Skip to content

K
kernel_linux

OpenHarmony / kernel_linux
上一次同步 大约 4 年

通知 14
Star 8
Fork 2
K
kernel_linux
切换分支/标签
  1. 30 9月, 2016 7 次提交
    • P
      sched/core: Rewrite and improve select_idle_siblings() · 10e2f1ac
      由 Peter Zijlstra 提交于 
      select_idle_siblings() is a known pain point for a number of
workloads; it either does too much or not enough and sometimes just
does plain wrong.

This rewrite attempts to address a number of issues (but sadly not
all).

The current code does an unconditional sched_domain iteration; with
the intent of finding an idle core (on SMT hardware). The problems
which this patch tries to address are:

 - its pointless to look for idle cores if the machine is real busy;
   at which point you're just wasting cycles.

 - it's behaviour is inconsistent between SMT and !SMT hardware in
   that !SMT hardware ends up doing a scan for any idle CPU in the LLC
   domain, while SMT hardware does a scan for idle cores and if that
   fails, falls back to a scan for idle threads on the 'target' core.

The new code replaces the sched_domain scan with 3 explicit scans:

 1) search for an idle core in the LLC
 2) search for an idle CPU in the LLC
 3) search for an idle thread in the 'target' core

where 1 and 3 are conditional on SMT support and 1 and 2 have runtime
heuristics to skip the step.

Step 1) is conditional on sd_llc_shared->has_idle_cores; when a cpu
goes idle and sd_llc_shared->has_idle_cores is false, we scan all SMT
siblings of the CPU going idle. Similarly, we clear
sd_llc_shared->has_idle_cores when we fail to find an idle core.

Step 2) tracks the average cost of the scan and compares this to the
average idle time guestimate for the CPU doing the wakeup. There is a
significant fudge factor involved to deal with the variability of the
averages. Esp. hackbench was sensitive to this.

Step 3) is unconditional; we assume (also per step 1) that scanning
all SMT siblings in a core is 'cheap'.

With this; SMT systems gain step 2, which cures a few benchmarks --
notably one from Facebook.

One 'feature' of the sched_domain iteration, which we preserve in the
new code, is that it would start scanning from the 'target' CPU,
instead of scanning the cpumask in cpu id order. This avoids multiple
CPUs in the LLC scanning for idle to gang up and find the same CPU
quite as much. The down side is that tasks can end up hopping across
the LLC for no apparent reason.
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      10e2f1ac
    • P
      sched/core: Replace sd_busy/nr_busy_cpus with sched_domain_shared · 0e369d75
      由 Peter Zijlstra 提交于 
      Move the nr_busy_cpus thing from its hacky sd->parent->groups->sgc
location into the much more natural sched_domain_shared location.
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      0e369d75
    • P
      sched/core: Introduce 'struct sched_domain_shared' · 24fc7edb
      由 Peter Zijlstra 提交于 
      Since struct sched_domain is strictly per cpu; introduce a structure
that is shared between all 'identical' sched_domains.

Limit to SD_SHARE_PKG_RESOURCES domains for now, as we'll only use it
for shared cache state; if another use comes up later we can easily
relax this.

While the sched_group's are normally shared between CPUs, these are
not natural to use when we need some shared state on a domain level --
since that would require the domain to have a parent, which is not a
given.
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: linux-kernel@vger.kernel.org
Signed-off-by: NIngo Molnar <mingo@kernel.org>
      24fc7edb
    • O
      sched/wait: Introduce init_wait_entry() · 0176beaf
      由 Oleg Nesterov 提交于 
      The partial initialization of wait_queue_t in prepare_to_wait_event() looks
ugly. This was done to shrink .text, but we can simply add the new helper
which does the full initialization and shrink the compiled code a bit more.

And. This way prepare_to_wait_event() can have more users. In particular we
are ready to remove the signal_pending_state() checks from wait_bit_action_f
helpers and change __wait_on_bit_lock() to use prepare_to_wait_event().
Signed-off-by: NOleg Nesterov <oleg@redhat.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Neil Brown <neilb@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20160906140055.GA6167@redhat.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      0176beaf
    • O
      sched/wait: Avoid abort_exclusive_wait() in __wait_on_bit_lock() · eaf9ef52
      由 Oleg Nesterov 提交于 
      __wait_on_bit_lock() doesn't need abort_exclusive_wait() too. Right
now it can't use prepare_to_wait_event() (see the next change), but
it can do the additional finish_wait() if action() fails.

abort_exclusive_wait() no longer has callers, remove it.
Signed-off-by: NOleg Nesterov <oleg@redhat.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Neil Brown <neilb@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20160906140053.GA6164@redhat.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      eaf9ef52
    • O
      sched/wait: Avoid abort_exclusive_wait() in ___wait_event() · b1ea06a9
      由 Oleg Nesterov 提交于 
      ___wait_event() doesn't really need abort_exclusive_wait(), we can simply
change prepare_to_wait_event() to remove the waiter from q->task_list if
it was interrupted.

This simplifies the code/logic, and this way prepare_to_wait_event() can
have more users, see the next change.
Signed-off-by: NOleg Nesterov <oleg@redhat.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Neil Brown <neilb@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20160908164815.GA18801@redhat.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
--
 include/linux/wait.h |    7 +------
 kernel/sched/wait.c  |   35 +++++++++++++++++++++++++----------
 2 files changed, 26 insertions(+), 16 deletions(-)
      b1ea06a9
    • O
      sched/wait: Fix abort_exclusive_wait(), it should pass TASK_NORMAL to wake_up() · 38a3e1fc
      由 Oleg Nesterov 提交于 
      Otherwise this logic only works if mode is "compatible" with another
exclusive waiter.

If some wq has both TASK_INTERRUPTIBLE and TASK_UNINTERRUPTIBLE waiters,
abort_exclusive_wait() won't wait an uninterruptible waiter.

The main user is __wait_on_bit_lock() and currently it is fine but only
because TASK_KILLABLE includes TASK_UNINTERRUPTIBLE and we do not have
lock_page_interruptible() yet.

Just use TASK_NORMAL and remove the "mode" arg from abort_exclusive_wait().
Yes, this means that (say) wake_up_interruptible() can wake up the non-
interruptible waiter(s), but I think this is fine. And in fact I think
that abort_exclusive_wait() must die, see the next change.
Signed-off-by: NOleg Nesterov <oleg@redhat.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Al Viro <viro@ZenIV.linux.org.uk>
Cc: Bart Van Assche <bvanassche@acm.org>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Neil Brown <neilb@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/20160906140047.GA6157@redhat.comSigned-off-by: NIngo Molnar <mingo@kernel.org>
      38a3e1fc
  3. 29 9月, 2016 1 次提交
  5. 26 9月, 2016 1 次提交
  7. 22 9月, 2016 2 次提交
  9. 21 9月, 2016 2 次提交
    • N
      vti6: fix input path · 63c43787
      由 Nicolas Dichtel 提交于 
      Since commit 1625f452, vti6 is broken, all input packets are dropped
(LINUX_MIB_XFRMINNOSTATES is incremented).

XFRM_TUNNEL_SKB_CB(skb)->tunnel.ip6 is set by vti6_rcv() before calling
xfrm6_rcv()/xfrm6_rcv_spi(), thus we cannot set to NULL that value in
xfrm6_rcv_spi().

A new function xfrm6_rcv_tnl() that enables to pass a value to
xfrm6_rcv_spi() is added, so that xfrm6_rcv() is not touched (this function
is used in several handlers).

CC: Alexey Kodanev <alexey.kodanev@oracle.com>
Fixes: 1625f452 ("net/xfrm_input: fix possible NULL deref of tunnel.ip6->parms.i_key")
Signed-off-by: NNicolas Dichtel <nicolas.dichtel@6wind.com>
Signed-off-by: NSteffen Klassert <steffen.klassert@secunet.com>
      63c43787
    • A
      fix fault_in_multipages_...() on architectures with no-op access_ok() · e23d4159
      由 Al Viro 提交于 
      Switching iov_iter fault-in to multipages variants has exposed an old
bug in underlying fault_in_multipages_...(); they break if the range
passed to them wraps around.  Normally access_ok() done by callers will
prevent such (and it's a guaranteed EFAULT - ERR_PTR() values fall into
such a range and they should not point to any valid objects).

However, on architectures where userland and kernel live in different
MMU contexts (e.g. s390) access_ok() is a no-op and on those a range
with a wraparound can reach fault_in_multipages_...().

Since any wraparound means EFAULT there, the fix is trivial - turn
those

    while (uaddr <= end)
	    ...
into

    if (unlikely(uaddr > end))
	    return -EFAULT;
    do
	    ...
    while (uaddr <= end);
Reported-by: NJan Stancek <jstancek@redhat.com>
Tested-by: NJan Stancek <jstancek@redhat.com>
Cc: stable@vger.kernel.org # v3.5+
Signed-off-by: NAl Viro <viro@zeniv.linux.org.uk>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
      e23d4159
  11. 20 9月, 2016 2 次提交
  13. 18 9月, 2016 1 次提交
  15. 17 9月, 2016 2 次提交
  17. 14 9月, 2016 2 次提交
  19. 13 9月, 2016 2 次提交
  21. 10 9月, 2016 2 次提交
  23. 09 9月, 2016 1 次提交
  25. 08 9月, 2016 1 次提交
  27. 07 9月, 2016 2 次提交
  29. 05 9月, 2016 6 次提交
    • J
      efi/libstub: Introduce ExitBootServices helper · fc07716b
      由 Jeffrey Hugo 提交于 
      The spec allows ExitBootServices to fail with EFI_INVALID_PARAMETER if a
race condition has occurred where the EFI has updated the memory map after
the stub grabbed a reference to the map.  The spec defines a retry
proceedure with specific requirements to handle this scenario.

This scenario was previously observed on x86 - commit d3768d88 ("x86,
efi: retry ExitBootServices() on failure") but the current fix is not spec
compliant and the scenario is now observed on the Qualcomm Technologies
QDF2432 via the FDT stub which does not handle the error and thus causes
boot failures.  The user will notice the boot failure as the kernel is not
executed and the system may drop back to a UEFI shell, but will be
unresponsive to input and the system will require a power cycle to recover.

Add a helper to the stub library that correctly adheres to the spec in the
case of EFI_INVALID_PARAMETER from ExitBootServices and can be universally
used across all stub implementations.
Signed-off-by: NJeffrey Hugo <jhugo@codeaurora.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Leif Lindholm <leif.lindholm@linaro.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: NMatt Fleming <matt@codeblueprint.co.uk>
      fc07716b
    • J
      efi/libstub: Allocate headspace in efi_get_memory_map() · dadb57ab
      由 Jeffrey Hugo 提交于 
      efi_get_memory_map() allocates a buffer to store the memory map that it
retrieves.  This buffer may need to be reused by the client after
ExitBootServices() is called, at which point allocations are not longer
permitted.  To support this usecase, provide the allocated buffer size back
to the client, and allocate some additional headroom to account for any
reasonable growth in the map that is likely to happen between the call to
efi_get_memory_map() and the client reusing the buffer.
Signed-off-by: NJeffrey Hugo <jhugo@codeaurora.org>
Cc: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Leif Lindholm <leif.lindholm@linaro.org>
Cc: Ingo Molnar <mingo@kernel.org>
Cc: <stable@vger.kernel.org>
Signed-off-by: NMatt Fleming <matt@codeblueprint.co.uk>
      dadb57ab
    • J
      efi: Make for_each_efi_memory_desc_in_map() cope with running on Xen · d4c4fed0
      由 Jan Beulich 提交于 
      While commit 55f1ea15 ("efi: Fix for_each_efi_memory_desc_in_map()
for empty memmaps") made an attempt to deal with empty memory maps, it
didn't address the case where the map field never gets set, as is
apparently the case when running under Xen.

Reported-by: <lists@ssl-mail.com>
Tested-by: <lists@ssl-mail.com>
Cc: Vitaly Kuznetsov <vkuznets@redhat.com>
Cc: Jiri Slaby <jslaby@suse.cz>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: <stable@vger.kernel.org> # v4.7+
Signed-off-by: NJan Beulich <jbeulich@suse.com>
[ Guard the loop with a NULL check instead of pointer underflow ]
Signed-off-by: NMatt Fleming <matt@codeblueprint.co.uk>
      d4c4fed0
    • J
      locking/barriers: Don't use sizeof(void) in lockless_dereference() · d7127b5e
      由 Johannes Berg 提交于 
      My previous commit:

  112dc0c8 ("locking/barriers: Suppress sparse warnings in lockless_dereference()")

caused sparse to complain that (in radix-tree.h) we use sizeof(void)
since that rcu_dereference()s a void *.

Really, all we need is to have the expression *p in here somewhere
to make sure p is a pointer type, and sizeof(*p) was the thing that
came to my mind first to make sure that's done without really doing
anything at runtime.

Another thing I had considered was using typeof(*p), but obviously
we can't just declare a typeof(*p) variable either, since that may
end up being void. Declaring a variable as typeof(*p)* gets around
that, and still checks that typeof(*p) is valid, so do that. This
type construction can't be done for _________p1 because that will
actually be used and causes sparse address space warnings, so keep
a separate unused variable for it.
Reported-by: NFengguang Wu <fengguang.wu@intel.com>
Signed-off-by: NJohannes Berg <johannes.berg@intel.com>
Signed-off-by: NPeter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Paul E . McKenney <paulmck@linux.vnet.ibm.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: kbuild-all@01.org
Fixes: 112dc0c8 ("locking/barriers: Suppress sparse warnings in lockless_dereference()")
Link: http://lkml.kernel.org/r/1472192160-4049-1-git-send-email-johannes@sipsolutions.netSigned-off-by: NIngo Molnar <mingo@kernel.org>
      d7127b5e
    • L
      af_unix: split 'u->readlock' into two: 'iolock' and 'bindlock' · 6e1ce3c3
      由 Linus Torvalds 提交于 
      Right now we use the 'readlock' both for protecting some of the af_unix
IO path and for making the bind be single-threaded.

The two are independent, but using the same lock makes for a nasty
deadlock due to ordering with regards to filesystem locking.  The bind
locking would want to nest outside the VSF pathname locking, but the IO
locking wants to nest inside some of those same locks.

We tried to fix this earlier with commit c845acb3 ("af_unix: Fix
splice-bind deadlock") which moved the readlock inside the vfs locks,
but that caused problems with overlayfs that will then call back into
filesystem routines that take the lock in the wrong order anyway.

Splitting the locks means that we can go back to having the bind lock be
the outermost lock, and we don't have any deadlocks with lock ordering.
Acked-by: NRainer Weikusat <rweikusat@cyberadapt.com>
Acked-by: NAl Viro <viro@zeniv.linux.org.uk>
Signed-off-by: NLinus Torvalds <torvalds@linux-foundation.org>
Acked-by: NHannes Frederic Sowa <hannes@stressinduktion.org>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      6e1ce3c3
    • M
      bonding: Fix bonding crash · 24b27fc4
      由 Mahesh Bandewar 提交于 
      Following few steps will crash kernel -

  (a) Create bonding master
      > modprobe bonding miimon=50
  (b) Create macvlan bridge on eth2
      > ip link add link eth2 dev mvl0 address aa:0:0:0:0:01 \
	   type macvlan
  (c) Now try adding eth2 into the bond
      > echo +eth2 > /sys/class/net/bond0/bonding/slaves
      <crash>

Bonding does lots of things before checking if the device enslaved is
busy or not.

In this case when the notifier call-chain sends notifications, the
bond_netdev_event() assumes that the rx_handler /rx_handler_data is
registered while the bond_enslave() hasn't progressed far enough to
register rx_handler for the new slave.

This patch adds a rx_handler check that can be performed right at the
beginning of the enslave code to avoid getting into this situation.
Signed-off-by: NMahesh Bandewar <maheshb@google.com>
Acked-by: NEric Dumazet <edumazet@google.com>
Signed-off-by: NDavid S. Miller <davem@davemloft.net>
      24b27fc4
  31. 03 9月, 2016 1 次提交
    • L
      ACPI / drivers: fix typo in ACPI_DECLARE_PROBE_ENTRY macro · 3feab13c
      由 Lorenzo Pieralisi 提交于 
      When the ACPI_DECLARE_PROBE_ENTRY macro was added in
commit e647b532 ("ACPI: Add early device probing infrastructure"),
a stub macro adding an unused entry was added for the !CONFIG_ACPI
Kconfig option case to make sure kernel code making use of the
macro did not require to be guarded within CONFIG_ACPI in order to
be compiled.

The stub macro was never used since all kernel code that defines
ACPI_DECLARE_PROBE_ENTRY entries is currently guarded within
CONFIG_ACPI; it contains a typo that should be nonetheless fixed.

Fix the typo in the stub (ie !CONFIG_ACPI) ACPI_DECLARE_PROBE_ENTRY()
macro so that it can actually be used if needed.
Signed-off-by: NLorenzo Pieralisi <lorenzo.pieralisi@arm.com>
Fixes: e647b532 (ACPI: Add early device probing infrastructure)
Cc: 4.4+ <stable@vger.kernel.org> # 4.4+
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>
      3feab13c
  33. 02 9月, 2016 3 次提交
  35. 01 9月, 2016 2 次提交
    • M
      ovl: don't cache acl on overlay layer · 2a3a2a3f
      由 Miklos Szeredi 提交于 
      Some operations (setxattr/chmod) can make the cached acl stale.  We either
need to clear overlay's acl cache for the affected inode or prevent acl
caching on the overlay altogether.  Preventing caching has the following
advantages:

 - no double caching, less memory used

 - overlay cache doesn't go stale when fs clears it's own cache

Possible disadvantage is performance loss.  If that becomes a problem
get_acl() can be optimized for overlayfs.

This patch disables caching by pre setting i_*acl to a value that

  - has bit 0 set, so is_uncached_acl() will return true

  - is not equal to ACL_NOT_CACHED, so get_acl() will not overwrite it

The constant -3 was chosen for this purpose.

Fixes: 39a25b2b ("ovl: define ->get_acl() for overlay inodes")
Signed-off-by: NMiklos Szeredi <mszeredi@redhat.com>
      2a3a2a3f
    • M
      mm: introduce get_task_exe_file · cd81a917
      由 Mateusz Guzik 提交于 
      For more convenient access if one has a pointer to the task.

As a minor nit take advantage of the fact that only task lock + rcu are
needed to safely grab ->exe_file. This saves mm refcount dance.

Use the helper in proc_exe_link.
Signed-off-by: NMateusz Guzik <mguzik@redhat.com>
Acked-by: NKonstantin Khlebnikov <khlebnikov@yandex-team.ru>
Acked-by: NRichard Guy Briggs <rgb@redhat.com>
Cc: <stable@vger.kernel.org> # 4.3.x
Signed-off-by: NPaul Moore <paul@paul-moore.com>
      cd81a917