curval=80000875 uval=80000875 newval=80000875 ret=0 ld-linux-x86-64-2165 [011] .... 410.760978: SyS_futex: 00007ffbeb76b028: 80000875 op=FUTEX_UNLOCK_PI ld-linux-x86-64-2165 [011] d..1 410.760979: do_futex: 00007ffbeb76b028: curval=80000875 uval=80000875 newval=80000871 ret=0 ld-linux-x86-64-2165 [011] .... 410.760980: SyS_futex: 00007ffbeb76b028: 80000871 ret=0000 ld-linux-x86-64-2161 [019] .... 410.760980: SyS_futex: 00007ffbeb76b028: 80000871 ret=ETIMEDOUT Task 2165 does an UNLOCK_PI, assigning the lock to the waiter task 2161 which then returns with -ETIMEDOUT. That wrecks the lock state, because now the owner isn't aware it acquired the lock and removes the pending robust list entry. If 2161 is killed, the robust list will not clear out this futex and the subsequent acquire on this futex will then (correctly) result in -ESRCH which is unexpected by glibc, triggers an internal assertion and dies. Task 2161 Task 2165 rt_mutex_wait_proxy_lock() timeout(); /* T2161 is still queued in the waiter list */ return -ETIMEDOUT; futex_unlock_pi() spin_lock(hb->lock); rtmutex_unlock() remove_rtmutex_waiter(T2161); mark_lock_available(); /* Make the next waiter owner of the user space side */ futex_uval = 2161; spin_unlock(hb->lock); spin_lock(hb->lock); rt_mutex_cleanup_proxy_lock() if (rtmutex_owner() !== current) ... return FAIL; .... return -ETIMEOUT; This means that rt_mutex_cleanup_proxy_lock() needs to call try_to_take_rt_mutex() so it can take over the rtmutex correctly which was assigned by the waker. If the rtmutex is owned by some other task then this call is harmless and just confirmes that the waiter is not able to acquire it. While there, fix what looks like a merge error which resulted in rt_mutex_cleanup_proxy_lock() having two calls to fixup_rt_mutex_waiters() and rt_mutex_wait_proxy_lock() not having any. Both should have one, since both potentially touch the waiter list. Fixes: 38d589f2fd08 ("futex,rt_mutex: Restructure rt_mutex_finish_proxy_lock()") Reported-by: Markus Trippelsdorf <markus@trippelsdorf.de> Bug-Spotted-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Florian Weimer <fweimer@redhat.com> Cc: Darren Hart <dvhart@infradead.org> Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de> Cc: Markus Trippelsdorf <markus@trippelsdorf.de> Link: http://lkml.kernel.org/r/20170519154850.mlomgdsd26drq5j6@hirez.programming.kicks-ass.net Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com> Acked-by: Joe Korty <joe.korty@concurrent-rt.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
[ Upstream commit 04dc1b2fff4e96cb4142227fbdc63c8871ad4ed9 ]

Markus reported that the glibc/nptl/tst-robustpi8 test was failing after
commit:

  cfafcd117da0 ("futex: Rework futex_lock_pi() to use rt_mutex_*_proxy_lock()")

The following trace shows the problem:

 ld-linux-x86-64-2161  [019] ....   410.760971: SyS_futex: 00007ffbeb76b028: 80000875  op=FUTEX_LOCK_PI
 ld-linux-x86-64-2161  [019] ...1   410.760972: lock_pi_update_atomic: 00007ffbeb76b028: curval=80000875 uval=80000875 newval=80000875 ret=0
 ld-linux-x86-64-2165  [011] ....   410.760978: SyS_futex: 00007ffbeb76b028: 80000875  op=FUTEX_UNLOCK_PI
 ld-linux-x86-64-2165  [011] d..1   410.760979: do_futex: 00007ffbeb76b028: curval=80000875 uval=80000875 newval=80000871 ret=0
 ld-linux-x86-64-2165  [011] ....   410.760980: SyS_futex: 00007ffbeb76b028: 80000871 ret=0000
 ld-linux-x86-64-2161  [019] ....   410.760980: SyS_futex: 00007ffbeb76b028: 80000871 ret=ETIMEDOUT

Task 2165 does an UNLOCK_PI, assigning the lock to the waiter task 2161
which then returns with -ETIMEDOUT. That wrecks the lock state, because now
the owner isn't aware it acquired the lock and removes the pending robust
list entry.

If 2161 is killed, the robust list will not clear out this futex and the
subsequent acquire on this futex will then (correctly) result in -ESRCH
which is unexpected by glibc, triggers an internal assertion and dies.

Task 2161			Task 2165

rt_mutex_wait_proxy_lock()
   timeout();
   /* T2161 is still queued in  the waiter list */
   return -ETIMEDOUT;

				futex_unlock_pi()
				spin_lock(hb->lock);
				rtmutex_unlock()
				  remove_rtmutex_waiter(T2161);
				   mark_lock_available();
				/* Make the next waiter owner of the user space side */
				futex_uval = 2161;
				spin_unlock(hb->lock);
spin_lock(hb->lock);
rt_mutex_cleanup_proxy_lock()
  if (rtmutex_owner() !== current)
     ...
     return FAIL;
....
return -ETIMEOUT;

This means that rt_mutex_cleanup_proxy_lock() needs to call
try_to_take_rt_mutex() so it can take over the rtmutex correctly which was
assigned by the waker. If the rtmutex is owned by some other task then this
call is harmless and just confirmes that the waiter is not able to acquire
it.

While there, fix what looks like a merge error which resulted in
rt_mutex_cleanup_proxy_lock() having two calls to
fixup_rt_mutex_waiters() and rt_mutex_wait_proxy_lock() not having any.
Both should have one, since both potentially touch the waiter list.

Fixes: 38d589f2fd08 ("futex,rt_mutex: Restructure rt_mutex_finish_proxy_lock()")
Reported-by: Markus Trippelsdorf <markus@trippelsdorf.de>
Bug-Spotted-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Florian Weimer <fweimer@redhat.com>
Cc: Darren Hart <dvhart@infradead.org>
Cc: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Cc: Markus Trippelsdorf <markus@trippelsdorf.de>
Link: http://lkml.kernel.org/r/20170519154850.mlomgdsd26drq5j6@hirez.programming.kicks-ass.net
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Acked-by: Joe Korty <joe.korty@concurrent-rt.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
futex: Avoid freeing an active timer 2021-08-10T15:39:42+00:00 Thomas Gleixner tglx@linutronix.de 2021-08-02T13:46:22+00:00 9b8d748d4bb027f9c2aa7ce03801d270dc0819e5 [ Upstream commit 97181f9bd57405b879403763284537e27d46963d ] Alexander reported a hrtimer debug_object splat: ODEBUG: free active (active state 0) object type: hrtimer hint: hrtimer_wakeup (kernel/time/hrtimer.c:1423) debug_object_free (lib/debugobjects.c:603) destroy_hrtimer_on_stack (kernel/time/hrtimer.c:427) futex_lock_pi (kernel/futex.c:2740) do_futex (kernel/futex.c:3399) SyS_futex (kernel/futex.c:3447 kernel/futex.c:3415) do_syscall_64 (arch/x86/entry/common.c:284) entry_SYSCALL64_slow_path (arch/x86/entry/entry_64.S:249) Which was caused by commit: cfafcd117da0 ("futex: Rework futex_lock_pi() to use rt_mutex_*_proxy_lock()") ... losing the hrtimer_cancel() in the shuffle. Where previously the hrtimer_cancel() was done by rt_mutex_slowlock() we now need to do it manually. Reported-by: Alexander Levin <alexander.levin@verizon.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: Linus Torvalds <torvalds@linux-foundation.org> Cc: Peter Zijlstra <peterz@infradead.org> Fixes: cfafcd117da0 ("futex: Rework futex_lock_pi() to use rt_mutex_*_proxy_lock()") Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1704101802370.2906@nanos Signed-off-by: Ingo Molnar <mingo@kernel.org> Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com> Acked-by: Joe Korty <joe.korty@concurrent-rt.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
[ Upstream commit 97181f9bd57405b879403763284537e27d46963d ]

Alexander reported a hrtimer debug_object splat:

  ODEBUG: free active (active state 0) object type: hrtimer hint: hrtimer_wakeup (kernel/time/hrtimer.c:1423)

  debug_object_free (lib/debugobjects.c:603)
  destroy_hrtimer_on_stack (kernel/time/hrtimer.c:427)
  futex_lock_pi (kernel/futex.c:2740)
  do_futex (kernel/futex.c:3399)
  SyS_futex (kernel/futex.c:3447 kernel/futex.c:3415)
  do_syscall_64 (arch/x86/entry/common.c:284)
  entry_SYSCALL64_slow_path (arch/x86/entry/entry_64.S:249)

Which was caused by commit:

  cfafcd117da0 ("futex: Rework futex_lock_pi() to use rt_mutex_*_proxy_lock()")

... losing the hrtimer_cancel() in the shuffle. Where previously the
hrtimer_cancel() was done by rt_mutex_slowlock() we now need to do it
manually.

Reported-by: Alexander Levin <alexander.levin@verizon.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Fixes: cfafcd117da0 ("futex: Rework futex_lock_pi() to use rt_mutex_*_proxy_lock()")
Link: http://lkml.kernel.org/r/alpine.DEB.2.20.1704101802370.2906@nanos
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Acked-by: Joe Korty <joe.korty@concurrent-rt.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
futex: Handle transient "ownerless" rtmutex state correctly 2021-08-10T15:39:42+00:00 Mike Galbraith efault@gmx.de 2021-08-02T13:46:21+00:00 6255b40352498beb0309c99367542302711231e4 [ Upstream commit 9f5d1c336a10c0d24e83e40b4c1b9539f7dba627 ] Gratian managed to trigger the BUG_ON(!newowner) in fixup_pi_state_owner(). This is one possible chain of events leading to this: Task Prio Operation T1 120 lock(F) T2 120 lock(F) -> blocks (top waiter) T3 50 (RT) lock(F) -> boosts T1 and blocks (new top waiter) XX timeout/ -> wakes T2 signal T1 50 unlock(F) -> wakes T3 (rtmutex->owner == NULL, waiter bit is set) T2 120 cleanup -> try_to_take_mutex() fails because T3 is the top waiter and the lower priority T2 cannot steal the lock. -> fixup_pi_state_owner() sees newowner == NULL -> BUG_ON() The comment states that this is invalid and rt_mutex_real_owner() must return a non NULL owner when the trylock failed, but in case of a queued and woken up waiter rt_mutex_real_owner() == NULL is a valid transient state. The higher priority waiter has simply not yet managed to take over the rtmutex. The BUG_ON() is therefore wrong and this is just another retry condition in fixup_pi_state_owner(). Drop the locks, so that T3 can make progress, and then try the fixup again. Gratian provided a great analysis, traces and a reproducer. The analysis is to the point, but it confused the hell out of that tglx dude who had to page in all the futex horrors again. Condensed version is above. [ tglx: Wrote comment and changelog ] Fixes: c1e2f0eaf015 ("futex: Avoid violating the 10th rule of futex") Reported-by: Gratian Crisan <gratian.crisan@ni.com> Signed-off-by: Mike Galbraith <efault@gmx.de> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: stable@vger.kernel.org Link: https://lore.kernel.org/r/87a6w6x7bb.fsf@ni.com Link: https://lore.kernel.org/r/87sg9pkvf7.fsf@nanos.tec.linutronix.de Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com> Acked-by: Joe Korty <joe.korty@concurrent-rt.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
[ Upstream commit 9f5d1c336a10c0d24e83e40b4c1b9539f7dba627 ]

Gratian managed to trigger the BUG_ON(!newowner) in fixup_pi_state_owner().
This is one possible chain of events leading to this:

Task Prio       Operation
T1   120	lock(F)
T2   120	lock(F)   -> blocks (top waiter)
T3   50 (RT)	lock(F)   -> boosts T1 and blocks (new top waiter)
XX   		timeout/  -> wakes T2
		signal
T1   50		unlock(F) -> wakes T3 (rtmutex->owner == NULL, waiter bit is set)
T2   120	cleanup   -> try_to_take_mutex() fails because T3 is the top waiter
     			     and the lower priority T2 cannot steal the lock.
     			  -> fixup_pi_state_owner() sees newowner == NULL -> BUG_ON()

The comment states that this is invalid and rt_mutex_real_owner() must
return a non NULL owner when the trylock failed, but in case of a queued
and woken up waiter rt_mutex_real_owner() == NULL is a valid transient
state. The higher priority waiter has simply not yet managed to take over
the rtmutex.

The BUG_ON() is therefore wrong and this is just another retry condition in
fixup_pi_state_owner().

Drop the locks, so that T3 can make progress, and then try the fixup again.

Gratian provided a great analysis, traces and a reproducer. The analysis is
to the point, but it confused the hell out of that tglx dude who had to
page in all the futex horrors again. Condensed version is above.

[ tglx: Wrote comment and changelog ]

Fixes: c1e2f0eaf015 ("futex: Avoid violating the 10th rule of futex")
Reported-by: Gratian Crisan <gratian.crisan@ni.com>
Signed-off-by: Mike Galbraith <efault@gmx.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/r/87a6w6x7bb.fsf@ni.com
Link: https://lore.kernel.org/r/87sg9pkvf7.fsf@nanos.tec.linutronix.de
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Acked-by: Joe Korty <joe.korty@concurrent-rt.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
rtmutex: Make wait_lock irq safe 2021-08-10T15:39:42+00:00 Thomas Gleixner tglx@linutronix.de 2021-08-02T13:46:20+00:00 6ef8ca1e4f08745b1e56b289bf418474becc937b [ Upstream commit b4abf91047cf054f203dcfac97e1038388826937 ] Sasha reported a lockdep splat about a potential deadlock between RCU boosting rtmutex and the posix timer it_lock. CPU0 CPU1 rtmutex_lock(&rcu->rt_mutex) spin_lock(&rcu->rt_mutex.wait_lock) local_irq_disable() spin_lock(&timer->it_lock) spin_lock(&rcu->mutex.wait_lock) --> Interrupt spin_lock(&timer->it_lock) This is caused by the following code sequence on CPU1 rcu_read_lock() x = lookup(); if (x) spin_lock_irqsave(&x->it_lock); rcu_read_unlock(); return x; We could fix that in the posix timer code by keeping rcu read locked across the spinlocked and irq disabled section, but the above sequence is common and there is no reason not to support it. Taking rt_mutex.wait_lock irq safe prevents the deadlock. Reported-by: Sasha Levin <sasha.levin@oracle.com> Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Cc: Peter Zijlstra <peterz@infradead.org> Cc: Paul McKenney <paulmck@linux.vnet.ibm.com> Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com> Acked-by: Joe Korty <joe.korty@concurrent-rt.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
[ Upstream commit b4abf91047cf054f203dcfac97e1038388826937 ]

Sasha reported a lockdep splat about a potential deadlock between RCU boosting
rtmutex and the posix timer it_lock.

CPU0					CPU1

rtmutex_lock(&rcu->rt_mutex)
  spin_lock(&rcu->rt_mutex.wait_lock)
					local_irq_disable()
					spin_lock(&timer->it_lock)
					spin_lock(&rcu->mutex.wait_lock)
--> Interrupt
    spin_lock(&timer->it_lock)

This is caused by the following code sequence on CPU1

     rcu_read_lock()
     x = lookup();
     if (x)
     	spin_lock_irqsave(&x->it_lock);
     rcu_read_unlock();
     return x;

We could fix that in the posix timer code by keeping rcu read locked across
the spinlocked and irq disabled section, but the above sequence is common and
there is no reason not to support it.

Taking rt_mutex.wait_lock irq safe prevents the deadlock.

Reported-by: Sasha Levin <sasha.levin@oracle.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Paul McKenney <paulmck@linux.vnet.ibm.com>
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Acked-by: Joe Korty <joe.korty@concurrent-rt.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
futex: Futex_unlock_pi() determinism 2021-08-10T15:39:42+00:00 Peter Zijlstra peterz@infradead.org 2021-08-02T13:46:19+00:00 1f705af703b314e969264de54f3bcdfffabf2cf5 [ Upstream commit bebe5b514345f09be2c15e414d076b02ecb9cce8 ] The problem with returning -EAGAIN when the waiter state mismatches is that it becomes very hard to proof a bounded execution time on the operation. And seeing that this is a RT operation, this is somewhat important. While in practise; given the previous patch; it will be very unlikely to ever really take more than one or two rounds, proving so becomes rather hard. However, now that modifying wait_list is done while holding both hb->lock and wait_lock, the scenario can be avoided entirely by acquiring wait_lock while still holding hb-lock. Doing a hand-over, without leaving a hole. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: juri.lelli@arm.com Cc: bigeasy@linutronix.de Cc: xlpang@redhat.com Cc: rostedt@goodmis.org Cc: mathieu.desnoyers@efficios.com Cc: jdesfossez@efficios.com Cc: dvhart@infradead.org Cc: bristot@redhat.com Link: http://lkml.kernel.org/r/20170322104152.112378812@infradead.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com> Acked-by: Joe Korty <joe.korty@concurrent-rt.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
[ Upstream commit bebe5b514345f09be2c15e414d076b02ecb9cce8 ]

The problem with returning -EAGAIN when the waiter state mismatches is that
it becomes very hard to proof a bounded execution time on the
operation. And seeing that this is a RT operation, this is somewhat
important.

While in practise; given the previous patch; it will be very unlikely to
ever really take more than one or two rounds, proving so becomes rather
hard.

However, now that modifying wait_list is done while holding both hb->lock
and wait_lock, the scenario can be avoided entirely by acquiring wait_lock
while still holding hb-lock. Doing a hand-over, without leaving a hole.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: juri.lelli@arm.com
Cc: bigeasy@linutronix.de
Cc: xlpang@redhat.com
Cc: rostedt@goodmis.org
Cc: mathieu.desnoyers@efficios.com
Cc: jdesfossez@efficios.com
Cc: dvhart@infradead.org
Cc: bristot@redhat.com
Link: http://lkml.kernel.org/r/20170322104152.112378812@infradead.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Acked-by: Joe Korty <joe.korty@concurrent-rt.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
futex: Rework futex_lock_pi() to use rt_mutex_*_proxy_lock() 2021-08-10T15:39:42+00:00 Peter Zijlstra peterz@infradead.org 2021-08-02T13:46:18+00:00 b5dac38eb0ff3cbef23afd36d6822291a2a757a5 [ Upstream commit cfafcd117da0216520568c195cb2f6cd1980c4bb ] By changing futex_lock_pi() to use rt_mutex_*_proxy_lock() all wait_list modifications are done under both hb->lock and wait_lock. This closes the obvious interleave pattern between futex_lock_pi() and futex_unlock_pi(), but not entirely so. See below: Before: futex_lock_pi() futex_unlock_pi() unlock hb->lock lock hb->lock unlock hb->lock lock rt_mutex->wait_lock unlock rt_mutex_wait_lock -EAGAIN lock rt_mutex->wait_lock list_add unlock rt_mutex->wait_lock schedule() lock rt_mutex->wait_lock list_del unlock rt_mutex->wait_lock <idem> -EAGAIN lock hb->lock After: futex_lock_pi() futex_unlock_pi() lock hb->lock lock rt_mutex->wait_lock list_add unlock rt_mutex->wait_lock unlock hb->lock schedule() lock hb->lock unlock hb->lock lock hb->lock lock rt_mutex->wait_lock list_del unlock rt_mutex->wait_lock lock rt_mutex->wait_lock unlock rt_mutex_wait_lock -EAGAIN unlock hb->lock It does however solve the earlier starvation/live-lock scenario which got introduced with the -EAGAIN since unlike the before scenario; where the -EAGAIN happens while futex_unlock_pi() doesn't hold any locks; in the after scenario it happens while futex_unlock_pi() actually holds a lock, and then it is serialized on that lock. Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org> Cc: juri.lelli@arm.com Cc: bigeasy@linutronix.de Cc: xlpang@redhat.com Cc: rostedt@goodmis.org Cc: mathieu.desnoyers@efficios.com Cc: jdesfossez@efficios.com Cc: dvhart@infradead.org Cc: bristot@redhat.com Link: http://lkml.kernel.org/r/20170322104152.062785528@infradead.org Signed-off-by: Thomas Gleixner <tglx@linutronix.de> Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com> Acked-by: Joe Korty <joe.korty@concurrent-rt.com> Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> 
[ Upstream commit cfafcd117da0216520568c195cb2f6cd1980c4bb ]

By changing futex_lock_pi() to use rt_mutex_*_proxy_lock() all wait_list
modifications are done under both hb->lock and wait_lock.

This closes the obvious interleave pattern between futex_lock_pi() and
futex_unlock_pi(), but not entirely so. See below:

Before:

futex_lock_pi()			futex_unlock_pi()
  unlock hb->lock

				  lock hb->lock
				  unlock hb->lock

				  lock rt_mutex->wait_lock
				  unlock rt_mutex_wait_lock
				    -EAGAIN

  lock rt_mutex->wait_lock
  list_add
  unlock rt_mutex->wait_lock

  schedule()

  lock rt_mutex->wait_lock
  list_del
  unlock rt_mutex->wait_lock

				  <idem>
				    -EAGAIN

  lock hb->lock

After:

futex_lock_pi()			futex_unlock_pi()

  lock hb->lock
  lock rt_mutex->wait_lock
  list_add
  unlock rt_mutex->wait_lock
  unlock hb->lock

  schedule()
				  lock hb->lock
				  unlock hb->lock
  lock hb->lock
  lock rt_mutex->wait_lock
  list_del
  unlock rt_mutex->wait_lock

				  lock rt_mutex->wait_lock
				  unlock rt_mutex_wait_lock
				    -EAGAIN

  unlock hb->lock

It does however solve the earlier starvation/live-lock scenario which got
introduced with the -EAGAIN since unlike the before scenario; where the
-EAGAIN happens while futex_unlock_pi() doesn't hold any locks; in the
after scenario it happens while futex_unlock_pi() actually holds a lock,
and then it is serialized on that lock.

Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: juri.lelli@arm.com
Cc: bigeasy@linutronix.de
Cc: xlpang@redhat.com
Cc: rostedt@goodmis.org
Cc: mathieu.desnoyers@efficios.com
Cc: jdesfossez@efficios.com
Cc: dvhart@infradead.org
Cc: bristot@redhat.com
Link: http://lkml.kernel.org/r/20170322104152.062785528@infradead.org
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Zhen Lei <thunder.leizhen@huawei.com>
Acked-by: Joe Korty <joe.korty@concurrent-rt.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>